[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Peldom--papers_for_protein_design_using_DL":3,"tool-Peldom--papers_for_protein_design_using_DL":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",150037,2,"2026-04-10T23:33:47",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":79,"owner_website":78,"owner_url":80,"languages":78,"stars":81,"forks":82,"last_commit_at":83,"license":84,"difficulty_score":85,"env_os":86,"env_gpu":87,"env_ram":87,"env_deps":88,"category_tags":91,"github_topics":92,"view_count":10,"oss_zip_url":78,"oss_zip_packed_at":78,"status":17,"created_at":95,"updated_at":96,"faqs":97,"releases":98},2101,"Peldom\u002Fpapers_for_protein_design_using_DL","papers_for_protein_design_using_DL","List of papers about Proteins Design using Deep Learning","papers_for_protein_design_using_DL 是一个专注于“利用深度学习进行蛋白质设计”领域的开源论文清单库。它旨在解决该交叉学科领域文献爆炸式增长、研究者难以快速追踪最新前沿成果的痛点，为社区提供了一个系统化、持续更新的知识导航平台。\n\n该资源特别适合计算生物学研究人员、AI 算法开发者以及从事新药或新材料设计的科学家使用。无论是需要调研抗体、酶、结合肽等特定方向的设计方法，还是寻找基准数据集与评测标准，用户都能在此找到分类清晰的学术指引。其独特亮点在于不仅涵盖了从序列到结构、从功能到骨架等多种设计范式的经典与最新论文，还紧密跟进每周发表的顶刊成果与预印本（如 2026 年最新的 AAV 衣壳设计、组合变异基准平台等），并关联了相关的代码仓库与技术报告。此外，项目倡导负责任的 AI 生物设计理念，部分论文还配有中文知乎专栏的深度笔记，极大地降低了跨学科学习门槛，是进入智能蛋白质设计领域的理想入门工具。","# List of papers about Protein Design using Deep Learning\n\n> This repository is inspired by the remarkable work of [Kevin Kaichuang Yang](https:\u002F\u002Fgithub.com\u002Fyangkky) and their outstanding project [Machine-learning-for-proteins](https:\u002F\u002Fgithub.com\u002Fyangkky\u002FMachine-learning-for-proteins). We have established this repository to provide a specialized and focused platform for the field of **Deep Learning for Protein Design**, a rapidly advancing domain in computational biology.\n>\n> [Contributions](https:\u002F\u002Fgithub.com\u002FPeldom\u002Fpapers_for_protein_design_using_DL\u002Fblob\u002Fmain\u002FCONTRIBUTING.md) and [suggestions](https:\u002F\u002Fgithub.com\u002FPeldom\u002Fpapers_for_protein_design_using_DL\u002Fissues) are warmly welcome!\n> Community Values, Guiding Principles, and Commitments for the Responsible Development of AI for Protein Design: [details](https:\u002F\u002Fresponsiblebiodesign.ai\u002F)\n\n\u003C!-- >\n>1. Mini protein, binders, metalloprotein, antibody, peptide & molecule designs are included  \n>2. More de novo protein design paper list at [Wangchentong](https:\u002F\u002Fgithub.com\u002FWangchentong)'s GitHub repo: [paper_for_denovo_protein_design](https:\u002F\u002Fgithub.com\u002FWangchentong\u002Fpaper_for_denovo_protein_design)  \n>3. Our notes of these papers are shared in a **[Zhihu Column](https:\u002F\u002Fwww.zhihu.com\u002Fcolumn\u002Fc_1475864742820929537)** (simplified Chinese\u002FEnglish), more suggested notes at [RosettAI](https:\u002F\u002Fwww.zhihu.com\u002Fcolumn\u002Frosettastudy)   -->\n\n*Papers last week, updated on 2026.3.28:*\n+   Frontiers and challenges in the design of binders for intrinsically disordered proteins\n    + [[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X26000382)]\n+   Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids\n    + [[arXiv:2603.19473](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.19473)] • [[code](https:\u002F\u002Fgithub.com\u002Fliseda-lab\u002FgenAAV)]\n+   CombinGym: a benchmark platform for machine learning-assisted design of combinatorial protein variants\n    + [[bioRxiv 2026.03.24.714074](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.24.714074v1)] • [[code](https:\u002F\u002Fgithub.com\u002Fsitonglab\u002FCombinGym)] • [[Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F25\u002F2026.03.24.714074\u002FDC1\u002Fembed\u002Fmedia-1.pdf)] • [[website](https:\u002F\u002Fwww.combingym.org)]\n+   Latent-Y: A Lab-Validated Autonomous Agent for De Novo Drug Design\n    + [[technical report](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2026\u002F03\u002FLatent-Y-Technical-Report.pdf)] • [[website](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-y\u002F)] • commercial\n\n\n\n---\n\n\u003Cp align=\"center\">\n  \u003Cbr>\n  \u003C!-- \u003Cimg src=\"dl_pd.png\" alt=\"deep learning for protein design\" width=\"500\"> -->\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FPeldom_papers_for_protein_design_using_DL_readme_4f4d6762ec60.jpg\" alt=\"deep learning for protein design\">\n\u003C\u002Fp>\n\u003C!-- ## Menu -->\n\u003C!-- > Heading [[2]](#2-model-based-design) follows a **\"generator-predictor-optimizer\" paradigm**, Heading [[3]](#3-function-to-scaffold), [[4]](#4scaffold-to-sequence)&[[6]](#6-function-to-structure) follow [\"Inside-out\" paradigm](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fnature19946)(*function-scaffold-sequence*) from [RosettaCommons](https:\u002F\u002Fwww.rosettacommons.org\u002F), Heading [[5]](#5function-to-sequence)&[[7]](#7-other-tasks) follow other ML\u002FDL strategies   -->\n\u003Cp align='center'>\n  \u003Cstrong>\u003Ca href='#0-benchmarks-and-datasets'>0) Benchmarks and datasets \u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#01-sequence-datasets-benchmarks\">Sequence dataset\u002Fbenchmarks\u003C\u002Fa> •\n  \u003Ca href=\"#02-structure-datasets-benchmarks\">Structure datasets\u002Fbenchmarks\u003C\u002Fa> •\n  \u003Ca href=\"#03-databases\">Public database\u003C\u002Fa> •\n  \u003Ca href=\"#04-similar-list\">Similar list\u003C\u002Fa> •\n  \u003Ca href=\"#05-guides\">Guides\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#1-reviews\">1) Reviews and surveys\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#11-de-novo-protein-design\">De novo design\u003C\u002Fa> •\n  \u003Ca href=\"#12-antibody-design\">Antibody design\u003C\u002Fa> •\n  \u003Ca href=\"#13-peptide-design\">Peptide design\u003C\u002Fa> •\n  \u003Ca href=\"#14-binder-design\">Binder design\u003C\u002Fa> •\n  \u003Ca href=\"#15-enzyme-design\">Enzyme design\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#2-model-based-design\">2) Model-based design\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#21-structure-prediction-model-based\">Structure Prediction Model-based\u003C\u002Fa> •\n  \u003Ca href=\"#22-cm-align\">CM-Align\u003C\u002Fa> •\n  \u003Ca href=\"#23-msa-transformer-based\">MSA transformer-based\u003C\u002Fa> •\n  \u003Ca href=\"#24-LLM-based\">LLM-based\u003C\u002Fa> •\n  \u003Ca href=\"#25-sampling-algorithms\">Sampling-algorithms\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#3-function-to-scaffold\" class=\"large-link\">3) Function to Scaffold\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#31-gan-based\">GAN-based\u003C\u002Fa> •\n  \u003Ca href=\"#32-autoencoder-based\">AutoEncoder-based\u003C\u002Fa> •\n  \u003Ca href=\"#33-mlp-based\">MLP-based\u003C\u002Fa> •\n  \u003Ca href=\"#34-diffusion-based\">Diffusion-based\u003C\u002Fa> •\n  \u003Ca href=\"#35-rl-based\">RL-based\u003C\u002Fa> •\n  \u003Ca href=\"#36-flow-based\">Flow-based\u003C\u002Fa> •\n  \u003Ca href=\"#37-score-based\">Score-based\u003C\u002Fa> •\n  \u003Ca href=\"#38-autoregressive\">Autoregressive\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#4scaffold-to-sequence\">4) Scaffold to Sequence\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#40-review\">Review\u003C\u002Fa> •\n  \u003Ca href=\"#41-mlp-based\">MLP-based\u003C\u002Fa> •\n  \u003Ca href=\"#42-vae-based\">VAE-based\u003C\u002Fa> •\n  \u003Ca href=\"#43-lstm-based\">LSTM-based\u003C\u002Fa> •\n  \u003Ca href=\"#44-cnn-based\">CNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#45-gnn-based\">GNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#46-gan-based\">GAN-based\u003C\u002Fa> •\n  \u003Ca href=\"#47-transformer-based\">Transformer-based\u003C\u002Fa> •\n  \u003Ca href=\"#48-resnet-based\">ResNet-based\u003C\u002Fa> •\n  \u003Ca href=\"#49-diffusion-based\">Diffusion-based\u003C\u002Fa> •\n  \u003Ca href=\"#410-bayesian-based\">Bayesian method\u003C\u002Fa> •\n  \u003Ca href=\"#411-flow-based\">Flow-based\u003C\u002Fa> •\n  \u003Ca href=\"#412-rl-based\">RL-based\u003C\u002Fa> •\n  \u003Ca href=\"#413-train-method\">Train method\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#5function-to-sequence\">5) Function to Sequence\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#51-cnn-based\">CNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#52-vae-based\">VAE-based\u003C\u002Fa> •\n  \u003Ca href=\"#53-gan-based\">GAN-based\u003C\u002Fa> •\n  \u003Ca href=\"#54-transformer-based\">Transformer-based\u003C\u002Fa> •\n  \u003Ca href=\"#55-bayesian-based\">Bayesian method\u003C\u002Fa> •\n  \u003Ca href=\"#56-rl-based\">Reinforcement Learning\u003C\u002Fa> •\n  \u003Ca href=\"#57-flow-based\">Flow-based\u003C\u002Fa> •\n  \u003Ca href=\"#58-rnn-based\">RNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#59-lstm-based\">LSTM-based\u003C\u002Fa> •\n  \u003Ca href=\"#510-autoregressive-models\">Autoregressive\u003C\u002Fa> •\n  \u003Ca href=\"#511-boltzmann-machine-based\">Boltzmann machine\u003C\u002Fa> •\n  \u003Ca href=\"#512-diffusion-based\">Diffusion-based\u003C\u002Fa> •\n  \u003Ca href=\"#513-gnn-based\">GNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#514-score-based\">Score-based\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#6-function-to-structure\">6) Function to Structure\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#60-review\">Review\u003C\u002Fa> •\n  \u003Ca href=\"#61-lstm-based\">LSTM-based\u003C\u002Fa> •\n  \u003Ca href=\"#62-diffusion-based\">Diffusion-based\u003C\u002Fa> •\n  \u003Ca href=\"#63-rosettafold-based\">RoseTTAFold-based\u003C\u002Fa> •\n  \u003Ca href=\"#64-cnn-based\">CNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#65-gnn-based\">GNN-based\u003C\u002Fa> •\n  \u003Ca href=\"#66-transformer-based\">Transformer-based\u003C\u002Fa> •\n  \u003Ca href=\"#67-mlp-based\">MLP-based\u003C\u002Fa> •\n  \u003Ca href=\"#68-flow-based\">Flow-based\u003C\u002Fa> •\n  \u003Ca href=\"#69-alphafold-based\">AlphaFold-based\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#7-other-tasks\">7) Other\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#71-effects-of-mutation--fitness-landscape\">Effects of mutations & Fitness Landscape\u003C\u002Fa>  •\n  \u003Ca href=\"#72-protein-language-models-plm-and-representation-learning\">Protein Language Model & Representation Learning\u003C\u002Fa>  •\n  \u003Ca href=\"#73-molecular-design-models\">Molecular Design Model\u003C\u002Fa> •\n  \u003Ca href=\"#74-unclassified\">Unclassified\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## 0. Benchmarks and datasets\n\n### 0.1 Sequence Datasets, Benchmarks\n\n**FLIP: Benchmark tasks in fitness landscape inference for proteins**\nChristian Dallago, Jody Mou, Kadina E Johnston, Bruce Wittmann, Nick Bhattacharya, Samuel Goldman, Ali Madani, Kevin K Yang\n[NeurIPS 2021 Datasets and Benchmarks Track](https:\u002F\u002Fopenreview.net\u002Fforum?id=p2dMLEwL8tF)\u002F[bioRxiv 2021](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.11.09.467890v2) • [website](https:\u002F\u002Fbenchmark.protein.properties\u002F) • [code](https:\u002F\u002Fgithub.com\u002FJ-SNACKKB\u002FFLIP) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F01\u002F19\u002F2021.11.09.467890\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**A Benchmark Framework for Evaluating Structure-to-Sequence Models for Protein Design**\nJeffrey Chan, Seyone Chithrananda, David Brookes, Sam Sinai\nPaper unavailable at [Machine Learning in Structural Biology Workshop 2022](https:\u002F\u002Fnips.cc\u002FConferences\u002F2022\u002FScheduleMultitrack?event=50005)\n\n**PDBench: Evaluating Computational Methods for Protein-Sequence Design**\nLeonardo V Castorina, Rokas Petrenas, Kartic Subr, Christopher W Wood\n[Bioinformatics, 2023;, btad027](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtad027\u002F6986968) • [code](https:\u002F\u002Fgithub.com\u002Fwells-wood-research\u002FPDBench)\n\n**Benchmarking deep generative models for diverse antibody sequence design**\nIgor Melnyk, Payel Das, Vijil Chenthamarakshan, Aurelie Lozano\n[arXiv:2111.06801](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.06801)\n\n**The Protein Engineering Tournament: An Open Science Benchmark for Protein Modeling and Design**\nChase Armer, Hassan Kane, Dana Cortade, Dave Estell, Adil Yusuf, Radhakrishna Sanka, Henning Redestig, TJ Brunette, Pete Kelly, Erika DeBenedictis\n[arXiv:2309.09955](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.09955v2)\n\n**Computational Scoring and Experimental Evaluation of Enzymes Generated by Neural Networks**\nSean R.Johnson, Xiaozhi Fu, Sandra Viknander, Clara Goldin, Sarah Monaco, Aleksej Zelezniak, Kevin K. Yang\n[bioRxiv (2023)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.04.531015v2) • [code](https:\u002F\u002Fgithub.com\u002Fseanrjohnson\u002Fprotein_scoring)\n\n**FLOP: Tasks for Fitness Landscapes Of Protein Wildtypes**\nPeter Mørch Groth, Richard Michael, Jesper Salomon, Pengfei Tian, Wouter Boomsma\n[bioRxiv 2023.06.21.545880](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.21.545880v2) • [code](https:\u002F\u002Fgithub.com\u002Fpetergroth\u002FFLOP)\n\n**ProteinGym: Large-Scale Benchmarks for Protein Design and Fitness Prediction**\nPascal Notin, Aaron W Kollasch, Daniel Ritter, Lood van Niekerk, Steffanie Paul, Hansen Spinner, Nathan Rollins, Ada Shaw, Ruben Weitzman, Jonathan Frazer, Mafalda Dias, Dinko Franceschi, Rose Orenbuch, Yarin Gal, Debora S Marks\n[bioRxiv 2023.12.07.570727](https:\u002F\u002Fbiorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.07.570727v1) • [code](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FProteinGym)\n\n**Results of the Protein Engineering Tournament: An Open Science Benchmark for Protein Modeling and Design**\nChase Armer, Hassan Kane, Dana L. Cortade, Henning Redestig, David A. Estell, Adil Yusuf, Nathan Rollins, Hansen Spinner, Debora Marks, TJ Brunette, Peter J. Kelly, Erika DeBenedictis\n[bioRxiv 2024.08.12.606135](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.12.606135v1)\u002F[Proteins: Structure, Function, and Bioinformatics (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fprot.70008) • [code](https:\u002F\u002Fgithub.com\u002Fthe-protein-engineering-tournament\u002Fpet-pilot-2023) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F12\u002F2024.08.12.606135\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Generative AI Models for the Protein Scaffold Filling Problem**\nLetu Qingge, Kushal Badal, Richard Annan, Jordan Sturtz, Xiaowen Liu, and Binhai Zhu\n[Journal of Computational Biology](https:\u002F\u002Fwww.liebertpub.com\u002Fdoi\u002F10.1089\u002Fcmb.2024.0510)\n\n**Benchmarking Inverse Folding Models for Antibody CDR Sequence Design**\nPer Junior Greisen, Yifan Li, Yuxiang Lang, Chenrui Xu, Yi Zhou, Ziwei Pang\n[bioRxiv 2024.12.16.628614](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.16.628614v1)\n\n**Self-supervised machine learning methods for protein design improve sampling but not the identification of high-fitness variants**\nMoritz Ertelt, Rocco Moretti, Jens Meiler, and Clara T. Schoeder\n[Science Advances 11.7 (2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.adr7338) • [code](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002Fprobabilities_design)\n\n**Crowdsourced Protein Design: Lessons From the Adaptyv EGFR Binder Competition**\nTudor-Stefan Cotet, Igor Krawczuk, Filippo Stocco, Noelia Ferruz, Anthony Gitter, Yoichi Kurumida, Lucas de Almeida Machado, Francesco Paesani, Cianna N. Calia, Chance A. Challacombe, Nikhil Haas, Ahmad Qamar, Bruno E. Correia, Martin Pacesa, Lennart Nickel, Kartic Subr, Leonardo V. Castorina, Maxwell J. Campbell, Constance Ferragu, Patrick Kidger, Logan Hallee, Christopher W. Wood, Michael J. Stam, Tadas Kluonis, Suleyman Mert Unal, Elian Belot, Alexander Naka, Adaptyv Competition Organizers\n[bioRxiv 2025.04.17.648362](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.17.648362v2) • [github](https:\u002F\u002Fgithub.com\u002Fadaptyvbio\u002Fegfr2024_post_competition)\n\n**Experimental Evaluation of AI-Driven Protein Design Risks Using Safe Biological Proxies**  \nSvetlana P. Ikonomova, Bruce J. Wittmann, Fernanda Piorino, David J. Ross, Samuel W. Schaffter, Olga Vasilyeva, Eric Horvitz, James Diggans, Elizabeth A. Strychalski, Sheng Lin-Gibson, Geoffrey J. Taghon  \n[bioRxiv 2025.05.15.654077](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.15.654077v1) • [code](https:\u002F\u002Fgithub.com\u002Fusnistgov\u002FAIPD_TEVV\u002F)\n\n**Benchmark for Antibody Binding Affinity Maturation and Design**  \nXinyan Zhao, Yi-Ching Tang, Akshita Singh, Victor J Cantu, KwanHo An, Junseok Lee, Adam E Stogsdill, Ashwin Kumar Ramesh, Zhiqiang An, Xiaoqian Jiang, Yejin Kim  \n[arXiv:2506.04235](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.04235) • [dataset](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FAbBibench\u002FAntibody_Binding_Benchmark_Dataset) • [code](https:\u002F\u002Fgithub.com\u002FMSBMI-SAFE\u002FAbBiBench)\n\n**The Dayhoff Atlas: scaling sequence diversity for improved protein generation**  \nKevin K. Yang, Sarah Alamdari, Alex J. Lee, Kaeli Kaymak-Loveless, Samir Char, Garyk Brixi, Carles Domingo-Enrich, Chentong Wang, Suyue Lyu, Nicolo Fusi, Neil Tenenholtz, Ava P. Amini  \n[bioRxiv 2025.07.21.665991](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.21.665991v1) • [code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdayhoff) • [dataset](https:\u002F\u002Fhuggingface.co\u002Fcollections\u002Fmicrosoft\u002Fdayhoff-atlas-6866d679465a2685b06ee969)\n\n**Consistent Synthetic Sequences Unlock Structural Diversity in Fully Atomistic De Novo Protein Design**  \nDanny Reidenbach, Zhonglin Cao, Zuobai Zhang, Kieran Didi, Tomas Geffner, Guoqing Zhou, Jian Tang, Christian Dallago, Arash Vahdat, Emine Kucukbenli, Karsten Kreis  \n[arXiv:2512.01976](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01976)\n\n**Benchmarking Generative AI Protein Models Reveals Differences Between Structural and Sequence-based Approaches**  \nAlexander J Barnett , Rajendra KC , Pratikshya Pandey , Pamodha Somasiri , Kirsten A Fairfax , Sandy Hung , Alex W Hewitt  \n[Genomics, Proteomics & Bioinformatics (2026)](https:\u002F\u002Facademic.oup.com\u002Fgpb\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fgpbjnl\u002Fqzag014\u002F8487189)\n\n**AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design**  \nLing Luo, Wenbin Jiang, Hongyuan Chang, Xinkang Wang, Xushi Zhang, Yueting Xiong, Mengsha Tong, Rongshan Yu  \n[arXiv:2602.04916](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04916) • [code](https:\u002F\u002Fgithub.com\u002Fdumbgoos\u002FAfd-Instruction\u002F) • [dataset](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLLMasterLL\u002FAFD) • [website](https:\u002F\u002Fafd-instruction.github.io\u002F)\n\n### 0.2 Structure Datasets, Benchmarks\n\n**AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB**\nZhangyang Gao, Cheng Tan, Stan Z. Li\n[arxiv (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079)\n\n**SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning**\nJonathan E. King, David Ryan Koes\n[arxiv](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08162) • [github::sidechainnet](https:\u002F\u002Fgithub.com\u002Fjonathanking\u002Fsidechainnet)\n\n[TDC](https:\u002F\u002Ftdcommons.ai\u002Foverview\u002F) maintains a resource list that currently contains 22 tasks (and its datasets) related to small molecules and macromolecules, including PPI, DDI and so on. [MoleculeNet](https:\u002F\u002Fgithub.com\u002FGLambard\u002FMolecules_Dataset_Collection) published a small molecule related benchmark four years ago.\n\n> In terms of datasets and benchmarks, protein design is far less mature than drug discovery ([paperwithcode drug discovery benchmarks](https:\u002F\u002Fpaperswithcode.com\u002Ftask\u002Fdrug-discovery)). (Maybe should add the evaluation of protein design for deep learning method (especially deep generative model))\n> Difficulties and opportunities always coexist. Happy to see the work of [Christian Dallago, Jody Mou, Kadina E. Johnston, Bruce J. Wittmann, Nicholas Bhattacharya, Samuel Goldman, Ali Madani, Kevin K. Yang](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.11.09.467890v1) and [Zhangyang Gao, Cheng Tan, Stan Z. Li](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079).\n\n**Sampling of structure and sequence space of small protein folds**\nThomas W. Linsky, Kyle Noble, Autumn R. Tobin, Rachel Crow, Lauren Carter, Jeffrey L. Urbauer, David Baker & Eva-Maria Strauch\n[Nat Commun 13, 7151 (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-34937-8) • [code](https:\u002F\u002Fgithub.com\u002Fstrauchlab\u002Fscaffold_design) • [Supplementary](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41467-022-34937-8\u002FMediaObjects\u002F41467_2022_34937_MOESM1_ESM.pdf)\n\n**OpenProteinSet: Training data for structural biology at scale**\nGustaf Ahdritz, Nazim Bouatta, Sachin Kadyan, Lukas Jarosch, Daniel Berenberg, Ian Fisk, Andrew M. Watkins, Stephen Ra, Richard Bonneau, Mohammed AlQuraishi\n[arXiv:2308.05326](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.05326) • [OpenFold](https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fopenfold)\n\n**ProteinInvBench: Benchmarking Protein Design on Diverse Tasks, Models, and Metrics**\nZhangyang Gao, Cheng Tan, Yijie Zhang, Xingran Chen, Stan Z. Li\n[GitHub](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FProteinInvBench)\n\n**PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Design**\nChuanrui Wang, Bozitao Zhong, Zuobai Zhang, Narendra Chaudhary, Sanchit Misra, Jian Tang\n[arXiv preprint arXiv:2312.00080 (2023)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.00080) • [code](https:\u002F\u002Fgithub.com\u002FWANG-CR\u002FPDB-Struct)\n\n**Scaffold-Lab: Critical Evaluation and Ranking of Protein Backbone Generation Methods in A Unified Framework**\nZhuoqi Zheng, Bo Zhang, Bozitao Zhong, Kexin Liu, Jinyu Yu, Zhengxin Li, JunJie Zhu, Ting Wei, Hai-Feng Chen\n[bioRxiv 2024.02.10.579743](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.10.579743v1) • [code](https:\u002F\u002Fgithub.com\u002FImmortals-33\u002FScaffold-Lab) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F02\u002F12\u002F2024.02.10.579743\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design**\nNataša Tagasovska, Ji Won Park, Matthieu Kirchmeyer, Nathan C. Frey, Andrew Martin Watkins, Aya Abdelsalam Ismail, Arian Rokkum Jamasb, Edith Lee, Tyler Bryson, Stephen Ra, Kyunghyun Cho\n[arXiv:2407.21028](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.21028) • [code](https:\u002F\u002Fgithub.com\u002Fprescient-design\u002Fantibody-domainbed) • [dataset](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffo\u002Fe670i9adp29yv2knfu6wd\u002Fh?rlkey=uax6phjjfumkk8xoxrbwcit1h&e=1&dl=0)\n\n**Large protein databases reveal structural complementarity and functional locality**\nPaweł Szczerbiak, Lukasz Szydlowski, Witold Wydmański, P. Douglas Renfrew, Julia Koehler Leman, Tomasz Kosciolek\n[bioRxiv 2024.08.14.607935](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.14.607935v1) • [code](https:\u002F\u002Fgithub.com\u002FTomasz-Lab\u002Fprotein-structure-landscape) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F14\u002F2024.08.14.607935\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [website](https:\u002F\u002Fprotein-structure-landscape.sano.science\u002F)\n\n**The Protein Design Archive (PDA): insights from 40 years of protein design**\nMarta Chronowska, Michael J. Stam, Derek N. Woolfson, Luigi F. Di Constanzo, Christopher W. Wood\n[bioRxiv 2024.09.05.611465](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.05.611465v1)\u002F[Nat Biotechnol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-025-02607-x) • [code](https:\u002F\u002Fgithub.com\u002Fwells-wood-research\u002Fchronowska-stam-wood-2024-protein-design-archive) • [Supplementary](hhttps:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F09\u002F07\u002F2024.09.05.611465\u002FDC1\u002Fembed\u002Fmedia-1.docx) • [website](https:\u002F\u002Fpragmaticproteindesign.bio.ed.ac.uk\u002Fpda\u002F)\n\n**ProteinBench: A Holistic Evaluation of Protein Foundation Models**\nFei Ye, Zaixiang Zheng, Dongyu Xue, Yuning Shen, Lihao Wang, Yiming Ma, Yan Wang, Xinyou Wang, Xiangxin Zhou, Quanquan Gu\n[arXiv:2409.06744](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.06744) • [code](https:\u002F\u002Fproteinbench.github.io\u002F)\n\n**Benchmarking Generative Models for Antibody Design & Exploring Log-Likelihood for Sequence Ranking**\nTalip Uçar, Cedric Malherbe, Ferran Gonzalez\n[bioRxiv 2024.10.07.617023](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.07.617023v3) • [code](https:\u002F\u002Fgithub.com\u002FAstraZeneca\u002FDiffAbXL)\n\n**Towards Robust Evaluation of Protein Generative Models: A Systematic Analysis of Metrics**\nPavel Strashnov, Andrey Shevtsov, Viacheslav Meshchaninov, Maria Ivanova, Fedor Nikolaev, Olga Kardymon, Dmitry Vetrov\n[bioRxiv 2024.10.25.620213](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.25.620213v1)\n\n**MotifBench: A standardized protein design benchmark for motif-scaffolding problems**\nZhuoqi Zheng, Bo Zhang, Kieran Didi, Kevin K. Yang, Jason Yim, Joseph L. Watson, Hai-Feng Chen, Brian L. Trippe\n[arXiv:2502.12479](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.12479) • [code](https:\u002F\u002Fgithub.com\u002Fblt2114\u002FMotifBench)\n\n**Systematic comparison of Generative AI-Protein Models reveals fundamental differences between structural and sequence-based approaches**\nAlexander J Barnett, KC Rajendra, Pratikshya Pandey, Pamodha Somasiri, Kirsten A Fairfax, Sandy Hung, Alex W Hewitt\n[bioRxiv 2025.03.23.644844](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.23.644844v1) • [code](https:\u002F\u002Fgithub.com\u002Fhewittlab\u002FSystematic-comparison-of-Generative-AI-Protein-Models) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F24\u002F2025.03.23.644844\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**Conformation-specific Design: a New Benchmark and Algorithm with Application to Engineer a Constitutively Active Map Kinase**  \nJacob A. Stern, Siba Alharbi, Anandsukeerthi Sandholu, Stefan T. Arold, Dennis Della Corte  \n[bioRxiv 2025.04.23.650138](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.23.650138v1) • [code](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fcs_design) • [dataset](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fmotif_div)\n\n**PRIDE-New-Benchmark-Dataset-For-Protein-Structural-Design**  \nHanqun CAO, dchenhe  \n[github](https:\u002F\u002Fgithub.com\u002Fchq1155\u002FPRIDE_Benchmark_ProteinDesign)\n\n**Protein FID: Improved Evaluation of Protein Structure Generative Models**  \nFelix Faltings, Hannes Stark, Tommi Jaakkola, Regina Barzilay  \n[arXiv:2505.08041](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.08041)\n\n**PDFBench: A Benchmark for De novo Protein Design from Function**  \nJiahao Kuang, Nuowei Liu, Changzhi Sun, Tao Ji, Yuanbin Wu  \n[arXiv:2505.20346](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.20346) • [website](https:\u002F\u002Fpdfbench.github.io\u002F) • [code](https:\u002F\u002Fgithub.com\u002Fpdfbench\u002FPDFBench)\n\n**An improved model for prediction of de novo designed proteins with diverse geometries**  \nBenjamin Orr, Stephanie E Crilly, Deniz Akpinaroglu, Eleanor Zhu, Michael J. Keiser, Tanja Kortemme  \n[bioRxiv 2025.06.02.657515](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.02.657515v1)\n\n**Protein-SE(3): Benchmarking SE(3)-based Generative Models for Protein Structure Design**  \nLang Yu, Zhangyang Gao, Cheng Tan, Qin Chen, Jie Zhou, Liang He\n[arXiv:2507.20243](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.20243v1)\n\n**Evaluating zero-shot prediction of protein design success by AlphaFold, ESMFold, and ProteinMPNN**  \nMario Garcia, Gabriel Jacob Rocklin, Sugyan Dixit  \n[bioRxiv 2025.07.29.667290](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.29.667290v1)\n\n**Predicting Experimental Success in De Novo Binder Design: A Meta-Analysis of 3,766 Experimentally Characterised Binders**  \nMax Daniel Overath, Andreas Rygaard, Christian Peder Jacobsen, Valentas Brasas, Oliver Morell, Pietro Sormanni, Timothy Patrick Jenkins  \n[bioRxiv 2025.08.14.670059](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.14.670059v1) • [dataset](https:\u002F\u002Fzenodo.org\u002Frecords\u002F15722219)\n\n**Limitations of the refolding pipeline for de novo protein design**  \nKerlen T. Korbeld, Vsevolod Viliuga, Maximilian J.L.J. Fürst  \n[bioRxiv 2025.12.09.693122](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.09.693122v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F12\u002F11\u002F2025.12.09.693122\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [data](https:\u002F\u002Fgithub.com\u002Fkt-korbeld\u002FLimitations-refolding-pipeline-data)\n\n**Assessment of Generative De Novo Peptide Design Methods for G Protein-Coupled Receptors**  \nHannes Junker, Clara T. Schoeder  \n[bioRxiv 2026.02.26.708415](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.26.708415v1)\n\n### 0.3 Databases\n\n> A list of suggested protein databases, more lists at [CNCB](https:\u002F\u002Fngdc.cncb.ac.cn\u002Fdatabasecommons\u002F).\n\n#### 0.3.1 Sequence Database\n\n1. [UniProt](https:\u002F\u002Fwww.uniprot.org\u002Fdownloads)\n2. [DisProt](https:\u002F\u002Fdisprot.org)\n3. [MobiDB](https:\u002F\u002Fmobidb.bio.unipd.it\u002F)\n4. [Peptipedia](https:\u002F\u002Fapp.peptipedia.cl\u002F)\n\n#### 0.3.2 Structure Database\n\n| Database                                                    | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |\n| ----------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| [PDB](https:\u002F\u002Fwww.rcsb.org\u002F)                                   | The Protein Data Bank (PDB) is a database of 3D structural data of large biological molecules, such as proteins and nucleic acids. These data are gathered using experimental methods such as X-ray crystallography, NMR spectroscopy, or cryo-electron microscopy                                                                                                                                                                                                                                                                |\n| [AlphaFoldDB](https:\u002F\u002Falphafold.ebi.ac.uk\u002F)                    | AlphaFoldDB is a database of protein structure predictions produced by DeepMind's AlphaFold system. It provides highly accurate predictions of protein 3D structures                                                                                                                                                                                                                                                                                                                                                              |\n| [PDBbind](http:\u002F\u002Fwww.pdbbind.org.cn\u002Fdownload.php)              | PDBbind is a comprehensive collection of the binding data of all types of biomolecular complexes in the PDB database. It is primarily used for the development and validation of computational methods for predicting molecular interactions                                                                                                                                                                                                                                                                                      |\n| [AB-Bind](https:\u002F\u002Fgithub.com\u002Fsarahsirin\u002FAB-Bind-Database)      | AB-Bind is a database for antibody binding affinity data. It offers a curated set of experimental binding data and corresponding antibody-protein complex structures                                                                                                                                                                                                                                                                                                                                                              |\n| [AntigenDB](http:\u002F\u002Fcrdd.osdd.net\u002Fraghava\u002Fantigendb\u002F)           | AntigenDB is a manually curated database of experimentally verified antigens that includes detailed information about the antigen, the source organism, and the associated antibodies                                                                                                                                                                                                                                                                                                                                             |\n| [CAMEO](https:\u002F\u002Fwww.cameo3d.org\u002F)                              | CAMEO (Continuous Automated Model EvaluatiOn) is a project for the automated evaluation of methods predicting macromolecular structure. It continuously assesses the performance of automated protein structure prediction servers                                                                                                                                                                                                                                                                                                |\n| [CAPRI](https:\u002F\u002Fwww.ebi.ac.uk\u002Fmsd-srv\u002Fcapri\u002F)                  | The Critical Assessment of PRediction of Interactions (CAPRI) is a community-wide experiment to evaluate protein-protein interaction prediction methods                                                                                                                                                                                                                                                                                                                                                                           |\n| [PIFACE](http:\u002F\u002Fprism.ccbb.ku.edu.tr\u002Fpiface)                   | PIFACE is a web server for the prediction of protein-protein interactions. It identifies potential interaction interfaces on protein surfaces                                                                                                                                                                                                                                                                                                                                                                                     |\n| [SAbDab](http:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fnewsabdab\u002Fsabdab\u002F) | The Structural Antibody Database (SAbDab) is an automatically updated resource for the structural information of antibodies from the PDB. It allows for easy access to curated, annotated, and classified antibody structures                                                                                                                                                                                                                                                                                                     |\n| [SKEMPI v2.0](https:\u002F\u002Flife.bsc.es\u002Fpid\u002Fskempi2)                 | SKEMPI 2.0 is a database of experimental measurements of the change in binding free energy caused by mutations in protein-protein complexes                                                                                                                                                                                                                                                                                                                                                                                       |\n| [ProtCAD](http:\u002F\u002Fdunbrack2.fccc.edu\u002Fprotcad\u002F)                  | ProtCAD is a suite of tools for the design and engineering of novel protein structures, sequences, and functions. It allows users to build and manipulate complex protein structures, generate and evaluate sequence libraries, and simulate mutational effects. ProtCAD is a suite of tools for the design and engineering of novel protein structures, sequences, and functions. It allows users to build and manipulate complex protein structures, generate and evaluate sequence libraries, and simulate mutational effects. |\n| [Proteinbase](https:\u002F\u002Fproteinbase.com\u002F)|The home of protein design data. An open platform by [adaptyvbio](http:\u002F\u002Fadaptyvbio.com\u002F) for sharing protein designs, their experimental validation and their design methods.|\n\n### 0.4 Similar List\n\n> Some similar GitHub lists that include papers about protein design using deep learning:\n\n1. [design_tools](https:\u002F\u002Fgithub.com\u002Fhefeda\u002Fdesign_tools\u002Fblob\u002Fmain\u002FREADME.md)\n2. [awesome-AI-based-protein-design](https:\u002F\u002Fgithub.com\u002Fopendilab\u002Fawesome-AI-based-protein-design)\n3. [ProteinStructureWithDL](https:\u002F\u002Fgithub.com\u002FYang-J-LIN\u002FProteinStructureWithDL)\n4. [List of available bioinformatic tools and services](https:\u002F\u002Fneurosnap.ai\u002Fservices)\n\n### 0.5 Guides\n\nGuides\u002FTutorials for beginners on GitHub:\n\n1. [how_to_create_a_protein](https:\u002F\u002Fgithub.com\u002Funiversvm\u002Fhow_to_create_a_protein)\n2. [protein-design-tutorials](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fprotein-design-tutorials)\n3. [AI-driven-protein-design](https:\u002F\u002Fgithub.com\u002Fmiangoar\u002FAI-driven-protein-design\u002Ftree\u002Fmain)\n\nCollection of Protein Design Labs:\n\n- [ProteinDesignLabs](https:\u002F\u002Fgithub.com\u002FZuricho\u002FProteinDesignLabs)\n- [proteindesigngroups](https:\u002F\u002Fullahsamee.github.io\u002Fproteindesigngroups\u002F)\n\n## 1. Reviews\n\n### 1.1 De novo protein design\n\n**Protein design: from computer models to artificial intelligence**\nAntonella Paladino, Filippo Marchetti, Silvia Rinaldi, Giorgio Colombo\n[Wiley Interdisciplinary Reviews: Computational Molecular Science 7.5 (2017): e1318](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fwcms.1318)\n\n**Advances in protein structure prediction and design**\nBrian Kuhlman, Philip Bradley\n[Nat Rev Mol Cell Biol 20, 681-697 (2019)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41580-019-0163-x)\n\n**Deep learning in protein structural modeling and design**\nWenhao Gao, Sai Pooja Mahajan, Jeremias Sulam, and Jeffrey J. Gray\n[Patterns 1.9](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2666389920301902) • 2020\n\n**100th anniversary of macromolecular science viewpoint: Data-driven protein design**\nFerguson, Andrew L., and Rama Ranganathan\n[ACS Macro Letters 10.3 (2021)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facsmacrolett.0c00885)\n\n**Artificial intelligence in early drug discovery enabling precision medicine**\nFabio Bonioloa, Emilio Dorigattia, Alexander J. Ohnmachta, Dieter Saurb, Benjamin Schuberta, and Michael P. Menden\n[Expert Opinion on Drug Discovery 16.9 (2021)](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17460441.2021.1918096)\n\n**Protein design with deep learning**\nDefresne, Marianne, Sophie Barbe, and Thomas Schiex\n[International Journal of Molecular Sciences 22.21 (2021)](https:\u002F\u002Fwww.mdpi.com\u002F1422-0067\u002F22\u002F21\u002F11741)\n\n**Protein sequence design with deep generative models**\nZachary Wu, Kadina E. Johnston, Frances H. Arnold, Kevin K. Yang\n[Current Opinion in Chemical Biology 65](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS136759312100051X) • [note](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F466616309) • 2021\n\n**Structure-based protein design with deep learning**\nOvchinnikov, Sergey, and Po-Ssu Huang\n[Current opinion in chemical biology 65](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1367593121001125) • [note](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F467001175) • 2021\n\n**Deep learning techniques have significantly impacted protein structure prediction and protein design**\nPearce, Robin, and Yang Zhang\n[Current opinion in structural biology 68 (2021)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X21000142)\n\n**Recent advances in de novo protein design: Principles, methods, and applications**\nPan, Xingjie, and Tanja Kortemme\n[Journal of Biological Chemistry 296 (2021)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0021925821003367)\n\n**Protein design via deep learning**\nWenze Ding, Kenta Nakai, Haipeng Gong\n[Briefings in Bioinformatics](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbib\u002Fbbac102\u002F6554124) • 25 March 2022\n\n**Deep generative modeling for protein design**\nStrokach, Alexey, and Philip M. Kim\n[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X21001573) • 2022\n\n**Dawn of a new era for membrane protein design**\nSowlati-Hashjin, Shahin, Aanshi Gandhi, and Michael Garton\n[BioDesign Research (2022)](https:\u002F\u002Fspj.science.org\u002Fdoi\u002F10.34133\u002F2022\u002F9791435)\n\n**Deep learning approaches for conformational flexibility and switching properties in protein design**\nRudden, Lucas SP, Mahdi Hijazi, and Patrick Barth\n[Frontiers in Molecular Biosciences](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffmolb.2022.928534\u002Ffull)\n\n**Computational protein design with evolutionary-based and physics-inspired modeling: current and future synergies**\nCyril Malbranke, David Bikard, Simona Cocco, Rémi Monasson, Jérôme Tubiana\n[arXiv:2208.13616v2](https:\u002F\u002Farxiv.org\u002Fabs\u002F2208.13616v2)\n\n**From sequence to function through structure: deep learning for protein design**\nNoelia Ferruz, Michael Heinzinger, Mehmet Akdel, Alexander Goncearenco, Luca Naef, Christian Dallago\n[bioRxiv 2022.08.31.505981](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.31.505981v1)\u002F[Computational and Structural Biotechnology Journal Volume 21, 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2001037022005086) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F09\u002F03\u002F2022.08.31.505981\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [accompanying list](https:\u002F\u002Fgithub.com\u002Fhefeda\u002Fdesign_tools\u002Fblob\u002Fmain\u002FREADME.md)\n\n**Computational protein design with data-driven approaches: Recent developments and perspectives**\nHaiyan Liu, Quan Chen\n[WIREs Comput Mol Sci. 2022. e1646](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fwcms.1646)\n\n**Understanding by design: Implementing deep learning from protein structure prediction to protein design**\nGao, Yuanxu, Jiangshan Zhan, and Albert CH Yu\n[MedComm-Future Medicine 1.2 (2022): e22](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Ffull\u002F10.1002\u002Fmef2.22)\n\n**Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Action**\nZhiye Guo, Jian Liu, Yanli Wang, Mengrui Chen, Duolin Wang, Dong Xu, Jianlin Cheng\n[arXiv:2302.10907](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.10907)\n\n**Machine learning for evolutionary-based and physicsinspired protein design: Current and future synergies**\nCyril Malbranke, David Bikard, Simona Cocco, Rémi Monasson, Jérôme Tubiana\n[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X23000453)\n\n**De novo design of polyhedral protein assemblies: before and after the AI revolution**\nBhoomika Basu Mallik, Jenna Stanislaw, Tharindu Madhusankha Alawathurage, and Alena Khmelinskaia\n[ChemBioChem 2023, e202300117](http:\u002F\u002Fdx.doi.org\u002F10.1002\u002Fcbic.202300117)\n\n**Research progress of artificial intelligence in protein design**\nCHEN Zhihang, JI Menglin, QI Yifei\n[Synthetic Biology Journal (2023)](https:\u002F\u002Fsynbioj.cip.com.cn\u002Farticle\u002F2023\u002F2096-8280\u002F2023-008.shtml)\n\n**A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Material**\nMengchun Zhang, Maryam Qamar, Taegoo Kang, Yuna Jung, Chenshuang Zhang, Sung-Ho Bae, Chaoning Zhang\n[https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.01565](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2304.01565.pdf)\n\n**Exploring the Protein Sequence Space with Global Generative Models**\nSergio Romero-Romero, Sebastian Lindner, Noelia Ferruz\n[arXiv:2305.01941](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.01941)\n\n**The Era of Machine Learning for Protein Design, Summarized in Four Key Methods**\nLucianoSphere\n[Towards Data Science](https:\u002F\u002Ftowardsdatascience.com\u002Fthe-era-of-machine-learning-for-protein-design-summarized-in-four-key-methods-d6f1dac5de96)\n\n**Is novelty predictable?**\nClara Fannjiang, Jennifer Listgarten\n[arXiv:2306.00872](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.00872)\n\n**Computational protein design - where it goes?**\nXu Binbin, Chen Yingjun and Xue Weiwei\n[Current Medicinal Chemistry 2023](https:\u002F\u002Fwww.eurekaselect.com\u002Farticle\u002F132267)\n\n**How can the protein design community best support biologists who want to harness AI tools for protein structure prediction and design?**\nBirte Höcker, Peilong Lu, Anum Glasgow, Debora S. Marks\nPranam Chatterjee, Joanna S.G. Slusky, Ora Schueler-Furman, Possu Huang\n[Cell Systems 14.8 (2023)](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(23)00212-0)\n\n**De novo 設計ナノポアの創製**\n新津藍\n[生物工学会誌 101.8 (2023)](https:\u002F\u002Fwww.jstage.jst.go.jp\u002Farticle\u002Fseibutsukogaku\u002F101\u002F8\u002F101_101.8_431\u002F_article\u002F-char\u002Fja\u002F)\n\n**Generative artificial intelligence for de novo protein design**\nAdam Winnifrith, Carlos Outeiral, Brian Hie\n[arXiv:2310.09685](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.09685)\n\n**Intelligent Protein Design and Molecular Characterization Techniques: A Comprehensive Review**\nJingjing Wang, Chang Chen, Ge Yao, Junjie Ding, Liangliang Wang and Hui Jiang\n[Molecules 28.23 (2023)](https:\u002F\u002Fwww.mdpi.com\u002F1420-3049\u002F28\u002F23\u002F7865)\n\n**Generative models for protein sequence modeling: recent advances and future directions**\nMehrsa Mardikoraem, Zirui Wang, Nathaniel Pascual, Daniel Woldring\n[Briefings in Bioinformatics](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F24\u002F6\u002Fbbad358\u002F7325909)\n\n**A new age in protein design empowered by deep learning**\nHamed Khakzad, Ilia Igashov, Arne Schneuing, Casper Goverde, Michael Bronstein, Bruno Correia\n[Cell Systems, Volume 14, Issue 11](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(23)00298-3)\n\n**Deep learning for protein structure prediction and design—progress and applications**\nJürgen Jänes and Pedro Beltrao\n[Mol Syst Biol(2024)](https:\u002F\u002Fwww.embopress.org\u002Fdoi\u002Ffull\u002F10.1038\u002Fs44320-024-00016-x)\n\n**De novo protein design—From new structures to programmable functions**\nTanja Kortemme\n[Cell 187.3 (2024)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(23)01402-2)\n\n**Generative models for protein structures and sequences**\nChloe Hsu, Clara Fannjiang & Jennifer Listgarten\n[Nat Biotechnol 42, 196–199 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-02115-w)\n\n**What does it take for an ‘AlphaFold Moment’ in functional protein engineering and design?**\nRoberto A. Chica & Noelia Ferruz\n[Nat Biotechnol 42, 173–174 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-02120-z)\n\n**Protein design: the experts speak**\nAnne Doerr\n[Nat Biotechnol 42, 175–178 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-02111-0)\n\n**Machine learning for functional protein design**\nPascal Notin, Nathan Rollins, Yarin Gal, Chris Sander & Debora Marks\n[Nat Biotechnol 42, 216–228 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02127-0)\n\n**Sparks of function by de novo protein design**\nAlexander E. Chu, Tianyu Lu & Po-Ssu Huang\n[Nat Biotechnol 42, 203–215 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02133-2) • [poster](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1sG3OlEWvhHcWAdtf7RTcCawAapDmyeEx\u002Fview)\n\n**A Survey of Generative AI for De Novo Drug Design: New Frontiers in Molecule and Protein Generation**\nXiangru Tang, Howard Dai, Elizabeth Knight, Fang Wu, Yunyang Li, Tianxiao Li, Mark Gerstein\n[arXiv:2402.08703](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.08703)\n\n**Security challenges by AI-assisted protein design**\nPhilip Hunter\n[EMBO Rep(2024)](https:\u002F\u002Fwww.embopress.org\u002Fdoi\u002Ffull\u002F10.1038\u002Fs44319-024-00124-7)\n\n**Opportunities and challenges in design and optimization of protein function**\nDina Listov, Casper A. Goverde, Bruno E. Correia & Sarel Jacob Fleishman\n[Nat Rev Mol Cell Biol (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41580-024-00718-y)\n\n**The State-of-the-Art Overview to Application of Deep Learning in Accurate Protein Design and Structure Prediction**\nSaber Saharkhiz, Mehrnaz Mostafavi, Amin Birashk, Shiva Karimian, Shayan Khalilollah, Sohrab Jaferian, Yalda Yazdani, Iraj Alipourfard, Yun Suk Huh, Marzieh Ramezani Farani & Reza Akhavan-Sigari\n[Top Curr Chem (Z) 382, 23 (2024)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs41061-024-00469-6)\n\n**Computational methods for protein design**\nNoelia Ferruz, Amelie Stein\n[Protein Engineering, Design and Selection, Volume 37, 2024](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Farticle\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzae011\u002F7710436)\n\n**Structure-based protein and small molecule generation using EGNN and diffusion models: A comprehensive review**\nFarzan Soleymani, Eric Paquet, Herna Lydia Viktor, Wojtek Michalowski\n[Computational and Structural Biotechnology Journal (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2001037024002228)\n\n**Machine learning in biological physics: From biomolecular prediction to design**\nJonathan Martin, Marcos Lequerica Mateos, José N. Onuchic, and Faruck Morcos\n[Proceedings of the National Academy of Sciences 121.27 (2024)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2311807121)\n\n**AI has dreamt up a blizzard of new proteins. Do any of them actually work?**\nEwen Callaway\n[Nature 634.8034 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-03335-z)\n\n**Five protein-design questions that still challenge AI**\nSara Reardon\n[Nature 635.8037 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-03595-9)\n\n**De novo protein design in the age of artificial intelligence**\nNan Liu, Xiaocheng Jin, Chongzhou Yang, Ziyang Wang, Xiaoping Min, Shengxiang Ge\n[Sheng Wu Gong Cheng Xue Bao](https:\u002F\u002Fdoi.org\u002F10.13345\u002Fj.cjb.240087)\n\n**Generative Models in Protein Engineering: A Comprehensive Survey**\nChen Xinhui, Yiwen Yuan, Joseph Liu, Chak Tou Leong, Xiaoye Zhu, Jiaqi Chen\n[Neurips 2024 Workshop](https:\u002F\u002Fopenreview.net\u002Fforum?id=Xc7l84S0Ao)\n\n**A Survey of Deep Learning Methods in Protein Bioinformatics and its Impact on Protein Design**\nWeihang Dai\n[arXiv:2501.01477](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.01477)\n\n**The Promise of Protein Design: A Q&A with Nobel Laureate David Baker**\nDavid Baker and Fay Lin\n[GEN Biotechnology (2025)](https:\u002F\u002Fwww.liebertpub.com\u002Fdoi\u002Fabs\u002F10.1089\u002Fgenbio.2025.0004?journalCode=genbio)\n\n**Protein design and structure solution for drug discovery**\nPetra Bombicz\n[Crystallography Reviews (2024)](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F0889311X.2024.2461923)\n\n**A Model-Centric Review of Deep Learning for Protein Design**\nGregory W. Kyro, Tianyin Qiu, Victor S. Batista\n[arXiv:2502.19173](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19173)\n\n**Computational protein design**\nKatherine I. Albanese, Sophie Barbe, Shunsuke Tagami, Derek N. Woolfson & Thomas Schiex\n[Nature Reviews Methods Primers 5.1 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43586-025-00383-1)\n\n**Exploring the Blueprint of Life: The Innovation in Antibody and Protein Design**\nYang, Zhiwei, and Gerald H. Lushington\n[Combinatorial chemistry & high throughput screening](https:\u002F\u002Fwww.eurekaselect.com\u002Farticle\u002F146786)\n\n**Advanced Deep Learning Methods for Protein Structure Prediction and Design**\nYichao Zhang, Ningyuan Deng, Xinyuan Song, Ziqian Bi, Tianyang Wang, Zheyu Yao, Keyu Chen, Ming Li, Qian Niu, Junyu Liu, Benji Peng, Sen Zhang, Ming Liu, Li Zhang, Xuanhe Pan, Jinlang Wang, Pohsun Feng, Yizhu Wen, Lawrence KQ Yan, Hongming Tseng, Yan Zhong, Yunze Wang, Ziyuan Qin, Bowen Jing, Junjie Yang, Jun Zhou, Chia Xin Liang, Junhao Song\n[arXiv:2503.13522](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.13522)\n\n**Deep Learning-Driven Protein Structure Prediction and Design: Key Model Developments by Nobel Laureates and Multi-Domain Applications**\nWanqing Yang, Yanwei Wang, Yang Wang\n[arXiv:2504.01490](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.01490)\n\n**Intelligent mining, engineering, and de novo design of proteins**\nLIU Cui, SHI Zhenkun, MA Hongwu, LIAO Xiaoping\n[Sheng wu gong cheng xue bao= Chinese journal of biotechnology 41.3 (2025)](https:\u002F\u002Fcjb.ijournals.cn\u002Fhtml\u002Fcjbcn\u002F2025\u002F3\u002F07240629.htm)\n\n**Protein-based Materials: Applications, Modification and Molecular Design**  \nAlitenai Tunuhe, Ze Zheng, Xinran Rao, Hongbo Yu, Fuying Ma, Yaxian Zhou, Shangxian Xie  \n[BioDesign Research (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2693125725000056)\n\n**Artificial intelligence is transforming the study of proteins: Structures and beyond**  \nHaiyan Liu, Quan Chen, and Yufeng Liu  \n[hLife (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2949928325000021)\n\n**Artificial intelligence methods for protein folding and design**  \nZhidian Zhang, Chenxi Ou, Yehlin Cho, Yo Akiyama, Sergey Ovchinnikov  \n[Current Opinion in Structural Biology 93 (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X25000843)\n\n**AI4Protein: transforming the future of protein design**  \nDequan Wang, Zheling Tan, Jin Gao, Shaoting Zhang, Jiaqi Shen & Yuming Lu  \n[Science China Life Sciences (2025)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11427-024-2906-3)\n\n**Comment on the Use of AI-based Protein Design for Autoimmune Encephalitis: Exciting Possibilities and Practical Considerations**  \nZengwei Kou  \n[Multiple Sclerosis and Related Disorders (2025)](https:\u002F\u002Fwww.msard-journal.com\u002Farticle\u002FS2211-0348(25)00335-9\u002Ffulltext)\n\n**Computational Protein Design: Advancing Biotechnology through In Silico Engineering**  \nRanjit Ranbhor, Ruthvik Venkatesan, Amay Sanjay Redkar, Vibin Ramakrishnan  \n[Progress in Biophysics and Molecular Biology (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0079610725000380)\n\n**Advances of computational protein design: Principles, strategies and applications in nutrition and health**  \nZiling Zhao, Qiyang Qu, Fuwei Sun, Jiachen Zang, Bowen Zheng, Tuo Zhang, \nGuanghua Zhao, Chenyan Lv, Zhongjiang Wang  \n[Biotechnology Advances (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0734975025001429)\n\n**Artificial intelligence in de novo protein design**  \nYao, Jiawei, and Xiaogang Wang  \n[Medicine in Novel Technology and Devices (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2590093525000177)\n\n**AI-driven protein design**  \nHuan Yee Koh, Yizhen Zheng, Madeleine Yang, Rohit Arora, Geoffrey I. Webb, Shirui Pan, Li Li & George M. Church  \n[Nat Rev Bioeng (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs44222-025-00349-8)\n\n**DL4Proteins Jupyter Notebooks Teach how to use Artificial Intelligence for Biomolecular Structure Prediction and Design**  \nMichael Chungyoun, Gabe Au, Britnie Carpentier, Sreevarsha Puvada, Courtney Thomas, Jeffrey J. Gray  \n[arXiv:2511.02128](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.02128v1)\n\n**Guiding Generative Models for Protein Design: Prompting, Steering and Aligning**  \nFilippo Stocco, Michele Garibbo, Noelia Ferruz  \n[arXiv:2511.21476](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.21476)\n\n**RFDiffusion: Revolutionizing Protein Design with Generative AI**  \nZhangzhi(Fred) Peng  \n[Serican Journal of Medicine 2.4 (2025)](https:\u002F\u002Fjournals.ku.edu\u002Fsjm\u002Farticle\u002Fview\u002F23410)\n\n**The role of ai-driven de novo protein design in the exploration of the protein functional universe**  \nGuohao Zhang,Chuanyang Liu, Jiajie Lu, Shaowei Zhang and Lingyun Zhu  \n[Biology 14.9 (2025): 1268](https:\u002F\u002Fwww.mdpi.com\u002F2079-7737\u002F14\u002F9\u002F1268)\n\n**Protein design and RNA design: Perspectives**  \nXi Chen, Xu Dai, Peilong Lu  \n[Quantitative Biology 14.2 (2026)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fqub2.70029)\n\n**Transformation of Protein Design: From Traditional Approaches to AI-Driven Precision Engineering**  \nXin Fang  \n[MedScien 1.1 (2025)](https:\u002F\u002Flseee.net\u002Findex.php\u002Fms\u002Farticle\u002Fview\u002F1426)\n\n**Harnessing advances in artificial intelligence for protein design**  \nRussell Johnson  \n[Nature Chemical Biology (2025): 1-4](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-02110-z)\n\n**De novo protein design: a transformative frontier in clinical protein applications**  \nJie Gao, Zaiyong Zheng, Xueting Yu, Yamei Luo, Yang Yu & Chunxiang Zhang  \n[J Transl Med (2026)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1186\u002Fs12967-026-07784-0)\n\n**Designing de novo TIM barrels: insights into stabilization, diversification, and functionalization strategies**  \nJulian Beck, Sergio Romero-Romero  \n[Biochem Soc Trans](https:\u002F\u002Fportlandpress.com\u002Fbiochemsoctrans\u002Farticle\u002F54\u002F2\u002FBST20253060\u002F237195\u002FDesigning-de-novo-TIM-barrels-insights-into)\n\n**AI-enabled protein design facilitates future plant research and crop breeding**  \nYuxuan Lou, Tianhao Wu, Fan Xia, Anwen Zhao, Xiangfeng Wang  \n[Plant Physiology](https:\u002F\u002Facademic.oup.com\u002Fplphys\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fplphys\u002Fkiag147\u002F8528248)\n\n**Frontiers and challenges in the design of binders for intrinsically disordered proteins**  \nChentong Wang, Yanzhe Zhang, Minchao Fang, Zhangzhi Peng, Longxing Cao  \n[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X26000382)\n\n### 1.2 Antibody design\n\n**A review of deep learning methods for antibodies**\nJordan Graves, Jacob Byerly, Eduardo Priego, Naren Makkapati , S. Vince Parish, Brenda Medellin and Monica Berrondo\n[Antibodies 9.2 (2020)](https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fpmc\u002Farticles\u002FPMC7344881\u002Fpdf\u002Fantibodies-09-00012.pdf)\n\n**Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies**\nRahmad Akbar, Habib Bashour, Puneet Rawat, Philippe A. Robert, Eva Smorodina, Tudor-Stefan Cotet, Karine Flem-Karlsen, Robert Frank, Brij Bhushan Mehta, Mai Ha Vu, Talip Zengin, Jose Gutierrez-Marcos, Fridtjof Lund-Johansen,  Jan Terje Andersen, and Victor Greif\n[Mabs. Vol. 14. No. 1. Taylor & Francis, 2022](https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fpmc\u002Farticles\u002FPMC8928824\u002F)\n\n**Advances in computational structure-based antibody design**\nHummer, Alissa M., Brennan Abanades, and Charlotte M. Deane\n[Current Opinion in Structural Biology 74 (2022)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X22000586)\n\n**Computational and artificial intelligence-based methods for antibody development**\nJisun Kim, Matthew McFee, Qiao Fang, Osama Abdin, Philip M. Kim\n[Trends in Pharmacological Sciences (2023)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0165614722002796)\n\n**Leveraging deep learning to improve vaccine design**\nAndrew P. Hederman, Margaret E. Ackerman\n[Trends in immunology (2023)](https:\u002F\u002Fwww.cell.com\u002Ftrends\u002Fimmunology\u002Ffulltext\u002FS1471-4906(23)00046-7)\n\n**In Silico Approaches to Deliver Better Antibodies by Design: The Past, the Present and the Future**\nAndreas Evers, Shipra Malhotra, Vanita D. Sood\n[arXiv:2305.07488](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.07488)\n\n**AI Models for Protein Design are Driving Antibody Engineering**\nMichael Chungyoun, Jeffrey J. Gray\n[Current Opinion in Biomedical Engineering (2023): 100473](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS2468451123000296)\n\n**Computational Methods in Immunology and Vaccinology: Design and Development of Antibodies and Immunogens**\nFederica Guarra and Giorgio Colombo\n[Journal of Chemical Theory and Computation (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jctc.3c00513)\n\n**Simplifying complex antibody engineering using machine learning**\nMakowski, Emily K., Hsin-Ting Chen, and Peter M. Tessier\n[Cell Systems 14.8 (2023)](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(23)00118-7)\u002F[2022 AIChE Annual Meeting. AIChE, 2022.](https:\u002F\u002Faiche.confex.com\u002Faiche\u002F2022\u002Fmeetingapp.cgi\u002FPaper\u002F650993)\n\n**AI driven B-cell Immunotherapy Design**\nBruna Moreira da Silva, David B. Ascher, Nicholas Geard, Douglas E. V. Pires\n[arXiv:2309.01122](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.01122)\n\n**Best practices for machine learning in antibody discovery and development**\nLeonard Wossnig, Norbert Furtmann, Andrew Buchanan, Sandeep Kumar, Victor Greiff\n[arXiv:2312.08470](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.08470)\u002F[Drug Discovery Today (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1359644624001508)\n\n**Next generation of multispecific antibody engineering**\nDaniel Keri, Matt Walker, Isha Singh, Kyle Nishikawa, Fernando Garces\n[Antibody Therapeutics (2023): tbad027](https:\u002F\u002Facademic.oup.com\u002Fabt\u002Farticle\u002F7\u002F1\u002F37\u002F7463325)\n\n**A primer on ML in antibody engineering**\n[ABHISHAIKE MAHAJAN](https:\u002F\u002Fsubstack.com\u002F@abhishaikemahajan)\n[Substack](https:\u002F\u002Fwww.abhishaike.com\u002Fp\u002Fa-primer-on-ai-in-antibody-engineering) • blog\n\n**Antibody design using deep learning: from sequence and structure design to affinity maturation**\nSara Joubbi, Alessio Micheli, Paolo Milazzo, Giuseppe Maccari, Giorgio Ciano, Dario Cardamone, Duccio Medini\n[Briefings in Bioinformatics, Volume 25, Issue 4, July 2024, bbae307](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F4\u002Fbbae307\u002F7705535)\n\n**AI-accelerated therapeutic antibody development: practical insights**\nLuca Santuari, Marianne Bachmann Salvy, Ioannis Xenarios, Bulak Arpat\n[Frontiers in Drug Discovery 4 (2024)](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fdrug-discovery\u002Farticles\u002F10.3389\u002Ffddsv.2024.1447867\u002Ffull)\n\n**AI-driven antibody design with generative diffusion models: current insights and future directions**\nXin-heng He, Jun-rui Li, James Xu, Hong Shan, Shi-yi Shen, Si-han Gao & H. Eric Xu\n[Acta Pharmacologica Sinica (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41401-024-01380-y)\n\n**Applying computational protein design to therapeutic antibody discovery -- current state and perspectives**\nWeronika Bielska, Igor Jaszczyszyn, Pawel Dudzic, Bartosz Janusz, Dawid Chomicz, Sonia Wrobel, Victor Greiff, Ryan Feehan, Jared Adolf-Bryfogle, Konrad Krawczyk\n[arXiv:2503.00913](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.00913)\u002F[Frontiers in Immunology 16 (2025)](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fimmunology\u002Farticles\u002F10.3389\u002Ffimmu.2025.1571371\u002Ffull)\n\n**Artificial intelligence-driven computational methods for antibody design and optimization**  \nLuiz Felipe Vecchietti, Bryan Nathanael Wijaya, Azamat Armanuly,Begench Hangeldiyev, Hyunkyu Jung, Sooyeon Lee, Meeyoung Cha & Ho Min Kim  \n[mAbs, 2025](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F19420862.2025.2528902)\n\n**In Silico Peptide Design: Methods, Resources, and Role of AI**  \nPriyanka Ray Choudhury, Sai Kumar Mishra, Siddharth Yadav, Shubhi Singh, Puniti Mathur  \n[Journal of Peptide Science 31.12 (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpsc.70063)\n\n**Artificial intelligence in antibody design and development: harnessing the power of computational approaches**  \nSoudabeh Kavousipour, Mahdi Barazesh, Shiva Mohammadi  \n[Medical & Biological Engineering & Computing (2025)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11517-025-03429-4)\n\n**Harnessing deep learning to accelerate the development of antibodies and aptamers**\nPan Tan, Song Li, Jin Huang, Ziyi Zhou, Liang Hong  \n[Acta Pharmaceutica Sinica B (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2211383525008251)\n\n### 1.3 Peptide design\n\n**Deep generative models for peptide design**\nWan, Fangping, Daphne Kontogiorgos-Heintz, and Cesar de la Fuente-Nunez\n[Digital Discovery (2022)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlehtml\u002F2022\u002Fdd\u002Fd1dd00024a)\n\n**Design of protein segments and peptides for binding to protein targets**\nGupta, Suchetana, Noora Azadvari, and Parisa Hosseinzadeh\n[BioDesign Research 2022 (2022)](https:\u002F\u002Fspj.science.org\u002Fdoi\u002F10.34133\u002F2022\u002F9783197)\n\n**Revolutionizing peptide-based drug discovery: Advances in the post-AlphaFold era**\nLiwei Chang, Arup Mondal, Bhumika Singh, Yisel Martínez-Noa, Alberto Perez\n[Wiley Interdisciplinary Reviews: Computational Molecular Science](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002Fepdf\u002F10.1002\u002Fwcms.1693)\n\n**Peptide-based drug discovery through artificial intelligence: towards an autonomous design of therapeutic peptides**\nMontserrat Goles, Anamaría Daza, Gabriel Cabas-Mora, Lindybeth Sarmiento-Varón, Julieta Sepúlveda-Yañez, Hoda Anvari-Kazemabad, Mehdi D Davari, Roberto Uribe-Paredes, Álvaro Olivera-Nappa, Marcelo A Navarrete, David Medina-Ortiz\n[Briefings in Bioinformatics 25.4 (2024)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F4\u002Fbbae275\u002F7690345)\n\n**Accelerating antimicrobial peptide design: Leveraging deep learning for rapid discovery**\nAhmad M. Al-Omari ,Yazan H. Akkam,Ala’a Zyout,Shayma’a Younis,Shefa M. Tawalbeh,Khaled Al-Sawalmeh,Amjed Al Fahoum ,Jonathan Arnold\n[PloS one 19.12 (2024): e0315477](https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle?id=10.1371\u002Fjournal.pone.0315477)\n\n**Trends in the Research and Development of Peptide Drug Conjugates: Artificial Intelligence Aided Design**\nDong-E Zhang, Dong-E Zhang, Tong He, Tong He, Tianyi Shi, Tianyi Shi, Kun Huang, Kun Huang, Anlin Peng, Anlin Peng\n[Frontiers in Pharmacology 16](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fpharmacology\u002Farticles\u002F10.3389\u002Ffphar.2025.1553853\u002Ffull)\n\n**Generative models for antimicrobial peptide design: auto-encoders and beyond**  \nLukas Beierle, Julian Hahnfeld, Alexander Goesmann, Reihaneh Mostolizadeh, Franz Cemič  \n[bioRxiv 2025.10.29.685317](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.29.685317v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F10\u002F30\u002F2025.10.29.685317\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fdevshibe\u002Famp-autencoders)\n\n### 1.4 Binder design\n\n**Improving de novo Protein Binder Design with Deep Learning**\nNathaniel Bennett, Brian Coventry, Inna Goreshnik, Buwei Huang, Aza Allen, Dionne Vafeados, Ying Po Peng, Justas Dauparas, Minkyung Baek, Lance Stewart, Frank DiMaio, Steven De Munck, Savvas Savvides, David Baker\n[bioRxiv 2022.06.15.495993](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.15.495993v1)\u002F[Nat Commun 14, 2625 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-38328-5) • [code](https:\u002F\u002Fgithub.com\u002Fnrbennet\u002Fdl_binder_design) • [news](https:\u002F\u002Fphys.org\u002Fnews\u002F2023-08-deep-protein.html)\n\n**Data and AI-driven synthetic binding protein discovery**\nYanlin Li, Zixin Duan, Zhenwen Li, Weiwei Xue\n[Trends in Pharmacological Sciences (2025)](https:\u002F\u002Fwww.cell.com\u002Ftrends\u002Fpharmacological-sciences\u002Fabstract\u002FS0165-6147(24)00268-2)\n\n**Code to complex: AI-driven de novo binder design**  \nDaniel R. Fox, Cyntia Taveneau, Janik Clement, Rhys Grinter, Gavin J. Knott  \n[Structure (2025)](https:\u002F\u002Fwww.cell.com\u002Fstructure\u002Ffulltext\u002FS0969-2126(25)00311-9)\n\n### 1.5 Enzyme design\n\n**A review of enzyme design in catalytic stability by artificial intelligence**\nYongfan Ming, Wenkang Wang, Rui Yin, Min Zeng, Li Tang, Shizhe Tang, Min Li\n[Briefings in Bioinformatics, 2023](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fbib\u002Fbbad065\u002F7086816)\n\n**Application of \"foldability\" in the intelligent of enzymes engineering and design: take AlphaFold2 for example**\nMENG Qiaozhen, GUO Fei\n[Synthetic Biology Journal (2023)](https:\u002F\u002Fsynbioj.cip.com.cn\u002Farticle\u002F2023\u002F2096-8280\u002F2023-011.shtml)\n\n**AlphaFold2 and Deep Learning for Elucidating Enzyme Conformational Flexibility and Its Application for Design**\nCasadevall, Guillem, Cristina Duran, and Sí­lvia Osuna\n[JACS Au (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacsau.3c00188)\n\n**Accelerating Biocatalysis Discovery with Machine Learning: A Paradigm Shift in Enzyme Engineering, Discovery, and Design**\nBraun Markus, Gruber Christian C, Krassnigg Andreas, Kummer Arkadij, Lutz Stefan, Oberdorfer Gustav, Siirola Elina, and Snajdrova Radka\n[ACS Catal. 2023](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facscatal.3c03417)\n\n**Building Enzymes through Design and Evolution**\nHossack, Euan J., Florence J. Hardy, and Anthony P. Green\n[ACS Catalysis 13.19 (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facscatal.3c02746)\n\n**Advances in generative modeling methods and datasets to design novel enzymes for renewable chemicals and fuels**\nRana A Barghout, Zhiqing Xu, Siddharth Betala, Radhakrishnan Mahadevan\n[Current Opinion in Biotechnology, Volume 84, 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0958166923001179)\n\n**Opportunites and Challenges for Machine Learning-Assisted Enzyme Engineering**\nJason Yang, Francesca-Zhoufan Li, Frances H. Arnold\n[ACS Central Science (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facscentsci.3c01275)\n\n**Navigating the landscape of enzyme design: from molecular simulations to machine learning**\nJiahui Zhoua, Meilan Huang\n[Chemical Society Reviews (2024)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002FContent\u002FArticleLanding\u002F2024\u002FCS\u002FD4CS00196F)\n\n**Structure Prediction and Computational Protein Design for Efficient Biocatalysts and Bioactive Proteins**\nRebecca Buller, Jiri Damborsky, Donald Hilvert, Uwe Bornscheuer\n[Angewandte Chemie (International ed. in English)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fanie.202421686)\n\n**Generative AI for Enzyme Design and Biocatalysis**  \nLasse Middendorf, Noelia Ferruz  \n[arXiv:2602.03779](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.03779)\n\n## 2. Model-based design\n\n> Invert trained models with optimize algorithms through iterations for sequence design. Inverted structure prediction models are known as **Hallucination**.\n\n### 2.1 Structure Prediction Model-based\n\n### 2.1.1 trRosetta-based\n\n**Design of proteins presenting discontinuous functional sites using deep learning**\nDoug Tischer, Sidney Lisanza, Jue Wang, Runze Dong,  View ORCID ProfileIvan Anishchenko, Lukas F. Milles, Sergey Ovchinnikov, David Baker\n[bioRxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.11.29.402743v1)\n\n**Fast differentiable DNA and protein sequence optimization for molecular design**\nLinder, Johannes, and Georg Seelig\n[arXiv preprint arXiv:2005.11275 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11275)\n\n**De novo protein design by deep network hallucination**\nIvan Anishchenko, Samuel J. Pellock, Tamuka M. Chidyausiku, Theresa A. Ramelot, Sergey Ovchinnikov, Jingzhou Hao, Khushboo Bafna, Christoffer Norn, Alex Kang, Asim K. Bera, Frank DiMaio, Lauren Carter, Cameron M. Chow, Gaetano T. Montelione & David Baker\n[Nature (2021)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41586-021-04184-w)  • [code](https:\u002F\u002Fgithub.com\u002Fgjoni\u002FtrDesign) • [trRosetta](https:\u002F\u002Fyanglab.nankai.edu.cn\u002FtrRosetta\u002Fdownload\u002F)\n\n**Protein sequence design by conformational landscape optimization**\nChristoffer Norn, Basile I. M. Wicky, David Juergens, and Sergey Ovchinnikov\n[Proceedings of the National Academy of Sciences 118.11 (2021)](https:\u002F\u002Fwww.pnas.org\u002Fcontent\u002F118\u002F11\u002Fe2017228118) • [code](https:\u002F\u002Fgithub.com\u002Fgjoni\u002FtrDesign)\n\n**De novo design of small beta barrel proteins**\nDavid E. Kim, Davin R. Jensen, David Feldman, Doug Tischer  and Ayesha Saleem, Cameron M. Chow, Xinting Li, Lauren Carter, Lukas Milles, Hannah Nguyen, Alex Kang, Asim K. Bera, Francis C. Peterson, Brian F. Volkman, Sergey Ovchinnikov, David Baker\n[PNAS(2023),e2207974120](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2207974120) • [code](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FTrDesign_partialhal)\n\n**Exploring \"dark matter\" protein folds using deep learning**\nZander Harteveld, Alexandra Van Hall-Beauvais, Irina Morozova, Joshua Southern, Casper Alexander Goverde, Sandrine Georgeon, Stephane Rosset, Andreas Loukas, Pierre Vandergheynst, Michael Bronstein, Bruno Correia\n[bioRxiv 2023.08.30.555621](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.30.555621v1)\u002F[Cell Systems](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(24)00270-9) • [Suppplymentary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F09\u002F01\u002F2023.08.30.555621\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fzanderharteveld\u002Fgenesis)\n\n**Carving out a Glycoside Hydrolase Active Site for Incorporation into a New Protein Scaffold Using Deep Network Hallucination**\nAnders Lønstrup Hansen, Frederik Friis Theisen, Ramon Crehuet, Enrique Marcos, Nushin Aghajari, and Martin Willemoës\n[ACS Synth. Biol. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.3c00674)\n\n**Implicit modeling of the conformational landscape and sequence allows scoring and generation of stable proteins**\nYehlin Cho, Justas Dauparas, Kotaro Tsuboyama, Gabriel Rocklin, Sergey Ovchinnikov\n[bioRxiv 2024.12.20.629706](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.20.629706v1)\u002F[Nat Commun (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-66526-w) • [code](https:\u002F\u002Fgithub.com\u002Fyehlincho\u002FJoint_Model_Stability) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F22\u002F2024.12.20.629706\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n#### 2.1.2 AlphaFold-based\n\n**End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman**\nPetti, Samantha, Bhattacharya, Nicholas, Rao, Roshan, Dauparas, Justas, Thomas, Neil, Zhou, Juannan, Rush, Alexander M, Koo, Peter K, Ovchinnikov, Sergey\n[bioRxiv (2021)](http:\u002F\u002Frepository.cshl.edu\u002Fid\u002Feprint\u002F40409\u002F)\u002F[Bioinformatics, 2022;, btac724](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtac724\u002F6820925) • [ColabDesign](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign), [SMURF](https:\u002F\u002Fgithub.com\u002Fspetti\u002FSMURF), [AF2 back propagation](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002Faf_backprop) • [our notes1](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F468219547), [notes2](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F472037977) • [lecture1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=2HmXwlKWMVs), [lecture2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BJdRvODiDnk) • [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FFpYPneYB)\n\n**AlphaDesign: A de novo protein design framework based on AlphaFold**\nJendrusch, Michael, Jan O. Korbel, and S. Kashif Sadiq\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.10.11.463937v1)\u002F[Molecular Systems Biology (2025)](https:\u002F\u002Fwww.embopress.org\u002Fdoi\u002Ffull\u002F10.1038\u002Fs44320-025-00119-z)\n\n**Using AlphaFold for Rapid and Accurate Fixed Backbone Protein Design**\nMoffat, Lewis, Joe G. Greener, and David T. Jones\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.08.24.457549v1)\n\n**State-of-the-art estimation of protein model accuracy using AlphaFold**\nJames P. Roney, Sergey Ovchinnikov\n[bioRxiv 2022.03.11.484043](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.03.11.484043v3)\u002F[Physical Review Letters 129.23 (2022)](https:\u002F\u002Fjournals.aps.org\u002Fprl\u002Fabstract\u002F10.1103\u002FPhysRevLett.129.238101) • [code](https:\u002F\u002Fgithub.com\u002Fjproney\u002FAF2Rank)\n\n**Solubility-aware protein binding peptide design using AlphaFold**\nTakatsugu Kosugi, Masahito Ohue\n[bioRxiv 2022.05.14.491955](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2022.05.14.491955)\u002F[Biomedicines 10.7 (2022)](https:\u002F\u002Fwww.mdpi.com\u002F2227-9059\u002F10\u002F7\u002F1626) • [Supplemental Materials](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F05\u002F15\u002F2022.05.14.491955\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fohuelab\u002FSolubility_AfDesign)\n\n**Hallucinating protein assemblies**\nBasile I M Wicky, Lukas F Milles, Alexis Courbet, Robert J Ragotte, Justas Dauparas, Elias Kinfu, Sam Tipps, Ryan D Kibler, Minkyung Baek, Frank DiMaio, Xinting Li, Lauren Carter, Alex Kang, Hannah Nguyen, Asim K Bera, David Baker\n[bioRxiv 2022.06.09.493773](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.09.493773v1)\u002F[Science (2022)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.add1964) • [related slides](https:\u002F\u002Fdocs.google.com\u002Fpresentation\u002Fd\u002F1_tvzLKks83sYOKemfFeImCPnWtCQ-CHqmKK_3IQI1so\u002F) • [our notes](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F527152827) • [news](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-022-02947-7)\n\n**EvoBind: in silico directed evolution of peptide binders with AlphaFold**\nPatrick Bryant, Arne Elofsson\n[bioRxiv 2022.07.23.501214](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.23.501214v1) • [code](https:\u002F\u002Fgithub.com\u002Fpatrickbryant1\u002FEvoBind)\n\n**Hallucination of closed repeat proteins containing central pockets**\nLinna An, Derrick R Hicks, Dmitri Zorine, Justas Dauparas, Basile I. M. Wicky, Lukas F Milles, Alexis Courbet, Asim K. Bera, Hannah Nguyen, Alex Kang, Lauren Carter, David Baker\n[bioRxiv 2022.09.01.506251](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.01.506251v1)\u002F[Nat Struct Mol Biol 30, 1755-1760 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41594-023-01112-6) • [Supplementary data](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41594-023-01112-6\u002FMediaObjects\u002F41594_2023_1112_MOESM1_ESM.pdf)\n\n**Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search**\nPatrick Bryant, Gabriele Pozzati, Wensi Zhu, Aditi Shenoy, Petras Kundrotas & Arne Elofsson\n[Nature communications 13.1 (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-33729-4) • [gitlba](https:\u002F\u002Fgitlab.com\u002Fpatrickbryant1\u002Fmolpc), [github](https:\u002F\u002Fgithub.com\u002Fpatrickbryant1\u002FMoLPC) • [Supplementary data1](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.6367019), [Supplementary data2](https:\u002F\u002Fdoi.org\u002F10.17044\u002Fscilifelab.19375172)\n\n**De novo protein design by inversion of the AlphaFold structure prediction network**\nCasper Goverde, Benedict Wolf, Hamed Khakzad, Stephane Rosset, Bruno E Correia\n[bioRxiv 2022.12.13.520346](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.13.520346v1) • [code](https:\u002F\u002Fgithub.com\u002Fbene837\u002Faf_gradmcmc) • [lecture1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=aUMGuogMZCA) • [lecture2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4S4J7gbhAa0)\n\n**Code of OpenComplex**\nJingcheng, Yu and Zhaoming, Chen and Zhaoqun, Li and Mingliang, Zeng and Wenjun, Lin and He, Huang and Qiwei, Ye\n[code](https:\u002F\u002Fgithub.com\u002Fbaaihealth\u002FOpenComplex)\n\n**Efficient and scalable de novo protein design using a relaxed sequence space**\nChristopher Josef Frank, Ali Khoshouei, Yosta de Stigter, Dominik Schiewitz, Shihao Feng, Sergey Ovchinnikov, Hendrik Dietz\n[bioRxiv 2023.02.24.529906](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.24.529906v1) • [code](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fmain\u002Faf\u002Fexamples\u002Faf_relax_design.ipynb)\n\n**Cyclic peptide structure prediction and design using AlphaFold**\nStephen A. Rettie, Katelyn V. Campbell, Asim K. Bera, Alex Kang, Simon Kozlov, Joshmyn De La Cruz, Victor Adebomi, Guangfeng Zhou, Frank DiMaio, Sergey Ovchinnikov, Gaurav Bhardwaj\n[bioRxiv](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.25.529956v1)\u002F[Nat Commun 16, 4730 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-59940-7) • [Code](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fmain\u002Faf\u002Fexamples\u002Faf_cyc_design.ipynb) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F02\u002F26\u002F2023.02.25.529956\u002FDC1\u002Fembed\u002Fmedia-1.xlsx)\n\n**De novo design of luciferases using deep learning**\nAndy Hsien-Wei Yeh, Christoffer Norn, Yakov Kipnis, Doug Tischer, Samuel J. Pellock, Declan Evans, Pengchen Ma, Gyu Rie Lee, Jason Z. Zhang, Ivan Anishchenko, Brian Coventry, Longxing Cao, Justas Dauparas, Samer Halabiya, Michelle DeWitt, Lauren Carter, K. N. Houk & David Baker\n[Nature](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-05696-3) • [Code](https:\u002F\u002Ffiles.ipd.uw.edu\u002Fpub\u002FluxSit\u002Fscaffold_generation.tar.gz) • [Supplementary Materials](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41586-023-05696-3\u002FMediaObjects\u002F41586_2023_5696_MOESM1_ESM.pdf)\n\n**In silico evolution of protein binders with deep learning models for structure prediction and sequence design**\nOdessa J Goudy, Amrita Nallathambi, Tomoaki Kinjo, Nicholas Randolph, Brian Kuhlman\n[bioRxiv 2023.05.03.539278](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.03.539278v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F05\u002F03\u002F2023.05.03.539278\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FKuhlmanLab\u002Fevopro)\n\n**Computational design of soluble analogues of integral membrane protein structures**\nCasper Alexander Goverde, Martin Pacesa, Lars Jeremy Dornfeld, Sandrine Georgeon, Stephane Rosset, Justas Dauparas, Christian Shellhaas, Simon Kozlov, David Baker, Sergey Ovchinnikov, Bruno Correia\n[bioRxiv 2023.05.09.540044](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.09.540044v2)\u002F[Nature (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-07601-y) • [code](https:\u002F\u002Fgithub.com\u002Fbene837\u002Faf2seq) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F05\u002F09\u002F2023.05.09.540044\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Antibody Complementarity-Determining Region Sequence Design using AlphaFold2 and Binding Affinity Prediction Model**\nTakafumi Ueki, Masahito Ohue\n[bioRxiv 2023.06.02.543382](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.02.543382v1)\n\n**Context-Dependent Design of Induced-fit Enzymes using Deep Learning Generates Well Expressed, Thermally Stable and Active Enzymes**\nLior Zimmerman, Noga Alon, Itay Levin, Anna Koganitsky, Nufar Shpigel, Chen Brestel, Gideon David Lapidoth\n[bioRxiv 2023.07.27.550799](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.27.550799v2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F07\u002F31\u002F2023.07.27.550799\u002FDC1\u002Fembed\u002Fmedia-1.xlsx)\n\n**Highly accurate and robust protein sequence design with CarbonDesign**\u002F**Accurate and robust protein sequence design with CarbonDesign**\nMilong Ren, Chungong Yu, Dongbo Bu, Haicang Zhang\n[bioRxiv 2023.08.07.552204](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.07.552204v1)\u002F[Nat Mach Intell 6, 536–547 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-024-00838-2) • [code](https:\u002F\u002Fgithub.com\u002Fzhanghaicang\u002Fcarbonmatrix_public)\n\n**Design of Cyclic Peptides Targeting Protein-Protein Interactions using AlphaFold**\nTakatsugu Kosugi, Masahito Ohue\n[bioRxiv 2023.08.20.554056](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.20.554056v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F08\u002F21\u002F2023.08.20.554056\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FYoshitakaMo\u002Flocalcolabfold\u002F)\n\n**MetaPPI: In Silico Screen for Novel CRBN-based Substrates**\nneoxbio\n[website](https:\u002F\u002Fwww.neoxbio.com\u002Fplatform-technology.html) • [news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FKb4EQ0YvYDvoLZ_cnAlUPw) • masif-based • commercial\n\n**AlphaFold Distillation for Protein Design**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=3pgJNIx3gc) • [code](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002FAFDistill-28C3)\n\n**High-throughput computational discovery of inhibitory protein fragments with AlphaFold**\nAndrew Savinov, Sebastian Swanson, Amy E. Keating, Gene-Wei Li\n[bioRxiv 2023.12.19.572389](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.19.572389v1) • [code](https:\u002F\u002Fgithub.com\u002Fswanss\u002FFragFold)\n\n**An integrative approach to protein sequence design through multiobjective optimization**\nLu Hong, Tanja Kortemme\n[bioRxiv 2024.03.01.582670](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.01.582670v1)\u002F[PLOS Computational Biology 20(7)](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1011953) • [code](https:\u002F\u002Fgithub.com\u002Fluhong88\u002Fint_seq_des) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F03\u002F04\u002F2024.03.01.582670\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Protein Design Using Structure-Prediction Networks: AlphaFold and RoseTTAFold as Protein Structure Foundation Models**\nJue Wang, Joseph L. Watson and Sidney L. Lisanza\n[Cold Spring Harbor Perspectives in Biology(2024)](https:\u002F\u002Fcshperspectives.cshlp.org\u002Fcontent\u002Fearly\u002F2024\u002F03\u002F01\u002Fcshperspect.a041472.short)\n\n**Context-dependent design of induced-fit enzymes using deep learning generates well-expressed, thermally stable and active enzymes**\nLior Zimmerman, Noga Alon, Itay Levin, and Gideon D. Lapidoth\n[Proceedings of the National Academy of Sciences 121.11(2024)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2313809121)\n\n**Design of Repeat Alpha-Beta Proteins with Capping Helices**\nDmitri Zorine, David Baker\n[bioRxiv 2024.06.15.590358](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.15.590358v1) • [code](https:\u002F\u002Fgithub.com\u002Fdmitropher\u002Faf2_multistate_hallucination)\n\n**Design of linear and cyclic peptide binders of different lengths only from a protein target sequence**\nQiuzhen Li, Efstathios Nikolaos Vlachos, Patrick Bryant\n[bioRxiv 2024.06.20.599739](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.20.599739v1) • [code](https:\u002F\u002Fzenodo.org\u002Frecords\u002F11543503) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F06\u002F22\u002F2024.06.20.599739\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**BindCraft: one-shot design of functional protein binders**\nMartin Pacesa, Lennart Nickel, Joseph Schmidt, Ekaterina Pyatova, Christian Schellhaas, Lucas Kissling, Ana Alcaraz-Serna, Yehlin Cho, Kourosh H. Ghamary, Laura Vinue, Brahm J. Yachnin, Andrew M. Wollacott, Stephen Buckley, Sandrine Georgeon, Casper A. Goverde, Georgios N. Hatzopoulos, Pierre Gonczy, Yannick D. Muller, Gerald Schwank, Sergey Ovchinnikov, Bruno E. Correia\n[bioRxiv 2024.09.30.615802](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.30.615802v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09429-6) • [code](https:\u002F\u002Fgithub.com\u002Fmartinpacesa\u002FBindCraft)\n\n**Design of linear and cyclic peptide binders of different lengths from protein sequence information**\nQiuzhen Li, Efstathios Nikolaos Vlachos, Patrick Bryant\n[bioRxiv 2024.06.20.599739](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.20.599739v2) • [code](https:\u002F\u002Fzenodo.org\u002Frecords\u002F13913345)\n\n**Scalable protein design using optimization in a relaxed sequence space**\nChristopher Frank, Ali Khoshouei , Lara Fub , Dominik Schiwietz , Dominik Putz, Lara Weber, Zhixuan Zhao, Motoyuki Hattori, Shihao Feng, Yosta de Stigter, Sergey Ovchinnikov, Hendrik Dietz\n[Science386,439-445(2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adq1741) • [code](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign)\n\n**Alphafold2 refinement improves designability of large de novo proteins**\nChristopher Josef Frank, Dominik Schiwietz, Lara Fuss, Sergey Ovchinnikov, Hendrik Dietz\n[bioRxiv 2024.11.21.624687](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.21.624687v1) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F14ULdrjOmH-XMtGDrikzjDF1FLegZg3-a?usp=sharing)\n\n**Low-N OpenFold fine-tuning improves peptide design without additional structures**\nTheodore Sternlieb, Jakub Otwinowski, Sam Sinai, Jeffrey Chan\n[Machine Learning for Structural Biology Workshop, NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FLow-N_OpenFold_fine-tuning_improves_peptide_design_without_additional_structures.pdf)\n\n**HighPlay: Cyclic Peptide Sequence Design Based on Reinforcement Learning and Protein Structure Prediction**\nHuitian Lin, Cheng Zhu, Tianfeng Shang, Ning Zhu, Kang Lin, Xiang Shao, Xudong Wang, Hongliang Duan\n[bioRxiv 2025.03.17.643626](http:\u002F\u002Fbiorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.17.643626v1)\n\n**Designing Novel Solenoid Proteins with In Silico Evolution**\nDaniella Pretorius, Georgi Ivanov Nikov, Kono Washio, Steve-William Florent, Henry Taunt, Sergey Ovchinnikov, James William Murray\n[bioRxiv 2025.04.23.646631](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.23.646631v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F04\u002F24\u002F2025.04.23.646631\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Single-Shot Design of a Cyclic Peptide Inhibitor of HIV-1 Membrane Fusion with EvoBind**  \nDiandra Daumiller, Federica Giammarino, Qiuzhen Li, Anders Sönnerborg, Rafael Ceña Diez, Patrick Bryant  \n[bioRxiv 2025.04.30.651413](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.30.651413v1)\n\n**BindEnergyCraft: Casting Protein Structure Predictors as Energy-Based Models for Binder Design**  \nDivya Nori, Anisha Parsan, Caroline Uhler, Wengong Jin  \n[arXiv:2505.21241](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21241)\n\n**Blind De Novo Design of Dual Cyclic Peptide Agonists Targeting GCGR and GLP1R**  \nQiuzhen Li, Elisee Wiita, Thomas Helleday, Patrick Bryant  \n[bioRxiv 2025.06.06.658268](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.06.658268v1) • [code](https:\u002F\u002Fzenodo.org\u002Frecords\u002F13933365)\n\n**AlphaFold distillation for inverse protein design**  \nIgor Melnyk, Aurélie Lozano, Payel Das & Vijil Chenthamarakshan  \n[Sci Rep 15, 21743 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-025-00436-1) • [code](https:\u002F\u002Fgithub.com\u002FIBM\u002FAFDistill)\n\n**Fold-Conditioned De Novo Binder Design via AlphaFold2-Multimer Hallucination**  \nKhondamir. R. Rustamov, Artyom Y. Baev  \n[bioRxiv 2025.07.02.662497](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.02.662497v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F05\u002F2025.07.02.662497\u002FDC1\u002Fembed\u002Fmedia-1.docx) • [code](https:\u002F\u002Fgithub.com\u002FKhondamirRustamov\u002FFoldCraft)\n\n**Design of linear and cyclic peptide binders from protein sequence  information**  \nQiuzhen Li, Efstathios Nikolaos Vlachos & Patrick Bryant  \n[Commun Chem 8, 211 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42004-025-01601-3)\n\n**Generative Design of High-Affinity Peptides Using BindCraft**  \nMike Filius, Thanasis Patsos, Hugo Minee, Gianluca Turco, Jingming Liu, Monika Gnatzy, Ramon S.M. Rooth, Andy C. H. Liu, Rosa D.T. Ta, Isa H. A. Rijk, Safiya Ziani, Femke J. Boxman, Sebastian J. Pomplun  \n[bioRxiv 2025.07.23.666285](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.23.666285v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F25\u002F2025.07.23.666285\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Computational Design of Soluble CCR8 Analogues with Preserved Antibody Binding**  \nTrang Nguyen, Songming Liu, Yifan Li, Longfei Cong, Roger Shek, Tek Hyang Lee, Li Yi, Per Greisen  \n[bioRxiv 2025.08.18.670068](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.670068v1)\n\n**De novo design of a peptide modulator to reverse sodium channel dysfunction linked to cardiac arrhythmias and epilepsy**  \nRyan Mahling, Bence Hegyi, Erin R. Cullen, Timothy M. Cho, Aaron R. Rodriques, Lucile Fossier, Marc Yehya, Lin Yang, Bi-Xing Chen, Alexander N. Katchman, Nourdine Chakouri, Ruiping Ji, Elaine Y. Wan, Jared Kushner, Steven O. Marx, Sergey Ovchinnikov, Christopher D. Makinson, Donald M. Bers, Manu Ben-Johny  \n[Cell (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(25)00860-8)\n\n**Efficient generation of epitope-targeted de novo antibodies with Germinal**  \nLuis Santiago Mille-Fragoso, John N Wang, Claudia L Driscoll, Haoyu Dai, Talal M Widatalla, Xiaowei Zhang, Brian L Hie, Xiaojing J Gao  \n[bioRxiv 2025.09.19.677421](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.19.677421v2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F25\u002F2025.09.19.677421\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FSantiagoMille\u002Fgerminal)\n\n**mBER: Controllable de novo antibody design with million-scale experimental screening**  \nErik Swanson, Michael Nichols, Supriya Ravichandran, Pierce Ogden  \n[bioRxiv 2025.09.26.678877](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.26.678877v1)\n\n**Automated Deep Learning-Based Pipelines for Multi-Objective De Novo Protein Design**  \nAmrita Nallathambi, Brian Kuhlman  \n[Current protocols 5.10 (2025)](https:\u002F\u002Fcurrentprotocols.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fcpz1.70208)\n\n**Protein Hunter: exploiting structure hallucination within diffusion for protein design**  \nYehlin Cho, Griffin Rangel, Gaurav Bhardwaj, Sergey Ovchinnikov  \n[bioRxiv 2025.10.10.681530](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.10.681530v2) • [code](https:\u002F\u002Fgithub.com\u002Fyehlincho\u002FProtein-Hunter)\n\n**De novo protein design enables targeting of intractable oncogenic interfaces**  \nVarshika Ram Prakash, Yusuf Najy, Kalel Garrett, Brian F.P. Edwards, Benjamin L Kidder  \n[bioRxiv 2025.10.22.683953](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.22.683953v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F10\u002F23\u002F2025.10.22.683953\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**HalluDesign: Protein Optimization and de novo Design via Iterative Structure Hallucination and Sequence design**  \nMinchao Fang, Chentong Wang, Jungang Shi, Fangbai Lian, Qihan Jin, Zhe Wang, Yanzhe Zhang, Zhanyuan Cui, YanJun Wang, Yitao Ke, Qingzheng Han, Longxing Cao  \n[bioRxiv 2025.11.08.686881](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.08.686881v1) • [code](https:\u002F\u002Fgithub.com\u002FMinchaoFang\u002FHalluDesign)\n\n**Sequence and structural determinants of efficacious de novo chimeric antigen receptors**  \nArthur Chow, Hoyin Chu, Ruofan Li, Benan Nalbant, Abdul Dozic, Laura Kida, Caleb Lareau  \n[bioRxiv 2025.12.12.694033](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.12.694033v1) • [code](https:\u002F\u002Fgithub.com\u002Fclareaulab\u002Fdenovo-cart-reproducibility)\n\n**De novo design of protein competitors for small molecule immunosensing**  \nYosta de Stigter, Tallie Godschalk, Maarten Merkx  \n[bioRxiv 2025.12.16.694474](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.16.694474v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F12\u002F16\u002F2025.12.16.694474\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n#### 2.1.3 DMPfold2-based\n\n**Design in the DARK: Learning Deep Generative Models for De Novo Protein Design**\nMoffat, Lewis, Shaun M. Kandathil, and David T. Jones\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.27.478087v1) • [DMPfold2](https:\u002F\u002Fgithub.com\u002Fpsipred\u002FDMPfold2)\n\n#### 2.1.4 DeepAb-based\n\n**Towards deep learning models for target-specific antibody design**\nSai Pooja Mahajan, Jeffrey Ruffolo, Rahel Frick, Jeffrey J. Gray\n[Biophysical Journal 121.3 (2022)](https:\u002F\u002Fwww.cell.com\u002Fbiophysj\u002Fpdf\u002FS0006-3495(21)03758-9.pdf) • [DeepAb](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FDeepAb) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LIo-1jPfrns)\n\n**Hallucinating structure-conditioned antibody libraries for target-specific binders**\nSai Pooja Mahajan, Jeffrey A Ruffolo, Rahel Frick, Jeffrey J. Gray\n[bioRxiv 2022.06.06.494991](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.06.494991v1)\u002F[Front. Immunol. 13:999034](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffimmu.2022.999034\u002Ffull) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F06\u002F06\u002F2022.06.06.494991\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FFvHallucinator)\n\n#### 2.1.5 TRFold2-based\n\n[News of TRDesign](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FOQzKawtL9RdK9HzYsfu80g)\n[TIANRANG XLab](https:\u002F\u002Fxlab.tianrang.com\u002F)\npaper unavailable • [slides](https:\u002F\u002Fpan.baidu.com\u002Fshare\u002Finit?surl=4AOW_D9dwlvC7VGGZA2tmQ&pwd=ffui) • [website](https:\u002F\u002Fxcreator.tianrang.com\u002Fauth\u002Flogin) • commercial • [news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002F45Gz7GWOGxHl0i6LXxTUpw)\n\n#### 2.1.6 Boltz-based\n\n**Boltzdesign1: Inverting All-Atom Structure Prediction Model for Generalized Biomolecular Binder Design**\nYehlin Cho, Martin Pacesa, Zhidian Zhang, Bruno E. Correia, Sergey Ovchinnikov\n[bioRxiv 2025.04.06.647261](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.06.647261v1) • [code](https:\u002F\u002Fgithub.com\u002Fyehlincho\u002FBoltzDesign1)\n\n#### 2.1.7 RareFold-based\n\n**RareFold: Structure prediction and design of proteins with noncanonical amino acids**  \nQiuzhen Li, Diandra Daumiller, Patrick Bryant  \n[bioRxiv 2025.05.19.654846](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.19.654846v1) • [code](https:\u002F\u002Fgithub.com\u002Fpatrickbryant1\u002FRareFold)\n\n#### 2.1.8 HelixFold-based\n\n**HelixDesign-Binder: A Scalable Production-Grade Platform for Binder Design Built on HelixFold3**  \nJie Gao, Jun Li, Jing Hu, Shanzhuo Zhang, Kunrui Zhu, Yueyang Huang, Xiaonan Zhang, Xiaomin Fang  \n[arXiv:2505.21873](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21873) • ESM-IF-based\n\n**HelixDesign-Antibody: A Scalable Production-Grade Platform for Antibody Design Built on HelixFold3**  \nJie Gao, Jing Hu, Shanzhuo Zhang, Kunrui Zhu, Sheng Qian, Yueyang Huang, Xiaonan Zhang, Xiaomin Fang  \n[arXiv:2507.02345](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.02345) • [website](https:\u002F\u002Fpaddlehelix.baidu.com\u002F)\n\n#### 2.1.9 ESMfold-based\n\n**Design of proteins by parallel tempering in the sequence space**  \nPreet Kalani, Vojtěch Spiwok  \n[Protein Science 34.10 (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70246)\n\n#### 2.1.10 tFold-based\n\n**De novo design of epitope-specific antibodies via a structure-driven computational workflow**  \nFandi Wu, Yu Zhao, JiaXiang Wu, Biaobin Jiang, Bing He, Longkai Huang, Chenchen Qin, Yang Xiao, Fan Yang, Rubo Wang, Ningqiao Huang, Huaxian Jia, Yuyi Liu, Houtim Lai, Tingyang Xu, Fang Wang, Zihan Wu, Yidong Song, Shaoning Li, Wei Liu, Yu Rong, Peilin Zhao & Jianhua Yao  \n[Nat Commun (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-67361-9) • [code](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002Ftfold)\n\n#### 2.1.11 Chai-based\n\n**De novo protein ligand design including protein flexibility and conformational adaptation**  \nJakob Agamia, Martin Zacharias  \n[bioRxiv 2026.01.08.698398](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.08.698398v1) • [code](https:\u002Fgithub.com\u002FJakobAgamia\u002FAI-MCLig) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F08\u002F2026.01.08.698398\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n### 2.2 CM-Align\n\n**AutoFoldFinder: An Automated Adaptive Optimization Toolkit for De Novo Protein Fold Design**\nShuhao Zhang, Youjun Xu, Jianfeng Pei, Luhua Lai\n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_AutoFoldFinder.pdf)\n\n### 2.3 MSA-transformer-based\n\n**Protein language models trained on multiple sequence alignments learn phylogenetic relationships**\nDamiano Sgarbossa, Umberto Lupo, Anne-Florence Bitbol\n[arXiv preprint arXiv:2203.15465 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.15465)\u002F[bioRxiv 2022.04.14.488405](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.14.488405v1)\n\n**EvoOpt: an MSA-guided, fully unsupervised sequence optimization pipeline for protein design**\nHideki Yamaguchi, Yutaka Saito\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FEvoOpt_an_MSA_guided_fully_unsupervised_sequence_optimization_pipeline_for_protein_design.pdf)\n\n**Generative power of a protein language model trained on multiple sequence alignments**\nSgarbossa, Damiano, Umberto Lupo, and Anne-Florence Bitbol\n[Elife 12 (2023): e79854](https:\u002F\u002Felifesciences.org\u002Farticles\u002F79854) • [code](https:\u002F\u002Fgithub.com\u002FBitbol-Lab\u002FIterative_masking)\n\n### 2.4 LLM-based\n\n#### 2.4.1 GPT-based\n\n**Multi-segment preserving sampling for deep manifold sampler**\nDaniel Berenberg, Jae Hyeon Lee, Simon Kelow, Ji Won Park, Andrew Watkins, Vladimir Gligorijević, Richard Bonneau, Stephen Ra, Kyunghyun Cho\n[arXiv preprint arXiv:2205.04259 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.04259)\n\n**Preference optimization of protein language models as a multi-objective binder design paradigm**\nPouria Mistani, Venkatesh Mysore\n[arXiv:2403.04187](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.04187)\n\n**HMAMP: Hypervolume-Driven Multi-Objective Antimicrobial Peptides Design**\nLi Wang, Yiping Li, Xiangzheng Fu, Xiucai Ye, Junfeng Shi, Gary G. Yen, Xiangxiang Zeng\n[arXiv:2405.00753](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.00753)\n\n#### 2.4.2 ESM-based\n\n**Generating novel protein sequences using Gibbs sampling of masked language models**\nSean R. Johnson, Sarah Monaco, Kenneth Massie, Zaid Syed\n[bioRxiv 2021.01.26.428322](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.01.26.428322v1) • [code](https:\u002F\u002Fgithub.com\u002Fseanrjohnson\u002Fprotein_gibbs_sampler)\n\n**A high-level programming language for generative protein design**\nBrian Hie, Salvatore Candido, Zeming Lin, Ori Kabeli, Roshan Rao, Nikita Smetanin, Tom Sercu, Alexander Rives\n[bioRxiv 2022.12.21.521526](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.21.521526v1)\n\n**Language models generalize beyond natural proteins**\nRobert Verkuil, Ori Kabeli, Yilun Du, Basile IM Wicky, Lukas F Milles, Justas Dauparas, David Baker, Sergey Ovchinnikov, Tom Sercu, Alexander Rives\n[bioRxiv 2022.12.21.521521](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.21.521521v1)\n\n**ESMFold Hallucinates Native-Like Protein Sequences**\nJeliazko R Jeliazkov, Diego del Alamo, Joel D Karpiak\n[bioRxiv 2023.05.23.541774](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.23.541774v1)\n\n**Protein Language Model Supervised Precise and Efficient Protein Backbone Design Method**\nBo Zhang, Kexin Liu, Zhuoqi Zheng, Yunfeiyang Liu, Junxi Mu, Ting Wei, Hai-Feng Chen\n[bioRxiv 2023.10.26.564121](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.26.564121v1)\u002F[preprint](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-5450034\u002Fv1) • [code](https:\u002F\u002Fgithub.com\u002Fsirius777coder\u002FGPDL) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F10\u002F30\u002F2023.10.26.564121\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Unexplored regions of the protein sequence-structure map revealed at scale by a library of foldtuned language models**\nArjuna M. Subramanian, Matt Thomson\n[bioRxiv 2023.12.22.573145](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.22.573145v1)\n\n**Computational scoring and experimental evaluation of enzymes generated by neural networks**\nSean R. Johnson, Xiaozhi Fu, Sandra Viknander, Clara Goldin, Sarah Monaco, Aleksej Zelezniak & Kevin K. Yang\n[Nature Biotechnology (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02214-2) • [code](https:\u002F\u002Fgithub.com\u002Fseanrjohnson\u002Fprotein_scoring)\n\n**Exploring Latent Space for Generating Peptide Analogs Using Protein Language Models**\nPo-Yu Liang, Xueting Huang, Tibo Duran, Andrew J. Wiemer, Jun Bai\n[arXiv:2408.08341](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.08341) • [code](https:\u002F\u002Fgithub.com\u002FLabJunBMI\u002FLatent-Space-Peptide-Analogues-Generation)\n\n**Designing diverse and high-performance proteins with a large language model in the loop**\nCarlos A. Gomez-Uribe, Japheth Gado, Meiirbek Islamov\n[bioRxiv 2024.10.25.620340](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.25.620340v1)\n\n**Key-cutting machine: A novel optimization framework for tailored protein and peptide design**\nYan C. Leyva, Marcelo D. T. Torres, Carlos A. Oliva, Cesar de la Fuente-Nunez, Carlos A. Brizuela\n[bioRxiv 2025.01.05.631393](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.05.631393v1) • [code](https:\u002F\u002Fgithub.com\u002Fcbrizuel\u002FKCM)\n\n**Improving functional protein generation via foundation model-derived latent space likelihood optimization**\nChangge Guan, Fangping Wan, Marcelo D. T. Torres, Cesar de la Fuente-Nunez\n[bioRxiv 2025.01.07.631724](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.07.631724v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F01\u002F08\u002F2025.01.07.631724\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**DPAC: Prediction and Design of Protein-DNA Interactions via Sequence-Based Contrastive Learning**  \nLeo Tianlai Chen, Rishab Pulugurta, Pranay Vure, Pranam Chatterjee  \n[bioRxiv 2025.05.14.654102](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.14.654102v1) • [code](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fdpac)\n\n**BAGEL: Protein Engineering via Exploration of an Energy Landscape**  \nJakub Lála, Ayham Al-Saffar, Stefano Angiolleti-Uberti  \n[bioRxiv 2025.07.05.663138](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.05.663138v1) • [code](https:\u002F\u002Fgithub.com\u002Fsoftnanolab\u002Fbagel)\n\n**GeoEvoBuilder: A deep learning framework for efficient functional and thermostable protein design**  \nJiale Liu, Zheng Guo and Luhua Lai  \n[Proceedings of the National Academy of Sciences 122.41 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2504117122) • [code](https:\u002F\u002Fgithub.com\u002FPKUliujl\u002FGeoEvoBuilder)\n\n**Harnessing protein-folding algorithms to drug intrinsically disordered epitopes**  \nJakub Lála, Stefano Angioletti-Uberti  \n[bioRxiv 2025.11.11.687846](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.11.687846v1)\n\n#### 2.4.3 Antiberta-based\n\n**DyAb: sequence-based antibody design and property prediction in a low-data regime**\nJoshua Yao-Yu Lin, Jennifer L. Hofmann, Andrew Leaver-Fay, Wei-Ching Liang, Stefania Vasilaki, Edith Lee, Pedro O. Pinheiro, Natasa Tagasovska, James R. Kiefer, Yan Wu, Franziska Seeger, Richard Bonneau, Vladimir Gligorijevic, Andrew Watkins, Kyunghyun Cho, Nathan C. Frey\n[bioRxiv 2025.01.28.635353](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.28.635353v1) • [code](github.com\u002Fprescient-design\u002Flobster) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F02\u002F02\u002F2025.01.28.635353\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**An Energy Landscape Approach to Miniaturizing Enzymes using Protein Language Model Embeddings**  \nJakub Lála, Harsh Agrawal, Fanfei Dong, Jude Wells, Stefano Angioletti-Uberti  \n[bioRxiv 2026.03.04.709378](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.04.709378v1)\n\n### 2.5 Sampling-algorithms\n\n**AdaLead: A simple and robust adaptive greedy search algorithm for sequence design**\nSam Sinai, Richard Wang, Alexander Whatley, Stewart Slocum, Elina Locane, Eric D. Kelsic\n[arXiv preprint arXiv:2010.02141 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.02141) • [code](https:\u002F\u002Fgithub.com\u002Fsamsinai\u002FFLEXS)\n\n**Autofocused oracles for model-based design**\nFannjiang, Clara, and Jennifer Listgarten\n[Advances in Neural Information Processing Systems 33 (2020)](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Ffile\u002F972cda1e62b72640cb7ac702714a115f-Paper.pdf)\n\n**An Efficient MCMC Approach to Energy Function Optimization in Protein Structure Prediction**\nLakshmi A. Ghantasala, Risi Jaiswal, Supriyo Datta\n[arXiv:2211.03193](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.03193)\n\n**Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC**\nPatrick Emami, Aidan Perreault, Jeffrey Law, David Biagioni, Peter St. Joh\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FPlug_Play_Directed_Evolution_of_Proteins_with_Gradient_based_Discrete_MCMC.pdf)\u002F[arXiv:2212.09925](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.09925)\n\n**Importance Weighted Expectation-Maximization for Protein Sequence Design**\nZhenqiao Song, Lei Li\n[arXiv:2305.00386](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.00386) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F05\u002F09\u002F2023.05.09.539914\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Simultaneous enhancement of multiple functional properties using evolution-informed protein design**\nBenjamin Fram, Ian Truebridge, Yang Su, Adam J. Riesselman, John B. Ingraham, Alessandro Passera, Eve Napier, Nicole N. Thadani, Samuel Lim, Kristen Roberts, Gurleen Kaur, Michael Stiffler, Debora S. Marks, Christopher D. Bahl, Amir R. Khan, Chris Sander, Nicholas P. Gauthier\n[bioRxiv (2023): 2023-05](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.09.539914v1)\n\n**Optimizing protein fitness using Gibbs sampling with Graph-based Smoothing**\nAndrew Kirjner, Jason Yim, Raman Samusevich, Tommi Jaakkola, Regina Barzilay, Ila Fiete\n[arXiv:2307.00494](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.00494) • [code](https:\u002F\u002Fgithub.com\u002Fkirjner\u002FGGS)\n\n**Sampling Protein Language Models for Functional Protein Design**  \nJeremie Theddy Darmawan, Yarin Gal, Pascal Notin  \n[ICLR 2025 Workshop LMRL](https:\u002F\u002Fopenreview.net\u002Fforum?id=eRALDwvk9O)\n\n**Reliable algorithm selection for machine learning-guided design**\nClara Fannjiang, Ji Won Park\n[arXiv:2503.20767](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.20767)\n\n**Why risk matters for protein binder design**\nTudor-Stefan Cotet, Igor Krawczuk\n[arXiv:2504.00146](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.00146)\n\n**Guide your favorite protein sequence generative model**  \nJunhao Xiong, Hunter Nisonoff, Ishan Gaur, Jennifer Listgarten  \n[arXiv:2505.04823](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.04823)\n\n**Computational nanobody design using graph neural networks and Metropolis Monte Carlo sampling**  \nLei Wang, Xiaoming He, Gaoxing Guo, Xinzhou Qian, Qiang Huang  \n[bioRxiv 2025.06.08.658414](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.08.658414v1) • [code](https:\u002F\u002Fgithub.com\u002FFudan-HQLab\u002FAiPPA)\n\n**Monte Carlo Tree Diffusion with Multiple Experts for Protein Design**  \nXuefeng Liu, Mingxuan Cao, Songhao Jiang, Xiao Luo, Xiaotian Duan, Mengdi Wang, Tobin R. Sosnick, Jinbo Xu, Rick Stevens  \n[arXiv:2509.15796](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15796)\n\n**Relaxed Sequence Sampling for Diverse Protein Design**  \nJoohwan Ko, Aristofanis Rontogiannis, Yih-En Andrew Ban, Axel Elaldi, Nicholas Franklin  \n[arXiv:2510.23786](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.23786)\n\n**Advancing Protein Design via Multi-Agent Reinforcement Learning with Pareto-Based Collaborative Optimization**  \nMingming Zhu, Jiahua Rao, Xiaoyu Chen, Qianmu Yuan, Yuedong Yang  \n[bioRxiv 2026.01.13.699365](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.13.699365v1)\n\n## 3. Function to Scaffold\n\n> These models design backbone\u002Fscaffold\u002Ftemplate in Cartesian coordinates, contact maps, distance maps and φ & ψ angles. Including conditional\u002Funconditional generative models.\n\n### 3.1 GAN-based\n\n**Generative modeling for protein structures**\nAnand, Namrata, and Possu Huang\n[NeurIPS 2018](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2018\u002Ffile\u002Fafa299a4d1d8c52e75dd8a24c3ce534f-Paper.pdf)\n\n**Fully differentiable full-atom protein backbone generation**\nAnand Namrata, Raphael Eguchi, and Po-Ssu Huang\n[OpenReview ICLR 2019 workshop DeepGenStruct](https:\u002F\u002Fopenreview.net\u002Fforum?id=SJxnVL8YOV) • without code\n\n**RamaNet: Computational de novo helical protein backbone design using a long short-term memory generative neural network**\nSabban, Sari, and Mikhail Markovsky\n[F1000Research 9 (2020)](http:\u002F\u002Ff1000researchdata.s3.amazonaws.com\u002Fmanuscripts\u002F29106\u002Ff45e92eb-5d68-4da0-b918-91ded85d2e7d_22907_-_sari_sabban_v2.pdf) • [code](https:\u002F\u002Fsarisabban.github.io\u002FRamaNet\u002F) • pyRosetta • tensorflow • maximizaing the fluorescence of a protein\n\n**A Generative Model for Creating Path Delineated Helical Proteins**\nNicholas B. Woodall, Ryan Kibler, Basile Wicky, Brian Coventry\n[bioRxiv 2023.05.24.542095](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.24.542095v1) • [code](https:\u002F\u002Fgithub.com\u002FNickWoodall\u002FHelixGen)\n\n### 3.2 AutoEncoder-based\n\n**Conditioning by adaptive sampling for robust design**\nBrookes, David, Hahnbeom Park, and Jennifer Listgarten\n[International conference on machine learning. PMLR, 2019](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fbrookes19a\u002Fbrookes19a.pdf)  • without code\n\n**IG-VAE: generative modeling of immunoglobulin proteins by direct 3D coordinate generation**\nRaphael R. Eguchi, Christian A. Choe, Po-Ssu Huang\n[Biorxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.08.07.242347v2) • without code\n\n**Generating tertiary protein structures via an interpretative variational autoencoder**\nXiaojie Guo, Yuanqi Du, Sivani Tadepalli, Liang Zhao, Amarda Shehu\n[arXiv preprint arXiv:2004.07119 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.07119) • code not available\n\n**Function-guided protein design by deep manifold sampling**\nVladimir Gligorijevic, Stephen Ra, Daniel Berenberg, Richard Bonneau, Kyunghyun Cho\n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_Function-guided_protein_design_by.pdf) • without code\n\n**Deep sharpening of topological features for de novo protein design**\nZander Harteveld, Joshua Southern, Michaël Defferrard, Andreas Loukas, Pierre Vandergheynst, Micheal Bronstein, Bruno Correia\n[ICLR2022 Machine Learning for Drug Discovery. 2022](https:\u002F\u002Fopenreview.net\u002Fforum?id=DwN81YIXGQP) • code not available\n\n**End-to-End deep structure generative model for protein design**\nBoqiao Lai, matthew McPartlon, Jinbo Xu\n[bioRxiv 2022.07.09.499440](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.09.499440v1)\n\n**Deep Generative Design of Epitope-Specific Binding Proteins by Latent Conformation Optimization**\nRaphael R Eguchi, Christian A Choe, Udit Parekh, Irene S Khalek, Michael D Ward, Neha Vithani, Gregory R Bowman, Joseph G Jardine, Possu Huang\n[bioRxiv 2022.12.22.521698](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.22.521698v1)\n\n**Leveraging Deep Generative Model For Computational Protein Design And Optimization**\nBoqiao Lai\n[arXiv:2408.17241](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.17241) • PhD thesis\n\n**CyclicCAE: A Conformational Autoencoder for Efficient Heterochiral Macrocyclic Backbone Sampling**\nAndrew C. Powers, P. Douglas Renfrew, Parisa Hosseinzadeh, Vikram Khipple Mulligan\n[bioRxiv 2025.02.21.639569](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.21.639569v1)\n\n### 3.3 MLP-based\n\n**A backbone-centred energy function of neural networks for protein design**\nBin Huang, Yang Xu, Xiuhong Hu, Yongrui Liu, Shanhui Liao, Jiahai Zhang, Chengdong Huang, Jingjun Hong, Quan Chen & Haiyan Liu\n[Nature (2022)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41586-021-04383-5) • [code](https:\u002F\u002Fzenodo.org\u002Frecord\u002F4533424#.YwP3UPFBwqs)\n\n**De novo Design of Cavity-Containing Proteins with a Backbone-Centered Neural Network Energy Function**\nYang Xu, Xiuhong Hu, Chenchen Wang, Yongrui Liu, Quan Chen\nHaiyan Liu\n[Structure (2024)](https:\u002F\u002Fwww.cell.com\u002Fstructure\u002Ffulltext\u002FS0969-2126(24)00007-8)\n\n### 3.4 Diffusion-based\n\n**Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem**\nBrian L. Trippe, Jason Yim, Doug Tischer, Tamara Broderick, David Baker, Regina Barzilay, Tommi Jaakkola\n[arXiv:2206.04119](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.04119v2)\u002F[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FDiffusion_probabilistic_modeling_of_protein_backbones_in_3D_for_the_motif_scaffolding_problem.pdf)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=6TxBxqNME1Y) • [poster](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002Fd3d9446802a44259755d38e6d163e820.png?t=1667835607.0141048) • [Supplementary](https:\u002F\u002Fopenreview.net\u002Fattachment?id=6TxBxqNME1Y&name=supplementary_material) • [code](https:\u002F\u002Fgithub.com\u002Fblt2114\u002FProtDiff_SMCDiff)\n\n**ProteinSGM: Score-based generative modeling for de novo protein design**\nJin Sub Lee, Philip M Kim\n[bioRxiv 2022.07.13.499967](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.13.499967v2)\u002F[Nat Comput Sci (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43588-023-00440-3) • [code](https:\u002F\u002Fgitlab.com\u002Fmjslee0921\u002Fproteinsgm)\n\n**Protein structure generation via folding diffusion**\nKevin E. Wu, Kevin K. Yang, Rianne van den Berg, James Y. Zou, Alex X. Lu, Ava P. Amini\n[arXiv:2209.15611](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15611v2)\u002F[Nat Commun 15, 1059 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-45051-2) • [code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffoldingdiff)\n\n**Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds**\nYeqing Lin, Mohammed AlQuraishi\n[arXiv:2301.12485v3](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.12485v3) • [code](https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fgenie) • [news](https:\u002F\u002Fwww.dw.com\u002Fen\u002Fgenerative-ai-inventing-proteins-is-changing-medicine\u002Fa-66356415)\n\n**SE(3) diffusion model with application to protein backbone generation**\nJason Yim, Brian L. Trippe, Valentin De Bortoli, Emile Mathieu, Arnaud Doucet, Regina Barzilay, Tommi Jaakkola\n[arXiv:2302.02277](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.02277v2)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=6TxBxqNME1Y) • [code](https:\u002F\u002Fgithub.com\u002Fjasonkyuyim\u002Fse3_diffusion) • [Supplementary](https:\u002F\u002Fopenreview.net\u002Fattachment?id=6TxBxqNME1Y&name=supplementary_material)\n\n**A Latent Diffusion Model for Protein Structure Generation**\nCong Fu, Keqiang Yan, Limei Wang, Wing Yee Au, Michael McThrow, Tao Komikado, Koji Maruhashi, Kanji Uchino, Xiaoning Qian, Shuiwang Ji\n[arXiv:2305.04120](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.04120)\n\n**Practical and Asymptotically Exact Conditional Sampling in Diffusion Models**\nLuhuan Wu, Brian L. Trippe, Christian A. Naesseth, David M. Blei, John P. Cunningham\n[arXiv:2306.17775](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.17775) • [code](https:\u002F\u002Fgithub.com\u002Fblt2114\u002Ftwisted_diffusion_sampler)\n\n**Dynamics-Informed Protein Design with Structure Conditioning**\nSimon V. Mathis, Urszula Julia Komorowska, Mateja Jamnik, Pietro Lió\n[WCBICML2023](https:\u002F\u002Ficml-compbio.github.io\u002F2023\u002Fpapers\u002FWCBICML2023_paper121.pdf)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=jZPqf2G9Sw)\n\n**ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model**\nBo Ni and David L. Kaplan and M. Buehler\n[arXiv:2310.10605](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10605)\u002F[Science Advances 10.6 (2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.adl4000) • [Supplementary](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffi\u002F33tnpd6u2xwermlvj22y9\u002FSI_3_unfolding_movies_from_dataset.zip?rlkey=qno7rcitcdree8t9cj8wzg9sf&dl=0) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProteinMechanicsDiffusionDesign)\n\n**DiffSDS: A geometric sequence diffusion model for protein backbone inpainting**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=2xYO9oxh0y)\u002F[arXiv:2301.09642](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.09642)\n\n**A framework for conditional diffusion modelling with applications in motif scaffolding for protein design**\nKieran Didi, Francisco Vargas, Simon V Mathis, Vincent Dutordoir, Emile Mathieu, Urszula J Komorowska, Pietro Lio\n[arXiv:2312.09236](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.09236)\n\n**Improving diffusion-based protein backbone generation with global-geometry-aware latent encoding**\nYuyang Zhang, Yuhang Liu, Zinnia Ma, Min Li, Chunfu Xu & Haipeng Gong  \n[bioRxiv 2023.12.13.571602](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.13.571602v1)\u002F[Nat Mach Intell (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01059-x)• [code](https:\u002F\u002Fgithub.com\u002Fmeneshail\u002FTopoDiff)\n\n**Improved motif-scaffolding with SE(3) flow matching**\nJason Yim, Andrew Campbell, Emile Mathieu, Andrew Y. K. Foong, Michael Gastegger, José Jiménez-Luna, Sarah Lewis, Victor Garcia Satorras, Bastiaan S. Veeling, Frank Noé, Regina Barzilay, Tommi S. Jaakkola\n[arXiv:2401.04082](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.04082)\u002F[TMLR](https:\u002F\u002Fopenreview.net\u002Fforum?id=fa1ne8xDGn) • [code1](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fframe-flow),[code2](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fprotein-frame-flow)\n\n**DiffTopo: Fold exploration using coarse grained protein topology representations**\nYangyang Miao, Bruno Correia\n[bioRxiv 2024.02.01.578456](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.01.578456v1)\u002FICLR 2024\n\n**Diffusion models in protein structure and docking**\nJason Yim, Hannes Stärk, Gabriele Corso, Bowen Jing, Regina Barzilay, Tommi S. Jaakkola\n[Wiley Interdisciplinary Reviews: Computational Molecular Science 14.2 (2024)](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fwcms.1711) • review\n\n**De novo antibody design with SE(3) diffusion**\nDaniel Cutting, Frédéric A. Dreyer, David Errington, Constantin Schneider, Charlotte M. Deane\n[arXiv:2405.07622](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.07622)\n\n**Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2**\nYeqing Lin, Minji Lee, Zhao Zhang, Mohammed AlQuraishi\n[arXiv:2405.15489](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.15489) • [code](https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fgenie2) • [news](https:\u002F\u002Fwww.marktechpost.com\u002F2024\u002F05\u002F29\u002Fgenie-2-transforming-protein-design-with-advanced-multi-motif-scaffolding-and-enhanced-structural-diversity\u002F)\n\n**DSG2-mini**\n[DiffuseBio](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fdiffuse-bio\u002F)\n[technical appendix](https:\u002F\u002Fdiffuse.bio\u002Fupdates.html#appendix) • [website](https:\u002F\u002Fapp.diffuse.bio\u002F) • commercial\n\n**Floating Anchor Diffusion Model for Multi-motif Scaffolding**\nKe Liu, Weian Mao, Shuaike Shen, Xiaoran Jiao, Zheng Sun, Hao Chen, Chunhua Shen\n[ICML 2024](https:\u002F\u002Fproceedings.mlr.press\u002Fv235\u002Fliu24av.html)\u002F[arXiv:2406.03141](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.03141) • [code](https:\u002F\u002Fgithub.com\u002Faim-uofa\u002FFADiff) • [poster](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F34654)\n\n**De novo Design of A Fusion Protein Tool for GPCR Research**\nKaixuan Gao, Xin Zhang, Jia Nie, Hengyu Meng, Weishe Zhang, Boxue Tian, Xiangyu Liu\n[bioRxiv 2024.09.14.613090](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.14.613090v1)\u002F[Proceedings of the National Academy of Sciences 122.29 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2422360122) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F09\u002F15\u002F2024.09.14.613090\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFdiffusion-based\n\n**Text2Protein: A Generative Model for Designated Protein Design on Given Description**\nRamtin Hosseini, Siyang Zhang, Pengtao Xie\n[PREPRINT (Version 1) available at Research Square](https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-4868665\u002Fv1) • [code](https:\u002F\u002Fgithub.com\u002Fszhan227\u002Ftext2protein)\n\n**Diffusion Posterior Sampling via Sequential Monte Carlo for Zero-Shot Scaffolding of Protein Motifs**\nYoung, James Matthew Uygongco, and Omer Deniz Akyildiz\n[Imperial CollegeofScience, Technology and Medicine, 2024](https:\u002F\u002Fmatsagad.com\u002Ffiles\u002Fpapers\u002FMRes_Project.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fmatsagad\u002Fmres-project) • Master thesis • Genie-based\n\n**Protein A-like Peptide Design Based on Diffusion and ESM2 Models**\nLong Zhao, Qiang He, Huijia Song, Huijia Song,Tianqian Zhou, An Luo, Zhenguo Wen,Teng Wang, and Xiaozhu Lin\n[Molecules 29.20 (2024)](https:\u002F\u002Fwww.mdpi.com\u002F1420-3049\u002F29\u002F20\u002F4965) • [code](https:\u002F\u002Fgithub.com\u002Ftomlongcool\u002Fdiffusion4Protein)\n\n**FoldMark: Protecting Protein Generative Models with Watermarking**\nZaixi Zhang, Ruofan Jin, Kaidi Fu, Le Cong, Marinka Zitnik, Mengdi Wang\n[arXiv:2410.20354](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.20354) • [code](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FFoldMark)\n\n**ProteinWeaver: A Divide-and-Assembly Approach for Protein Backbone Design**\nYiming Ma, Fei Ye, Yi Zhou, Zaixiang Zheng, Dongyu Xue, Quanquan Gu\n[arXiv:2411.16686](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.16686)\n\n**On Diffusion Posterior Sampling via Sequential Monte Carlo for Zero-Shot Scaffolding of Protein Motifs**\nJames Matthew Young, O. Deniz Akyildiz\n[arXiv:2412.05788](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.05788) • [code](https:\u002F\u002Fgithub.com\u002Fmatsagad\u002Fmres-project)\n\n**From thermodynamics to protein design: Diffusion models for biomolecule generation towards autonomous protein engineering**\nWen-ran Li, Xavier F. Cadet, David Medina-Ortiz, Mehdi D. Davari, Ramanathan Sowdhamini, Cedric Damour, Yu Li, Alain Miranville, Frederic Cadet\n[arXiv:2501.02680](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.02680) • review\n\n**RFdiffusion Exhibits Low Success Rate in De Novo Design of Functional Protein Binders for Biochemical Detection**\nBruce Jiang, Xiaoxiao Li, Amber Guo, Moris Wei, Jonny Wu\n[bioRxiv 2025.02.07.636769](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.07.636769v1)\n\n**From Atoms to Fragments: A Coarse Representation for Efficient and Functional Protein Design**\nLeonardo V Castorina, Christopher W Wood, Kartic Subr\n[bioRxiv 2025.03.19.644162](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.19.644162v2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F20\u002F2025.03.19.644162\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFdiffusion-based\n\n**Hierarchical Protein Backbone Generation with Latent and Structure Diffusion**\nJason Yim, Marouane Jaakik, Ge Liu, Jacob Gershon, Karsten Kreis, David Baker, Regina Barzilay, Tommi Jaakkola\n[ICLR 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=J19jKa3wFj)\n\n**The Dance of Atoms-De Novo Protein Design with Diffusion Model**\nYujie Qin, Ming He, Changyong Yu, Ming Ni, Xian Liu, Xiaochen Bo\n[arXiv:2504.16479](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.16479) • review\n\n**ProT-GFDM: A Generative Fractional Diffusion Model for Protein Generation**  \nXiao Liang, Wentao Ma, Eric Paquet, Herna Lydia Viktor, Wojtek Michalowski\n[arXiv:2504.21092](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.21092)\n\n**NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones**  \nUrszula Julia Komorowska, Francisco Vargas, Alessandro Rondina, Pietro Lio, Mateja Jamnik  \n[ICML 2025 poster](https:\u002F\u002Fopenreview.net\u002Fforum?id=2dlTi4S4JN)\n\n**AIDO.StructureDiffusion: The AIDO Module for Molecular Design**  \n[GenBio Team](https:\u002F\u002Fgenbio.ai\u002Fauthor\u002Fgenbioaiteam\u002F)  \n[website](https:\u002F\u002Fgenbio.ai\u002Faido-structurediffusion-the-aido-module-for-molecular-design\u002F)\n\n**De novo design of phosphorylation-induced protein switches for synthetic signaling in cells**  \nStephen Buckley, Yangyang Miao, Mubarak Idris, Pao-Wan Lee, Leo Scheller, Roland Riek, Sebastian J. Maerkl, Luciano A. Abriata, Bruno E. Correia  \n[bioRxiv 2025.09.10.675034](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.10.675034v1)\n\n**Constrained Diffusion for Protein Design with Hard Structural Constraints**  \nJacob K Christopher, Austin Seamann, Jingyi Cui, Sagar Khare, Ferdinando Fioretto  \n[bioRxiv 2025.10.15.682365](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.15.682365v1)\n\n**Controllable protein design through Feynman-Kac steering**  \nErik Hartman, Jonas Wallin, Johan Malmström, Jimmy Olsson  \n[arXiv:2511.09216](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.09216) • [code](https:\u002F\u002Fgithub.com\u002FErikHartman\u002FFK-RFdiffusion)\n\n**Protein generation with embedding learning for motif diversification**  \nKevin Michalewicz, Chen Jin, Philip Alexander Teare, Tom Diethe, Mauricio Barahona, Barbara Bravi, Asher Mullokandov  \n[arXiv:2510.18790](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.18790)\n\n**Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement**  \nLakshaditya Singh, Adwait Shelke, Divyansh Agrawal  \n[arXiv:2511.19184](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.19184)\n\n**SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers**  \nShentong Mo, Lanqing Li  \n[arXiv:2602.06706](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06706)\n\n### 3.5 RL-based\n\n**Top-down design of protein nanomaterials with reinforcement learning**\nIsaac D Lutz, Shunzhi Wang, Christoffer Norn, Andrew J Borst, Yan Ting Zhao, Annie Dosey, Longxing Cao, Zhe Li, Minkyung Baek, Neil P King, Hannele Ruohola-Baker, David Baker\n[bioRxiv 2022.09.25.509419](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.25.509419v1)\u002F[Science380, 266-273(2023)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adf6591) • [code](https:\u002F\u002Fgithub.com\u002Fidlutz\u002Fprotein-backbone-MCTS),[code2](https:\u002F\u002Ffiles.ipd.uw.edu\u002Fpub\u002F2023_RL_capsid_design\u002Fsequence_design_pipeline.tar)\n\n**Model-based reinforcement learning for protein backbone design**\nFrederic Renard, Cyprien Courtot, Alfredo Reichlin, Oliver Bent\n[arXiv:2405.01983](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.01983)\n\n**Target-based de novo design of cyclic peptide binders**\nFanhao Wang, Tiantian Zhang, Jintao Zhu, Xiaoling Zhang, Changsheng Zhang, Luhua Lai\n[bioRxiv 2025.01.18.633746](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.18.633746v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F01\u002F19\u002F2025.01.18.633746\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n### 3.6 Flow-based\n\n**SE(3)-Stochastic Flow Matching for Protein Backbone Generation**\nAvishek Joey Bose, Tara Akhound-Sadegh, Kilian Fatras, Guillaume Huguet, Jarrid Rector-Brooks, Cheng-Hao Liu, Andrei Cristian Nica, Maksym Korablyov, Michael Bronstein, Alexander Tong\n[arXiv:2310.02391](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.02391)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=kJFIH23hXb)\n\n**Fast protein backbone generation with SE(3) flow matching**\nJason Yim, Andrew Campbell, Andrew Y. K. Foong, Michael Gastegger, José Jiménez-Luna, Sarah Lewis, Victor Garcia Satorras, Bastiaan S. Veeling, Regina Barzilay, Tommi Jaakkola, Frank Noé\n[arXiv:2310.05297](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05297) • [code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fframe-flow)\n\n**Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation**\nGuillaume Huguet, James Vuckovic, Kilian Fatras, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam, Cheng-Hao Liu, Jarrid Rector-Brooks, Tara Akhound-Sadegh, Michael Bronstein, Alexander Tong, Avishek Joey Bose\n[arXiv:2405.20313](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.20313)\u002F[NeurIPS 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=paYwtPBpyZ) • [website](https:\u002F\u002Fwww.dreamfold.ai\u002Fblog\u002Ffoldflow-2) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xgA8T9h8mm0)\n\n**Design of Ligand-Binding Proteins with Atomic Flow Matching**\nJunqi Liu, Shaoning Li, Chence Shi, Zhi Yang, Jian Tang\n[arXiv:2409.12080](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.12080)\n\n**ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation**  \nAngxiao Yue, Zichong Wang, Hongteng Xu  \n[arXiv:2502.14637](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14637) • [code](https:\u002F\u002Fgithub.com\u002FAngxiaoYue\u002FReQFlow)\n\n**Proteina: Scaling Flow-based Protein Structure Generative Models**\nTomas Geffner, Kieran Didi, Zuobai Zhang, Danny Reidenbach, Zhonglin Cao, Jason Yim, Mario Geiger, Christian Dallago, Emine Kucukbenli, Arash Vahdat, Karsten Kreis\n[ICLR 2025 Oral](https:\u002F\u002Fopenreview.net\u002Fforum?id=TVQLu34bdw) • [code](https:\u002F\u002Fgithub.com\u002FNVIDIA-Digital-Bio\u002Fproteina\u002F) • [website](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fproteina\u002F) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Y2dRj9_ZEHw)\n\n**ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids**\nHannes Stark, Bowen Jing, Tomas Geffner, Jason Yim, Tommi Jaakkola, Arash Vahdat, Karsten Kreis\n[ICLR 2025 Oral](https:\u002F\u002Fopenreview.net\u002Fforum?id=0ctvBgKFgc) • [code](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fprotcomposer) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=2G0d-RePc7c)\n\n**Robust and Reliable de novo Protein Design: A Flow-Matching-Based Protein Generative Model Achieves Remarkably High Success Rates**  \nJunyu Yan, Zibo Cui, Wenqing Yan, Yuhang Chen, Mengchen Pu, Shuai Li, Sheng Ye  \n[bioRxiv 2025.04.29.651154](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.29.651154v1) • [code](https:\u002F\u002Fgithub.com\u002FJoreyYan\u002FOriginflow)\n\n**Flexibility-conditioned protein structure design with flow matching**  \nVsevolod Viliuga, Leif Seute, Nicolas Wolf, Simon Wagner, Arne Elofsson, Jan Stühmer, Frauke Gräter  \n[ICML 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=890gHX7ieS)\n\n**Challenges and Guidelines in Deep Generative Protein Design: Four Case Studies**  \nTianyuan Zheng, Alessandro Rondina, Gos Micklem, Pietro Lio\n[FM4LS 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=FcfpwlFDUZ)\n\n**Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation**  \nYogesh Verma, Markus Heinonen, Vikas Garg  \n[arXiv:2509.25379](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2509.25379)\n\n**Distilled Protein Backbone Generation**  \nLiyang Xie, Haoran Zhang, Zhendong Wang, Wesley Tansey, Mingyuan Zhou  \n[arXiv:2510.03095](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2510.03095)\n\n**Flows, straight but not so fast: Exploring the design space of Rectified Flows in Protein Design**  \nJunhua Chen, Simon Mathis, Charles Harris, Kieran Didi, Pietro Lio  \n[arXiv:2510.24732](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.24732)\n\n**High-Affinity Protein Binder Design via Flow Matching and In Silico Maturation**  \nQilin Yu, Liangyue Guo, Xiayan Qin, Xikun Huang, Baihui Tian, Hongzhun Wang, Yu Liu, Yunzhi Lang, Di Wang, Zhouhanyu Shen, Jie Lin, and Mingchen Chen  \n[preprint](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffi\u002F9v6myel7uodrdsckwk5bd\u002FMain_SI1_High-Affinity-Protein-Binder-Design-via-Flow-Matching-and-In-Silico-Maturation.pdf?rlkey=ohvrohvflnyq993mq24skjm2v&e=1&st=tr7t3x3a&dl=0) • [code](https:\u002F\u002Fgithub.com\u002FMingchenchen\u002FPPIFlow)\n\n### 3.7 Score-based\n\n**Score-Based Generative Models for Designing Binding Peptide Backbones**\nJohn D Boom, Matthew Greenig, Pietro Sormanni, Pietro Liò\n[arXiv:2310.07051](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.07051) • [code](https:\u002F\u002Fgithub.com\u002Fmgreenig\u002Floopgen)\n\n**Building Confidence in Deep Generative Protein Design**\nTianyuan Zheng, Alessandro Rondina, Pietro Liò\n[arXiv:2411.18568](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.18568) • [code](https:\u002F\u002Fgithub.com\u002FECburx\u002FPROTEVAL)\n\n### 3.8 Autoregressive\n\n**Protein Autoregressive Modeling via Multiscale Structure Generation**  \nYanru Qu, Cheng-Yen Hsieh, Zaixiang Zheng, Ge Liu, Quanquan Gu\n[arXiv:2602.04883](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04883)\n\n## 4.Scaffold to Sequence\n\n> Identify amino sequence from given backbone\u002Fscaffold\u002Ftemplate constrains: torsion angles(φ & ψ), backbone angles(θ and τ), backbone dihedrals (φ, ψ & ω), backbone atoms (Cα, N, C, & O), Cα − Cα distance, unit direction vectors of Cα−Cα, Cα−N & Cα−C, etc(aka. inverse folding). Referred from [here](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079). Energy-based models are also inculded for task of rotamer conformation(χ angles or atom coordinates) recovery.\n\n### 4.0 Review\n\n**Protein sequence design on given backbones with deep learning**\nYufeng Liu, Haiyan Liu\n[Protein Engineering, Design and Selection, 2023](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzad024\u002F7503843)\n\n**Multi-indicator comparative evaluation for deep Learning-Based protein sequence design methods**\nJinyu Yu, Junxi Mu, Ting Wei, Hai-Feng Chen\n[Bioinformatics, 2024;, btae037](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtae037\u002F7585533)\n\n**Generative AI for Controllable Protein Sequence Design: A Survey**\nYiheng Zhu, Zitai Kong, Jialu Wu, Weize Liu, Yuqiang Han, Mingze Yin, Hongxia Xu, Chang-Yu Hsieh, Tingjun Hou\n[arXiv:2402.10516](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.10516)\n\n**Backbone Conditional Protein Sequence Design**  \nJustas Dauparas  \n[Cold Spring Harbor Perspectives in Biology (2025)](https:\u002F\u002Fcshperspectives.cshlp.org\u002Fcontent\u002Fearly\u002F2025\u002F05\u002F03\u002Fcshperspect.a041517)\n\n**Zero-shot protein stability prediction by inverse folding models: a free energy interpretation**  \nJes Frellsen, Maher M. Kassem, Tone Bengtsen, Lars Olsen, Kresten Lindorff-Larsen, Jesper Ferkinghoff-Borg, Wouter Boomsma  \n[arXiv:2506.05596](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.05596)\n\n### 4.1 MLP-based\n\n**3D representations of amino acids-applications to protein sequence comparison and classification**\nLi, Jie, and Patrice Koehl\n[Computational and structural biotechnology journal 11.18 (2014)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2001037014000270) • 2014\n\n**Direct prediction of profiles of sequences compatible with a protein structure by neural networks with fragment-based local and energy-based nonlocal profiles**\nZhixiu Li, Yuedong Yang, Eshel Faraggi, Jian Zhan, Yaoqi Zhou\n[Proteins: Structure, Function, and Bioinformatics 82.10 (2014)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fprot.24620) • code unavailable\n\n**SPIN2: Predicting sequence profiles from protein structures using deep neural networks**\nJames O'Connell, Zhixiu Li, Jack Hanson, Rhys Heffernan, James Lyons, Kuldip Paliwal, Abdollah Dehzangi, Yuedong Yang, Yaoqi Zhou\n[Proteins: Structure, Function, and Bioinformatics 86.6 (2018)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fprot.25489) • code unavailable\n\n**Computational protein design with deep learning neural networks**\nJingxue Wang, Huali Cao, John Z. H. Zhang & Yifei Qi\n[Scientific reports 8.1 (2018)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-018-24760-x.pdf) • code unavailable\n\n**Ligand-aware protein sequence design using protein self contacts**\nJody Mou, Benjamin Fry, Chun-Chen Yao, Nicholas Polizzi\n[NeurIPS 2022](https:\u002F\u002Fwww.dropbox.com\u002Fs\u002F98ri2f9gverljcw\u002FLigand-aware_protein_sequence_design_using_protein_self_contacts.pdf?dl=0)\n\n**SeqPredNN: a neural network that generates protein sequences that fold into specified tertiary structures**\nLategan, F. Adriaan, Caroline Schreiber, and Hugh G. Patterton\n[BMC bioinformatics 24.1 (2023)](https:\u002F\u002Fbmcbioinformatics.biomedcentral.com\u002Farticles\u002F10.1186\u002Fs12859-023-05498-4) • [code](https:\u002F\u002Fgithub.com\u002Ffalategan\u002FSeqPredNN)\n\n### 4.2 VAE-based\n\n**Design of metalloproteins and novel protein folds using variational autoencoders**\nGreener, Joe G., Lewis Moffat, and David T. Jones\n[Scientific reports 8.1 (2018)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-018-34533-1)\n\n**AlphaFold Database Debiasing for Robust Inverse Folding**  \nCheng Tan, Zhenxiao Cao, Zhangyang Gao, Siyuan Li, Yufei Huang, Stan Z. Li  \n[arXiv:2506.08365](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08365)\n\n**DivPro: diverse protein sequence design with direct structure recovery guidance**  \nXinyi Zhou, Guibao Shen, Yingcong Chen, Guangyong Chen, Pheng Ann Heng  \n[Bioinformatics (2025)](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F41\u002FSupplement_1\u002Fi382\u002F8199395) • [code](https:\u002F\u002Fgithub.com\u002Fveghen\u002FDivPro)\n\n### 4.3 LSTM-based\n\n**To improve protein sequence profile prediction through image captioning on pairwise residue distance map**\nSheng Chen, Zhe Sun, Lihua Lin, Zifeng Liu, Xun Liu, Yutian Chong, Yutong Lu, Huiying Zhao, and Yuedong Yang\n[Journal of chemical information and modeling 60.1 (2019)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.9b00438) • [SPROF](https:\u002F\u002Fgithub.com\u002Fbiomed-AI\u002FSPROF)\n\n**Deep learning of Protein Sequence Design of Protein-protein Interactions**\nSyrlybaeva, Raulia, and Eva-Maria Strauch\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.28.478262v1)\u002F[Bioinformatics, 2022;, btac733](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtac733\u002F6827796) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.28.478262v1.supplementary-material) • [code](https:\u002F\u002Fgithub.com\u002Fstrauchlab\u002FiNNterfaceDesign)\n\n### 4.4 CNN-based\n\n**A structure-based deep learning framework for protein engineering**\nRaghav Shroff, Austin W. Cole, Barrett R. Morrow, Daniel J. Diaz, Isaac Donnell, Jimmy Gollihar, Andrew D. Ellington, Ross Thyer\n[bioRxiv (2019)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F833905v1)\n\n**ProDCoNN: Protein design using a convolutional neural network**\nYuan Zhang, Yang Chen, Chenran Wang, Chun-Chao Lo, Xiuwen Liu, Wei Wu, Jinfeng Zhang\n[Proteins: Structure, Function, and Bioinformatics 88.7 (2020)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fprot.25868) • code unavailable\n\n**Protein sequence design with a learned potential**\nNamrata Anand, Raphael Eguchi, Irimpan I. Mathews, Carla P. Perez, Alexander Derry, Russ B. Altman & Po-Ssu Huang\n[Nacture Communications (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-28313-9) • [code](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fprotein_seq_des)\n\n**TIMED-Design: Flexible and Accessible Protein Sequence Design with Convolutional Neural Networks**\nLeonardo V Castorina, Suleyman Mert Ünal, Kartic Subr, Christopher W Wood\n[Protein Engineering, Design and Selection, 2024](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzae002\u002F7591701)) • [code](https:\u002F\u002Fgithub.com\u002Fwells-wood-research\u002Ftimed-design) • [website](https:\u002F\u002Fpragmaticproteindesign.bio.ed.ac.uk\u002Ftimed\u002F)\n\n**Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme**\nSimon d’Oelsnitz, Daniel J. Diaz, Wantae Kim, Daniel J. Acosta, Tyler L. Dangerfield, Mason W. Schechter, Matthew B. Minus, James R. Howard, Hannah Do, James M. Loy, Hal S. Alper, Y. Jessie Zhang & Andrew D. Ellington\n[Nature Communications 15.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-46356-y) • [code1](https:\u002F\u002Fgithub.com\u002Fdanny305\u002FMutComputeX), [code2](https:\u002F\u002Fgithub.com\u002Fsimonsnitz\u002Fplotting)\n\n**OPUS-Design: Designing Protein Sequence from Backbone Structure with 3DCNN and Protein Language Model**\nGang Xu, Yulu Yang, Yiqiu Zhang, Qinghua Wang, Jianpeng Ma\n[bioRxiv 2024.08.20.608889](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.20.608889v2) • [code](https:\u002F\u002Fgithub.com\u002FOPUS-MaLab\u002Fopus_design)\n\n**ProBID-Net: A Deep Learning Model for Protein-Protein Binding Interface Design**\nZhihang Chen, Menglin Ji, Jie Qiana, Zhe Zhang, Xiangying Zhang, Haotian Gao, Haojie Wang, Renxiao Wang, Yifei Qi\n[Chemical Science (2024)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002FContent\u002FArticleLanding\u002F2024\u002FSC\u002FD4SC02233E) • [code](https:\u002F\u002Fgithub.com\u002FComputArtCMCG\u002FProBID-NET)\n\n### 4.5 GNN-based\n\n**Learning from protein structure with geometric vector perceptrons**\nBowen Jing, Stephan Eismann, Patricia Suriana, Raphael J.L. Townshend, Ron Dror\n[arXiv preprint arXiv:2009.01411 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01411)\u002F[ICLR(2021)](https:\u002F\u002Fopenreview.net\u002Fforum?id=1YLJDvSx6J4) • [GVP](https:\u002F\u002Fgithub.com\u002Fdrorlab\u002Fgvp-pytorch)\n\n**Fast and flexible protein design using deep graph neural networks**\nAlexey Strokach, David Becerra, Carles Corbi-Verge, Albert Perez-Riba, Philip M. Kim\n[Cell Systems (2020)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2405471220303276) • [code::ProteinSolver](https:\u002F\u002Fgitlab.com\u002Fostrokach\u002Fproteinsolver)\n\n**Mimetic Neural Networks: A unified framework for Protein Design and Folding**\nMoshe Eliasof, Tue Boesen, Eldad Haber, Chen Keasar, Eran Treister\n[arXiv:2102.03881](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.03881)\u002F[Front. Bioinform. 2:715006](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffbinf.2022.715006\u002Ffull)\n\n**TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifs**\nAlex J. Li, Vikram Sundar, Gevorg Grigoryan, Amy E. Keating\n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_TERMinator:_A_Neural_Framework.pdf) \u002F [arXiv (2022)](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2204.13048.pdf)\n\n**A neural network model for prediction of amino-acid probability from a protein backbone structure**\nShintaro Minami, Koya Sakuma, Naoya Kobayashi\nUnpublished yet (June 2021)• [GCNdesgin](https:\u002F\u002Fgithub.com\u002FShintaroMinami\u002FGCNdesign)\n\n**XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers**\nJack B Maguire, Daniele Grattarola, Vikram Khipple Mulligan, Eugene Klyshko, Hans Melo\n[PLoS computational biology 17.9 (2021)](https:\u002F\u002Fpdfs.semanticscholar.org\u002F23bc\u002F58424378d15fda91e9d427fb553728c38b8a.pdf)\n\n**AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB**\nGao, Zhangyang, Cheng Tan, and Stan Li\n[arXiv preprint arXiv:2202.01079 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079) • [code](https:\u002F\u002Fgithub.com\u002Fjonathanking\u002Fsidechainnet)\n\n**Generative De Novo Protein Design with Global Context**\nCheng Tan, Zhangyao Gao, Jun Xia and Stan Z. Li\n[arXiv](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.10673) • Apr 2022 • [code](https:\u002F\u002Fgithub.com\u002Fchengtan9907\u002Fgca-generative-protein-design)\n\n**Masked inverse folding with sequence transfer for protein representation learning**\nKevin K Yang, Hugh Yeh, Niccolò Zanichelli\n[bioRxiv 2022.05.25.493516](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.05.25.493516v1)\u002F[Protein Engineering, Design and Selection 36 (2023)](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Farticle\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzad015\u002F7330543) • [code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fprotein-sequence-models) • [model](https:\u002F\u002Fdoi.org\u002F10.1234\u002Fmifst)\n\n**Robust deep learning based protein sequence design using ProteinMPNN**\nJustas Dauparas, Ivan Anishchenko, Nathaniel Bennett, Hua Bai, Robert J. Ragotte, Lukas F. Milles, Basile I. M. Wicky, Alexis Courbet, Robbert J. de Haas, Neville Bethel, Philip J. Y. Leung, Timothy F. Huddy, Sam Pellock, Doug Tischer, Frederick Chan, Brian Koepnick, Hannah Nguyen, Alex Kang, Banumathi Sankaran, Asim Bera, Neil P. King, David Baker\n[bioRxiv 2022.06.03.494563](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.03.494563v1.article-metrics)\u002F[Science (2022)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.add2187) • [code](https:\u002F\u002Fgithub.com\u002Fdauparas\u002FProteinMPNN) • [hugging face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fsimonduerr\u002FProteinMPNN) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=aVQQuoToTJA) • [colab(in_jax)](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fv1.1.0\u002Fmpnn\u002Fexamples\u002Fproteinmpnn_in_jax.ipynb) • [ProteinMPNN+ESMFold](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fsimonduerr\u002FProteinMPNNESM\u002Fblob\u002Fmain\u002FREADME.md)\n\n**Antibody-Antigen Docking and Design via Hierarchical Equivariant Refinement**\nJin, Wengong, Regina Barzilay, and Tommi Jaakkola\n[arXiv preprint arXiv:2207.06616 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.06616)\u002F[International Conference on Machine Learning. PMLR, 2022](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2022\u002Fposter\u002F16625) • [code](https:\u002F\u002Fgithub.com\u002Fwengong-jin\u002Fabdockgen) • [poster](https:\u002F\u002Ficml.cc\u002Fmedia\u002FPosterPDFs\u002FICML%202022\u002Fb7f520a55897b35e6eb462bbf80915c6.png)\n\n**Neural Network-Derived Potts Models for Structure-Based Protein Design using Backbone Atomic Coordinates and Tertiary Motifs**\nAlex J. Li, Mindren Lu, Israel Desta, Vikram Sundar, Gevorg Grigoryan, and Amy E. Keating\n[bioRxiv 2022.08.02.501736](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.02.501736v1.full.pdf)\u002F[Protein Science, 32(2)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.4554)\n\n**SE(3) Equivalent Graph Attention Network as an Energy-Based Model for Protein Side Chain Conformation**\nDeqin Liu, Sheng Chen, Shuangjia Zheng, Sen Zhang, Yuedong Yang\n[bioRxiv 2022.09.05.506704](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.05.506704v1) • [code](https:\u002F\u002Fgithub.com\u002Fbiomed-AI\u002FGraphEBM)\n\n**PiFold: Toward effective and efficient protein inverse folding**\nZhangyang Gao, Cheng Tan, Stan Z. Li\n[arXiv:2209.12643v2](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.12643v3)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fpdf?id=oMsN9TYwJ0j) • [github](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FPiFold)\n\n**Protein Sequence Design by Entropy-based Iterative Refinement**\nXinyi Zhou, Guangyong Chen, Junjie Ye, Ercheng Wang, Jun Zhang, Cong Mao, Zhanwei Li, Jianye Hao, Xingxu Huang, Jin Tang, Pheng Ann Heng\n[bioRxiv 2023.02.04.527099](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.04.527099v1)\n\n**Lightweight Contrastive Protein Structure-Sequence Transformation**\nJiangbin Zheng, Ge Wang, Yufei Huang, Bozhen Hu, Siyuan Li, Cheng Tan, Xinwen Fan, Stan Z. Li\n[arXiv:2303.11783](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.11783)\n\n**Modeling Protein Structure Using Geometric Vector Field Networks**\nWeian Mao, Muzhi Zhu, Hao Chen, Chunhua Shen\n[bioRxiv 2023.05.07.539736](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.07.539736v1)\n\n**Knowledge-Design: Pushing the Limit of Protein Deign via Knowledge Refinement**\nZhangyang Gao, Cheng Tan, Stan Z. Li\n[arXiv:2305.15151](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.15151)\u002F[ICLR](https:\u002F\u002Fopenreview.net\u002Fforum?id=mpqMVWgqjn) • [code](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FProteinInvBench)\n\n**SPIN-CGNN: Improved fixed backbone protein design with contact map-based graph construction and contact graph neural network**\nXing Zhang, Hongmei Yin, Fei Ling, Jian Zhan, Yaoqi Zhou\n[bioRxiv 2023.07.07.548080](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.07.548080v1)\u002F[PLOS Computational Biology](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1011330) • [code](https:\u002F\u002Fgithub.com\u002FEricZhangSCUT\u002FSPIN-CGNN)\n\n**ZetaDesign: an end-to-end deep learning method for protein sequence design and side-chain packing**\nJunyu Yan and others\n[Briefings in Bioinformatics, 2023](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fbib\u002Fbbad257\u002F7222295) • [code](https:\u002F\u002Fgithub.com\u002FJoreyYan\u002Fzetadesign)\n\n**Contextual protein encodings from equivariant graph transformers**\nSai Pooja Mahajan, Jeffrey A. Ruffolo, Jeffrey J. Gray\n[bioRxiv 2023.07.15.549154](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.15.549154v1) • [code](https:\u002F\u002Fgithub.com\u002FGrayLab\u002FMaskedProteinEnT)\n\n**Robust Design of Effective Allosteric Activators for Rsp5 E3 Ligase Using the Machine Learning Tool ProteinMPNN**\nHsi-Wen Kao, Wei-Lin Lu, Meng-Ru Ho, Yu-Fong Lin, Yun-Jung Hsieh, Tzu-Ping Ko, Shang-Te Danny Hsu, and Kuen-Phon Wu\n[ACS Synthetic Biology (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.3c00042) • [Supplementary](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fsuppl\u002F10.1021\u002Facssynbio.3c00042\u002Fsuppl_file\u002Fsb3c00042_si_001.pdf)\n\n**Rapid and automated design of two-component protein nanomaterials using ProteinMPNN**\nRobbert J. de Haas, Natalie Brunette, Alex Goodson, Justas Dauparas, Sue Y. Yi, Erin C. Yang, Quinton Dowling, Hannah Nguyen, Alex Kang, Asim K. Bera, Banumathi Sankaran, Renko de Vries, David Baker, Neil P. King\n[bioRxiv 2023.08.04.551935](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.04.551935v1)\u002F[Proceedings of the National Academy of Sciences 121.(13)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2314646121) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F08\u002F04\u002F2023.08.04.551935\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [data](https:\u002F\u002Fzenodo.org\u002Frecords\u002F8278877)\n\n**Rationally seeded computational protein design**\nKatherine I. Albanese, Rokas Petrenas, Fabio Pirro, Elise A. Naudin, Ufuk Borucu, William M. Dawson, D. Arne Scott, Graham J. Leggett, Orion D. Weiner, Thomas A. A. Oliver, Derek N. Woolfson\n[bioRxiv 2023.08.25.554789](https:\u002F\u002Fwww.biorxiv.orxg\u002Fcontent\u002F10.1101\u002F2023.08.25.554789v1) • [code](https:\u002F\u002Fgithub.com\u002Fpolizzilab\u002Fdesign_tools)\n\n**Computational design of sequence-specific DNA-binding proteins**\nCameron J Glasscock, Robert Pecoraro, Ryan McHugh, Lindsey A. Doyle, Wei Chen, Olivier Boivin, Beau Lonnquist, Emily Na, Yuliya Politanska, Hugh K Haddox, David Cox, Christoffer Norn, Brian Coventry, Inna Goreshnik, Dionne Vafeados, Gyu Rie Lee, Raluca Gordan, Barry L Stoddard, Frank DiMaio, David Baker\n[bioRxiv 2023.09.20.558720](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.20.558720v1)\u002F[Nat Struct Mol Biol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41594-025-01669-4) • [code](https:\u002F\u002Fgithub.com\u002Fcjg263\u002Fdbp_design)  • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F09\u002F21\u002F2023.09.20.558720\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**Improving protein expression, stability, and function with ProteinMPNN**\nKiera H. Sumida, Reyes Núñez Franco, Indrek Kalvet, Samuel J. Pellock, Basile I. M. Wicky, Lukas F. Milles, Justas Dauparas, Jue Wang, Yakov Kipnis, Noel Jameson, Alex Kang, Joshmyn De La Cruz, Banumathi Sankaran, Asim K Bera, Gonzalo Jimenez Oses, David Baker\n[bioRxiv 2023.10.03.560713](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.03.560713v1)\u002F[J. Am. Chem. Soc. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Fjacs.3c10941) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F10\u002F03\u002F2023.10.03.560713\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**A Suite of Designed Protein Cages Using Machine Learning Algorithms and Protein Fragment-Based Protocols**\nKyle Meador, Roger Castells-Graells, Roman Aguirre, Michael R. Sawaya, Mark A. Arbing, Trent Sherman, Chethaka Senarathne, Todd O. Yeates\n[bioRxiv 2023.10.09.561468](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.09.561468v1) • [code](https:\u002F\u002Fgithub.com\u002Fkylemeador\u002Fsymdesign) • [colab](https:\u002F\u002Fbit.ly\u002Fsymdesign-colab)\n\n**PROTEIN DESIGNER BASED ON SEQUENCE PROFILE USING ULTRAFAST SHAPE RECOGNITION**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=s4mPCrSNUZ)\n\n**Inverse folding for antibody sequence design using deep learning**\nFrédéric A. Dreyer, Daniel Cutting, Constantin Schneider, Henry Kenlay, Charlotte M. Deane\n[arXiv:2310.19513](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.19513)\n\n**De novo design of allosterically switchable protein assemblies**\nArvind Pillai, Abbas Idris, Annika Philomin, Connor Weidle, Rebecca Skotheim, Philip J. Y. Leung, Adam Broerman, Cullen Demakis, Andrew J. Borst, Florian Praetorius, David Baker\n[bioRxiv 2023.11.01.565167](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.01.565167v1)\u002F[Nature (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-07813-2) • [code](https:\u002F\u002Fgithub.com\u002Farvind-pillai\u002Fswitchable_rings) • [data](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F11\u002F02\u002F2023.11.01.565167\u002FDC1\u002Fembed\u002Fmedia-1.zip)\n\n**ProRefiner: an entropy-based refining strategy for inverse protein folding with global graph attention**\nXinyi Zhou, Guangyong Chen, Junjie Ye, Ercheng Wang, Jun Zhang, Cong Mao, Zhanwei Li, Jianye Hao, Xingxu Huang, Jin Tang, Pheng Ann Heng\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-43166-6) • [Supplementary](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41467-023-43166-6\u002FMediaObjects\u002F41467_2023_43166_MOESM1_ESM.pdf) • [code](https:\u002F\u002Fzenodo.org\u002Frecords\u002F10030882)\n\n**Engineered immunogens to elicit antibodies against conserved coronavirus epitopes**\nA. Brenda Kapingidza, Daniel J. Marston, Caitlin Harris, Daniel Wrapp, Kaitlyn Winters, Dieter Mielke, Lu Xiaozhi, Qi Yin, Andrew Foulger, Rob Parks, Maggie Barr, Amanda Newman, Alexandra Schäfer, Amanda Eaton, Justine Mae Flores, Austin Harner, Nicholas J. Catanzaro Jr., Michael L. Mallory, Melissa D. Mattocks, Christopher Beverly, Brianna Rhodes, Katayoun Mansouri, Elizabeth Van Itallie, Pranay Vure, Brooke Dunn, Taylor Keyes, Sherry Stanfield-Oakley, Christopher W. Woods, Elizabeth A. Petzold, Emmanuel B. Walter, Kevin Wiehe, Robert J. Edwards, David C. Montefiori, Guido Ferrari, Ralph Baric, Derek W. Cain, Kevin O. Saunders, Barton F. Haynes & Mihai L. Azoitei\n[Nat Commun 14, 7897 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-43638-9) • [code](https:\u002F\u002Fgithub.com\u002FAzoiteiLab\u002FS2-scaffold-scripts)\n\n**DNDesign: Enhancing Physical Understanding of Protein Inverse Folding Model via Denoising**\nYouhan Lee, Jaehoon Kim\n[bioRxiv 2023.12.05.570298](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.05.570298v1)\n\n**In vitro validated antibody design against multiple therapeutic antigens using generative inverse folding**\nAmir Shanehsazzadeh, Julian Alverio, George Kasun, Simon Levine, Jibran A Khan, Chelsea Chung, Nicolas Diaz, Breanna K Luton, Ysis Tarter, Cailen McCloskey, Katherine B Bateman, Hayley Carter, Dalton Chapman, Rebecca Consbruck, Alec Jaeger, Christa Kohnert, Gaelin Kopec-Belliveau, John M Sutton, Zheyuan Guo, Gustavo Canales, Kai Ejan, Emily Marsh, Alyssa Ruelos, Rylee Ripley, Brooke Stoddard, Rodante Caguiat, Kyra Chapman, Matthew Saunders, Jared Sharp, Douglas Ganini da Silva, Audree Feltner, Jake Ripley, Megan E Bryant, Danni Castillo, Joshua Meier, Christian M Stegmann, Katherine Moran, Christine Lemke, Shaheed Abdulhaqq, Lillian R Klug, Sharrol Bachas\n[bioRxiv 2023.12.08.570889](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.08.570889v1)\n\n**SPDesign: protein sequence designer based on structural sequence profile using ultrafast shape recognition**\nHui Wang, Dong Liu, Kailong Zhao, Yajun Wang, Guijun Zhang\n[bioRxiv 2023.12.14.571651](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.14.571651v1)\u002F[Briefings in Bioinformatics 25.3 (2024): bbae146](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F3\u002Fbbae146\u002F7642672) • [website](http:\u002F\u002Fzhanglab-bioinf.com\u002FSPDesign\u002F)\n\n**De novo design of diverse small molecule binders and sensors using Shape Complementary Pseudocycles**\nLinna An, Meerit Said, Long Tran, Sagardip Majumder, Inna Goreshnik, Gyu Rie Lee, David Juergens, Justas Dauparas, Ivan Anishchenko, Brian Coventry, Asim K Bera, Alex Kang, Paul M Levine, Valentina Alvarez, Arvindd Pillai, Christoffer Norn, David Feldman, Dmitri Zorine, Derrick R Hicks, Xinting Li, Mariana Garcia Sanchez, Dionne K Vafeados, Patrick J Salveson, Anastassia A Vorobieva, David Baker\n[bioRxiv 2023.12.20.572602](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.20.572602v1)\u002F[Science385,276-282(2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adn3780) • [code1](https:\u002F\u002Fgithub.com\u002FLAnAlchemist\u002FPseudocycle_small_molecule_binder), [code2](https:\u002F\u002Fgithub.com\u002Fiamlongtran\u002Fpseudocycle_paper), [code3](https:\u002F\u002Fgithub.com\u002Ffeldman4\u002Fngs_app)\n\n**Atomic context-conditioned protein sequence design using LigandMPNN**\nJustas Dauparas, Gyu Rie Lee, Robert Pecoraro, Linna An, Ivan Anishchenko, Cameron Glasscock, D. Baker\n[bioRxiv 2023.12.22.573103](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.22.573103v1)\u002F[Nat Methods (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-025-02626-1) • [code](https:\u002F\u002Fgithub.com\u002Fdauparas\u002FLigandMPNN)\n\n**Structure-conditioned masked language models for protein sequence design generalize beyond the native sequence space**\nDeniz Akpinaroglu, Kosuke Seki, Amy Guo, Eleanor Zhu, Mark J. S. Kelly, Tanja Kortemme\n[bioRxiv 2023.12.15.571823](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.15.571823v1) • [code](https:\u002F\u002Fgithub.com\u002Fdakpinaroglu\u002FFrame2seq)\n\n**ProteinMPNN Recovers Complex Sequence Properties of Transmembrane β-Barrels**\nMarissa D Dolorfino, Anastassia A Vorobieva\n[bioRxiv 2024.01.16.575764](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.01.16.575764v1) • [code](https:\u002F\u002Fgithub.com\u002Fmarissadolorfino2024\u002FProteinMPNN-TMB-Design.git)\n\n**DIProT: A deep learning based interactive toolkit for efficient and effective Protein design**\nHe, Jieling, Wenxu Wu, and Xiaowo Wang\n[Synthetic and Systems Biotechnology (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2405805X24000115)\n\n**Blueprinting extendable nanomaterials with standardized protein blocks**\nTimothy F. Huddy, Yang Hsia, Ryan D. Kibler, Jinwei Xu, Neville Bethel, Deepesh Nagarajan, Rachel Redler, Philip J. Y. Leung, Connor Weidle, Alexis Courbet, Erin C. Yang, Asim K. Bera, Nicolas Coudray, S. John Calise, Fatima A. Davila-Hernandez, Hannah L. Han, Kenneth D. Carr, Zhe Li, Ryan McHugh, Gabriella Reggiano, Alex Kang, Banumathi Sankaran, Miles S. Dickinson, Brian Coventry, T. J. Brunette, Yulai Liu, Justas Dauparas, Andrew J. Borst, Damian Ekiert, Justin M. Kollman, Gira Bhabha & David Baker\n[Nature (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-07188-4) • [RosettaScripts](https:\u002F\u002Fgithub.com\u002Ftfhuddy\u002F2023-manuscript-materials)\n\n**All-atom protein sequence design based on geometric deep learning**\nJiale Liu, Zheng Guo, Changsheng Zhang, Luhua Lai\n[bioRxiv 2024.03.18.585651](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.18.585651v1)\u002F[Angew. Chem. Int. Ed. 2024](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fanie.202411461) • [code](https:\u002F\u002Fgithub.com\u002FPKUliujl\u002FGesSeqBuilder)\n\n**Graphormer supervised de novo protein design method and function validation**\nJunxi Mu, Zhengxin Li, Bo Zhang, Qi Zhang, Jamshed Iqbal,   Abdul Wadood, Ting Wei, Yan Feng, Hai-Feng Chen\n[Briefings in Bioinformatics 25.3 (2024): bbae135](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F3\u002Fbbae135\u002F7638270) • [code](https:\u002F\u002Fgithub.com\u002Fdecodermu\u002FGPD)\n\n**The Damietta Server: a comprehensive protein design toolkit**\nIwan Grin, Kateryna Maksymenko, Tobias Wörtwein, Mohammad ElGamacy\n[Nucleic Acids Research, 2024;, gkae297](https:\u002F\u002Facademic.oup.com\u002Fnar\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fnar\u002Fgkae297\u002F7658041) • [website](https:\u002F\u002Fdamietta.de\u002F) • ProteinMPNN-based • [news](https:\u002F\u002Fcbirt.net\u002Fprotein-design-made-easy-with-damietta-server-a-comprehensive-toolkit\u002F), [news2](https:\u002F\u002Fwww.innovations-report.com\u002Flife-sciences\u002Ftoolkit-makes-protein-design-faster-and-more-accessible\u002F)\n\n**Exploring the Potential of Structure-Based Deep Learning Approaches for T cell Receptor Design**\nHelder V. Ribeiro-Filho, Gabriel E. Jara, João V. S. Guerra, Melyssa Cheung, Nathaniel R. Felbinger, José G. C. Pereira, Brian G. Pierce, Paulo S. Lopes-de-Oliveira\n[bioRxiv 2024.04.19.590222](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.19.590222v1) • [code](https:\u002F\u002Fgithub.com\u002FLBC-LNBio\u002FESMIFDesign), [code2](https:\u002F\u002Fgithub.com\u002Fpiercelab\u002Ftcrmodel2\u002F)\n\n**SurfPro: Functional Protein Design Based on Continuous Surface**\nZhenqiao Song, Tinglin Huang, Lei Li, Wengong Jin\n[arXiv:2405.06693](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.06693) • ProteinMPNN-based\n\n**Computational Design of Myoglobin-based Carbene Transferases for Monoterpene Derivatization**\nYiyang Sun, Yinian Tang, Jing Zhou, Bingchen Guo, Feiyan Yuan, Bo Yao, Yang Yu, Chun Li\n[Biochemical and Biophysical Research Communications (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0006291X2400696X) • [code](https:\u002F\u002Fgithub.com\u002Fyangyu1-github\u002FMbDesignMPNN) • LigandMPNN-based\n\n**UniIF: Unified Molecule Inverse Folding**\nZhangyang Gao, Jue Wang, Cheng Tan, Lirong Wu, Yufei Huang, Siyuan Li, Zhirui Ye, Stan Z. Li\n[arXiv:2405.18968](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.18968)\n\n**Integrating MHC Class I visibility targets into the ProteinMPNN protein design process**\nHans-Christof Gasser, Diego A. Oyarzún, Javier Antonio Alfaro, Ajitha Rajan\n[bioRxiv 2024.06.04.597365](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.04.597365v1)\n\n**A Top-Down Design Approach for Generating a Peptide PROTAC Drug Targeting Androgen Receptor for Androgenetic Alopecia Therapy**\nBohan Ma, Donghua Liu, Zhe Wang, Dize Zhang, Yanlin Jian, Kun Zhang, Tianyang Zhou, Yibo Gao, Yizeng Fan, Jian Ma, Yang Gao, Yule Chen, Si Chen, Jing Liu, Xiang Li, and Lei Li\n[Journal of Medicinal Chemistry (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jmedchem.4c00828)\n\n**Improving Inverse Folding models at Protein Stability Prediction without additional Training or Data**\nOliver Dutton, Sandro Bottaro, Michele Invernizzi, Istvan Redl, Albert Chung, Carlo Fisicaro, Fabio Airoldi, Stefano Ruschetta, Louie Henderson, Benjamin MJ Owens, Patrik Foerch, Kamil Tamiola\n[bioRxiv 2024.06.15.599145](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.15.599145v1) • ProteinMPNN\u002FESMIF-based\n\n**Kernel-Based Evaluation of Conditional Biological Sequence Models**\nPierre Glaser, Steffanie Paul, Alissa M Hummer, Charlotte Deane, Debora Susan Marks, Alan Nawzad Amin\n[Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15678-15705, 2024](https:\u002F\u002Fproceedings.mlr.press\u002Fv235\u002Fglaser24a.html) • ProteinMPNN-based\n\n**Design of intrinsically disordered region binding proteins**  \nKejia Wu, Hanlun Jiang, Derrick R. Hicks, Caixuan Liu, Edin Muratspahić, Theresa A. Ramelot, Yuexuan Liu, Kerrie McNally, Sebastian Kenny, Andrei Mihut, Amit Gaur, Brian Coventry, Wei Chen, Asim K. Bera, Alex Kang, Stacey Gerben, Mila Ya-Lan Lamb, Analisa Murray, Xinting Li, Madison A. Kennedy, Wei Yang, Zihao Song, Gudrun Schober, Stuart M. Brierley, John O’Neill, Michael H. Gelb, Gaetano T. Montelione, Emmanuel Derivery, David Baker  \n[bioRxiv 2024.07.15.603480](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.15.603480v3)\u002F[Science389,eadr8063(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adr8063)\n\n**Deep learning guided design of dynamic proteins**\nAmy B. Guo, Deniz Akpinaroglu, Mark J.S. Kelly, Tanja Kortemme\n[bioRxiv 2024.07.17.603962](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.17.603962v1)\u002F[Science388,eadr7094(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adr7094) • [code](https:\u002F\u002Fgithub.com\u002Famyguo1997\u002Fdynamic_protein_design) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F19\u002F2024.07.17.603962\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**CodonMPNN for Organism Specific and Codon Optimal Inverse Folding**\nHannes Stark, Umesh Padia, Julia Balla, Cameron Diao, George Church\n[arXiv:2409.17265](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.17265) • ProteinMPNN-based • [code](https:\u002F\u002Fgithub.com\u002FHannesStark\u002FCodonMPNN)\n\n**Exploring the potential of structure-based deep learning approaches for T cell receptor design**\nHelder V. Ribeiro-Filho, Gabriel E. Jara, João V. S. Guerra, Melyssa Cheung,Nathaniel R. Felbinger, José G. C. Pereira, Brian G. Pierce, Paulo S. Lopes-de-Oliveira\n[PLoS Comput Biol 20(9)](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1012489) • ProteinMPNN-based • ESM-based\n\n**ProteusAI: An Open-Source and User-Friendly Platform for Machine Learning-Guided Protein Design and Engineering**\nJonathan Funk, Laura Machado, Samuel A. Bradley, Marta Napiorkowska, Rodrigo Gallegos-Dextre, Liubov Pashkova, Niklas G. Madsen, Henry Webel, Patrick Victor Phaneuf, Timothy P. Jenkins, Carlos G. Acevedo-Rocha Sr\n[bioRxiv 2024.10.01.616114](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.01.616114v1) • ProteinMPNN-based • ESM-based\n\n**Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization**\nRyan Park, Darren J. Hsu, C. Brian Roland, Maria Korshunova, Chen Tessler, Shie Mannor, Olivia Viessmann, Bruno Trentini\n[arXiv:2410.19471](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.19471)\n\n**Computational design of developable therapeutic antibodies: efficient traversal of binder landscapes and rescue of escape mutations**\nFrédéric A. Dreyer, Constantin Schneider, Aleksandr Kovaltsuk, Daniel Cutting, Matthew J. Byrne, Daniel A. Nissley, Newton Wahome, Henry Kenlay, Claire Marks, David Errington, Richard J. Gildea, David Damerell, Pedro Tizei, Wilawan Bunjobpol, John F. Darby, Ieva Drulyte, Daniel L. Hurdiss, Sachin Surade, Douglas E. V. Pires, Charlotte M. Deane\n[bioRxiv 2024.10.03.616038](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.03.616038v1) • [code](https:\u002F\u002Fgithub.com\u002FExscientia\u002Fab-characterisation) • AbMPNN-based\n\n**BC-Design: A Biochemistry-Aware Framework for Inverse Protein Design**  \nXiangru Tang, Xinwu Ye, Fang Wu, Yimeng Liu, Anna Su, Antonia Panescu, Guanlue Li, Daniel Shao, Dong Xu, Mark Gerstein  \n[bioRxiv 2024.10.28.620755](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.28.620755v3)\n\n**State-specific Peptide Design Targeting G Protein-coupled Receptors**\nYang Xue, Jun Li, Hong Wang, Jianguo Hu, Zhi Zheng, Jingzhou He, Huanzhang Gong, Xiangqun Li, Xiaonan Zhang, Xiaomin Fang\n[bioRxiv 2024.11.27.625792](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.27.625792v2)\u002F[Journal of Chemical Information and Modeling (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c00884) • ProteinMPNN-based\n\n**Computer-guided design of Z domain peptides with improved inhibition of VEGF**\nCarsten Geist, Abibe Useini, Aleksandr Kazimir, Richy Kümpfel, Jens Meiler, Christina Lamers, Stefan Kalkhof, Georg Künze\n[bioRxiv 2024.11.29.626075](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.29.626075v1) [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F30\u002F2024.11.29.626075\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • ProteinMPNN-based\n\n**HyperMPNN – A general strategy to design thermostable proteins learned from hyperthermophiles**\nMoritz Ertelt, Phillip Schlegel, Max Beining, Leonard Kaysser, Jens Meiler, Clara T. Schoeder\n[bioRxiv 2024.11.26.625397](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.26.625397v1) • [code](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002FHyperMPNN) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F01\u002F2024.11.26.625397\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**IgDesign: In vitro validated antibody design against multiple therapeutic antigens using inverse folding**\nAmir Shanehsazzadeh, Julian Alverio, George Kasun, Simon Levine, Ido Calman, Jibran A. Khan, Chelsea Chung, Nicolas Diaz, Breanna K. Luton, Ysis Tarter, Cailen McCloskey, Katherine B. Bateman, Hayley Carter, Dalton Chapman, Rebecca Consbruck, Alec Jaeger, Christa Kohnert, Gaelin Kopec-Belliveau, John M. Sutton, Zheyuan Guo, Gustavo Canales, Kai Ejan, Emily Marsh, Alyssa Ruelos, Rylee Ripley, Brooke Stoddard, Rodante Caguiat, Kyra Chapman, Matthew Saunders, Jared Sharp, Douglas Ganini da Silva, Audree Feltner, Jake Ripley, Megan E. Bryant, Danni Castillo, Joshua Meier, Christian M. Stegmann, Katherine Moran, Christine Lemke, Shaheed Abdulhaqq, Lillian R. Klug, Sharrol Bachas\n[bioRxiv 2023.12.08.570889](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.08.570889v1) • [code](https:\u002F\u002Fgithub.com\u002FAbSciBio\u002Figdesign)\n\n**Learning to engineer protein flexibility**\nPetr Kouba, Joan Planas-Iglesias, Jiri Damborsky, Jiri Sedlar, Stanislav Mazurenko, Josef Sivic\n[arXiv:2412.18275](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.18275) • [code](https:\u002F\u002Fgithub.com\u002FKoubaPetr\u002FFlexpert)\n\n**AI.zymes – A modular platform for evolutionary enzyme design**\nLucas P. Merlicek, Jannik Neumann, Abbie Lear, Vivian Degiorgi, Moor de Waal, Tudor-Stefan Cotet, Adrian J. Mulholland, H. Adrian Bunzel\n[bioRxiv 2025.01.18.633707](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.18.633707v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F01\u002F22\u002F2025.01.18.633707\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**AI-assisted protein design to rapidly convert antibody sequences to intrabodies targeting diverse peptides and histone modifications**\nGabriel Galindo, Daiki Maejima, Jacob DeRoo, Scott R. Burlingham, Gretchen Fixen, Tatsuya Morisaki, Hallie P. Febvre, Ryan Hasbrook, Ning Zhao, Soham Ghosh, E. Handly Mayton, Christopher D. Snow, Brian J. Geiss, Yasuyuki Ohkawa, Yuko Sato, Hiroshi Kimura, Timothy J. Stasevich\n[bioRxiv 2025.02.06.636921](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.06.636921v2)\u002F[Sci. Adv.12,eadx8352(2026)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.adx8352) • [code](https:\u002F\u002Fgithub.com\u002Fjbderoo\u002FscFv_Pmpnn_AF2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F02\u002F09\u002F2025.02.06.636921\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • ProteinMPNN-based\n\n**Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN**\nRichard W. Shuai, Talal Widatalla, Po-Ssu Huang, Brian L. Hie\n[bioRxiv 2025.02.13.637498](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.13.637498v1) • [code](https:\u002F\u002Fgithub.com\u002Frichardshuai\u002Ffampnn)\n\n**Fast and Accurate Antibody Sequence Design via Structure Retrieval**\nXingyi Zhang, Kun Xie, Ningqiao Huang, Wei Liu, Peilin Zhao, Sibo Wang, Kangfei Zhao, Biaobin Jiang\n[arXiv:2502.19395](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19395)\n\n**Enhancing Functional Protein Design Using Heuristic Optimization and Deep Learning for Anti‐Inflammatory and Gene Therapy Applications**\nPatat, Ayşenur Soytürk, and Özkan Ufuk Nalbantoğlu\n[Proteins: Structure, Function, and Bioinformatics (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fprot.26810) • [code](https:\u002F\u002Fgithub.com\u002Faysenursoyturk\u002FHMHO)\n\n**ProDualNet: Dual-Target Protein Sequence Design Method Based on Protein Language Model and Structure Model**\nLiu Cheng, Ting Wei, Xiaochen Cui, Haifeng Chen, Zhangsheng Yu\n[bioRxiv 2025.02.28.640919](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.28.640919v1)\u002F[Briefings in Bioinformatics, July 2025, bbaf391](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F26\u002F4\u002Fbbaf391\u002F8241296) • [code](https:\u002F\u002Fgithub.com\u002Fchengliu97\u002FProDualNet)\n\n**CHIEF: An Attention-based Ensemble Learning Framework for Functional Protein Design**\nZilong Geng, Yuze Wang, Tingting Liu, Ao Tan, Shuo Wu, Xiaoling Guo, Ruogu Li, Xumin Hou, Kun Sun, LianPin Wu, Qinghua Cui, Lintai Da, Zhiyuan Ma, Honglin Li, Bing Zhang\n[bioRxiv 2025.03.07.641005](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.07.641005v2) • ProteinMPNN-based • ESM-IF-based • Frame2seq-based • PiFold-based\n\n**Tuning ProteinMPNN to reduce protein visibility via MHC Class I through direct preference optimization**\nHans-Christof Gasser, Diego A Oyarzún, Javier Alfaro, Ajitha Rajan\n[Protein Engineering, Design and Selection (2025)](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzaf003\u002F8082933) • [code](https:\u002F\u002Fgithub.com\u002Fhcgasser\u002FCAPE_MPNN) • ProteinMPNN-based\n\n**AI-Driven Efficient De Novo design of GLP-1RAs with Extended Half-Life and Enhanced Efficacy**\nTing Wei, Xiaochen Cui, Jiahui Lin, Zhuoqi Zheng, Taiying Cui, Liu Cheng, Xiaoqian Lin, Junjie Zhu, Xuyang Ran, Xiaohun Hong, Zhangsheng Yu, Haifeng Chen\n[bioRxiv 2025.03.26.645438](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.26.645438v1) • ProteinMPNN-based\n\n**A novel decoding strategy for ProteinMPNN to design with less MHC Class I immune-visibility**\nHans-Christof Gasser, Ajitha Rajan, Javier A. Alfaro\n[bioRxiv 2025.04.14.648837](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.14.648837v1) • ProteinMPNN-based\n\n**Zero-shot design of drug-binding proteins via neural selection-expansion**  \nBenjamin Fry, Kaia Slaw, Nicholas F. Polizzi  \n[bioRxiv 2025.04.22.649862](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.22.649862v1) • [code](https:\u002F\u002Fgithub.com\u002Fpolizzilab\u002FLASErMPNN)\n\n**Conformation-specific Design: a New Benchmark and Algorithm with Application to Engineer a Constitutively Active Map Kinase**  \nJacob A. Stern, Siba Alharbi, Anandsukeerthi Sandholu, Stefan T. Arold, Dennis Della Corte  \n[bioRxiv 2025.04.23.650138](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.23.650138v1) • [code](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fcs_design) • [dataset](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fmotif_div)\n\n**AI. zymes–A modular platform for evolutionary enzyme design**  \nLucas P. Merlicek, Jannik Neumann, Abbie Lear, Vivian Degiorgi, Moor M. de Waal, Tudor-Stefan Cotet, Adrian J. Mulholland, Adrian Bunzel  \n[Angewandte Chemie International Edition (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fanie.202507031) • [code](https:\u002F\u002Fgithub.com\u002Fbunzela\u002FAIzymes) • ProteinMPNN-based\n\n**Design of overlapping genes using deep generative models of protein sequences**  \nGun Woo Byeon, Marc Expòsit, David Baker, Georg Seelig  \n[bioRxiv 2025.05.06.652464](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.06.652464v1) • [code](https:\u002F\u002Fgithub.com\u002Fgwbyeon\u002FOLG-design) • ProteinMPNN-based\n\n**De novo design of porphyrin-containing proteins as efficient and stereoselective catalysts**  \nKaipeng Hou, Wei Huang, Miao Qi, Thomas H. Tugwell, Turki M. Alturaifi, Yuda Chen, Xingjie Zhang, Lei Lu, Samuel I. Mann, Peng Liu, Yang Yang, and William F. DeGrado  \n[Science 388.6747 (2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002Ffull\u002F10.1126\u002Fscience.adt7268) • LigandMPNN-based\n\n**Adapting ProteinMPNN for antibody design without retraining**  \nDiego del Alamo, Rahel Frick, Daphne Truan, Joel D Karpiak  \n[bioRxiv 2025.05.09.653228](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.09.653228v1)\n\n**HighMPNN: A Graph Neural Network Approach for Structure-Constrained Cyclic Peptide Sequence Design**  \nWen Xu, Chengyun Zhang ,Tianfeng Shang ,Qingyi Mao ,Hongliang Duan  \n[ChemRxiv. 2025](https:\u002F\u002Fchemrxiv.org\u002Fengage\u002Fchemrxiv\u002Farticle-details\u002F6826dcef927d1c2e661210c2)\n\n**Computational design of dynamic biosensors for emerging synthetic opioids**  \nAlison C. Leonard, Chase Lenert-Mondou, Rachel Chayer, Samuel Swift, Zachary T. Baumer, Ryan Delaney, Anika J. Friedman, Nicholas R. Robertson, Norman Seder, Jordan Wells, Lindsey M. Whitmore, Sean R. Cutler, Michael R. Shirts, Ian Wheeldon, Timothy A. Whitehead  \n[bioRxiv 2025.05.15.654300](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.15.654300v1) • LigandMPNN-based\n\n**Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling**  \nXiangxin Zhou, Mingyu Li, Yi Xiao, Jiahan Li, Dongyu Xue, Zaixiang Zheng, Jianzhu Ma, Quanquan Gu  \n[arXiv:2505.21452](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21452)\n\n**De novo design of high-affinity miniprotein binders targeting Francisella tularensis virulence factor**  \nGizem Gokce-Alpkilic, Buwei Huang, Andi Liu, Lieselotte S.M. Kreuk, Yaxi Wang, Victor Adebomi, Yensi Flores Bueso, Asim K. Bera, Alex Kang, Stacey R. Gerben, Stephen Rettie, Dionne K. Vafeados, Nicole Roullier, Inna Goreshnik, Xinting Li, David Baker, Joshua J. Woodward, Joseph D. Mougous, Gaurav Bhardwaj  \n[bioRxiv 2025.07.02.662053](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.02.662053v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F05\u002F2025.07.02.662053\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F05\u002F2025.07.02.662053\u002FDC2\u002Fembed\u002Fmedia-2.zip) • ProteinMPNN-based\n\n**A Computational Workflow for Structure-Guided Design of Potent and Selective Kinase Peptide Substrates**  \nAbeeb A. Yekeen, Cynthia J. Meyer, Melissa McCoy, Bruce Posner, Kenneth D. Westover  \n[bioRxiv 2025.07.04.663216](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.04.663216v1) • ProteinMPNN-based\n\n**Fully functional AAV viral vectors with highly altered structural cores and subunit interfaces using ProteinMPNN**  \nZiyu Jiang, Sirimar Laosinwattana, Paul A. Dalby  \n[bioRxiv 2025.07.24.666527](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.24.666527v1)\n\n**Computational design of bifaceted protein nanomaterials**  \nSanela Rankovic, Kenneth D. Carr, Justin Decarreau, Rebecca Skotheim, Ryan D. Kibler, Sebastian Ols, Sangmin Lee, Jung-Ho Chun, Marti R. Tooley, Justas Dauparas, Helen E. Eisenach, Matthias Glögl, Connor Weidle, Andrew J. Borst, David Baker & Neil P. King  \n[Nat. Mater. (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41563-025-02295-7)\n\n**Multi-state Protein Design with DynamicMPNN**  \nAlex Abrudan, Sebastian Pujalte Ojeda, Chaitanya K. Joshi, Matthew Greenig, Felipe Engelberger, Alena Khmelinskaia, Jens Meiler, Michele Vendruscolo, Tuomas P. J. Knowles  \n[arXiv:2507.21938](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.21938) • [code](https:\u002F\u002Fgithub.com\u002FAlex-Abrudan\u002FDynamicMPNN)\n\n**De Novo Design of High-Performance Cortisol Luminescent Biosensors**\nJulie Yi-Hsuan Chen, Xue Peng, Chenggang Xi, Gyu Rie Lee, David Baker, Andy Hsien-Wei Yeh  \n[J. Am. Chem. Soc](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Fjacs.5c05004)\n\n**Accelerating protein design by scaling experimental characterization**  \nJason Qian, Lukas F. Milles, Basile I. M. Wicky, Amir Motmaen, Xinting Li, Ryan D. Kibler, Lance Stewart, David Baker  \n[bioRxiv 2025.08.05.668824](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.05.668824v1) • [code](https:\u002F\u002Fgithub.com\u002Fbwicky\u002FSAPP_DMX)\n\n**AI-Driven De Novo Design of Ultra Long-Acting GLP-1 Receptor Agonists**  \nTing Wei, Jiating Ma, Xiaochen Cui, Jiahui Lin, Zhuoqi Zheng, Liu Cheng, Taiying Cui, Xiaoqian Lin, Junjie Zhu, Xuyang Ran, Xiaokun Hong, Luke Johnston, Zhangsheng Yu, Haifeng Chen  \n[Advanced science (Weinheim, Baden-Wurttemberg, Germany)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202507044) • ProteinMPNN-based\n\n**From sequence to scaffold: computational design of protein nanoparticle vaccines from AlphaFold2-predicted building blocks**  \nCyrus M. Haas, Naveen Jasti, Annie Dosey, Joel D. Allen, Rebecca Gillespie, Jackson McGowan, Elizabeth M. Leaf, Max Crispin, Cole A. DeForest, Masaru Kanekiyo, Neil P. King  \n[bioRxiv 2025.08.20.671178](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.20.671178v1)\u002F[Proceedings of the National Academy of Sciences 122.45 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2409566122) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F08\u002F20\u002F2025.08.20.671178\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**De novo design of light-responsive protein–protein interactions enables reversible formation of protein assemblies**  \nBowen Yu, Jiao Liu, Zhanyuan Cui, Chu Wang, Peipei Chen, Chentong Wang, Yanzhe Zhang, Xingxing Zhu, Ze Zhang, Shichao Li, Jinheng Pan, Mingqi Xie, Huaizong Shen & Longxing Cao  \n[Nat. Chem. (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41557-025-01929-2) • [code](https:\u002F\u002Fgithub.com\u002FLongxingLab\u002FNCAA_Light_Assembly)\n\n**Multi-objective optimization for designing structurally similar proteins with diverse sequences**  \nRyo Akiba, Yoshitaka Moriwaki, Ryuichiro Ishitani, Naruki Yoshikawa  \n[bioRxiv 2025.09.13.676063](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.13.676063v1) • ProteinMPNN-based\n\n**Ensemble-conditioned protein sequence design with Caliby**  \nRichard W. Shuai, Tianyu Lu, Subhang Bhatti, Petr Kouba, Po-Ssu Huang  \n[bioRxiv 2025.09.30.679633](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.30.679633v3) • [code](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fcaliby)\n\n**De novo designed voltage-gated anion channels suppress neuron firing**  \nChen Zhou, Huican Li, Jiaxing Wang, Cheng Qian, Hui Xiong, Zhilin Chu, Qiming Shao, Xuan Li, Shijin Sun, Ke Sun, Aiqin Zhu, Jiawei Wang, Xueqin Jin, Fan Yang, Tamer M. Gamal El-Din, Bo Li, Jing Huang, Kun Wu, Peilong Lu  \n[Cell(2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Fabstract\u002FS0092-8674(25)01091-8)\n\n**AI-Guided Hydrophobic Core Design of Robust Six-Helix Bundle Proteins**  \nYinying Meng, Guojin Tang, Ruishi Wang, Bin Zheng, Yuanhao Liu, Hantian Zhang, Peng Zheng  \n[ACS Nano .5c13783](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facsnano.5c13783) • ProteinMPNN-based\n\n**De Novo Design of High‐Affinity Miniprotein Binders Targeting Francisella Tularensis Virulence Factor**  \nGizem Gokce-Alpkilic, Buwei Huang, Andi Liu, Lieselotte S.M. Kreuk, Yaxi Wang, Victor Adebomi, Yensi Flores Bueso, Asim K. Bera, Alex Kang, Stacey R. Gerben, Stephen Rettie, Dionne K. Vafeados, Nicole Roullier, Inna Goreshnik, Xinting Li, David Baker, Joshua J. Woodward, Joseph D. Mougous, Gaurav Bhardwaj  \n[Angewandte Chemie International Edition (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fanie.202516058) • ProteinMPNN-based\n\n**Targeting peptide-MHC complexes with designed T cell receptors and antibodies**  \nAmir Motmaen, Kevin M Jude, Nan Wang, Anastasia Minervina, David Feldman, Mauriz A Lichtenstein, Abishai Ebenezer, Colin Correnti, Paul G Thomas, K. Christopher Garcia, David Baker, Philip Bradley  \n[bioRxiv 2025.11.19.689381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.19.689381v1) • ProteinMPNN-based\n\n**Computational Design and Glycoengineering of Interferon-Lambda for Nasal Prophylaxis Against Respiratory Viruses**  \nJeongwon Yun,  Seungju Yang,  Jae Hyuk Kwon,  Luiz Felipe Vecchietti,  Ji Hyun Choi,  Mi-ra Choi,  Keun Bon Ku,  Hyun-Joo Ro,  Kyun-Do Kim,  Meeyoung Cha,  Hyun Jung Chung,  Ji Eun Oh,  Ho Min Kim  \n[Adv. Sci. (2025)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202506764) • ProteinMPNN-based\n\n**De novo design of small molecule–regulated protein oligomers**  \nQihan Jin, Yukai Wang, Dachuan Chen, Jinyang Liao, Zhanyuan Cui, Yuxuan Fan, Anping Zeng, Mingqi Xie, Longxing Cao  \n[Science391,eady6017(2026)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.ady6017) • [code](https:\u002F\u002Fgithub.com\u002FLongxingLab\u002FLigand_Induced_Oligomer)\n\n**De novo design of dual-topology membrane transporters**  \nXi Chen, Xiaofeng Zhou, Jiawei Zhou, Tengyu Xie, Yaning Li, Yuxuan Yan, Jing Huang, Zibo Chen, Dan Ma, Peilong Lu  \n[LangTaoSha Preprint Server](https:\u002F\u002Flangtaosha.org.cn\u002Findex.php\u002Flts\u002Fen\u002Fpreprint\u002Fview\u002F74)\n\n**Origin-1: a generative AI platform for de novo antibody design against novel epitopes**  \nSimon Levine, Jonathan Edward King, Jacob Stern, David Grayson, Raymond Wang, Rui Yin, Umberto Lupo, Paulina Kulyte, Ryan Matthew Brand, Tristan Bertin, Robert Pfingsten, Jovan Cejovic, Chelsea Chung, Breanna K Luton, Andrew Hagemann, Robel Haile, Elliot Medina, Pankaj Panwar, Oleksii Dubrovskyi, Chase LaCombe, Zahra Anderson, Derrik Mildh, Scott Benjamin, Joe Kaiser, Joseph Ferron, Marta Sarrico, Alexandria Kershner, Apurva Mishra, Kai R Ejan, Emily K Marsh, Paul Bringas, Phetsamay Vilaychack, Kyra Chapman, Jacob Ripley, Muttappa Gowda, Kathryn M Collins, Cailen M McCloskey, Jeremiah S Joseph, Rylee Ripley, Shaheed A Abdulhaqq, Audree Feltner, Michael Guerin, Jeffrey Goby, Jesse Hendricks, Danielle Castillo, Sean McClain, Douglas Ganini, Derek Shpiel, James Mategko, Eder Cruz Garcia, Masoud Zabet-Moghaddam, John M Sutton, Zheyuan Guo, Sean M West, Janani S Iyer, Amir Shanehsazzadeh  \n[bioRxiv 2026.01.14.699389](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.14.699389v1) • [code](https:\u002F\u002Fgithub.com\u002FAbSciBio\u002Forigin-1)\n\n**Nab-paclitaxel fused with the de novo designed receptor binder exhibits enhanced tumor targeting and therapeutic efficacy**  \nYuanying Qian, Weikang Yan, Fan Xu, Yali Liu, Fabao Chen, Yue Lu, Zihan Zhang, Ao Gu, Ruobing Yu, Zhen Fang, Yang Yu, Maolan Li, Longxing Cao, Yingbin Liu, Yongning He  \n[bioRxiv 2026.01.28.702218](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.28.702218v1)\n\n**CyclicMPNN: Stable Cyclic Peptide Sequence Generation**  \nAndrew C. Powers, Yanapat Janthana, Parisa Hosseinzadeh  \n[bioRxiv 2026.01.31.702993](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.31.702993v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F31\u002F2026.01.31.702993\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FParisaH-Lab\u002FCyclicMPNN)\n\n**Mesostructured Water Enhances Stability of ProteinMPNN-Designed Ubiquitin-Fold**  \nLu-Yi Chen, Wei-Lin Lu, Tanvi Pathania, I-Hsuan Chu, Meng-Ru Ho, Wei-Chen Chuang, Yuan-Chao Lou, Ta I. Hung, Yohei Miyanoiri, Chia-en A. Chang, Kuen-Phon Wu  \n[J. Am. Chem. Soc. 2026](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacs.5c19875) • ProteinMPNN-based\n\n### 4.6 GAN-based\n\n**De novo protein design for novel folds using guided conditional Wasserstein generative adversarial networks**\nMostafa Karimi, Shaowen Zhu, Yue Cao, Yang Shen\n[Journal of chemical information and modeling 60.12 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.0c00593) • [gcWGAN](https:\u002F\u002Fgithub.com\u002FShen-Lab\u002FgcWGAN)\n\n**HelixGAN: A bidirectional Generative Adversarial Network with search in latent space for generation under constraints**\nXuezhi Xie, Philip M. Kim\n[Machine Learning for Structural Biology Workshop, NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_HelixGAN:_A_bidirectional_Generative.pdf)\u002F[Bioinformatics, 2023;, btad036](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtad036\u002F6991169) • [code](https:\u002F\u002Fgithub.com\u002Fxxiexuezhi\u002Fhelix_gan)\n\n### 4.7 Transformer-based\n\n**Generative models for graph-based protein design**\n[John Ingraham](https:\u002F\u002Fopenreview.net\u002Fprofile?email=ingraham%40csail.mit.edu), Vikas K Garg, Dr.Regina Barzilay, Tommi Jaakkola\n[NeurIPS 2019](https:\u002F\u002Fopenreview.net\u002Fforum?id=ByMEAHrgLB) • [GraphTrans](https:\u002F\u002Fgithub.com\u002Fjingraham\u002Fneurips19-graph-protein-design)\n\n**Fold2Seq: A Joint Sequence (1D)-Fold (3D) Embedding-based Generative Model for Protein Design**\nYue Cao, Payel Das, Vijil Chenthamarakshan, Pin-Yu Chen, Igor Melnyk, Yang Shen\n[International Conference on Machine Learning. PMLR, 2021](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.13058)\n\n**Rotamer-Free Protein Sequence Design Based on Deep Learning and Self-Consistency**\nYufeng Liu, Lu Zhang, Weilun Wang, Min Zhu, Chenchen Wang, Fudong Li, Jiahai Zhang, Houqiang Li, Quan Chen& Haiyan Liu\n[Nature portfolio (2022)](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-1209166\u002Fv1)\u002F[Nature computational science(2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43588-022-00273-6) • [Supplementary](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs43588-022-00273-6\u002FMediaObjects\u002F43588_2022_273_MOESM1_ESM.pdf) • [Comment](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43588-022-00274-5) • [code](https:\u002F\u002Fcodeocean.com\u002Fcapsule\u002F6949436\u002Ftree\u002Fv1)\n\n**A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding**\nMmatthew McPartlon, Ben Lai, Jinbo Xu\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.15.488492v1)\n\n**Learning inverse folding from millions of predicted structures**\nChloe Hsu, Robert Verkuil, Jason Liu, Zeming Lin, Brian Hie, Tom Sercu, Adam Lerer, Alexander Rives\n[bioRxiv (2022)](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2022.04.10.487779) • [esm](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fesm)\n\n**Breaking boundaries in protein design with a new AI model that understands interactions with any kind of molecule**\nLucianoSphere\n[Towards Data Science](https:\u002F\u002Ftowardsdatascience.com\u002Fbreaking-boundaries-in-protein-design-with-a-new-ai-model-that-understands-interactions-with-any-388fd747ee40)\n\n**Accurate and efficient protein sequence design through learning concise local environment of residues**\nBin Huang, Tingwen Fan, Kaiyue Wang, Haicang Zhang, Chungong Yu, Shuyu Nie, Yangshuo Qi, Wei-Mou Zheng, Jian Han, Zheng Fan, Shiwei Sun, Sheng Ye, Huaiyi Yang, Dongbo Bu\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.25.497605v4)\u002F[Bioinformatics 39.3 (2023)](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F39\u002F3\u002Fbtad122\u002F7077134) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F06\u002F30\u002F2022.06.25.497605\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [website](http:\u002F\u002F81.70.37.223) • [code](https:\u002F\u002Fgithub.com\u002Fbigict\u002FProDESIGN-LE)\n\n**PeTriBERT : Augmenting BERT with tridimensional encoding for inverse protein folding and design**\nBaldwin Dumortier, Antoine Liutkus, Clément Carré, Gabriel Krouk\n[bioRxiv 2022.08.10.503344](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.10.503344v1)\n\n**Evolutionary-scale prediction of atomic level protein structure with a language model**\nZeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Robert Verkuil, Ori Kabeli, Yaniv Shmueli, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Salvatore Candido, Alexander Rives\n[bioRxiv 2022.07.20.500902](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.20.500902v2) • [blog](https:\u002F\u002Fai.facebook.com\u002Fblog\u002Fprotein-folding-esmfold-metagenomics\u002F) • [github](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fesm)\n\n**Structure-informed Language Models Are Protein Designers**\nZaixiang Zheng, Yifan Deng, Dongyu Xue, Yi Zhou, Fei YE, Quanquan Gu\n[arXiv:2302.01649](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.01649) • [code::ByProt](https:\u002F\u002Fgithub.com\u002FBytedProtein\u002FByProt)\n\n**Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design**\nKaiyuan Gao, Lijun Wu, Jinhua Zhu, Tianbo Peng, Yingce Xia, Liang He, Shufang Xie, Tao Qin, Haiguang Liu, Kun He, Tie-Yan Liu\n[arXiv:2211.08406](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.08406) • [code](https:\u002F\u002Fgithub.com\u002FKyGao\u002FABGNN)\n\n**A Text-guided Protein Design Framework**\nShengchao Liu, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Anthony Gitter, Chaowei Xiao, Jian Tang, Hongyu Guo, Anima Anandkumar\n[arXiv:2302.04611](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.04611)\u002F[Nat Mach Intell (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01011-z) • [code](https:\u002F\u002Fgithub.com\u002Fchao1224\u002FProteinDT)\n\n**An end-to-end deep learning method for protein side-chain packing and inverse folding**\nMcPartlon, Matthew, and Jinbo Xu\n[Proceedings of the National Academy of Sciences 120.23 (2023)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2216438120) • [code](https:\u002F\u002Fgithub.com\u002FMattMcPartlon\u002FAttnPacker) • [Supplementary](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002Fsuppl\u002F10.1073\u002Fpnas.2216438120\u002Fsuppl_file\u002Fpnas.2216438120.sapp.pdf)\n\n**Context-aware geometric deep learning for protein sequence design**\nLucien Krapp, Fernado Meireles, Luciano Abriata, Matteo Dal Peraro\n[bioRxiv 2023.06.19.545381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.19.545381v1)\u002F[Nature Communications, 2024](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-50571-y) • [code](https:\u002F\u002Fgithub.com\u002FLBM-EPFL\u002FCARBonARa) • [News](https:\u002F\u002Factu.epfl.ch\u002Fnews\u002Fa-new-ai-approach-to-protein-design\u002F)\n\n**De Novo Generation and Prioritization of Target-Binding Peptide Motifs from Sequence Alone**\nSuhaas Bhat, Kalyan Palepu, Vivian Yudistyra, Lauren Hong, Venkata Srikar Kavirayuni, Tianlai Chen, Lin Zhao, Tian Wang, Sophia Vincoff, Pranam Chatterjee\n[bioRxiv 2023.06.26.546591](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.26.546591v1) • [code](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fpepprclip) • [colab](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Fu\u002F0\u002Ffolders\u002F1A4kQXjsG5j3OrO0XQtzBWWZu9Zm7c0ak) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F06\u002F28\u002F2023.06.26.546591\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**ProstT5: Bilingual Language Model for Protein Sequence and Structure Michael Heinzinger**\nKonstantin Weissenow, Joaquin Gomez Sanchez, Adrian Henkel, Martin Steinegger, Burkhard Rost\n[bioRxiv 2023.07.23.550085](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.23.550085v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F07\u002F25\u002F2023.07.23.550085\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fmheinzinger\u002FProstT5)\n\n**De novo Protein Sequence Design Based on Deep Learning and Validation on CalB Hydrolase**\nJunxi Mu, ZhengXin Li, Bo Zhang, Qi Zhang, Jamshed Iqbal, Abdul Wadood, Ting Wei, Yan Feng, Haifeng Chen\n[bioRxiv 2023.08.01.551444](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.01.551444v1) • [code](https:\u002F\u002Fgithub.com\u002Fweitinging\u002FGPD)\n\n**Invariant point message passing for protein side chain packing and design**\nNicholas Z Randolph, Brian Kuhlman\n[bioRxiv 2023.08.03.551328](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.03.551328v1) • [code](https:\u002F\u002Fgithub.com\u002FKuhlman-Lab\u002FPIPPack)\n\n**Atom-by-atom protein generation and beyond with language models**\nDaniel Flam-Shepherd, Kevin Zhu, Alán Aspuru-Guzik\n[arXiv:2308.09482](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.09482)\n\n**SaProt: Protein Language Modeling with Structure-aware Vocabulary**\nJin Su, Chenchen Han, Yuyang Zhou, Junjie Shan, Xibin Zhou, Fajie Yuan\n[bioRxiv 2023.10.01.560349](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.01.560349v5) • [code](https:\u002F\u002Fgithub.com\u002Fwestlake-repl\u002FSaProt)\n\n**SaprotHub: Making Protein Modeling Accessible to All Biologists**\nJin Su, Zhikai Li, Chenchen Han, Yuyang Zhou, Yan He, Junjie Shan, Xibin Zhou, Xing Chang, Shiyu Jiang, Dacheng Ma, The OPMC, Martin Steinegger, Sergey Ovchinnikov,  Fajie Yuan\n[bioRxiv 2024.05.24.595648](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.24.595648)  •  [code](https:\u002F\u002Fgithub.com\u002Fwestlake-repl\u002FSaprotHub) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fwestlake-repl\u002FSaprotHub\u002Fblob\u002Fmain\u002Fcolab\u002FSaprotHub_v2.ipynb)\n\n**AntiFold: Improved antibody structure design using inverse folding**\nMagnus Høie, Alissa Hummer, Tobias Olsen, Morten Nielsen, Charlotte Deane\n[GenBio@NeurIPS2023 Spotlight](https:\u002F\u002Fopenreview.net\u002Fforum?id=bxZMKHtlL6)\u002F[Bioinformatics Advances (2025)](https:\u002F\u002Facademic.oup.com\u002Fbioinformaticsadvances\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioadv\u002Fvbae202\u002F8090019) • [code](https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fdata\u002Fdownloads\u002FAntiFold\u002F), [github](https:\u002F\u002Fgithub.com\u002Foxpig\u002FAntiFold) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1TTfgjoZx3mzF5u4e9b4Un9Y7b_rqXc_4), [website](https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fantifold\u002F)\n\n**MMDesign: Multi-Modality Transfer Learning for Generative Protein Design**\nJiangbin Zheng, Siyuan Li, Yufei Huang, Zhangyang Gao, Cheng Tan, Bozhen Hu, Jun Xia, Ge Wang, Stan Z. Li\n[arXiv preprint arXiv:2312.06297 (2023)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.06297)\n\n**ShapeProt: Top-down Protein Design with 3D Protein Shape Generative Model**\nLee, Youhan, and Jaehoon Kim\n[bioRxiv (2023): 2023-12](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.03.567710v3)\n\n**X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Design**\nEric L. Buehler, Markus J. Buehler\n[arXiv:2402.07148](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.07148) • [code](https:\u002F\u002Fgithub.com\u002FEricLBuehler\u002Fxlora) • [Model & weights](https:\u002F\u002Fhuggingface.co\u002Flamm-mit\u002Fx-lora)\n\n**AntiFold: Improved antibody structure-based design using inverse folding**\nMagnus Haraldson Høie, Alissa Hummer, Tobias H. Olsen, Broncio Aguilar-Sanjuan, Morten Nielsen, Charlotte M. Deane\n[arXiv:2405.03370](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.03370) • [code](https:\u002F\u002Fgithub.com\u002Foxpig\u002FAntiFold) • [website](https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fantifold\u002F) • ESM-IF-based\n\n**Protein Design with StructureGPT: a Deep Learning Model for Protein Structure-to-Sequence Translation**\nNicanor Zalba Sr., Pablo Ursua-Medrano Sr., Humberto Bustince Sr\n[bioRxiv 2024.06.03.597105](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.03.597105v1) • [code](https:\u002F\u002Fgithub.com\u002FStructureGPT) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F06\u002F07\u002F2024.06.03.597105\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Adapting protein language models for structure-conditioned design**\nJeffrey A Ruffolo, Aadyot Bhatnagar, Joel Beazer, Stephen Nayfach, Jordan Russ, Emily Hill, Riffat Hussain, Joseph Gallagher, Ali Madani\n[bioRxiv 2024.08.03.606485](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.03.606485v1) • [code](https:\u002F\u002Fgithub.com\u002FProfluent-AI\u002FproseLM-public) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F03\u002F2024.08.03.606485\u002FDC1\u002Fembed\u002Fmedia-1.zip) • [news](https:\u002F\u002Fwww.genengnews.com\u002Ftopics\u002Fartificial-intelligence\u002Fgiving-structure-to-language-profluents-ai-models-move-toward-precise-and-steerable-protein-design\u002F) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=MkwM3t80XpQ)\n\n**EMOCPD: Efficient Attention-based Models for Computational Protein Design Using Amino Acid Microenvironment**\nXiaoqi Ling, Cheng Cai, Demin Kong, Zhisheng Wei, Jing Wu, Lei Wang, Zhaohong Deng\n[arXiv:2410.21069](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.21069)\u002F[Journal of Chemical Information and Modeling (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c00378) • [data](https:\u002F\u002Fgithub.com\u002Flingxqqqqq\u002FDataSet)\n\n**Mixture of Experts Enable Efficient and Effective Protein Understanding and Design**\nNing Sun, Shuxian Zou, Tianhua Tao, Sazan Mahbub, Dian Li, Yonghao Zhuang, Hongyi Wang, Xingyi Cheng, Le Song, Eric P. Xing\n[bioRxiv 2024.11.29.625425](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.29.625425v1) • [code](https:\u002F\u002Fgithub.com\u002Fgenbio-ai\u002FAIDO\u002F)\n\n**Finetuning ESM3 with Contrastive Preference Optimization for Antigen-Specific Antibody Design**\nAnirudh Venkatraman, Gopinath Balaji, Veeresh Kande\n[UIUC Fall 2024 CS582 MLCB](https:\u002F\u002Fopenreview.net\u002Fforum?id=wDpvm3TrhE) • [code](https:\u002F\u002Fgithub.com\u002Fanirudhvenk\u002Fantibody-dpo)\n\n**Protein CREATE enables closed-loop design of de novo synthetic protein binders**\nAlec Lourenço, Arjuna Subramanian, Ryan Spencer, Michael Anaya, Jiapei Miao, William Fu, Eric Chow, Matt Thomson\n[bioRxiv 2024.12.20.629847](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.20.629847v1) • ESM-IF-based\n\n**DS-ProGen: A Dual-Structure Deep Language Model for Functional Protein Design**  \nYanting Li, Jiyue Jiang, Zikang Wang, Ziqian Lin, Dongchen He, Yuheng Shan, Yanruisheng Shao, Jiayi Li, Xiangyu Shi, Jiuming Wang, Yanyu Chen, Yimin Fan, Han Li, Yu Li  \n[arXiv:2505.12511](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.12511)\n\n**Structure-Aware Antibody Design with Affinity-Optimized Inverse Folding**  \nXinyan Zhao, Yi-Ching Tang, Rivaaj Monsia, Victor J. Cantu, Ashwin Kumar Ramesh, Xiaozhong Liu, Zhiqiang An, Xiaoqian Jiang, Yejin Kim  \n[arXiv:2512.17815](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.17815) • ESM-IF-based\n\n### 4.8 ResNet-based\n\n**DenseCPD: improving the accuracy of neural-network-based computational protein sequence design with DenseNet**\nQi, Yifei, and John ZH Zhang\n[Journal of chemical information and modeling 60.3 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fpdf\u002F10.1021\u002Facs.jcim.0c00043) • code unavailable\n\n**DeepUSPS: Deep Learning‐Empowered Unconstrained‐Structural Protein Sequence Design**  \nZhichong Ma, Jiawen Yang  \n[Proteins: Structure, Function, and Bioinformatics (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fprot.26847) • [code](https:\u002F\u002Fgithub.com\u002Fmazhichong\u002FMZC) • [data](https:\u002F\u002Fzenodo.org\u002Frecords\u002F10811470)\n\n### 4.9 Diffusion-based\n\n**De novo protein backbone generation based on diffusion with structured priors and adversarial training**\nYufeng Liu, Linghui Chen, Haiyan Liu\n[bioRxiv 2022.12.17.520847](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.17.520847v1)\u002F[Nat Methods (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-024-02437-w) • [code](https:\u002F\u002Fgithub.com\u002Fliuyf020419\u002FSCUBA-D)\n\n**Generative design of de novo proteins based on secondary-structure constraints using an attention-based diffusion model**\nBo Ni, David L. Kaplan, Markus J. Buehler\n[Chem,(2023)](https:\u002F\u002Fwww.cell.com\u002Fchem\u002Ffulltext\u002FS2451-9294(23)00139-0) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProteinDiffusionGenerator) • [news](https:\u002F\u002Fnews.mit.edu\u002F2023\u002Fai-system-can-generate-novel-proteins-structural-design-0420)\n\n**Graph Denoising Diffusion for Inverse Protein Folding**\nKai Yi, Bingxin Zhou, Yiqing Shen, Pietro Liò, Yu Guang Wang\n[arXiv:2306.16819](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.16819)\u002F[NeurIPS 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=u4YXKKG5dX) • [code](https:\u002F\u002Fgithub.com\u002Fykiiiiii\u002FGraDe_IF)\n\n**Conditional Protein Denoising Diffusion Generates Programmable Endonucleases**\nBingxin Zhou, Lirong Zheng, Banghao Wu, Kai Yi, Bozitao Zhong, Pietro Lio, Liang Hong\n[bioRxiv 2023.08.10.552783](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.10.552783v1)\n\n**Diffusion in a quantized vector space generates non-idealized protein structures and predicts conformational distributions**\nLiu Haiyan, Liu Yufeng, Chen Linghui\n[bioRxiv 2023.11.18.567666](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.18.567666v1)\n\n**Fast non-autoregressive inverse folding with discrete diffusion**\nJohn J. Yang, Jason Yim, Regina Barzilay, Tommi Jaakkola\n[arXiv:2312.02447](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.02447) • [code](https:\u002F\u002Fgithub.com\u002Fjohnyang101\u002Fpmpnndiff)\n\n**Diffusion Language Models Are Versatile Protein Learners**\nXinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, Quanquan Gu\n[arXiv:2402.18567](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.18567)\n\n**LéxFusion**\nLevinthal\npaper not available • [news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FIex0YndimhLDM0mASp1MtA) • commercial\n\n**A conditional protein diffusion model generates artificial programmable endonuclease sequences with enhanced activity**\nBingxin Zhou, Lirong Zheng, Banghao Wu, Kai Yi, Bozitao Zhong, Yang Tan, Qian Liu, Pietro Liò, Liang Hong\n[bioRxiv 2023.08.10.552783](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.10.552783v2)\u002F[Cell Discovery 10.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41421-024-00728-2) • [code](https:\u002F\u002Fgithub.com\u002Fbzho3923\u002FCPDiffusion)\n\n**LaGDif: Latent Graph Diffusion Model for Efficient Protein Inverse Folding with Self-Ensemble**\nTaoyu Wu, Yu Guang Wang, Yiqing Shen\n[arXiv:2411.01737](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.01737) • [code](https:\u002F\u002Fgithub.com\u002FTaoyuW\u002FLaGDif)\n\n**Bridge-IF: Learning Inverse Protein Folding with Markov Bridges**\nYiheng Zhu, Jialu Wu, Qiuyi Li, Jiahuan Yan, Mingze Yin, Wei Wu, Mingyang Li, Jieping Ye, Zheng Wang, Jian Wu\n[arXiv:2411.02120](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.02120) • [code](https:\u002F\u002Fgithub.com\u002Fviolet-sto\u002FBridge-IF)\n\n**Mask prior-guided denoising diffusion improves inverse protein folding**\nPeizhen Bai, Filip Miljković, Xianyuan Liu, Leonardo De Maria, Rebecca Croasdale-Wood, Owen Rackham, Haiping Lu\n[arXiv:2412.07815](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.07815)\u002F[Nature Machine Intelligence (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01042-6) • [code](https:\u002F\u002Fgithub.com\u002Fpeizhenbai\u002FMapDiff)\n\n**Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model**\nBo Ni, Markus J. Buehler\n[arXiv preprint arXiv:2502.10173 (2025)](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2502.10173) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FModeShapeDiffusionDesign), [model](https:\u002F\u002Fhuggingface.co\u002Flamm-mit\u002FVibeGen)\n\n**All-Atom Protein Sequence Design using Discrete Diffusion Models**  \nAmelia Villegas-Morcillo, Gijs J. Admiraal, Marcel J.T. Reinders, Jana M. Weber  \n[bioRxiv 2025.06.13.659451](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.13.659451v1) • [code](https:\u002F\u002Fgithub.com\u002FIntelligent-molecular-systems\u002FAll-Atom-Protein-Sequence-Generation)\n\n**Enhancing functional proteins through multimodal inverse folding with ABACUS-T**  \nYufeng Liu, Rui Wu, Xinyu Wang, Sheng Wang, Linghui Chen, Fudong Li, Quan Chen & Haiyan Liu  \n[Nat Commun 16, 10177 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-65175-3) • [code](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.17089342)\n\n### 4.10 Bayesian-based\n\n**Inverse Protein Folding Using Deep Bayesian Optimization**\nNatalie Maus, Yimeng Zeng, Daniel Allen Anderson, Phillip Maffettone, Aaron Solomon, Peyton Greenside, Osbert Bastani, Jacob R. Gardner\n[arXiv:2305.18089](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.18089) • [code](https:\u002F\u002Fgithub.com\u002Fnataliemaus\u002Fbo-if)\n\n**Design of Protein Sequences with Precisely Tuned Kinetic Properties**\nZ. Faidon Brotzakis, Michele Vendruscolo, Georgios Skretas\n[bioRxiv 2025.02.13.638027](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.13.638027v1)\n\n**IgCraft: A versatile sequence generation framework for antibody discovery and engineering**\nMatthew Greenig, Haowen Zhao, Vladimir Radenkovic, Aubin Ramon, Pietro Sormanni\n[arXiv:2503.19821](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.19821) • [code](https:\u002F\u002Fgithub.com\u002Fmgreenig\u002FIgCraft)\n\n### 4.11 Flow-based\n\n**Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design**\nHannes Stärk, Bowen Jing, Regina Barzilay, Tommi Jaakkola\n[arXiv:2310.05764](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05764) • [code](https:\u002F\u002Fgithub.com\u002FHannesStark\u002FFlowSite)\n\n### 4.12 RL-based\n\n**Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design**\nChenyu Wang, Masatoshi Uehara, Yichun He, Amy Wang, Tommaso Biancalani, Avantika Lal, Tommi Jaakkola, Sergey Levine, Hanchen Wang, Aviv Regev\n[arXiv:2410.13643](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.13643) • [code](https:\u002F\u002Fgithub.com\u002FChenyuWang-Monica\u002FDRAKES)\n\n**Reinforcement learning on structure-conditioned categorical diffusion for protein inverse folding**\nYasha Ektefaie, Olivia Viessmann, Siddharth Narayanan, Drew Dresser, J. Mark Kim, Armen Mkrtchyan\n[arXiv:2410.17173](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.17173) • [code](https:\u002F\u002Fgithub.com\u002Fflagshippioneering\u002Fpi-rldif)\n\n**ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search**  \nMengdi Liu, Xiaoxue Cheng, Zhangyang Gao, Hong Chang, Cheng Tan, Shiguang Shan, Xilin Chen  \n[arXiv:2506.00925](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.00925)\n\n**ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning**  \nZiwen Wang, Jiajun Fan, Ruihan Guo, Thao Nguyen, Heng Ji, Ge Liu  \n[arXiv:2506.07459](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.07459)\n\n**ProDCARL: Reinforcement Learning-Aligned Diffusion Models for De Novo Antimicrobial Peptide Design**  \nFang Sheng, Mohammad Noaeen, Zahra Shakeri  \n[arXiv:2602.00157](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00157)\n\n### 4.13 Train-method\n\n**Protein Inverse Folding From Structure Feedback**  \nJunde Xu, Zijun Gao, Xinyi Zhou, Jie Hu, Xingyi Cheng, Le Song, Guangyong Chen, Pheng-Ann Heng, Jiezhong Qiu  \n[arXiv:2506.03028](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.03028v1)\n\n**Improving Protein Sequence Design through Designability Preference Optimization**  \nFanglei Xue, Andrew Kubaney, Zhichun Guo, Joseph K. Min, Ge Liu, Yi Yang, David Baker\n[arXiv:2506.00297](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.00297) • LigandMPNN-based\n\n**EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization**  \nDingyi Rong, Haotian Lu, Wenzhuo Zheng, Fan Zhang, Shuangjia Zheng, Ning Liu  \n[arXiv:2506.09496](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.09496) • [code](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FEnerBridge-DPO)\n\n**Attribution assignment for deep-generative sequence models enables interpretability analysis using positive-only data**  \nRobert Frank, Michael Widrich, Rahmad Akbar, Günter Klambauer, Geir Kjetil Sandve, Philippe A. Robert, Victor Greiff  \n[arXiv:2506.23182](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.23182)\n\n**Adaptive Protein Design Protocols and Middleware**  \nAymen Alsaadi, Jonathan Ash, Mikhail Titov, Matteo Turilli, Andre Merzky, Shantenu Jha, Sagar Khare  \n[arXiv:2510.06396](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.06396)\n\n**Decoding the physicochemical basis of taxonomy preferences in protein design models**  \nLaura B Dillon, Oliver Crook, Aaron Maiwald  \n[bioRxiv 2025.10.21.683350](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.21.683350v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F10\u002F21\u002F2025.10.21.683350\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n## 5.Function to Sequence\n\n> These models generate sequences from expected function.\n\n### 5.1 CNN-based\n\n**Antibody complementarity determining region design using high-capacity machine learning**\nGe Liu, Haoyang Zeng, Jonas Mueller, Brandon Carter,   Ziheng Wang, Jonas Schilz, Geraldine Horny, Michael E Birnbaum, Stefan Ewert, David K Gifford\n[Bioinformatics 36.7 (2020): 2126-2133](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F36\u002F7\u002F2126\u002F5645171) • [code](https:\u002F\u002Fgithub.com\u002Fgifford-lab\u002Fantibody-2019)\n\n**Protein design and variant prediction using autoregressive generative models**\nJung-Eun Shin, Adam J. Riesselman, Aaron W. Kollasch, Conor McMahon, Elana Simon, Chris Sander, Aashish Manglik, Andrew C. Kruse & Debora S. Marks\n[Nature communications 12.1 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-22732-w.pdf) • [code::SeqDesign](https:\u002F\u002Fgithub.com\u002Fdebbiemarkslab\u002FSeqDesign) • mutation effect prediction • sequence generation • April 2021\n\n**Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning**\nDerek M. Mason, Simon Friedensohn, Cédric R. Weber, Christian Jordi, Bastian Wagner, Simon M. Meng, Roy A. Ehling, Lucia Bonati, Jan Dahinden, Pablo Gainza, Bruno E. Correia & Sai T. Reddy\n[Nature Biomedical Engineering 5.6 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41551-021-00699-9) • [code](https:\u002F\u002Fgithub.com\u002Fdahjan\u002FDMS_opt)\n\n**Accelerated Engineering of ELP‐based Materials through Hybrid Biomimetic‐De Novo Predictive Molecular Design**\nTimo Laakko, Antti Korkealaakso, Burcu Firatligil Yildirir, Piotr Batys, Ville Liljeström, Ari Hokkanen, Nonappa, Merja Penttilä, Anssi Laukkanen, Ali Miserez, Caj Södergård, Pezhman Mohammadi\n[Advanced Materials (2024)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadma.202312299)\n\n### 5.2 VAE-based\n\n**Machine learning-aided design and screening of an emergent protein function in synthetic cells**\nShunshi Kohyama, Béla P. Frohn, Leon Babl & Petra Schwille\n[Nature Communications 15, 2010 (2024)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41467-024-46203-0) • [code](https:\u002F\u002Fgithub.com\u002FBelaFrohn\u002FsynMinE)\n\n**Variational auto-encoding of protein sequences**\nSam Sinai, Eric Kelsic, George M. Church, Martin A. Nowak\n[arXiv preprint arXiv:1712.03346 (2017)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.03346)\n\n**Design by adaptive sampling**\nBrookes, David H., and Jennifer Listgarten\n[arXiv preprint arXiv:1810.03714 (2018)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.03714)\n\n**Pepcvae: Semi-supervised targeted design of antimicrobial peptide sequences**\nPayel Das, Kahini Wadhawan, Oscar Chang, Tom Sercu, Cicero Dos Santos, Matthew Riemer, Vijil Chenthamarakshan, Inkit Padhi, Aleksandra Mojsilovic\n[arXiv preprint arXiv:1810.07743 (2018)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.07743)\n\n**Deep generative models for T cell receptor protein sequences**\nKristian Davidsen, Branden J Olson, William S DeWitt III, Jean Feng, Elias Harkins, Philip Bradley, Frederick A Matsen IV\n[Elife 8 (2019)](https:\u002F\u002Felifesciences.org\u002Farticles\u002F46935)\n\n**How to hallucinate functional proteins**\nCostello, Zak, and Hector Garcia Martin\n[arXiv preprint arXiv:1903.00458 (2019)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.00458)\n\n**Convergent selection in antibody repertoires is revealed by deep learning**\nSimon Friedensohn, Daniel Neumeier, Tarik A Khan, Lucia Csepregi, Cristina Parola, Arthur R Gorter de Vries, Lena Erlach, Derek M Mason, Sai T Reddy\n[BioRxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.02.25.965673v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2020\u002F02\u002F26\u002F2020.02.25.965673\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • code available after publication\n\n**Variational autoencoder for generation of antimicrobial peptides**\nDean, Scott N., and Scott A. Walper\n[ACS omega 5.33 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facsomega.0c00442)\n\n**Generating functional protein variants with variational autoencoders**\nAlex Hawkins-Hooker, Florence Depardieu, Sebastien Baur, Guillaume Couairon, Arthur Chen, David Bikard\n[PLoS computational biology 17.2 (2021)](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1008736)\n\n**Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations**\nPayel Das, Tom Sercu, Kahini Wadhawan, Inkit Padhi, Sebastian Gehrmann, Flaviu Cipcigan, Vijil Chenthamarakshan, Hendrik Strobelt, Cicero dos Santos, Pin-Yu Chen, Yi Yan Yang, Jeremy P. K. Tan, James Hedrick, Jason Crain & Aleksandra Mojsilovic\n[Nature Biomedical Engineering 5.6 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41551-021-00689-x)\n\n**Deep generative models create new and diverse protein structures**\nZeming, Tom, Yann and Alexander\n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_Deep_generative_models_create.pdf)\n\n**PepVAE: variational autoencoder framework for antimicrobial peptide generation and activity prediction**\nScott N. Dean, Jerome Anthony E. Alvarez, Dan Zabetakis, Scott A. Walper, and Anthony P. Malanoski\n[Frontiers in microbiology 12 (2021)](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffmicb.2021.725727\u002Ffull) • [code](https:\u002F\u002Fgithub.com\u002Fzswitten\u002FAntimicrobial-Peptides) • [Supplementary](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffmicb.2021.725727\u002Ffull#supplementary-material)\n\n**HydrAMP: a deep generative model for antimicrobial peptide discovery**\nPaulina Szymczak, Marcin Możejko, Tomasz Grzegorzek, Marta Bauer, Damian Neubauer, Michał Michalski, Jacek Sroka, Piotr Setny, Wojciech Kamysz, Ewa Szczurek\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.27.478054v2) • [code](https:\u002F\u002Fgithub.com\u002Fszczurek-lab\u002Fhydramp)\n\n**Therapeutic enzyme engineering using a generative neural network**\nAndrew Giessel, Athanasios Dousis, Kanchana Ravichandran, Kevin Smith, Sreyoshi Sur, Iain McFadyen, Wei Zheng & Stuart Licht\n[Scientific Reports 12.1 (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-022-05195-x)\n\n**GM-Pep: A High Efficiency Strategy to De Novo Design Functional Peptide Sequences**\nQushuo Chen, Changyan Yang, Yihao Xie, Yuqiang Wang, Xiaoxu Li, Kairong Wang, Jinqi Huang, and Wenjin Yan\n[Journal of Chemical Information and Modeling (2022)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.2c00089) • [code](https:\u002F\u002Fgithub.com\u002FTimothyChen225\u002FGM-Pep)\n\n**Mean Dimension of Generative Models for Protein Sequences**\nChristoph Feinauer, Emanuele Borgonovo\n[bioRxiv 2022.12.12.520028](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.12.520028v1) • [code](https:\u002F\u002Fgithub.com\u002Fchristophfeinauer\u002FProteinMeanDimension)\n\n**Prediction of designer-recombinases for DNA editing with generative deep learning**\nLukas Theo Schmitt, Maciej Paszkowski-Rogacz, Florian Jug & Frank Buchholz\n[Nat Commun 13, 7966 (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-35614-6) • [code](https:\u002F\u002Fgithub.com\u002Fltschmitt\u002FRecGen) • [Supplementary](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41467-022-35614-6\u002FMediaObjects\u002F41467_2022_35614_MOESM1_ESM.pdf)\n\n**ProT-VAE: Protein Transformer Variational AutoEncoder for Functional Protein Design**\nEmre Sevgen, Joshua Moller, Adrian Lange, John Parker, Sean Quigley, Jeff Mayer, Poonam Srivastava, Sitaram Gayatri, David Hosfield, Maria Korshunova, Micha Livne, Michelle Gill, Rama Ranganathan, Anthony B Costa, Andrew L Ferguson\n[bioRxiv 2023.01.23.525232](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.23.525232v1)\u002F[Proc. Natl. Acad. Sci. U.S.A. 122 (41) e2408737122](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2408737122)\n\n**Target specific peptide design using latent space approximate trajectory collector**\nTong Lin, Sijie Chen, Ruchira Basu, Dehu Pei, Xiaolin Cheng, Levent Burak Kara\n[arXiv:2302.01435](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.01435)\n\n**Deep-learning generative models enable design of synthetic orthologs of a signaling protein**\nXinran Lian, Niksa Praljak, Andrew L. Ferguson, Rama Ranganathan\n[Biophysical Journal 122.3 (2023): 311a](https:\u002F\u002Fwww.cell.com\u002Fbiophysj\u002Ffulltext\u002FS0006-3495(22)02664-9)\n\n**Designing a protein with emergent function by combined in silico, in vitro and in vivo screening**\nShunshi Kohyama, Bela Paul Frohn, Leon Babl, Petra Schwille\n[bioRxiv 2023.02.16.528840](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.16.528840v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F02\u002F19\u002F2023.02.16.528840\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**ProteinVAE: Variational AutoEncoder for Translational Protein Design**\nSuyue Lyu, Shahin Sowlati-Hashjin, Michael Garton\n[bioRxiv 2023.03.04.531110](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.04.531110v1)\u002F[Nat Mach Intell (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-023-00787-2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F03\u002F05\u002F2023.03.04.531110\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fhuggingface.co\u002FRostlab\u002Fprot_bert)\n\n**ProtWave-VAE: Integrating autoregressive sampling with latent-based inference for data-driven protein design**\nNiksa Praljak, Xinran Lian, Rama Ranganathan, Andrew Ferguson\n[bioRxiv 2023.04.23.537971](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.04.23.537971v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F04\u002F23\u002F2023.04.23.537971\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FPraljakReps\u002FProtWaveVAE)\n\n**Designing meaningful continuous representations of T cell receptor sequences with deep generative models**\nAllen Y. Leary, Darius Scott, Namita T. Gupta, Janelle C. Waite, Dimitris Skokos, Gurinder S. Atwal, Peter G. Hawkins\n[bioRxiv 2023.06.17.545423](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.17.545423v1) • [code](https:\u002F\u002Fgithub.com\u002Fpeterghawkins-regn\u002Ftcrvalid)\n\n**Utility of language model and physics-based approaches in modifying MHC Class-I immune-visibility for the design of vaccines and therapeutics**\nHans-Christof Gasser, Diego Oyarzun, Ajitha Rajan, Javier Alfaro\n[bioRxiv 2023.07.10.548300](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.10.548300v1)\n\n**Cell-free biosynthesis combined with deep learning accelerates de novo-development of antimicrobial peptides**\nAmir Pandi, David Adam, Amir Zare, Van Tuan Trinh, Stefan L. Schaefer, Marie Burt, Björn Klabunde, Elizaveta Bobkova, Manish Kushwaha, Yeganeh Foroughijabbari, Peter Braun, Christoph Spahn, Christian Preußer, Elke Pogge von Strandmann, Helge B. Bode, Heiner von Buttlar, Wilhelm Bertrams, Anna Lena Jung, Frank Abendroth, Bernd Schmeck, Gerhard Hummer, Olalla Vázquez & Tobias J. Erb\n[Nature Communications 14.1 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-42434-9) • [code](https:\u002F\u002Fgithub.com\u002Famirpandi\u002FDeep_AMP)\n\n**Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations**\nSijie Chen, Tong Lin, Ruchira Basu, Jeremy Ritchey, Shen Wang, Yichuan Luo, Xingcan Li, Dehua Pei, Levent Burak Kara & Xiaolin Cheng\n[Nat Commun 15, 1611 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-45766-2) • [code](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.10587692)\n\n**Deep-learning-based design of synthetic orthologs of SH3 signaling domains**\nXinran Lian, Nikša Praljak, Subu K. Subramanian, Sarah Wasinger, Rama Ranganathan, Andrew L. Ferguson\n[Cell Systems (2024)](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Fabstract\u002FS2405-4712(24)00204-7)\n\n**CMADiff: Cross-Modal Aligned Diffusion for Controllable Protein Generation**  \nChangjian Zhou, Yuexi Qiu, Tongtong Ling, Jiafeng Li, Shuanghe Liu, Xiangjing Wang, Jia Song, Wensheng Xiang  \n[arXiv:2503.21450](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.21450) • [code](https:\u002F\u002Fgithub.com\u002FHPC-NEAU\u002FPhysChemDiff)\n\n**Efficient Design of Affilin® Protein Binders for HER3**\nAnna Maria Díaz-Rovira, Jonathan Lotze, Gregor Hoffmann, Chiara Pallara, Alexis Molina, Ina Coburger, Manja Gloser-Bräunig, Maren Meysing, Madlen Zwarg, Lucía Díaz, Victor Guallar, Eva Bosse-Doenecke, Sergi Roda\n[bioRxiv 2025.04.02.646551](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.02.646551v1) • [code](https:\u002F\u002Fgithub.com\u002Fannadiarov\u002FProtVAE) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F04\u002F02\u002F2025.04.02.646551\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**A Structure-Aware Generative Framework for Exploring Protein Sequence and Function Space**  \nDivyanshu Shukla, Jonathan Martin, Faruck Morcos, Davit A. Potoyan  \n[bioRxiv 2025.09.18.676787](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.18.676787v1)\n\n**De Novo Multi-Mechanism Antimicrobial Peptide Design via Multimodal Deep Learning**  \nXiaojuan Li, Haifan Gong, Yue Wang, Yinuo Zhao, Lixiang Li, Peijing Bao, Qingzhou Kong, Jialu Fu, Boyao Wan, Yumeng Zhang, Jinghui Zhang, Jiekun Ni, Zhongxue Han, Xueping Nan, Kunping Ju, Longfei Sun, Yuerui Ma, Huijun Chang, Mengqi Zheng, Yanbo Yu, Xiaoyun Yang, Xiuli Zuo, Haina Wang, Yanqing Li  \n[Advanced science](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202515835) • [code](https:\u002F\u002Fgithub.com\u002Fhaifangong\u002FM3CAD)\n\n### 5.3 GAN-based\n\n**Feedback GAN for DNA optimizes protein functions**\nGupta, Anvita, and James Zou\n[Nature Machine Intelligence 1.2 (2019)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-019-0017-4) • [code](https:\u002F\u002Fgithub.com\u002Fav1659\u002Ffbgan)\n\n**Generating protein sequences from antibiotic resistance genes data using Generative Adversarial Networks**\nChhibbar, Prabal, and Arpit Joshi\n[arXiv preprint arXiv:1904.13240 (2019)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.13240)\n\n**ProGAN: Protein solubility generative adversarial nets for data augmentation in DNN framework**\nXi Han, Liheng Zhang, Kang Zhou, Xiaonan Wang\n[Computers & Chemical Engineering 131 (2019)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0098135419304922)\n\n**GANDALF: Peptide Generation for Drug Design using Sequential and Structural Generative Adversarial Networks**\nRossetto, Allison, and Wenjin Zhou\n[Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. 2020](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3388440.3412487)\n\n**Designing feature-controlled humanoid antibody discovery libraries using generative adversarial networks**\nTileli Amimeur, Jeremy M. Shaver, Randal R. Ketchem, J. Alex Taylor, Rutilio H. Clark, Josh Smith, Danielle Van Citters, Christine C. Siska, Pauline Smidt, Megan Sprague, Bruce A. Kerwin, Dean Pettit\n[BioRxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.04.12.024844v2)\n\n**Generating ampicillin-level antimicrobial peptides with activity-aware generative adversarial networks**\nAndrejs Tucs, Duy Phuoc Tran, Akiko Yumoto, Yoshihiro Ito, Takanori Uzawa, and Koji Tsuda\n[ACS omega 5.36 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facsomega.0c02088) • [code](https:\u002F\u002Fgithub.com\u002Ftsudalab\u002FPepGAN)\n\n**Conditional Generative Modeling for De Novo Protein Design with Hierarchical Functions**\nKucera, Tim, Matteo Togninalli, and Laetitia Meng-Papaxanthos\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.11.10.467885v1)\u002F[Bioinformatics 38.13 (2022)](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F38\u002F13\u002F3454\u002F6593486) • [code](https:\u002F\u002Fgithub.com\u002Ftimkucera\u002Fproteogan)\n\n**Expanding functional protein sequence spaces using generative adversarial networks**\nDonatas Repecka, Vykintas Jauniskis, Laurynas Karpus, Elzbieta Rembeza, Irmantas Rokaitis, Jan Zrimec, Simona Poviloniene, Audrius Laurynenas, Sandra Viknander, Wissam Abuajwa, Otto Savolainen, Rolandas Meskys, Martin K. M. Engqvist & Aleksej Zelezniak\n[Nature Machine Intelligence 3.4 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-021-00310-5) • [code](https:\u002F\u002Fgithub.com\u002FBiomatter-Designs\u002FProteinGAN)\n\n**A Generative Approach toward Precision Antimicrobial Peptide Design.**\nJonathon B. Ferrell, Jacob M. Remington, Colin M. Van Oort, Mona Sharafi, Reem Aboushousha, Yvonne Janssen-Heininger, Severin T. Schneebeli, Matthew J. Wargo, Safwan Wshah, Jianing Li\n[BioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.10.02.324087v2) • [code](https:\u002F\u002Fgitlab.com\u002Fvail-uvm\u002Famp-gan\u002F-\u002Ftree\u002Ftest_samples\u002F)\n\n**AMPGAN v2: Machine Learning-Guided Design of Antimicrobial Peptides**\nColin M. Van Oort, Jonathon B. Ferrell, Jacob M. Remington, Safwan Wshah, and Jianing Li\n[Journal of chemical information and modeling 61.5 (2021)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.0c01441)\n\n**DeepImmuno: deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity**\nGuangyuan Li, Balaji Iyer, V B Surya Prasath, Yizhao Ni, Nathan Salomonis\n[Briefings in bioinformatics 22.6 (2021)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle-abstract\u002F22\u002F6\u002Fbbab160\u002F6261914) • [code](https:\u002F\u002Fgithub.com\u002Ffrankligy\u002FDeepImmuno) • [web](https:\u002F\u002Fdeepimmuno.research.cchmc.org\u002F)\n\n**PandoraGAN: Generating antiviral peptides using Generative Adversarial Network**\nShraddha Surana, Pooja Arora, Divye Singh, Deepti Sahasrabuddhe, Jayaraman Valadi\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.02.15.431193v2)\n\n**Feedback-AVPGAN: Feedback-guided generative adversarial network for generating antiviral peptides**\nKano Hasegawa, Yoshitaka Moriwaki, Tohru Terada, Cao Wei, and Kentaro Shimizu\n[Journal of Bioinformatics and Computational Biology (2022)](https:\u002F\u002Fwww.worldscientific.com\u002Fdoi\u002F10.1142\u002FS0219720022500263) • [code](https:\u002F\u002Fgithub.com\u002FKanoHase\u002FAVP-Generator)\n\n**Designing antimicrobial peptides using deep learning and molecular dynamic simulations**\nQiushi Cao, Cheng Ge, Xuejie Wang, Peta J Harvey, Zixuan Zhang, Yuan Ma, Xianghong Wang, Xinying Jia, Mehdi Mobli, David J Craik, Tao Jiang, Jinbo Yang, Zhiqiang Wei, Yan Wang, Shan Chang, Rilei Yu\n[Briefings in Bioinformatics (2023)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle-abstract\u002F24\u002F2\u002Fbbad058\u002F7066348)\n\n**Generative β-Hairpin Design Using a Residue-Based Physicochemical Property Landscape**\nVardhan Satalkar and Gemechis D. Degaga and Wei Li and Yui Tik Pang and Andrew C. McShan and James C. Gumbart and Julie C. Mitchell and Matthew P. Torres\n[Biophysical Journal(2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0006349524000705) • [code](https:\u002F\u002Fgithub.com\u002Fjuliecmitchell\u002FbeGAN)\n\n**De Novo Antimicrobial Peptide Design with Feedback Generative Adversarial Networks**\nMichaela Areti Zervou, Effrosyni Doutsi, Yannis Pantazis, Panagiotis Tsakalides\n[International Journal of Molecular Sciences 25.10 (2024)](https:\u002F\u002Fwww.mdpi.com\u002F1422-0067\u002F25\u002F10\u002F5506) • [code](https:\u002F\u002Fgithub.com\u002Faretiz\u002Fde_novo_design_GAN)\n\n**Binary Discriminator Facilitates GPT-based Protein Design**\nZishuo Zeng, Rufang Xu, Jin Guo, Xiaozhou Luo\n[bioRxiv 2023.11.20.567789](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.20.567789v3) • [code](https:\u002F\u002Fgithub.com\u002Fzishuozeng\u002FGPT_protein_design) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F12\u002F21\u002F2023.11.20.567789\u002FDC1\u002Fembed\u002Fmedia-1.xlsx)\n\n**De Novo Design of Multiple Microplastic-Binding Peptides with a Protein Language Model-Guided Generative Adversarial Network**  \nSiyuan Wang, Michael T. Bergman, Carol K. Hall, Fengqi You  \n[Journal of Chemical Information and Modeling 65.16 (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c01401)\n\n**AI-driven peptide discovery for endometrial cancer: deep generative modeling and molecular simulation in the big data era**  \nIsrar Fatima, Abdur Rehman, Zhibo Wang, Hafeez Ur Rehman, Mohamed Aldaw, Dawood Ahmed Warraich, Yuxuan Meng, Yan Li & Mingzhi Liao  \n[J Comput Aided Mol Des 40, 47 (2026)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10822-025-00735-9)\n\n### 5.4 Transformer-based\n\n> Including protein large language models(pLLM) and autoregressive language models.\n\n**Progen: Language modeling for protein generation** \u002F **Large language models generate functional protein sequences across diverse families**\nAli Madani, Bryan McCann, Nikhil Naik, Nitish Shirish Keskar, Namrata Anand, Raphael R. Eguchi, Po-Ssu Huang, Richard Socher\n[arXiv preprint arXiv:2004.03497 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.03497)\u002F[Nat Biotechnol (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-022-01618-2) • [ProGen](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Fprogen), [CTRL](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Fctrl)\n\n**Signal peptides generated by attention-based neural networks**\nZachary Wu, Kevin K. Yang, Michael J. Liszka, Alycia Lee, Alina Batzilla, David Wernick, David P. Weiner, and Frances H. Arnold\n[ACS Synthetic Biology 9.8 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Facssynbio.0c00219)\n\n**ProtTrans: towards cracking the language of Life's code through self-supervised deep learning and high performance computing**\nAhmed Elnaggar, Michael Heinzinger, Christian Dallago, Ghalia Rehawi, Yu Wang, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Martin Steinegger,Debsindhu Bhowmik, and Burkhard Rost\n[arXiv preprint arXiv:2007.06225 (2020)](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9477085) • [code](https:\u002F\u002Fgithub.com\u002Fagemagician\u002FProtTrans)\n\n**Generative Language Modeling for Antibody Design**\nShuai, Richard W., Jeffrey A. Ruffolo, and Jeffrey J. Gray\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.12.13.472419v2)\u002F[Cell Systems](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Fpdf\u002FS2405-4712(23)00271-5.pdf) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F20\u002F2021.12.13.472419\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FGraylab\u002FIgLM)\n\n**Deep neural language modeling enables functional protein generation across families**\nAli Madani, Ben Krause, Eric R. Greene, Subu Subramanian, Benjamin P. Mohr, James M. Holton, Jose Luis Olmos Jr., Caiming Xiong, Zachary Z. Sun, Richard Socher, James S. Fraser, Nikhil Naik\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.07.18.452833v1)\n\n**Protein sequence sampling and prediction from structural data**\nGabriel A. Orellana, Javier Caceres-Delpiano, Roberto Ibañez, Michael P. Dunne, Leonardo Alvarez\n[bioRxiv 2021.09.06.459171](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.09.06.459171v3)\n\n**Transformer-based protein generation with regularized latent space optimization**\nEgbert Castro, Abhinav Godavarthi, Julian Rubinfien, Kevin Givechian, Dhananjay Bhaskar & Smita Krishnaswamy\n[Nat Mach Intell (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-022-00532-1)\u002F[arXiv:2201.09948](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.09948) • [code](https:\u002F\u002Fgithub.com\u002FKrishnaswamyLab\u002FReLSO-Guided-Generative-Protein-Design-using-Regularized-Transformers)\n\n**BioPhi: A platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning**\nDavid Prihoda, Jad Maamary, Andrew Waight, Veronica Juan, Laurence Fayadat-Dilman, Daniel Svozil, Danny A. Bitton\n[mAbs. Vol. 14. No. 1. Taylor & Francis, 2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F19420862.2021.2020203)\n\n**Guided Generative Protein Design using Regularized Transformers**\nEgbert Castro, Abhinav Godavarthi, Julian Rubinfien, Kevin B. Givechian, Dhananjay Bhaskar, Smita Krishnaswamy\n[arXiv preprint arXiv:2201.09948 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.09948)\n\n**Towards Controllable Protein design with Conditional Transformers**\nNoelia Ferruz, Birte Höcker\n[arXiv preprint arXiv:2201.07338 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.07338)\u002F[Nature Machine Intelligence (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-022-00499-z) • review of [Heading 5.4](#54-transformer-based)\n\n**ProteinBERT: a universal deep-learning model of protein sequence and function**  \nNadav Brandes, Dan Ofer, Yam Peleg, Nadav Rappoport, Michal Linial  \n[Bioinformatics, March 2022](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F38\u002F8\u002F2102\u002F6502274) • [code](https:\u002F\u002Fgithub.com\u002Fnadavbra\u002Fprotein_bert)\n\n**ProtGPT2 is a deep unsupervised language model for protein design**\nNoelia Ferruz,  View ProfileSteffen Schmidt,  View ProfileBirte Höcker\n[bioRxiv](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.03.09.483666v1.full)\u002F[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-32007-7) • [model::huggingface](https:\u002F\u002Fhuggingface.co\u002Fnferruz\u002FProtGPT2) [datasets::hugingface](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fnferruz\u002FUR50_2021_04) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BA5C0kLcErM) • [research highlights](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-022-01518-5) • [news](https:\u002F\u002Fcen.acs.org\u002Fphysical-chemistry\u002Fprotein-folding\u002FGenerative-AI-dreaming-new-proteins\u002F101\u002Fi12#)\n\n**Few Shot Protein Generation**\nRam, Soumya, and Tristan Bepler\n[arXiv preprint arXiv:2204.01168 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.01168)\n\n**RITA: a Study on Scaling Up Generative Protein Sequence Models**\nDaniel Hesslow, Niccoló Zanichelli, Pascal Notin, Iacopo Poli, Debora Marks\n[arXiv preprint arXiv:2205.05789 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.05789) • [code](https:\u002F\u002Fhuggingface.co\u002Flightonai\u002FRITA_xl)\n\n**ProGen2: Exploring the Boundaries of Protein Language Models**\nErik Nijkamp, Jeffrey Ruffolo, Eli N. Weinstein, Nikhil Naik, Ali Madani\n[arXiv:2206.13517](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.13517) • [code](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Fprogen) • [guide](https:\u002F\u002Fgithub.com\u002FZeeSid\u002FBioLM_Tutes\u002Ftree\u002Fmain)\n\n**AbLang: an antibody language model for completing antibody sequences**\nTobias H Olsen, Iain H Moal, Charlotte M Deane\n[Bioinformatics Advances, Volume 2, Issue 1, 2022, vbac046](https:\u002F\u002Facademic.oup.com\u002Fbioinformaticsadvances\u002Farticle\u002F2\u002F1\u002Fvbac046\u002F6609807)\n\n**Reprogramming Pretrained Language Models for Antibody Sequence Infilling**\nIgor Melnyk, Vijil Chenthamarakshan, Pin-Yu Chen, Payel Das, Amit Dhurandhar, Inkit Padhi, Devleena Das\n[arXiv:2210.07144](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.07144) • [code](https:\u002F\u002Fgithub.com\u002FIBM\u002FReprogBERT)\n\n**AbBERT: Learning Antibody Humanness via Masked Language Modeling**\nDenis Vashchenko, Sam Nguyen, Andre Goncalves, Felipe Leno da Silva, Brenden Petersen, Thomas Desautels, Daniel Faissol\n[bioRxiv 2022.08.02.502236](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2022.08.02.502236)\n\n**Accelerating Antibody Design with Active Learning**\nSeung-woo Seo, Min Woo Kwak, Eunji Kang, Chaeun Kim, Eunyoung Park, Tae Hyun Kang, Jinhan Kim\n[bioRxiv 2022.09.12.507690](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.12.507690v1)\n\n**Reprogramming Large Pretrained Language Models for Antibody Sequence Infilling**\nIgor Melnyk, Vijil Chenthamarakshan, Pin-Yu Chen, Payel Das, Amit Dhurandhar, Inkit Padhi, Devleena Das\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=axFCgjTKP45)\u002F[arXiv:2210.07144](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.07144)\n\n**Machine Learning Optimization of Candidate Antibodies Yields Highly Diverse Sub-nanomolar Affinity Antibody Libraries**\nLin Li, Esther Gupta, John Spaeth, Leslie Shing, Rafael Jaimes, Rajmonda Sulo Caceres, Tristan Bepler, Matthew E. Walsh\n[bioRxiv 2022.10.07.502662](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.10.07.502662v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F10\u002F07\u002F2022.10.07.502662\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • code will be available\n\n**ZymCTRL: a conditional language model for the contollable generation of artificial enzymes**\nNoelia Ferruz\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FZymCTRL_a_conditional_language_model_for_the_controllable_generation_of_artificial_enzymes.pdf)\u002F[bioRxiv 2024.05.03.592223](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.03.592223v1) • [hugging face](https:\u002F\u002Fhuggingface.co\u002Fnferruz\u002FZymCTRL) • [poster](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002F59047.png?t=1669864213.082831)\n\n**Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model**\nChu, Simon, and Kathy Wei\n[NeurIPS 2023 Generative AI and Biology (GenBio) Workshop. 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=QrH4bhWhwY)\u002F[arXiv:2301.02748](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.02748)\n\n**Unlocking de novo antibody design with generative artificial intelligence**\nAmir Shanehsazzadeh, Matt McPartlon, George Kasun, Andrea K. Steiger, John M. Sutton, Edriss Yassine, Cailen McCloskey, Robel Haile, Richard Shuai, Julian Alverio, Goran Rakocevic, Simon Levine, Jovan Cejovic, Jahir M. Gutierrez, Alex Morehead, Oleksii Dubrovskyi, Chelsea Chung, Breanna K. Luton, Nicolas Diaz, Christa Kohnert, Rebecca Consbruck, Hayley Carter, Chase LaCombe, Itti Bist, Phetsamay Vilaychack, Zahra Anderson, Lichen Xiu, Paul Bringas, Kimberly Alarcon, Bailey Knight, Macey Radach, Katherine Bateman, Gaelin Kopec-Belliveau, Dalton Chapman, Joshua Bennett, Abigail B. Ventura, Gustavo M. Canales, Muttappa Gowda, Kerianne A. Jackson, Rodante Caguiat, Amber Brown, Douglas Ganini da Silva, Zheyuan Guo, Shaheed Abdulhaqq, Lillian R. Klug, Miles Gander, Engin Yapici, Joshua Meier, Sharrol Bachas\n[bioRxiv (2023): 2023-01](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.08.523187v4) • [data](https:\u002F\u002Fgithub.com\u002FAbSciBio\u002Funlocking-de-novo-antibody-design) • [news](https:\u002F\u002Fwww.genengnews.com\u002Ftopics\u002Fdrug-discovery\u002Fantibodies\u002Fabsci-eyes-ind-for-platforms-first-de-novo-antibody-within-two-years\u002F) • [blog](https:\u002F\u002Fwww.science.org\u002Fcontent\u002Fblog-post\u002Fcomputing-our-way-antibodies) • commercial\n\n**A universal deep-learning model for zinc finger design enables transcription factor reprogramming**\nDavid M. Ichikawa, Osama Abdin, Nader Alerasool, Manjunatha Kogenaru, April L. Mueller, Han Wen, David O. Giganti, Gregory W. Goldberg, Samantha Adams, Jeffrey M. Spencer, Rozita Razavi, Satra Nim, Hong Zheng, Courtney Gionco, Finnegan T. Clark, Alexey Strokach, Timothy R. Hughes, Timothee Lionnet, Mikko Taipale, Philip M. Kim & Marcus B. Noyes\n[Nat Biotechnol (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-022-01624-4)\n\n**XuperNovo®\u002FProteinGPT**\nXtalPi\n[news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs?__biz=MzI4MzUwNjI5OQ==&mid=2247499137&sn=d8c9e006cdb131dcf5639db6824bb0e3&chksm=eb8b1e95dcfc97835268d9e66636e63a4c6eb2f6fde780a4d45180872ea8d79bbd1d29363aff) • [news2](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002Fh_mpZXnQQ_o8vSWzXl3wcQ) • [website](https:\u002F\u002Fwww.xtalpi.com\u002Fen\u002Fmacromolecular-drug-discovery) • commercial\n\n**Evaluating Prompt Tuning for Conditional Protein Sequence Generation**\nAndrea Nathansen, Kevin Klein, Bernhard Y. Renard, Melania Nowicka, Jakub M. Bartoszewicz\n[bioRxiv 2023.02.28.530492](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.28.530492v1) • [code](https:\u002F\u002Fgitlab.com\u002Fdacs-hpi\u002Fprotein-prompt-tuning)\n\n**AB-Gen: Antibody Library Design with Generative Pre-trained Transformer and Deep Reinforcement Learning**\nXiaopeng Xu, Tiantian Xu, Juexiao Zhou, Xingyu Liao, Ruochi Zhang, Yu Wang, Lu Zhang, Xin Gao\n[bioRxiv 2023.03.17.533102](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.17.533102v1) • [code](https:\u002F\u002Fgithub.com\u002Fcharlesxu90\u002Fab-gen) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F03\u002F21\u002F2023.03.17.533102\u002FDC1\u002Fembed\u002Fmedia-1.docx) • [data](https:\u002F\u002Fzenodo.org\u002Frecord\u002F7657016)\n\n**Unsupervised cross-domain translation via deep learning and adversarial attention neural networks and application to music-inspired protein designs**\nBuehler, Markus J\n[Patterns 4.3 (2023)](https:\u002F\u002Fwww.cell.com\u002Fpatterns\u002Ffulltext\u002FS2666-3899(23)00023-5) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FAttentionCrossTranslation)\n\n**ProtFIM: Fill-in-Middle Protein Sequence Design via Protein Language Models**\nLee, Youhan, and Hasun Yu\n[arXiv preprint arXiv:2303.16452 (2023)](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2303.16452.pdf)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=9XAZBUfnefS)\n\n**REXzyme: A Translation Machine for the Generation of New-to-Nature Enzymes**\nSebastian Lindner, Michael Heinzinger, Noelia Ferruz\npaper coming soon • [hugging face](https:\u002F\u002Fhuggingface.co\u002FAI4PD\u002FREXzyme)\n\n**A generalized protein design ML model enables generation of functional de novo proteins**\nTimothy P. Riley, Pourya Kalantari, Ismail Naderi, Kooshiar Azimian, Kathy Y. Wei, Oleg Matusovsky, Mohammad S. Parsa\n[bioRxiv 2025.03.21.644400](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.21.644400v1) • [news](https:\u002F\u002Fmedium.com\u002F310-ai\u002Fmpm4-ai-text2protein-breakthrough-tackles-the-molecule-programming-challenge-870045a8c1ad) • [repo](https:\u002F\u002F310.ai\u002Fmpm\u002Frepo) • commercial\n\n**De Novo Design of Peptide Binders to Conformationally Diverse Targets with Contrastive Language Modeling**\nSuhaas Bhat, Kalyan Palepu, Lauren Hong, Joey Mao, Tianzheng Ye, Rema Iyer, Lin Zhao, Tianlai Chen, Sophia Vincoff, Rio Watson, Tian Wang, Divya Srijay, Venkata Srikar Kavirayuni, Kseniia Kholina, Shrey Goel, Pranay Vure, Aniruddha H Desphande, Scott Soderling, Matthew DeLisa, Pranam Chatterjee\n[bioRxiv 2023.06.26.546591](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.26.546591v2) • [code](https:\u002F\u002Fzenodo.org\u002Fdoi\u002F10.5281\u002Fzenodo.10971077) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F22\u002F2023.06.26.546591\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein**\nBo Chen, Xingyi Cheng, Li-ao Gengyang, Shen Li, Xin Zeng, Boyan Wang, Gong Jing, Chiming Liu, Aohan Zeng, Yuxiao Dong, Jie Tang, Le Song\n[bioRxiv 2023.07.05.547496](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.05.547496v1)\u002F[Nat Methods (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-025-02636-z) • [news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FXQn8je49z23UYby8pR7fkA) • [website](https:\u002F\u002Fwww.biomap.com\u002Faigp-light-beta\u002Fform) • [code](https:\u002F\u002Fgithub.com\u002Fbiomap-research\u002FxTrimoPGLM) • [model](https:\u002F\u002Fhuggingface.co\u002Fbiomap-research) • commercial\n\n**TULIP - a Transformer based Unsupervised Language model for Interacting Peptides and T-cell receptors that generalizes to unseen epitopes**\nBarthelemy Meynard-Piganeau, Christoph Feinauer, Martin Weigt, Aleksandra M Walczak, Thierry Mora\n[bioRxiv 2023.07.19.549669](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.19.549669v1) • [code](https:\u002F\u002Fgithub.com\u002Fbarthelemymp\u002FTULIP-TCR\u002F)\n\n**Efficient and accurate sequence generation with small-scale protein language models**\nYaiza Serrano, Sergi Roda, Victor Guallar, Alexis Molina\n[bioRxiv 2023.08.04.551626](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.04.551626v1)\n\n**IMPROVING ANTIBODY AFFINITY USING LABORATORY DATA WITH LANGUAGE MODEL GUIDED DESIGN**\nBen Krause, Subu Subramanian, Tom Yuan, Marisa Yang, Aaron Sato, Nikhil Naik\n[bioRxiv 2023.09.13.557505](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.13.557505v1)\n\n**NL2ProGPT: Taming Large Language Model for Conversational Protein Design**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=sFJr7okOBi)\n\n**PepMLM: Target Sequence-Conditioned Generation of Peptide Binders via Masked Language Modeling**\nTianlai Chen, Sarah Pertsemlidis, Rio Watson, Venkata Srikar Kavirayuni, Ashley Hsu, Pranay Vure, Rishab Pulugurta, Sophia Vincoff, Lauren Hong, Tian Wang, Vivian Yudistyra, Elena Haarer, Lin Zhao, Pranam Chatterjee\n[arXiv:2310.03842](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.03842) • [code](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fpepmlm)\n\n**De novo generation of antibody CDRH3 with a pre-trained generative large language model**\nHaoHuai He, Bing He, Lei Guan, Yu Zhao, Guanxing Chen, Qingge Zhu, Calvin Yu-Chian Chen, Ting Li, Jianhua Yao\n[bioRxiv 2023.10.17.562827](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.17.562827v1)\u002F[Nature Communications 15.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-50903-y) • [code](https:\u002F\u002Fgithub.com\u002FTencentAILabHealthcare\u002FPALM) • [data](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.7794583)\n\n**SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders**\nGaryk Brixi, Tianzheng Ye, Lauren Hong, Tian Wang, Connor Monticello, Natalia Lopez-Barbosa, Sophia Vincoff, Vivian Yudistyra, Lin Zhao, Elena Haarer, Tianlai Chen, Sarah Pertsemlidis, Kalyan Palepu, Suhaas Bhat, Jayani Christopher, Xinning Li, Tong Liu, Sue Zhang, Lillian Petersen, Matthew P. DeLisa & Pranam Chatterjee\n[Commun Biol 6, 1081 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42003-023-05464-z) • [code](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fsaltnpeppr)\n\n**ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers**\nPascal Notin, Ruben Weitzman, Debora S Marks, Yarin Gal\n[bioRxiv 2023.12.06.570473](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.06.570473v1) • [code](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FProteinNPT)\n\n**The promises of large language models for protein design and modeling**\nGiorgio Valentini, Dario Malchiodi, Jessica Gliozzo, Marco Mesiti, Mauricio Soto-Gomez, Alberto Cabri, Justin Reese, Elena Casiraghi, and Peter N. Robinson\n[Frontiers in Bioinformatics 3 (2023)](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffbinf.2023.1304099\u002Ffull)\n\n**Conversational Drug Editing Using Retrieval and Domain Feedback**\nShengchao Liu, Jiongxiao Wang, Yijin Yang, Chengpeng Wang, Ling Liu, Hongyu Guo, Chaowei Xiao\n[ICLR (2024)](https:\u002F\u002Fopenreview.net\u002Fforum?id=yRrPfKyJQ2) • [code](https:\u002F\u002Fgithub.com\u002Fchao1224\u002FChatDrug) • [website](https:\u002F\u002Fchao1224.github.io\u002FChatDrug)\n\n**ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning**\nAlireza Ghafarollahi, Markus J. Buehler\n[arXiv:2402.04268](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.04268) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProtAgents)\n\n**Designing proteins with language models**\nRuffolo, J.A., Madani, A\n[Nat Biotechnol 42, 200–202 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02123-4) • review\n\n**ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing**\nLiuzhenghao Lv, Zongying Lin, Hao Li, Yuyang Liu, Jiaxi Cui, Calvin Yu-Chian Chen, Li Yuan, Yonghong Tian\n[arXiv:2402.16445](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.16445) • [code](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.16445.pdf)\n\n**Combining machine learning with structure-based protein design to predict and engineer post-translational modifications of proteins**\nMoritz Ertelt, Vikram Khipple Mulligan, Jack B. Maguire, Sergey Lyskov, Rocco Moretti, Torben Schiffner, Jens Meiler, Clara T. Schoeder\n[PLOS Computational Biology 20(3): e1011939](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1011939) • [code](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002FPTMPrediction)\n\n**Combining Rosetta Sequence Design with Protein Language Model Predictions Using Evolutionary Scale Modeling (ESM) as Restraint**\nMoritz Ertelt, Jens Meiler, and Clara T. Schoeder\n[ACS Synth. Biol. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.3c00753) • [code](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002FPLM_restraint)\n\n**Design of Antigen-Specific Antibody CDRH3 Sequences Using AI and Germline-Based Templates**\nToma M. Marinov, Alexandra A. Abu-Shmais, Alexis K. Janke, Ivelin S. Georgiev\n[bioRxiv 2024.03.22.586241](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.22.586241v1.full)\n\n**Design of highly functional genome editors by modeling the universe of CRISPR-Cas sequences**\nJeffrey A. Ruffolo, Stephen Nayfach, Joseph Gallagher, Aadyot Bhatnagar, Joel Beazer, Riffat Hussain, Jordan Russ, Jennifer Yip, Emily Hill, Martin Pacesa, Alexander J. Meeske, Peter Cameron, Ali Madani\n[bioRxiv 2024.04.22.590591](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.22.590591v1) • [code](https:\u002F\u002Fgithub.com\u002FProfluent-AI\u002FOpenCRISPR)\n\n**Functional Protein Design with Local Domain Alignment**\nChaohao Yuan, Songyou Li, Geyan Ye, Yikun Zhang, Long-Kai Huang, Wenbing Huang, Wei Liu, Jianhua Yao, Yu Rong\n[arXiv:2404.16866](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.16866)\n\n**The Continuous Language of Protein Structure**\nLukas Billera, Anton Oresten, Aron Stålmarck, Kenta Sato, Mateusz Kaduk, Ben Murrell\n[bioRxiv 2024.05.11.593685](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.11.593685v1) • [code](https:\u002F\u002Fgithub.com\u002FMurrellGroup\u002FInvariantPointAttention.jl)\n\n**Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates**\nZhenqiao Song, Yunlong Zhao, Wenxian Shi, Wengong Jin, Yang Yang, Lei Li\n[arXiv:2405.08205](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.08205)\u002F[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fpdf\u002Fb349f5504ef1e6143231064979e2e96feaf5a6a9.pdf) • [code](https:\u002F\u002Fgithub.com\u002FLeiLiLab\u002FEnzyGen)\n\n**A generative foundation model for antibody sequence understanding**\nJustin Barton, Aretas Gaspariunas, David A Yadin, Jorge Dias, Francesca L Nice, Danielle H Minns, Olivia Snudden, Chelsea Povall, Sara Valle Tomas, Harry Dobson, James HR Farmery, Jinwoo Leem, Jacob D Galson\n[bioRxiv 2024.05.22.594943](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.22.594943v1) • [huggingface](https:\u002F\u002Fhuggingface.co\u002Falchemab)\n\n**Decoupled Sequence and Structure Generation for Realistic Antibody Design**\nNayoung Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park\n[arXiv:2402.05982](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.05982)\u002F[Under review for TMLR](https:\u002F\u002Fopenreview.net\u002Fforum?id=CTkABQvnkm) • [code](https:\u002F\u002Fgithub.com\u002Flkny123\u002FASSD_public)\n\n**Addressing the antibody germline bias and its effect on language models for improved antibody design**\nTobias H. Olsen, Iain H. Moal, Charlotte M. Deane\n[bioRxiv 2024.02.02.578678](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.02.578678v1)\u002F[Bioinformatics (2024): btae618](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F40\u002F11\u002Fbtae618\u002F7845256) • [code](https:\u002F\u002Fgithub.com\u002Foxpig\u002FAbLang2)\n\n**MoFormer: Multi-objective Antimicrobial Peptide Generation Based on Conditional Transformer Joint Multi-modal Fusion Descriptor**\nLi Wang, Xiangzheng Fu, Jiahao Yang, Xinyi Zhang, Xiucai Ye, Yiping Liu, Tetsuya Sakurai, Xiangxiang Zeng\n[arXiv:2406.00735](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.02610)\n\n**HELM-GPT: de novo macrocyclic peptide design using generative pre-trained transformer**\nXiaopeng Xu, Chencheng Xu, Wenjia He, Lesong Wei, Haoyang Li, Juexiao Zhou, Ruochi Zhang, Yu Wang, Yuanpeng Xiong, Xin Gao\n[Bioinformatics (2024): btae364](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtae364\u002F7691994) • [code](https:\u002F\u002Fgithub.com\u002Fcharlesxu90\u002Fhelm-gpt)\n\n**Unifying Sequences, Structures, and Descriptions for Any-to-Any Protein Generation with the Large Multimodal Model HelixProtX**\nZhiyuan Chen, Tianhao Chen, Chenggang Xie, Yang Xue, Xiaonan Zhang, Jingbo Zhou, Xiaomin Fang\n[arXiv:2407.09274](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.09274) • [code](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FPaddleHelix\u002Ftree\u002Fdev\u002Fapps\u002Fhelixprotx)\n\n**A foundation model approach to guide antimicrobial peptide design in the era of artificial intelligence driven scientific discovery**\nJike Wang, Jianwen Feng, Yu Kang, Peichen Pan, Jingxuan Ge, Yan Wang, Mingyang Wang, Zhenxing Wu, Xingcai Zhang, Jiameng Yu, Xujun Zhang, Tianyue Wang, Lirong Wen, Guangning Yan, Yafeng Deng, Hui Shi, Chang-Yu Hsieh, Zhihui Jiang, Tingjun Hou\n[arXiv:2407.12296](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.12296) • [code](https:\u002F\u002Fgithub.com\u002Fjkwang93\u002FAMP-Designer)\n\n**Conditional Sequence-Structure Integration: A Novel Approach for Precision Antibody Engineering and Affinity Optimization**\nBenyamin Jamialahmadi, Mahmood Chamankhah, Mohammad Kohandel, Ali Ghodsi\n[bioRxiv 2024.07.16.603820](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.16.603820v1) • [blog](https:\u002F\u002Fsimplescience.ai\u002Fen\u002F2024-08-28-advancements-in-antibody-design-with-aida-method--an1v4d)\n\n**moPPIt: De Novo Generation of Motif-Specific Binders with Protein Language Models**\nTong Chen, Yinuo Zhang, Pranam Chatterjee\n[bioRxiv 2024.07.31.606098](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.31.606098v1) • [code](https:\u002F\u002Fhuggingface.co\u002FChatterjeeLab\u002FmoPPIt)\n\n**Toward De Novo Protein Design from Natural Language**\nFengyuan Dai, Yuliang Fan, Jin Su, Chentong Wang, Chenchen Han, Xibin Zhou, Jianming Liu, Hui Qian, Shunzhi Wang, Anping Zeng, Yajie Wang, Fajie Yuan\n[bioRxiv 2024.08.01.606258](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.01.606258v5) • [code](https:\u002F\u002Fgithub.com\u002Fwestlake-repl\u002FDenovo-Pinal) •[demo](http:\u002F\u002Fwww.denovo-pinal.com\u002F)\n\n**Design Proteins Using Large Language Models: Enhancements and Comparative Analyses**\nKamyar Zeinalipour, Neda Jamshidi, Monica Bianchini, Marco Maggini, Marco Gori\n[arXiv:2408.06396](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.06396) • [code](https:\u002F\u002Fgithub.com\u002FKamyarZeinalipour\u002Fprotein-design-LLMs)\n\n**Miniaturizing, Modifying, and Augmenting Nature's Proteins with Raygun**\nKapil Devkota, Daichi Shonai, Joey Mao, Scott H Soderling, Rohit Singh\n[bioRxiv 2024.08.13.607858](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.13.607858v1) • [code](https:\u002F\u002Fgithub.com\u002Frohitsinghlab\u002Fraygun)\n\n**TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering**\nYiqing Shen, Zan Chen, Michail Mamalakis, Yungeng Liu, Tianbin Li, Yanzhou Su, Junjun He, Pietro Liò, Yu Guang Wang\n[arXiv:2408.15299](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.15299) • [code](https:\u002F\u002Fgithub.com\u002Ftsynbio\u002FTourSynbio) • [model](https:\u002F\u002Fhuggingface.co\u002Ftsynbio\u002FToursynbio) • [website](http:\u002F\u002Fprdtst.tsynbio.com:51443\u002F) • [news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FIROlGdP04uLUUipNAd7YOg) • commercial\n\n**AbGPT: De Novo Antibody Design via Generative Language Modeling**\nDesmond Kuan, Amir Barati Farimani\n[arXiv:2409.06090](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.06090v1) • [code](https:\u002F\u002Fgithub.com\u002Fdeskk\u002FAbGPT)\n\n**PepINVENT: Generative peptide design beyond the natural amino acids**\nGökçe Geylan, Jon Paul Janet, Alessandro Tibo, Jiazhen He, Atanas Patronov, Mikhail Kabeshov, Florian David, Werngard Czechtizky, Ola Engkvist, Leonardo De Maria\n[arXiv:2409.14040](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.14040)\n\n**Conditional Enzyme Generation Using Protein Language Models with Adapters**\nJason Yang, Aadyot Bhatnagar, Jeffrey A. Ruffolo, Ali Madani\n[arXiv:2410.03634](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.03634) • [code](https:\u002F\u002Fgithub.com\u002FProfluent-Internships\u002FProCALM)\n\n**Re-examining Metrics for Success in Machine Learning, from Fairness and Interpretability to Protein Design**\nFrances Ding\n[Diss. University of California, Berkeley, 2024](https:\u002F\u002Fwww2.eecs.berkeley.edu\u002FPubs\u002FTechRpts\u002F2024\u002FEECS-2024-156.html) • Phd thesis\n\n**Computational design of target-specific linear peptide binders with TransformerBeta**\nHaowen Zhao, Francesco A. Aprile, Barbara Bravi\n[arXiv:2410.16302](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.16302) • [code](https:\u002F\u002Fgithub.com\u002FHZ3519\u002FTransformerBeta_project)\n\n**Structure Language Models for Protein Conformation Generation**\nJiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Chence Shi, Hongyu Guo, Yoshua Bengio, Jian Tang\n[arXiv:2410.18403](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.18403) • [code](https:\u002F\u002Fgithub.com\u002Flujiarui\u002Fesmdiff)\n\n**Peptide-GPT: Generative Design of Peptides using Generative Pre-trained Transformers and Bio-informatic Supervision**\nAayush Shah, Chakradhar Guntuboina, Amir Barati Farimani\n[arXiv:2410.19222](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.19222) • [code](https:\u002F\u002Fgithub.com\u002Faayush-shah14\u002FPeptideGPT)\n\n**An adaptive autoregressive diffusion approach to design active humanized antibody and nanobody**\nJian Ma, Fandi Wu, Tingyang Xu, Shaoyong Xu, Wei Liu, Divin Yan, Qifeng Bai, Jianhua Yao\n[bioRxiv 2024.10.22.619416](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.22.619416v1) • [code](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002FHuDiff)\n\n**Concept Bottleneck Language Models For protein design**\nAya Abdelsalam Ismail, Tuomas Oikarinen, Amy Wang, Julius Adebayo, Samuel Stanton, Taylor Joren, Joseph Kleinhenz, Allen Goodman, Héctor Corrada Bravo, Kyunghyun Cho, Nathan C. Frey\n[arXiv:2411.06090](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.06090)\n\n**De novo design of triosephosphate isomerases using generative language models**\nSergio Romero-Romero, Alexander E. Braun, Timo Kossendey, Noelia Ferruz, Steffen Schmidt, Birte Höcker\n[bioRxiv 2024.11.10.622869](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.10.622869v1)\n\n**Natural Language Prompts Guide the Design of Novel Functional Protein Sequences**\nNikša Praljak, Hugh Yeh, Miranda Moore, Michael Socolich, Rama Ranganathan, Andrew L. Ferguson\n[bioRxiv 2024.11.11.622734](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.11.622734v1)\n\n**Multi-purpose controllable protein generation via prompted language models**\nZeyuan Wang, Binbin Chen, Keyan Ding, Jiawen Cao, Ming Qin, Yadan Niu, Xiang Zhuang, Xiaotong Li, Kehua Feng, Tong Xu, Ningyu Zhang, Haoran Yu, Qiang Zhang, Huajun Chen\n[bioRxiv 2024.11.17.624051](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.17.624051v1)\n\n**Antiviral Peptide-Generative Pre-Trained Transformer (AVP-GPT): A Deep Learning-Powered Model for Antiviral Peptide Design with High-Throughput Discovery and Exceptional Potency**\nHuajian Zhao, Gengshen Song\n[Viruses 16.11 (2024)](https:\u002F\u002Fwww.mdpi.com\u002F1999-4915\u002F16\u002F11\u002F1673)\n\n**Pan-protein Design Learning Enables Task-adaptive Generalization for Low-resource Enzyme Design**\nJiangbin Zheng, Ge Wang, Han Zhang, Stan Z. Li\n[arXiv:2411.17795](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.17795)\n\n**ProtDAT: A Unified Framework for Protein Sequence Design from Any Protein Text Description**\nXiao-Yu Guo, Yi-Fan Li, Yuan Liu, Xiaoyong Pan, Hong-Bin Shen\n[arXiv:2412.04069](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.04069) • [code](https:\u002F\u002Fgithub.com\u002FGXY0116\u002FProtDAT)\n\n**Annotation-guided Protein Design with Multi-Level Domain Alignment**\nChaohao Yuan, Songyou Li, Geyan Ye, Yikun Zhang, Long-Kai Huang, Wenbing Huang, Wei Liu, Jianhua Yao, Yu Rong\n[arXiv:2404.16866](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.16866)\n\n**Open-Source Protein Language Models for Function Prediction and Protein Design**\nShivasankaran Vanaja Pandi, Bharath Ramsundar\n[arXiv:2412.13519](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.13519)\n\n**Discovery and language model-guided design of hyperactive transposase**\nMarc Güell, Dimitrije Ivančić, Alejandro Agudelo, Jonathan Lindstrom-Vautri, Jessica Jaraba-Wallace, Maria Gallo, Alejandro Ragel, Irene Higueras, Federico Billeci, Marta Sanvicente, Paolo Petazzi, Noelia Ferruz, Avencia Sánchez-Mejías, Ravi Das\n[preprint](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-5536951\u002Fv1) • [code](https:\u002F\u002Fgithub.com\u002FIntegra-tx\u002FPiggybac_bioprospecting_pipeline) • Progen2-based\n\n**Generation of antigen-specific paired heavy-light chain antibody sequences using large language models**\nPerry T. Wasdin, Nicole V. Johnson, Alexis K. Janke, Sofia Held, Toma M. Marinov, Gwen Jordaan, Léna Vandenabeele, Fani Pantouli, Rebecca A. Gillespie, Matthew J. Vukovich, Clinton M. Holt, Jeongryeol Kim, Grant Hansman, Jennifer Logue, Helen Y. Chu, Sarah F. Andrews, Masaru Kanekiyo, Giuseppe A. Sautto, Ted M. Ross, Daniel J. Sheward, Jason S. McLellan, Alexandra A. Abu-Shmais, Ivelin S. Georgiev\n[bioRxiv 2024.12.20.629482](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.20.629482v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F22\u002F2024.12.20.629482\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Controllable Protein Sequence Generation with LLM Preference Optimization**\nXiangyu Liu, Yi Liu, Silei Chen, Wei Hu\n[arXiv:2501.15007](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.15007) • [code](https:\u002F\u002Fgithub.com\u002Fnju-websoft\u002FCtrlProt)\n\n**Discovery of antimicrobial peptides with notable antibacterial potency by an LLM-based foundation model**\nJike Wang, Jianwen Feng, Yu Kang, Peichen Pan, Jingxuan Ge, Yan Wang, Mingyang Wang, Zhenxing Wu, Xingcai Zhang, Jiameng Yu, Xujun Zhang, Tianyue Wang, Lirong Wen, Guangning Yan, Yafeng Deng, Hui Shi, Chang-Yu Hsieh, Zhihui Jiang, and Tingjun Hou\n[Sci. Adv.11,eads8932(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.ads8932) • [code](https:\u002F\u002Fgithub.com\u002Fjkwang93\u002FAMP-Designer)\n\n**CasGen: A Regularized Generative Model for CRISPR Cas Protein Design with Classification and Margin-Based Optimization**\nBharani Nammi, Vindi M. Jayasinghe-Arachchige, Sita Sirisha Madugula, Maria Artiles, Charlene Norgan Radler, Tyler Pham, Jin Liu, Shouyi Wang\n[bioRxiv 2025.02.28.640911](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.28.640911v1) • [code](https:\u002F\u002Fgithub.com\u002Fshouyisxty\u002FCasGen)\n\n**Language models for protein design**\nJin Sub Lee, Osama Abdin, and Philip M. Kim\n[Current Opinion in Structural Biology 92 (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X25000454) • review\n\n**De Novo Design of Antigen-Specific Antibodies Using Structural Constraint-Based Generative Language Model**  \nYuran Jia, Bing He, Tianxu Lv, YangXiao, Tianyi Zhao, Jianhua Yao  \n[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=8F2JrQC2DJ)\n\n**SOAPI: Siamese-guided generation of Off-Target-Avoiding Protein Interactions**  \nSophia Vincoff, Oscar Davis, Alexander Tong, Joey Bose, Pranam Chatterjee  \n[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=mUp7mfNfXz)\n\n**Prot42: a Novel Family of Protein Language Models for Target-aware Protein Binder Generation**\nMohammad Amaan Sayeed, Engin Tekin, Maryam Nadeem, Nancy A. ElNaker, Aahan Singh, Natalia Vassilieva, Boulbaba Ben Amor\n[arXiv:2504.04453](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.04453) • [model](https:\u002F\u002Fhuggingface.co\u002Finceptionai)\n\n**Customizing Spider Silk: Generative Models with Mechanical Property Conditioning for Protein Engineering**\nNeeru Dubey, Elin Karlsson, Miguel Angel Redondo, Johan Reimegård, Anna Rising, Hedvig Kjellström\n[arXiv:2504.08437](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.08437) • ProtGPT2-based\n\n**A multimodal foundation model for controllable protein generation and representation learning**  \nTimothy Fei Truong Jr, Tristan Bepler  \n[blog](https:\u002F\u002Fwww.openprotein.ai\u002Fa-multimodal-foundation-model-for-controllable-protein-generation-and-representation-learning) • commercial\n\n**Elucidating the Design Space of Multimodal Protein Language Models**\nCheng-Yen Hsieh, Xinyou Wang, Daiheng Zhang, Dongyu Xue, Fei Ye, Shujian Huang, Zaixiang Zheng, Quanquan Gu\n[arXiv:2504.11454](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.11454)\n\n**Scaling unlocks broader generation and deeper functional understanding of proteins**\nAadyot Bhatnagar, Sarthak Jain, Joel Beazer, Samuel C Curran, Alexander M Hoffnagle, Kyle Ching, Michael Martyn, Stephen Nayfach, Jeffrey A Ruffolo, Ali Madani\n[bioRxiv 2025.04.15.649055](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.15.649055v1) • [code](https:\u002F\u002Fgithub.com\u002FProfluent-AI\u002Fprogen3)\n\n**Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles**  \nAlireza Ghafarollahi, Markus J. Buehler  \n[arXiv:2504.19017](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.19017) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FSparks\u002F)\n\n**Protein Design with Dynamic Protein Vocabulary**  \nNuowei Liu, Jiahao Kuang, Yanting Liu, Changzhi Sun, Tao Ji, Yuanbin Wu, Man Lan  \n[arXiv:2505.18966](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.18966) • [code](https:\u002F\u002Fgithub.com\u002FsornkL\u002FProDVa)\n\n**ProtMamba: a homology-aware but alignment-free protein state space model**  \nDamiano Sgarbossa, Cyril Malbranke, Anne-Florence Bitbol  \n[bioRxiv 2024.05.24.595730](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.24.595730v4) • [code](https:\u002F\u002Fgithub.com\u002FBitbol-Lab\u002FProtMamba)\n\n**Natural Language Guided Ligand-Binding Protein Design**  \nZhenqiao Song, Ramith Hettiarachchi, Chuan Li, Jianwen Xie, Lei Li  \n[arXiv:2506.09332](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2506.09332)\n\n**Toward the Explainability of Protein Language Models for Sequence Design**  \nAndrea Hunklinger, Noelia Ferruz  \n[arXiv:2506.19532](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.19532)\n\n**Metalorian: De Novo Generation of Heavy Metal-Binding Peptides with Classifier-Guided Diffusion Sampling**  \nYinuo Zhang, Divya Srijay, Zachary Quinn, Pranam Chatterjee  \n[bioRxiv 2025.07.10.664242](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.10.664242v1) • ESM2-based\n\n**ProteinReasoner: A Multi-Modal Protein Language Model with Chain-of-Thought Reasoning for Efficient Protein Design**  \nChaozhong Liu, Linlin Chao, Shaomin Ji, Hao Wang, Taorui Jiang, Zhangyang Gao, Yucheng Guo, Ming Yang, Xiaoming Zhang  \n[bioRxiv 2025.07.21.665832](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.21.665832v1)\n\n**The Dayhoff Atlas: scaling sequence diversity for improved protein generation**  \nKevin K. Yang, Sarah Alamdari, Alex J. Lee, Kaeli Kaymak-Loveless, Samir Char, Garyk Brixi, Carles Domingo-Enrich, Chentong Wang, Suyue Lyu, Nicolo Fusi, Neil Tenenholtz, Ava P. Amini  \n[bioRxiv 2025.07.21.665991](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.21.665991v1) • [code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdayhoff) • [dataset](https:\u002F\u002Fhuggingface.co\u002Fcollections\u002Fmicrosoft\u002Fdayhoff-atlas-6866d679465a2685b06ee969)\n\n**The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies**  \nKyle Swanson, Wesley Wu, Nash L. Bulaong, John E. Pak & James Zou  \n[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09442-9)\n\n**Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization**  \nYuhao Wang, Keyan Ding, Kehua Feng, Zeyuan Wang, Ming Qin, Xiaotong Li, Qiang Zhang, Huajun Chen  \n[arXiv:2507.10923](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.10923) • [code](https:\u002F\u002Fgithub.com\u002FHICAI-ZJU\u002FKPO)\n\n**Target sequence-conditioned design of peptide binders using masked language modeling**  \nLeo Tianlai Chen, Zachary Quinn, Madeleine Dumas, Christina Peng, Lauren Hong, Moises Lopez-Gonzalez, Alexander Mestre, Rio Watson, Sophia Vincoff, Lin Zhao, Jianli Wu, Audrey Stavrand, Mayumi Schaepers-Cheu, Tian Zi Wang, Divya Srijay, Connor Monticello, Pranay Vure, Rishab Pulugurta, Sarah Pertsemlidis, Kseniia Kholina, Shrey Goel, Matthew P. DeLisa, Jen-Tsan Ashley Chi, Ray Truant, Hector C. Aguilar & Pranam Chatterjee  \n[Nat Biotechnol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-025-02761-2) • [code](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fpepmlm) • [model](https:\u002F\u002Fhuggingface.co\u002FChatterjeeLab\u002FPepMLM-650M)\n\n**ICEPIC: A Toolkit to Discover Ice Binding Proteins from Sequence**  \nJimmy Zhang, Subbulakshmi Suresh, Shmuel Gleizer, Sophia Ewens, Aarya Venkat, Valentin Zulkower, Thomas Biernacki, Daniel Wen, Catherine Li, Mohammed Eslami, Susan Buckhout-White  \n[bioRxiv 2025.08.08.669420](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.08.669420v2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F08\u002F14\u002F2025.08.08.669420\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fnetrias\u002FICEPIC)\n\n**Improved multimodal protein language model-driven universal biomolecules-binding protein design with EiRA**  \nWenwu Zeng, Haitao Zou, Xiaoyu Li, Xiaoqi Wang, Shaoliang Peng  \n[bioRxiv 2025.09.02.673615](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.02.673615v2) • [code](https:\u002F\u002Fgithub.com\u002Fpengsl-lab\u002FEiRA)\n\n**LSMTCR: A Scalable Multi-Architecture Model for Epitope-Specific T Cell Receptor de novo Design**  \nRuihao Zhang, Xiao Liu  \n[arXiv:2509.07627](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.07627)\n\n**PRIME: A Multi-Agent Environment for Orchestrating Dynamic Computational Workflows in Protein Engineerings**  \nYuyang Zhou, Jin Su, Jiawei Zhang, Wangyang Hu, Tianli Tao, Guanqi Li, Xibin Zhou, Li Fan, Fajie Yuan  \n[bioRxiv 2025.09.22.677756](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.22.677756v1)\n\n**Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents**  \nJacopo Teneggi, Tanya Marwah, Alberto Bietti, P. Douglas Renfrew, Vikram Khipple Mulligan, Siavash Golkar  \n[NeurIPS 2025 Poster](https:\u002F\u002Fopenreview.net\u002Fforum?id=7U3RQRisyb)\n\n**Discovery and protein language model-guided design of hyperactive transposases**  \nDimitrije Ivančić, Alejandro Agudelo, Jonathan Lindstrom-Vautrin, Jessica Jaraba-Wallace, Maria Gallo, Ravi Das, Alejandro Ragel, Jorge Herrero-Vicente, Irene Higueras, Federico Billeci, Marta Sanvicente-García, Paolo Petazzi, Noelia Ferruz, Avencia Sánchez-Mejías & Marc Güell  \n[Nat Biotechnol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-025-02816-4) • [code](https:\u002F\u002Fgithub.com\u002FIntegra-tx\u002FPiggybac_bioprospecting_pipeline) • Progen2-based\n\n**Generative design of antibody Fc-variants with synthetic and programmable functional profiles**  \nEdward B. Irvine, Thomas Bikias, Evangelos Stamkopoulos, Lester Frei, Nick Schürmann, Annmaree K. Warrender, Helen Schmid, Dimitri Coukos, Huilin Yang, Mason Minot, William Kelton, Sai T. Reddy  \n[bioRxiv 2025.10.10.681689](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.10.681689v1)\n\n**Reasoning Models Outperform Standard Language Models in De Novo Protein Design**  \nAlfred Greisen, Longfei Cong, Per Jr. Greisen, Sergey Ovchinnikov  \n[Agents4Science](https:\u002F\u002Fopenreview.net\u002Fforum?id=yXYEbPQp8x)\n\n**DLFea4AMPGen de novo design of antimicrobial peptides by integrating features learned from deep learning models**  \nHan Gao, Feifei Guan, Boyu Luo, Dongdong Zhang, Wei Liu, Yuying Shen, Lingxi Fan, Guoshun Xu, Yuan Wang, Tao Tu, Ningfeng Wu, Bin Yao, Huiying Luo, Yue Teng, Jian Tian & Huoqing Huang  \n[Nat Commun 16, 9134 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-64378-y) • [code](https:\u002F\u002Fgithub.com\u002Fhgao12345\u002FDLFea4AMPGen)\n\n**De Novo Design of High-Performance Sec-type Signal Peptide via a Hybrid Deep Learning Architecture**  \nXiao-peng Dai, Xiang-chun Meng, Ying-jun Zhou, Zhi-min Li, Yu Ji, Ulrich Schwaneberg, Zong-lin Li  \n[JACS Au 5.10 (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacsau.5c00757) • [code](https:\u002F\u002Fgithub.com\u002Flzlinn801\u002FSPgo)\n\n**MOFormer: navigating the antimicrobial peptide design space with Pareto-based multi-objective transformer**  \nLi Wang, Xiangzheng Fu, Jiahao Yang, Xinyi Zhang, Xiucai Ye, Tetsuya Sakurai, Xiangxiang Zeng, Yiping Liu  \n[Briefings in Bioinformatics 26.6 (2025)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F26\u002F6\u002Fbbaf376\u002F8315069) • [code](https:\u002F\u002Fgithub.com\u002Fwl-wl\u002FMOFormer\u002Ftree\u002Fmaster)\n\n**Generation of antigen-specific paired-chain antibodies using large language models**  \nPerry T. Wasdin, Nicole V. Johnson, Alexis K. Janke, Sofia Held, Toma M. Marinov, Gwen Jordaan, Rebecca A. Gillespie, Le´ na Vandenabeele, Fani Pantouli, Olivia C. Powers, Matthew J. Vukovich, Clinton M. Holt, Jeongryeol Kim, Grant Hansman, Jennifer Logue, Helen Y. Chu, Sarah F. Andrews, Masaru Kanekiyo, Giuseppe A. Sautto, Ted M. Ross, Daniel J. Sheward, Jason S. McLellan, Alexandra A. Abu-Shmais, and Ivelin S. Georgiev  \n[Cell (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(25)01135-3) • [code](https:\u002F\u002Fgithub.com\u002FIGlab-VUMC\u002FMAGE_ab_generation) • [model](https:\u002F\u002Fhuggingface.co\u002Fperrywasdin\u002FMAGE_V1)\n\n**Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design**  \nBruno Jacob, Khushbu Agarwal, Marcel Baer, Peter Rice, Simone Raugei  \n[arXiv:2511.19423](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.19423v1)\n\n**General-Purpose Large Language Models, such as DeepSeek V3.2, Have Evolved Protein Design Capabilities**  \nJiawei Li, Xinxiu Dong  \n[bioRxiv 2025.11.23.689994](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.23.689994v1) • [code](https:\u002F\u002Fgithub.com\u002FLIJIAWEI040301\u002FGLLMs_for_protein)\n\n**Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation**  \nFiona Y. Wang, Di Sheng Lee, David L. Kaplan, Markus J. Buehler  \n[arXiv:2511.22311](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.22311v1) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProteinSwarm)\n\n**Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein Design**  \nAmin Tavakoli, Raswanth Murugan, Ozan Gokdemir, Arvind Ramanathan, Frances Arnold, Anima Anandkumar  \n[arXiv:2512.09329](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.09329v1)\n\n**TCRdesign: an antigen-specific generative language model for de novo design of T-cell receptors**  \nXiaokun Li, Qiang Yang, Long Xu, Weihe Dong, Kuanquan Wang, Suyu Dong, Wei Wang, Gongning Luo, Xianyu Zhang, Tiansong Yang, Xin Gao, Guohua Wang  \n[Briefings in Bioinformatics, Volume 26, Issue 6, November 2025, bbaf691](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F26\u002F6\u002Fbbaf691\u002F8405050) • [data](https:\u002F\u002Fgithub.com\u002Flixiaokun2020\u002FTCRdesign) • [code](https:\u002F\u002Fgithub.com\u002Flixiaokun2020\u002FTCRdesign)\n\n**TcrDesign: De novo design of epitope specific full-length T cell receptors**  \nKaixuan Diao, Jing Chen, Xiangyu Zhao, Tao Wu, Die Qiu, Weiliang Wang, Haopeng Wang, Xue-Song Liu  \n[bioRxiv 2026.01.15.699824](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.15.699824v1) • [code](https:\u002F\u002Fgithub.com\u002FXSLiuLab\u002FTcrDesign)\n\n**TCRAD: An End-to-End Framework for Antigen-Targeted T Cell Receptor Design**  \nChenao Li, Yaochi Guo, Xin Guan, Hui Chen, Yong Zhang, Pengyuan Yang, Jizhong Lou  \n[bioRxiv 2026.01.21.700513](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.21.700513v1)\n\n**De novo functional protein sequence generation: overcoming data scarcity through regeneration and large language models**  \nChenyu Ren, Daihai He, Jian Huang  \n[Briefings in Bioinformatics](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F27\u002F2\u002Fbbag095\u002F8510708) • [data](https:\u002F\u002Fgithub.com\u002FChenyuzZZ73\u002FProteinRG\u002Fdata)\n\n### 5.5 Bayesian-based\n\n**Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design**\nMelis Ilayda Bal, Pier Giuseppe Sessa, Mojmir Mutny, Andreas Krause\n[NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World, 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=ScOvmGz4xH)\u002F[arXiv:2409.18582](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.18582)\n\n**Discovering de novo peptide substrates for enzymes using machine learning**\nLorillee Tallorin, JiaLei Wang, Woojoo E. Kim, Swagat Sahu, Nicolas M. Kosa, Pu Yang, Matthew Thompson, Michael K. Gilson, Peter I. Frazier, Michael D. Burkart & Nathan C. Gianneschi\n[Nature communications 9.1 (2018)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-018-07717-6) • [code](https:\u002F\u002Fgithub.com\u002Fpeter-i-frazier\u002Fpool)\n\n**Biological Sequences Design using Batched Bayesian Optimization**\nDavid Belanger, Suhani Vora, Zelda Mariet, Ramya Deshpande, David Dohan, Christof Angermueller, Kevin Murphy, Olivier Chapelle, Lucy Colwell\n[Machine Learning and the Physical Sciences Workshop (NeurIPS 2019)](https:\u002F\u002Fml4physicalsciences.github.io\u002F2019\u002Ffiles\u002FNeurIPS_ML4PS_2019_141.pdf)\n\n**Lattice protein design using Bayesian learning**\nTakahashi, Tomoei, George Chikenji, and Kei Tokita\n[arXiv:2003.06601](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.06601)\u002F[Physical Review E 104.1 (2021): 014404](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.104.014404)\n\n**Now What Sequence? Pre-trained Ensembles for Bayesian Optimization of Protein Sequences**\nZiyue Yang, Katarina A Milas, Andrew D White\n[bioRxiv 2022.08.05.502972](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.05.502972v2) • [code](https:\u002F\u002Fgithub.com\u002Fur-whitelab\u002Fwazy) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F08\u002F06\u002F2022.08.05.502972\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fur-whitelab\u002Fwazy\u002Fblob\u002Fmaster\u002Fcolab\u002FWazyAlphaFold2.ipynb)\n\n**AntBO: Towards Real-World Automated Antibody Design with Combinatorial Bayesian Optimisation**\nAsif Khan, Alexander I. Cowen-Rivers, Antoine Grosnit, Derrick-Goh-Xin Deik, Philippe A. Robert, Victor Greiff, Eva Smorodina, Puneet Rawat, Kamil Dreczkowski, Rahmad Akbar, Rasul Tutunov, Dany Bou-Ammar, Jun Wang, Amos Storkey, Haitham Bou-Ammar\n[arXiv preprint (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.12570)\u002F[Cell Reports Methods (2023): 100374](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2667237522002764)\n\n**Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders**\nSamuel Stanton, Wesley Maddox, Nate Gruver, Phillip Maffettone, Emily Delaney, Peyton Greenside, Andrew Gordon Wilson\n[ICML 2022](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.12742) • [code](https:\u002F\u002Fgithub.com\u002Fsamuelstanton\u002Flambo)\n\n**Statistical Mechanics of Protein Design**\nTakahashi, Tomoei, George Chikenji, and Kei Tokita\n[arXiv preprint arXiv:2205.03696 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.03696)\n\n**PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design**\nJi Won Park, Samuel Stanton, Saeed Saremi, Andrew Watkins, Henri Dwyer, Vladimir Gligorijevic, Richard Bonneau, Stephen Ra, Kyunghyun Cho\n[arXiv:2210.04096](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.04096)\n\n**A probabilistic view of protein stability, conformational specificity, and design**\nJacob A. Stern, Tyler J. Free, Kimberlee L. Stern, Spencer Gardiner, Nicholas A. Dalley, Bradley C. Bundy, Joshua L. Price, David Wingate, Dennis Della Corte\n[bioRxiv 2022.12.28.521825](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.28.521825v1)\u002F[Scientific Reports 13.1 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-023-42032-1) • [code](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fbayes_design) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F30\u002F2022.12.28.521825\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Design of antimicrobial peptides containing non-proteinogenic amino acids using multi-objective Bayesian optimisation**\nMurakami Y, Ishida S, Demizu Y, Terayama K\n[ChemRxiv. Cambridge: Cambridge Open Engage; 2023](https:\u002F\u002Fchemrxiv.org\u002Fengage\u002Fchemrxiv\u002Farticle-details\u002F645f192ef2112b41e97720f3) • [code](https:\u002F\u002Fgithub.com\u002Fycu-iil\u002FMODAN)\n\n**Vaxformer: Antigenicity-controlled Transformer for Vaccine Design Against SARS-CoV-2**\nAryo Pradipta Gema, Michał Kobiela, Achille Fraisse, Ajitha Rajan, Diego A. Oyarzún, Javier Antonio Alfaro\n[arXiv:2305.11194](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.11194) • [code](https:\u002F\u002Fgithub.com\u002Faryopg\u002Fvaxformer)\n\n**Sample-efficient Antibody Design through Protein Language Model for Risk-aware Batch Bayesian Optimization**\nYanzheng Wang, Boyue Wang, Tianyu Shi, Jie Fu, Yi Zhou, Zhizhuo Zhang\n[bioRxiv 2023.11.06.565922](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.06.565922v1)\n\n**Integrating Protein Structure Prediction and Bayesian Optimization for Peptide Design**\nNegin Manshour, Fei He, Duolin Wang, Dong Xu\n[NeurIPS 2023 Generative AI and Biology (GenBio) Workshop. 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=CsjGuWD7hk)\n\n**Bayesian Optimisation for Protein Sequence Design: Gaussian Processes with Zero-Shot Protein Language Model Prior Mean**\nCarolin Benjamins, Shikha Surana, Oliver Bent, Marius Lindauer, Paul Duckworth\n[Machine Learning for Structural Biology Workshop, NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FBayesian_Optimisation_for_Protein_Sequence_Design:_Gaussian_Processes_with_Zero-Shot_Protein_Language_Model_Prior_Mean.pdf)\n\n**Steering Protein Family Design through Profile Bayesian Flow**\nJingjing Gong, Yu Pei, Siyu Long, Yuxuan Song, Zhe Zhang, Wenhao Huang, Ziyao Cao, Shuyi Zhang, Hao Zhou, Wei-Ying Ma\n[arXiv:2502.07671](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.07671)\n\n**AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model**  \nChangze Lv, Jiang Zhou, Siyu Long, Lihao Wang, Jiangtao Feng, Dongyu Xue, Yu Pei, Hao Wang, Zherui Zhang, Yuchen Cai, Zhiqiang Gao, Ziyuan Ma, Jiakai Hu, Chaochen Gao, Jingjing Gong, Yuxuan Song, Shuyi Zhang, Xiaoqing Zheng, Deyi Xiong, Lei Bai, Wanli Ouyang, Ya-Qin Zhang, Wei-Ying Ma, Bowen Zhou, Hao Zhou  \n[arXiv:2507.08920](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.08920) • [code](https:\u002F\u002Fgensi-thuair.github.io\u002FAMix-1\u002F)\n\n### 5.6 RL-based\n\n**Model-based reinforcement learning for biological sequence design**\nChristof Angermueller, David Dohan, David Belanger, Ramya Deshpande, Kevin Murphy, Lucy Colwell\n[International conference on learning representations. 2019](https:\u002F\u002Fopenreview.net\u002Fforum?id=HklxbgBKvr&fileGuid=3xgr169o12oUrbxS)\n\n**Structured Q-learning For Antibody Design**\nAlexander I. Cowen-Rivers, Philip John Gorinski, Aivar Sootla, Asif Khan, Liu Furui, Jun Wang, Jan Peters, Haitham Bou Ammar\n[arXiv preprint arXiv:2209.04698 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.04698)\n\n**Protein Sequence Design in a Latent Space via Model-based Reinforcement Learning**\nMinji Lee, Luiz Felipe Vecchietti, Hyunkyu Jung, Hyunjoo Ro, Ho Min Kim, Meeyoung Cha\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=OhjGzRE5N6o)\u002F[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FProtein_Sequence_Design_in_a_Latent_Space_via_Model_based_Reinforcement_Learning.pdf) • [Supplementary](https:\u002F\u002Fopenreview.net\u002Fattachment?id=OhjGzRE5N6o&name=supplementary_material)\n\n**Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization**\nLeo Feng, Padideh Nouri, Aneri Muni, Yoshua Bengio, Pierre-Luc Bacon\n[arXiv:2209.06259](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.06259)\u002F[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FDesigning_Biological_Sequences_via_Meta_Reinforcement_Learning_and_Bayesian_Optimization.pdf) • [poster](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002F58993.png?t=1669588933.2017226)\n\n**Self-play reinforcement learning guides protein engineering**\nYi Wang, Hui Tang, Lichao Huang, Lulu Pan, Lixiang Yang, Huanming Yang, Feng Mu & Meng Yang\n[Nature Machine Intelligence (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-023-00691-9) • [code](https:\u002F\u002Fgithub.com\u002Fmelobio\u002FEvoPlay)\n\n**Curiosity Driven Protein Sequence Generation via Reinforcement Learning**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=tPjVRmHqCg)\n\n**Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design**\nYannick Vogt, Mehdi Naouar, Maria Kalweit, Christoph Cornelius Miething, Justus Duyster, Roland Mertelsmann, Gabriel Kalweit, Joschka Boedecker\n[arXiv:2401.05341](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.05341)\n\n**Peptide Vaccine Design by Evolutionary Multi-Objective Optimization**\nDan-Xuan Liu, Yi-Heng Xu, Chao Qian\n[arXiv:2406.05743](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.05743)\n\n**Reinforcement Learning for Sequence Design Leveraging Protein Language Models**\nJithendaraa Subramanian, Shivakanth Sujit, Niloy Irtisam, Umong Sain, Derek Nowrouzezahrai, Samira Ebrahimi Kahou, Riashat Islam\n[arXiv:2407.03154](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.03154)\n\n**BetterBodies: Reinforcement Learning guided Diffusion for Antibody Sequence Design**\nYannick Vogt, Mehdi Naouar, Maria Kalweit, Christoph Cornelius Miething, Justus Duyster, Joschka Boedecker, Gabriel Kalweit\n[arXiv:2409.16298](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.16298)\n\n**Reinforcement learning-driven exploration of peptide space: accelerating generation of drug-like peptides**\nQian Wang, Xiaotong Hu, Zhiqiang Wei, Hao Lu, Hao Liu\n[Briefings in Bioinformatics 25.5 (2024): bbae444](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F5\u002Fbbae444\u002F7754450) • [code](https:\u002F\u002Fgithub.com\u002Fp1acemker\u002FMomdTDSRL)\n\n**Guiding Generative Protein Language Models with Reinforcement Learning**\nFilippo Stocco, Maria Artigues-Lleixa, Andrea Hunklinger, Talal Widatalla, Marc Guell, Noelia Ferruz\n[arXiv:2412.12979](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.12979) • [code](https:\u002F\u002Fgithub.com\u002FAI4PDLab\u002FDPO_pLM)\n\n**DOTA: Developability-Optimized Antibody Generation**\nThao Nguyen, Jiateng Liu, Anna Hart\n[UIUC Fall 2024 CS582 MLCB](https:\u002F\u002Fopenreview.net\u002Fforum?id=H4430Z0HfD)\n\n**PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion**\nSophia Tang, Yinuo Zhang, Pranam Chatterjee\n[arXiv:2412.17780](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.17780)\n\n**PepINVENT: generative peptide design beyond natural amino acids**  \nGökçe Geylan, Jon Paul Janet, Alessandro Tibo, Jiazhen He, Atanas Patronov, Mikhail Kabeshov, Werngard Czechtizky, Florian David, Ola Engkvist and Leonardo De Maria  \n[Chemical Science (2025)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlelanding\u002F2025\u002Fsc\u002Fd4sc07642g) • [code](https:\u002F\u002Fgithub.com\u002FMolecularAI\u002FPepINVENT\u002F)\n\n**A deep reinforcement learning platform for antibiotic discovery**  \nHanqun Cao, Marcelo D. T. Torres, Jingjie Zhang, Zijun Gao, Fang Wu, Chunbin Gu, Jure Leskovec, Yejin Choi, Cesar de la Fuente-Nunez, Guangyong Chen, Pheng-Ann Heng  \n[bioRxiv 2025.09.23.678086](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.23.678086v1)\n\n**Designing proteins with reduced T-cell epitopes through policy optimization**  \nManvitha Ponnapati, Sapna Sinha, Brian Lynch, Edward S. Boyden, Joseph Jacobson  \n[bioRxiv 2025.09.27.678937](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.27.678937v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F29\u002F2025.09.27.678937\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids**  \nLucas Ferraz, Ana F. Rodrigues, Pedro Giesteira Cotovio, Mafalda Ventura, Gabriela Silva, Ana Sofia Coroadinha, Miguel Machuqueiro, Catia Pesquita  \n[arXiv:2603.19473](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.19473) • [code](https:\u002F\u002Fgithub.com\u002Fliseda-lab\u002FgenAAV)\n\n### 5.7 Flow-based\n\n**Biological Sequence Design with GFlowNets**\nMoksh Jain, Emmanuel Bengio, Alex-Hernandez Garcia, Jarrid Rector-Brooks, Bonaventure F. P. Dossou, Chanakya Ekbote, Jie Fu, Tianyu Zhang, Micheal Kilgour, Dinghuai Zhang, Lena Simine, Payel Das, Yoshua Bengio\n[arXiv preprint arXiv:2203.04115 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.04115) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=YRbFDThaAmo)\n\n**ProtFlow: Fast Protein Sequence Design via Flow Matching on Compressed Protein Language Model Embeddings**\nZitai Kong, Yiheng Zhu, Yinlong Xu, Hanjing Zhou, Mingzhe Yin, Jialu Wu, Hongxia Xu, Chang-Yu Hsieh, Tingjun Hou, Jian Wu\n[arXiv:2504.10983](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.10983)\n\n**Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer**  \nMingze Yin, Hanjing Zhou, Yiheng Zhu, Jialu Wu, Wei Wu, Mingyang Li, Kun Fu, Zheng Wang, Chang-Yu Hsieh, Tingjun Hou, Jian Wu  \n[Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. No. 21. 2025](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F34370)\n\n**Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design**  \nTong Chen, Yinuo Zhang, Sophia Tang, Pranam Chatterjee  \n[arXiv:2505.07086](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.07086v2) • [model](https:\u002F\u002Fhuggingface.co\u002FChatterjeeLab\u002FMOG-DFM)\n\n**Modeling the structure-conditioned sequence landscape for large-scale protein design with TriFlow**  \nHarish Srinivasan, Rongqing Yuan, Qian Cong, Jian Zhou  \n[bioRxiv 2025.11.30.691458](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.11.30.691458v1) • [code](https:\u002F\u002Fgithub.com\u002Fjzhoulab\u002FTriFlow)\n\n**ProtFlow: Flow Matching-based Protein Sequence Design with Comprehensive Protein Semantic Distribution Learning and High-quality Generation**  \nZitai Kong, Yiheng Zhu, Yinlong Xu, Mingze Yin, Tingjun Hou, Jian Wu, Hongxia Xu, Chang-Yu Hsieh  \n[bioRxiv 2026.02.14.705870](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.14.705870v1) • [code](https:\u002F\u002Fgithub.com\u002FHiracharleFranklin\u002FProtFlow)\n\n### 5.8 RNN-based\n\n**Deep learning to design nuclear-targeting abiotic miniproteins**\nCarly K. Schissel, Somesh Mohapatra, Justin M. Wolfe, Colin M. Fadzen, Kamela Bellovoda, Chia-Ling Wu, Jenna A. Wood, Annika B. Malmberg, Andrei Loas, Rafael Gómez-Bombarelli & Bradley L. Pentelute\n[Nature Chemistry 13.10 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41557-021-00766-3) • [code](https:\u002F\u002Fgithub.com\u002Flearningmatter-mit\u002Fpeptimizer)\n\n**Recurrent neural network model for constructive peptide design**\nMüller, Alex T., Jan A. Hiss, and Gisbert Schneider\n[Journal of chemical information and modeling 58.2 (2018)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.7b00414)\n\n**Machine learning designs non-hemolytic antimicrobial peptides**\nAlice Capecchi, Xingguang Cai, Hippolyte Personne, Thilo Köhler, Christian van Delden, and Jean-Louis Reymond\n[Chemical Science 12.26 (2021)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlehtml\u002F2021\u002Fsc\u002Fd1sc01713f)\n\n**Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides**\nDuy Phuoc Tran, Seiichi Tada, Akiko Yumoto, Akio Kitao, Yoshihiro Ito, Takanori Uzawa & Koji Tsuda\n[Scientific reports 11.1 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-021-90245-z)\n\n**De novo antioxidant peptide design via machine learning and DFT studies**\nParsa Hesamzadeh, Abdolvahab Seif, Kazem Mahmoudzadeh, Mokhtar Ganjali Koli, Amrollah Mostafazadeh, Kosar Nayeri, Zohreh Mirjafary & Hamid Saeidian\n[Scientific Reports 14.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-024-57247-z) • [code](https:\u002F\u002Fgithub.com\u002Fmephisto121\u002FDeepGenAntiOxidantPeptide)\n\n### 5.9 LSTM-based\n\n**Computational antimicrobial peptide design and evaluation against multidrug-resistant clinical isolates of bacteria**\nDeepesh Nagarajan, Tushar Nagarajan, Natasha Roy, Omkar Kulkarni, Sathyabaarathi Ravichandran, Madhulika Mishra\nDipshikha Chakravortty, Nagasuma Chandra\n[Journal of Biological Chemistry 293.10 (2018)](https:\u002F\u002Fwww.jbc.org\u002Farticle\u002FS0021-9258(20)40390-4\u002Ffulltext)\n\n**Deep learning enables the design of functional de novo antimicrobial proteins**\nJavier Caceres-Delpiano, Roberto Ibañez, Patricio Alegre, Cynthia Sanhueza, Romualdo Paz-Fiblas, Simon Correa, Pedro Retamal, Juan Cristóbal Jiménez, Leonardo Álvarez\n[bioRxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.08.26.266940v1.full)\n\n**ECNet is an evolutionary context-integrated deep learning framework for protein engineering**\nYunan Luo, Guangde Jiang, Tianhao Yu, Yang Liu, Lam Vo, Hantian Ding, Yufeng Su, Wesley Wei Qian, Huimin Zhao & Jian Peng\n[Nature communications 12.1 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-25976-8)\n\n**Deep learning for novel antimicrobial peptide design**\nWang, Christina, Sam Garlick, and Mire Zloh\n[Biomolecules 11.3 (2021)](https:\u002F\u002Fwww.mdpi.com\u002F2218-273X\u002F11\u002F3\u002F471)\n\n**Antibody design using LSTM based deep generative model from phage display library for affinity maturation**\nKoichiro Saka, Taro Kakuzaki, Shoichi Metsugi, Daiki Kashiwagi, Kenji Yoshida, Manabu Wada, Hiroyuki Tsunoda & Reiji Teramoto\n[Scientific reports 11.1 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-021-85274-7)\n\n**In silico proof of principle of machine learning-based antibody design at unconstrained scale**\nAkbar, Rahmad, et al\n[Mabs. Vol. 14. No. 1. Taylor & Francis, 2022](https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fpmc\u002Farticles\u002FPMC8986205\u002Fpdf\u002FKMAB_14_2031482.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fcsi-greifflab\u002Fmanuscript_insilico_antibody_generation)\n\n**Large-scale design and refinement of stable proteins using sequence-only models**\nJedediah M. Singer , Scott Novotney, Devin Strickland, Hugh K. Haddox, Nicholas Leiby, Gabriel J. Rocklin, Cameron M. Chow, Anindya Roy, Asim K. Bera, Francis C. Motta, Longxing Cao, Eva-Maria Strauch, Tamuka M. Chidyausiku, Alex Ford, Ethan Ho, Alexander Zaitzeff, Craig O. Mackenzie, Hamed Eramian, Frank DiMaio, Gevorg Grigoryan, Matthew Vaughn, Lance J. Stewart, David Baker, Eric Klavins\n[PloS one 17.3 (2022)](https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle?id=10.1371\u002Fjournal.pone.0265020) • [code](https:\u002F\u002Fzenodo.org\u002Frecord\u002F4906529)\n\n**Deep-learning based bioactive therapeutic peptides generation and screening**\nHaiping Zhang, Konda Mani Saravanan, Yanjie Wei, Yang Jiao, Yang Yang, Yi Pan, Xuli Wu, John Z.H. Zhang\n[bioRxiv 2022.11.14.516530](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.11.14.516530v1) • [code](https:\u002F\u002Fgithub.com\u002Fhaiping1010\u002FNew_peptide_iteration) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F11\u002F16\u002F2022.11.14.516530\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Deep-learning based bioactive peptides generation and screening against Xanthine oxidase**\nHaiping Zhang, Konda Mani Saravanan, John Z.H. Zhang, Xuli Wu\n[bioRxiv 2023.01.11.523536](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.11.523536v1)\n\n**Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening**\nHaiping Zhang, Konda Mani Saravanan, Yanjie Wei, Yang Jiao, Yang Yang, Yi Pan, Xuli Wu, and John Z. H. Zhang\n[Journal of Chemical Information and Modeling 63.3 (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.2c01485) • [code](https:\u002F\u002Fgithub.com\u002Fhaiping1010\u002FNew_peptide_iteration\u002Ftree\u002Fmaster\u002Fiteration_main_protease_Antiviral_pep)\n\n**Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences**\nNiklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer\n[arXiv:2411.04165](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.04165)\n\n### 5.10 Autoregressive-models\n\n**Efficient generative modeling of protein sequences using simple autoregressive models**\nJeanne Trinquier, Guido Uguzzoni, Andrea Pagnani, Francesco Zamponi & Martin Weigt\n[Nature communications 12.1 (2021): 1-11](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-25756-4) • [code](https:\u002F\u002Fgithub.com\u002Fpagnani\u002FArDCA.jl)\n\n**Conformal prediction for the design problem**\nClara Fannjiang, Stephen Bates, Anastasios N. Angelopoulos, Jennifer Listgarten, Michael I. Jordan\n[arXiv:2202.03613v4](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.03613) • [code](https:\u002F\u002Fgithub.com\u002Fclarafy\u002Fconformal-for-design)\n\n**Enhancing privacy in biosecurity with watermarked protein design**  \nYanshuo Chen, Zhengmian Hu, Yihan Wu, Ruibo Chen, Yongrui Jin, Marcus Zhan, Chengjin Xie, Wei Chen, Heng Huang\n[Bioinformatics, 2025;, btaf141](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtaf141\u002F8124073) • [code](https:\u002F\u002Fgithub.com\u002Fposeidonchan\u002FProteinWatermark)\n\n**Controllable Protein Design via Autoregressive Direct Coupling Analysis Conditioned on Principal Components**  \nFrancesco Caredda, Andrea Pagnani, Paolo De Los Rios, Lisa Gennai  \n[bioRxiv 2025.08.18.669886](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.669886v1) • [code](https:\u002F\u002Fgithub.com\u002Ffrancescocaredda\u002FFeatureDCA.jl)\n\n**ProChoreo: De novo Binder Design from Conformational Ensembles with Generative Deep Learning**  \nSaisai Ding, Yi Zhang  \n[bioRxiv 2026.01.23.701298](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.23.701298v1)\n\n### 5.11 Boltzmann-machine-based\n\n**How pairwise coevolutionary models capture the collective residue variability in proteins?**\nFigliuzzi, Matteo, Pierre Barrat-Charlaix, and Martin Weigt\n[Molecular biology and evolution 35.4 (2018): 1018-1027](https:\u002F\u002Facademic.oup.com\u002Fmbe\u002Farticle\u002F35\u002F4\u002F1018\u002F4815777) • [code](https:\u002F\u002Fgithub.com\u002Fmatteofigliuzzi\u002FbmDCA)\n\n**A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences**\nNataša Tagasovska, Nathan C. Frey, Andreas Loukas, Isidro Hötzel, Julien Lafrance-Vanasse, Ryan Lewis Kelly, Yan Wu, Arvind Rajpal, Richard Bonneau, Kyunghyun Cho, Stephen Ra, Vladimir Gligorijević\n[arXiv:2210.10838](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.10838) • [slides](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1spTU-iZ4EEq8ZICRHBw8CstpYQXCxMy8\u002Fview)\n\n**Computational design of novel Cas9 PAM-interacting domains using evolution-based modelling and structural quality assessment**\nCyril Malbranke, William Rostain, Florence Depardieu, Simona Cocco, Remi Monasson, David Bikard\n[bioRxiv 2023.03.20.533501](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.20.533501v1) • [code](https:\u002F\u002Fgithub.com\u002FCyrilMa\u002FDesignCas9WithCLD) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.20.533501v1.supplementary-material)\n\n**Protein Discovery with Discrete Walk-Jump Sampling**\nNathan C. Frey, Daniel Berenberg, Karina Zadorozhny, Joseph Kleinhenz, Julien Lafrance-Vanasse, Isidro Hotzel, Yan Wu, Stephen Ra, Richard Bonneau, Kyunghyun Cho, Andreas Loukas, Vladimir Gligorijevic, Saeed Saremi\n[arXiv:2306.12360](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.12360)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=zMPHKOmQNb) • [code](https:\u002F\u002Fgithub.com\u002FGenentech\u002Fwalk-jump) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=r28m5Vk77Wk)\n\n### 5.12 Diffusion-based\n\n**denoising-diffusion-protein-sequence**\nZhangzhi Peng\nPaper unavailable • [github](https:\u002F\u002Fgithub.com\u002Fpengzhangzhi\u002Fprotein-sequence-diffusion-model)\n\n**Protein Design with Guided Discrete Diffusion**\nNate Gruver, Samuel Stanton, Nathan C. Frey, Tim G. J. Rudner, Isidro Hotzel, Julien Lafrance-Vanasse, Arvind Rajpal, Kyunghyun Cho, Andrew Gordon Wilson\n[arXiv:2305.20009](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.20009)\u002F[Advances in neural information processing systems, 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=MfiK69Ga6p) • [code](https:\u002F\u002Fgithub.com\u002Fngruver\u002FNOS) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Hm8Z0SIyLqw)\n\n**PRO-LDM: Protein Sequence Generation with Conditional Latent Diffusion Models**\nZixuan Jiang, Sitao Zhang, Rundong Huang, Shaoxun Mo, Letao Zhu, Peiheng Li, Ziyi Zhang, Xi Chen, Yunfei Long, Renjing Xu, Rui Qing\n[bioRxiv 2023.08.22.554145](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.22.554145v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F08\u002F23\u002F2023.08.22.554145\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Protein generation with evolutionary diffusion: sequence is all you need**\nSarah Alamdari, Nitya Thakkar, Rianne van den Berg, Alex Xijie Lu, Nicolo Fusi, Ava Pardis Amini, Kevin K Yang\n[bioRxiv 2023.09.11.556673](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.11.556673v1) • [code](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fevodiff) • [data](https:\u002F\u002Fzenodo.org\u002Frecord\u002F8045076) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=e1e-_SkyNjw), [lecture2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=iV_7mgxe4OI)\n\n**AntiBARTy Diffusion for Property Guided Antibody Design**\nJordan Venderley\n[arXiv:2309.13129](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.13129)\n\n**PD-1 Targeted Antibody Discovery Using AI Protein Diffusion**\nColby T. Ford\n[bioRxiv 2024.01.18.576323](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.01.18.576323v2) • [code](https:\u002F\u002Fgithub.com\u002Ftuplexyz\u002FPD-1_Fab_Diffusion)\n\n**ProT-Diff: A Modularized and Efficient Approach to De Novo Generation of Antimicrobial Peptide Sequences through Integration of Protein Language Model and Diffusion Model**\nXue-Fei Wang, Jing-Ya Tang, Han Liang, Jing Sun, Sonam Dorje, Bo Peng, Xu-Wo Ji, Zhe Li, Xian-En Zhang, Dian-Bing Wang\n[bioRxiv 2024.02.22.581480](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.22.581480v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F02\u002F23\u002F2024.02.22.581480\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation**\nLin Zongying, Li Hao, Lv Liuzhenghao, Lin Bin, Zhang Junwu, Chen Calvin Yu-Chian, Yuan Li, Tian Yonghong\n[arXiv:2402.17156](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.17156) • [code](https:\u002F\u002Fgithub.com\u002FLinzy19\u002FTaxDiff)\n\n**Diffusion on language model embeddings for protein sequence generation**\nViacheslav Meshchaninov, Pavel Strashnov, Andrey Shevtsov, Fedor Nikolaev, Nikita Ivanisenko, Olga Kardymon, Dmitry Vetrov\n[arXiv:2403.03726](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.03726)\n\n**AMP-Diffusion: Integrating Latent Diffusion with Protein Language Models for Antimicrobial Peptide Generation**\nTianlai Chen, Pranay Vure, Rishab Pulugurta, Pranam Chatterjee\n[bioRxiv 2024.03.03.583201](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.03.583201v1)\n\n**Atomically accurate de novo design of single-domain antibodies**\nNathaniel R. Bennett, Joseph L. Watson, Robert J. Ragotte, Andrew J. Borst, DeJenae L. See, Connor Weidle, Riti Biswas, Ellen L. Shrock, Philip J. Y. Leung, Buwei Huang, Inna Goreshnik, Russell Ault, Kenneth D. Carr, Benedikt Singer, Cameron Criswell, Dionne Vafeados, Mariana Garcia Sanchez, Ho Min Kim, Susana Vazquez Torres, Sidney Chan, David Baker\n[bioRxiv 2024.03.14.585103](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.14.585103v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09721-5) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F03\u002F18\u002F2024.03.14.585103\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Complex-based Ligand-Binding Proteins Redesign by Equivariant Diffusion-based Generative Models**\nViet Thanh Duy Nguyen, Nhan Nguyen, Truong Son Hy\n[bioRxiv 2024.04.17.589997](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.17.589997v1) • [code](https:\u002F\u002Fgithub.com\u002FHySonLab\u002FProtein_Redesign)\n\n**Cytochrome P450 Enzyme Design by Constraining Catalytic Pocket in Diffusion model**\nQian Wang, Xiaonan Liu, Hejian Zhang, Huanyu Chu, Chao Shi, Lei Zhang, Jie Bai, Pi Liu, Jing Li, Xiaoxi Zhu, Yuwan Liu, Zhangxin Chen, Rong Huang, Hong Chang, Tian Liu, Zhenzhan Chang , Jian Cheng , and Huifeng Jiang\n[Research (2024)](https:\u002F\u002Fspj.science.org\u002Fdoi\u002F10.34133\u002Fresearch.0413) • [code](https:\u002F\u002Fgithub.com\u002FJiangLab2020\u002FP450Diffusion)\n\n**Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design**\nLeo Klarner, Tim G. J. Rudner, Garrett M. Morris, Charlotte M. Deane, Yee Whye Teh\n[arXiv:2407.11942](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.11942) • [code](https:\u002F\u002Fgithub.com\u002Fleojklarner\u002Fcontext-guided-diffusion)\n\n**Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph Diffusion**\nYutong Hu, Yang Tan, Andi Han, Lirong Zheng, Liang Hong, Bingxin Zhou\n[arXiv:2407.07443](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.07443) • [code](https:\u002F\u002Fgithub.com\u002Friacd\u002FCPDiffusion-SS)\n\n**AI-generated small binder improves prime editing**\nJu-Chan Park, Heesoo Uhm, Yong-Woo Kim, Ye Eun Oh, Sangsu Bae\n[bioRxiv 2024.09.11.612443](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.11.612443v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F09\u002F14\u002F2024.09.11.612443\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**MeMDLM: De Novo Membrane Protein Design with Masked Discrete Diffusion Protein Language Models**\nShrey Goel, Vishrut Thoutam, Edgar Mariano Marroquin, Aaron Gokaslan, Arash Firouzbakht, Sophia Vincoff, Volodymyr Kuleshov, Huong T. Kratochvil, Pranam Chatterjee\n[arXiv:2410.16735](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.16735)\u002F[ICLR 2025 Workshop LMRL](https:\u002F\u002Fopenreview.net\u002Fforum?id=ZnEx3GbU9C)\n\n**Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization**\nZichen Wang, Yaokun Ji, Jianing Tian, Shuangjia Zheng\n[arXiv:2410.15040](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.15040)\n\n**ProtDiff: Function-Conditioned Masked Diffusion Models for Robust Directed Protein Generation**\nVishrut Thoutam, Yair Schiff, Sergey Ovchinnikov, Pranam Chatterjee\n[Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges](https:\u002F\u002Fopenreview.net\u002Fforum?id=POrk2Cc7Ux)\n\n**Diffusion on language model encodings for protein sequence generation**\nViacheslav Meshchaninov, Pavel Strashnov, Andrey Shevtsov, Fedor Nikolaev, Nikita Ivanisenko, Olga Kardymon, Dmitry Vetrov\n[ICLR 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=LoXJlAW3gU)\n\n**Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design**\nMasatoshi Uehara, Xingyu Su, Yulai Zhao, Xiner Li, Aviv Regev, Shuiwang Ji, Sergey Levine, Tommaso Biancalani\n[arXiv:2502.14944](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14944) • [code](https:\u002F\u002Fgithub.com\u002Fmasa-ue\u002FProDifEvo-Refinement)\n\n**De Novo Design of Large Polypeptides Using a Lightweight Diffusion Model Integrating LSTM and Attention Mechanism Under Per-Residue Secondary Structure Constraints**\nSisheng Liao,Gang Xu,Li Jin and Jianpeng Ma\n[Molecules 30.5 (2025)](https:\u002F\u002Fwww.mdpi.com\u002F1420-3049\u002F30\u002F5\u002F1116) • [code](https:\u002F\u002Fgithub.com\u002Fdaedaluser\u002FPPD)\n\n**AI-Based Antibody Design Targeting Recent H5N1 Avian Influenza Strains**  \nNicholas Santolla, Colby T. Ford  \n[bioRxiv 2025.04.24.650061](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.24.650061v1) • [code](https:\u002F\u002Fgithub.com\u002FSantollan\u002FFrankies) • EvoDiff-based\n\n**CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models**  \nJunbo Yin, Chao Zha, Wenjia He, Chencheng Xu, Xin Gao  \n[arXiv:2505.22869](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22869)\n\n**AMPGen: an evolutionary information-reserved and diffusion-driven generative model for de novo design of antimicrobial peptides**  \nShuwen Jin, Zihan Zeng, Xiyan Xiong, Baicheng Huang, Li Tang, Hongsheng Wang, Xiao Ma, Xiaochun Tang, Guoqing Shao, Xingxu Huang & Feng Lin  \n[Communications Biology 8.1 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42003-025-08282-7) • [code](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.15454482.7433980)\n\n**Diffusion Sequence Models for Enhanced Protein Representation and Generation**  \nLogan Hallee, Nikolaos Rafailidis, David B. Bichara, Jason P. Gleghorn  \n[arXiv:2506.08293](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08293) • [code](https:\u002F\u002Fgithub.com\u002FGleghorn-Lab\u002FDSM)\n\n**Uncertainty-Aware Discrete Diffusion Improves Protein Design**  \nSazan Mahbub, Christoph Feinauer, Caleb N. Ellington, Le Song, Eric P. Xing  \n[bioRxiv 2025.06.30.662407](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.30.662407v1)\n\n**Guided Generation for Developable Antibodies**  \nSiqi Zhao, Joshua Moller, Porfi Quintero-Cadena, Lood van Niekerk  \n[arXiv:2507.02670](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.02670) • ESM-2-based\n\n**PRO‐LDM: A Conditional Latent Diffusion Model for Protein Sequence Design and Functional Optimization**  \nSitao Zhang, Zixuan Jiang, Rundong Huang, Wenting Huang, Siyuan Peng, Shaoxun Mo, Letao Zhu, Peiheng Li, Ziyi Zhang, Emily Pan, Xi Chen, Yunfei Long, Qi Liang, Jin Tang, Renjing Xu, Rui Qing  \n[Advanced Science (2025)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202502723) • ESM-2-based\n\n**Protein A-like peptide generation based on generalized diffusion model**  \nTianqian Zhou, Shibo Zhang, Huijia Song, Qiang He, Chun Fang & Xiaozhu Lin  \n[J Comput Aided Mol Des 39, 76 (2025)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10822-025-00653-w) • [code](https:\u002F\u002Fgithub.com\u002FPotatoGan\u002FProteinGeneration-GeneralizedDiffusion)\n\n**PepCCD: A Contrastive Conditioned Diffusion Framework for Target-Specific Peptide Generation**  \nJun Zhang, Yangyang Zhou, Tiantian Zhu, Zexuan Zhu  \n[bioRxiv 2025.09.01.673427](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.01.673427v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F04\u002F2025.09.01.673427\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Generative latent diffusion language modeling yields anti-infective synthetic peptides**  \nMarcelo D.T. Torres, Leo Tianlai Chen, Fangping Wan, Pranam Chatterjee, Cesar de la Fuente-Nunez  \n[Cell Biomaterials (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell-biomaterials\u002Ffulltext\u002FS3050-5623(25)00174-6) • [code](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Famp-diffusion)\n\n**Controllable Generation of Pathogen-Specific Antimicrobial Peptides Through Knowledge-Aware Prompt Diffusion Model**  \nYongkang Wang, Menglu Li, Feng Huang, Minyao Qiu, Wen Zhang  \n[Advanced science (Weinheim, Baden-Wurttemberg, Germany)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202507457)\n\n**High-PepBinder: A pLM-Guided Latent Diffusion Framework for Affinity-Aware Target-Specific Peptide Design**  \nQingyi Mao, Silong Zhai, Sen Cao, Renjie Zhu, Wen Xu, Chengyun Zhang, Ning Zhu, Jingjing Guo, Hongliang Duan  \n[bioRxiv 2026.01.12.69898](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.12.698988v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F19\u002F2026.01.12.698988\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n### 5.13 GNN-based\n\n**Generative Pretrained Autoregressive Transformer Graph Neural Network applied to the Analysis and Discovery of Novel Proteins**\nMarkus J. Buehler\n[arXiv:2305.04934](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.04934) • [code](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FMateriomicTransformer)\n\n### 5.14 Score-based\n\n**Microdroplet screening rapidly profiles a biocatalyst to enable its AI-assisted engineering**\nMaximilian Gantz, Simon V. Mathis, Friederike E. H. Nintzel, Paul J. Zurek, Tanja Knaus, Elie Patel, Daniel Boros, Friedrich-Maximilian Weberling, Matthew R. A. Kenneth, Oskar J. Klein, Elliot J. Medcalf, Jacob Moss, Michael Herger, Tomasz S. Kaminski, Francesco G. Mutti, Pietro Lio, Florian Hollfelder\n[bioRxiv (2024.04.08)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.08.588565v1.full.pdf)\n\n**Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences**\nMinsu Kim, Federico Berto, Sungsoo Ahn, Jinkyoo Park\n[arXiv:2306.03111](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.03111)  • [code](https:\u002F\u002Fgithub.com\u002Fkaist-silab\u002Fbootgen)\n\n## 6. Function to Structure\n\n> These models generate protein structures(including side chains) from expected function or recover a part of protein structures(aka. **inpainting**)\n\n### 6.0 Review\n\n**Towards deep learning sequence-structure co-generation for protein design**\nChentong Wang, Sarah Alamdari, Carles Domingo-Enrich, Ava Amini, Kevin K. Yang\n[arXiv:2410.01773](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.01773)\u002F[Current Opinion in Structural Biology (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X25000363)\n\n### 6.1 LSTM-based\n\n**One-sided design of protein-protein interaction motifs using deep learning**\nSyrlybaeva, Raulia, and Eva-Maria Strauch\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.03.30.486144v2) • [code](https:\u002F\u002Fgithub.com\u002Fstrauchlab\u002FiNNterfaceDesign) • [our notes](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F521613546) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bSWkXy56rt8)\n\n### 6.2 Diffusion-based\n\n**Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models**\nNamrata Anand, Tudor Achim\n[GitHub (2022)](https:\u002F\u002Fnanand2.github.io\u002Fproteins\u002F)\u002F[arXiv (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.15019) • [our notes](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F520488133) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=i8fGzddGbU8)\n\n**Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures**\nShitong Luo, Yufeng Su, Xingang Peng, Sheng Wang, Jian Peng, Jianzhu Ma\n[bioRxiv 2022.07.10.499510](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.10.499510v5)\u002F[ICML (2023)](https:\u002F\u002Ficml-compbio.github.io\u002F2023\u002Fpapers\u002FWCBICML2023_paper143.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fluost26\u002Fdiffab) • [hugging face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fluost26\u002FDiffAb)\n\n**Illuminating protein space with a programmable generative model**\nJohn Ingraham, Max Baranov, Zak Costello, Vincent Frappier, Ahmed Ismail, Shan Tie, Wujie Wang, Vincent Xue, Fritz Obermeyer, Andrew Beam, Gevorg Grigoryan\n[Generate Biomedicines Preprint](https:\u002F\u002Fcdn.generatebiomedicines.com\u002Fassets\u002Fingraham2022.pdf)\u002F[bioRxiv 2022.12.01.518682](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.01.518682v1)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-06728-8) • [website](https:\u002F\u002Fgeneratebiomedicines.com\u002Fchroma) • [news](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-01705-y) • [code](https:\u002F\u002Fgithub.com\u002Fgeneratebio\u002Fchroma) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fgeneratebio\u002Fchroma\u002Fblob\u002Fmain\u002Fnotebooks\u002FChromaTutorial.ipynb) • commercial\n\n**Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction**\nZuobai Zhang, Minghao Xu, Aurélie Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang\n[arXiv:2301.12068](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.12068) • [code](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FSiamDiff)\n\n**TRDiffusion**\n[TIANRANG XLab](https:\u002F\u002Fxlab.tianrang.com\u002F)\n[news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002F9rJ6IoJbf6cvz3UqE-rpIg) • [website](https:\u002F\u002Fxlab.tianrang.com\u002FxCREATOR) • commercial\n\n**An all-atom protein generative model**\nAlexander E Chu, Lucy Cheng, Gina El Nesr, Minkai Xu, Po-Ssu Huang\n[bioRxiv 2023.05.24.542194](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.24.542194v1)\u002F[Proceedings of the National Academy of Sciences 121.27 (2024)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002Ffull\u002F10.1073\u002Fpnas.2311500121) • [code](https:\u002F\u002Fgithub.com\u002Falexechu\u002Fprotpardelle)\n\n**DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing**\nYangtian Zhan, Zuobai Zhang, Bozitao Zhong, Sanchit Misra, Jian Tang\n[arxiv 2023.06.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.01794) • [code](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FDiffPack)\n\n**AbDiffuser: Full-Atom Generation of In-Vitro Functioning Antibodies**\nKarolis Martinkus, Jan Ludwiczak, Kyunghyun Cho, Wei-Ching Lian, Julien Lafrance-Vanasse, Isidro Hotzel, Arvind Rajpal, Yan Wu, Richard Bonneau, Vladimir Gligorijevic, Andreas Loukas\n[arXiv:2308.05027](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.05027) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=95w0Ht3m0JY)\n\n**Generative Diffusion Models for Antibody Design, Docking, and Optimization**\nZhangzhi Peng, Chenchen Han, Xiaohan Wang, Dapeng Li, Fajiie Yuan\n[bioRxiv 2023.09.25.559190](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.25.559190v1) • [code](https:\u002F\u002Fgithub.com\u002Fpengzhangzhi\u002Fab_opt) • [website](https:\u002F\u002Fpengzhangzhi.github.io\u002Fab_opt_homepage\u002F)\n\n**Bridging Sequence and Structure: Latent Diffusion for Conditional Protein Generation**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=DP4NkPZOpD)\n\n**Guiding diffusion models for antibody sequence and structure co-design with developability properties**\nAmelia Villegas-Morcillo, Jana M. Weber, Marcel J.T. Reinders\n[bioRxiv 2023.11.22.568230](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.22.568230v1)\u002F[NeurIPS 2023 Generative AI and Biology Workshop](https:\u002F\u002Fopenreview.net\u002Fforum?id=bPcgbKDCUQ) • [code](https:\u002F\u002Fgithub.com\u002Famelvim\u002Fantibody-diffusion-properties)\n\n**A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation**\nYongkang Wang, Xuan Liu, Feng Huang, Zhankun Xiong, Wen Zhang\n[arXiv:2312.15665](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.15665) • [code](https:\u002F\u002Fgithub.com\u002Fwyky481l\u002FMMCD)\n\n**Towards Joint Sequence-Structure Generation of Nucleic Acid and Protein Complexes with SE(3)-Discrete Diffusion**\nAlex Morehead, Jeffrey Ruffolo, Aadyot Bhatnagar, Ali Madani\n[arXiv:2401.06151](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.06151) • [code](https:\u002F\u002Fgithub.com\u002FProfluent-Internships\u002FMMDiff)\n\n**Proteus: exploring protein structure generation for enhanced designability and efficiency**\nChentong Wang, Yannan Qu, Zhangzhi Peng, Yukai Wang, Hongli Zhu, Dachuan Chen, Longxing Cao\n[bioRxiv 2024.02.10.579791](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.10.579791v3) • [code](https:\u002F\u002Fgithub.com\u002FWangchentong\u002FProteus)\n\n**Full-Atom Peptide Design with Geometric Latent Diffusion**\nXiangzhe Kong, Wenbing Huang, Yang Liu\n[arXiv:2402.13555](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.13555)\n\n**A Hybrid Diffusion Model for Stable, Affinity-Driven, Receptor-Aware Peptide Generation**\nR Vishva Saravanan, Soham Choudhuri, Bhaswar Ghosh\n[bioRxiv 2024.03.14.584934](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.14.584934v1) • [code](https:\u002F\u002Fgithub.com\u002FBhaswarGhoshLab\u002FHYDRA) • [dataset](http:\u002F\u002Fhuanglab.phys.hust.edu.cn\u002Fpepbdb\u002F)\n\n**Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization**\nXiangxin Zhou, Dongyu Xue, Ruizhe Chen, Zaixiang Zheng, Liang Wang, Quanquan Gu\n[arXiv:2403.16576](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.16576)\n\n**HelixDiff, a Score-Based Diffusion Model for Generating All-Atom α-Helical Structures**\nXuezhi Xie, Pedro A Valiente, Jisun Kim, and Philip M Kim\n[ACS Central Science (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Facscentsci.3c01488) • [code](https:\u002F\u002Fgithub.com\u002Fxxiexuezhi\u002FHelixDiff)\n\n**Combining transformer and 3DCNN models to achieve co-design of structures and sequences of antibodies in a diffusional manner**\nYue Hu, Feng Tao, Jun Wen Lan, Jing Zhang\n[bioRxiv 2024.04.25.587828](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.25.587828v1) • [code](https:\u002F\u002Fgithub.com\u002FYueHuLab\u002FAlphaPanda)\n\n**Target-Specific De Novo Peptide Binder Design with DiffPepBuilder**\nFanhao Wang, Yuzhe Wang, Laiyi Feng, Changsheng Zhang, Luhua Lai\n[arXiv:2405.00128](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.00128)\u002F[J. Chem. Inf. Model. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.4c00975) • [code](https:\u002F\u002Fgithub.com\u002FYuzheWangPKU\u002FDiffPepBuilder)\n\n**Improving Antibody Design with Force-Guided Sampling in Diffusion Models**\nPaulina Kulytė, Francisco Vargas, Simon Valentin Mathis, Yu Guang Wang, José Miguel Hernández-Lobato, Pietro Liò\n[arXiv:2406.05832](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.05832)\n\n**Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints**\nTian Zhu, Milong Ren, Haicang Zhang\n[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=1YsQI04KaN) • [code](https:\u002F\u002Fgithub.com\u002Fzhanghaicang\u002Fcarbonmatrix_public)\n\n**Antibody-SGM, a Score-Based Generative Model for Antibody Heavy-Chain Design**\nXuezhi Xie, Pedro A. Valiente, Jin Sub Lee, Jisun Kim, Philip M. Kim\n[Journal of Chemical Information and Modeling (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.4c00711) • [code](https:\u002F\u002Fgithub.com\u002Fxxiexuezhi\u002FABSGM)\n\n**Hybrid Diffusion Model for Stable, Affinity-Driven, Receptor-Aware Peptide Generation**\nVishva Saravanan R, Soham Choudhuri, Bhaswar Ghosh\n[J. Chem. Inf. Model. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.4c01020) • [code](https:\u002F\u002Fgithub.com\u002FComputationalBiologyLab-IIITH\u002FHYDRA)\n\n**De novo design of high-affinity protein binders with AlphaProteo**\nVinicius Zambaldi, David La, Alexander E. Chu, Harshnira Patani, Amy E. Danson, Tristan O. C., Kwan, Thomas Frerix, Rosalia G. Schneider, David Saxton, Ashok Thillaisundaram, Zachary Wu, Isabel Moraes, Oskar Lange, Eliseo Papa, Gabriella Stanton, Victor Martin, Sukhdeep Singh, Lai H. Wong, Russ Bates, Simon A. Kohl, Josh Abramson, Andrew W. Senior, Yilmaz Alguel, Mary Y. Wu, Irene M. Aspalter, Katie Bentley, David L.V. Bauer, Peter Cherepanov, Demis Hassabis, Pushmeet Kohli, Rob Fergus, and Jue Wang\n[DeepMind Preprint](https:\u002F\u002Fstorage.googleapis.com\u002Fdeepmind-media\u002FDeepMind.com\u002FBlog\u002Falphaproteo-generates-novel-proteins-for-biology-and-health-research\u002FProtein_Design_White_Paper_2024.pdf)\u002F[arXiv:2409.08022](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.08022) • [blog](https:\u002F\u002Fdeepmind.google\u002Fdiscover\u002Fblog\u002Falphaproteo-generates-novel-proteins-for-biology-and-health-research\u002F)\n\n**DPLM-2: A Multimodal Diffusion Protein Language Model**\nXinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, Quanquan Gu\n[arXiv:2410.13782](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.13782) • [code](https:\u002F\u002Fgithub.com\u002Fbytedance\u002Fdplm) • [website](https:\u002F\u002Fbytedance.github.io\u002Fdplm\u002Fdplm-2)\n\n**E(3)-invaraint diffusion model for pocket-aware peptide generation**\nPo-Yu Liang, Jun Bai\n[arXiv:2410.21335](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.21335) • [code](https:\u002F\u002Fgithub.com\u002FLabJunBMI\u002FE3-invaraint-diffusion-model-for-pocket-aware-peptide-generation)\n\n**Generating All-Atom Protein Structure from Sequence-Only Training Data** \u002F **All-Atom Protein Generation with Latent Diffusion**\nAmy X. Lu, Wilson Yan, Sarah A. Robinson, Kevin K. Yang, Vladimir  Gligorijevic, Kyunghyun Cho, Richard Bonneau, Pieter Abbeel, Nathan Frey\n[bioRxiv 2024.12.02.626353](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.02.626353v2)\u002F[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=5zNRgNMxIS) • [code](https:\u002F\u002Fgithub.com\u002Famyxlu\u002Fplaid) • [blog](https:\u002F\u002Fwww.matricedigitale.it\u002Ftech\u002Fintelligenza-artificiale\u002Fplaid-intelligenza-artificiale-proteine-3d\u002F)\n\n**Efficient protein structure generation with sparse denoising models**\nMichael Jendrusch, Jan O. Korbel\n[bioRxiv 2025.01.31.635780](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.31.635780v1)\u002F[Nat Mach Intell 7, 1429–1445 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01100-z) • [code](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.14711580), [github](https:\u002F\u002Fgithub.com\u002Fmjendrusch\u002Fsalad)\n\n**Neo-1**\n[VANTAI](https:\u002F\u002Fwww.vant.ai\u002Fteam)\npaper not available • [website](https:\u002F\u002Fwww.vant.ai\u002Fneo-1) • commercial\n\n**UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design**\nXiangzhe Kong, Zishen Zhang, Ziting Zhang, Rui Jiao, Jianzhu Ma, Kai Liu, Wenbing Huang, Yang Liu\n[arXiv:2503.19300](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.19300v1)\n\n**PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design**  \nZhenqiao Song, Tiaoxiao Li, Lei Li, Martin Renqiang Min  \n[arXiv:2506.11420](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.11420)\n\n**Antibody Design and Optimization with Multi-scale Equivariant Graph Diffusion Models for Accurate Complex Antigen Binding**  \nJiameng Chen, Xiantao Cai, Jia Wu, Wenbin Hu  \n[arXiv:2506.20957](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.20957v1) • [code](https:\u002F\u002Fgithub.com\u002FPatrick221215\u002FAbMEGD)\n\n**Demystify Protein Generation with Hierarchical Conditional Diffusion Models**  \nZinan Ling, Yi Shi, Da Yan, Yang Zhou, Bo Hui  \n[arXiv:2507.18603](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.18603)\n\n**PXDesign: Fast, Modular, and Accurate De Novo Design of Protein Binders**  \nMilong Ren, Jinyuan Sun, Jiaqi Guan, Cong Liu, Chengyue Gong, Yuzhe Wang, Lan Wang, Qixu Cai, Xinshi Chen, Wenzhi Xiao  \n[technical report](https:\u002F\u002Fprotenix.github.io\u002Fpxdesign\u002Ftechnical_report.pdf)\u002F[bioRxiv 2025.08.15.670450](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.15.670450v1) • [code](https:\u002F\u002Fgithub.com\u002Fbytedance\u002FPXDesignBench) • [server](https:\u002F\u002Fprotenix-server.com\u002F) • [data]([supplements\u002F670450_file03.zip])\n\n**Deep learning-based joint sequence-structure de novo membrane protein design**  \nLucas Rudden, Remo Battig, Vinnie Andrews, Julie Nguyen, Martin Stoll, Lorenzo Scutteri, Michal Winnicki, Melissa J Call, Matthew E Call, Damien Thevenin, Patrick Barth  \n[bioRxiv 2025.08.15.670493](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.15.670493v1)\n\n**Conditional Protein Structure Generation with Protpardelle-1C**  \nTianyu Lu, Richard Shuai, Petr Kouba, Zhaoyang Li, Yilin Chen, Akio Shirali, Jinho Kim, Po-Ssu Huang  \n[bioRxiv 2025.08.18.670959](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.670959v2) • [code](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fprotpardelle-1c\u002Ftree\u002Fmain)\n\n**Generating functional and multistate proteins with a multimodal diffusion transformer**  \nBowen Jing, Anna Sappington, Mihir Bafna, Ravi Shah, Adrina Tang, Rohith Krishna, Adam Klivans, Daniel J Diaz, Bonnie Berger  \n[bioRxiv 2025.09.03.672144](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.03.672144v2) • [code](https:\u002F\u002Fgithub.com\u002Fbjing2016\u002FProDiT)\n\n**Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model**  \nGuanlue Li, Xufeng Zhao, Fang Wu, Sören Laue  \n[NeurIPS 2025 poster](https:\u002F\u002Fopenreview.net\u002Fforum?id=QqCv9SI0X3)\n\n**Peptide design through binding interface mimicry with PepMimic**  \nXiangzhe Kong, Rui Jiao, Haowei Lin, Ruihan Guo, Wenbing Huang, Wei-Ying Ma, Zihua Wang, Yang Liu & Jianzhu Ma  \n[Nat. Biomed. Eng (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41551-025-01507-4) • [code](https:\u002F\u002Fgithub.com\u002Fkxz18\u002FPepMimic)\n\n**Rapid De Novo Antibody Design with GeoFlow-V3**  \nBioGeometry Team  \n[Technical Report](https:\u002F\u002Fopen-res.biogeom.com\u002F2025\u002Fgeoflowv3\u002FGeoFlow_V3_report.pdf) • [website](https:\u002F\u002Fprot.design) • commercial\n\n**AbEgDiffuser: Antibody Sequence-Structure Codesign with Equivariant Graph Neural Networks and Diffusion Models**  \nYibo Zhu, Xiumin Shi, Jingjuan Zhang, Weizhong Sun, Lu Wang  \n[J. Chem. Theory Comput.(2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jctc.5c00990) •  [code](https:\u002F\u002Fgithub.com\u002FShiLab-GitHub\u002FAbEgDiffuser)\n\n**ODesign: A World Model for Biomelecular Interaction Design**  \nODesign Team  \n[Technical Report](https:\u002F\u002Fodesign1.github.io\u002Fstatic\u002Fpdfs\u002Ftechnical_report.pdf) • [website](https:\u002F\u002Fodesign.lglab.ac.cn\u002F) • [code](https:\u002F\u002Fgithub.com\u002FThe-Institute-for-AI-Molecular-Design\u002FODesign)\n\n**BoltzGen: Toward Universal Binder Design**  \nHannes Stark, Felix Faltings, MinGyu Choi, Yuxin Xie, Eunsu Hur, Timothy O’Donnell, Anton Bushuiev, Talip Uçar, Saro Passaro, Weian Mao, Mateo Reveiz, Roman Bushuiev, Tomáš Pluskal, Josef Sivic, Karsten Kreis, Arash Vahdat, Shamayeeta Ray, Jonathan T. Goldstein, Andrew Savinov, Jacob A. Hambalek, Anshika Gupta, Diego A. Taquiri-Diaz, Yaotian Zhang, A. Katherine Hatstat, Angelika Arada, Nam Hyeong Kim, Ethel Tackie-Yarboi, Dylan Boselli, Lee Schnaider, Chang C. Liu, Gene-Wei Li, Denes Hnisz, David M. Sabatini, William F. DeGrado, Jeremy Wohlwend, Gabriele Corso, Regina Barzilay, Tommi Jaakkola\n[Technical Report](https:\u002F\u002Fhannes-stark.com\u002Fassets\u002Fboltzgen.pdf) • [website](https:\u002F\u002Fboltz.bio\u002Fboltzgen) • [model](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fludocomito\u002Fanatomy-of-boltzgen)\n\n**Multimodal diffusion for joint design of protein sequence and structure**  \nShaowen Zhu, Siddhant Gulati, Yuxuan Liu, Siddhi Kotnis, Qing Sun, Yang Shen  \n[Protein Science 34.12 (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70340) • [code](https:\u002F\u002Fgithub.com\u002FShen-Lab\u002FJointDiff)\n\n**Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding**  \nXinheng He, Yijia Zhang, Haowei Lin, Xingang Peng, Xiangzhe Kong, Mingyu Li, Jianzhu Ma  \n[arXiv:2511.04984](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.04984)\n\n**Joint Design of Protein Surface and Structure Using a Diffusion Bridge Model**  \nGuanlue Li, Xufeng Zhao, Fang Wu, Sören Laue  \n[arXiv:2511.16675](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.16675v1) • [code](https:\u002F\u002Fgithub.com\u002Fguanlueli\u002FPepbridge)\n\n**SeedProteo: Accurate De Novo All-Atom Design of Protein Binders**  \nWei Qu, Yiming Ma, Fei Ye, Chan Lu, Yi Zhou, Kexin Zhang, Lan Wang, Minrui Gui, Quanquan Gu  \n[arXiv:2512.24192](http:\u002F\u002Farxiv.org\u002Fabs\u002F2512.24192) • [github](https:\u002F\u002Fseedfold.github.io\u002F)\n\n**De novo design of metalloproteases for targeted amyloid-β cleavage**  \nYannan Qu, Chentong Wang, Hongli Zhu, Yanjun Wang, Longxing Cao  \n[bioRxiv 2026.01.06.697903](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.06.697903v1)\n\n### 6.3 RoseTTAFold-based\n\n**Deep learning methods for designing proteins scaffolding functional sites** \u002F **Scaffolding protein functional sites using deep learning**\nJue Wang, Sidney Lisanza, David Juergens, Doug Tischer, Ivan Anishchenko, Minkyung Baek, Joseph L. Watson, Jung Ho Chun, Lukas F. Milles, Justas Dauparas, Marc Expòsit, Wei Yang, Amijai Saragovi, Sergey Ovchinnikov, David Baker\n[bioRxiv(2021)](https:\u002F\u002Feuropepmc.org\u002Farticle\u002Fppr\u002Fppr419387)\u002F[Science(2022)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.abn2100) • [RFDesign](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRFDesign) • [our notes](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F477854488) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-EJ8SXTBin0) • [RoseTTAFold](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRoseTTAFold) • [Supplementary](https:\u002F\u002Fwww.science.org\u002Fdoi\u002Fsuppl\u002F10.1126\u002Fscience.abn2100\u002Fsuppl_file\u002Fscience.abn2100_sm.pdf), [Other Supplementary](https:\u002F\u002Fwww.science.org\u002Fdoi\u002Fsuppl\u002F10.1126\u002Fscience.abn2100\u002Fsuppl_file\u002Fscience.abn2100_data_s1_and_s2.zip)\n\n**Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models** \u002F **De novo design of protein structure and function with RFdiffusion**\nJoseph L. Watson, David Juergens, Nathaniel R. Bennett, Brian L. Trippe, Jason Yim, Helen E. Eisenach, Woody Ahern, Andrew J. Borst, Robert J. Ragotte, Lukas F. Milles, Basile I. M. Wicky, Nikita Hanikel, Samuel J. Pellock, Alexis Courbet, William Sheffler, Jue Wang, Preetham Venkatesh, Isaac Sappington, Susana Vázquez Torres, Anna Lauko, Valentin De Bortoli, Emile Mathieu, Regina Barzilay, Tommi S. Jaakkola, Frank DiMaio, Minkyung Baek, David Baker\n[Bakerlab Preprint](https:\u002F\u002Fwww.bakerlab.org\u002Fwp-content\u002Fuploads\u002F2022\u002F11\u002FDiffusion_preprint_12012022.pdf)\u002F[bioRxiv 2022.12.09.519842](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.09.519842v2)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-06415-8) • [news](https:\u002F\u002Fwww.bakerlab.org\u002F2022\u002F11\u002F30\u002Fdiffusion-model-for-protein-design\u002F), [news2](https:\u002F\u002Fwww.ipd.uw.edu\u002F2023\u002F03\u002Frf-diffusion-now-free-and-open-source\u002F), [news3](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-023-02227-y) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F10\u002F2022.12.09.519842\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=wIHwHDt2NoI), [lecture2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=828WPIIOwaA) • [RFdiffusion:code](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRFdiffusion), [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fv1.1.1\u002Frf\u002Fexamples\u002Fdiffusion.ipynb) • [blog](https:\u002F\u002Fwww.science.org\u002Fcontent\u002Fblog-post\u002Fprotein-design-ai-way)\n\n**De novo design of high-affinity protein binders to bioactive helical peptides**\nSusana Vázquez Torres, Philip J. Y. Leung, Isaac D. Lutz, Preetham Venkatesh, Joseph L Watson, Fabian Hink, Huu-Hien Huynh, Andy Hsien-Wei Yeh, David Juergens, Nathaniel R. Bennett, Andrew N. Hoofnagle, Eric Huang, Michael J. MacCoss, Marc Expòsit, Gyu Rie Lee, Elif Nihal Korkmaz, Jeff Nivala, Lance Stewart, Joseph M. Rodgers, David Baker\n[bioRxiv 2022.12.10.519862](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.10.519862v1)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-06953-1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F10\u002F2022.12.10.519862\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Joint Generation of Protein Sequence and Structure with RoseTTAFold Sequence Space Diffusion**\nSidney Lyayuga Lisanza, Jacob Merle Gershon, Sam Wayne Kenmore Tipps, Lucas Arnoldt, Samuel Hendel, Jeremiah Nelson Sims, Xinting Li, David Baker\n[bioRxiv 2023.05.08.539766](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.08.539766v1)\u002F[Nat Biotechnol (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02395-w) • [code](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002Fprotein_generator#proteingenerator-generate-sequence-structure-pairs-with-rosettafold) • [hugging face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fmerle\u002FPROTEIN_GENERATOR) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bS71K2U0amA)\n\n**The structural landscape of the immunoglobulin fold by large-scale de novo design**\nJorge Roel-Touris, Lourdes Carcelen, Enrique Marcos\n[bioRxiv 2023.10.03.560637](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.03.560637v1)\u002F[Protein Science (2024)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.4936) • [Supplementary](https:\u002F\u002Fonlinelibrary.wiley.com\u002Faction\u002FdownloadSupplement?doi=10.1002%2Fpro.4936&file=pro4936-sup-0001-supinfo.docx) • [code](https:\u002F\u002Fgithub.com\u002FJorgeRoel\u002Fbetasandwich) • [data](https:\u002F\u002Fzenodo.org\u002Frecord\u002F8380285)\n\n**Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom**\nRohith Krishna, Jue Wang, Woody Ahern, Pascal Sturmfels, Preetham Venkatesh, Indrek Kalvet, Gyu Rie Lee, Felix S Morey-Burrows, Ivan Anishchenko, Ian R Humphreys, Ryan McHugh, Dionne Vafeados, Xinting Li, George A Sutherland, Andrew Hitchcock, C Neil Hunter, Minkyung Baek, Frank DiMaio, David Baker\n[bioRxiv 2023.10.09.561603](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.09.561603v1)\u002F[Science](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adl2528) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F10\u002F09\u002F2023.10.09.561603\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fbaker-laboratory\u002FRoseTTAFold-All-Atom)\n\n**Amalga: Designable Protein Backbone Generation with Folding and Inverse Folding Guidance**\nShugao Chen, Ziyao Li, Xiangxiang Zeng, Guolin Ke\n[bioRxiv 2023.11.07.565939](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.07.565939v1)\n\n**Replicating enzymatic activity by positioning active sites with synthetic protein scaffolds**  \nYujing Ding, Shanshan Zhang, Henry Hess, Xian Kong, Yifei Zhang  \n[bioRxiv 2024.01.31.577620](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.01.31.577620v1)\u002F[Advanced Science (2025)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202500859) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F01\u002F31\u002F2024.01.31.577620\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFjoint\u002FProteinMPNN-based\n\n**Accurate single domain scaffolding of three non-overlapping protein epitopes using deep learning**\nKarla M Castro, Joseph L Watson, Jue Wang, Joshua Southern, Reyhaneh Ayardulabi, Sandrine Georgeon, Stephane Rosset, David Baker, Bruno E Correia\n[bioRxiv 2024.05.07.592871](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.07.592871v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F05\u002F10\u002F2024.05.07.592871\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Diversifying de novo TIM barrels by hallucination**\nBeck, Julian, Sooruban Shanmugaratnam, and Birte Höcker\n[Protein Science 33.6 (2024)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.5001)\n\n**De novo designed proteins neutralize lethal snake venom toxins**\nSusana Vázquez Torres, Melisa Benard Valle, Stephen P. Mackessy, Stefanie K. Menzies, Nicholas R. Casewell, Shirin Ahmadi, Nick J. Burlet, Edin Muratspahić, Isaac Sappington, Max D.Overath, Esperanza Rivera-de-Torre, Jann Ledergerber, Andreas H. Laustsen, Kim Boddum, Asim K.Bera, Alex Kang,Evans Brackenbrough, Iara A. Cardoso, Edouard P. Crittenden, Rebecca J.Edge, Justin Decarreau, Robert J. Ragotte, Arvind S. Pillai, Mohamad Abedi, Hannah L. Han,Stacey R. Gerben, Analisa Murray, Rebecca Skotheim, Lynda Stuart, Lance Stewart, Thomas J.A. Fryer, Timothy P. Jenkins, David Baker\n[PREPRINT (Version 1) available at Research Square](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-4402792\u002Fv1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-08393-x)\n\n**De novo design of metal-oxide templating proteins**  \nAmijai Saragovi, Harley Pyles, Timothy F. Huddy, Wenzhao Dai, Xinqi Li, Andrew J. Borst, Nikita Hanikel, Alexis Courbet, Paul Kwon, Fátima A. Dávila-Hernández, Ryan Kibler, Dionne K. Vafeados, Aza Allen, Kenneth D. Carr, Asim K. Bera, Alex Kang, Evans Brackenbrough, Sakshi Schmid, Yuna Bae, Lance Stewart, Shuai Zhang, James De Yoreo, David Baker  \n[bioRxiv 2024.06.24.600095](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.24.600095v2)\n\n**Diffusing protein binders to intrinsically disordered proteins**\nCaixuan Liu, Kejia Wu, Hojun Choi, Hannah Han, Xueli Zhang, Joseph L Watson, Sara Shijo, Asim K Bera, Alex Kang, Evans Brackenbrough, Brian Coventry, Derrick R Hick, Andrew N Hoofnagle, Ping Zhu, Xingting Li, Justin Decarreau, Stacey R Gerben, Wei Yang, Xinru Wang, Mila Lamp, Analisa Murray, Magnus Bauer, David Baker\n[bioRxiv 2024.07.16.603789](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.16.603789v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09248-9) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F16\u002F2024.07.16.603789\u002FDC1\u002Fembed\u002Fmedia-1.mov)\n\n**Parametrically guided design of beta barrels and transmembrane nanopores using deep learning**\nDavid E. Kim, Joseph L. Watson, David Juergens, Sagardip Majumder, Stacey R. Gerben, Alex Kang, Asim K. Bera, Xinting Li, David Baker\n[bioRxiv 2024.07.22.604663](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.22.604663v1)\u002F[Proc. Natl. Acad. Sci. U.S.A. 122 (38) e2425459122](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2425459122) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F23\u002F2024.07.22.604663\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code1](https:\u002F\u002Fgithub.com\u002Fdavidekim\u002Fparametric_barrels), [code2](https:\u002F\u002Fgithub.com\u002Fsagardipm\u002FdenovoPores)\n\n**Computational design of highly active de novo enzymes**\nMarkus Braun, Adrian Tripp, Morakot Chakatok, Sigrid Kaltenbrunner, Massimo G. Totaro, David Stoll, Aleksandar Bijelic, Wael Elaily, Shlomo Yakir Yakir Hoch, Matteo Aleotti, Melanie Hall, Gustav Oberdorfer\n[bioRxiv 2024.08.02.606416](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.02.606416v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F03\u002F2024.08.02.606416\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Computational design of serine hydrolases**\nAnna Lauko, Samuel J Pellock, Ivan Anischanka, Kiera H Sumida, David Juergens, Woody Ahern, Alex Shida, Andrew Hunt, Indrek Kalvet, Christoffer Norn, Ian R Humphreys, Cooper S Jamieson, Alex Kang, Evans Brackenbrough, Banumathi Sankaran, K N Houk, David Baker\n[bioRxiv 2024.08.29.610411](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.29.610411v1)\u002F[Science0,eadu2454](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adu2454) • [news](https:\u002F\u002Fwww.asimov.press\u002Fp\u002Fai-enzymes)\n\n**De novo design of Ras isoform selective binders**\nJason Zhaoxing Zhang, Xinting Li, Caixuan Liu, Hanlun Jiang, Kejia Wu, David Baker\n[bioRxiv 2024.08.29.610300](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.29.610300v1)\u002F[Cell Chemical Biology](https:\u002F\u002Fwww.cell.com\u002Fcell-chemical-biology\u002Ffulltext\u002FS2451-9456(26)00063-2)\n\n**Improved protein binder design using beta-pairing targeted RFdiffusion**\nIsaac Sappington, Martin Toul, David S. Lee, Stephanie A. Robinson, Inna Goreshnik, Clara McCurdy, Tung Ching Chan, Nic Buchholz, Buwei Huang, Dionne Vafeados, Mariana Garcia-Sanchez, Nicole Roullier, Matthias Glögl, Chris Kim, Joseph L. Watson, Susana Vázquez Torres, Koen H. G. Verschueren, Kenneth Verstraete, Cynthia S. Hinck, Melisa Benard-Valle, Brian Coventry, Jeremiah Nelson Sims, Green Ahn, Xinru Wang, Andrew P. Hinck, Timothy P. Jenkins, Hannele Ruohola-Baker, Steven M. Banik, Savvas N. Savvides, David Baker\n[bioRxiv 2024.10.11.617496](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.11.617496v1)\u002F[preprint](https:\u002F\u002Fassets-eu.researchsquare.com\u002Ffiles\u002Frs-5473963\u002Fv1_covered_81143f0e-3579-4f09-86c3-c0e316288e3a.pdf) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F10\u002F12\u002F2024.10.11.617496\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Afpdb–an efficient structure manipulation package for AI protein design**\nYingyao Zhou, Jiayi Cox, Bin Zhou, Steven Zhu, Yang Zhong, Glen Spraggon\n[Bioinformatics (2024): btae654](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtae654\u002F7876263) • [code](https:\u002F\u002Fgithub.com\u002Fdata2code\u002Fafpdb) • [website](https:\u002F\u002Fpypi.org\u002Fproject\u002Fafpdb)\n\n**GRACE: Generative Redesign in Artificial Computational Enzymology**\nRuei-En, HuChi-Hua, Yu I-Son Ng\n[ACS Synthetic Biology (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.4c00624) • [code](https:\u002F\u002Fgithub.com\u002FRyan-Hu-Hu-Hu\u002FGRACE)\n\n**Computational Design of Metallohydrolases**\nDonghyo Kim, Seth M. Woodbury, Woody Ahern, Indrek Kalvet, Nikita Hanikel, Saman Salike, Samuel J. Pellock, Anna Lauko, Donald Hilvert, David Baker\n[bioRxiv 2024.11.13.623507](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.13.623507v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09746-w) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F14\u002F2024.11.13.623507\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Design of facilitated dissociation enables control over cytokine signaling duration**\nAdam J. Broerman, Christoph Pollmann, Mauriz A. Lichtenstein, Mark D. Jackson, Maxx H. Tessmer, Won Hee Ryu, Mohamad H. Abedi, Danny D. Sahtoe, Aza Allen, Alex Kang, Joshmyn De La Cruz, Evans Brackenbrough, Banumathi Sankaran, Asim K. Bera, Daniel M. Zuckerman, Stefan Stoll, Florian Praetorius, Jacob Piehler, David Baker\n[bioRxiv 2024.11.15.623900](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.15.623900v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09549-z) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F16\u002F2024.11.15.623900\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Accurate de novo design of high-affinity protein binding macrocycles using deep learning**\nStephen A. Rettie, David Juergens, Victor Adebomi, Yensi Flores Bueso, Qinqin Zhao, Alexandria N. Leveille, Andi Liu, Asim K. Bera, Joana A. Wilms, Alina Üffing, Alex Kang, Evans Brackenbrough, Mila Lamb, Stacey R. Gerben, Analisa Murray, Paul M. Levine, Maika Schneider, Vibha Vasireddy, Sergey Ovchinnikov, Oliver H. Weiergräber, Dieter Willbold, Joshua A. Kritzer, Joseph D. Mougous, David Baker, Frank DiMaio, Gaurav Bhardwaj\n[bioRxiv 2024.11.18.622547](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.18.622547v1)\u002F[Nat Chem Biol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-01929-w) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F18\u002F2024.11.18.622547\u002FDC1\u002Fembed\u002Fmedia-1.zip) • [code](https:\u002F\u002Fzenodo.org\u002Frecords\u002F15264344)\n\n**Engineering de novo binder CAR-T cell therapies with generative AI**\nMarkus Mergen, Daniela Abele, Naile Koleci, Alba Schmahl Fernandez, Maya Sugden, Noah Holzleitner, Andreas Carr, Leonie Rieger, Valentina Leone, Maximilian Reichert, Karl-Ludwig Laugwitz, Florian Bassermann, Dirk H. Busch, Julian Grünewald, Andrea Schmidts\n[bioRxiv 2024.11.25.625151](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.25.625151v1) • RFDiffusion\u002FProteinMPNN-based\n\n**CycleDesigner: Leveraging RFdiffusion and HighFold to Design Cyclic Peptide Binders for Specific Targets**\nChenhao Zhang, Zhenyu Xu, Kang Lin, Chengyun Zhang, Wen Xu, Hongliang Duan\n[bioRxiv 2024.11.27.625581](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.27.625581v1) • RFDiffusion\u002FProteinMPNN-based\n\n**De novo designed pMHC binders facilitate T cell induced killing of cancer cells**\nKristoffer Haurum Johansen, Darian Stephan Wolff, Beatrice Scapolo, Monica L. Fernández Quintero, Charlotte Risager Christensen, Johannes R. Loeffler, Esperanza Rivera-de-Torre, Max D. Overath, Kamilla Kjærgaard Munk, Oliver Morell, Marie Christine Viuff, Alberte T. Damm Englund, Mathilde Due, Stefano Forli, Emma Qingjie Andersen, Jordan Sylvester Fernandes, Suthimon Thumtecho, Andrew B. Ward, Maria Ormhøj, Sine Reker Hadrup, Timothy P. Jenkins\n[bioRxiv 2024.11.27.624796](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.27.624796v1)\u002F[Science389,380-385(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adv0422) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F03\u002F2024.11.27.624796\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Design of high specificity binders for peptide-MHC-I complexes**  \nBingxu Liu, Nathan F. Greenwood, Julia E. Bonzanini, Amir Motmaen, Jazmin Sharp, Chunyu Wang, Gian Marco Visani, Dionne K. Vafeados, Nicole Roullier, Armita Nourmohammad, K. Christopher Garcia, David Baker  \n[bioRxiv 2024.11.28.625793](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.28.625793v1)\u002F[Science389,386-391(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adv0185)\n\n**Target-conditioned diffusion generates potent TNFR superfamily antagonists and agonists**\nMatthias Glögl, Aditya Krishnakumar, Robert J. Ragotte, Inna Goreshnik, Brian Coventry, Asim K. Bera, Alex Kang, Emily Joyce, Green Ahn, Buwei Huang, Wei Yang, Wei Chen, Mariana Garcia Sanchez, Brian Koepnick, David Baker\n[Science 386.6726 (2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adp1779)\n\n**Design of a Water-Soluble CD20 Antigen with Computational Epitope Scaffolding**\nZhiyuan Yao, Brian Kuhlman\n[bioRxiv 2024.12.05.627087](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.05.627087v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F06\u002F2024.12.05.627087\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F06\u002F2024.12.05.627087\u002FDC2\u002Fembed\u002Fmedia-2.zip) • RFDiffusion-based\n\n**Inhibiting heme-piracy by pathogenic Escherichia coli using de novo-designed proteins**\nDaniel R Fox, Kazem Asadollahi, Imogen G Samuels, Bradley Spicer, Ashleigh Kropp, Chris Lupton, Kevin Lim, Chunxiao Wang, Hariprasad Venugopal, Marija Dramicanin, Gavin J Knott, Rhys Grinter\n[bioRxiv 2024.12.05.626953](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.05.626953v1)\u002F[Nat Commun 16, 6066 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-60612-9) • RFDiffusion\u002FProteinMPNN-based\n\n**De novo design of potent CRISPR-Cas13 inhibitors**\nCyntia Taveneau, Her Xiang Chai, Jovita D'Silva, Rebecca S Bamert, Brooke K Hayes, Roland W Calvert, Daniel J Curwen, Fabian Munder, Lisandra L Martin, Jeremy J Barr, Rhys Grinter, Gavin J Knott\n[bioRxiv 2024.12.05.626932](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.05.626932v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F06\u002F2024.12.05.626932\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFDiffusion\u002FProteinMPNN-based\n\n**Development of a De Novo Protein Binder that Inhibits the Alpha Kinase eEF2K**\nKody A Klupt, Ethan Belrose, Zongchao Jia\n[bioRxiv 2024.12.10.627789](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.10.627789v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F11\u002F2024.12.10.627789\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFDiffusion\u002FProteinMPNN-based\n\n**Generating and evaluating diverse sequences for protein backbones**\nYo Akiyama, Sergey Ovchinnikov\n[Machine Learning for Structural Biology Workshop, NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FGenerating_and_evaluating_diverse_sequences_for_protein_backbones.pdf) • RFDiffusion\u002FProteinMPNN-based\n\n**De novo design and structure of a peptide-centric TCR mimic binding module**\nKarsten D. Householder, Xinyu Xiang, Kevin M. Jude, Arthur Deng, Matthias Obenaus, Steven C. Wilson, Xiaojing Chen, Nan Wang, K. Christopher Garcia\n[bioRxiv 2024.12.16.628822](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.16.628822v1)\u002F[Science389,375-379(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adv3813) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F20\u002F2024.12.16.628822\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFDiffusion\u002FProteinMPNN-based\n\n**Design of pseudosymmetric protein hetero-oligomers**\nRyan D. Kibler, Sangmin Lee, Madison A. Kennedy, Basile I. M. Wicky, Stella M. Lai, Marius M. Kostelic, Ann Carr, Xinting Li, Cameron M. Chow, Tina K. Nguyen, Lauren Carter, Vicki H. Wysocki, Barry L. Stoddard & David Baker\n[Nat Commun 15, 10684 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-54913-8) • [code](https:\u002F\u002Fgithub.com\u002Frdkibler\u002FStepwise-design-of-pseudosymmetric-protein-hetero-oligomers)\n\n**Bottom-up design of calcium channels from defined selectivity filter geometry**\nYulai Liu, Connor Weidle, Ljubica Mihaljevic, Joseph L. Watson, Zhe Li, Le Tracy Yu, Sagardip Majumder, Andrew J. Borst, Kenneth D. Carr, Ryan D. Kibler, Tamer M. Gamal El-Din, William A. Catterall, David Baker\n[bioRxiv 2024.12.19.629320](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.19.629320v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F20\u002F2024.12.19.629320\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • RFDiffusion\u002FProteinMPNN-based\n\n**Solubilization of Membrane Proteins using designed protein WRAPS**\nLjubica Mihaljević, David E. Kim, Helen E. Eisenach, Pooja D. Bandawane, Andrew J. Borst, Alexis Courbet, Everton Bettin, Qiushi Liu, Connor Weidle, Sagardip Majumder, Xinting Li, Mila Lamb, Analisa Nicole Azcárraga Murray, Rashmi Ravichandran, Elizabeth C. Williams, Shuyuan Hu, Lynda Stuart, Linda Grillová, Nicholas R. Thomson, Pengxiang Chang, Melissa J. Caimano, Kelly L. Hawley, Neil P. King, David Baker\n[bioRxiv 2025.02.04.636539](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.04.636539v1) • RFDiffusion\u002FProteinMPNN-based\n\n**Inhibition of ice recrystallization with designed twistless helical repeat proteins**\nRobbert J. de Haas, Harley Pyles, Timothy F. Huddy, Jannick van Ossenbruggen, Chuanbao Zheng, Daniëlle van den Broek, Ann Carr, Asim K. Bera, Alex Kang, Evans Brackenbrough, Emily Joyce, Banumathi Sankaran, David Baker, Ilja K. Voets, Renko de Vries\n[bioRxiv 2025.03.09.642278](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.09.642278v1)\u002F[Proceedings of the National Academy of Sciences 122.48 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2514871122) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F13\u002F2025.03.09.642278\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.13763849) • RFDiffusion\u002FProteinMPNN-based\n\n**RoseTTAFold diffusion-guided short peptide design: a case study of binders against Keap1\u002FNrf2**\nFrancesco Morena, Chiara Cencinia, Carla Emiliani, Sabata Martinoa\n[Computational and Structural Biotechnology Journal (2025)](https:\u002F\u002Fwww.csbj.org\u002Farticle\u002FS2001-0370(25)00061-3\u002Ffulltext) • RFDiffusion\u002FProteinMPNN-based\n\n**De novo design of miniprotein agonists and antagonists targeting G protein-coupled receptors**\nEdin Muratspahić, David Feldman, David E. Kim, Xiangli Qu, Ana-Maria Bratovianu, Paula Rivera-Sánchez, Federica Dimitri, Jason Cao, Brian P. Cary, Matthew J. Belousoff, Peter Keov, Qingchao Chen, Yue Ren, Justyn Fine, Isaac Sappington, Thomas Schlichthaerle, Jason Z. Zhang, Arvind Pillai, Ljubica Mihaljević, Magnus Bauer, Susana Vázquez Torres, Amir Motmaen, Gyu Rie Lee, Long Tran, Xinru Wang, Inna Goreshnik, Dionne K. Vafeados, Justin E. Svendsen, Parisa Hosseinzadeh, Nicolai Lindegaard, Matthäus Brandt, Yann Waltenspühl, Kristine Deibler, Luke Oostdyk, William Cao, Lakshmi Anantharaman, Lance Stewart, Lauren Halloran, Jamie B. Spangler, Patrick M. Sexton, Bryan L. Roth, Brian E. Krumm, Denise Wootten, Christopher G. Tate, Christoffer Norn, David Baker\n[bioRxiv 2025.03.23.644666](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.23.644666v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F23\u002F2025.03.23.644666\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Atom level enzyme active site scaffolding using RFdiffusion2**\nWoody Ahern, Jason Yim, Doug Tischer, Saman Salike, Seth Woodbury, Donghyo Kim, Indrek Kalvet, Yakov Kipnis, Brian Coventry, Han Altae-Tran, Magnus Bauer, Regina Barzilay, Tommi Jaakkola, Rohith Krishna, David A Baker\n[bioRxiv 2025.04.09.648075](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.09.648075v2)\u002F[Nat Methods (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-025-02975-x) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F04\u002F10\u002F2025.04.09.648075.1\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bd6bFXRmEGA&pp=ygUMcmZkaWZmdXNpb24y) • [code](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRFdiffusion2)\n\n**Generative protein design meets synthetic porphyrin assembly**\nHiroaki Inaba, Hiroki Onoda, Takayuki Uchihashi, Atsunori Oshima and Osami Shoji\n[ChemRxiv. 2025](https:\u002F\u002Fchemrxiv.org\u002Fengage\u002Fchemrxiv\u002Farticle-details\u002F67f4f96381d2151a0284768f) • RFDiffusion\u002FProteinMPNN-based\n\n**Development of AI-designed protein binders for detection and targeting of cancer cell surface proteins**  \nBianca Broske, Sophie C. Binder, Benjamin A. McEnroe, Tim N. Kempchen, Caroline I. Fandrey, Julia M. Messmer, Elisabeth Tan, Peter Konopka, Dominic Ferber, Michelle C. R. Yong, Marie Kleinert, Alexander Hoch, Katja Blumenstock, Jan M. P. Tödtmann, Johannes Oldenburg, Heiko Rühl, Alexander Semaan, Marieta I. Toma, Kristina Markova, Sebastian Kobold, Tim Rollenske, Matthias Geyer, Stephan Menzel, Tobias Bald, Jonathan L. Schmid-Burgk, Gregor Hagelueken, Michael Hölzel  \n[bioRxiv 2025.05.11.652819](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.11.652819v1) • [code](https:\u002F\u002Fgithub.com\u002FHoelzelLab\u002FIEO_AI_Binder_cancer_surface_2025) • RFDiffusion\u002FProteinMPNN-based\n\n**Poxvirus targeted by RFdiffusion peptide-binders**  \nJ. Coll  \n[bioRxiv 2025.05.14.654163](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.14.654163v1) • RFDiffusion\u002FProteinMPNN-based\n\n**AI assisted design of ligands for Lipocalin-2**  \nJacopo Sgrignani, Sara Buscarini, Patrizia Locatelli, Concetta Guerra, Alberto Furlan, Yingyi Chen, Giada Zoppi, Andrea Cavalli  \n[bioRxiv 2025.05.18.654718](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.18.654718v1)\u002F[Frontiers in Immunology, 2025](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fimmunology\u002Farticles\u002F10.3389\u002Ffimmu.2025.1631868) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F05\u002F19\u002F2025.05.18.654718\u002FDC1\u002Fembed\u002Fmedia-1.docx) • RFDiffusion\u002FProteinMPNN-based\n\n**De novo luciferases enable multiplexed bioluminescence imaging**  \nJulie Yi-Hsuan Chen, Qing Shi, Xue Peng, Jean de Dieu Habimana, James Wang, William Sobolewski, Andy Hsien-Wei Yeh  \n[Chem 11.3 (2025)](https:\u002F\u002Fwww.cell.com\u002Fchem\u002Ffulltext\u002FS2451-9294(24)00539-4) • RFjoint\u002FProteinMPNN-based\n\n**Bioinformatics classification of the MgtE Mg2+ channel and de novo protein design for the stabilization of its novel subclass**  \nZhixuan Zhao, Kimiho Omae, Wataru Iwasaki, Ziyi Zhang, Fazhi Pan, Eun-Jin Lee, Motoyuki Hattori  \n[bioRxiv 2025.05.26.656215](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.26.656215v1) • [code](https:\u002F\u002Fgithub.com\u002F0mae\u002Fmgte_short) • RFDiffusion\u002FProteinMPNN-based\n\n**De Novo Structure-Based Design of TEM-171 β-Lactamase Protein Inhibitors Using Integrated Deep Learning and Multi-Scale Simulations to Combat Bacterial Resistance**  \nKrishiv Potluri  \n[bioRxiv 2025.06.23.661177](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.23.661177v1) • [code](https:\u002F\u002Fgithub.com\u002Fkishpish\u002Ftem171-inhibitor-pipeline) • RFDiffusion\u002FProteinMPNN-based\n\n**Generation of structure-guided pMHC-I libraries using Diffusion Models**  \nSergio Mares, Ariel Espinoza Weinberger, Nilah M. Ioannidis  \n[arXiv:2507.08902](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.08902v1) • [code](https:\u002F\u002Fgithub.com\u002Fsermare\u002Fstruct-mhc-dev) • RFDiffusion\u002FProteinMPNN-based\n\n**CycleDesigner: Leveraging CycRFdiffusion and HighFold to Design Cyclic Peptide Binders for Specific Targets**  \nChenhao ZhangZhenyu XuKang LinNing ZhuChengyun ZhangWen XuJingjing GuoAn SuChengxi LiHongliang Duan  \n[J. Chem. Inf. Model. 2025](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c00227)\n\n**De novo design of protein binders to stabilize monomeric TDP-43 and inhibit its pathological aggregation**  \nGangyu Sun, Xiang Li, Jiaojiao Hu, Tianbin Yang, Cong Liu, Zhizhi Wang, Dan Li, and Wenqing Xu  \n[Proc. Natl. Acad. Sci. U.S.A. 122 (36) e2505320122](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2505320122)\n\n**AI-generated MLH1 small binder improves prime editing efficiency**  \nJu-Chan Park, Heesoo Uhm, Yong-Woo Kim, Ye Eun Oh, Jang Hyeon Lee, Jiyun Yang, Kyoungmi Kim, Sangsu Bae  \n[Cell (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(25)00799-8) • [code](https:\u002F\u002Fgithub.com\u002Fbaelab\u002FPE-SB)\n\n**De novo design of light-regulated dynamic proteins using deep learning**  \nPATRICK BARTH, Lorenzo Scutteri, Luciano Abriata, Shuhao Zhang, Aysima Hacisuleyman, Kelvin Lau, Florence Pojer, Sahand Jamal Rahi  \n[bioRxiv 2025.08.12.669910](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.12.669910v1) • RFDiffusion\u002FProteinMPNN-based\n\n**De Novo Design of Miniprotein Inhibitors of Bacterial Adhesins**  \nAdam M. Chazin-Gray, Tuscan R. Thompson, Edward D. B. Lopatto, Pearl Magala, Patrick W. Erickson, Andrew C. Hunt, Anna Manchenko, Pavel Aprikian, Veronika Tchesnokova, Irina Basova, Denise A. Sanick, Kevin O. Tamadonfar, Morgan R. Timm, Jerome S. Pinkner, Karen W. Dodson, Alex Kang, Emily Joyce, Asim K. Bera, Aaron J. Schmitz, Ali H. Ellebedy, Kelli L. Hvorecny, Mark J. Cartwright, Andyna Vernet, Sarai Bardales, Desmond White, Rachel E. Klevit, Evgeni V. Sokurenko, Scott J. Hultgren, David Baker  \n[bioRxiv 2025.08.18.670751](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.670751v1) • RFDiffusion\u002FProteinMPNN-based\n\n**Computationally Designed Nanobinders as Affinity Ligands in Diagnostic and Therapeutic Applications**\nJueun Jeon, Q. John Liu, Hyunkyung Woo, Isabel Barth, Yoonjeong Choi, L. Jessica Sang, Hakho Lee  \n[J. Am. Chem. Soc.(2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacs.5c11289) • RFDiffusion\u002FProteinMPNN-based\n\n**Automated and modular protein binder design with BinderFlow**  \nCarlos Chacon-Sanchez, Nayim Gonzalez-Rodriguez, Oscar Llorca, Rafael Fernandez-Leiro  \n[bioRxiv 2025.09.10.675490](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.10.675490v2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F18\u002F2025.09.10.675490\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fbinderflow) • RFDiffusion\u002FProteinMPNN-based\n\n**De novo Design of All-atom Biomolecular Interactions with RFdiffusion3**  \nJasper Kenneth Veje Butcher, Rohith Krishna, Raktim Mitra, Rafael Isaac Brent, Yanjing Li, Nathaniel Corley, Paul Kim, Jonathan Funk, Simon Valentin Mathis, Saman Salike, Aiko Muraishi, Helen Eisenach, Tuscan Rock Thompson, Jie Chen, Yuliya Politanska, Enisha Sehgal, Brian Coventry, Odin Zhang, Bo Qiang, Kieran Didi, Maxwell Kazman, Frank DiMaio, David Baker  \n[bioRxiv 2025.09.18.676967](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.18.676967v2) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F18\u002F2025.09.18.676967\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002Ffoundry)\n\n**AI-Guided Design of Cyclic Peptide Binders Targeting TREM2 Using CycleRFdiffusion and Experimental Validation**  \nSungwoo Cho, Renjie Zhu, Katarzyna Kuncewicz, Hongliang Duan, Moustafa Gabr  \n[bioRxiv 2025.09.18.676322](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.18.676322v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F21\u002F2025.09.18.676322\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**ProteinDJ: a high-performance and modular protein design pipeline**  \nDylan Silke, Julie Iskander, Junqi Pan, Andrew P Thompson, Anthony T Papenfuss, Isabelle S Lucet, Joshua M Hardy  \n[bioRxiv 2025.09.24.678028](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.24.678028v1)\u002F[Protein Science. 2026](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70464)\n\n**Computational epitope profiling and AI-driven protein engineering enable rational design of multi-epitope vaccines against Mycobacterium tuberculosis**  \nXinfeng Li, Xinyu Tao, Mingyue Zhong, Yiyao Wang, Heng Xue, Binda T. Andongma, Shan-Ho Chou, Hongping Wei, Jin He, Hang Yang  \n[Computational and Structural Biotechnology Journal (2025)](https:\u002F\u002Fwww.csbj.org\u002Farticle\u002FS2001-0370(25)00375-7)\n\n**Computational design of pH-sensitive binders**  \nGreen Ahn, Brian Coventry, Ella Haefner, Shayan Sadre, Jenny Hu, Mimosa Van, Buwei Huang, Isaac Sappington, Adam J. Broerman, Mauriz A. Lichtenstein, Matthias Glögl, Inna Goreshnik, Dionne Vafeados, David Baker  \n[bioRxiv 2025.09.29.678932](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.29.678932v1)\n\n**De novo design of phospho-tyrosine peptide binders**  \nMagnus S Bauer, Jason Z Zhang, Kejia Wu, Gyu Rie Lee, Brian Coventry, Kody A Klupt, Jiuhan Shi, Rafael I Brent, Xinting Li, Carolina Moller, Nicole Roullier, Dionne K Vafeados, Indrek Kalvet, Rebecca K Skotheim, Siyu Zhu, Amir Motmaen, Luca C Herrmann, Pascal Sturmfels, Doug Tischer, Han Raut Altae-Tran, David Juergens, Rohith Krishna, Woody Ahern, Jason Yim, Asim K Bera, Alex Kang, Emily Joyce, Andrew Lu, Lance Stewart, Frank DiMaio, David Baker  \n[bioRxiv 2025.09.29.678898](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.29.678898v1)\n\n**De novo design of RNA and nucleoprotein complexes**  \nAndrew H Favor, Riley Quijano, Elizaveta Chernova, Andrew Kubaney, Connor Weidle, Morgan A Esler, Lilian McHugh, Ann Carr, Yang Hsia, David Juergens, Kenneth D Carr, Paul T Kim, Yuliya Politanska, Enisha Sehgal, Paul S Kwon, Robert J Pecoraro, Cameron Glasscock, Andrew J Borst, Frank DiMaio, Barry L Stoddard, David Baker  \n[bioRxiv 2025.10.01.679929](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.01.679929v1)\n\n**Geometric Tuning of Cytokine Receptor Association Modulates Synthetic Agonist Signaling**  \nMarc Expòsit, Mohamad Abedi, Aditya Krishnakumar, Shruti Jain, Ta-Yi Yu, Timothy R. Hercus, Divij Mathew, Sophie Gray-Gaillard, Zhijie Chen, William S. Grubbe, Andrew Favor, Winnie L. Kan, Thomas Schlichthaerle, Wei Chen, Michael W. Parker, Juan L. Mendoza, Angel F. Lopez, E. John Wherry, David Baker  \n[bioRxiv 2025.10.12.681819](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.12.681819v1)\n\n**High-Throughput De Novo Protein Design Yields Novel Immunomodulatory Agonists**  \nMohamad Abedi, Marc Expòsit, Brian Coventry, Divij Mathew, Shruti Jain, Aditya Krishnakumar, Inna Goreshnik, Sophie L. Gray-Gaillard, Margaret Lunn-Halbert, Ta-Yi Yu, Matthias Glögl, Uma Mitchell, Riya Keshri, Jung Ho Chun, Hannele Ruohola-Baker, E. John Wherry, David Baker  \n[bioRxiv 2025.10.12.681920](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.12.681920v1)\n\n**Bottom-up design of Ca2+ channels from defined selectivity filter geometry**  \nYulai Liu, Connor Weidle, Ljubica Mihaljević, Joseph L. Watson, Zhe Li, Le Tracy Yu, Sagardip Majumder, Andrew J. Borst, Kenneth D. Carr, Ryan D. Kibler, Tamer M. Gamal El-Din, William A. Catterall & David Baker  \n[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09646-z) • [code](https:\u002F\u002Fgithub.com\u002Fylliu15\u002F2025_Ca_channel)\n\n**Targeted Inhibition of Colorectal Carcinoma Using a Designed CEA-Binding Protein to Deliver p53 Protein and TCF\u002FLEF Transcription Factor Decoy DNA**  \nWen Wang, Xuan Sun and Geng Wu  \n[International Journal of Molecular Sciences. 2025](https:\u002F\u002Fwww.mdpi.com\u002F1422-0067\u002F26\u002F20\u002F9846) • [Supplementary](https:\u002F\u002Fwww.mdpi.com\u002Farticle\u002F10.3390\u002Fijms26209846\u002Fs1) • RFDiffusion\u002FProteinMPNN-based\n\n**Hybrid AI\u002Fphysics pipeline for miniprotein binder prioritization: application to the BRD3 ET domain**  \nJokent Gaza, Monica J. Roth, Gaetano T. Montelione and Alberto Perez  \n[Chemical Communications (2025)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlelanding\u002F2025\u002Fcc\u002Fd5cc05032d) • [code](https:\u002F\u002Fgithub.com\u002FPDNALab\u002FMiniprotein_Design)\n\n**Computational design of superstable proteins through maximized hydrogen bonding**  \nBin Zheng, Zhuojian Lu, Shangchen Wang, Lichao Liu, Mingjun Ao, Yurui Zhou, Guojing Tang, Ruishi Wang, Yuanhao Liu, Hantian Zhang, Yinying Meng, Jun Qiu, Tianfu Feng, Ziyi Wang, Renming Liu, Yuelong Xiao, Yutong Liu, Ziling Wang, Yifen Huang, Yajun Jiang & Peng Zheng  \n[Nat. Chem. (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41557-025-01998-3)\n\n**De Novo Design of High-Affinity HER2-Targeting Protein Minibinders**  \nYize Zhao, Wenping Wei, Zijun Cheng, Min Yang and Yunjun Yan  \n[Biomolecules 15.11 (2025)](https:\u002F\u002Fwww.mdpi.com\u002F2218-273X\u002F15\u002F11\u002F1587)\n\n**De Novo Design of a Protein Binder to Probe Gas Channel and Enhance the Oxygen Tolerance of [NiFe] Hydrogenase**  \nXuan Sun, Wenjin Li, Wangzhe Li, Hang Luo, Qi Xiao, Leyan Zhang, Yilin Fan, Peiyu Jiang, Geng Wu, Liyun Zhang  \n[bioRxiv 2025.11.19.689374](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.19.689374v1)\n\n**Computational design of metalloproteases**  \nAnqi Chen, Kejia Wu, Hojae Choi, Preetham Venkatesh, Samuel J. Pellock, Nikita Hanikel, Brian Coventry, Donghyo Kim, Seth M. Woodbury, Pengfei Ji, Shingo Honda, Xinting Li, Stacey Gerben, Lemuel Chang, Xiao Yan, Anthony A. Hyman, Donald Hilvert, David Baker  \n[bioRxiv 2025.11.20.689622](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.20.689622v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F11\u002F21\u002F2025.11.20.689622\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**Computational design of cysteine proteases**  \nHojae Choi, Brian Coventry, Magnus Bauer, Preetham Venkatesh, Anqi Chen, Donghyo Kim, Asim K. Bera, Alex Kang, Hannah Nguyen, Emily Joyce, Bhanumathi Shankaran, Tuscan Rock Thompson, Jacob Merle Gershon, Alexander F. Shida, Gyu Rie Lee, Donald Hilvert, Samuel J. Pellock, David Baker  \n[bioRxiv 2025.11.21.689808](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.21.689808v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F11\u002F22\u002F2025.11.21.689808\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**De Novo Design of Peptide Masks Enables Rapid Generation of Conditionally-Active Miniprotein Binders**  \nMontserrat Escobar-Rosales, Cristina Montaner, Marc Expòsit, Roberta Lucchi, Cristina Díaz-Perlas, David Baker, Benjamí Oller-Salvia  \n[Journal of the American Chemical Society (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Fjacs.5c16108)\n\n**Ovo, an Open-Source Ecosystem for De Novo Protein Design**  \nDavid Prihoda, Marco Ancona, Tereza Calounova, Adam Kral, Lukas Polak, Hugo Hrban, Nicholas J. Dickens, Danny Asher Bitton  \n[bioRxiv 2025.11.27.691041](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.27.691041v1) • [code](https:\u002F\u002Fgithub.com\u002FMSDLLCpapers\u002Fovo)\n\n**Machine learning enables de novo multiepitope design of Plasmodium falciparum circumsporozoite protein to target trimeric L9 antibody**  \nJ. Andrew D. Nelson, Samuel E. Garfinkle, Zi Jie Lin, Joyce Park, Amber J. Kim, Kelly Bayruns, Madison E. McCanna, Kylie M. Konrath, Colby J. Agostino, Daniel W. Kulp Daniel.Kulp, Audrey R. Odom John, and Jesper Pallesen  \n[Proceedings of the National Academy of Sciences 122.49 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2512358122)\n\n**Accurate single-domain scaffolding of three nonoverlapping protein epitopes using deep learning**  \nKarla M. Castro, Joseph L. Watson, Jue Wang, Joshua Southern, Reyhaneh Ayardulabi, Sandrine Georgeon, Stéphane Rosset, David Baker & Bruno E. Correia  \n[Nat Chem Biol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-02083-z)\n\n**Computational enzyme design by catalytic motif scaffolding**  \nMarkus Braun, Adrian Tripp, Morakot Chakatok, Sigrid Kaltenbrunner, Celina Fischer, David Stoll, Aleksandar Bijelic, Wael Elaily, Massimo G. Totaro, Melanie Moser, Shlomo Y. Hoch, Horst Lechner, Federico Rossi, Matteo Aleotti, Mélanie Hall & Gustav Oberdorfer  \n[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09747-9) • [code](https:\u002F\u002Fgithub.com\u002Fmabr3112\u002Friff_diff_protflow)\n\n**De novo design of protein nanoparticles with integrated functional motifs**  \nCyrus M Haas, Sanela Rankovic, Hanul K Lewis, Kenneth D Carr, Connor Weidle, Sophie S Gerdes, Lily R Nuss, Felicitas Ruiz, Syed Moiz, Maggie Fiorelli, Emily Grey, Jackson McGowan, Nikhila Kumar, Adrian Creanga, Alex Kang, Hannah Nguyen, Yanqing Wang, Banumathi Sankaran, Annie Dosey, Rashmi Ravichandran, Asim K Bera, Elizabeth M Leaf, Cole A DeForest, Masaru Kanekiyo, Andrew J Borst, Neil P King  \n[bioRxiv 2025.12.19.695620](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.19.695620v2) • [code](https:\u002F\u002Fgithub.com\u002Fkinglab-uiuc\u002FDeNovoNano-2026)\n\n**De novo design of protein binders that target DELE1 to inhibit the mitochondrial stress response**  \nRui Yang, Kaiyuan Zheng, McGuire Metts, Yiluo Wang, Danyan Yin, Kevin P. Li, Agnieszka A. Prazmowska, David F. Kashatus, Brian Kuhlman, Jie Yang  \n[bioRxiv 2025.12.22.695711](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.22.695711v1)\n\n**De novo design of protein binders targeting the human sweet taste receptor as potential sweet proteins**  \nSaisai Ding, Yi Zhang  \n[arXiv:2601.14574](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.14574)\n\n**Templating and confining calcium phosphate mineralization within designed protein assemblies**  \nLe Tracy Yu, Harley Pyles, Xinqi Li, Andrew J. Borst, Neville P. Bethel, Paul S. Kwon, Connor Weidle, Ryan D. Kibler, Kenneth D. Carr, Yulai Liu, Stanislav Moroz, Shuai Zhang, James De Yoreo, David Baker  \n[bioRxiv 2026.01.14.699524](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.14.699524v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F14\u002F2026.01.14.699524\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**De novo design of potent CRISPR–Cas13 inhibitors**  \nCyntia Taveneau, Her Xiang Chai, Jovita D’Silva, Rebecca S. Bamert, Honglin Chen, Brooke K. Hayes, Roland W. Calvert, Jacob Purcell, Daniel J. Curwen, Fabian Munder, Lisandra L. Martin, Jeremy J. Barr, Joseph Rosenbluh, Mohamed Fareh, Rhys Grinter & Gavin J. Knott  \n[Nat Chem Biol (2026)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-02136-3)\n\n**Experimental Analyses of RFdiffusion Designed Miniproteins for Binding to SARS-CoV-2 Nucleocapsid Protein**  \nZeenat Khakerwala , Ashwani Kumar , Sujay S Gaikwad , Truptimayee Barik , Shweta Singh , Gagan Deep Gupta , Ravindra D Makde  \n[Protein Engineering, Design and Selection, 2026](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzag004\u002F8471194)\n\n**Computational design of blue melanin with peptide motif scaffolding**  \nDi Sheng Lee, Bomi Park, Sergio Salgado, James Dolgin, David L. Kaplan  \n[bioRxiv 2026.02.02.703104](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.02.703104v1.full)\n\n**De novo design of GPCR exoframe modulators**  \nShizhuo Cheng, Jia Guo, Yun-li Zhou, Xumei Luo, Gufang Zhang, Ya-zhi Zhang, Yixin Yang, Jiannan Xie, Ping Xu, Dan-dan Shen, Shaokun Zang, Huicui Yang, Xuechu Zhen, Min Zhang & Yan Zhang  \n[Nature (2026)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09957-1)\n\n**Reprogramming CAR T-Cells with designed bioPROTACs**  \nVivek S Peche, Sebastian Kenny, Tae Gun Kang, Brian Coventry, Tian Mi, Inna Goreshnik, Mariana Garcia Sanchez, Reid Martin, Macey Smith, Dionne Vafeados, Rahul S Kathayat, Yu Kaiwen, Zuo-Fei Yuan, Long Wu, Anthony High, Andrew Nemecek, Elizabeth Wickmann, Adeleye Adeshakin, Francesca Ferrara, Robert E Throm, Taosheng Chen, Benjamin Youngblood, David Baker, Stephen Gottschalk  \n[bioRxiv 2026.02.21.706835](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.21.706835v1)\n\n**Miniprotein inhibitors of the Staphylococcus aureus efflux transporter NorA**  \nPriyanka Mishra, Adam Chazin-Gray, Gaëlle Lamon, David Kim, David Baker, Nathaniel J. Traaseth  \n[bioRxiv 2026.03.05.709893](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.05.709893v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F05\u002F2026.03.05.709893\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Design of miniprotein inhibitors targeting complement C9 to block membrane attack complex assembly**  \nBing He, Chenchen Qin, Yu Zhao, Long-Kai Huang, Zihan Wu, Fang Wang, Fandi Wu, Fan Yang & Jianhua Yao  \n[Nat Commun (2026)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-026-70667-x)\n\n### 6.4 CNN-based\n\n**De Novo Design of Site-specific Protein Binders Using Surface Fingerprints**\nPablo Gainza, Sarah Wehrle, Alexandra Van Hall-Beauvais, Anthony Marchand, Andreas Scheck, Zander Harteveld, Stephen Buckley, Dongchun Ni, Shuguang Tan, Freyr Sverrisson, Casper Goverde, Priscilla Turelli, Charlène Raclot, Alexandra Teslenko, Martin Pacesa, Stéphane Rosset, Sandrine Georgeon, Jane Marsden, Aaron Petruzzella, Kefang Liu, Zepeng Xu, Yan Chai, Pu Han, George F. Gao, Elisa Oricchio, Beat Fierz, Didier Trono, Henning Stahlberg, Michael Bronstein, Bruno E. Correia\n[Protein Science 30.CONF (2021)](https:\u002F\u002Finfoscience.epfl.ch\u002Frecord\u002F290120)\u002F[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.16.496402v2)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-05993-x) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F06\u002F17\u002F2022.06.16.496402\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [masif_seed](https:\u002F\u002Fgithub.com\u002FLPDI-EPFL\u002Fmasif_seed) • [masif](https:\u002F\u002Fgithub.com\u002FLPDI-EPFL\u002Fmasif) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4S4J7gbhAa0)\n\n**Targeting protein-ligand neosurfaces using a generalizable deep learning approach**\nAnthony Marchand, Stephen Buckley, Arne Schneuing, Martin Pacesa, Pablo Gainza, Evgenia Elizarova, Rebecca Manuela Neeser, Pao-Wan Lee, Luc Reymond, Maddalena Elia, Leo Scheller, Sandrine Georgeon, Joseph Schmidt, Philippe Schwaller, Sebastian Josef Maerkl, Michael Bronstein, Bruno Emmanuel Correia\n[bioRxiv 2024.03.25.585721](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.25.585721v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-08435-4) • [Supplementary](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41586-024-08435-4\u002FMediaObjects\u002F41586_2024_8435_MOESM1_ESM.pdf) • [code](https:\u002F\u002Fgithub.com\u002FLPDI-EPFL\u002Fmasif-neosurf) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=setIzkcEAVs)\n\n**Mapping targetable sites on the human surfaceome for the design of novel binders**\nPetra E. M. Balbi, Ahmed Sadek, Anthony Marchand, Ta-Yi Yu, Sandrine Georgeon, Joseph Schmidt, Simone Fulle, Che Yang, Hamed Khakzad, and Bruno E. Correia  \n[bioRxiv 2024.12.16.628626](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.16.628626v1)\u002F[Proc. Natl. Acad. Sci.](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2506269123) • [code](https:\u002F\u002Fgithub.com\u002Fhamedkhakzad\u002FSURFACE-Bind) • [wetbsite](https:\u002F\u002Fsurface-bind.inria.fr\u002F)\n\n**AutoBinder Agent: An MCP-Based Agent for End-to-End Protein Binder Design**  \nFukang Ge, Jiarui Zhu, Linjie Zhang, Haowen Xiao, Xiangcheng Bao, Fangnan Xie, Danyang Chen, Yanrui Lu, Yuting Wang, Ziqian Guan, Lin Gu, Jinhao Bi, Yingying Zhu\n[arXiv:2602.00019](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00019)\n\n### 6.5 GNN-based\n\n**Iterative refinement graph neural network for antibody sequence-structure co-design**\nWengong Jin, Jeremy Wohlwend, Regina Barzilay, Tommi Jaakkola\n[arXiv preprint arXiv:2110.04624 (2021)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.04624) • [RefineGNN](https:\u002F\u002Fgithub.com\u002Fwengong-jin\u002FRefineGNN) • [lecture1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=uDTccbg_Ai4), [lecture2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=px5iC79jtfc)\n\n**Antibody Complementarity Determining Regions (CDRs) design using Constrained Energy Model**\nFu, Tianfan, and Jimeng Sun\n[Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3534678.3539285) • [code](https:\u002F\u002Fgithub.com\u002Ffutianfan\u002Fenergy_model4antibody_design)\n\n**Conditional Antibody Design as 3D Equivariant Graph Translation**\nXiangzhe Kong, Wenbing Huang, Yang Liu\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=LFHFQbjxIiP)\u002F[arXiv:2208.06073](https:\u002F\u002Farxiv.org\u002Fabs\u002F2208.06073)\n\n**End-to-End Full-Atom Antibody Design**\nXiangzhe Kong, Wenbing Huang, Yang Liu\n[arXiv:2302.00203](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.00203) • [code](https:\u002F\u002Fgithub.com\u002FTHUNLP-MT\u002FdyMEAN)\n\n**AbODE: Ab Initio Antibody Design using Conjoined ODEs**\nYogesh Verma, Markus Heinonen, Vikas Garg\n[arXiv:2306.01005](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.01005)\n\n**Joint Design of Protein Sequence and Structure based on Motifs**\nZhenqiao Song, Yunlong Zhao, Yufei Song, Wenxian Shi, Yang Yang, Lei Li\n[arXiv:2310.02546](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.02546)\n\n**De novo protein design using geometric vector field networks**\nWeian Mao, Muzhi Zhu, Zheng Sun, Shuaike Shen, Lin Yuanbo Wu, Hao Chen, Chunhua Shen\n[arXiv:2310.11802](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.11802)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=9UIGyJJpay)\n\n**A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications**\nJiaqi Han, Jiacheng Cen, Liming Wu, Zongzhao Li, Xiangzhe Kong, Rui Jiao, Ziyang Yu, Tingyang Xu, Fandi Wu, Zihe Wang, Hongteng Xu, Zhewei Wei, Yang Liu, Yu Rong, Wenbing Huang\n[arXiv:2403.00485](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.00485) • review\n\n**GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation**\nHaitao LIN, Lirong Wu, Huang Yufei, Yunfan Liu, Odin Zhang, Yuanqing Zhou, Rui Sun, Stan Z Li\n[bioRxiv 2024.05.15.594274](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.15.594274v1)\u002F[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=6pHP51F55x) • [code](https:\u002F\u002Fgithub.com\u002FEdapinenut\u002FGeoAB)\n\n**Topological Neural Networks go Persistent, Equivariant, and Continuous**\nYogesh Verma, Amauri H Souza, Vikas Garg\n[arXiv:2406.03164](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.03164) • [code](https:\u002F\u002Fgithub.com\u002FAalto-QuML\u002FTopNets)\n\n**Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimization**\nLirong Wu, Haitao Lin, Yufei Huang, Zhangyang Gao, Cheng Tan, Yunfan Liu, Tailin Wu, Stan Z. Li\n[arXiv:2501.00013](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.00013) • [code](https:\u002F\u002Fgithub.com\u002FLirongWu\u002FRAAD)\n\n**Towards More Accurate Full-Atom Antibody Co-Design**\nJiayang Wu, Xingyi Zhang, Xiangyu Dong, Kun Xie, Ziqi Liu, Wensheng Gan, Sibo Wang, Le Song\n[arXiv:2502.19391](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19391)\u002F[OpenReiview](https:\u002F\u002Fopenreview.net\u002Fforum?id=1VLdFJFWhL)\n\n**NanoDesigner: Resolving the complex–CDR interdependency with iterative refinement**\nMelissa Maria Rios Zertuche, Şenay Kafkas, Dominik Renn, Magnus Rueping, Robert Hoehndorf\n[bioRxiv 2025.02.25.640028](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.25.640028v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F01\u002F2025.02.25.640028\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fbio-ontology-research-group\u002FNanoDesigner) • dyMEAN-based\n\n### 6.6 Transformer-based\n\n**Protein Sequence and Structure Co-Design with Equivariant Translation**\nChence Shi, Chuanrui Wang, Jiarui Lu, Bozitao Zhong, Jian Tang\n[arXiv:2210.08761](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.08761)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=pRCMXcfdihq) • [Supplementary](https:\u002F\u002Fopenreview.net\u002Fattachment?id=pRCMXcfdihq&name=supplementary_material) • [code](https:\u002F\u002Fgithub.com\u002Fshichence\u002FProtSeed)\n\n**Deep Learning for Flexible and Site-Specific Protein Docking and Design**\nMatt McPartlon, Jinbo Xu\n[bioRxiv 2023.04.01.535079](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.04.01.535079v1) • [code](https:\u002F\u002Fgithub.com\u002Fdrorlab\u002FDIPS)\n\n**Full-Atom Protein Pocket Design via Iterative Refinement**\nZaixi Zhang, Zepu Lu, Zhongkai Hao, Marinka Zitnik, Qi Liu\n[arXiv:2310.02553](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.02553) • [code](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FFAIR)\n\n**Functional Geometry Guided Protein Sequence and Backbone Structure Co-Design**\nAnonymous\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=Dr4qD9bzZd)\n\n**Fast and accurate modeling and design of antibody-antigen complex using tFold**\nFandi Wu, Yu Zhao, Jiaxiang Wu, Biaobin Jiang, Bing He, Longkai Huang, Chenchen Qin, Fan Yang, Ningqiao Huang, Yang Xiao, Rubo Wang, Huaxian Jia, Yu Rong, Yuyi Liu, Houtim Lai, Tingyang Xu, Wei Liu, Peilin Zhao, Jianhua Yao\n[bioRxiv 2024.02.05.578892](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.05.578892v1) • [website](https:\u002F\u002Fdrug.ai.tencent.com\u002Fcn)\n\n**PocketGen: Generating Full-Atom Ligand-Binding Protein Pockets**\nZhang Zaixi, Wanxiang Shen, Qi Liu, Marinka Zitnik\n[bioRxiv 2024.02.25.581968](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.25.581968v1)\u002F[Nature Machine Intelligence, 2024](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-024-00920-9) • [code](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FPocketGen) • [website](https:\u002F\u002Fzitniklab.hms.harvard.edu\u002Fprojects\u002FPocketGen\u002F)\n\n**Simulating 500 million years of evolution with a language model**\nThomas Hayes,  Roshan Rao,  Halil Akin,  Nicholas James Sofroniew,  Deniz Oktay,  Zeming Lin, Robert Verkuil, Vincent Quy Tran, Jonathan Deaton, Marius Wiggert, Rohil Badkundri, Irhum Shafkat, Jun Gong, Alexander Derry, Raul Santiago Molina, Neil Thomas, Yousuf Khan, Chetan Mishra, Carolyn Kim, Liam J. Bartie, Patrick D. Hsu, Tom Sercu, Salvatore Candido, Alexander Rives\n[preprint](https:\u002F\u002Fevolutionaryscale-public.s3.us-east-2.amazonaws.com\u002Fresearch\u002Fesm3.pdf)\u002F[bioRxiv 2024.07.01.600583](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.01.600583v1)\u002F[Science (2025): eads0018](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.ads0018) • [website](https:\u002F\u002Fwww.evolutionaryscale.ai\u002Fblog\u002Fesm3-release) • [code](https:\u002F\u002Fgithub.com\u002Fevolutionaryscale\u002Fesm) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fevolutionaryscale\u002Fesm\u002Fblob\u002Fmain\u002Fexamples\u002Fgenerate.ipynb) • [news](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-02214-x)\n\n**Towards Protein Sequence & Structure Co-Design with Multi-Modal Language Models**  \nStephen Zhewen Lu, Stephen_Zhewen_Lu, Jiarui Lu, Hongyu Guo, Jian Tang  \n[ICLR 2025 Workshop LMRL](https:\u002F\u002Fopenreview.net\u002Fforum?id=QLszcahdXR) • ESM3-based\n\n**All-atom protein design via SE(3) flow matching with ProteinZen**  \nAlex J. Li, Tanja Kortemme  \n[bioRxiv 2025.10.18.683228](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.18.683228v1) • [code](https:\u002F\u002Fgithub.com\u002Falexjli\u002Fproteinzen)\n\n**Ab-initio amino acid sequence design from protein text description with ProtDAT**  \nXiao-Yu Guo, Yi-Fan Li, Yuan Liu, Xiaoyong Pan & Hong-Bin Shen  \n[Nat Commun 16, 10544 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-65562-w) • [code](https:\u002F\u002Fgithub.com\u002FGXY0116\u002FProtDAT\u002Ftree\u002Fv1.0.0) • [website](http:\u002F\u002Fwww.csbio.sjtu.edu.cn\u002Fbioinf2\u002FProtDAT\u002F)\n\n**Ligand-guided Sequence–structure Co-design of De Novo Functional Enzymes**  \nZhenqiao Song, Huichong Liu, Yunlong Zhao, Yang Yang, Lei Li  \n[bioRxiv 2026.03.02.709205](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.02.709205v1) • [code](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F04\u002F2026.03.02.709205\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n### 6.7 MLP-based\n\n**Protein Complex Invariant Embedding with Cross-Gate MLP is A One-Shot Antibody Designer**\nCheng Tan, Zhangyang Gao, Stan Z. Li\n[arXiv:2305.09480](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.09480)\n\n**Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension**\nJiahan Li, Tong Chen, Shitong Luo, Chaoran Cheng, Jiaqi Guan, Ruihan Guo, Sheng Wang, Ge Liu, Jian Peng, Jianzhu Ma\n[arXiv:2411.18463](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.18463)\n\n### 6.8 Flow-based\n\n**Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design**\nAndrew Campbell, Jason Yim, Regina Barzilay, Tom Rainforth, Tommi Jaakkola\n[arXiv:2402.04997](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.04997) • [code](https:\u002F\u002Fgithub.com\u002Fandrew-cr\u002Fdiscrete_flow_models) • [lecture](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=yzc29vhM2Aw)\n\n**PPFlow: Target-Aware Peptide Design with Torsional Flow Matching**\nHaitao Lin, Odin Zhang, Huifeng Zhao, Dejun Jiang, Lirong Wu, Zicheng Liu, Yufei Huang, Stan Z. Li\n[bioRxiv 2024.03.07.583831](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.07.583831v1)\u002F[arXiv:2405.06642](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.06642) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F03\u002F08\u002F2024.03.07.583831\u002FDC1\u002Fembed\u002Fmedia-1.zip) • [code](https:\u002F\u002Fgithub.com\u002FEDAPINENUT\u002Fppflow)\n\n**Full-Atom Peptide Design based on Multi-modal Flow Matching**\nJiahan Li, Chaoran Cheng, Zuofan Wu, Ruihan Guo, Shitong Luo, Zhizhou Ren, Jian Peng, Jianzhu Ma\n[arXiv:2406.00735](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.00735) • [code](https:\u002F\u002Fgithub.com\u002FCed3-han\u002FPepFlowww)\n\n**AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions**\nBohao Xu, Yanbo Wang, Wenyu Chen, Shimin Shan\n[arXiv:2406.13162](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.13162)\n\n**Generalized Protein Pocket Generation with Prior-Informed Flow Matching**\nZaixi Zhang, Marinka Zitnik, Qi Liu\n[arXiv:2409.19520](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.19520)\n\n**D-Flow: Multi-modality Flow Matching for D-peptide Design**\nFang Wu, Tinson Xu, Shuting Jin, Xiangru Tang, Zerui Xu, James Zou, Brian Hie\n[arXiv:2411.10618](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.10618) • [code](https:\u002F\u002Fgithub.com\u002Fsmiles724\u002FPeptideDesign)\n\n**FlowDesign: Improved Design of Antibody CDRs Through Flow Matching and Better Prior Distributions**\nJun Wu, Xiangzhe Kong, Ningguan Sun, Jing Wei, Sisi Shan, Fuli Feng, Feng Wu, Jian Peng, Linqi Zhang, Yang Liu, Jianzhu Ma\n[bioRxiv 2024.11.07.622422](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.07.622422v2)\u002F[Cell Systems (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Fabstract\u002FS2405-4712(25)00103-6) • [code](https:\u002F\u002Fgithub.com\u002Fnohandsomewujun\u002FFlowDesign)\n\n**Reaction-conditioned De Novo Enzyme Design with GENzyme**\nChenqing Hua, Jiarui Lu, Yong Liu, Odin Zhang, Jian Tang, Rex Ying, Wengong Jin, Guy Wolf, Doina Precup, Shuangjia Zheng\n[arXiv:2411.16694](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.16694) • [code](https:\u002F\u002Fgithub.com\u002FWillHua127\u002FGENzyme)\n\n**ProteinZen: combining latent and SE(3) flow matching for all-atom protein generation**\nAlex Li, Tanja Kortemme\n[Machine Learning for Structural Biology Workshop, NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FProteinZen:_combining_latent_and_SE(3)_flow_matching_for_all-atom_protein_generation.pdf)\n\n**HelixFlow, SE(3)–equivariant Full-atom Design of Peptides With Flow-matching Models**\nXuezhi Xie, Pedro A Valiente, Jisun Kim, Jin Sub Lee, Philip Kim\n[Machine Learning for Structural Biology Workshop, NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FHelixFlow,_SE(3)–equivariant_Full-atom_Design_of_Peptides_With_Flow-matching_Models.pdf)\n\n**IgFlow: Flow Matching for De Novo Antibody Design**\nSanjay Nagaraj, Amir Shanehsazzadeh, Hyun Park, Jonathan King, Simon Levine\n[Machine Learning for Structural Biology Workshop, NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FIgFlow:_Flow_Matching_for_De_Novo_Antibody_Design.pdf)\n\n**Surface-based Peptide Design with Multi-modal Flow Matching**  \nFang Wu, Shuting Jin, xiangxiang Zeng, Jure Leskovec, Jinbo Xu  \n[ICLR 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=MeCPwqrm19)\n\n**Non-Linear Flow Matching for Full-Atom Peptide Design**\nDengdeng Huang, Shikui Tu\n[arXiv:2502.15855](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.15855)\n\n**dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigen**\nCheng Tan, Yijie Zhang, Zhangyang Gao, Yufei Huang, Haitao Lin, Lirong Wu, Fandi Wu, Mathieu Blanchette, Stan. Z. Li\n[arXiv:2503.01910](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.01910) • [code](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FdyAb)\n\n**GeoFlow-V2: A Unified Atomic Diffusion Model for Protein Structure Prediction and De Novo Design**\nBioGeometry Team\n[preprint](https:\u002F\u002Fopen-res.biogeom.com\u002Fgeoflow-v2\u002Ftechnical-report.pdf) • [website](https:\u002F\u002Fprot.design\u002F) • commercial\n\n**All-atom inverse protein folding through discrete flow matching**  \nKai Yi, Kiarash Jamali, Sjors HW Scheres  \n[ICML 2025 poster](https:\u002F\u002Fopenreview.net\u002Fforum?id=8tQdwSCJmA)\n\n**Co-Design protein sequence and structure in discrete space via generative flow**  \nSen Yang, Lingli Ju, Cheng Peng, JiangLin Zhou, Yamin Cai, Dawei Feng  \n[Bioinformatics, 2025](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtaf248\u002F8123382) • [code](https:\u002F\u002Fgithub.com\u002FLtECoD\u002FCoFlow) • [model](https:\u002F\u002Fzenodo.org\u002Frecords\u002F14842367)\n\n**La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching**  \nTomas Geffner, Kieran Didi, Zhonglin Cao, Danny Reidenbach, Zuobai Zhang, Christian Dallago, Emine Kucukbenli, Karsten Kreis, Arash Vahdat  \n[arXiv:2507.09466](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.09466) • [webstie](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fla-proteina\u002F)\n\n**Design of peptides with non-canonical amino acids using flow matching**  \nJin Sub Lee, Philip M Kim  \n[bioRxiv 2025.07.31.667780](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.31.667780v1)\n\n**Investigating the impacts of sidechains on de-novo protein design**  \nCooper Svajda, Joshua Yuan  \n[bioRxiv 2025.08.08.669410](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.08.669410v1)\n\n**Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A**  \nHao Qian, Pu You, Lin Zeng, Jingyuan Zhou, Dengdeng Huang, Kaicheng Li, Shikui Tu, Lei Xu\n[arXiv:2512.02030](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.02030v1)\n\n**AbFlow : End-to-end Paratope-Centric Antibody Design by Interaction Enhanced Flow Matching**  \nWenda Wang, Yang Zhang, Zhewei Wei, Wenbing Huang  \n[arXiv:2602.07084](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.07084) • [code](https:\u002F\u002Fgithub.com\u002FWangWenda87\u002FAbFlow)\n\n**Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles**  \nZhanghan Ni, Yanjing Li, Zeju Qiu, Bernhard Schölkopf, Hongyu Guo, Weiyang Liu, Shengchao Liu  \n[arXiv:2603.02406](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.02406)\n\n**Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute**  \nKieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach, Zhonglin Cao, Sooyoung Cha, Tomas Geffner, Christian Dallago, Jian Tang, Michael M. Bronstein, Martin Steinegger, Emine Kucukbenli, Arash Vahdat, Karsten Kreis  \n[ICLR 2026 Oral](https:\u002F\u002Fopenreview.net\u002Fforum?id=qmCpJtFZra)\u002F[wetlab paper](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fproteina-complexa\u002Fassets\u002Fproteina_complexa_validation.pdf) • [code](https:\u002F\u002Fgithub.com\u002FNVIDIA-Digital-Bio\u002Fproteina-complexa) • [website](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fproteina-complexa\u002F)\n\n### 6.9 AlphaFold-based\n\n**CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model**\nRen, Milong, Tian Zhu, and Haicang Zhang\n[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=FSxTEvuFa7) • [code](https:\u002F\u002Fgithub.com\u002Fzhanghaicang\u002Fcarbonmatrix_public)\n\n**P(all-atom) Is Unlocking New Path For Protein Design**\nWei Qu, Jiawei Guan, Rui Ma, Ke Zhai, Weikun Wu, Haobo Wang\n[bioRxiv 2024.08.16.608235](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.16.608235v1) • [code](https:\u002F\u002Fgithub.com\u002Flevinthal\u002FPallatom) • [news](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002Fj86-ncoYMM2gfbvTJX6I7w)\n\n**EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow-Matching and Co-Evolutionary Dynamics**\nChenqing Hua\npaper not available • [code](https:\u002F\u002Fgithub.com\u002FWillHua127\u002FEnzymeFlow)\n\n**IgGM: A Generative Model for Functional Antibody and Nanobody Design**\nRubo Wang, Fandi Wu, Xingyu Gao, Jiaxiang Wu, Peilin Zhao, Jianhua Yao\n[bioRxiv 2024.09.19.613838](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.19.613838v1) • [code](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002FIgGM)\n\n**An All-Atom Generative Model for Designing Protein Complexes**\nRuizhe Chen, Dongyu Xue, Xiangxin Zhou, Zaixiang Zheng, Xiangxiang Zeng, Quanquan Gu\n[arXiv:2504.13075](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.13075) • [code](https:\u002F\u002Fgithub.com\u002Fbytedance\u002Fapm)\n\n**Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design**  \nNianzu Yang, Nianzu_Yang, Jian Ma, Songlin Jiang, Huaijin Wu, Shuangjia Zheng, Wengong Jin, Junchi Yan  \n[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=Ja2le9YnqN)\n\n**A synergistic generative-ranking framework for tailored design of therapeutic single-domain antibodies**  \nYu Kong, Jiale Shi, Fandi Wu, Ting Zhao, Rubo Wang, Xiaoyi Zhu, Qingyuan Xu, Yidong Song, Quanxiao Li, Yulu Wang, Xingyu Gao, Yuedong Yang, Yi Feng, Zifei Wang, Weifeng Ge, Yanling Wu, Zhenlin Yang, Jianhua Yao & Tianlei Ying  \n[Cell Discov 11, 85 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41421-025-00843-8)\n\n**CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design**  \nZijun Gao, Mutian He, Shijia Sun, Hanqun Cao, Jingjie Zhang, Zihao Luo, Xiaorui Wang, Xiaojun Yao, Chang-Yu Hsieh, Chunbin Gu, Pheng Ann Heng  \n[arXiv:2512.02033](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.02033) • [code](https:\u002F\u002Fgithub.com\u002Fzjgao02\u002FCONFIDE)\n\n## 7. Other tasks\n\n### 7.1 Effects of mutation & Fitness Landscape\n\n**Deep generative models of genetic variation capture the effects of mutations**\nAdam J. Riesselman, John B. Ingraham & Debora S. Marks\n[Nature Methods](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-018-0138-4) • [code::DeepSequence](https:\u002F\u002Fgithub.com\u002Fdebbiemarkslab\u002FDeepSequence) • Oct 2018\n\n**Deciphering protein evolution and fitness landscapes with latent space models**\nXinqiang Ding, Zhengting Zou & Charles L. Brooks III\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-019-13633-0) • [code::PEVAE](https:\u002F\u002Fgithub.com\u002Fxqding\u002FPEVAE_Paper) • Dec 2019\n\n**Is transfer learning necessary for protein landscape prediction?**\nShanehsazzadeh, Amir, David Belanger, and David Dohan\n[arXiv preprint arXiv:2011.03443 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.03443)\n\n**Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions**\nAmirali Aghazadeh, Hunter Nisonoff, Orhan Ocal, David H. Brookes, Yijie Huang, O. Ozan Koyluoglu, Jennifer Listgarten & Kannan Ramchandran\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-25371-3) • [code](https:\u002F\u002Fgithub.com\u002Famirmohan\u002Fepistatic-net) • Sep 2021\n\n**The generative capacity of probabilistic protein sequence models**\nFrancisco McGee, Sandro Hauri, Quentin Novinger, Slobodan Vucetic, Ronald M. Levy, Vincenzo Carnevale & Allan Haldane\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-26529-9) • [code::generation_capacity_metrics](https:\u002F\u002Fgithub.com\u002Falagauche\u002Fgenerative_capacity_metrics) • [code::sVAE](https:\u002F\u002Fgithub.com\u002Fahaldane\u002FMSA_VAE) • Nov 2021\n\n**Learning the local landscape of protein structures with convolutional neural networks**\nAnastasiya V. Kulikova, Daniel J. Diaz, James M. Loy, Andrew D. Ellington & Claus O. Wilke\n[Journal of Biological Physics 47.4 (2021)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10867-021-09593-6)\n\n**Neural networks to learn protein sequence-function relationships from deep mutational scanning data**\nSam Gelman, Sarah A. Fahlberg, Pete Heinzelman, Philip A. Romero & Anthony Gitter\n[Proceedings of the National Academy of Sciences](https:\u002F\u002Fdoi.org\u002F10.1073\u002Fpnas.2104878118) • [code](https:\u002F\u002Fgithub.com\u002Fgitter-lab\u002Fnn4dms) • Nov 2021\n\n**Learning Protein Fitness Models from Evolutionary and Assay-labeled Data**\nChloe Hsu, Hunter Nisonoff, Clara Fannjiang, Jennifer Listgarten\n[Nature Biotechnology (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-021-01146-5) • [Supplementary Information](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41587-021-01146-5\u002FMediaObjects\u002F41587_2021_1146_MOESM1_ESM.pdf) • [code](https:\u002F\u002Fgithub.com\u002Fchloechsu\u002Fcombining-evolutionary-and-assay-labelled-data)\n\n**Proximal Exploration for Model-guided Protein Sequence Design**\nZhizhou Ren, Jiahan Li, Fan Ding, Yuan Zhou, Jianzhu Ma, Jian Peng\n[BioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.12.487986v1) • [code](https:\u002F\u002Fgithub.com\u002FHeliXonProtein\u002Fproximal-exploration) • commercial\n\n**Efficient evolution of human antibodies from general protein language models and sequence information alone**\nBrian L. Hie, Duo Xu, Varun R. Shanker, Theodora U.J. Bruun, Payton A. Weidenbacher, Shaogeng Tang, Peter S. Kim\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.10.487811v1) • [code](https:\u002F\u002Fgithub.com\u002Fbrianhie\u002Fefficient-evolution)\n\n**Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval**\nNotin, P., Dias, M., Frazer, J., Marchena-Hurtado, J., Gomez, A., Marks, D.S., Gal, Y\n[ICML (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13760)\u002F[arXiv:2205.13760](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13760) • [code](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FTranception) • [hugging face](https:\u002F\u002Fhuggingface.co\u002FICML2022\u002FTranception)\n\n**Protein engineering via Bayesian optimization-guided evolutionary algorithm and robotic experiments**\nRuyun Hu, Lihao Fu, Yongcan Chen, Junyu Chen, Yu Qiao, Tong Si\n[bioRxiv 2022.08.11.503535](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.11.503535v1)\n\n**Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness**\nSharrol Bachas, Goran Rakocevic, David Spencer, Anand V. Sastry, Robel Haile, John M. Sutton, George Kasun, Andrew Stachyra, Jahir M. Gutierrez, Edriss Yassine, Borka Medjo, Vincent Blay, Christa Kohnert, Jennifer T. Stanton, Alexander Brown, Nebojsa Tijanic, Cailen McCloskey, Rebecca Viazzo, Rebecca Consbruck, Hayley Carter, Simon Levine, Shaheed Abdulhaqq, Jacob Shaul, Abigail B. Ventura, Randal S. Olson, Engin Yapici, Joshua Meier, Sean McClain, Matthew Weinstock, Gregory Hannum, Ariel Schwartz, Miles Gander, Roberto Spreafico\n[bioRxiv 2022.08.16.504181](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.16.504181v1) • [poster](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002F58999.png?t=1668022673.3853557)\n\n**Construction of a Deep Neural Network Energy Function for Protein Physics**\nYang, Huan, Zhaoping Xiong, and Francesco Zonta\n[Journal of Chemical Theory and Computation (2022)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jctc.2c00069)\n\n**Inferring protein fitness landscapes from laboratory evolution experiments**\nSameer D’Costa, Emily C. Hinds, Chase R. Freschlin, Hyebin Song, Philip A. Romero\n[bioRxiv 2022.09.01.506224](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.01.506224v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.01.506224v1.supplementary-material)\n\n**BayeStab: Predicting Effects of Mutations on Protein Stability with Uncertainty Quantification**\nShuyu Wang, Hongzhou Tang, Yuliang Zhao, Lei Zuo\n[Protein Science (2022)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fpro.4467) • [code](https:\u002F\u002Fgithub.com\u002FHongzhouTang\u002FBayeStab) • [website](http:\u002F\u002Fwww.bayestab.com)\n\n**Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design**\nNeil Thomas, Atish Agarwala, David Belanger, Yun S. Song, Lucy Colwell\n[bioRxiv 2022.10.28.514293](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.10.28.514293v1) • [code](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fslip)\n\n**Protein design using structure-based residue preferences**\nDavid Ding, Ada Y Shaw, Sam Sinai, Nathan J Rollins, Noam Prywes, David Savage, Michael T Laub, Debora S Marks\n[bioRxiv 2022.10.31.514613](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.10.31.514613v2) • [code](https:\u002F\u002Fgithub.com\u002Fddingding\u002FCoVES)\n\n**Accurate Mutation Effect Prediction using RoseTTAFold**\nSanaa Mansoor, Minkyung Baek, David Juergens, Joseph L Watson, David Baker\n[bioRxiv 2022.11.04.515218](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.11.04.515218v1)\n\n**Learning the shape of protein micro-environments with a holographic convolutional neural network**\nMichael N. Pun, Andrew Ivanov, Quinn Bellamy, Zachary Montague, Colin LaMont, Philip Bradley, Jakub Otwinowski, Armita Nourmohammad\n[bioRxiv (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.02936) • [code](https:\u002F\u002Fgithub.com\u002FStatPhysBio\u002Fprotein_holography)\n\n**Infer global, predict local: quantity-quality trade-off in protein fitness predictions from sequence data**\nLorenzo Posani, Francesca Rizzato, Rémi Monasson, Simona Cocco\n[bioRxiv 2022.12.12.520004](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.12.520004v1)\n\n**Validation of de novo designed water-soluble and transmembrane proteins by in silico folding and melting**\nAlvaro Martin, Carolin Berner, Sergey Ovchinnikov, Anastassia Andreevna Vorobieva\n[bioRxiv 2023.06.06.543955](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.06.543955v1) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fvorobieva\u002FColabFold\u002Fblob\u002Fmain\u002Fbeta\u002FESMFold_melting.ipynb)\n\n**PoET: A generative model of protein families as sequences-of-sequences**\nTimothy F. Truong Jr, Tristan Bepler\n[arXiv:2306.06156](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.06156) • [code](https:\u002F\u002Fgithub.com\u002FOpenProteinAI\u002FPoET)\n\n**Rapid protein stability prediction using deep learning representations**\nLasse M BlaabjergMaher M KassemLydia L GoodNicolas JonssonMatteo CagiadaKristoffer E JohanssonWouter BoomsmaAmelie SteinKresten Lindorff-Larsen\n[eLife 12:e82593](https:\u002F\u002Felifesciences.org\u002Farticles\u002F82593) • [code](https:\u002F\u002Fgithub.com\u002FKULL-Centre\u002F_2022_ML-ddG-Blaabjerg\u002F)\n\n**A general Temperature-Guided Language model to engineer enhanced Stability and Activity in Proteins**\nPan Tan, Mingchen Li, Yuanxi Yu, Fan Jiang, Lirong Zheng, Banghao Wu, Xinyu Sun, Liqi Kang, Jie Song, Liang Zhang, Yi Xiong, Wanli Ouyang, Zhiqiang Hu, Guisheng Fan, Yufeng Pei, Liang Hong\n[arXiv:2307.12682](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.12682)\n\n**Transfer learning to leverage larger datasets for improved prediction of protein stability changes**\nHenry Dieckhaus, Michael Brocidiacono, Nicholas Randolph, Brian Kuhlman\n[bioRxiv 2023.07.27.550881](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.27.550881v1) • [code](https:\u002F\u002Fgithub.com\u002FKuhlman-Lab\u002FThermoMPNN) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F07\u002F30\u002F2023.07.27.550881\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**Structure-based self-supervised learning enables ultrafast prediction of stability changes upon mutation at the protein universe scale**\nJinyuan Sun, Tong Zhu, Yinglu Cui, Bian Wu\n[bioRxiv 2023.08.09.552725](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.09.552725v1) • [code](https:\u002F\u002Fgithub.com\u002FWublab\u002FPythia)\n\n**Boosting AND\u002FOR-Based Computational Protein Design: Dynamic Heuristics and Generalizable UFO**\nBobak Pezeshki, Radu Marinescu, Alexander Ihler, Rina Dechter\n[arXiv:2309.00408](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.00408)\n\n**Zero-shot Mutation Effect Prediction on Protein Stability and Function using RoseTTAFold**\nSanaa Mansoor, Minkyung Baek, David Juergens, Joseph L. Watson, David Baker\n[Protein Science](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.4780) • [dissertation](https:\u002F\u002Fwww.proquest.com\u002Fopenview\u002Fdba5569e5efd0dc60fc7bedccb6afee3\u002F)\n\n**Accurate proteome-wide missense variant effect prediction with AlphaMissense**\nJun Cheng, Guido Novati, Joshua Pan, Clare Bycroft, Akvile Žemgulyte, Taylor Applebaum, Alexander Pritzel, Lai Hong Wong, Michal Zielinski, Tobias Sargeant, Rosalia G. Schneider, Andrew W. Senior, John Jumper, Demis Hassabis, Pushmeet Kohli, Žiga Avsec\n[Science0,eadg7492DOI:10.1126\u002Fscience.adg7492](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adg7492) • [code](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Falphamissense) • [data](https:\u002F\u002Fconsole.cloud.google.com\u002Fstorage\u002Fbrowser\u002Fdm_alphamissense)\n\n**Enzyme structure correlates with variant effect predictability**\nFloris Julian van der Flier, Dave Estell, Sina Pricelius, Lydia Dankmeyer, Sander van Stigt Thans, Harm Mulder, Rei Otsuka, Frits Goedegebuur, Laurens Lammerts, Diego Staphorst, Aalt D.J. van Dijk, Dick de Ridder, Henning Redestig\n[bioRxiv 2023.09.25.559319](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.25.559319v2)\u002F[Computational and Structural Biotechnology Journal (2024)](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.csbj.2024.09.007) • [code](https:\u002F\u002Fgithub.com\u002Fflorisvdf\u002Fmutation-predictability)\n\n**Fast, accurate ranking of engineered proteins by target binding propensity using structure modeling**\nXiaozhe Ding, Xinhong Chen, Erin E. Sullivan, Timothy F. Shay, Viviana Gradinaru\n[bioRxiv 2023.01.11.523680](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.11.523680v2)\u002F[Molecular Therapy (2024)](https:\u002F\u002Fwww.cell.com\u002Fmolecular-therapy-family\u002Fmolecular-therapy\u002Ffulltext\u002FS1525-0016(24)00219-3) • [code](https:\u002F\u002Fgithub.com\u002FGradinaruLab\u002FAPPRAISE) • [colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002FGradinaruLab\u002FAPPRAISE\u002Fblob\u002Fmain\u002FColab_APPRAISE.ipynb)\n\n**Neural network extrapolation to distant regions of the protein fitness landscape**\nSarah A Fahlberg, Chase R Freschlin, Pete Heinzelman, Philip A Romero\n[bioRxiv 2023.11.08.566287](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.08.566287v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F11\u002F09\u002F2023.11.08.566287\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Accelerating protein engineering with fitness landscape modeling and reinforcement learning**\nHaoran Sun, Liang He, Pan Deng, Guoqing Liu, Haiguang Liu, Chuan Cao, Fusong Ju, Lijun Wu, Tao Qin, Tie-Yan Liu\n[bioRxiv 2023.11.16.565910](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.16.565910v1)\n\n**Protein Design by Directed Evolution Guided by Large Language Models**\nTrong Thanh Tran, Truong Son Hy\n[bioRxiv 2023.11.29.568945](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.28.568945v1) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F11\u002F29\u002F2023.11.28.568945\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [code](https:\u002F\u002Fgithub.com\u002FHySonLab\u002FDirected_Evolution)\n\n**High-throughput ML-guided design of diverse single-domain antibodies against SARS-CoV-2**\nChristof Angermueller, Zelda Marie, Benjamin Jester, Emily Engelhart, Ryan Emerson, Babak Alipanahi, Zachary Ryan McCaw, Jim Roberts, Randolph M Lopez, David Younger, Lucy Colwell\n[bioRxiv 2023.12.01.569227](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.01.569227v1)\n\n**Efficiently Predicting Protein Stability Changes Upon Single-point Mutation with Large Language Models**\nYijie Zhang, Zhangyang Gao, Cheng Tan, Stan Z.Li\n[arXiv preprint arXiv:2312.04019 (2023)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.04019)\n\n**DSMBind: SE(3) denoising score matching for unsupervised binding energy prediction and nanobody design**\nWengong Jin, Xun Chen, Amrita Vetticaden, Siranush Sarzikova, Raktima Raychowdhury, Caroline Uhler, Nir Hacohen\n[bioRxiv 2023.12.10.570461](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.10.570461v1) • [Supplementary1](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F12\u002F10\u002F2023.12.10.570461\u002FDC1\u002Fembed\u002Fmedia-1.xlsx) • [Supplementary2](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F12\u002F10\u002F2023.12.10.570461\u002FDC2\u002Fembed\u002Fmedia-2.pdf)\n\n**Inverse folding of protein complexes with a structure-informed language model enables unsupervised antibody evolution**\nVarun R. Shanker, Theodora U.J. Bruun, Brian L. Hie, Peter S. Kim\n[bioRxiv 2023.12.19.572475](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.19.572475v2)\n\n**EvolMPNN: Predicting Mutational Effect on Homologous Proteins by Evolution Encoding**\nZhiqiang Zhong, Davide Mottin\n[arXiv:2402.13418](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.13418)\n\n**Generating mutants of monotone affinity towards stronger protein complexes through adversarial learning**\nTian Lan, Shuquan Su, Pengyao Ping, Gyorgy Hutvagner, Tao Liu, Yi Pan & Jinyan Li\n[Nat Mach Intell 6, 315–325 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-024-00803-z) • [code](https:\u002F\u002Fgithub.com\u002Ftianlt\u002FDeepdirect)\n\n**Biophysics-based protein language models for protein engineering**\nSam Gelman, Bryce Johnson, Chase Freschlin, Sameer D'Costa, Anthony Gitter & Philip A. Romero\n[bioRxiv 2024.03.15.585128](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2024.03.15.585128) • [code](https:\u002F\u002Fgithub.com\u002Fgitter-lab\u002Fmetl)\n\n**Latent-based Directed Evolution accelerated by Gradient Ascent for Protein Sequence Design** \u002F **LatentDE: latent-based directed evolution for protein sequence design**\nNhat Khang Ngo, Thanh V. T. Tran, Viet Thanh Duy Nguyen, Truong Son Hy\n[bioRxiv 2024.04.13.589381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.13.589381v1)\u002F[NeurIPS 2024](https:\u002F\u002Fopenreview.net\u002Fpdf?id=4YkbQGVWGF)\u002F[Machine Learning: Science and Technology (2025)](https:\u002F\u002Fiopscience.iop.org\u002Farticle\u002F10.1088\u002F2632-2153\u002Fadc2e2) • [code](https:\u002F\u002Fgithub.com\u002FHySonLab\u002FLatentDE)\n\n**AAVDiff: Experimental Validation of Enhanced Viability and Diversity in Recombinant Adeno-Associated Virus (AAV) Capsids through Diffusion Generation**\nLijun Liu, Jiali Yang, Jianfei Song, Xinglin Yang, Lele Niu, Zeqi Cai, Hui Shi, Tingjun Hou, Chang-yu Hsieh, Weiran Shen, Yafeng Deng\n[arXiv:2404.10573](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.10573)\n\n**Protein engineering with lightweight graph denoising neural networks**\nBingxin Zhou, Lirong Zheng, Banghao Wu, Yang Tan, Outongyi Lv, Kai Yi, Guisheng Fan, and Liang Hong\n[Journal of Chemical Information and Modeling (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.4c00036) • [code](https:\u002F\u002Fgithub.com\u002Fbzho3923\u002FProtLGN)\n\n**VespaG: Expert-guided protein Language Models enable accurate and blazingly fast fitness prediction**\nCeline Marquet, Julius Schlensok, Marina Abakarova, Burkhard Rost, Elodie Laine\n[bioRxiv 2024.04.24.590982](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.24.590982v1) • [code](https:\u002F\u002Fgithub.com\u002FJSchlensok\u002FVespaG)\n\n**Interface design of SARS-CoV-2 symmetrical nsp7 dimer and machine learning-guided nsp7 sequence prediction reveals physicochemical properties and hotspots for nsp7 stability, adaptation, and therapeutic design**\nAmar Jeet Yadav, Shivank Kumar, Shweata Maurya, Khushboo Bhagat, and Aditya K. Padhi\n[Physical Chemistry Chemical Physics (2024)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlelanding\u002F2024\u002Fcp\u002Fd4cp01014k)\n\n**Aligning protein generative models with experimental fitness via Direct Preference Optimization**\nTalal Widatalla, Rafael Rafailov, Brian Hie\n[bioRxiv 2024.05.20.595026](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.20.595026v1) • [code](https:\u002F\u002Fgithub.com\u002Fevo-design\u002Fprotein-dpo)\n\n**ProBASS – a language model with sequence and structural features for predicting the effect of mutations on binding affinity**\nSagara N.S. Gurusinghe, Yibing Wu, William DeGrado, Julia M. Shifman\n[bioRxiv 2024.06.21.600041](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.21.600041v1) • [code](https:\u002F\u002Fgithub.com\u002Fsagagugit\u002FProBASS)\n\n**Unsupervised evolution of protein and antibody complexes with a structure-informed language model**\nVarun R. Shanker, Theodora U. J. Bruun, Brian L. Hie, Peter S. Kim\n[Science385,46-53(2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adk8946) • [code](https:\u002F\u002Fgithub.com\u002Fvarun-shanker\u002Fstructural-evolution)\n\n**Enhancing efficiency of protein language models with minimal wet-lab data through few-shot learning**\nZiyi Zhou, Liang Zhang, Yuanxi Yu, Banghao Wu, Mingchen Li, Liang Hong & Pan Tan\n[Nat Commun 15, 5566 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-49798-6) • [code](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FTranception)\n\n**Rapid protein evolution by few-shot learning with a protein language model**\nKaiyi Jiang, Zhaoqing Yan, Matteo Di Bernardo, Samantha R. Sgrizzi, Lukas Villiger, Alisan Kayabolen, Byungji Kim, Josephine K. Carscadden, Masahiro Hiraizumi, Hiroshi Nishimasu, Jonathan S. Gootenberg, Omar O. Abudayyeh\n[bioRxiv 2024.07.17.604015](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.17.604015v1) • [code1](https:\u002F\u002Fgithub.com\u002Fmat10d\u002FEvolvePro),[code2](https:\u002F\u002Fgithub.com\u002Fidmjky\u002FEvolvePro)\n\n**Zero-shot prediction of mutation effects with multimodal deep representation learning guides protein engineering**\nPeng Cheng, Cong Mao, Jin Tang, Sen Yang, Yu Cheng, Wuke Wang, Qiuxi Gu, Wei Han, Hao Chen, Sihan Li, Yaofeng Chen, Jianglin Zhou, Wuju Li, Aimin Pan, Suwen Zhao, Xingxu Huang, Shiqiang Zhu, Jun Zhang, Wenjie Shu & Shengqi Wang\n[Cell Research (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41422-024-00989-2) • [code](https:\u002F\u002Fgithub.com\u002Fwenjiegroup\u002FProMEP)\n\n**Machine learning-guided co-optimization of fitness and diversity facilitates combinatorial library design in enzyme engineering**\nKerr Ding, Michael Chin, Yunlong Zhao, Wei Huang, Binh Khanh Mai, Huanan Wang, Peng Liu, Yang Yang & Yunan Luo\n[Nature Communications 15.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-50698-y) • [code](https:\u002F\u002Fgithub.com\u002Fluo-group\u002FMODIFY), [model](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.12715542)\n\n**Dirichlet latent modelling enables effective learning and sampling of the functional protein design space**\nEvgenii Lobzaev, Giovanni Stracquadanio\n[Nat Commun 15, 9309 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-53622-6) • [code](https:\u002F\u002Flicensing.edinburgh-innovations.ed.ac.uk\u002Fproduct\u002Fproton)\n\n**MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization**\nGautham Dharuman, Kyle Hippe, Alexander Brace, Sam Foreman, Väinö Hatanpää, Varuni K. Sastry, Huihuo Zheng, Logan Ward, Servesh Muralidharan, Archit Vasan, Bharat Kale, Carla M. Mann, Heng Ma, Yun-Hsuan Cheng, Yuliana Zamora, Shengchao Liu, Chaowei Xiao, Murali Emani, Tom Gibbs, Mahidhar Tatineni, Deepak Canchi, Jerome Mitchell, Koichi Yamada, Maria Garzaran, Michael E. Papka, Ian Foster, Rick Stevens, Anima Anandkumar, Venkatram Vishwanath, Arvind Ramanathan\n[International Conference for High Performance Computing, Networking, Storage and Analysis SC. IEEE Computer Society, 2024](https:\u002F\u002Fwww.computer.org\u002Fcsdl\u002Fproceedings-article\u002Fsc\u002F2024\u002F529100a074\u002F21HUV88n1F6)\n\n**Scoring-Assisted Generative Exploration for Proteins (SAGE-Prot): A Framework for Multi-Objective Protein Optimization via Iterative Sequence Generation and Evaluation**  \nHocheol Lim, Geon-Ho Lee, Kyoung Tai No  \n[arXiv:2505.01277](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.01277) • [code](https:\u002F\u002Fgithub.com\u002Fhclim0213\u002FSAGE-Prot)\n\n**Artificial Intelligence And First Principle Methods In Protein Redesign: A Marriage Of Convenience?**  \nDamiano Cianferoni, David Vizarraga, Ana María Fernández-Escamilla, Ignacio Fita, Rahma Hamdani, Raul Reche, Javier Delgado, Luis Serrano  \n[bioRxiv 2025.05.12.653318](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.12.653318v1)\u002F[Protein Science](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70210) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F05\u002F15\u002F2025.05.12.653318\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Likelihood-based Fine-tuning of Protein Language Models for Few-shot Fitness Prediction and Design**  \nAlex Hawkins-Hooker, Shikha Surana, Jack Simons, Jakub Kmec, Oliver Bent, Paul Duckworth  \n[bioRxiv 2024.05.28.596156](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.28.596156v3)\n\n**ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods**  \nMichal Kmicikiewicz, Vincent Fortuin, Ewa Szczurek  \n[arXiv:2505.22494](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22494v1)\n\n**Heuristic Multi-site Optimization for Protein Sequence Design using Masked Protein Language Models**  \nLijuan Wang, Yuze Wang, Chen Qiu, Liwei Xiao, Xianliang Liu, Junjie Chen  \n[bioRxiv 2025.07.31.668012](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.31.668012v1)\n\n**Design of a Labile RNase A Using Protein Language Models**  \nGabriel OngKiat Whye KongSi En PohFong Tian WongYiqi SeowWinston Koh  \n[ACS Synthetic Biology (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.5c00287)\n\n**Zero-shot Deep Learning with Multi-Objective Optimization Improves Thermostability of Zearalenone Hydrolase and Xylanase**  \nFan Wu, Rui Wu, Linghui Chen, Quan Chen, Haiyan Liu  \n[New Biotechnology (2026)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1871678426000099)\n\n**A Discrete Language of Protein Words for Functional Discovery and Design**  \nZhengyang Guo, Zi Wang, Yongping Chai, Kaiming Xu, Ming Li, Wei Li, Guangshuo Ou  \n[bioRxiv 2026.02.14.705947](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.14.705947v1) • [code](https:\u002F\u002Fgithub.com\u002Fyoung55775\u002FProtWord)\n\n**Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability**  \nAna F. Rodrigues, Lucas Ferraz, Laura Balbi, Pedro Giesteira Cotovio, Catia Pesquita  \n[arXiv:2602.14828](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.14828) • [code](https:\u002F\u002Fgithub.com\u002FlasigeBioTM\u002FAAV-embeddings)\n\n**Deep learning-guided evolutionary optimization for protein design**  \nErik Hartman, Di Tang, Johan Malmström  \n[arXiv:2603.02753](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.02753)\n\n**Functional protein design and enhancement with ontology reinforcement iteration**  \nBing He, Chenchen Qin, Yu Zhao, Long-Kai Huang, Zihan Wu, Fang Wang, Fandi Wu, Fan Yang & Jianhua Yao  \n[Nat Commun (2026)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-026-69855-6) • [code](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002Fori)\n\n**CombinGym: a benchmark platform for machine learning-assisted design of combinatorial protein variants**  \nYongcan Chen, Lihao Fu, Xuchao Lu, Wenzhuo Li, Yuan Gao, Yibo Wang, Zhicheng Ruan, Tong Si  \n[bioRxiv 2026.03.24.714074](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.24.714074v1) • [code](https:\u002F\u002Fgithub.com\u002Fsitonglab\u002FCombinGym) • [Supplementary](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F25\u002F2026.03.24.714074\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [website](https:\u002F\u002Fwww.combingym.org)\n\n### 7.2 Protein Language Models (pLM) and representation learning\n\n> More detailed protein representation learning list:\n> [Lirong Wu](https:\u002F\u002Fgithub.com\u002FLirongWu)'s [awesome-protein-representation-learning](https:\u002F\u002Fgithub.com\u002FLirongWu\u002Fawesome-protein-representation-learning)\n\n**Unified rational protein engineering with sequence-based deep representation learning**\nEthan C. Alley, Grigory Khimulya, Surojit Biswas, Mohammed AlQuraishi & George M. Church\n[Nature methods 16.12 (2019)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-019-0598-1)\n\n**Protein Structure Representation Learning by Geometric Pretraining**\nZuobai Zhang, Minghao Xu, Arian Jamasb, Vijil Chenthamarakshan, Aurelie Lozano, Payel Das, Jian Tang\n[arXiv](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.06125) • Jan 2022\n\n**Evolutionary velocity with protein language models**\nBrian L. Hie, Kevin K. Yang, and Peter S. Kim\n[bioRxiv](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.06.07.447389v1.full.pdf)\n\n**Advancing protein language models with linguistics: a roadmap for improved interpretability**\nMai Ha Vu, Rahmad Akbar, Philippe A. Robert, Bartlomiej Swiatczak, Victor Greiff, Geir Kjetil Sandve, Dag Trygve Truslew Haug\n[arXiv:2207.00982](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.00982)\n\n**Deciphering the language of antibodies using self-supervised learning**\nJinwoo Leem, Laura S. Mitchell, James H.R. Farmery, Justin Barton, Jacob D. Galson\n[Patterns (2022): 100513](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2666389922001052) • [code](https:\u002F\u002Fgithub.com\u002Falchemab\u002Fantiberta)\n\n**On Pre-training Language Model for Antibody**\nAnonymous(Paper under double-blind review)\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=zaq4LV55xHl) • [Supplementary](https:\u002F\u002Fopenreview.net\u002Fattachment?id=zaq4LV55xHl&name=supplementary_material)\n\n**Antibody Representation Learning for Drug Discovery**\nLin Li, Esther Gupta, John Spaeth, Leslie Shing, Tristan Bepler, Rajmonda Sulo Caceres\n[arXiv:2210.02881](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.02881)\n\n**Learning Complete Protein Representation by Deep Coupling of Sequence and Structure**\nBozhen Hu, Cheng Tan, Jun Xia, Jiangbin Zheng, Yufei Huang, Lirong Wu, Yue Liu, Yongjie Xu, Stan Z. Li\n[bioRxiv 2023.07.05.547769](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.05.547769v1)\n\n**Leveraging Ancestral Sequence Reconstruction for Protein Representation Learning**\nD. S. Matthews, M. A. Spence, A. C. Mater, J. Nichols, S. B. Pulsford, M. Sandhu, J. A. Kaczmarski, C. M. Miton, N. Tokuriki, C. J. Jackson\n[bioRxiv 2023.12.20.572683](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.20.572683v1) • [code](https:\u002F\u002Fgithub.com\u002FRSCJacksonLab\u002Flocal-ancestral-sequence-embeddings)\n\n**Protein language models are biased by unequal sequence sampling across the tree of life**\nFrances Ding, Jacob Steinhardt\n[bioRxiv 2024.03.07.584001](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.07.584001v1)\n\n**InstructPLM: Aligning Protein Language Models to Follow Protein Structure Instructions**\nJiezhong Qiu, Junde Xu, Jie Hu, Hanqun Cao, Liya Hou, Zijun Gao, Xinyi Zhou, Anni Li, Xiujuan Li, Bin Cui, Fei Yang, Shuang Peng, Ning Sun, Fangyu Wang, Aimin Pan, Jie Tang, Jieping Ye, Junyang Lin, Jin Tang, Xingxu Huang, Pheng Ann Heng, Guangyong Chen\n[bioRxiv 2024.04.17.589642](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.17.589642v1)\n\n### 7.3 Molecular Design Models\n\n> Unlike **function-scaffold-sequence** paradigm in protein design, major molecular design models based on paradigm form DL from 3 kinds of level: **atom-based**, **fragment-based**, **reaction-based**, and they can be categorized as [Gradient optimization](#731-gradient-optimization) or [Optimized sampling](#732-optimized-sampling)(gradient-free). [Click here for detail review](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1359644621002531)In consideration of learning more various of generative models for design, these recommended latest models from **Molecular Design** might be helpful and even be able to be transplanted to protein design.\n> More paper list at :\n>\n> 1. [CondaPereira](https:\u002F\u002Fgithub.com\u002FCondaPereira)'s GitHub repo: [Essay_For_Molecular_Generation](https:\u002F\u002Fgithub.com\u002FCondaPereira\u002FEssay_For_Molecular_Generation).\n> 2. [AspirinCode](https:\u002F\u002Fgithub.com\u002FAspirinCode)'s :[papers-for-molecular-design-using-DL](https:\u002F\u002Fgithub.com\u002FAspirinCode\u002Fpapers-for-molecular-design-using-DL),[awesome-AI4MolConformation-MD](https:\u002F\u002Fgithub.com\u002FAspirinCode\u002Fawesome-AI4MolConformation-MD)\n> 3. [Alex Morehead](https:\u002F\u002Fgithub.com\u002Famorehead)'s :[awesome-molecular-generation](https:\u002F\u002Fgithub.com\u002Famorehead\u002Fawesome-molecular-generation)\n\n#### 7.3.1 Gradient optimization\n\n**Differentiable scaffolding tree for molecular optimization**\nFu, T., Gao, W., Xiao, C., Yasonik, J., Coley, C. W., & Sun, J\n[arXiv preprint arXiv:2109.10469](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.10469) • [code](https:\u002F\u002Fgithub.com\u002Ffutianfan\u002FDST) • Sept 21\n\n**Equivariant Energy-Guided SDE for Inverse Molecular Design**\nFan Bao, Min Zhao, Zhongkai Hao, Peiyao Li, Chongxuan Li, Jun Zhu\n[arXiv:2209.15408](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15408)\n\n**Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design**\nKeir Adams, Connor W. Coley\n[arXiv:2210.04893](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.04893) • [code](https:\u002F\u002Fgithub.com\u002Fkeiradams\u002FSQUID)\n\n**Structure-based Drug Design with Equivariant Diffusion Models**\nArne Schneuing, Yuanqi Du, Charles Harris, Arian Jamasb, Ilia Igashov, Weitao Du, Tom Blundell, Pietro Lió, Carla Gomes, Max Welling, Michael Bronstein, Bruno Correia\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FStructure_based_Drug_Design_with_Equivariant_Diffusion_Models.pdf)\u002F[arXiv:2210.13695](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.13695) • [code](https:\u002F\u002Fgithub.com\u002Farneschneuing\u002FDiffSBDD)\n\n#### 7.3.2 Optimized sampling\n\n**Generating 3D Molecules for Target Protein Binding**\nMeng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, Shuiwang Ji\n[International Conference on Machine Learning 39 (2022)](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fliu22m.html) • [GraphBP](https:\u002F\u002Fgithub.com\u002Fdivelab\u002Fgraphbp)\n\n**Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets**\nPeng, Xingang, et al\n[International Conference on Machine Learning 39 (2022)](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fpeng22b.html) • [code](https:\u002F\u002Fgithub.com\u002Fpengxingang\u002FPocket2Mol)\n\n**Reinforced Genetic Algorithm for Structure-based Drug Design**\nFu, Tianfan, et al\n[arXiv preprint arXiv:2211.16508 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.16508)\u002F[ICML22](https:\u002F\u002Fopenreview.net\u002Fforum?id=_Sfd-icezCa) • [code](https:\u002F\u002Fgithub.com\u002Ffutianfan\u002Freinforced-genetic-algorithm) • [website](https:\u002F\u002Fdeepai.org\u002Fpublication\u002Freinforced-genetic-algorithm-for-structure-based-drug-design)\n\n**Molecule Generation For Target Protein Binding with Structural Motifs**\nZhang, Zaixi, et al\n[International Conference on Learning Representations 11 (2023)](https:\u002F\u002Fopenreview.net\u002Fforum?id=Rq13idF0F73) • [code](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FFLAG)\n\n**3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction**\nGuan, Jiaqi, et al\n[International Conference on Learning Representations 11 (2023)](https:\u002F\u002Fopenreview.net\u002Fforum?id=kJqXEPXMsE0) • [code](https:\u002F\u002Fgithub.com\u002Fguanjq\u002Ftargetdiff)\n\n### 7.4 Unclassified\n\n**De novo design of epitope-specific antibodies against soluble and multipass membrane proteins with high specificity, developability,and function**\n[Nabla Bio](https:\u002F\u002Fwww.nabla.bio\u002F)\n[preprint](https:\u002F\u002Fnabla-public.s3.us-east-1.amazonaws.com\u002F2024_Nabla_JAM_de_novo_antibodies.pdf) • [blog](https:\u002F\u002Fwww.nabla.bio\u002Fnews\u002Fdenovo) • [news](https:\u002F\u002Fwww.science.org\u002Fcontent\u002Farticle\u002Fai-conjures-potential-new-antibody-drugs-matter-months) • commercial\n\n**JAM-2: Fully computational design of drug-like antibodies with high success rates**  \n[Nabla Bio](https:\u002F\u002Fwww.nabla.bio\u002F)\n[Whitepaper](https:\u002F\u002Fnabla-public.s3.us-east-1.amazonaws.com\u002F2025_Nabla_JAM2.pdf)\n\n**Chai-2: Zero-Shot Antibody Discovery in a 24-well Plate**  \nChai Discovery Team  \n[technical report](https:\u002F\u002Fchaiassets.com\u002Fchai-2\u002Fpaper\u002Ftechnical_report.pdf) • [news](https:\u002F\u002Fwww.chaidiscovery.com\u002Fnews\u002Fintroducing-chai-2) • commercial\n\n**Drug-like antibody design against challenging targets with atomic precision**  \nChai Discovery Team  \n[technical report](https:\u002F\u002Fchaiassets.com\u002Fchai-2\u002Fpaper\u002Ftechnical_report_challenging_targets.pdf) • [news](https:\u002F\u002Fwww.chaidiscovery.com\u002Fnews\u002Fchai-2-mab)\n\n**Latent-X: An Atom-level Frontier Model for De Novo Protein Binder Design**  \nLatent Labs Team  \n[technical report](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2025\u002F07\u002FLatent-X-Technical-Report.pdf) • [website](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-x\u002F) • commercial\n\n**Drug-like antibodies with low immunogenicity in human panels designed with Latent-X2**  \nLatent Labs Team  \n[technical report](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2025\u002F12\u002FLatent-X2-Technical-Report.pdf) • [website](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-x2\u002F) • commercial\n\n**Latent-Y: A Lab-Validated Autonomous Agent for De Novo Drug Design**  \nLatent Labs Team  \n[technical report](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2026\u002F03\u002FLatent-Y-Technical-Report.pdf) • [website](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-y\u002F) • commercial\n","# 基于深度学习的蛋白质设计论文列表\n\n> 本仓库受[杨凯创](https:\u002F\u002Fgithub.com\u002Fyangkky)及其杰出项目[Machine-learning-for-proteins](https:\u002F\u002Fgithub.com\u002Fyangkky\u002FMachine-learning-for-proteins)的启发而创建。我们建立此仓库，旨在为**蛋白质设计中的深度学习**这一快速发展的计算生物学领域，提供一个专业且聚焦的平台。\n>\n> 欢迎大家贡献内容和提出建议！蛋白质设计人工智能负责任发展的社区价值观、指导原则及承诺：[详情](https:\u002F\u002Fresponsiblebiodesign.ai\u002F)\n\n\u003C!-- >\n>1. 包含迷你蛋白、结合蛋白、金属蛋白、抗体、肽类及分子设计相关研究  \n>2. 更多从头蛋白质设计论文列表请参见[Wangchentong](https:\u002F\u002Fgithub.com\u002FWangchentong)的GitHub仓库：[paper_for_denovo_protein_design](https:\u002F\u002Fgithub.com\u002FWangchentong\u002Fpaper_for_denovo_protein_design)  \n>3. 我们对这些论文的笔记已分享至**知乎专栏**（简体中文\u002F英文），更多推荐笔记可在[RosettAI](https:\u002F\u002Fwww.zhihu.com\u002Fcolumn\u002Frosettastudy)中找到   -->\n\n*上周论文更新于2026年3月28日：*\n+   固有无序蛋白结合蛋白设计的前沿与挑战\n    + [[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X26000382)]\n+   强化学习引导的生成式蛋白质语言模型实现高度多样化的AAV衣壳从头设计\n    + [[arXiv:2603.19473](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.19473)] • [[代码](https:\u002F\u002Fgithub.com\u002Fliseda-lab\u002FgenAAV)]\n+   CombinGym：用于机器学习辅助组合型蛋白质变体设计的基准测试平台\n    + [[bioRxiv 2026.03.24.714074](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.24.714074v1)] • [[代码](https:\u002F\u002Fgithub.com\u002Fsitonglab\u002FCombinGym)] • [[补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F25\u002F2026.03.24.714074\u002FDC1\u002Fembed\u002Fmedia-1.pdf)] • [[官网](https:\u002F\u002Fwww.combingym.org)]\n+   Latent-Y：经实验室验证的自主药物从头设计智能体\n    + [[技术报告](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2026\u002F03\u002FLatent-Y-Technical-Report.pdf)] • [[官网](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-y\u002F)] • 商业用途\n\n\n\n---\n\n\u003Cp align=\"center\">\n  \u003Cbr>\n  \u003C!-- \u003Cimg src=\"dl_pd.png\" alt=\"deep learning for protein design\" width=\"500\"> -->\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FPeldom_papers_for_protein_design_using_DL_readme_4f4d6762ec60.jpg\" alt=\"deep learning for protein design\">\n\u003C\u002Fp>\n\u003C!-- ## Menu -->\n\u003C!-- > Heading [[2]](#2-model-based-design) follows a **\"generator-predictor-optimizer\" paradigm**, Heading [[3]](#3-function-to-scaffold), [[4]](#4scaffold-to-sequence)&[[6]](#6-function-to-structure) follow [\"Inside-out\" paradigm](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fnature19946)(*function-scaffold-sequence*) from [RosettaCommons](https:\u002F\u002Fwww.rosettacommons.org\u002F), Heading [[5]](#5function-to-sequence)&[[7]](#7-other-tasks) follow other ML\u002FDL strategies   -->\n\u003Cp align='center'>\n  \u003Cstrong>\u003Ca href='#0-benchmarks-and-datasets'>0) Benchmarks and datasets \u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#01-sequence-datasets-benchmarks\">序列数据集\u002F基准测试\u003C\u002Fa> •\n  \u003Ca href=\"#02-structure-datasets-benchmarks\">结构数据集\u002F基准测试\u003C\u002Fa> •\n  \u003Ca href=\"#03-databases\">公共数据库\u003C\u002Fa> •\n  \u003Ca href=\"#04-similar-list\">相似列表\u003C\u002Fa> •\n  \u003Ca href=\"#05-guides\">指南\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#1-reviews\">1) 评论与综述\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#11-de-novo-protein-design\">从头设计\u003C\u002Fa> •\n  \u003Ca href=\"#12-antibody-design\">抗体设计\u003C\u002Fa> •\n  \u003Ca href=\"#13-peptide-design\">肽设计\u003C\u002Fa> •\n  \u003Ca href=\"#14-binder-design\">结合蛋白设计\u003C\u002Fa> •\n  \u003Ca href=\"#15-enzyme-design\">酶设计\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#2-model-based-design\">2) 基于模型的设计\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#21-structure-prediction-model-based\">基于结构预测的模型\u003C\u002Fa> •\n  \u003Ca href=\"#22-cm-align\">CM-Align\u003C\u002Fa> •\n  \u003Ca href=\"#23-msa-transformer-based\">基于MSA的Transformer\u003C\u002Fa> •\n  \u003Ca href=\"#24-LLM-based\">基于LLM\u003C\u002Fa> •\n  \u003Ca href=\"#25-sampling-algorithms\">采样算法\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#3-function-to-scaffold\" class=\"large-link\">3) 功能到支架\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#31-gan-based\">基于GAN\u003C\u002Fa> •\n  \u003Ca href=\"#32-autoencoder-based\">基于自编码器\u003C\u002Fa> •\n  \u003Ca href=\"#33-mlp-based\">基于MLP\u003C\u002Fa> •\n  \u003Ca href=\"#34-diffusion-based\">基于扩散\u003C\u002Fa> •\n  \u003Ca href=\"#35-rl-based\">基于强化学习\u003C\u002Fa> •\n  \u003Ca href=\"#36-flow-based\">基于流模型\u003C\u002Fa> •\n  \u003Ca href=\"#37-score-based\">基于评分模型\u003C\u002Fa> •\n  \u003Ca href=\"#38-autoregressive\">自回归\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#4scaffold-to-sequence\">4) 支架到序列\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#40-review\">综述\u003C\u002Fa> •\n  \u003Ca href=\"#41-mlp-based\">基于MLP\u003C\u002Fa> •\n  \u003Ca href=\"#42-vae-based\">基于VAE\u003C\u002Fa> •\n  \u003Ca href=\"#43-lstm-based\">基于LSTM\u003C\u002Fa> •\n  \u003Ca href=\"#44-cnn-based\">基于CNN\u003C\u002Fa> •\n  \u003Ca href=\"#45-gnn-based\">基于GNN\u003C\u002Fa> •\n  \u003Ca href=\"#46-gan-based\">基于GAN\u003C\u002Fa> •\n  \u003Ca href=\"#47-transformer-based\">基于Transformer\u003C\u002Fa> •\n  \u003Ca href=\"#48-resnet-based\">基于ResNet\u003C\u002Fa> •\n  \u003Ca href=\"#49-diffusion-based\">基于扩散\u003C\u002Fa> •\n  \u003Ca href=\"#410-bayesian-based\">贝叶斯方法\u003C\u002Fa> •\n  \u003Ca href=\"#411-flow-based\">基于流模型\u003C\u002Fa> •\n  \u003Ca href=\"#412-rl-based\">基于强化学习\u003C\u002Fa> •\n  \u003Ca href=\"#413-train-method\">训练方法\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#5function-to-sequence\">5) 功能到序列\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#51-cnn-based\">基于CNN\u003C\u002Fa> •\n  \u003Ca href=\"#52-vae-based\">基于VAE\u003C\u002Fa> •\n  \u003Ca href=\"#53-gan-based\">基于GAN\u003C\u002Fa> •\n  \u003Ca href=\"#54-transformer-based\">基于Transformer\u003C\u002Fa> •\n  \u003Ca href=\"#55-bayesian-based\">贝叶斯方法\u003C\u002Fa> •\n  \u003Ca href=\"#56-rl-based\">强化学习\u003C\u002Fa> •\n  \u003Ca href=\"#57-flow-based\">基于流模型\u003C\u002Fa> •\n  \u003Ca href=\"#58-rnn-based\">基于RNN\u003C\u002Fa> •\n  \u003Ca href=\"#59-lstm-based\">基于LSTM\u003C\u002Fa> •\n  \u003Ca href=\"#510-autoregressive-models\">自回归模型\u003C\u002Fa> •\n  \u003Ca href=\"#511-boltzmann-machine-based\">基于玻尔兹曼机\u003C\u002Fa> •\n  \u003Ca href=\"#512-diffusion-based\">基于扩散\u003C\u002Fa> •\n  \u003Ca href=\"#513-gnn-based\">基于GNN\u003C\u002Fa> •\n  \u003Ca href=\"#514-score-based\">基于评分模型\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#6-function-to-structure\">6) 功能到结构\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#60-review\">综述\u003C\u002Fa> •\n  \u003Ca href=\"#61-lstm-based\">基于LSTM\u003C\u002Fa> •\n  \u003Ca href=\"#62-diffusion-based\">基于扩散\u003C\u002Fa> •\n  \u003Ca href=\"#63-rosettafold-based\">基于RoseTTAFold\u003C\u002Fa> •\n  \u003Ca href=\"#64-cnn-based\">基于CNN\u003C\u002Fa> •\n  \u003Ca href=\"#65-gnn-based\">基于GNN\u003C\u002Fa> •\n  \u003Ca href=\"#66-transformer-based\">基于Transformer\u003C\u002Fa> •\n  \u003Ca href=\"#67-mlp-based\">基于MLP\u003C\u002Fa> •\n  \u003Ca href=\"#68-flow-based\">基于流模型\u003C\u002Fa> •\n  \u003Ca href=\"#69-alphafold-based\">基于AlphaFold\u003C\u002Fa>\n  \u003Cbr>\n  \u003Cstrong>\u003Ca href=\"#7-other-tasks\">7) 其他\u003C\u002Fa>\u003C\u002Fstrong>\n  \u003Cbr>\n  \u003Ca href=\"#71-effects-of-mutation--fitness-landscape\">突变效应与适应度景观\u003C\u002Fa>  •\n  \u003Ca href=\"#72-protein-language-models-plm-and-representation-learning\">蛋白质语言模型与表征学习\u003C\u002Fa>  •\n  \u003Ca href=\"#73-molecular-design-models\">分子设计模型\u003C\u002Fa> •\n  \u003Ca href=\"#74-unclassified\">未分类\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n\n\n## 0. 基准测试和数据集\n\n### 0.1 序列数据集、基准测试\n\n**FLIP：用于蛋白质适应度景观推断的基准任务**\nChristian Dallago、Jody Mou、Kadina E Johnston、Bruce Wittmann、Nick Bhattacharya、Samuel Goldman、Ali Madani、Kevin K Yang\n[NeurIPS 2021 数据集与基准测试赛道](https:\u002F\u002Fopenreview.net\u002Fforum?id=p2dMLEwL8tF)\u002F[bioRxiv 2021](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.11.09.467890v2) • [网站](https:\u002F\u002Fbenchmark.protein.properties\u002F) • [代码](https:\u002F\u002Fgithub.com\u002FJ-SNACKKB\u002FFLIP) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F01\u002F19\u002F2021.11.09.467890\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**评估蛋白质设计中结构到序列模型的基准框架**\nJeffrey Chan、Seyone Chithrananda、David Brookes、Sam Sinai\n该论文未在[2022年结构生物学中的机器学习研讨会](https:\u002F\u002Fnips.cc\u002FConferences\u002F2022\u002FScheduleMultitrack?event=50005)上发表。\n\n**PDBench：评估蛋白质序列设计的计算方法**\nLeonardo V Castorina、Rokas Petrenas、Kartic Subr、Christopher W Wood\n[Bioinformatics, 2023;, btad027](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtad027\u002F6986968) • [代码](https:\u002F\u002Fgithub.com\u002Fwells-wood-research\u002FPDBench)\n\n**针对多样化抗体序列设计的深度生成模型基准测试**\nIgor Melnyk、Payel Das、Vijil Chenthamarakshan、Aurelie Lozano\n[arXiv:2111.06801](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.06801)\n\n**蛋白质工程锦标赛：蛋白质建模与设计的开放科学基准**\nChase Armer、Hassan Kane、Dana Cortade、Dave Estell、Adil Yusuf、Radhakrishna Sanka、Henning Redestig、TJ Brunette、Pete Kelly、Erika DeBenedictis\n[arXiv:2309.09955](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.09955v2)\n\n**神经网络生成的酶的计算评分与实验评估**\nSean R.Johnson、Xiaozhi Fu、Sandra Viknander、Clara Goldin、Sarah Monaco、Aleksej Zelezniak、Kevin K. Yang\n[bioRxiv (2023)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.04.531015v2) • [代码](https:\u002F\u002Fgithub.com\u002Fseanrjohnson\u002Fprotein_scoring)\n\n**FLOP：用于蛋白质野生型适应度景观的任务**\n彼得·莫尔奇·格罗特、理查德·迈克尔、耶斯珀·萨洛蒙、田鹏飞、沃特·布姆斯马\n[bioRxiv 2023.06.21.545880](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.21.545880v2) • [代码](https:\u002F\u002Fgithub.com\u002Fpetergroth\u002FFLOP)\n\n**ProteinGym：蛋白质设计与适应度预测的大规模基准测试**\n帕斯卡尔·诺丁、亚伦·W·科拉施、丹尼尔·里特、卢德·范·尼凯克、施特法妮·保罗、汉森·斯皮纳、内森·罗林斯、艾达·肖、鲁本·魏茨曼、乔纳森·弗雷泽、马法尔达·迪亚斯、丁科·弗朗切斯基、罗斯·奥伦布赫、亚林·加尔、黛博拉·S·马克斯\n[bioRxiv 2023.12.07.570727](https:\u002F\u002Fbiorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.07.570727v1) • [代码](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FProteinGym)\n\n**蛋白质工程锦标赛结果：蛋白质建模与设计的开放科学基准测试**\n蔡斯·阿默、哈桑·卡内、达娜·L·科塔德、亨宁·雷德斯蒂格、大卫·A·埃斯特尔、阿迪尔·优素福、内森·罗林斯、汉森·斯皮纳、黛博拉·马克斯、TJ·布鲁内特、彼得·J·凯利、艾丽卡·德贝内迪克蒂斯\n[bioRxiv 2024.08.12.606135](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.12.606135v1)\u002F[Proteins: Structure, Function, and Bioinformatics (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fprot.70008) • [代码](https:\u002F\u002Fgithub.com\u002Fthe-protein-engineering-tournament\u002Fpet-pilot-2023) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F12\u002F2024.08.12.606135\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**用于蛋白质支架填充问题的生成式AI模型**\n乐图青格、库沙尔·巴达尔、理查德·安南、乔丹·斯特茨、刘晓文和宾海·朱\n[计算生物学杂志](https:\u002F\u002Fwww.liebertpub.com\u002Fdoi\u002F10.1089\u002Fcmb.2024.0510)\n\n**抗体CDR序列设计的逆折叠模型基准测试**\n佩尔·朱尼尔·格赖森、李一凡、郎宇翔、徐晨睿、周毅、庞子威\n[bioRxiv 2024.12.16.628614](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.16.628614v1)\n\n**自监督机器学习方法用于蛋白质设计可改善采样效率，但无法提升高适应度变体的识别能力**\n莫里茨·埃尔特尔、罗科·莫雷蒂、延斯·迈勒和克拉拉·T·舍德尔\n[Science Advances 11.7 (2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.adr7338) • [代码](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002Fprobabilities_design)\n\n**众包蛋白质设计：来自Adaptyv EGFR结合剂竞赛的经验教训**\n图多尔-斯特凡·科泰特、伊戈尔·克拉夫丘克、菲利波·斯托科、诺埃利亚·费鲁兹、安东尼·吉特、小室洋一、卢卡斯·德·阿尔梅达·马查多、弗朗切斯科·帕埃萨尼、西安娜·N·卡利亚、钱斯·A·查拉科姆布、尼基尔·哈斯、艾哈迈德·卡马尔、布鲁诺·E·科雷亚、马丁·帕塞萨、伦纳特·尼克尔、卡蒂克·苏布、莱昂纳多·V·卡斯托里纳、麦克斯韦尔·J·坎贝尔、康斯坦斯·费拉古、帕特里克·基德格、洛根·哈利、克里斯托弗·W·伍德、迈克尔·J·斯塔姆、塔达斯·克卢尼斯、苏莱曼·梅尔特·乌纳尔、埃利安·贝洛特、亚历山大·纳卡以及Adaptyv竞赛组织者\n[bioRxiv 2025.04.17.648362](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.17.648362v2) • [GitHub](https:\u002F\u002Fgithub.com\u002Fadaptyvbio\u002Fegfr2024_post_competition)\n\n**利用安全生物代理对AI驱动蛋白质设计风险的实验评估**\n斯维特兰娜·P·伊科诺莫娃、布鲁斯·J·维特曼、费尔南达·皮奥里诺、大卫·J·罗斯、塞缪尔·W·沙夫特、奥尔加·瓦西里耶娃、埃里克·霍维茨、詹姆斯·迪甘斯、伊丽莎白·A·斯特里查尔斯基、盛琳·林-吉布森、杰弗里·J·塔贡\n[bioRxiv 2025.05.15.654077](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.15.654077v1) • [代码](https:\u002F\u002Fgithub.com\u002Fusnistgov\u002FAIPD_TEVV\u002F)\n\n**抗体结合亲和力成熟与设计的基准测试**\n辛燕·赵、易清·唐、阿克希塔·辛格、维克多·J·坎图、关浩·安、俊锡·李、亚当·E·斯托格斯迪尔、阿什温·库马尔·拉梅什、志强·安、晓倩·蒋、艺珍·金\n[arXiv:2506.04235](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.04235) • [数据集](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FAbBibench\u002FAntibody_Binding_Benchmark_Dataset) • [代码](https:\u002F\u002Fgithub.com\u002FMSBMI-SAFE\u002FAbBiBench)\n\n**戴霍夫图谱：扩展序列多样性以提升蛋白质生成质量**\n凯文·K·杨、萨拉·阿拉姆达里、亚历克斯·J·李、凯莉·凯马克-洛夫莱斯、萨米尔·查尔、加里克·布里克西、卡尔斯·多明戈-恩里奇、陈通·王、苏悦·吕、尼科洛·富西、尼尔·滕嫩霍尔茨、艾娃·P·阿米尼\n[bioRxiv 2025.07.21.665991](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.21.665991v1) • [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdayhoff) • [数据集](https:\u002F\u002Fhuggingface.co\u002Fcollections\u002Fmicrosoft\u002Fdayhoff-atlas-6866d679465a2685b06ee969)\n\n**一致的合成序列解锁全原子从头蛋白质设计中的结构多样性**\n丹尼·赖登巴赫、钟林·曹、左白·张、基兰·迪迪、托马斯·格夫纳、郭庆·周、建·唐、克里斯蒂安·达拉戈、阿拉什·瓦赫达特、埃米内·库楚克本利、卡斯滕·克莱斯\n[arXiv:2512.01976](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01976)\n\n**生成式AI蛋白质模型的基准测试揭示了基于结构与基于序列方法之间的差异**\n亚历山大·J·巴内特、拉真德拉·KC、普拉蒂克夏·潘黛、帕莫达·索马西里、克尔斯滕·A·费尔法克斯、桑迪·洪、亚历克斯·W·休伊特\n[基因组学、蛋白质组学与生物信息学（2026）](https:\u002F\u002Facademic.oup.com\u002Fgpb\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fgpbjnl\u002Fqzag014\u002F8487189)\n\n**AFD-INSTRUCTION：包含功能注释的全面抗体指令数据集，用于基于LLM的理解与设计**\n凌·罗、文斌·江、洪远·昌、欣康·王、旭时·张、月婷·熊、孟莎·童、荣山·于\n[arXiv:2602.04916](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04916) • [代码](https:\u002F\u002Fgithub.com\u002Fdumbgoos\u002FAfd-Instruction\u002F) • [数据集](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLLMasterLL\u002FAFD) • [网站](https:\u002F\u002Fafd-instruction.github.io\u002F)\n\n\n\n### 0.2 结构数据集、基准测试\n\n**AlphaDesign：一种基于图的蛋白质设计方法及在AlphaFoldDB上的基准测试**\n高章阳、谭成、Stan Z. Li\n[arXiv (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079)\n\n**SidechainNet：用于机器学习的全原子蛋白质结构数据集**\n乔纳森·E·金、大卫·瑞安·科斯\n[arXiv](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08162) • [GitHub::sidechainnet](https:\u002F\u002Fgithub.com\u002Fjonathanking\u002Fsidechainnet)\n\n[TDC](https:\u002F\u002Ftdcommons.ai\u002Foverview\u002F) 维护着一个资源列表，目前包含22项与小分子和大分子相关的任务（及其数据集），包括PPI、DDI等。[MoleculeNet](https:\u002F\u002Fgithub.com\u002FGLambard\u002FMolecules_Dataset_Collection) 四年前发布了一个与小分子相关的基准测试。\n\n> 在数据集和基准测试方面，蛋白质设计远不如药物发现成熟（[paperwithcode药物发现基准测试](https:\u002F\u002Fpaperswithcode.com\u002Ftask\u002Fdrug-discovery)）。（或许可以增加对蛋白质设计中深度学习方法（尤其是深度生成模型）的评估）\n> 困难与机遇总是并存。很高兴看到[克里斯蒂安·达拉戈、乔迪·穆、卡迪娜·E·约翰斯顿、布鲁斯·J·维特曼、尼古拉斯·巴塔查里亚、塞缪尔·戈德曼、阿里·马达尼、凯文·K·杨](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.11.09.467890v1)以及[高章阳、谭成、Stan Z. Li](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079)的工作。\n\n**小型蛋白质折叠结构与序列空间的采样**\n托马斯·W·林斯基、凯尔·诺布尔、奥特姆·R·托宾、瑞秋·克劳、劳伦·卡特、杰弗里·L·乌尔鲍尔、大卫·贝克和伊娃-玛丽亚·施特劳赫\n[Nat Commun 13, 7151 (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-34937-8) • [代码](https:\u002F\u002Fgithub.com\u002Fstrauchlab\u002Fscaffold_design) • [补充材料](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41467-022-34937-8\u002FMediaObjects\u002F41467_2022_34937_MOESM1_ESM.pdf)\n\n**OpenProteinSet：面向大规模结构生物学的训练数据集**\n古斯塔夫·阿德里茨、纳齐姆·布阿塔、萨钦·卡迪安、卢卡斯·雅罗施、丹尼尔·贝伦贝格、伊恩·菲斯克、安德鲁·M·沃特金斯、斯蒂芬·拉、理查德·邦诺、穆罕默德·阿尔库赖希\n[arXiv:2308.05326](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.05326) • [OpenFold](https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fopenfold)\n\n**ProteinInvBench：针对多样化任务、模型和指标的蛋白质设计基准测试**\n高张洋、谭成、张一杰、陈星然、李斯坦 Z.\n[GitHub](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FProteinInvBench)\n\n**PDB-Struct：基于结构的蛋白质设计综合基准测试**\n王传锐、钟博泽涛、张佐白、纳伦德拉·乔杜里、桑奇特·米斯拉、唐健\n[arXiv 预印本 arXiv:2312.00080 (2023)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.00080) • [代码](https:\u002F\u002Fgithub.com\u002FWANG-CR\u002FPDB-Struct)\n\n**Scaffold-Lab：统一框架下对蛋白质骨架生成方法的批判性评估与排名**\n郑卓奇、张博、钟博泽涛、刘可欣、于金宇、李正新、朱俊杰、魏婷、陈海峰\n[bioRxiv 2024.02.10.579743](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.10.579743v1) • [代码](https:\u002F\u002Fgithub.com\u002FImmortals-33\u002FScaffold-Lab) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F02\u002F12\u002F2024.02.10.579743\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**抗体 DomainBed：治疗性蛋白质设计中的分布外泛化能力**\n娜塔莎·塔加索夫斯卡、朴智源、马蒂厄·基尔希迈耶、内森·C·弗雷、安德鲁·马丁·沃特金斯、阿亚·阿卜杜勒萨拉姆·伊斯梅尔、阿里安·罗库姆·贾马斯布、埃迪丝·李、泰勒·布莱森、斯蒂芬·拉、丘京贤\n[arXiv:2407.21028](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.21028) • [代码](https:\u002F\u002Fgithub.com\u002Fprescient-design\u002Fantibody-domainbed) • [数据集](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffo\u002Fe670i9adp29yv2knfu6wd\u002Fh?rlkey=uax6phjjfumkk8xoxrbwcit1h&e=1&dl=0)\n\n**大型蛋白质数据库揭示结构互补性与功能局部性**\n帕韦乌·什切尔比亚克、卢卡什·希德洛夫斯基、维托尔德·维尔德曼斯基、P·道格拉斯·伦弗鲁、朱莉娅·科勒·莱曼、托马什·科西奥莱克\n[bioRxiv 2024.08.14.607935](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.14.607935v1) • [代码](https:\u002F\u002Fgithub.com\u002FTomasz-Lab\u002Fprotein-structure-landscape) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F14\u002F2024.08.14.607935\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [网站](https:\u002F\u002Fprotein-structure-landscape.sano.science\u002F)\n\n**蛋白质设计档案（PDA）：40年蛋白质设计的洞见**\n玛尔塔·克罗诺夫斯卡、迈克尔·J·斯塔姆、德里克·N·伍尔夫森、路易吉·F·迪·康斯坦佐、克里斯托弗·W·伍德\n[bioRxiv 2024.09.05.611465](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.05.611465v1)\u002F[Nat Biotechnol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-025-02607-x) • [代码](https:\u002F\u002Fgithub.com\u002Fwells-wood-research\u002Fchronowska-stam-wood-2024-protein-design-archive) • [补充材料](hhttps:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F09\u002F07\u002F2024.09.05.611465\u002FDC1\u002Fembed\u002Fmedia-1.docx) • [网站](https:\u002F\u002Fpragmaticproteindesign.bio.ed.ac.uk\u002Fpda\u002F)\n\n**ProteinBench：蛋白质基础模型的全面评估**\n叶飞、郑在祥、薛东宇、沈雨宁、王立浩、马一鸣、王燕、王鑫友、周向新、顾全全\n[arXiv:2409.06744](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.06744) • [代码](https:\u002F\u002Fproteinbench.github.io\u002F)\n\n**抗体设计生成模型的基准测试及利用对数似然进行序列排序的探索**\n塔利普·乌恰尔、塞德里克·马尔贝尔、费兰·冈萨雷斯\n[bioRxiv 2024.10.07.617023](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.07.617023v3) • [代码](https:\u002F\u002Fgithub.com\u002FAstraZeneca\u002FDiffAbXL)\n\n**迈向稳健的蛋白质生成模型评估：指标的系统性分析**\n帕维尔·斯特拉什诺夫、安德烈·谢夫佐夫、维亚切斯拉夫·梅什恰尼诺夫、玛丽亚·伊万诺娃、费多尔·尼古拉耶夫、奥尔加·卡尔迪蒙、德米特里·韦特罗夫\n[bioRxiv 2024.10.25.620213](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.25.620213v1)\n\n**MotifBench：用于基序支架问题的标准化蛋白质设计基准测试**\n郑卓奇、张博、基兰·迪迪、杨凯文 K.、尹杰森、约瑟夫 L. 沃森、陈海峰、特里普 Brian L.\n[arXiv:2502.12479](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.12479) • [代码](https:\u002F\u002Fgithub.com\u002Fblt2114\u002FMotifBench)\n\n**生成式 AI 蛋白质模型的系统比较揭示了结构与序列基础方法之间的根本差异**\n亚历山大 J·巴内特、KC 拉真德拉、普拉提克夏·潘黛、帕莫达·索马西里、克尔斯滕 A·费尔法克斯、桑迪·洪、亚历克斯 W·休伊特\n[bioRxiv 2025.03.23.644844](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.23.644844v1) • [代码](https:\u002F\u002Fgithub.com\u002Fhewittlab\u002FSystematic-comparison-of-Generative-AI-Protein-Models) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F24\u002F2025.03.23.644844\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**构象特异性设计：一种新的基准测试与算法，应用于工程化组成型活性 MAP 激酶**\n雅各布 A·斯特恩、西巴·阿尔哈尔比、阿南苏基尔蒂·桑德霍卢、斯特凡 T·阿罗尔德、丹尼斯·德拉科尔特\n[bioRxiv 2025.04.23.650138](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.23.650138v1) • [代码](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fcs_design) • [数据集](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fmotif_div)\n\n**PRIDE-新型蛋白质结构设计基准数据集**\n曹汉群、dchenhe\n[github](https:\u002F\u002Fgithub.com\u002Fchq1155\u002FPRIDE_Benchmark_ProteinDesign)\n\n**蛋白质 FID：改进的蛋白质结构生成模型评估方法**\n费利克斯·法尔廷斯、汉内斯·斯塔克、汤米·雅科拉、雷吉娜·巴尔齐莱\n[arXiv:2505.08041](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.08041)\n\n**PDFBench：从功能出发的从头蛋白质设计基准测试**\n匡嘉豪、刘诺伟、孙昌志、季涛、吴元彬\n[arXiv:2505.20346](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.20346) • [网站](https:\u002F\u002Fpdfbench.github.io\u002F) • [代码](https:\u002F\u002Fgithub.com\u002Fpdfbench\u002FPDFBench)\n\n**一种用于预测具有多样几何形状的从头设计蛋白质的改进模型**\n本杰明·奥尔、斯蒂芬妮 E·克里利、代尼兹·阿克皮纳罗格鲁、埃莉诺·朱、迈克尔 J·凯瑟、坦雅·科尔特梅\n[bioRxiv 2025.06.02.657515](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.02.657515v1)\n\n**蛋白质 SE(3)：基于 SE(3) 的蛋白质结构生成模型基准测试**\n于朗、高张洋、谭成、秦晨、周杰、何亮\n[arXiv:2507.20243](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.20243v1)\n\n**评估 AlphaFold、ESMFold 和 ProteinMPNN 对蛋白质设计成功与否的零样本预测能力**\n马里奥·加西亚、加布里埃尔·雅各布·罗克林、苏吉扬·迪克西特\n[bioRxiv 2025.07.29.667290](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.29.667290v1)\n\n**从头设计结合物的实验成功率预测：对3,766个经实验表征的结合物的荟萃分析**  \n马克斯·丹尼尔·奥韦拉特、安德烈亚斯·雷加德、克里斯蒂安·佩德尔·雅各布森、瓦伦塔斯·布拉萨斯、奥利弗·莫雷尔、皮耶特罗·索尔曼尼、蒂莫西·帕特里克·詹金斯  \n[bioRxiv 2025.08.14.670059](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.14.670059v1) • [数据集](https:\u002F\u002Fzenodo.org\u002Frecords\u002F15722219)\n\n**用于从头蛋白质设计的重折叠流程的局限性**  \n凯伦·T·科尔贝尔德、弗谢沃洛德·维柳加、马克西米利安·J.L.J. 弗斯特  \n[bioRxiv 2025.12.09.693122](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.09.693122v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F12\u002F11\u002F2025.12.09.693122\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [数据](https:\u002F\u002Fgithub.com\u002Fkt-korbeld\u002FLimitations-refolding-pipeline-data)\n\n**针对G蛋白偶联受体的生成式从头肽设计方法评估**  \n汉内斯·容克、克拉拉·T·舍德尔  \n[bioRxiv 2026.02.26.708415](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.26.708415v1)\n\n\n\n### 0.3 数据库\n\n> 推荐的蛋白质数据库列表，更多列表请参见[中国国家生物信息中心](https:\u002F\u002Fngdc.cncb.ac.cn\u002Fdatabasecommons\u002F)。\n\n#### 0.3.1 序列数据库\n\n1. [UniProt](https:\u002F\u002Fwww.uniprot.org\u002Fdownloads)\n2. [DisProt](https:\u002F\u002Fdisprot.org)\n3. [MobiDB](https:\u002F\u002Fmobidb.bio.unipd.it\u002F)\n4. [Peptipedia](https:\u002F\u002Fapp.peptipedia.cl\u002F)\n\n#### 0.3.2 结构数据库\n\n| 数据库                                                    | 描述                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |\n| ----------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| [PDB](https:\u002F\u002Fwww.rcsb.org\u002F)                                   | 蛋白质数据库（PDB）是一个包含大型生物分子（如蛋白质和核酸）三维结构数据的数据库。这些数据通过X射线晶体学、核磁共振波谱学或冷冻电子显微镜等实验方法获得。                                                                                                                                                                                                                                                                |\n| [AlphaFoldDB](https:\u002F\u002Falphafold.ebi.ac.uk\u002F)                    | AlphaFoldDB是由DeepMind的AlphaFold系统生成的蛋白质结构预测数据库。它提供了高度准确的蛋白质三维结构预测结果。                                                                                                                                                                                                                                                                                                                                                              |\n| [PDBbind](http:\u002F\u002Fwww.pdbbind.org.cn\u002Fdownload.php)              | PDBbind是PDB数据库中所有类型生物分子复合物结合数据的综合汇编，主要用于开发和验证预测分子相互作用的计算方法。                                                                                                                                                                                                                                                                                                                                                      |\n| [AB-Bind](https:\u002F\u002Fgithub.com\u002Fsarahsirin\u002FAB-Bind-Database)      | AB-Bind是一个抗体结合亲和力数据的数据库，提供经过精心整理的实验结合数据及相应的抗体-蛋白质复合物结构。                                                                                                                                                                                                                                                                                                                                                              |\n| [AntigenDB](http:\u002F\u002Fcrdd.osdd.net\u002Fraghava\u002Fantigendb\u002F)           | AntigenDB是一个手动 curated 的实验验证抗原数据库，包含关于抗原、来源生物体以及相关抗体的详细信息。                                                                                                                                                                                                                                                                                                                                             |\n| [CAMEO](https:\u002F\u002Fwww.cameo3d.org\u002F)                              | CAMEO（连续自动化模型评估）是一个用于自动评估大分子结构预测方法的项目，持续对自动化蛋白质结构预测服务器的性能进行评估。                                                                                                                                                                                                                                                                                                                                                                |\n| [CAPRI](https:\u002F\u002Fwww.ebi.ac.uk\u002Fmsd-srv\u002Fcapri\u002F)                  | 蛋白质-蛋白质相互作用预测的关键评估（CAPRI）是一项面向整个社区的实验，旨在评估蛋白质-蛋白质相互作用预测方法。                                                                                                                                                                                                                                                                                                                                                                           |\n| [PIFACE](http:\u002F\u002Fprism.ccbb.ku.edu.tr\u002Fpiface)                   | PIFACE是一个用于预测蛋白质-蛋白质相互作用的网络服务器，能够识别蛋白质表面潜在的相互作用界面。                                                                                                                                                                                                                                                                                                                                                                                     |\n| [SAbDab](http:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fnewsabdab\u002Fsabdab\u002F) | 结构抗体数据库（SAbDab）是一个自动更新的资源，提供来自PDB的抗体结构信息。它允许用户方便地访问经过整理、注释和分类的抗体结构。                                                                                                                                                                                                                                                                                                     |\n| [SKEMPI v2.0](https:\u002F\u002Flife.bsc.es\u002Fpid\u002Fskempi2)                 | SKEMPI 2.0是一个包含蛋白质-蛋白质复合物中突变引起的结合自由能变化的实验测量值的数据库。                                                                                                                                                                                                                                                                                                                                                                                       |\n| [ProtCAD](http:\u002F\u002Fdunbrack2.fccc.edu\u002Fprotcad\u002F)                  | ProtCAD是一套用于设计和工程化新型蛋白质结构、序列和功能的工具。它允许用户构建和操作复杂的蛋白质结构，生成和评估序列文库，并模拟突变效应。ProtCAD是一套用于设计和工程化新型蛋白质结构、序列和功能的工具。它允许用户构建和操作复杂的蛋白质结构，生成和评估序列文库，并模拟突变效应。 |\n| [Proteinbase](https:\u002F\u002Fproteinbase.com\u002F)|蛋白质设计数据的家园。由[adaptyvbio](http:\u002F\u002Fadaptyvbio.com\u002F)打造的一个开放平台，用于分享蛋白质设计、其实验验证及其设计方法。|\n\n### 0.4 相似列表\n\n> 一些包含使用深度学习进行蛋白质设计相关论文的相似 GitHub 列表：\n\n1. [design_tools](https:\u002F\u002Fgithub.com\u002Fhefeda\u002Fdesign_tools\u002Fblob\u002Fmain\u002FREADME.md)\n2. [awesome-AI-based-protein-design](https:\u002F\u002Fgithub.com\u002Fopendilab\u002Fawesome-AI-based-protein-design)\n3. [ProteinStructureWithDL](https:\u002F\u002Fgithub.com\u002FYang-J-LIN\u002FProteinStructureWithDL)\n4. [可用生物信息学工具和服务列表](https:\u002F\u002Fneurosnap.ai\u002Fservices)\n\n### 0.5 指南\n\nGitHub 上面向初学者的指南\u002F教程：\n\n1. [how_to_create_a_protein](https:\u002F\u002Fgithub.com\u002Funiversvm\u002Fhow_to_create_a_protein)\n2. [protein-design-tutorials](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fprotein-design-tutorials)\n3. [AI-driven-protein-design](https:\u002F\u002Fgithub.com\u002Fmiangoar\u002FAI-driven-protein-design\u002Ftree\u002Fmain)\n\n蛋白质设计实验室合集：\n\n- [ProteinDesignLabs](https:\u002F\u002Fgithub.com\u002FZuricho\u002FProteinDesignLabs)\n- [proteindesigngroups](https:\u002F\u002Fullahsamee.github.io\u002Fproteindesigngroups\u002F)\n\n## 1. 综述\n\n### 1.1 从头设计蛋白质\n\n**蛋白质设计：从计算机模型到人工智能**\nAntonella Paladino, Filippo Marchetti, Silvia Rinaldi, Giorgio Colombo\n[Wiley跨学科评论：计算分子科学 7.5 (2017): e1318](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fwcms.1318)\n\n**蛋白质结构预测与设计的进展**\nBrian Kuhlman, Philip Bradley\n[Nat Rev Mol Cell Biol 20, 681-697 (2019)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41580-019-0163-x)\n\n**深度学习在蛋白质结构建模与设计中的应用**\nWenhao Gao, Sai Pooja Mahajan, Jeremias Sulam, 和 Jeffrey J. Gray\n[Patterns 1.9](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2666389920301902) • 2020年\n\n**高分子科学百年纪念观点：数据驱动的蛋白质设计**\nFerguson, Andrew L., 和 Rama Ranganathan\n[ACS宏分子快报 10.3 (2021)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facsmacrolett.0c00885)\n\n**人工智能在早期药物发现中的应用，助力精准医学**\nFabio Bonioloa, Emilio Dorigattia, Alexander J. Ohnmachta, Dieter Saurb, Benjamin Schuberta, 和 Michael P. Menden\n[Expert Opinion on Drug Discovery 16.9 (2021)](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17460441.2021.1918096)\n\n**利用深度学习进行蛋白质设计**\nDefresne, Marianne, Sophie Barbe, 和 Thomas Schiex\n[国际分子科学杂志 22.21 (2021)](https:\u002F\u002Fwww.mdpi.com\u002F1422-0067\u002F22\u002F21\u002F11741)\n\n**基于深度生成模型的蛋白质序列设计**\nZachary Wu, Kadina E. Johnston, Frances H. Arnold, Kevin K. Yang\n[Current Opinion in Chemical Biology 65](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS136759312100051X) • [笔记](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F466616309) • 2021年\n\n**基于结构的深度学习蛋白质设计**\nOvchinnikov, Sergey, 和 Po-Ssu Huang\n[Current opinion in chemical biology 65](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1367593121001125) • [笔记](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F467001175) • 2021年\n\n**深度学习技术对蛋白质结构预测和蛋白质设计产生了重大影响**\nPearce, Robin, 和 Yang Zhang\n[Current opinion in structural biology 68 (2021)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X21000142)\n\n**从头设计蛋白质的最新进展：原理、方法与应用**\nPan, Xingjie, 和 Tanja Kortemme\n[Journal of Biological Chemistry 296 (2021)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0021925821003367)\n\n**通过深度学习进行蛋白质设计**\nWenze Ding, Kenta Nakai, Haipeng Gong\n[Briefings in Bioinformatics](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbib\u002Fbbac102\u002F6554124) • 2022年3月25日\n\n**用于蛋白质设计的深度生成建模**\nStrokach, Alexey, 和 Philip M. Kim\n[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X21001573) • 2022年\n\n**膜蛋白设计新时代的曙光**\nSowlati-Hashjin, Shahin, Aanshi Gandhi, 和 Michael Garton\n[BioDesign Research (2022)](https:\u002F\u002Fspj.science.org\u002Fdoi\u002F10.34133\u002F2022\u002F9791435)\n\n**深度学习方法在蛋白质设计中对构象灵活性和开关特性的影响**\nRudden, Lucas SP, Mahdi Hijazi, 和 Patrick Barth\n[Frontiers in Molecular Biosciences](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffmolb.2022.928534\u002Ffull)\n\n**基于进化和物理启发的建模进行蛋白质计算设计：当前与未来的协同作用**\nCyril Malbranke, David Bikard, Simona Cocco, Rémi Monasson, Jérôme Tubiana\n[arXiv:2208.13616v2](https:\u002F\u002Farxiv.org\u002Fabs\u002F2208.13616v2)\n\n**从序列到功能，经由结构：深度学习在蛋白质设计中的应用**\nNoelia Ferruz, Michael Heinzinger, Mehmet Akdel, Alexander Goncearenco, Luca Naef, Christian Dallago\n[bioRxiv 2022.08.31.505981](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.31.505981v1)\u002F[Computational and Structural Biotechnology Journal 第21卷，2023年](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2001037022005086) • [补充资料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F09\u002F03\u002F2022.08.31.505981\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [配套列表](https:\u002F\u002Fgithub.com\u002Fhefeda\u002Fdesign_tools\u002Fblob\u002Fmain\u002FREADME.md)\n\n**基于数据驱动方法的蛋白质计算设计：最新进展与展望**\nHaiyan Liu, Quan Chen\n[WIREs Comput Mol Sci. 2022. e1646](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fwcms.1646)\n\n**以设计促理解：将深度学习从蛋白质结构预测推进到蛋白质设计**\nGao, Yuanxu, Jiangshan Zhan, 和 Albert CH Yu\n[MedComm-Future Medicine 1.2 (2022): e22](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Ffull\u002F10.1002\u002Fmef2.22)\n\n**生物信息学中的扩散模型：深度学习革命的新浪潮正在发挥作用**\nZhiye Guo, Jian Liu, Yanli Wang, Mengrui Chen, Duolin Wang, Dong Xu, Jianlin Cheng\n[arXiv:2302.10907](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.10907)\n\n**机器学习在基于进化和物理启发的蛋白质设计中的应用：当前与未来的协同作用**\nCyril Malbranke, David Bikard, Simona Cocco, Rémi Monasson, Jérôme Tubiana\n[Current Opinion in Structural Biology](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X23000453)\n\n**多面体蛋白质组装的从头设计：AI革命前后**\nBhoomika Basu Mallik, Jenna Stanislaw, Tharindu Madhusankha Alawathurage, 和 Alena Khmelinskaia\n[ChemBioChem 2023, e202300117](http:\u002F\u002Fdx.doi.org\u002F10.1002\u002Fcbic.202300117)\n\n**人工智能在蛋白质设计中的研究进展**\nCHEN Zhihang, JI Menglin, QI Yifei\n[合成生物学杂志 (2023)](https:\u002F\u002Fsynbioj.cip.com.cn\u002Farticle\u002F2023\u002F2096-8280\u002F2023-008.shtml)\n\n**图扩散模型综述：生成式AI在分子、蛋白质和材料科学中的应用**\nMengchun Zhang, Maryam Qamar, Taegoo Kang, Yuna Jung, Chenshuang Zhang, Sung-Ho Bae, Chaoning Zhang\n[https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.01565](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2304.01565.pdf)\n\n**利用全局生成模型探索蛋白质序列空间**\n塞尔吉奥·罗梅罗-罗梅罗、塞巴斯蒂安·林德纳、诺埃利亚·费鲁斯\n[arXiv:2305.01941](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.01941)\n\n**蛋白质设计的机器学习时代：四大关键方法综述**\nLucianoSphere\n[Towards Data Science](https:\u002F\u002Ftowardsdatascience.com\u002Fthe-era-of-machine-learning-for-protein-design-summarized-in-four-key-methods-d6f1dac5de96)\n\n**新颖性可以预测吗？**\n克拉拉·范江、珍妮弗·利斯特加滕\n[arXiv:2306.00872](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.00872)\n\n**计算蛋白质设计——未来走向何方？**\n徐彬彬、陈英俊和薛伟伟\n[《当前药物化学》2023年刊](https:\u002F\u002Fwww.eurekaselect.com\u002Farticle\u002F132267)\n\n**蛋白质设计界如何最好地支持希望利用AI工具进行蛋白质结构预测与设计的生物学家？**\n比尔特·霍克尔、陆培龙、阿努姆·格拉斯哥、黛博拉·S·马克斯\n普拉南·查特吉、乔安娜·S.G. 斯卢斯基、奥拉·舒勒-福尔曼、黄伯苏\n[《细胞系统》第14卷第8期（2023）](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(23)00212-0)\n\n**从头设计纳米孔的创制**\n新津蓝\n[《生物工程学会杂志》第101卷第8期（2023）](https:\u002F\u002Fwww.jstage.jst.go.jp\u002Farticle\u002Fseibutsukogaku\u002F101\u002F8\u002F101_101.8_431\u002F_article\u002F-char\u002Fja\u002F)\n\n**用于从头蛋白质设计的生成式人工智能**\n亚当·温尼弗里思、卡洛斯·欧特伊拉尔、布莱恩·希\n[arXiv:2310.09685](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.09685)\n\n**智能蛋白质设计与分子表征技术：综合评述**\n王晶晶、陈昌、姚戈、丁俊杰、王亮亮和姜辉\n[《分子》第28卷第23期（2023）](https:\u002F\u002Fwww.mdpi.com\u002F1420-3049\u002F28\u002F23\u002F7865)\n\n**用于蛋白质序列建模的生成模型：最新进展与未来方向**\n梅赫萨·马尔迪科雷姆、王子睿、纳撒尼尔·帕斯夸尔、丹尼尔·沃尔德林\n[Briefings in Bioinformatics](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F24\u002F6\u002Fbbad358\u002F7325909)\n\n**深度学习赋能下的蛋白质设计新时代**\n哈迈德·哈克扎德、伊利亚·伊加绍夫、阿尔内·施诺因、卡斯珀·戈韦尔德、迈克尔·布朗斯坦、布鲁诺·科雷亚\n[《细胞系统》第14卷第11期](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(23)00298-3)\n\n**深度学习在蛋白质结构预测与设计中的进展及应用**\n尤尔根·雅内斯和佩德罗·贝尔特劳\n[Mol Syst Biol（2024）](https:\u002F\u002Fwww.embopress.org\u002Fdoi\u002Ffull\u002F10.1038\u002Fs44320-024-00016-x)\n\n**从头蛋白质设计——从新结构到可编程功能**\n坦雅·科尔特梅\n[《细胞》第187卷第3期（2024）](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(23)01402-2)\n\n**蛋白质结构与序列的生成模型**\n克洛伊·许、克拉拉·范江和珍妮弗·利斯特加滕\n[Nat Biotechnol 42, 196–199 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-02115-w)\n\n**功能性蛋白质工程与设计实现“AlphaFold时刻”需要什么？**\n罗伯托·A·奇卡和诺埃利亚·费鲁斯\n[Nat Biotechnol 42, 173–174 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-02120-z)\n\n**蛋白质设计：专家观点**\n安妮·多尔\n[Nat Biotechnol 42, 175–178 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-02111-0)\n\n**用于功能性蛋白质设计的机器学习**\n帕斯卡尔·诺廷、内森·罗林斯、亚林·加尔、克里斯·桑德和黛博拉·马克斯\n[Nat Biotechnol 42, 216–228 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02127-0)\n\n**通过从头蛋白质设计激发功能火花**\n亚历山大·E·楚、陆天宇和黄伯苏\n[Nat Biotechnol 42, 203–215 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02133-2) • [海报](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1sG3OlEWvhHcWAdtf7RTcCawAapDmyeEx\u002Fview)\n\n**用于从头药物设计的生成式AI综述：分子与蛋白质生成的新前沿**\n唐翔儒、戴浩华、伊丽莎白·奈特、吴芳、李云阳、李天晓和马克·格斯坦\n[arXiv:2402.08703](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.08703)\n\n**AI辅助蛋白质设计带来的安全挑战**\n菲利普·亨特\n[EMBO Rep（2024）](https:\u002F\u002Fwww.embopress.org\u002Fdoi\u002Ffull\u002F10.1038\u002Fs44319-024-00124-7)\n\n**蛋白质功能设计与优化的机遇与挑战**\n迪娜·利斯托夫、卡斯珀·A·戈韦尔德、布鲁诺·E·科雷亚和萨雷尔·雅各布·弗莱施曼\n[Nat Rev Mol Cell Biol（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41580-024-00718-y)\n\n**深度学习在精准蛋白质设计与结构预测中的应用现状概述**\n萨伯·萨哈尔基兹、梅赫纳兹·莫斯塔法维、阿敏·比拉什克、希瓦·卡里米安、沙扬·哈利洛拉、索赫拉卜·贾费里安、雅尔达·亚兹达尼、伊拉吉·阿里普尔法尔德、尹锡许、马尔齐耶·拉梅扎尼·法拉尼和雷扎·阿哈万-西加里\n[Top Curr Chem (Z) 382, 23 (2024)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs41061-024-00469-6)\n\n**用于蛋白质设计的计算方法**\n诺埃利亚·费鲁斯、阿梅莉·施泰因\n[《蛋白质工程、设计与选择》第37卷，2024年刊](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Farticle\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzae011\u002F7710436)\n\n**基于结构的蛋白质和小分子生成：EGNN与扩散模型的综合评述**\n法尔赞·索莱马尼、埃里克·帕凯、埃尔纳·莉迪娅·维克托和沃杰特·米哈洛夫斯基\n[《计算与结构生物技术期刊》（2024）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2001037024002228)\n\n**机器学习在生物物理学中的应用：从生物分子预测到设计**\n乔纳森·马丁、马科斯·莱奎里卡·马特奥斯、何塞·N·奥努奇克和法鲁克·莫尔科斯\n[《美国国家科学院院刊》第121卷第27期（2024）](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2311807121)\n\n**AI已梦想到大量新型蛋白质。它们真的有用吗？**\n尤恩·卡拉威\n[Nature 634.8034（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-03335-z)\n\n**五个仍对AI构成挑战的蛋白质设计问题**\n萨拉·里尔登\n[Nature 635.8037（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-03595-9)\n\n**人工智能时代的从头蛋白质设计**\n刘楠、金晓成、杨崇州、王梓洋、闵晓平、葛圣祥\n[《生物工程学报》](https:\u002F\u002Fdoi.org\u002F10.13345\u002Fj.cjb.240087)\n\n**蛋白质工程中的生成模型：综合调查**\n陈欣慧、袁艺文、约瑟夫·刘、卓涛梁、朱晓叶、陈佳琪\n[NeurIPS 2024研讨会](https:\u002F\u002Fopenreview.net\u002Fforum?id=Xc7l84S0Ao)\n\n**蛋白质生物信息学中深度学习方法及其对蛋白质设计影响的调查**\n魏航戴\n[arXiv:2501.01477](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.01477)\n\n**蛋白质设计的前景：与诺贝尔奖得主大卫·贝克的问答**\n大卫·贝克和林菲\n[GEN生物技术（2025）](https:\u002F\u002Fwww.liebertpub.com\u002Fdoi\u002Fabs\u002F10.1089\u002Fgenbio.2025.0004?journalCode=genbio)\n\n**蛋白质设计与结构解析在药物发现中的应用**\n佩特拉·邦比茨\n[《晶体学评论》（2024）](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F0889311X.2024.2461923)\n\n**以模型为中心的深度学习在蛋白质设计中的综述**\n格雷戈里·W·凯罗、邱天音、维克多·S·巴蒂斯塔\n[arXiv:2502.19173](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19173)\n\n**计算蛋白质设计**\n凯瑟琳·I·阿尔巴内塞、索菲·巴贝、田上俊介、德里克·N·伍尔夫森和托马斯·希耶克斯\n[《自然综述·方法总论》5.1期（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43586-025-00383-1)\n\n**探索生命的蓝图：抗体与蛋白质设计的创新**\n杨志伟和杰拉尔德·H·卢辛顿\n[《组合化学与高通量筛选》](https:\u002F\u002Fwww.eurekaselect.com\u002Farticle\u002F146786)\n\n**用于蛋白质结构预测与设计的先进深度学习方法**\n张一超、邓宁远、宋欣源、毕子谦、王天阳、姚哲宇、陈可宇、李明、牛倩、刘俊宇、彭本吉、张森、刘明、张力、潘宣赫、王金朗、冯泊逊、温义竹、严立秋、曾洪明、王云泽、秦子渊、景博文、杨俊杰、周俊、梁嘉欣、宋俊豪\n[arXiv:2503.13522](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.13522)\n\n**深度学习驱动的蛋白质结构预测与设计：诺奖得主的关键模型进展及多领域应用**\n杨万青、王延伟、王洋\n[arXiv:2504.01490](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.01490)\n\n**蛋白质的智能挖掘、工程化与从头设计**\n刘翠、史振坤、马洪武、廖小平\n[《生物工程学报》41卷第3期（2025年）](https:\u002F\u002Fcjb.ijournals.cn\u002Fhtml\u002Fcjbcn\u002F2025\u002F3\u002F07240629.htm)\n\n**基于蛋白质的材料：应用、修饰与分子设计**\n阿力提乃·吐努热、郑泽、饶欣然、于洪波、马福英、周雅娴、谢尚贤\n[《BioDesign Research》（2025年）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2693125725000056)\n\n**人工智能正在变革蛋白质研究：结构及其更深层次的应用**\n刘海燕、陈权和刘宇峰\n[hLife（2025年）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2949928325000021)\n\n**用于蛋白质折叠与设计的人工智能方法**\n张志典、欧晨曦、曹叶琳、秋山洋、谢尔盖·奥夫钦尼科夫\n[《当前结构生物学观点》93期（2025年）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X25000843)\n\n**AI4Protein：重塑蛋白质设计的未来**\n王德全、谭哲灵、高进、张绍婷、沈佳琪和陆宇明\n[《中国科学：生命科学》（2025年）](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11427-024-2906-3)\n\n**关于将基于人工智能的蛋白质设计应用于自身免疫性脑炎的评论：令人振奋的可能性与实际考量**\n寇增威\n[《多发性硬化症及相关疾病杂志》（2025年）](https:\u002F\u002Fwww.msard-journal.com\u002Farticle\u002FS2211-0348(25)00335-9\u002Ffulltext)\n\n**计算蛋白质设计：通过计算机辅助工程推动生物技术发展**\n兰吉特·兰博尔、鲁特维克·文卡特桑、阿迈·桑杰·雷德卡尔、维宾·拉马克里希南\n[《生物物理学与分子生物学进展》（2025年）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0079610725000380)\n\n**计算蛋白质设计的进展：原理、策略及在营养与健康领域的应用**\n赵子凌、曲启扬、孙富伟、臧家辰、郑博文、张拓、\n赵广华、吕晨妍、王中江\n[《生物技术进展》（2025年）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0734975025001429)\n\n**人工智能在从头蛋白质设计中的应用**\n姚嘉伟和王晓刚\n[《新型技术和设备中的医学》（2025年）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2590093525000177)\n\n**人工智能驱动的蛋白质设计**\n许环怡、郑依珍、杨玛德琳、罗希特·阿罗拉、杰弗里·I·韦伯、潘诗睿、李莉和乔治·M·丘奇\n[《自然综述·生物工程》（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs44222-025-00349-8)\n\n**DL4Proteins Jupyter笔记本：教你如何利用人工智能进行生物分子结构预测与设计**\n迈克尔·钟友恩、加布·奥、布丽特妮·卡彭蒂埃、斯里瓦尔沙·普瓦达、考特妮·托马斯、杰弗里·J·格雷\n[arXiv:2511.02128](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.02128v1)\n\n**指导生成式模型进行蛋白质设计：提示、引导与对齐**\n菲利波·斯托科、米凯莱·加里博、诺埃利亚·费鲁兹\n[arXiv:2511.21476](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.21476)\n\n**RFDiffusion：用生成式人工智能革新蛋白质设计**\n彭章志（弗雷德）\n[《丝蚕医学杂志》2卷第4期（2025年）](https:\u002F\u002Fjournals.ku.edu\u002Fsjm\u002Farticle\u002Fview\u002F23410)\n\n**人工智能驱动的从头蛋白质设计在探索蛋白质功能宇宙中的作用**\n张国浩、刘传阳、陆嘉杰、张绍伟和朱凌云\n[《生物学》14卷第9期（2025年）：1268页](https:\u002F\u002Fwww.mdpi.com\u002F2079-7737\u002F14\u002F9\u002F1268)\n\n**蛋白质设计与RNA设计：展望**\n陈曦、戴旭、陆培龙\n[《定量生物学》14卷第2期（2026年）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fqub2.70029)\n\n**蛋白质设计的变革：从传统方法到人工智能驱动的精准工程**\n方欣\n[《MedScien》1卷第1期（2025年）](https:\u002F\u002Flseee.net\u002Findex.php\u002Fms\u002Farticle\u002Fview\u002F1426)\n\n**利用人工智能的最新进展进行蛋白质设计**\n拉塞尔·约翰逊\n[《自然化学生物学》（2025年）：1—4页](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-02110-z)\n\n**从头蛋白质设计：临床蛋白质应用中的变革性前沿**\n高杰、郑载勇、于雪婷、罗亚美、于洋和张春翔\n[《转化医学杂志》（2026年）](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1186\u002Fs12967-026-07784-0)\n\n**从头设计TIM桶蛋白：稳定化、多样化与功能化策略的见解**\n朱利安·贝克、塞尔吉奥·罗梅罗-罗梅罗\n[《生物化学学会交流》](https:\u002F\u002Fportlandpress.com\u002Fbiochemsoctrans\u002Farticle\u002F54\u002F2\u002FBST20253060\u002F237195\u002FDesigning-de-novo-TIM-barrels-insights-into)\n\n**人工智能赋能的蛋白质设计助力未来的植物研究与作物育种**\n娄宇轩、吴天昊、夏凡、赵安雯、王向峰\n[《植物生理学》](https:\u002F\u002Facademic.oup.com\u002Fplphys\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fplphys\u002Fkiag147\u002F8528248)\n\n**内在无序蛋白质结合剂设计的前沿与挑战**\n王晨桐、张彦哲、方敏超、彭章志、曹隆兴\n[《当前结构生物学观点》](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X26000382)\n\n### 1.2 抗体设计\n\n**抗体深度学习方法综述**\n乔丹·格雷夫斯、雅各布·拜尔利、爱德华多·普里戈、纳伦·马卡帕蒂、S·文斯·帕里什、布伦达·梅德林和莫妮卡·贝隆多\n[Antibodies 9.2 (2020)](https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fpmc\u002Farticles\u002FPMC7344881\u002Fpdf\u002Fantibodies-09-00012.pdf)\n\n**基于机器学习的适切性单克隆抗体设计的进展与挑战**\n拉赫马德·阿克巴尔、哈比卜·巴舒尔、普尼特·拉瓦特、菲利普·A·罗伯特、伊娃·斯莫罗迪娜、图多尔-斯特凡·科泰特、卡琳·弗莱姆-卡尔森、罗伯特·弗兰克、布里杰·布尚·梅塔、迈·哈·武、塔利普·曾金、何塞·古铁雷斯-马科斯、弗里特约夫·伦德-约翰森、扬·特耶·安德森和维克托·格雷夫\n[Mabs. 第14卷第1期. 泰勒和弗朗西斯, 2022年](https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fpmc\u002Farticles\u002FPMC8928824\u002F)\n\n**基于计算结构的抗体设计进展**\n胡默尔、阿莉莎·M·布伦南·阿巴内德斯和夏洛特·M·迪恩\n[Current Opinion in Structural Biology 74 (2022)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X22000586)\n\n**用于抗体开发的计算与人工智能方法**\n金智善、马修·麦克菲、方乔、奥萨马·阿卜丁、菲利普·M·金\n[Trends in Pharmacological Sciences (2023)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0165614722002796)\n\n**利用深度学习改进疫苗设计**\n安德鲁·P·海德曼、玛格丽特·E·阿克曼\n[Trends in immunology (2023)](https:\u002F\u002Fwww.cell.com\u002Ftrends\u002Fimmunology\u002Ffulltext\u002FS1471-4906(23)00046-7)\n\n**通过计算机模拟方法实现更优抗体的设计：过去、现在与未来**\n安德烈亚斯·埃弗斯、希普拉·马尔霍特拉、瓦尼塔·D·苏德\n[arXiv:2305.07488](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.07488)\n\n**蛋白质设计的AI模型正在推动抗体工程的发展**\n迈克尔·钟友恩、杰弗里·J·格雷\n[Current Opinion in Biomedical Engineering (2023): 100473](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS2468451123000296)\n\n**免疫学与疫苗学中的计算方法：抗体和免疫原的设计与开发**\n费德里卡·瓜拉和乔治奥·科隆博\n[Journal of Chemical Theory and Computation (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jctc.3c00513)\n\n**利用机器学习简化复杂的抗体工程**\n马科夫斯基、艾米丽·K·陈欣婷和彼得·M·泰西耶\n[Cell Systems 14.8 (2023)](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(23)00118-7)\u002F[2022 AIChE年度会议. AIChE, 2022年。](https:\u002F\u002Faiche.confex.com\u002Faiche\u002F2022\u002Fmeetingapp.cgi\u002FPaper\u002F650993)\n\n**AI驱动的B细胞免疫疗法设计**\n布鲁娜·莫雷拉·达席尔瓦、大卫·B·阿舍、尼古拉斯·吉亚德、道格拉斯·E·V·皮雷斯\n[arXiv:2309.01122](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.01122)\n\n**抗体发现与开发中机器学习的最佳实践**\n莱昂纳德·沃斯尼格、诺伯特·富尔特曼、安德鲁·布坎南、桑迪普·库马尔、维克托·格赖夫\n[arXiv:2312.08470](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.08470)\u002F[Drug Discovery Today (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1359644624001508)\n\n**下一代多特异性抗体工程**\n丹尼尔·凯里、马特·沃克、伊莎·辛格、凯尔·西西川、费尔南多·加尔塞斯\n[Antibody Therapeutics (2023): tbad027](https:\u002F\u002Facademic.oup.com\u002Fabt\u002Farticle\u002F7\u002F1\u002F37\u002F7463325)\n\n**抗体工程中机器学习入门**\n[ABHISHAIKE MAHAJAN](https:\u002F\u002Fsubstack.com\u002F@abhishaikemahajan)\n[Substack](https:\u002F\u002Fwww.abhishaike.com\u002Fp\u002Fa-primer-on-ai-in-antibody-engineering) • 博客\n\n**利用深度学习进行抗体设计：从序列与结构设计到亲和力成熟**\n萨拉·朱比、阿莱西奥·米凯利、保罗·米拉佐、朱塞佩·马卡里、乔治奥·恰诺、达里奥·卡达莫内、杜奇奥·梅迪尼\n[Briefings in Bioinformatics, 第25卷第4期, 2024年7月, bbae307](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F4\u002Fbbae307\u002F7705535)\n\n**AI加速的治疗性抗体开发：实践见解**\n卢卡·桑图阿里、玛丽安娜·巴赫曼·萨尔维、伊万尼斯·泽纳里奥斯、布拉克·阿尔帕特\n[Frontiers in Drug Discovery 4 (2024)](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fdrug-discovery\u002Farticles\u002F10.3389\u002Ffddsv.2024.1447867\u002Ffull)\n\n**生成扩散模型驱动的AI抗体设计：当前见解与未来方向**\n辛恒·何、俊睿·李、詹姆斯·徐、洪山、诗怡·沈、思涵·高及H·埃里克·徐\n[Acta Pharmacologica Sinica (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41401-024-01380-y)\n\n**将计算蛋白质设计应用于治疗性抗体的发现——现状与展望**\n韦罗妮卡·别尔斯卡、伊戈尔·雅什奇津、帕维尔·杜季茨、巴托什·扬努什、达维德·霍米奇、索尼娅·沃贝尔、维克托·格赖夫、瑞安·菲汉、贾雷德·阿道夫-布赖福格尔、康拉德·克拉夫奇克\n[arXiv:2503.00913](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.00913)\u002F[Frontiers in Immunology 16 (2025)](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fimmunology\u002Farticles\u002F10.3389\u002Ffimmu.2025.1571371\u002Ffull)\n\n**人工智能驱动的抗体设计与优化计算方法**  \n路易斯·费利佩·韦基耶蒂、布莱恩·纳撒尼尔·维贾亚、阿扎马特·阿尔马努利、贝根奇·杭盖尔季耶夫、玄奎·郑、秀妍·李、美英·车及浩敏·金  \n[mAbs, 2025年](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F19420862.2025.2528902)\n\n**计算机模拟肽设计：方法、资源及AI的作用**  \n普里扬卡·雷·乔杜里、赛·库马尔·米什拉、西达尔特·亚达夫、舒布希·辛格、普尼蒂·马图尔  \n[Journal of Peptide Science 31.12 (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpsc.70063)\n\n**人工智能在抗体设计与开发中的应用：利用计算方法的力量**  \n索达贝·卡武西普尔、马赫迪·巴拉泽什、希瓦·穆罕默迪  \n[Medical & Biological Engineering & Computing (2025)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11517-025-03429-4)\n\n**利用深度学习加速抗体和适配体的开发**  \n潘坦、宋李、金黄、子义周、梁宏  \n[Acta Pharmaceutica Sinica B (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2211383525008251)\n\n### 1.3 肽设计\n\n**用于肽设计的深度生成模型**\n万方平、达芙妮·孔托吉奥戈斯-海因茨和塞萨尔·德拉富恩特-努涅斯\n[Digital Discovery（2022）](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlehtml\u002F2022\u002Fdd\u002Fd1dd00024a)\n\n**针对蛋白质靶标结合的蛋白质片段与肽的设计**\n古普塔、苏切塔娜、诺拉·阿扎德瓦里和帕丽萨·侯赛因扎德\n[BioDesign Research 2022（2022）](https:\u002F\u002Fspj.science.org\u002Fdoi\u002F10.34133\u002F2022\u002F9783197)\n\n**革新基于肽的药物发现：AlphaFold时代后的进展**\n李伟昌、阿鲁普·蒙达尔、布米卡·辛格、伊塞尔·马丁内斯-诺亚、阿尔贝托·佩雷斯\n[Wiley跨学科评论：计算分子科学](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002Fepdf\u002F10.1002\u002Fwcms.1693)\n\n**通过人工智能进行基于肽的药物发现：迈向治疗性肽的自主设计**\n蒙瑟拉特·戈莱斯、阿纳玛丽娅·达萨、加布里埃尔·卡巴斯-莫拉、林迪贝丝·萨尔米恩托-巴隆、胡莉埃塔·塞普尔韦达-雅涅斯、霍达·安瓦里-卡泽马巴德、梅赫迪·D·达瓦里、罗伯托·乌里贝-帕雷德斯、阿尔瓦罗·奥利韦拉-纳帕、马塞洛·A·纳瓦雷特、大卫·梅迪纳-奥尔蒂斯\n[Briefings in Bioinformatics 25.4（2024）](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F4\u002Fbbae275\u002F7690345)\n\n**加速抗菌肽设计：利用深度学习实现快速发现**\n艾哈迈德·M·阿尔-奥马里、亚赞·H·阿卡姆、阿拉·祖尤特、谢玛·尤尼斯、谢法·M·塔瓦勒贝、哈立德·阿尔-萨瓦尔梅、阿姆杰德·阿尔·法胡姆、乔纳森·阿诺德\n[PloS one 19.12（2024）：e0315477](https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle?id=10.1371\u002Fjournal.pone.0315477)\n\n**肽偶联药物研发趋势：人工智能辅助设计**\n张东E、张东E、何通、何通、史天义、史天义、黄坤、黄坤、彭安林、彭安林\n[Frontiers in Pharmacology 16](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fpharmacology\u002Farticles\u002F10.3389\u002Ffphar.2025.1553853\u002Ffull)\n\n**用于抗菌肽设计的生成模型：自编码器及更多**\n卢卡斯·拜尔勒、朱利安·哈恩费尔德、亚历山大·戈斯曼、雷哈内·莫斯托利扎德、弗朗茨·切米奇\n[bioRxiv 2025.10.29.685317](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.29.685317v1) • [补充资料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F10\u002F30\u002F2025.10.29.685317\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fdevshibe\u002Famp-autencoders)\n\n### 1.4 结合物设计\n\n**利用深度学习改进从头设计蛋白质结合物**\n纳撒尼尔·贝内特、布莱恩·科文特里、英娜·戈列什尼克、黄步伟、阿扎·艾伦、狄俄涅·瓦菲阿多斯、彭英波、尤斯塔斯·道帕拉斯、白敏京、兰斯·斯图尔特、弗兰克·迪马约、史蒂文·德芒克、萨瓦斯·萨维德斯、大卫·贝克\n[bioRxiv 2022.06.15.495993](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.15.495993v1)\u002F[Nat Commun 14, 2625（2023）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-38328-5) • [代码](https:\u002F\u002Fgithub.com\u002Fnrbennet\u002Fdl_binder_design) • [新闻](https:\u002F\u002Fphys.org\u002Fnews\u002F2023-08-deep-protein.html)\n\n**数据与人工智能驱动的合成结合蛋白发现**\n李延林、段子欣、李振文、薛伟伟\n[Trends in Pharmacological Sciences（2025）](https:\u002F\u002Fwww.cell.com\u002Ftrends\u002Fpharmacological-sciences\u002Fabstract\u002FS0165-6147(24)00268-2)\n\n**从代码到复杂结构：人工智能驱动的从头结合物设计**\n丹尼尔·R·福克斯、辛西娅·塔韦诺、雅尼克·克莱门特、里斯·格林特、加文·J·诺特\n[Structure（2025）](https:\u002F\u002Fwww.cell.com\u002Fstructure\u002Ffulltext\u002FS0969-2126(25)00311-9)\n\n### 1.5 酶设计\n\n**人工智能在催化稳定性方面的酶设计综述**\n明永凡、王文康、尹锐、曾敏、唐莉、唐世哲、李敏\n[Briefings in Bioinformatics，2023年](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fbib\u002Fbbad065\u002F7086816)\n\n**“可折叠性”在智能酶工程与设计中的应用：以AlphaFold2为例**\n孟巧珍、郭飞\n[Synthetic Biology Journal（2023）](https:\u002F\u002Fsynbioj.cip.com.cn\u002Farticle\u002F2023\u002F2096-8280\u002F2023-011.shtml)\n\n**AlphaFold2与深度学习在阐明酶构象灵活性及其设计应用中的作用**\n卡萨德瓦尔、吉列姆、克里斯蒂娜·杜兰和西尔维娅·奥苏纳\n[JACS Au（2023）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacsau.3c00188)\n\n**利用机器学习加速生物催化发现：酶工程、发现与设计的范式转变**\n布劳恩·马库斯、格鲁伯·克里斯蒂安·C、克拉思尼格·安德烈亚斯、库默尔·阿卡迪耶、卢茨·施特凡、奥伯多尔费尔·古斯塔夫、西罗拉·埃琳娜和斯奈德罗娃·拉德卡\n[ACS Catal. 2023](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facscatal.3c03417)\n\n**通过设计与进化构建酶**\n霍萨克、欧恩·J、佛罗伦斯·J·哈迪和安东尼·P·格林\n[ACS Catalysis 13.19（2023）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facscatal.3c02746)\n\n**用于设计新型酶以生产可再生化学品和燃料的生成建模方法及数据集的进展**\n拉娜·A·巴尔古特、许志清、西达尔斯·贝塔拉、拉达克里希南·马哈德文\n[Current Opinion in Biotechnology，第84卷，2023年](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0958166923001179)\n\n**机器学习辅助酶工程的机遇与挑战**\n杰森·杨、周凡·李、弗朗西斯卡·H·阿诺德\n[ACS Central Science（2024）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facscentsci.3c01275)\n\n**探索酶设计领域：从分子模拟到机器学习**\n周佳慧、黄美兰\n[Chemical Society Reviews（2024）](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002FContent\u002FArticleLanding\u002F2024\u002FCS\u002FD4CS00196F)\n\n**结构预测与计算蛋白质设计用于高效生物催化剂和生物活性蛋白质**\n丽贝卡·布尔、季里·丹博尔斯基、唐纳德·希尔弗特、乌韦·博恩绍尔\n[Angewandte Chemie（英文国际版）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fanie.202421686)\n\n**用于酶设计与生物催化的生成式人工智能**  \n拉塞·米登多夫、诺埃利亚·费鲁兹  \n[arXiv:2602.03779](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.03779)\n\n## 2. 基于模型的设计\n\n> 通过迭代优化算法对训练好的模型进行反演，以进行序列设计。反演后的结构预测模型被称为“幻觉”。\n\n### 2.1 基于结构预测模型\n\n### 2.1.1 基于trRosetta\n\n**利用深度学习设计呈现不连续功能位点的蛋白质**\n道格·提舍尔、西德尼·利桑扎、王珏、董润泽、查看ORCID个人资料的伊万·阿尼申科、卢卡斯·F·米勒斯、谢尔盖·奥夫钦尼科夫、大卫·贝克\n[bioRxiv（2020）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.11.29.402743v1)\n\n**面向分子设计的快速可微DNA和蛋白质序列优化**\n林德尔、约翰内斯和格奥尔格·泽利格\n[arXiv预印本arXiv:2005.11275（2020）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11275)\n\n**基于深度网络幻觉的从头蛋白质设计**\n伊万·阿尼申科、塞缪尔·J·佩洛克、塔穆卡·M·奇迪亚西库、特蕾莎·A·拉梅洛特、谢尔盖·奥夫钦尼科夫、郝景州、库什布·巴夫纳、克里斯托弗·诺恩、亚历克斯·康、阿西姆·K·贝拉、弗兰克·迪马约、劳伦·卡特、卡梅隆·M·乔、加埃塔诺·T·蒙特利奥内及大卫·贝克\n[《自然》杂志（2021年）](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41586-021-04184-w)  • [代码](https:\u002F\u002Fgithub.com\u002Fgjoni\u002FtrDesign) • [trRosetta](https:\u002F\u002Fyanglab.nankai.edu.cn\u002FtrRosetta\u002Fdownload\u002F)\n\n**通过构象景观优化进行蛋白质序列设计**\n克里斯托弗·诺恩、巴斯勒·I·M·维基、戴维·尤尔根斯和谢尔盖·奥夫钦尼科夫\n[《美国国家科学院院刊》2021年第11期](https:\u002F\u002Fwww.pnas.org\u002Fcontent\u002F118\u002F11\u002Fe2017228118) • [代码](https:\u002F\u002Fgithub.com\u002Fgjoni\u002FtrDesign)\n\n**小型β桶状蛋白质的从头设计**\n大卫·E·金、达文·R·詹森、大卫·费尔德曼、道格·蒂舍尔和阿耶莎·萨利姆、卡梅隆·M·乔、李欣婷、劳伦·卡特、卢卡斯·米勒斯、汉娜·阮、亚历克斯·康、阿西姆·K·贝拉、弗朗西斯·C·彼得森、布莱恩·F·沃尔克曼、谢尔盖·奥夫钦尼科夫、大卫·贝克\n[PNAS（2023年），e2207974120](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2207974120) • [代码](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FTrDesign_partialhal)\n\n**利用深度学习探索“暗物质”蛋白质折叠**\n赞德·哈特韦尔德、亚历山德拉·范·霍尔-博瓦伊斯、伊琳娜·莫罗佐娃、乔舒亚·桑德林、卡斯珀·亚历山大·戈弗德、桑德琳·乔治翁、斯特凡·罗塞、安德烈亚斯·卢卡斯、皮埃尔·万德盖因斯特、迈克尔·布朗斯坦、布鲁诺·科雷亚\n[bioRxiv 2023.08.30.555621](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.30.555621v1)\u002F[《细胞系统》杂志](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Ffulltext\u002FS2405-4712(24)00270-9) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F09\u002F01\u002F2023.08.30.555621\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fzanderharteveld\u002Fgenesis)\n\n**利用深度网络幻觉雕刻出糖苷水解酶活性位点，并将其整合到新型蛋白质支架中**\n安德斯·伦斯特鲁普·汉森、弗雷德里克·弗里斯·泰森、拉蒙·克雷韦特、恩里克·马科斯、努辛·阿加贾里和马丁·威廉莫斯\n[ACS合成生物学（2024年）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.3c00674)\n\n**通过对构象景观和序列的隐式建模，实现稳定蛋白质的评分与生成**\n叶林·乔、尤斯塔斯·道帕拉斯、小野山孝太郎、加布里埃尔·罗克林、谢尔盖·奥夫钦尼科夫\n[bioRxiv 2024.12.20.629706](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.20.629706v1)\u002F[《自然通讯》（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-66526-w) • [代码](https:\u002F\u002Fgithub.com\u002Fyehlincho\u002FJoint_Model_Stability) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F22\u002F2024.12.20.629706\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n#### 2.1.2 基于AlphaFold\n\n**使用可微分的Smith-Waterman算法进行多序列比对的端到端学习**\n佩蒂、萨曼莎、巴塔查里亚、尼古拉斯、拉奥、罗山、道帕拉斯、尤斯塔斯、托马斯、尼尔、周俊楠、拉什、亚历山大·M、库、彼得·K、奥夫钦尼科夫、谢尔盖\n[bioRxiv（2021年）](http:\u002F\u002Frepository.cshl.edu\u002Fid\u002Feprint\u002F40409\u002F)\u002F[生物信息学，2022年，btac724](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtac724\u002F6820925) • [ColabDesign](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign)、[SMURF](https:\u002F\u002Fgithub.com\u002Fspetti\u002FSMURF)、[AF2反向传播](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002Faf_backprop) • [我们的笔记1](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F468219547)、[笔记2](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F472037977) • [讲座1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=2HmXwlKWMVs)、[讲座2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BJdRvODiDnk) • [Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FFpYPneYB)\n\n**AlphaDesign：基于AlphaFold的从头蛋白质设计框架**\n延德鲁施、迈克尔、扬·O·科尔贝尔和S·卡希夫·萨迪克\n[bioRxiv（2021年）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.10.11.463937v1)\u002F[分子系统生物学（2025年）](https:\u002F\u002Fwww.embopress.org\u002Fdoi\u002Ffull\u002F10.1038\u002Fs44320-025-00119-z)\n\n**利用AlphaFold实现快速且准确的固定主链蛋白质设计**\n莫法特、刘易斯、乔·G·格里纳和戴维·T·琼斯\n[bioRxiv（2021年）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.08.24.457549v1)\n\n**利用AlphaFold进行蛋白质模型精度的最先进评估**\n詹姆斯·P·罗尼、谢尔盖·奥夫钦尼科夫\n[bioRxiv 2022.03.11.484043](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.03.11.484043v3)\u002F[《物理评论快报》2022年第129卷第23期](https:\u002F\u002Fjournals.aps.org\u002Fprl\u002Fabstract\u002F10.1103\u002FPhysRevLett.129.238101) • [代码](https:\u002F\u002Fgithub.com\u002Fjproney\u002FAF2Rank)\n\n**利用AlphaFold进行考虑溶解度的蛋白质结合肽设计**\n高杉隆次、大植正仁\n[bioRxiv 2022.05.14.491955](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2022.05.14.491955)\u002F[《生物医学》2022年第10卷第7期](https:\u002F\u002Fwww.mdpi.com\u002F2227-9059\u002F10\u002F7\u002F1626) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F05\u002F15\u002F2022.05.14.491955\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fohuelab\u002FSolubility_AfDesign)\n\n**幻觉生成蛋白质组装体**\n巴斯勒·I M 维基、卢卡斯·F 米勒斯、阿莱克西斯·库尔贝、罗伯特·J 拉戈特、尤斯塔斯·道帕拉斯、以利亚斯·金富、萨姆·蒂普斯、瑞安·D 基布勒、明京·白、弗兰克·迪马约、李欣婷、劳伦·卡特、亚历克斯·康、汉娜·阮、阿西姆·K 贝拉、大卫·贝克\n[bioRxiv 2022.06.09.493773](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.09.493773v1)\u002F[《科学》杂志（2022年）](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.add1964) • [相关幻灯片](https:\u002F\u002Fdocs.google.com\u002Fpresentation\u002Fd\u002F1_tvzLKks83sYOKemfFeImCPnWtCQ-CHqmKK_3IQI1so\u002F) • [我们的笔记](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F527152827) • [新闻](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-022-02947-7)\n\n**EvoBind：利用AlphaFold在硅胶中定向进化肽类结合剂**\n帕特里克·布莱恩特、阿尔内·埃洛夫松\n[bioRxiv 2022.07.23.501214](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.23.501214v1) • [代码](https:\u002F\u002Fgithub.com\u002Fpatrickbryant1\u002FEvoBind)\n\n**幻觉生成包含中心口袋的闭合重复蛋白质**\n林娜·安、德里克·R·希克斯、德米特里·佐林、尤斯塔斯·道帕拉斯、巴斯勒·I. M. 维基、卢卡斯·F 米勒斯、阿莱克西斯·库尔贝、阿西姆·K 贝拉、汉娜·阮、亚历克斯·康、劳伦·卡特、大卫·贝克\n[bioRxiv 2022.09.01.506251](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.01.506251v1)\u002F[《自然结构与分子生物学》2023年第30卷，1755–1760页](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41594-023-01112-6) • [补充数据](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41594-023-01112-6\u002FMediaObjects\u002F41594_2023_1112_MOESM1_ESM.pdf)\n\n**利用AlphaFold和蒙特卡洛树搜索预测大型蛋白质复合物的结构**\n帕特里克·布莱恩特、加布里埃莱·波扎蒂、朱文思、阿迪蒂·谢诺伊、彼特拉斯·昆德罗塔斯以及阿尔内·埃洛夫松\n[《自然通讯》2022年第13卷第1期](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-33729-4) • [gitlab](https:\u002F\u002Fgitlab.com\u002Fpatrickbryant1\u002Fmolpc)、[github](https:\u002F\u002Fgithub.com\u002Fpatrickbryant1\u002FMoLPC) • [补充数据1](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.6367019)、[补充数据2](https:\u002F\u002Fdoi.org\u002F10.17044\u002Fscilifelab.19375172)\n\n**通过反转 AlphaFold 结构预测网络进行从头蛋白质设计**\nCasper Goverde、Benedict Wolf、Hamed Khakzad、Stephane Rosset、Bruno E Correia\n[bioRxiv 2022.12.13.520346](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.13.520346v1) • [代码](https:\u002F\u002Fgithub.com\u002Fbene837\u002Faf_gradmcmc) • [讲座1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=aUMGuogMZCA) • [讲座2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4S4J7gbhAa0)\n\n**OpenComplex 的代码**\nJingcheng、Yu 和 Zhaoming、Chen 和 Zhaoqun、Li 和 Mingliang、Zeng 和 Wenjun、Lin 和 He、Huang 和 Qiwei、Ye\n[代码](https:\u002F\u002Fgithub.com\u002Fbaaihealth\u002FOpenComplex)\n\n**利用松弛的序列空间进行高效且可扩展的从头蛋白质设计**\nChristopher Josef Frank、Ali Khoshouei、Yosta de Stigter、Dominik Schiewitz、Shihao Feng、Sergey Ovchinnikov、Hendrik Dietz\n[bioRxiv 2023.02.24.529906](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.24.529906v1) • [代码](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fmain\u002Faf\u002Fexamples\u002Faf_relax_design.ipynb)\n\n**使用 AlphaFold 进行环肽结构预测与设计**\nStephen A. Rettie、Katelyn V. Campbell、Asim K. Bera、Alex Kang、Simon Kozlov、Joshmyn De La Cruz、Victor Adebomi、Guangfeng Zhou、Frank DiMaio、Sergey Ovchinnikov、Gaurav Bhardwaj\n[bioRxiv](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.25.529956v1)\u002F[Nat Commun 16, 4730 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-59940-7) • [代码](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fmain\u002Faf\u002Fexamples\u002Faf_cyc_design.ipynb) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F02\u002F26\u002F2023.02.25.529956\u002FDC1\u002Fembed\u002Fmedia-1.xlsx)\n\n**利用深度学习进行荧光素酶的从头设计**\nAndy Hsien-Wei Yeh、Christoffer Norn、Yakov Kipnis、Doug Tischer、Samuel J. Pellock、Declan Evans、Pengchen Ma、Gyu Rie Lee、Jason Z. Zhang、Ivan Anishchenko、Brian Coventry、Longxing Cao、Justas Dauparas、Samer Halabiya、Michelle DeWitt、Lauren Carter、K. N. Houk 和 David Baker\n[Nature](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-05696-3) • [代码](https:\u002F\u002Ffiles.ipd.uw.edu\u002Fpub\u002FluxSit\u002Fscaffold_generation.tar.gz) • [补充材料](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41586-023-05696-3\u002FMediaObjects\u002F41586_2023_5696_MOESM1_ESM.pdf)\n\n**利用深度学习模型进行结构预测和序列设计，实现蛋白质结合物的计算机模拟进化**\nOdessa J Goudy、Amrita Nallathambi、Tomoaki Kinjo、Nicholas Randolph、Brian Kuhlman\n[bioRxiv 2023.05.03.539278](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.03.539278v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F05\u002F03\u002F2023.05.03.539278\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FKuhlmanLab\u002Fevopro)\n\n**跨膜蛋白结构可溶性类似物的计算设计**\nCasper Alexander Goverde、Martin Pacesa、Lars Jeremy Dornfeld、Sandrine Georgeon、Stephane Rosset、Justas Dauparas、Christian Shellhaas、Simon Kozlov、David Baker、Sergey Ovchinnikov、Bruno Correia\n[bioRxiv 2023.05.09.540044](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.09.540044v2)\u002F[Nature (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-07601-y) • [代码](https:\u002F\u002Fgithub.com\u002Fbene837\u002Faf2seq) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F05\u002F09\u002F2023.05.09.540044\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用 AlphaFold2 和结合亲和力预测模型进行抗体互补决定区序列设计**\nTakafumi Ueki、Masahito Ohue\n[bioRxiv 2023.06.02.543382](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.02.543382v1)\n\n**基于深度学习的诱导契合酶上下文依赖性设计，生成表达良好、热稳定且具有活性的酶**\nLior Zimmerman、Noga Alon、Itay Levin、Anna Koganitsky、Nufar Shpigel、Chen Brestel、Gideon David Lapidoth\n[bioRxiv 2023.07.27.550799](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.27.550799v2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F07\u002F31\u002F2023.07.27.550799\u002FDC1\u002Fembed\u002Fmedia-1.xlsx)\n\n**使用 CarbonDesign 进行高精度且稳健的蛋白质序列设计**\u002F**使用 CarbonDesign 进行精确且稳健的蛋白质序列设计**\nMilong Ren、Chungong Yu、Dongbo Bu、Haicang Zhang\n[bioRxiv 2023.08.07.552204](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.07.552204v1)\u002F[Nat Mach Intell 6, 536–547 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-024-00838-2) • [代码](https:\u002F\u002Fgithub.com\u002Fzhanghaicang\u002Fcarbonmatrix_public)\n\n**利用 AlphaFold 设计靶向蛋白质-蛋白质相互作用的环肽**\nTakatsugu Kosugi、Masahito Ohue\n[bioRxiv 2023.08.20.554056](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.20.554056v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F08\u002F21\u002F2023.08.20.554056\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FYoshitakaMo\u002Flocalcolabfold)\n\n**MetaPPI：基于 CRBN 的新型底物的计算机筛选**\nneoxbio\n[网站](https:\u002F\u002Fwww.neoxbio.com\u002Fplatform-technology.html) • [新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FKb4EQ0YvYDvoLZ_cnAlUPw) • 基于 masif • 商业化\n\n**用于蛋白质设计的 AlphaFold 蒸馏**\n匿名\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=3pgJNIx3gc) • [代码](https:\u002F\u002Fanonymous.4open.science\u002Fr\u002FAFDistill-28C3)\n\n**利用 AlphaFold 高通量计算发现抑制性蛋白质片段**\nAndrew Savinov、Sebastian Swanson、Amy E. Keating、Gene-Wei Li\n[bioRxiv 2023.12.19.572389](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.19.572389v1) • [代码](https:\u002F\u002Fgithub.com\u002Fswanss\u002FFragFold)\n\n**通过多目标优化实现蛋白质序列设计的整合方法**\nLu Hong、Tanja Kortemme\n[bioRxiv 2024.03.01.582670](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.01.582670v1)\u002F[PLOS Computational Biology 20(7)](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1011953) • [代码](https:\u002F\u002Fgithub.com\u002Fluhong88\u002Fint_seq_des) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F03\u002F04\u002F2024.03.01.582670\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用结构预测网络进行蛋白质设计：AlphaFold 和 RoseTTAFold 作为蛋白质结构基础模型**\nJue Wang、Joseph L. Watson 和 Sidney L. Lisanza\n[Cold Spring Harbor Perspectives in Biology(2024)](https:\u002F\u002Fcshperspectives.cshlp.org\u002Fcontent\u002Fearly\u002F2024\u002F03\u002F01\u002Fcshperspect.a041472.short)\n\n**利用深度学习进行上下文依赖性设计的诱导契合酶，可产生表达良好、热稳定性高且具有活性的酶**\nLior Zimmerman、Noga Alon、Itay Levin 和 Gideon D. Lapidoth\n[美国国家科学院院刊 121.11(2024)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2313809121)\n\n**带有封端螺旋的重复 α-β 蛋白质设计**\nDmitri Zorine、David Baker\n[bioRxiv 2024.06.15.590358](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.15.590358v1) • [代码](https:\u002F\u002Fgithub.com\u002Fdmitropher\u002Faf2_multistate_hallucination)\n\n**仅根据蛋白质靶序列设计不同长度的线性与环状肽结合物**\n李秋珍、埃夫斯塔提奥斯·尼古拉斯·弗拉霍斯、帕特里克·布莱恩特\n[bioRxiv 2024.06.20.599739](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.20.599739v1) • [代码](https:\u002F\u002Fzenodo.org\u002Frecords\u002F11543503) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F06\u002F22\u002F2024.06.20.599739\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**BindCraft：功能性蛋白质结合物的一次性设计**\n马丁·帕切萨、伦纳特·尼克尔、约瑟夫·施密特、叶卡捷琳娜·皮亚托娃、克里斯蒂安·谢尔哈斯、卢卡斯·基斯林、安娜·阿尔卡拉兹-塞尔纳、耶林·乔、库鲁什·H·加马里、劳拉·维纽、布拉姆·J·亚赫宁、安德鲁·M·沃拉科特、斯蒂芬·巴克利、桑德琳·乔治翁、卡斯珀·A·戈韦尔德、格奥尔吉奥斯·N·哈佐普洛斯、皮埃尔·贡齐、扬尼克·D·穆勒、杰拉尔德·施万克、谢尔盖·奥夫钦尼科夫、布鲁诺·E·科雷亚\n[bioRxiv 2024.09.30.615802](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.30.615802v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09429-6) • [代码](https:\u002F\u002Fgithub.com\u002Fmartinpacesa\u002FBindCraft)\n\n**基于蛋白质序列信息设计不同长度的线性与环状肽结合物**\n李秋珍、埃夫斯塔提奥斯·尼古拉斯·弗拉霍斯、帕特里克·布莱恩特\n[bioRxiv 2024.06.20.599739](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.20.599739v2) • [代码](https:\u002F\u002Fzenodo.org\u002Frecords\u002F13913345)\n\n**在松弛序列空间中进行优化以实现可扩展的蛋白质设计**\n克里斯托弗·弗兰克、阿里·霍绍伊、拉拉·福布、多米尼克·希维茨、多米尼克·普茨、拉拉·韦伯、赵志轩、服部元幸、冯世豪、约斯塔·德·斯蒂赫特、谢尔盖·奥夫钦尼科夫、亨德里克·迪茨\n[Science386,439–445(2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adq1741) • [代码](https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabDesign)\n\n**AlphaFold2精炼提升大型从头设计蛋白质的可设计性**\n克里斯托弗·约瑟夫·弗兰克、多米尼克·希维茨、拉拉·福斯、谢尔盖·奥夫钦尼科夫、亨德里克·迪茨\n[bioRxiv 2024.11.21.624687](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.21.624687v1) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F14ULdrjOmH-XMtGDrikzjDF1FLegZg3-a?usp=sharing)\n\n**Low-N OpenFold微调可在无需额外结构的情况下改进肽设计**\n西奥多·斯特恩利布、雅库布·奥特维诺夫斯基、萨姆·锡奈、杰弗里·陈\n[机器学习用于结构生物学研讨会，NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FLow-N_OpenFold_fine-tuning_improves_peptide_design_without_additional_structures.pdf)\n\n**HighPlay：基于强化学习和蛋白质结构预测的环肽序列设计**\n林辉天、朱成、商天峰、朱宁、林康、邵翔、王旭东、段洪亮\n[bioRxiv 2025.03.17.643626](http:\u002F\u002Fbiorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.17.643626v1)\n\n**利用计算机模拟进化设计新型螺线管蛋白**\n丹妮拉·普雷托里乌斯、格奥尔吉·伊万诺夫·尼科夫、小盐浩之、史蒂夫-威廉·弗洛伦特、亨利·陶恩特、谢尔盖·奥夫钦尼科夫、詹姆斯·威廉·默里\n[bioRxiv 2025.04.23.646631](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.23.646631v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F04\u002F24\u002F2025.04.23.646631\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**使用EvoBind一次性设计针对HIV-1膜融合的环肽抑制剂**\n迪安德拉·道米勒、费德丽卡·贾马里诺、李秋珍、安德斯·松内博格、拉斐尔·塞尼亚·迪埃斯、帕特里克·布莱恩特\n[bioRxiv 2025.04.30.651413](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.30.651413v1)\n\n**BindEnergyCraft：将蛋白质结构预测器转化为基于能量的模型用于结合物设计**\n迪维娅·诺里、阿尼莎·帕尔桑、卡罗琳·乌勒、温功金\n[arXiv:2505.21241](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21241)\n\n**盲目的双重环肽激动剂从头设计，靶向GCGR和GLP1R**\n李秋珍、艾莉丝·维塔、托马斯·赫莱戴、帕特里克·布莱恩特\n[bioRxiv 2025.06.06.658268](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.06.658268v1) • [代码](https:\u002F\u002Fzenodo.org\u002Frecords\u002F13933365)\n\n**用于反向蛋白质设计的AlphaFold蒸馏**\n伊戈尔·梅尔尼克、奥蕾莉·洛萨诺、帕耶尔·达斯和维吉尔·琴塔马拉克尚\n[Sci Rep 15, 21743 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-025-00436-1) • [代码](https:\u002F\u002Fgithub.com\u002FIBM\u002FAFDistill)\n\n**通过AlphaFold2-Multimer幻觉进行折叠条件下的从头结合物设计**\n孔达米尔·R·鲁斯塔莫夫、阿廖姆·Y·巴耶夫\n[bioRxiv 2025.07.02.662497](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.02.662497v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F05\u002F2025.07.02.662497\u002FDC1\u002Fembed\u002Fmedia-1.docx) • [代码](https:\u002F\u002Fgithub.com\u002FKhondamirRustamov\u002FFoldCraft)\n\n**基于蛋白质序列信息设计线性与环状肽结合物**\n李秋珍、埃夫斯塔提奥斯·尼古拉斯·弗拉霍斯和帕特里克·布莱恩特\n[Commun Chem 8, 211 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42004-025-01601-3)\n\n**使用BindCraft生成高亲和力肽的设计**\n迈克·菲利乌斯、塔纳西斯·帕索斯、于戈·米尼、詹卢卡·图尔科、刘景明、莫妮卡·格纳齐、拉蒙·S.M.鲁思、安迪·C.H.刘、罗莎·D.T.塔、伊萨·H.A.赖克、萨菲娅·齐亚尼、费姆克·J.博克斯曼、塞巴斯蒂安·J.庞普伦\n[bioRxiv 2025.07.23.666285](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.23.666285v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F25\u002F2025.07.23.666285\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**具有保留抗体结合能力的可溶性CCR8类似物的计算设计**\n阮氏姮、刘松明、李一凡、丛龙飞、罗杰·谢克、李德贤、李毅、佩尔·格雷森\n[bioRxiv 2025.08.18.670068](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.670068v1)\n\n**从头设计一种肽调节剂，以逆转与心律失常和癫痫相关的钠通道功能障碍**\n瑞安·马林、本策·黑吉、艾琳·R·卡伦、蒂莫西·M·乔、亚伦·R·罗德里格斯、吕西尔·福西耶、马克·耶海亚、杨林、陈碧星、亚历山大·N·卡奇曼、努尔丁·沙库里、季瑞平、伊莲·Y·万、贾里德·库什纳、史蒂文·O·马克思、谢尔盖·奥夫钦尼科夫、克里斯托弗·D·麦金森、唐纳德·M·伯斯、马努·本-约翰尼\n[Cell (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(25)00860-8)\n\n**使用Germinal高效生成表位靶向的从头抗体**\n路易斯·圣地亚哥·米列-弗拉戈索、约翰·N·王、克劳迪娅·L·德里斯科尔、戴浩宇、塔拉勒·M·维达塔拉、张晓伟、布莱恩·L·希、高晓静\n[bioRxiv 2025.09.19.677421](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.19.677421v2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F25\u002F2025.09.19.677421\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FSantiagoMille\u002Fgerminal)\n\n**mBER：可控制的从头抗体设计，配合百万级实验筛选**\n埃里克·斯旺森、迈克尔·尼科尔斯、苏普里亚·拉维昌德兰、皮尔斯·奥格登\n[bioRxiv 2025.09.26.678877](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.26.678877v1)\n\n**基于深度学习的自动化多目标从头蛋白质设计流程**\n阿姆里塔·纳拉坦比、布莱恩·库尔曼\n[Current protocols 5.10 (2025)](https:\u002F\u002Fcurrentprotocols.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fcpz1.70208)\n\n**蛋白质猎手：利用扩散模型中的结构幻觉进行蛋白质设计**  \nYehlin Cho、Griffin Rangel、Gaurav Bhardwaj、Sergey Ovchinnikov  \n[bioRxiv 2025.10.10.681530](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.10.681530v2) • [代码](https:\u002F\u002Fgithub.com\u002Fyehlincho\u002FProtein-Hunter)\n\n**从头设计蛋白质可靶向难以攻克的致癌性界面**  \nVarshika Ram Prakash、Yusuf Najy、Kalel Garrett、Brian F.P. Edwards、Benjamin L Kidder  \n[bioRxiv 2025.10.22.683953](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.22.683953v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F10\u002F23\u002F2025.10.22.683953\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**HalluDesign：通过迭代式结构幻觉与序列设计实现蛋白质优化及从头设计**  \nMinchao Fang、Chentong Wang、Jungang Shi、Fangbai Lian、Qihan Jin、Zhe Wang、Yanzhe Zhang、Zhanyuan Cui、YanJun Wang、Yitao Ke、Qingzheng Han、Longxing Cao  \n[bioRxiv 2025.11.08.686881](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.08.686881v1) • [代码](https:\u002F\u002Fgithub.com\u002FMinchaoFang\u002FHalluDesign)\n\n**高效从头设计嵌合抗原受体的序列与结构决定因素**  \nArthur Chow、Hoyin Chu、Ruofan Li、Benan Nalbant、Abdul Dozic、Laura Kida、Caleb Lareau  \n[bioRxiv 2025.12.12.694033](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.12.694033v1) • [代码](https:\u002F\u002Fgithub.com\u002Fclareaulab\u002Fdenovo-cart-reproducibility)\n\n**用于小分子免疫传感的蛋白质竞争者从头设计**  \nYosta de Stigter、Tallie Godschalk、Maarten Merkx  \n[bioRxiv 2025.12.16.694474](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.16.694474v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F12\u002F16\u002F2025.12.16.694474\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n#### 2.1.3 基于DMPfold2\n\n**在黑暗中设计：学习深度生成模型用于从头蛋白质设计**  \nMoffat、Lewis、Shaun M. Kandathil 和 David T. Jones  \n[bioRxiv（2022）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.27.478087v1) • [DMPfold2](https:\u002F\u002Fgithub.com\u002Fpsipred\u002FDMPfold2)\n\n#### 2.1.4 基于DeepAb\n\n**迈向针对特定靶标的抗体设计深度学习模型**  \nSai Pooja Mahajan、Jeffrey Ruffolo、Rahel Frick、Jeffrey J. Gray  \n[生物物理杂志 121.3（2022）](https:\u002F\u002Fwww.cell.com\u002Fbiophysj\u002Fpdf\u002FS0006-3495(21)03758-9.pdf) • [DeepAb](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FDeepAb) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LIo-1jPfrns)\n\n**为靶标特异性结合剂幻觉生成结构条件下的抗体文库**  \nSai Pooja Mahajan、Jeffrey A Ruffolo、Rahel Frick、Jeffrey J. Gray  \n[bioRxiv 2022.06.06.494991](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.06.494991v1)\u002F[Front. Immunol. 13:999034](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffimmu.2022.999034\u002Ffull) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F06\u002F06\u002F2022.06.06.494991\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FFvHallucinator)\n\n#### 2.1.5 基于TRDesign\n\n[TRDesign新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FOQzKawtL9RdK9HzYsfu80g)  \n[TIANRANG XLab](https:\u002F\u002Fxlab.tianrang.com\u002F)  \n论文未公开 • [幻灯片](https:\u002F\u002Fpan.baidu.com\u002Fshare\u002Finit?surl=4AOW_D9dwlvC7VGGZA2tmQ&pwd=ffui) • [网站](https:\u002F\u002Fxcreator.tianrang.com\u002Fauth\u002Flogin) • 商业化 • [新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002F45Gz7GWOGxHl0i6LXxTUpw)\n\n#### 2.1.6 基于Boltz\n\n**Boltzdesign1：反演全原子结构预测模型以实现广义生物分子结合剂设计**  \nYehlin Cho、Martin Pacesa、Zhidian Zhang、Bruno E. Correia、Sergey Ovchinnikov  \n[bioRxiv 2025.04.06.647261](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.06.647261v1) • [代码](https:\u002F\u002Fgithub.com\u002Fyehlincho\u002FBoltzDesign1)\n\n#### 2.1.7 基于RareFold\n\n**RareFold：具有非经典氨基酸的蛋白质结构预测与设计**  \nQiuzhen Li、Diandra Daumiller、Patrick Bryant  \n[bioRxiv 2025.05.19.654846](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.19.654846v1) • [代码](https:\u002F\u002Fgithub.com\u002Fpatrickbryant1\u002FRareFold)\n\n#### 2.1.8 基于HelixFold\n\n**HelixDesign-Binder：基于HelixFold3构建的可扩展生产级结合剂设计平台**  \nJie Gao、Jun Li、Jing Hu、Shanzhuo Zhang、Kunrui Zhu、Yueyang Huang、Xiaonan Zhang、Xiaomin Fang  \n[arXiv:2505.21873](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21873) • 基于ESM-IF\n\n**HelixDesign-Antibody：基于HelixFold3构建的可扩展生产级抗体设计平台**  \nJie Gao、Jing Hu、Shanzhuo Zhang、Kunrui Zhu、Sheng Qian、Yueyang Huang、Xiaonan Zhang、Xiaomin Fang  \n[arXiv:2507.02345](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.02345) • [网站](https:\u002F\u002Fpaddlehelix.baidu.com\u002F)\n\n#### 2.1.9 基于ESMfold\n\n**在序列空间中通过平行退火设计蛋白质**  \nPreet Kalani、Vojtěch Spiwok  \n[蛋白质科学 34.10（2025）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70246)\n\n#### 2.1.10 基于tFold\n\n**通过结构驱动的计算工作流程从头设计表位特异性抗体**  \nFandi Wu、Yu Zhao、JiaXiang Wu、Biaobin Jiang、Bing He、Longkai Huang、Chenchen Qin、Yang Xiao、Fan Yang、Rubo Wang、Ningqiao Huang、Huaxian Jia、Yuyi Liu、Houtim Lai、Tingyang Xu、Fang Wang、Zihan Wu、Yidong Song、Shaoning Li、Wei Liu、Yu Rong、Peilin Zhao 和 Jianhua Yao  \n[Nat Commun（2025）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-67361-9) • [代码](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002Ftfold)\n\n#### 2.1.11 基于Chai\n\n**包括蛋白质柔性和构象适应在内的从头设计蛋白质配体**  \nJakob Agamia、Martin Zacharias  \n[bioRxiv 2026.01.08.698398](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.08.698398v1) • [代码](https:\u002Fgithub.com\u002FJakobAgamia\u002FAI-MCLig) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F08\u002F2026.01.08.698398\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n\n\n### 2.2 CM-Align\n\n**AutoFoldFinder：用于从头蛋白质折叠设计的自动化自适应优化工具包**  \nShuhao Zhang、Youjun Xu、Jianfeng Pei、Luhua Lai  \n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_AutoFoldFinder.pdf)\n\n### 2.3 基于MSA-transformer\n\n**基于多序列比对训练的蛋白质语言模型能够学习系统发育关系**  \nDamiano Sgarbossa、Umberto Lupo、Anne-Florence Bitbol  \n[arXiv预印本 arXiv:2203.15465（2022）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.15465)\u002F[bioRxiv 2022.04.14.488405](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.14.488405v1)\n\n**EvoOpt：一种由MSA引导、完全无监督的序列优化管道，用于蛋白质设计**  \nHideki Yamaguchi、Yutaka Saito  \n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FEvoOpt_an_MSA_guided_fully_unsupervised_sequence_optimization_pipeline_for_protein_design.pdf)\n\n**基于多序列比对训练的蛋白质语言模型的生成能力**  \nSgarbossa、Damiano、Umberto Lupo 和 Anne-Florence Bitbol  \n[Elife 12（2023）：e79854](https:\u002F\u002Felifesciences.org\u002Farticles\u002F79854) • [代码](https:\u002F\u002Fgithub.com\u002FBitbol-Lab\u002FIterative_masking)\n\n### 2.4 基于大语言模型\n\n#### 2.4.1 基于GPT\n\n**用于深度流形采样的多片段保留采样**\n丹尼尔·贝伦伯格、李在贤、西蒙·凯洛、朴智源、安德鲁·沃特金斯、弗拉基米尔·格利戈里耶维奇、理查德·邦诺、史蒂芬·拉、曹庆贤\n[arXiv预印本 arXiv:2205.04259 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.04259)\n\n**作为多目标结合物设计范式的蛋白质语言模型偏好优化**\n普里亚·米斯塔尼、文卡特什·梅索尔\n[arXiv:2403.04187](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.04187)\n\n**HMAMP：超体积驱动的多目标抗菌肽设计**\n王莉、李一平、付向征、叶秀才、石俊峰、加里·G·延、曾祥祥\n[arXiv:2405.00753](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.00753)\n\n#### 2.4.2 基于ESM\n\n**利用掩码语言模型的吉布斯采样生成新型蛋白质序列**\n肖恩·R·约翰逊、萨拉·莫纳科、肯尼思·马西、扎伊德·赛义德\n[bioRxiv 2021.01.26.428322](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.01.26.428322v1) • [代码](https:\u002F\u002Fgithub.com\u002Fseanrjohnson\u002Fprotein_gibbs_sampler)\n\n**用于生成式蛋白质设计的高级编程语言**\n布莱恩·希、萨尔瓦托雷·坎迪多、林泽明、奥里·卡贝利、罗山·饶、尼基塔·斯梅塔宁、汤姆·塞尔库、亚历山大·里夫斯\n[bioRxiv 2022.12.21.521526](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.21.521526v1)\n\n**语言模型的泛化能力超越天然蛋白质**\n罗伯特·韦库伊尔、奥里·卡贝利、杜一伦、巴斯勒·IM·维基、卢卡斯·F·米勒斯、尤斯塔斯·道帕拉斯、大卫·贝克、谢尔盖·奥夫钦尼科夫、汤姆·塞尔库、亚历山大·里夫斯\n[bioRxiv 2022.12.21.521521](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.21.521521v1)\n\n**ESMFold 幻觉出类天然蛋白质序列**\n杰利亚兹科·R·杰利亚兹科夫、迭戈·德尔阿拉莫、乔尔·D·卡尔皮亚克\n[bioRxiv 2023.05.23.541774](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.23.541774v1)\n\n**蛋白质语言模型监督下的精确高效蛋白质主链设计方法**\n张博、刘可欣、郑卓奇、刘云飞阳、穆俊熙、魏婷、陈海峰\n[bioRxiv 2023.10.26.564121](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.26.564121v1)\u002F[预印本](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-5450034\u002Fv1) • [代码](https:\u002F\u002Fgithub.com\u002Fsirius777coder\u002FGPDL) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F10\u002F30\u002F2023.10.26.564121\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**由折叠调优型语言模型库大规模揭示的蛋白质序列-结构图未探索区域**\n阿朱纳·M·苏布拉马尼安、马特·汤姆森\n[bioRxiv 2023.12.22.573145](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.22.573145v1)\n\n**神经网络生成酶的计算评分与实验评估**\n肖恩·R·约翰逊、傅晓志、桑德拉·维克南德、克拉拉·戈尔丁、萨拉·莫纳科、阿列克谢·泽列兹尼亚克及凯文·K·杨\n[自然生物技术（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02214-2) • [代码](https:\u002F\u002Fgithub.com\u002Fseanrjohnson\u002Fprotein_scoring)\n\n**利用蛋白质语言模型探索潜在空间以生成肽类似物**\n梁博宇、黄雪婷、蒂博·杜兰、安德鲁·J·威默、白俊\n[arXiv:2408.08341](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.08341) • [代码](https:\u002F\u002Fgithub.com\u002FLabJunBMI\u002FLatent-Space-Peptide-Analogues-Generation)\n\n**借助大型语言模型闭环设计多样且高性能蛋白质**\n卡洛斯·A·戈麦斯-乌里韦、贾菲斯·加多、梅尔别克·伊斯兰诺夫\n[bioRxiv 2024.10.25.620340](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.25.620340v1)\n\n**钥匙切割机：一种用于定制化蛋白质和肽设计的新颖优化框架**\n颜·C·莱瓦、马塞洛·D·T·托雷斯、卡洛斯·A·奥利瓦、塞萨尔·德拉富恩特-努涅斯、卡洛斯·A·布里苏埃拉\n[bioRxiv 2025.01.05.631393](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.05.631393v1) • [代码](https:\u002F\u002Fgithub.com\u002Fcbrizuel\u002FKCM)\n\n**通过基础模型衍生的潜在空间似然优化提升功能性蛋白质生成**\n关昌格、万芳平、马塞洛·D·T·托雷斯、塞萨尔·德拉富恩特-努涅斯\n[bioRxiv 2025.01.07.631724](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.07.631724v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F01\u002F08\u002F2025.01.07.631724\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**DPAC：基于序列的对比学习预测与设计蛋白质-DNA相互作用**\n陈天来、里沙布·普卢古尔塔、普拉奈·武雷、普拉南·查特吉\n[bioRxiv 2025.05.14.654102](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.14.654102v1) • [代码](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fdpac)\n\n**BAGEL：通过探索能量景观进行蛋白质工程**\n雅库布·拉拉、艾哈姆·阿尔-萨法尔、斯特凡诺·安吉奥莱蒂-乌贝尔蒂\n[bioRxiv 2025.07.05.663138](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.05.663138v1) • [代码](https:\u002F\u002Fgithub.com\u002Fsoftnanolab\u002Fbagel)\n\n**GeoEvoBuilder：用于高效功能性和耐热性蛋白质设计的深度学习框架**\n刘佳乐、郭政和赖陆华\n[美国国家科学院院刊 122.41 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2504117122) • [代码](https:\u002F\u002Fgithub.com\u002FPKUliujl\u002FGeoEvoBuilder)\n\n**利用蛋白质折叠算法靶向药物内在无序表位**\n雅库布·拉拉、斯特凡诺·安吉奥莱蒂-乌贝尔蒂\n[bioRxiv 2025.11.11.687846](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.11.687846v1)\n\n#### 2.4.3 基于Antiberta\n\n**DyAb：低数据环境下基于序列的抗体设计与属性预测**\n林耀宇、詹妮弗·L·霍夫曼、安德鲁·利弗-费伊、梁伟青、斯特法尼亚·瓦西拉基、伊迪丝·李、佩德罗·O·皮涅罗、娜塔莎·塔加索夫斯卡、詹姆斯·R·基弗、吴燕、弗兰齐斯卡·西格尔、理查德·邦诺、弗拉基米尔·格利戈里耶维奇、安德鲁·沃特金斯、曹庆贤、内森·C·弗雷\n[bioRxiv 2025.01.28.635353](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.28.635353v1) • [代码](github.com\u002Fprescient-design\u002Flobster) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F02\u002F02\u002F2025.01.28.635353\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于能量景观的方法利用蛋白质语言模型嵌入实现酶的小型化**\n雅库布·拉拉、哈什·阿格拉瓦尔、董凡飞、朱德·威尔斯、斯特凡诺·安吉奥莱蒂-乌贝尔蒂\n[bioRxiv 2026.03.04.709378](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.04.709378v1)\n\n### 2.5 采样算法\n\n**AdaLead：一种简单且鲁棒的自适应贪心搜索算法，用于序列设计**\n萨姆·西奈、理查德·王、亚历山大·沃特利、斯图尔特·斯洛克姆、埃莉娜·洛卡内、埃里克·D·凯尔西\n[arXiv 预印本 arXiv:2010.02141 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.02141) • [代码](https:\u002F\u002Fgithub.com\u002Fsamsinai\u002FFLEXS)\n\n**基于模型设计的自动聚焦预言机**\n范江、克拉拉、珍妮弗·利斯特加滕\n[神经信息处理系统进展第33卷（2020）](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2020\u002Ffile\u002F972cda1e62b72640cb7ac702714a115f-Paper.pdf)\n\n**蛋白质结构预测中能量函数优化的高效 MCMC 方法**\n拉克什米·A·甘塔萨拉、里西·贾伊斯瓦尔、苏普里约·达塔\n[arXiv:2211.03193](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.03193)\n\n**基于梯度的离散 MCMC 插拔式蛋白质定向进化**\n帕特里克·埃马米、艾丹·佩罗、杰弗里·劳、大卫·比亚乔尼、彼得·圣约翰\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FPlug_Play_Directed_Evolution_of_Proteins_with_Gradient_based_Discrete_MCMC.pdf)\u002F[arXiv:2212.09925](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.09925)\n\n**重要性加权期望-最大化方法在蛋白质序列设计中的应用**\n宋振桥、李磊\n[arXiv:2305.00386](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.00386) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F05\u002F09\u002F2023.05.09.539914\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用进化信息指导的蛋白质设计同时增强多种功能特性**\n本杰明·弗拉姆、伊恩·特鲁布里奇、苏阳、亚当·J·里塞尔曼、约翰·B·英格拉汉姆、亚历山德罗·帕塞拉、伊芙·纳皮尔、妮可·N·萨达尼、塞缪尔·林、克里斯汀·罗伯茨、古尔琳·考尔、迈克尔·斯蒂夫勒、黛博拉·S·马克斯、克里斯托弗·D·巴尔、阿米尔·R·汗、克里斯·桑德、尼古拉斯·P·高蒂耶\n[bioRxiv（2023）：2023-05](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.09.539914v1)\n\n**使用基于图的平滑 Gibbs 采样优化蛋白质适应度**\n安德鲁·基尔杰纳、杰森·尹、拉曼·萨穆塞维奇、汤米·雅科拉、雷吉娜·巴尔齐莱、伊拉·菲特\n[arXiv:2307.00494](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.00494) • [代码](https:\u002F\u002Fgithub.com\u002Fkirjner\u002FGGS)\n\n**为功能性蛋白质设计采样蛋白质语言模型**\n热雷米·泰迪·达尔马万、亚林·加尔、帕斯卡尔·诺丁\n[ICLR 2025 工作坊 LMRL](https:\u002F\u002Fopenreview.net\u002Fforum?id=eRALDwvk9O)\n\n**机器学习引导设计中的可靠算法选择**\n克拉拉·范江、朴智源\n[arXiv:2503.20767](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.20767)\n\n**为什么风险对蛋白质结合剂设计至关重要**\n图多尔-斯特凡·科特、伊戈尔·克拉夫丘克\n[arXiv:2504.00146](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.00146)\n\n**指导您最喜欢的蛋白质序列生成模型**\n熊俊豪、亨特·尼索诺夫、伊尚·高尔、珍妮弗·利斯特加滕\n[arXiv:2505.04823](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.04823)\n\n**利用图神经网络和 Metropolis 蒙特卡洛采样进行计算纳米抗体设计**\n王磊、何晓明、郭高星、钱新洲、黄强\n[bioRxiv 2025.06.08.658414](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.08.658414v1) • [代码](https:\u002F\u002Fgithub.com\u002FFudan-HQLab\u002FAiPPA)\n\n**具有多专家的蒙特卡洛树扩散用于蛋白质设计**\n刘雪峰、曹明轩、蒋松浩、罗晓、段小天、王梦迪、托宾·R·索斯尼克、徐金波、里克·史蒂文斯\n[arXiv:2509.15796](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15796)\n\n**用于多样化蛋白质设计的松弛序列采样**\n具周焕、阿里斯托法尼斯·荣托吉安尼斯、班义恩·安德鲁、阿克塞尔·埃拉尔迪、尼古拉斯·富兰克林\n[arXiv:2510.23786](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.23786)\n\n**通过基于 Pareto 的协作优化的多智能体强化学习推进蛋白质设计**\n朱明明、饶嘉华、陈晓宇、袁千木、杨跃东\n[bioRxiv 2026.01.13.699365](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.13.699365v1)\n\n## 3. 骨架构建功能\n\n> 这些模型以笛卡尔坐标、接触图、距离图以及 φ 和 ψ 角度来设计主链\u002F骨架\u002F模板。包括条件\u002F非条件生成模型。\n\n### 3.1 基于 GAN 的\n\n**蛋白质结构的生成建模**\n阿南德、南拉塔、黄博思\n[NeurIPS 2018](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2018\u002Ffile\u002Fafa299a4d1d8c52e75dd8a24c3ce534f-Paper.pdf)\n\n**完全可微分的全原子蛋白质主链生成**\n阿南德·南拉塔、拉斐尔·江口、黄博思\n[OpenReview ICLR 2019 工作坊 DeepGenStruct](https:\u002F\u002Fopenreview.net\u002Fforum?id=SJxnVL8YOV) • 无代码\n\n**RamaNet：利用长短期记忆生成神经网络进行从头螺旋蛋白质主链设计**\n萨班、萨里、米哈伊尔·马尔科夫斯基\n[F1000Research 第9卷（2020）](http:\u002F\u002Ff1000researchdata.s3.amazonaws.com\u002Fmanuscripts\u002F29106\u002Ff45e92eb-5d68-4da0-b918-91ded85d2e7d_22907_-_sari_sabban_v2.pdf) • [代码](https:\u002F\u002Fsarisabban.github.io\u002FRamaNet\u002F) • pyRosetta • tensorflow • 最大化蛋白质荧光\n\n**用于创建路径限定螺旋蛋白质的生成模型**\n尼古拉斯·B·伍德尔、瑞安·基布勒、巴西勒·维基、布莱恩·科文特里\n[bioRxiv 2023.05.24.542095](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.24.542095v1) • [代码](https:\u002F\u002Fgithub.com\u002FNickWoodall\u002FHelixGen)\n\n### 3.2 基于自编码器的方法\n\n**基于自适应采样的鲁棒设计条件化**\nBrookes, David, Hahnbeom Park 和 Jennifer Listgarten  \n[国际机器学习会议。PMLR，2019年](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fbrookes19a\u002Fbrookes19a.pdf)  • 无代码\n\n**IG-VAE：通过直接生成三维坐标进行免疫球蛋白蛋白质的生成建模**\nRaphael R. Eguchi, Christian A. Choe, Po-Ssu Huang  \n[Biorxiv（2020）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.08.07.242347v2) • 无代码\n\n**通过可解释变分自编码器生成蛋白质三级结构**\nXiaojie Guo, Yuanqi Du, Sivani Tadepalli, Liang Zhao, Amarda Shehu  \n[arXiv 预印本 arXiv:2004.07119（2020）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.07119) • 代码不可用\n\n**基于深度流形采样的功能导向蛋白质设计**\nVladimir Gligorijevic, Stephen Ra, Daniel Berenberg, Richard Bonneau, Kyunghyun Cho  \n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_Function-guided_protein_design_by.pdf) • 无代码\n\n**用于从头蛋白质设计的拓扑特征深度锐化**\nZander Harteveld, Joshua Southern, Michaël Defferrard, Andreas Loukas, Pierre Vandergheynst, Micheal Bronstein, Bruno Correia  \n[ICLR2022 药物发现中的机器学习。2022年](https:\u002F\u002Fopenreview.net\u002Fforum?id=DwN81YIXGQP) • 代码不可用\n\n**用于蛋白质设计的端到端深度结构生成模型**\nBoqiao Lai, matthew McPartlon, Jinbo Xu  \n[bioRxiv 2022.07.09.499440](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.09.499440v1)\n\n**通过潜在构象优化进行表位特异性结合蛋白质的深度生成设计**\nRaphael R Eguchi, Christian A Choe, Udit Parekh, Irene S Khalek, Michael D Ward, Neha Vithani, Gregory R Bowman, Joseph G Jardine, Possu Huang  \n[bioRxiv 2022.12.22.521698](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.22.521698v1)\n\n**利用深度生成模型进行蛋白质计算设计与优化**\nBoqiao Lai  \n[arXiv:2408.17241](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.17241) • 博士论文\n\n**CyclicCAE：用于高效异手性大环骨架采样的构象自编码器**\nAndrew C. Powers, P. Douglas Renfrew, Parisa Hosseinzadeh, Vikram Khipple Mulligan  \n[bioRxiv 2025.02.21.639569](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.21.639569v1)\n\n### 3.3 基于MLP的方法\n\n**用于蛋白质设计的以主链为中心的神经网络能量函数**\nBin Huang, Yang Xu, Xiuhong Hu, Yongrui Liu, Shanhui Liao, Jiahai Zhang, Chengdong Huang, Jingjun Hong, Quan Chen & Haiyan Liu  \n[Nature（2022）](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41586-021-04383-5) • [代码](https:\u002F\u002Fzenodo.org\u002Frecord\u002F4533424#.YwP3UPFBwqs)\n\n**具有空腔的蛋白质的从头设计：基于主链中心的神经网络能量函数**\nYang Xu, Xiuhong Hu, Chenchen Wang, Yongrui Liu, Quan Chen  \nHaiyan Liu  \n[Structure（2024）](https:\u002F\u002Fwww.cell.com\u002Fstructure\u002Ffulltext\u002FS0969-2126(24)00007-8)\n\n### 3.4 基于扩散的方法\n\n**针对基序支架问题的蛋白质主链三维概率扩散建模**\nBrian L. Trippe, Jason Yim, Doug Tischer, Tamara Broderick, David Baker, Regina Barzilay, Tommi Jaakkola  \n[arXiv:2206.04119](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.04119v2)\u002F[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FDiffusion_probabilistic_modeling_of_protein_backbones_in_3D_for_the_motif_scaffolding_problem.pdf)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=6TxBxqNME1Y) • [海报](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002Fd3d9446802a44259755d38e6d163e820.png?t=1667835607.0141048) • [补充材料](https:\u002F\u002Fopenreview.net\u002Fattachment?id=6TxBxqNME1Y&name=supplementary_material) • [代码](https:\u002F\u002Fgithub.com\u002Fblt2114\u002FProtDiff_SMCDiff)\n\n**ProteinSGM：基于分数的生成模型用于从头蛋白质设计**\nJin Sub Lee, Philip M Kim  \n[bioRxiv 2022.07.13.499967](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.13.499967v2)\u002F[Nat Comput Sci（2023）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43588-023-00440-3) • [代码](https:\u002F\u002Fgitlab.com\u002Fmjslee0921\u002Fproteinsgm)\n\n**通过折叠扩散生成蛋白质结构**\nKevin E. Wu, Kevin K. Yang, Rianne van den Berg, James Y. Zou, Alex X. Lu, Ava P. Amini  \n[arXiv:2209.15611](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15611v2)\u002F[Nat Commun 15, 1059（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-45051-2) • [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffoldingdiff)\n\n**通过等变扩散定向残基云生成新颖、可设计且多样的蛋白质结构**\nYeqing Lin, Mohammed AlQuraishi  \n[arXiv:2301.12485v3](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.12485v3) • [代码](https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fgenie) • [新闻](https:\u002F\u002Fwww.dw.com\u002Fen\u002Fgenerative-ai-inventing-proteins-is-changing-medicine\u002Fa-66356415)\n\n**具有蛋白质主链生成应用的SE(3)扩散模型**\nJason Yim, Brian L. Trippe, Valentin De Bortoli, Emile Mathieu, Arnaud Doucet, Regina Barzilay, Tommi Jaakkola  \n[arXiv:2302.02277](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.02277v2)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=6TxBxqNME1Y) • [代码](https:\u002F\u002Fgithub.com\u002Fjasonkyuyim\u002Fse3_diffusion) • [补充材料](https:\u002F\u002Fopenreview.net\u002Fattachment?id=6TxBxqNME1Y&name=supplementary_material)\n\n**用于蛋白质结构生成的潜在扩散模型**\nCong Fu, Keqiang Yan, Limei Wang, Wing Yee Au, Michael McThrow, Tao Komikado, Koji Maruhashi, Kanji Uchino, Xiaoning Qian, Shuiwang Ji  \n[arXiv:2305.04120](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.04120)\n\n**扩散模型中实用且渐近精确的条件采样**\nLuhuan Wu, Brian L. Trippe, Christian A. Naesseth, David M. Blei, John P. Cunningham  \n[arXiv:2306.17775](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.17775) • [代码](https:\u002F\u002Fgithub.com\u002Fblt2114\u002Ftwisted_diffusion_sampler)\n\n**基于动力学信息的结构条件化蛋白质设计**\nSimon V. Mathis, Urszula Julia Komorowska, Mateja Jamnik, Pietro Lió  \n[WCBICML2023](https:\u002F\u002Ficml-compbio.github.io\u002F2023\u002Fpapers\u002FWCBICML2023_paper121.pdf)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=jZPqf2G9Sw)\n\n**ForceGen：基于非线性机械展开响应的端到端从头蛋白质生成，使用蛋白质语言扩散模型**\nBo Ni 和 David L. Kaplan 和 M. Buehler  \n[arXiv:2310.10605](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.10605)\u002F[Science Advances 10.6（2024）](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.adl4000) • [补充材料](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffi\u002F33tnpd6u2xwermlvj22y9\u002FSI_3_unfolding_movies_from_dataset.zip?rlkey=qno7rcitcdree8t9cj8wzg9sf&dl=0) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProteinMechanicsDiffusionDesign)\n\n**DiffSDS：用于蛋白质主链修复的几何序列扩散模型**\n匿名  \n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=2xYO9oxh0y)\u002F[arXiv:2301.09642](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.09642)\n\n**一种用于条件扩散建模的框架及其在蛋白质设计基序支架中的应用**\nKieran Didi, Francisco Vargas, Simon V Mathis, Vincent Dutordoir, Emile Mathieu, Urszula J Komorowska, Pietro Lio  \n[arXiv:2312.09236](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.09236)\n\n**基于全局几何感知潜在编码改进的扩散蛋白骨架生成**\n张宇阳、刘宇航、马津娅、李敏、徐春富和龚海鹏  \n[bioRxiv 2023.12.13.571602](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.13.571602v1)\u002F[Nat Mach Intell (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01059-x)• [代码](https:\u002F\u002Fgithub.com\u002Fmeneshail\u002FTopoDiff)\n\n**利用SE(3)流匹配改进基序支架构建**\n杰森·尹、安德鲁·坎贝尔、埃米尔·马蒂厄、安德鲁·Y·K·冯、迈克尔·加斯特格、何塞·希门尼斯-卢纳、萨拉·刘易斯、维克托·加西亚·萨托拉斯、巴斯蒂安·S·维尔林、弗兰克·诺埃、雷吉娜·巴尔齐莱、汤米·S·雅科拉\n[arXiv:2401.04082](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.04082)\u002F[TMLR](https:\u002F\u002Fopenreview.net\u002Fforum?id=fa1ne8xDGn) • [代码1](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fframe-flow),[代码2](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fprotein-frame-flow)\n\n**DiffTopo：利用粗粒度蛋白质拓扑表示进行折叠探索**\n苗洋洋、布鲁诺·科雷亚\n[bioRxiv 2024.02.01.578456](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.01.578456v1)\u002FICLR 2024\n\n**蛋白质结构与对接中的扩散模型**\n杰森·尹、汉内斯·施塔克、加布里埃莱·科尔索、景博文、雷吉娜·巴尔齐莱、汤米·S·雅科拉\n[Wiley跨学科评论：计算分子科学 14.2 (2024)](https:\u002F\u002Fwires.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fwcms.1711) • 综述\n\n**基于SE(3)扩散的从头抗体设计**\n丹尼尔·卡廷、弗雷德里克·A·德雷耶、大卫·埃林顿、康斯坦丁·施奈德、夏洛特·M·迪恩\n[arXiv:2405.07622](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.07622)\n\n**众里寻一：利用Genie 2在结构宇宙尺度上设计与搭建蛋白质**\n林叶青、李敏智、张兆、穆罕默德·阿尔库赖希\n[arXiv:2405.15489](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.15489) • [代码](https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fgenie2) • [新闻](https:\u002F\u002Fwww.marktechpost.com\u002F2024\u002F05\u002F29\u002Fgenie-2-transforming-protein-design-with-advanced-multi-motif-scaffolding-and-enhanced-structural-diversity\u002F)\n\n**DSG2-mini**\n[DiffuseBio](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fdiffuse-bio\u002F)\n[技术附录](https:\u002F\u002Fdiffuse.bio\u002Fupdates.html#appendix) • [网站](https:\u002F\u002Fapp.diffuse.bio\u002F) • 商业化\n\n**用于多基序支架构建的浮动锚点扩散模型**\n刘凯、毛伟安、沈帅科、焦晓然、孙正、陈浩、沈春华\n[ICML 2024](https:\u002F\u002Fproceedings.mlr.press\u002Fv235\u002Fliu24av.html)\u002F[arXiv:2406.03141](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.03141) • [代码](https:\u002F\u002Fgithub.com\u002Faim-uofa\u002FFADiff) • [海报](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2024\u002Fposter\u002F34654)\n\n**用于GPCR研究的融合蛋白工具的从头设计**\n高凯轩、张欣、聂佳、孟恒宇、张伟设、田博雪、刘向宇\n[bioRxiv 2024.09.14.613090](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.14.613090v1)\u002F[美国国家科学院院刊 122.29 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2422360122) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F09\u002F15\u002F2024.09.14.613090\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于RF扩散\n\n**Text2Protein：基于给定描述的指定蛋白质设计生成模型**\n拉姆廷·侯赛尼、张思扬、谢鹏涛\n[预印本（第1版）可在Research Square上获取](https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-4868665\u002Fv1) • [代码](https:\u002F\u002Fgithub.com\u002Fszhan227\u002Ftext2protein)\n\n**通过顺序蒙特卡洛进行扩散后验采样，实现蛋白质基序的零样本支架构建**\n杨、詹姆斯·马修·乌永戈科和奥梅尔·德尼兹·阿基尔迪兹\n[帝国理工学院科学、技术和医学学院，2024年](https:\u002F\u002Fmatsagad.com\u002Ffiles\u002Fpapers\u002FMRes_Project.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fmatsagad\u002Fmres-project) • 硕士论文 • 基于Genie\n\n**基于扩散和ESM2模型的类似蛋白A肽的设计**\n赵龙、何强、宋慧嘉、周天谦、罗安、文振国、王腾和林晓竹\n[Molecules 29.20 (2024)](https:\u002F\u002Fwww.mdpi.com\u002F1420-3049\u002F29\u002F20\u002F4965) • [代码](https:\u002F\u002Fgithub.com\u002Ftomlongcool\u002Fdiffusion4Protein)\n\n**FoldMark：通过水印保护蛋白质生成模型**\n张在熙、金若凡、傅凯迪、黎聪、马林卡·齐特尼克、王梦迪\n[arXiv:2410.20354](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.20354) • [代码](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FFoldMark)\n\n**ProteinWeaver：一种用于蛋白质骨架设计的分而治之方法**\n马一鸣、叶飞、周毅、郑在祥、薛东宇、顾全全\n[arXiv:2411.16686](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.16686)\n\n**关于通过顺序蒙特卡洛进行扩散后验采样以实现蛋白质基序的零样本支架构建**\n詹姆斯·马修·杨、O·德尼兹·阿基尔迪兹\n[arXiv:2412.05788](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.05788) • [代码](https:\u002F\u002Fgithub.com\u002Fmatsagad\u002Fmres-project)\n\n**从热力学到蛋白质设计：面向自主蛋白质工程的生物分子生成扩散模型**\n李文然、泽维尔·F·卡代、大卫·梅迪纳-奥尔蒂斯、梅赫迪·D·达瓦里、拉马纳坦·索德哈米尼、塞德里克·达穆尔、李宇、阿兰·米兰维尔、弗雷德里克·卡代\n[arXiv:2501.02680](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.02680) • 综述\n\n**RF扩散在用于生化检测的功能性蛋白质结合剂的从头设计中表现出较低的成功率**\n布鲁斯·江、李晓晓、郭安珀、莫里斯·魏、吴乔尼\n[bioRxiv 2025.02.07.636769](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.07.636769v1)\n\n**从原子到片段：用于高效且功能性蛋白质设计的粗粒度表示**\n莱昂纳多·V·卡斯托里纳、克里斯托弗·W·伍德、卡尔蒂克·苏布\n[bioRxiv 2025.03.19.644162](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.19.644162v2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F20\u002F2025.03.19.644162\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于RF扩散\n\n**基于潜在空间和结构扩散的分层蛋白质骨架生成**\n杰森·尹、马鲁安·贾基克、刘戈、雅各布·格申、卡斯滕·克莱斯、戴维·贝克、雷吉娜·巴尔齐莱、汤米·雅科拉\n[ICLR 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=J19jKa3wFj)\n\n**原子之舞——基于扩散模型的从头蛋白质设计**\n秦宇杰、何明、于昌勇、倪明、刘贤、薄晓晨\n[arXiv:2504.16479](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.16479) • 综述\n\n**ProT-GFDM：用于蛋白质生成的生成式分数阶扩散模型**  \n梁晓、马文涛、埃里克·帕克、埃尔娜·莉迪娅·维克托、沃伊切赫·米哈洛夫斯基\n[arXiv:2504.21092](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.21092)\n\n**NMA-tune：生成高度可设计且考虑动态特性的蛋白质骨架**  \n乌尔舒拉·朱莉娅·科莫罗夫斯卡、弗朗西斯科·巴尔加斯、亚历山德罗·隆迪纳、皮耶特罗·利奥、马泰娅·雅姆尼克  \n[ICML 2025海报](https:\u002F\u002Fopenreview.net\u002Fforum?id=2dlTi4S4JN)\n\n**AIDO.StructureDiffusion：用于分子设计的AIDO模块**  \n[GenBio团队](https:\u002F\u002Fgenbio.ai\u002Fauthor\u002Fgenbioaiteam\u002F)  \n[网站](https:\u002F\u002Fgenbio.ai\u002Faido-structurediffusion-the-aido-module-for-molecular-design\u002F)\n\n**从头设计磷酸化诱导的蛋白质开关，用于细胞中的合成信号传导**  \n斯蒂芬·巴克利、苗阳阳、穆巴拉克·伊德里斯、李宝婉、利奥·谢勒、罗兰·里克、塞巴斯蒂安·J·马克尔、卢西亚诺·A·阿布里亚塔、布鲁诺·E·科雷亚  \n[bioRxiv 2025.09.10.675034](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.10.675034v1)\n\n**具有严格结构约束的蛋白质设计中的受限扩散**  \n雅各布·K·克里斯托弗、奥斯汀·西曼、崔静怡、萨加尔·卡雷、费迪南多·菲奥雷托  \n[bioRxiv 2025.10.15.682365](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.15.682365v1)\n\n**通过费曼-卡茨引导实现可控的蛋白质设计**  \n埃里克·哈特曼、乔纳斯·瓦林、约翰·马尔姆斯特伦、吉米·奥尔松  \n[arXiv:2511.09216](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.09216) • [代码](https:\u002F\u002Fgithub.com\u002FErikHartman\u002FFK-RFdiffusion)\n\n**基于嵌入学习的蛋白质生成，用于基序多样化**  \n凯文·米夏列维奇、金晨、菲利普·亚历山大·蒂尔、汤姆·迪特、毛里西奥·巴拉霍纳、芭芭拉·布拉维、阿舍尔·穆洛坎多夫  \n[arXiv:2510.18790](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.18790)\n\n**扭转空间扩散法用于蛋白质主链生成及几何精修**  \n拉克沙迪提亚·辛格、阿德瓦特·谢尔克、迪万尚·阿格瓦尔  \n[arXiv:2511.19184](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.19184)\n\n**SaDiT：基于潜在结构标记和扩散变换器的高效蛋白质主链设计**  \n莫申通、李兰青  \n[arXiv:2602.06706](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.06706)\n\n\n\n### 3.5 基于强化学习的方法\n\n**利用强化学习自上而下设计蛋白质纳米材料**  \n艾萨克·D·卢茨、王顺志、克里斯托弗·诺恩、安德鲁·J·博斯特、赵艳婷、安妮·多西、曹龙兴、李哲、白敏京、尼尔·P·金、汉内莱·鲁霍拉-贝克、大卫·贝克  \n[bioRxiv 2022.09.25.509419](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.25.509419v1)\u002F[Science380, 266-273(2023)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adf6591) • [代码](https:\u002F\u002Fgithub.com\u002Fidlutz\u002Fprotein-backbone-MCTS),[代码2](https:\u002F\u002Ffiles.ipd.uw.edu\u002Fpub\u002F2023_RL_capsid_design\u002Fsequence_design_pipeline.tar)\n\n**基于模型的强化学习用于蛋白质主链设计**  \n弗雷德里克·雷纳尔、西普里安·库尔托、阿尔弗雷多·赖克林、奥利弗·本特  \n[arXiv:2405.01983](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.01983)\n\n**基于目标的环肽结合蛋白从头设计**  \n王凡浩、张天田、朱金涛、张晓玲、张昌盛、赖陆华  \n[bioRxiv 2025.01.18.633746](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.18.633746v1) • [补充资料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F01\u002F19\u002F2025.01.18.633746\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n### 3.6 基于流的方法\n\n**SE(3)-随机流匹配用于蛋白质主链生成**  \n阿维谢克·乔伊·博斯、塔拉·阿洪德-萨德格、基利安·法特拉斯、纪尧姆·于盖、贾里德·雷克托-布鲁克斯、刘成浩、安德烈·克里斯蒂安·尼卡、马克西姆·科拉布廖夫、迈克尔·布朗斯坦、亚历山大·通  \n[arXiv:2310.02391](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.02391)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=kJFIH23hXb)\n\n**利用SE(3)流匹配快速生成蛋白质主链**  \n杰森·尹、安德鲁·坎贝尔、安德鲁·Y·K·冯、迈克尔·加斯特格尔、何塞·希门尼斯-卢纳、莎拉·刘易斯、维克托·加西亚·萨托拉斯、巴斯蒂安·S·维尔林、雷吉娜·巴尔齐莱、汤米·雅科拉、弗兰克·诺埃  \n[arXiv:2310.05297](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05297) • [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fframe-flow)\n\n**序列增强的SE(3)流匹配用于条件性蛋白质主链生成**  \n纪尧姆·于盖、詹姆斯·武科维奇、基利安·法特拉斯、埃里克·蒂博多-劳费尔、巴勃罗·莱莫斯、里亚沙特·伊斯兰、刘成浩、贾里德·雷克托-布鲁克斯、塔拉·阿洪德-萨德格、迈克尔·布朗斯坦、亚历山大·通、阿维谢克·乔伊·博斯  \n[arXiv:2405.20313](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.20313)\u002F[NeurIPS 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=paYwtPBpyZ) • [网站](https:\u002F\u002Fwww.dreamfold.ai\u002Fblog\u002Ffoldflow-2) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xgA8T9h8mm0)\n\n**利用原子流匹配设计配体结合蛋白质**  \n刘俊奇、李绍宁、施辰策、杨智、唐健  \n[arXiv:2409.12080](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.12080)\n\n**ReQFlow：修正四元数流用于高效高质量的蛋白质主链生成**  \n岳昂霄、王子冲、许鸿腾  \n[arXiv:2502.14637](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14637) • [代码](https:\u002F\u002Fgithub.com\u002FAngxiaoYue\u002FReQFlow)\n\n**Proteina：扩展基于流的蛋白质结构生成模型**  \n托马斯·格夫纳、基兰·迪迪、张佐白、丹尼·赖登巴赫、曹忠林、杰森·尹、马里奥·盖格、克里斯蒂安·达拉戈、埃米内·库丘克本利、阿拉什·瓦赫达特、卡斯滕·克莱斯  \n[ICLR 2025 口头报告](https:\u002F\u002Fopenreview.net\u002Fforum?id=TVQLu34bdw) • [代码](https:\u002F\u002Fgithub.com\u002FNVIDIA-Digital-Bio\u002Fproteina\u002F) • [网站](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fproteina\u002F) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Y2dRj9_ZEHw)\n\n**ProtComposer：基于3D椭球的组合式蛋白质结构生成**  \n汉内斯·斯塔克、景博文、托马斯·格夫纳、杰森·尹、汤米·雅科拉、阿拉什·瓦赫达特、卡斯滕·克莱斯  \n[ICLR 2025 口头报告](https:\u002F\u002Fopenreview.net\u002Fforum?id=0ctvBgKFgc) • [代码](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fprotcomposer) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=2G0d-RePc7c)\n\n**稳健可靠的从头蛋白质设计：基于流匹配的蛋白质生成模型实现了极高的成功率**  \n闫俊宇、崔子博、严文清、陈宇航、蒲孟晨、李帅、叶晟  \n[bioRxiv 2025.04.29.651154](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.29.651154v1) • [代码](https:\u002F\u002Fgithub.com\u002FJoreyYan\u002FOriginflow)\n\n**基于流匹配的柔性条件化蛋白质结构设计**  \n弗谢沃洛德·维柳加、莱夫·绍特、尼古拉斯·沃尔夫、西蒙·瓦格纳、阿内·埃洛夫松、扬·施图默、弗劳克·格雷特  \n[ICML 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=890gHX7ieS)\n\n**深度生成式蛋白质设计的挑战与指南：四个案例研究**  \n郑天元、亚历山德罗·隆迪纳、戈斯·米克勒姆、皮耶特罗·利奥  \n[FM4LS 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=FcfpwlFDUZ)\n\n**让物理学指引你的蛋白质流：拓扑感知的展开与生成**  \n约格什·维尔马、马库斯·海诺宁、维卡斯·加格  \n[arXiv:2509.25379](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2509.25379)\n\n**蒸馏式蛋白质主链生成**  \n谢立洋、张浩然、王振东、韦斯利·坦西、周明远  \n[arXiv:2510.03095](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2510.03095)\n\n**流，直而不疾：探索修正流在蛋白质设计中的设计空间**  \n陈俊华、西蒙·马蒂斯、查尔斯·哈里斯、基兰·迪迪、皮耶特罗·利奥  \n[arXiv:2510.24732](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.24732)\n\n**通过流匹配和体内成熟设计高亲和力蛋白质结合剂**  \n于启林、郭梁悦、秦夏燕、黄锡坤、田柏慧、王洪准、刘宇、郎云芝、王迪、沈周涵宇、林杰以及陈明晨  \n[预印本](https:\u002F\u002Fwww.dropbox.com\u002Fscl\u002Ffi\u002F9v6myel7uodrdsckwk5bd\u002FMain_SI1_High-Affinity-Protein-Binder-Design-via-Flow-Matching-and-In-Silico-Maturation.pdf?rlkey=ohvrohvflnyq993mq24skjm2v&e=1&st=tr7t3x3a&dl=0) • [代码](https:\u002F\u002Fgithub.com\u002FMingchenchen\u002FPPIFlow)\n\n### 3.7 基于评分\n\n**基于评分的生成模型用于设计结合肽骨架**  \n约翰·D·布姆、马修·格林尼格、皮耶特罗·索尔曼尼、皮耶特罗·利奥  \n[arXiv:2310.07051](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.07051) • [代码](https:\u002F\u002Fgithub.com\u002Fmgreenig\u002Floopgen)\n\n**提升深度生成蛋白质设计的信心**  \n郑天元、亚历山德罗·隆迪纳、皮耶特罗·利奥  \n[arXiv:2411.18568](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.18568) • [代码](https:\u002F\u002Fgithub.com\u002FECburx\u002FPROTEVAL)\n\n### 3.8 自回归\n\n**基于多尺度结构生成的蛋白质自回归建模**  \n瞿燕茹、谢承延、郑在祥、刘戈、顾全权  \n[arXiv:2602.04883](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.04883)\n\n## 4. 骨架到序列\n\n> 根据给定的主链\u002F骨架\u002F模板约束确定氨基酸序列：包括扭转角(φ & ψ)、主链角度(θ和τ)、主链二面角(φ、ψ和ω)、主链原子(Cα、N、C和O)、Cα−Cα距离、Cα−Cα、Cα−N和Cα−C的单位方向向量等（即逆折叠）。参考自[这里](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079)。此外，还包含基于能量的模型，用于恢复侧链构象（χ角或原子坐标）。\n\n### 4.0 综述\n\n**基于深度学习的给定主链蛋白质序列设计**  \n刘宇峰、刘海燕  \n[Protein Engineering, Design and Selection, 2023](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzad024\u002F7503843)\n\n**深度学习驱动的蛋白质序列设计方法的多指标比较评估**  \n于金宇、穆俊熙、魏婷、陈海峰  \n[Bioinformatics, 2024;, btae037](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtae037\u002F7585533)\n\n**可控蛋白质序列设计的生成式AI：综述**  \n朱一恒、孔子泰、吴嘉璐、刘伟泽、韩宇强、尹明泽、徐红霞、谢昌宇、侯廷军  \n[arXiv:2402.10516](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.10516)\n\n**主链条件下的蛋白质序列设计**  \n尤斯塔斯·道帕拉斯  \n[Cold Spring Harbor Perspectives in Biology (2025)](https:\u002F\u002Fcshperspectives.cshlp.org\u002Fcontent\u002Fearly\u002F2025\u002F05\u002F03\u002Fcshperspect.a041517)\n\n**通过逆折叠模型进行零样本蛋白质稳定性预测：自由能解释**  \n杰斯·弗雷尔森、马赫尔·M·卡塞姆、托内·本格森、拉斯·奥尔森、克雷斯滕·林多夫-拉森、杰斯珀·费尔金霍夫-博格、沃特·布姆斯马  \n[arXiv:2506.05596](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.05596)\n\n### 4.1 基于MLP\n\n**氨基酸的3D表示——应用于蛋白质序列比较与分类**  \n李洁和帕特里斯·科埃尔  \n[Computational and Structural Biotechnology Journal 11.18 (2014)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2001037014000270) • 2014年\n\n**利用基于片段的局部特征和基于能量的非局部特征，通过神经网络直接预测与蛋白质结构相容的序列谱**  \n李志秀、杨跃东、埃舍尔·法拉吉、詹健、周耀奇  \n[Proteins: Structure, Function, and Bioinformatics 82.10 (2014)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fprot.24620) • 代码不可用\n\n**SPIN2：使用深度神经网络从蛋白质结构预测序列谱**  \n詹姆斯·奥康奈尔、李志秀、杰克·汉森、瑞斯·赫弗南、詹姆斯·莱昂斯、库尔迪普·帕利瓦尔、阿卜杜拉·德赞吉、杨跃东、周耀奇  \n[Proteins: Structure, Function, and Bioinformatics 86.6 (2018)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fprot.25489) • 代码不可用\n\n**利用深度学习神经网络进行蛋白质计算设计**  \n王静雪、曹华莉、张志恒和齐义飞  \n[Scientific Reports 8.1 (2018)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-018-24760-x.pdf) • 代码不可用\n\n**利用蛋白质自身接触进行配体感知的蛋白质序列设计**  \n乔迪·牟、本杰明·弗莱、姚春辰、尼古拉斯·波利齐  \n[NeurIPS 2022](https:\u002F\u002Fwww.dropbox.com\u002Fs\u002F98ri2f9gverljcw\u002FLigand-aware_protein_sequence_design_using_protein_self_contacts.pdf?dl=0)\n\n**SeqPredNN：一种能够生成折叠成指定三级结构的蛋白质序列的神经网络**  \n拉特甘、F·阿德里安、卡罗琳·施赖伯和休·G·帕特顿  \n[BMC Bioinformatics 24.1 (2023)](https:\u002F\u002Fbmcbioinformatics.biomedcentral.com\u002Farticles\u002F10.1186\u002Fs12859-023-05498-4) • [代码](https:\u002F\u002Fgithub.com\u002Ffalategan\u002FSeqPredNN)\n\n### 4.2 基于VAE\n\n**利用变分自编码器设计金属蛋白和新型蛋白质折叠**  \n格林纳、乔·G、刘易斯·莫法特和戴维·T·琼斯  \n[Scientific Reports 8.1 (2018)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-018-34533-1)\n\n**AlphaFold数据库去偏以实现稳健的逆折叠**  \n程坦、曹振晓、高章阳、李思远、黄宇飞、李斯坦 Z  \n[arXiv:2506.08365](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08365)\n\n**DivPro：具有直接结构恢复指导的多样化蛋白质序列设计**  \n周欣怡、沈贵宝、陈英聪、陈广勇、彭安恒  \n[Bioinformatics (2025)](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F41\u002FSupplement_1\u002Fi382\u002F8199395) • [代码](https:\u002F\u002Fgithub.com\u002Fveghen\u002FDivPro)\n\n### 4.3 基于LSTM\n\n**通过残基间距离图的图像描述改进蛋白质序列谱预测**  \n陈盛、孙哲、林丽华、刘子峰、刘勋、崇玉田、陆宇彤、赵慧英和杨跃东  \n[Journal of Chemical Information and Modeling 60.1 (2019)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.9b00438) • [SPROF](https:\u002F\u002Fgithub.com\u002Fbiomed-AI\u002FSPROF)\n\n**蛋白质—蛋白质相互作用的深度学习蛋白质序列设计**  \n瑟尔利巴耶娃、劳莉娅和伊娃-玛丽亚·施特劳赫  \n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.28.478262v1)\u002F[Bioinformatics, 2022;, btac733](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtac733\u002F6827796) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.28.478262v1.supplementary-material) • [代码](https:\u002F\u002Fgithub.com\u002Fstrauchlab\u002FiNNterfaceDesign)\n\n### 4.4 基于卷积神经网络\n\n**基于结构的蛋白质工程深度学习框架**\n拉加夫·什罗夫、奥斯汀·W·科尔、巴雷特·R·莫罗、丹尼尔·J·迪亚斯、艾萨克·多内尔、吉米·戈利哈尔、安德鲁·D·埃林顿、罗斯·泰耶\n[bioRxiv（2019）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F833905v1)\n\n**ProDCoNN：利用卷积神经网络进行蛋白质设计**\n张源、陈洋、王晨然、罗春潮、刘秀文、吴伟、张金峰\n[《蛋白质：结构、功能与生物信息学》88.7期（2020）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fprot.25868) • 代码不可用\n\n**基于学习势能的蛋白质序列设计**\n纳姆拉塔·阿南德、拉斐尔·江口、伊林潘·I·马修斯、卡拉·P·佩雷斯、亚历山大·德里、罗斯·B·奥特曼及黄博思\n[《自然通讯》（2022）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-28313-9) • [代码](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fprotein_seq_des)\n\n**TIMED-Design：利用卷积神经网络实现灵活且易用的蛋白质序列设计**\n莱昂纳多·V·卡斯托里纳、苏莱曼·梅尔特·于纳尔、卡尔蒂克·苏布尔、克里斯托弗·W·伍德\n[《蛋白质工程、设计与选择》，2024年](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzae002\u002F7591701) • [代码](https:\u002F\u002Fgithub.com\u002Fwells-wood-research\u002Ftimed-design) • [网站](https:\u002F\u002Fpragmaticproteindesign.bio.ed.ac.uk\u002Ftimed\u002F)\n\n**基于生物传感器和机器学习的石蒜科酶工程改造**\n西蒙·德厄尔斯尼茨、丹尼尔·J·迪亚斯、金万泰、丹尼尔·J·阿科斯塔、泰勒·L·丹杰菲尔德、梅森·W·谢赫特、马修·B·米纳斯、詹姆斯·R·霍华德、汉娜·多、詹姆斯·M·洛伊、哈尔·S·阿尔珀、Y·杰西·张及安德鲁·D·埃林顿\n[《自然通讯》15.1期（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-46356-y) • [代码1](https:\u002F\u002Fgithub.com\u002Fdanny305\u002FMutComputeX)、[代码2](https:\u002F\u002Fgithub.com\u002Fsimonsnitz\u002Fplotting)\n\n**OPUS-Design：基于主链结构，结合3D卷积神经网络与蛋白质语言模型进行蛋白质序列设计**\n许刚、杨雨露、张一秋、王庆华、马建鹏\n[bioRxiv 2024.08.20.608889](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.20.608889v2) • [代码](https:\u002F\u002Fgithub.com\u002FOPUS-MaLab\u002Fopus_design)\n\n**ProBID-Net：用于蛋白质—蛋白质结合界面设计的深度学习模型**\n陈志航、季梦琳、齐洁娜、张哲、张向英、高浩天、王浩杰、王仁晓、齐一飞\n[《化学科学》（2024）](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002FContent\u002FArticleLanding\u002F2024\u002FSC\u002FD4SC02233E) • [代码](https:\u002F\u002Fgithub.com\u002FComputArtCMCG\u002FProBID-NET)\n\n### 4.5 基于图神经网络\n\n**利用几何向量感知器从蛋白质结构中学习**\n景博文、施特凡·艾斯曼、帕特里夏·苏里亚纳、拉斐尔·J.L. 汤申德、罗恩·德罗尔\n[arXiv预印本 arXiv:2009.01411（2020）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01411)\u002F[ICLR（2021）](https:\u002F\u002Fopenreview.net\u002Fforum?id=1YLJDvSx6J4) • [GVP](https:\u002F\u002Fgithub.com\u002Fdrorlab\u002Fgvp-pytorch)\n\n**利用深度图神经网络实现快速灵活的蛋白质设计**\n阿列克谢·斯特罗卡奇、大卫·贝塞拉、卡莱斯·科尔比-韦尔赫、阿尔伯特·佩雷斯-里瓦、菲利普·M·金\n[《细胞系统》（2020）](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2405471220303276) • [代码：ProteinSolver](https:\u002F\u002Fgitlab.com\u002Fostrokach\u002Fproteinsolver)\n\n**拟态神经网络：蛋白质设计与折叠的统一框架**\n摩西·埃利亚索夫、图·博森、埃尔达德·哈伯、陈·凯萨尔、埃兰·特赖斯特\n[arXiv:2102.03881](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.03881)\u002F[Front. Bioinform. 2:715006](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffbinf.2022.715006\u002Ffull)\n\n**TERMinator：基于三级重复基序的结构导向型神经网络蛋白质设计框架**\n亚历克斯·J·李、维克拉姆·桑达尔、格沃格·格里戈里扬、艾米·E·基廷\n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_TERMinator:_A_Neural_Framework.pdf) \u002F [arXiv（2022）](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2204.13048.pdf)\n\n**一种基于神经网络的模型，用于根据蛋白质主链结构预测氨基酸概率**\n南美新太郎、佐久间耕也、小林直也\n尚未发表（2021年6月）• [GCNdesgin](https:\u002F\u002Fgithub.com\u002FShintaroMinami\u002FGCNdesign)\n\n**XENet：利用新型图卷积加速量子计算机上的蛋白质设计进程**\n杰克·B·麦圭尔、达尼埃莱·格拉塔罗拉、维克拉姆·希普尔·穆利根、尤金·克利什科、汉斯·梅洛\n[《PLoS计算生物学》17.9期（2021）](https:\u002F\u002Fpdfs.semanticscholar.org\u002F23bc\u002F58424378d15fda91e9d427fb553728c38b8a.pdf)\n\n**AlphaDesign：一种基于图的蛋白质设计方法，并在AlphaFoldDB上进行基准测试**\n高、张阳、程坦和斯坦·李\n[arXiv预印本 arXiv:2202.01079（2022）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01079) • [代码](https:\u002F\u002Fgithub.com\u002Fjonathanking\u002Fsidechainnet)\n\n**具有全局上下文的生成式从头蛋白质设计**\n程坦、张耀高、夏俊和斯坦·Z·李\n[arXiv](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.10673) • 2022年4月 • [代码](https:\u002F\u002Fgithub.com\u002Fchengtan9907\u002Fgca-generative-protein-design)\n\n**利用序列迁移进行掩码反折叠以实现蛋白质表示学习**\n凯文·K·杨、休·叶、尼科洛·扎尼凯利\n[bioRxiv 2022.05.25.493516](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.05.25.493516v1)\u002F[《蛋白质工程、设计与选择》36期（2023）](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Farticle\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzad015\u002F7330543) • [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fprotein-sequence-models) • [模型](https:\u002F\u002Fdoi.org\u002F10.1234\u002Fmifst)\n\n**利用ProteinMPNN实现稳健的基于深度学习的蛋白质序列设计**\n尤斯塔斯·道帕拉斯、伊万·阿尼申科、纳撒尼尔·贝内特、白华、罗伯特·J·拉戈特、卢卡斯·F·米勒斯、巴西勒·I·M·威基、阿莱克西斯·库尔贝、罗伯特·J·德哈斯、内维尔·贝塞尔、菲利普·J·Y·梁、蒂莫西·F·哈迪、萨姆·佩洛克、道格·提舍尔、弗雷德里克·陈、布赖恩·科普尼克、汉娜·阮、亚历克斯·康、巴努马蒂·桑卡兰、阿西姆·贝拉、尼尔·P·金、大卫·贝克\n[bioRxiv 2022.06.03.494563](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.03.494563v1.article-metrics)\u002F[《科学》（2022）](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.add2187) • [代码](https:\u002F\u002Fgithub.com\u002Fdauparas\u002FProteinMPNN) • [Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fsimonduerr\u002FProteinMPNN) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=aVQQuoToTJA) • [Colab（in_jax）](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fv1.1.0\u002Fmpnn\u002Fexamples\u002Fproteinmpnn_in_jax.ipynb) • [ProteinMPNN+ESMFold](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fsimonduerr\u002FProteinMPNNESM\u002Fblob\u002Fmain\u002FREADME.md)\n\n**通过层次化等变精炼进行抗体—抗原对接与设计**\n金、温功、雷吉娜·巴尔齐莱以及汤米·雅各拉\n[arXiv预印本 arXiv:2207.06616（2022）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.06616)\u002F[国际机器学习大会。PMLR，2022年](https:\u002F\u002Ficml.cc\u002Fvirtual\u002F2022\u002Fposter\u002F16625) • [代码](https:\u002F\u002Fgithub.com\u002Fwengong-jin\u002Fabdockgen) • [海报](https:\u002F\u002Ficml.cc\u002Fmedia\u002FPosterPDFs\u002FICML%202022\u002Fb7f520a55897b35e6eb462bbf80915c6.png)\n\n**基于骨架原子坐标和三级基序的结构导向蛋白质设计的神经网络衍生Potts模型**\nAlex J. Li、Mindren Lu、Israel Desta、Vikram Sundar、Gevorg Grigoryan 和 Amy E. Keating\n[bioRxiv 2022.08.02.501736](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.02.501736v1.full.pdf)\u002F[Protein Science, 32(2)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.4554)\n\n**作为基于能量模型的SE(3)等变图注意力网络用于蛋白质侧链构象**\nDeqin Liu、Sheng Chen、Shuangjia Zheng、Sen Zhang、Yuedong Yang\n[bioRxiv 2022.09.05.506704](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.05.506704v1) • [代码](https:\u002F\u002Fgithub.com\u002Fbiomed-AI\u002FGraphEBM)\n\n**PiFold：迈向高效且有效的蛋白质逆折叠**\nZhangyang Gao、Cheng Tan、Stan Z. Li\n[arXiv:2209.12643v2](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.12643v3)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fpdf?id=oMsN9TYwJ0j) • [github](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FPiFold)\n\n**基于熵的迭代优化的蛋白质序列设计**\nXinyi Zhou、Guangyong Chen、Junjie Ye、Ercheng Wang、Jun Zhang、Cong Mao、Zhanwei Li、Jianye Hao、Xingxu Huang、Jin Tang、Pheng Ann Heng\n[bioRxiv 2023.02.04.527099](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.04.527099v1)\n\n**轻量级对比学习的蛋白质结构-序列转换**\nJiangbin Zheng、Ge Wang、Yufei Huang、Bozhen Hu、Siyuan Li、Cheng Tan、Xinwen Fan、Stan Z. Li\n[arXiv:2303.11783](https:\u002F\u002Farxiv.org\u002Fabs\u002F2303.11783)\n\n**利用几何向量场网络建模蛋白质结构**\nWeian Mao、Muzhi Zhu、Hao Chen、Chunhua Shen\n[bioRxiv 2023.05.07.539736](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.07.539736v1)\n\n**知识设计：通过知识精炼突破蛋白质设计的极限**\nZhangyang Gao、Cheng Tan、Stan Z. Li\n[arXiv:2305.15151](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.15151)\u002F[ICLR](https:\u002F\u002Fopenreview.net\u002Fforum?id=mpqMVWgqjn) • [代码](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FProteinInvBench)\n\n**SPIN-CGNN：基于接触图构建与接触图神经网络的固定骨架蛋白质设计改进**\nXing Zhang、Hongmei Yin、Fei Ling、Jian Zhan、Yaoqi Zhou\n[bioRxiv 2023.07.07.548080](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.07.548080v1)\u002F[PLOS Computational Biology](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1011330) • [代码](https:\u002F\u002Fgithub.com\u002FEricZhangSCUT\u002FSPIN-CGNN)\n\n**ZetaDesign：一种端到端的深度学习方法，用于蛋白质序列设计和侧链填充**\nJunyu Yan 等人\n[Briefings in Bioinformatics, 2023](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fbib\u002Fbbad257\u002F7222295) • [代码](https:\u002F\u002Fgithub.com\u002FJoreyYan\u002Fzetadesign)\n\n**来自等变图变换器的上下文蛋白编码**\nSai Pooja Mahajan、Jeffrey A. Ruffolo、Jeffrey J. Gray\n[bioRxiv 2023.07.15.549154](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.15.549154v1) • [代码](https:\u002F\u002Fgithub.com\u002FGrayLab\u002FMaskedProteinEnT)\n\n**使用机器学习工具ProteinMPNN稳健设计Rsp5 E3连接酶的有效别构激活剂**\nHsi-Wen Kao、Wei-Lin Lu、Meng-Ru Ho、Yu-Fong Lin、Yun-Jung Hsieh、Tzu-Ping Ko、Shang-Te Danny Hsu 和 Kuen-Phon Wu\n[ACS Synthetic Biology (2023)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.3c00042) • [补充材料](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fsuppl\u002F10.1021\u002Facssynbio.3c00042\u002Fsuppl_file\u002Fsb3c00042_si_001.pdf)\n\n**使用ProteinMPNN快速自动化设计双组分蛋白质纳米材料**\nRobbert J. de Haas、Natalie Brunette、Alex Goodson、Justas Dauparas、Sue Y. Yi、Erin C. Yang、Quinton Dowling、Hannah Nguyen、Alex Kang、Asim K. Bera、Banumathi Sankaran、Renko de Vries、David Baker、Neil P. King\n[bioRxiv 2023.08.04.551935](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.04.551935v1)\u002F[美国国家科学院院刊 121.(13)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2314646121) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F08\u002F04\u002F2023.08.04.551935\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [数据](https:\u002F\u002Fzenodo.org\u002Frecords\u002F8278877)\n\n**理性种子引导的计算蛋白质设计**\nKatherine I. Albanese、Rokas Petrenas、Fabio Pirro、Elise A. Naudin、Ufuk Borucu、William M. Dawson、D. Arne Scott、Graham J. Leggett、Orion D. Weiner、Thomas A. A. Oliver、Derek N. Woolfson\n[bioRxiv 2023.08.25.554789](https:\u002F\u002Fwww.biorxiv.orxg\u002Fcontent\u002F10.1101\u002F2023.08.25.554789v1) • [代码](https:\u002F\u002Fgithub.com\u002Fpolizzilab\u002Fdesign_tools)\n\n**序列特异性DNA结合蛋白的计算设计**\nCameron J Glasscock、Robert Pecoraro、Ryan McHugh、Lindsey A. Doyle、Wei Chen、Olivier Boivin、Beau Lonnquist、Emily Na、Yuliya Politanska、Hugh K Haddox、David Cox、Christoffer Norn、Brian Coventry、Inna Goreshnik、Dionne Vafeados、Gyu Rie Lee、Raluca Gordan、Barry L Stoddard、Frank DiMaio、David Baker\n[bioRxiv 2023.09.20.558720](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.20.558720v1)\u002F[Nat Struct Mol Biol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41594-025-01669-4) • [代码](https:\u002F\u002Fgithub.com\u002Fcjg263\u002Fdbp_design) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F09\u002F21\u002F2023.09.20.558720\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**利用ProteinMPNN提升蛋白质表达、稳定性和功能**\nKiera H. Sumida、Reyes Núñez Franco、Indrek Kalvet、Samuel J. Pellock、Basile I. M. Wicky、Lukas F. Milles、Justas Dauparas、Jue Wang、Yakov Kipnis、Noel Jameson、Alex Kang、Joshmyn De La Cruz、Banumathi Sankaran、Asim K Bera、Gonzalo Jimenez Oses、David Baker\n[bioRxiv 2023.10.03.560713](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.03.560713v1)\u002F[J. Am. Chem. Soc. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Fjacs.3c10941) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F10\u002F03\u002F2023.10.03.560713\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于机器学习算法和蛋白质片段化协议的设计蛋白笼系列**\nKyle Meador、Roger Castells-Graells、Roman Aguirre、Michael R. Sawaya、Mark A. Arbing、Trent Sherman、Chethaka Senarathne、Todd O. Yeates\n[bioRxiv 2023.10.09.561468](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.09.561468v1) • [代码](https:\u002F\u002Fgithub.com\u002Fkylemeador\u002Fsymdesign) • [colab](https:\u002F\u002Fbit.ly\u002Fsymdesign-colab)\n\n**基于序列profile的超快速形状识别蛋白质设计师**\n匿名\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=s4mPCrSNUZ)\n\n**利用深度学习进行抗体序列设计的逆折叠**\nFrédéric A. Dreyer、Daniel Cutting、Constantin Schneider、Henry Kenlay、Charlotte M. Deane\n[arXiv:2310.19513](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.19513)\n\n**别构可切换蛋白质组装体的从头设计**\nArvind Pillai、Abbas Idris、Annika Philomin、Connor Weidle、Rebecca Skotheim、Philip J. Y. Leung、Adam Broerman、Cullen Demakis、Andrew J. Borst、Florian Praetorius、David Baker\n[bioRxiv 2023.11.01.565167](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.01.565167v1)\u002F[Nature (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-07813-2) • [代码](https:\u002F\u002Fgithub.com\u002Farvind-pillai\u002Fswitchable_rings) • [数据](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F11\u002F02\u002F2023.11.01.565167\u002FDC1\u002Fembed\u002Fmedia-1.zip)\n\n**ProRefiner：基于熵的精炼策略，用于具有全局图注意力机制的反向蛋白质折叠**\nXinyi Zhou、Guangyong Chen、Junjie Ye、Ercheng Wang、Jun Zhang、Cong Mao、Zhanwei Li、Jianye Hao、Xingxu Huang、Jin Tang、Pheng Ann Heng\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-43166-6) • [补充材料](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41467-023-43166-6\u002FMediaObjects\u002F41467_2023_43166_MOESM1_ESM.pdf) • [代码](https:\u002F\u002Fzenodo.org\u002Frecords\u002F10030882)\n\n**工程化免疫原以诱导针对保守冠状病毒表位的抗体**\nA. Brenda Kapingidza、Daniel J. Marston、Caitlin Harris、Daniel Wrapp、Kaitlyn Winters、Dieter Mielke、Lu Xiaozhi、Qi Yin、Andrew Foulger、Rob Parks、Maggie Barr、Amanda Newman、Alexandra Schäfer、Amanda Eaton、Justine Mae Flores、Austin Harner、Nicholas J. Catanzaro Jr.、Michael L. Mallory、Melissa D. Mattocks、Christopher Beverly、Brianna Rhodes、Katayoun Mansouri、Elizabeth Van Itallie、Pranay Vure、Brooke Dunn、Taylor Keyes、Sherry Stanfield-Oakley、Christopher W. Woods、Elizabeth A. Petzold、Emmanuel B. Walter、Kevin Wiehe、Robert J. Edwards、David C. Montefiori、Guido Ferrari、Ralph Baric、Derek W. Cain、Kevin O. Saunders、Barton F. Haynes 和 Mihai L. Azoitei\n[Nat Commun 14, 7897 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-43638-9) • [代码](https:\u002F\u002Fgithub.com\u002FAzoiteiLab\u002FS2-scaffold-scripts)\n\n**DNDesign：通过去噪增强对蛋白质逆折叠模型物理理解的方法**\nYouhan Lee、Jaehoon Kim\n[bioRxiv 2023.12.05.570298](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.05.570298v1)\n\n**利用生成式逆折叠技术设计出经体外验证的针对多种治疗性抗原的抗体**\nAmir Shanehsazzadeh、Julian Alverio、George Kasun、Simon Levine、Jibran A Khan、Chelsea Chung、Nicolas Diaz、Breanna K Luton、Ysis Tarter、Cailen McCloskey、Katherine B Bateman、Hayley Carter、Dalton Chapman、Rebecca Consbruck、Alec Jaeger、Christa Kohnert、Gaelin Kopec-Belliveau、John M Sutton、Zheyuan Guo、Gustavo Canales、Kai Ejan、Emily Marsh、Alyssa Ruelos、Rylee Ripley、Brooke Stoddard、Rodante Caguiat、Kyra Chapman、Matthew Saunders、Jared Sharp、Douglas Ganini da Silva、Audree Feltner、Jake Ripley、Megan E Bryant、Danni Castillo、Joshua Meier、Christian M Stegmann、Katherine Moran、Christine Lemke、Shaheed Abdulhaqq、Lillian R Klug、Sharrol Bachas\n[bioRxiv 2023.12.08.570889](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.08.570889v1)\n\n**SPDesign：基于结构序列 profile 的超快速形状识别蛋白质序列设计工具**\nHui Wang、Dong Liu、Kailong Zhao、Yajun Wang、Guijun Zhang\n[bioRxiv 2023.12.14.571651](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.14.571651v1)\u002F[Briefings in Bioinformatics 25.3 (2024): bbae146](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F3\u002Fbbae146\u002F7642672) • [网站](http:\u002F\u002Fzhanglab-bioinf.com\u002FSPDesign\u002F)\n\n**利用形状互补假环设计多样化的低分子量结合物和传感器**\nLinna An、Meerit Said、Long Tran、Sagardip Majumder、Inna Goreshnik、Gyu Rie Lee、David Juergens、Justas Dauparas、Ivan Anishchenko、Brian Coventry、Asim K Bera、Alex Kang、Paul M Levine、Valentina Alvarez、Arvindd Pillai、Christoffer Norn、David Feldman、Dmitri Zorine、Derrick R Hicks、Xinting Li、Mariana Garcia Sanchez、Dionne K Vafeados、Patrick J Salveson、Anastassia A Vorobieva、David Baker\n[bioRxiv 2023.12.20.572602](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.20.572602v1)\u002F[Science385,276-282(2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adn3780) • [代码1](https:\u002F\u002Fgithub.com\u002FLAnAlchemist\u002FPseudocycle_small_molecule_binder)、[代码2](https:\u002F\u002Fgithub.com\u002Fiamlongtran\u002Fpseudocycle_paper)、[代码3](https:\u002F\u002Fgithub.com\u002Ffeldman4\u002Fngs_app)\n\n**基于配体MPNN的原子上下文条件蛋白序列设计**\nJustas Dauparas、Gyu Rie Lee、Robert Pecoraro、Linna An、Ivan Anishchenko、Cameron Glasscock、D. Baker\n[bioRxiv 2023.12.22.573103](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.22.573103v1)\u002F[Nat Methods (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-025-02626-1) • [代码](https:\u002F\u002Fgithub.com\u002Fdauparas\u002FLigandMPNN)\n\n**基于结构条件的掩码语言模型在蛋白质序列设计中的应用超越了天然序列空间**\nDeniz Akpinaroglu、Kosuke Seki、Amy Guo、Eleanor Zhu、Mark J. S. Kelly、Tanja Kortemme\n[bioRxiv 2023.12.15.571823](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.15.571823v1) • [代码](https:\u002F\u002Fgithub.com\u002Fdakpinaroglu\u002FFrame2seq)\n\n**ProteinMPNN 恢复跨膜 β-桶蛋白的复杂序列特性**\nMarissa D Dolorfino、Anastassia A Vorobieva\n[bioRxiv 2024.01.16.575764](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.01.16.575764v1) • [代码](https:\u002F\u002Fgithub.com\u002Fmarissadolorfino2024\u002FProteinMPNN-TMB-Design.git)\n\n**DIProT：基于深度学习的交互式工具包，用于高效且有效的蛋白质设计**\nHe, Jieling、Wenxu Wu 和 Xiaowo Wang\n[合成与系统生物技术 (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2405805X24000115)\n\n**利用标准化蛋白质模块构建可扩展纳米材料蓝图**\nTimothy F. Huddy、Yang Hsia、Ryan D. Kibler、Jinwei Xu、Neville Bethel、Deepesh Nagarajan、Rachel Redler、Philip J. Y. Leung、Connor Weidle、Alexis Courbet、Erin C. Yang、Asim K. Bera、Nicolas Coudray、S. John Calise、Fatima A. Davila-Hernandez、Hannah L. Han、Kenneth D. Carr、Zhe Li、Ryan McHugh、Gabriella Reggiano、Alex Kang、Banumathi Sankaran、Miles S. Dickinson、Brian Coventry、T. J. Brunette、Yulai Liu、Justas Dauparas、Andrew J. Borst、Damian Ekiert、Justin M. Kollman、Gira Bhabha 和 David Baker\n[Nature (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-07188-4) • [RosettaScripts](https:\u002F\u002Fgithub.com\u002Ftfhuddy\u002F2023-manuscript-materials)\n\n**基于几何深度学习的全原子蛋白质序列设计**\nJiale Liu、Zheng Guo、Changsheng Zhang、Luhua Lai\n[bioRxiv 2024.03.18.585651](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.18.585651v1)\u002F[Angew. Chem. Int. Ed. 2024](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fanie.202411461) • [代码](https:\u002F\u002Fgithub.com\u002FPKUliujl\u002FGesSeqBuilder)\n\n**Graphormer 监督式从头蛋白质设计方法及功能验证**\n穆俊熙、李正欣、张博、张琪、贾姆谢德·伊克巴尔、阿卜杜勒·瓦杜德、魏婷、冯燕、陈海峰\n[Briefings in Bioinformatics 25.3 (2024): bbae135](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F3\u002Fbbae135\u002F7638270) • [代码](https:\u002F\u002Fgithub.com\u002Fdecodermu\u002FGPD)\n\n**达米埃塔服务器：综合性蛋白质设计工具包**\n伊万·格林、卡捷琳娜·马克西门科、托比亚斯·沃特韦因、穆罕默德·埃尔加马西\n[Nucleic Acids Research, 2024;, gkae297](https:\u002F\u002Facademic.oup.com\u002Fnar\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fnar\u002Fgkae297\u002F7658041) • [网站](https:\u002F\u002Fdamietta.de\u002F) • 基于 ProteinMPNN • [新闻](https:\u002F\u002Fcbirt.net\u002Fprotein-design-made-easy-with-damietta-server-a-comprehensive-toolkit\u002F)、[新闻2](https:\u002F\u002Fwww.innovations-report.com\u002Flife-sciences\u002Ftoolkit-makes-protein-design-faster-and-more-accessible\u002F)\n\n**基于结构的深度学习方法在T细胞受体设计中的潜力探索**\n赫尔德·V·里贝罗-菲略、加布里埃尔·E·哈拉、若昂·V·S·格拉、梅丽莎·张、纳撒尼尔·R·费尔宾格、若泽·G·C·佩雷拉、布莱恩·G·皮尔斯、保罗·S·洛佩斯-德-奥利维拉\n[bioRxiv 2024.04.19.590222](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.19.590222v1) • [代码](https:\u002F\u002Fgithub.com\u002FLBC-LNBio\u002FESMIFDesign)、[代码2](https:\u002F\u002Fgithub.com\u002Fpiercelab\u002Ftcrmodel2\u002F)\n\n**SurfPro：基于连续表面的功能性蛋白质设计**\n宋振乔、黄廷林、李磊、金文功\n[arXiv:2405.06693](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.06693) • 基于 ProteinMPNN\n\n**基于肌红蛋白的卡宾转移酶用于单萜衍生物化的计算设计**\n孙一洋、唐义年、周静、郭炳辰、袁飞燕、姚波、余阳、李春\n[Biochemical and Biophysical Research Communications (2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0006291X2400696X) • [代码](https:\u002F\u002Fgithub.com\u002Fyangyu1-github\u002FMbDesignMPNN) • 基于 LigandMPNN\n\n**UniIF：统一分子逆折叠**\n高章阳、王珏、谭成、吴立荣、黄宇飞、李思远、叶志锐、李斯坦 Z.\n[arXiv:2405.18968](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.18968)\n\n**将MHC I类抗原呈递可见性目标整合到 ProteinMPNN 蛋白质设计流程中**\n汉斯-克里斯托夫·加瑟、迭戈·A·奥亚尔苏恩、哈维尔·安东尼奥·阿尔法罗、阿吉塔·拉詹\n[bioRxiv 2024.06.04.597365](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.04.597365v1)\n\n**自上而下的设计方法用于开发靶向雄激素受体的肽类PROTAC药物，用于治疗雄激素性脱发**\n马博文、刘东华、王哲、张迪泽、简艳琳、张坤、周天阳、高艺博、范义增、马健、高扬、陈宇乐、陈思、刘静、李翔以及李磊\n[Journal of Medicinal Chemistry (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jmedchem.4c00828)\n\n**无需额外训练或数据即可提升逆折叠模型在蛋白质稳定性预测方面的性能**\n奥利弗·达顿、桑德罗·博塔罗、米凯莱·英韦尔尼齐、伊什特万·雷德尔、阿尔伯特·钟、卡洛·菲西卡罗、法比奥·艾罗尔迪、斯特凡诺·鲁斯凯塔、路易·亨德森、本杰明·MJ·欧文斯、帕特里克·福尔奇、卡米尔·塔米奥拉\n[bioRxiv 2024.06.15.599145](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.15.599145v1) • 基于 ProteinMPNN\u002FESMIF\n\n**基于核函数的条件型生物序列模型评估**\n皮埃尔·格拉瑟、施特法妮·保罗、阿莉萨·M·胡默、夏洛特·迪恩、黛博拉·苏珊·马克斯、艾伦·纳兹瓦德·阿敏\n[第41届国际机器学习大会论文集，PMLR 235:15678–15705, 2024](https:\u002F\u002Fproceedings.mlr.press\u002Fv235\u002Fglaser24a.html) • 基于 ProteinMPNN\n\n**内在无序区域结合蛋白的设计**\n吴可嘉、江翰伦、德里克·R·希克斯、刘凯旋、埃丁·穆拉特沙皮奇、特蕾莎·A·拉梅洛特、刘悦轩、克里·麦克纳利、塞巴斯蒂安·肯尼、安德烈·米胡特、阿米特·高尔、布莱恩·科文特里、陈伟、阿西姆·K·贝拉、亚历克斯·康、斯泰西·格尔本、米拉·雅兰·兰布、阿纳丽萨·默里、李欣婷、麦迪逊·A·肯尼迪、杨伟、宋子豪、古德伦·肖伯、斯图尔特·M·布赖利、约翰·奥尼尔、迈克尔·H·盖尔布、加埃塔诺·T·蒙特利奥内、埃马纽埃尔·德里维里、大卫·贝克\n[bioRxiv 2024.07.15.603480](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.15.603480v3)\u002F[Science389,eadr8063(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adr8063)\n\n**深度学习指导下的动态蛋白质设计**\n艾米·B·郭、代尼兹·阿克皮纳罗格鲁、马克·J.S.凯利、坦雅·科尔特梅\n[bioRxiv 2024.07.17.603962](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.17.603962v1)\u002F[Science388,eadr7094(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adr7094) • [代码](https:\u002F\u002Fgithub.com\u002Famyguo1997\u002Fdynamic_protein_design) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F19\u002F2024.07.17.603962\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**CodonMPNN用于生物体特异性和密码子优化的逆折叠**\n汉内斯·斯塔克、乌梅什·帕迪亚、朱莉娅·巴拉、卡梅隆·迪奥、乔治·丘奇\n[arXiv:2409.17265](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.17265) • 基于 ProteinMPNN • [代码](https:\u002F\u002Fgithub.com\u002FHannesStark\u002FCodonMPNN)\n\n**基于结构的深度学习方法在T细胞受体设计中的潜力探索**\n赫尔德·V·里贝罗-菲略、加布里埃尔·E·哈拉、若昂·V·S·格拉、梅丽莎·张、纳撒尼尔·R·费尔宾格、若泽·G·C·佩雷拉、布莱恩·G·皮尔斯、保罗·S·洛佩斯-德-奥利维拉\n[PLoS Comput Biol 20(9)](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1012489) • 基于 ProteinMPNN • 基于 ESM\n\n**ProteusAI：一个开源且用户友好的平台，用于机器学习指导下的蛋白质设计与工程**\n乔纳森·芬克、劳拉·马查多、塞缪尔·A·布拉德利、玛尔塔·纳皮奥尔科夫斯卡、罗德里戈·加列戈斯-德克斯特、柳博芙·帕什科娃、尼克拉斯·G·马德森、亨利·韦贝尔、帕特里克·维克托·法纽夫、蒂莫西·P·詹金斯、卡洛斯·G·阿塞韦多-罗查 Sr\n[bioRxiv 2024.10.01.616114](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.01.616114v1) • 基于 ProteinMPNN • 基于 ESM\n\n**通过多样性正则化的直接偏好优化改进用于肽设计的逆折叠**\n瑞安·帕克、达伦·J·许、C·布莱恩·罗兰、玛丽亚·科尔舒诺娃、陈·特斯勒、希耶·曼诺尔、奥利维亚·菲斯曼、布鲁诺·特伦蒂尼\n[arXiv:2410.19471](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.19471)\n\n**可开发治疗性抗体的计算设计：高效遍历结合物景观并挽救逃逸突变**\n弗雷德里克·A·德雷耶、康斯坦丁·施奈德、亚历山大·科瓦尔楚克、丹尼尔·卡ティング、马修·J·伯恩、丹尼尔·A·尼斯利、牛顿·瓦霍梅、亨利·肯莱、克莱尔·马克斯、大卫·埃林顿、理查德·J·吉尔迪亚、大卫·达默尔、佩德罗·蒂泽伊、维拉万·奔乔布波尔、约翰·F·达比、伊娃·德鲁利特、丹尼尔·L·赫迪斯、萨钦·苏拉德、道格拉斯·E·V·皮雷斯、夏洛特·M·迪恩\n[bioRxiv 2024.10.03.616038](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.03.616038v1) • [代码](https:\u002F\u002Fgithub.com\u002FExscientia\u002Fab-characterisation) • 基于 AbMPNN\n\n**BC-Design：一种生物化学感知的逆向蛋白质设计框架**\n唐湘如、叶新武、吴芳、刘怡梦、安娜·苏、安东尼娅·帕内斯库、关璐、邵丹、徐东、马克·格斯坦\n[bioRxiv 2024.10.28.620755](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.28.620755v3)\n\n**针对G蛋白偶联受体的状态特异性肽设计**\n杨雪、李俊、王洪、胡建国、郑志、何景洲、龚焕章、李向群、张晓楠、方晓敏\n[bioRxiv 2024.11.27.625792](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.27.625792v2)\u002F[化学信息与建模杂志（2025）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c00884) • 基于ProteinMPNN\n\n**计算机指导设计具有更强VEGF抑制能力的Z结构域肽**\n卡斯滕·盖斯特、阿比贝·乌塞尼、亚历山大·卡齐米尔、里奇·库姆佩尔、延斯·迈勒、克里斯蒂娜·拉默斯、施特凡·卡尔克霍夫、格奥尔格·昆策\n[bioRxiv 2024.11.29.626075](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.29.626075v1) [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F30\u002F2024.11.29.626075\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于ProteinMPNN\n\n**HyperMPNN——一种从超嗜热菌中学习而来的设计耐热蛋白质的通用策略**\n莫里茨·埃尔特尔、菲利普·施莱格尔、马克斯·贝宁、莱昂纳德·凯瑟、延斯·迈勒、克拉拉·T·舍德尔\n[bioRxiv 2024.11.26.625397](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.26.625397v1) • [代码](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002FHyperMPNN) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F01\u002F2024.11.26.625397\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**IgDesign：利用逆折叠技术设计针对多种治疗性抗原的体外验证抗体**\n阿米尔·沙内萨扎德、朱利安·阿尔韦里奥、乔治·卡孙、西蒙·莱文、伊多·卡尔曼、吉布兰·A·汗、切尔西·钟、尼古拉斯·迪亚斯、布雷安娜·K·卢顿、伊西斯·塔特尔、凯伦·麦克洛克西、凯瑟琳·B·贝特曼、海莉·卡特、达尔顿·查普曼、丽贝卡·康斯布鲁克、亚历克·贾格尔、克里斯塔·科恩特、盖林·科佩克-贝利沃、约翰·M·萨顿、郭哲远、古斯塔沃·卡纳莱斯、凯·埃扬、艾米丽·马什、阿莉莎·鲁埃洛斯、莱莉·里普利、布鲁克·斯托达德、罗丹特·卡圭亚特、凯拉·查普曼、马修·桑德斯、贾雷德·夏普、道格拉斯·加尼尼·达席尔瓦、奥德丽·费尔特纳、杰克·里普利、梅根·E·布莱恩特、丹妮·卡斯蒂略、乔舒亚·迈尔、克里斯蒂安·M·施泰格曼、凯瑟琳·莫兰、克里斯汀·莱姆克、沙希德·阿卜杜勒哈克、莉莲·R·克鲁格、沙罗尔·巴查斯\n[bioRxiv 2023.12.08.570889](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.08.570889v1) • [代码](https:\u002F\u002Fgithub.com\u002FAbSciBio\u002Figdesign)\n\n**学习如何工程化蛋白质柔性**\n彼得·寇巴、琼·普拉纳斯-伊格莱西亚斯、季里·丹博尔斯基、季里·塞德拉尔、斯坦尼斯拉夫·马祖连科、约瑟夫·西维奇\n[arXiv:2412.18275](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.18275) • [代码](https:\u002F\u002Fgithub.com\u002FKoubaPetr\u002FFlexpert)\n\n**AI.zymes——一个用于进化酶设计的模块化平台**\n卢卡斯·P·梅尔利切克、扬尼克·诺伊曼、艾比·利尔、维维安·德焦尔吉、摩尔·德瓦尔、图多尔-斯特凡·科特、阿德里安·J·穆尔霍兰、H·阿德里安·邦泽尔\n[bioRxiv 2025.01.18.633707](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.18.633707v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F01\u002F22\u002F2025.01.18.633707\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**人工智能辅助的蛋白质设计，可快速将抗体序列转化为靶向多种肽和组蛋白修饰的胞内抗体**\n加布里埃尔·加林多、前岛大辉、雅各布·德鲁、斯科特·R·伯林厄姆、格雷琴·菲克森、森崎达也、哈利·P·费布雷、瑞安·哈斯布鲁克、赵宁、索汉·戈什、E·汉德利·梅顿、克里斯托弗·D·斯诺、布莱恩·J·盖斯、大川靖之、佐藤裕子、木村浩史、蒂莫西·J·斯塔塞维奇\n[bioRxiv 2025.02.06.636921](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.06.636921v2)\u002F[Sci. Adv.12,eadx8352(2026)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.adx8352) • [代码](https:\u002F\u002Fgithub.com\u002Fjbderoo\u002FscFv_Pmpnn_AF2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F02\u002F09\u002F2025.02.06.636921\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于ProteinMPNN\n\n**使用FAMPNN进行全原子蛋白质序列设计的侧链条件化与建模**\n理查德·W·帅、塔拉勒·维达塔拉、黄柏苏、布莱恩·L·希\n[bioRxiv 2025.02.13.637498](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.13.637498v1) • [代码](https:\u002F\u002Fgithub.com\u002Frichardshuai\u002Ffampnn)\n\n**通过结构检索实现快速准确的抗体序列设计**\n张兴义、谢坤、黄宁巧、刘伟、赵培琳、王思博、赵康飞、姜标斌\n[arXiv:2502.19395](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19395)\n\n**利用启发式优化和深度学习增强功能性蛋白质设计，用于抗炎和基因治疗应用**\n帕塔特、艾申努尔·索伊图尔克和厄兹坎·乌福克·纳尔班托格鲁\n[蛋白质：结构、功能与生物信息学（2025）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fprot.26810) • [代码](https:\u002F\u002Fgithub.com\u002Faysenursoyturk\u002FHMHO)\n\n**ProDualNet：基于蛋白质语言模型和结构模型的双靶点蛋白质序列设计方法**\n刘成、魏婷、崔晓晨、陈海峰、于章生\n[bioRxiv 2025.02.28.640919](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.28.640919v1)\u002F[生物信息学简报，2025年7月，bbaf391](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F26\u002F4\u002Fbbaf391\u002F8241296) • [代码](https:\u002F\u002Fgithub.com\u002Fchengliu97\u002FProDualNet)\n\n**CHIEF：一种基于注意力机制的集成学习框架，用于功能性蛋白质设计**\n耿子龙、王宇泽、刘婷婷、谭傲、吴硕、郭晓玲、李若谷、侯旭敏、孙坤、吴连平、崔庆华、戴林泰、马志远、李宏林、张兵\n[bioRxiv 2025.03.07.641005](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.07.641005v2) • 基于ProteinMPNN • 基于ESM-IF • 基于Frame2seq • 基于PiFold\n\n**通过直接偏好优化调整ProteinMPNN，以降低蛋白质通过MHC I类分子的免疫可见性**\n汉斯-克里斯托夫·加瑟、迭戈·A·奥亚尔松、哈维尔·阿尔法罗、阿吉塔·拉詹\n[蛋白质工程、设计与选择（2025）](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzaf003\u002F8082933) • [代码](https:\u002F\u002Fgithub.com\u002Fhcgasser\u002FCAPE_MPNN) • 基于ProteinMPNN\n\n**人工智能驱动的高效GLP-1RA从头设计，具有延长的半衰期和增强的疗效**\n魏婷、崔晓晨、林佳慧、郑卓琪、崔太英、刘成、林晓倩、朱俊杰、冉旭阳、洪晓勋、于章生、陈海峰\n[bioRxiv 2025.03.26.645438](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.26.645438v1) • 基于ProteinMPNN\n\n**一种新的ProteinMPNN解码策略，用于设计具有更低MHC I类免疫可见性的蛋白质**\n汉斯-克里斯托夫·加瑟、阿吉塔·拉詹、哈维尔·A·阿尔法罗\n[bioRxiv 2025.04.14.648837](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.14.648837v1) • 基于ProteinMPNN\n\n**通过神经选择-扩展实现药物结合蛋白的零样本设计**\n本杰明·弗莱、凯娅·斯劳、尼古拉斯·F·波利齐\n[bioRxiv 2025.04.22.649862](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.22.649862v1) • [代码](https:\u002F\u002Fgithub.com\u002Fpolizzilab\u002FLASErMPNN)\n\n**构象特异性设计：一项新的基准与算法及其在工程组成型活性 MAP 激酶中的应用**  \n雅各布·A·斯特恩、西巴·阿尔哈尔比、阿南德苏基尔蒂·桑多卢、施特凡·T·阿罗尔德、丹尼斯·德拉科尔特  \n[bioRxiv 2025.04.23.650138](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.23.650138v1) • [代码](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fcs_design) • [数据集](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fmotif_div)\n\n**AI. zymes——用于进化酶设计的模块化平台**  \n卢卡斯·P·梅尔利切克、扬尼克·诺伊曼、艾比·利尔、维维安·德焦尔吉、穆尔·M·德瓦尔、图多尔-斯特凡·科泰特、阿德里安·J·穆尔霍兰、阿德里安·邦泽尔  \n[《应用化学》国际版（2025）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fanie.202507031) • [代码](https:\u002F\u002Fgithub.com\u002Fbunzela\u002FAIzymes) • 基于 ProteinMPNN\n\n**利用蛋白质序列的深度生成模型设计重叠基因**  \n卞君宇、马克·埃克斯波西特、大卫·贝克、格奥尔格·塞利格  \n[bioRxiv 2025.05.06.652464](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.06.652464v1) • [代码](https:\u002F\u002Fgithub.com\u002Fgwbyeon\u002FOLG-design) • 基于 ProteinMPNN\n\n**从头设计含卟啉的蛋白质作为高效且具有立体选择性的催化剂**  \n侯凯鹏、黄伟、齐淼、托马斯·H·塔格韦尔、图尔基·M·阿尔图赖菲、陈宇达、张兴杰、陆磊、塞缪尔·I·曼恩、刘鹏、杨洋以及威廉·F·德格拉多  \n[《科学》388.6747（2025）](https:\u002F\u002Fwww.science.org\u002Fdoi\u002Ffull\u002F10.1126\u002Fscience.adt7268) • 基于 LigandMPNN\n\n**无需重新训练即可将 ProteinMPNN 用于抗体设计**  \n迭戈·德尔阿拉莫、拉赫尔·弗里克、达芙妮·特鲁安、乔尔·D·卡皮亚克  \n[bioRxiv 2025.05.09.653228](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.09.653228v1)\n\n**HighMPNN：一种基于图神经网络的结构约束环肽序列设计方法**  \n徐文、张成云、商天峰、毛庆义、段洪亮  \n[ChemRxiv. 2025](https:\u002F\u002Fchemrxiv.org\u002Fengage\u002Fchemrxiv\u002Farticle-details\u002F6826dcef927d1c2e661210c2)\n\n**针对新兴合成阿片类药物的动态生物传感器的计算设计**  \n艾莉森·C·莱昂纳德、蔡斯·莱内特-蒙杜、瑞秋·谢耶、塞缪尔·斯威夫特、扎卡里·T·鲍默、瑞安·德拉尼、阿尼卡·J·弗里德曼、尼古拉斯·R·罗伯逊、诺曼·塞德尔、乔丹·威尔斯、林赛·M·惠特莫尔、肖恩·R·卡特勒、迈克尔·R·希茨、伊恩·惠尔登、蒂莫西·A·怀特黑德  \n[bioRxiv 2025.05.15.654300](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.15.654300v1) • 基于 LigandMPNN\n\n**通过带原子-键建模的谐波 SDE 设计环肽**  \n周翔鑫、李明宇、肖毅、李佳涵、薛东宇、郑再祥、马建竹、顾全全  \n[arXiv:2505.21452](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21452)\n\n**针对土伦热弗朗西斯菌毒力因子的高亲和力迷你蛋白结合物的从头设计**  \n吉泽姆·戈克切-阿尔普基利奇、黄步伟、刘安迪、利瑟洛特·S.M. 克鲁克、王雅熙、维克多·阿德博米、延西·弗洛雷斯·布埃索、阿西姆·K·贝拉、康乐、斯泰西·R·格尔本、斯蒂芬·雷蒂、狄俄涅·K·瓦菲阿多斯、妮可·鲁利耶、因娜·戈列什尼克、李欣婷、大卫·贝克、约书亚·J·伍德沃德、约瑟夫·D·莫古斯、高拉夫·巴德瓦杰  \n[bioRxiv 2025.07.02.662053](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.02.662053v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F05\u002F2025.07.02.662053\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F07\u002F05\u002F2025.07.02.662053\u002FDC2\u002Fembed\u002Fmedia-2.zip) • 基于 ProteinMPNN\n\n**基于结构指导的强大且具有选择性的激酶肽底物的计算工作流程**  \n阿比布·A·耶肯、辛西娅·J·迈耶、梅丽莎·麦考伊、布鲁斯·波斯纳、肯尼思·D·韦斯托弗  \n[bioRxiv 2025.07.04.663216](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.04.663216v1) • 基于 ProteinMPNN\n\n**使用 ProteinMPNN 设计具有高度改变的结构核心和亚基界面的完全功能 AAV 病毒载体**  \n蒋子宇、西里玛尔·劳辛瓦塔纳、保罗·A·达尔比  \n[bioRxiv 2025.07.24.666527](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.24.666527v1)\n\n**双面蛋白质纳米材料的计算设计**  \n萨内拉·兰科维奇、肯尼思·D·卡尔、贾斯汀·德卡罗、丽贝卡·斯科特海姆、瑞安·D·基布勒、塞巴斯蒂安·奥尔斯、李相珉、春正浩、马蒂·R·图利、尤斯塔斯·道帕拉斯、海伦·E·艾森纳赫、马蒂亚斯·格勒格尔、康纳·魏德尔、安德鲁·J·博斯特、大卫·贝克及尼尔·P·金  \n[Nat. Mater.（2025）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41563-025-02295-7)\n\n**利用 DynamicMPNN 进行多状态蛋白质设计**  \n亚历克斯·阿布鲁丹、塞巴斯蒂安·普哈尔特·奥赫达、柴坦亚·K·乔希、马修·格林尼格、费利佩·恩格尔贝格、阿廖娜·赫梅林斯卡娅、延斯·迈勒、米歇莱·文德鲁斯科洛、图奥马斯·P·J·诺尔斯  \n[arXiv:2507.21938](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.21938) • [代码](https:\u002F\u002Fgithub.com\u002FAlex-Abrudan\u002FDynamicMPNN)\n\n**高性能皮质醇发光生物传感器的从头设计**  \n朱莉·易萱·陈、彭雪、奚成刚、李奎丽、大卫·贝克、叶宪伟·安迪  \n[J. Am. Chem. Soc](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Fjacs.5c05004)\n\n**通过扩大实验表征规模加速蛋白质设计**  \n贾森·钱、卢卡斯·F·米勒斯、巴西勒·I·M·维基、阿米尔·莫特曼、李欣婷、瑞安·D·基布勒、兰斯·斯图尔特、大卫·贝克  \n[bioRxiv 2025.08.05.668824](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.05.668824v1) • [代码](https:\u002F\u002Fgithub.com\u002Fbwicky\u002FSAPP_DMX)\n\n**人工智能驱动的超长效 GLP-1 受体激动剂的从头设计**  \n丁薇、马嘉婷、崔晓晨、林佳慧、郑卓琪、刘成、崔泰英、林晓倩、朱俊杰、冉旭阳、洪晓坤、卢克·约翰斯顿、于章生、陈海峰  \n[《先进科学》（德国巴登-符腾堡州魏恩海姆）](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202507044) • 基于 ProteinMPNN\n\n**从序列到支架：基于 AlphaFold2 预测构建块的蛋白质纳米颗粒疫苗的计算设计**  \n赛勒斯·M·哈斯、纳文·贾斯蒂、安妮·多西、乔尔·D·艾伦、丽贝卡·吉莱斯皮、杰克逊·麦戈温、伊丽莎白·M·利夫、马克斯·克里斯平、科尔·A·德福雷斯特、真守金木、尼尔·P·金  \n[bioRxiv 2025.08.20.671178](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.20.671178v1)\u002F[《美国国家科学院院刊》122.45（2025）](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2409566122) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F08\u002F20\u002F2025.08.20.671178\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**光响应性蛋白质-蛋白质相互作用的从头设计实现了蛋白质组装的可逆形成**  \n于博文、刘娇、崔占元、王楚、陈培培、王辰通、张彦哲、朱星星、张泽、李世超、潘金恒、谢明启、沈怀宗及曹龙星  \n[Nat. Chem.（2025）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41557-025-01929-2) • [代码](https:\u002F\u002Fgithub.com\u002FLongxingLab\u002FNCAA_Light_Assembly)\n\n**针对设计结构相似但序列多样的蛋白质的多目标优化**  \n良明秋叶、森胁义隆、石谷龙一郎、吉川成树  \n[bioRxiv 2025.09.13.676063](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.13.676063v1) • 基于 ProteinMPNN\n\n**基于Caliby的集合条件蛋白序列设计**  \n理查德·W·帅、陆天宇、苏邦·巴蒂、彼得·库巴、黄博思  \n[bioRxiv 2025.09.30.679633](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.30.679633v3) • [代码](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fcaliby)\n\n**从头设计的电压门控阴离子通道可抑制神经元放电**  \n周晨、李慧灿、王佳兴、钱成、熊辉、褚志林、邵启明、李轩、孙世锦、孙科、朱爱琴、王嘉伟、金雪芹、杨帆、塔梅尔·M·加马勒·埃尔丁、李波、黄静、吴坤、陆培龙  \n[Cell(2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Fabstract\u002FS0092-8674(25)01091-8)\n\n**AI引导的稳健六螺旋束蛋白疏水核心设计**  \n孟银英、唐国进、王瑞石、郑斌、刘元昊、张瀚田、郑鹏  \n[ACS Nano .5c13783](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facsnano.5c13783) • 基于ProteinMPNN\n\n**针对土拉弗朗西斯菌毒力因子的高亲和力迷你蛋白结合物的从头设计**  \n吉泽姆·戈克切-阿尔普基利奇、黄步伟、刘安迪、莉瑟洛特·S.M. 克鲁克、王雅希、维克托·阿德博米、延西·弗洛雷斯·布埃索、阿西姆·K·贝拉、亚历克斯·康、斯泰西·R·格尔本、斯蒂芬·雷蒂、狄俄尼·K·瓦菲阿多斯、妮可·鲁耶、因娜·戈列什尼克、李欣婷、大卫·贝克、乔舒亚·J·伍德沃德、约瑟夫·D·莫古斯、高拉夫·巴德瓦杰  \n[德国应用化学国际版(2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fanie.202516058) • 基于ProteinMPNN\n\n**利用设计的T细胞受体和抗体靶向肽-MHC复合物**  \n阿米尔·莫特曼、凯文·M·朱德、王楠、安娜斯塔西娅·米涅尔维娜、大卫·费尔德曼、毛里茨·A·利希滕斯坦、阿比谢伊·埃班尼泽、科林·科伦蒂、保罗·G·托马斯、K·克里斯托弗·加西亚、大卫·贝克、菲利普·布拉德利  \n[bioRxiv 2025.11.19.689381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.19.689381v1) • 基于ProteinMPNN\n\n**用于呼吸道病毒鼻腔预防的干扰素-λ的计算设计与糖工程化**  \n尹正源、杨承柱、权在赫、路易斯·费利佩·韦奇耶蒂、崔智贤、崔美罗、具根本、卢贤珠、金健度、车美英、郑贤贞、吴智恩、金浩敏  \n[Advanced Science (2025)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202506764) • 基于ProteinMPNN\n\n**小分子调控型蛋白质寡聚体的从头设计**  \n金琪涵、王雨凯、陈大川、廖晋阳、崔展远、范宇轩、曾安平、谢明琦、曹隆兴  \n[Science391,eady6017(2026)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.ady6017) • [代码](https:\u002F\u002Fgithub.com\u002FLongxingLab\u002FLigand_Induced_Oligomer)\n\n**双拓扑膜转运蛋白的从头设计**  \n陈曦、周晓峰、周家伟、谢腾宇、李亚宁、燕宇轩、黄静、陈子博、马丹、陆培龙  \n[浪涛沙预印本服务器](https:\u002F\u002Flangtaosha.org.cn\u002Findex.php\u002Flts\u002Fen\u002Fpreprint\u002Fview\u002F74)\n\n**Origin-1：针对新型表位的从头抗体设计生成式AI平台**  \n西蒙·莱文、乔纳森·爱德华·金、雅各布·斯特恩、戴维·格雷森、雷蒙德·王、尹睿、翁贝托·卢波、保利娜·库利特、瑞安·马修·布兰德、特里斯坦·贝尔坦、罗伯特·普芬格斯滕、约万·塞约维奇、切尔西·钟、布里安娜·K·卢顿、安德鲁·哈格曼、罗贝尔·海勒、埃利奥特·梅迪纳、潘卡杰·潘瓦尔、奥列克西·杜布罗夫斯基、蔡斯·拉孔布、扎赫拉·安德森、德里克·米尔德、斯科特·本杰明、乔·凯撒、约瑟夫·费伦、玛尔塔·萨里科、亚历山德拉·克什纳、阿普尔瓦·米什拉、凯·R·埃扬、艾米丽·K·马什、保罗·布林加斯、佩特萨迈·维莱恰克、凯拉·查普曼、雅各布·里普利、穆塔帕·高达、凯瑟琳·M·柯林斯、凯伦·M·麦克洛克西、杰里米亚·S·约瑟夫、赖莉·里普利、沙希德·A·阿卜杜勒哈克、奥德里·费尔特纳、迈克尔·盖林、杰弗里·戈比、杰西·亨德里克斯、丹妮尔·卡斯蒂略、肖恩·麦克莱恩、道格拉斯·加尼尼、德里克·施皮尔、詹姆斯·马特格科、埃德尔·克鲁兹·加西亚、马苏德·扎贝特-莫加达姆、约翰·M·萨顿、郭哲远、肖恩·M·韦斯特、贾纳尼·S·艾耶尔、阿米尔·沙内赫萨扎德  \n[bioRxiv 2026.01.14.699389](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.14.699389v1) • [代码](https:\u002F\u002Fgithub.com\u002FAbSciBio\u002Forigin-1)\n\n**与从头设计的受体结合物融合的纳米白蛋白结合型紫杉醇表现出更强的肿瘤靶向性和治疗效果**  \n钱元英、严伟康、徐凡、刘雅莉、陈法宝、吕悦、张子涵、顾傲、余若冰、方振、于洋、李茂兰、曹隆兴、刘英斌、何永宁  \n[bioRxiv 2026.01.28.702218](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.28.702218v1)\n\n**CyclicMPNN：稳定环状肽序列生成**  \n安德鲁·C·鲍尔斯、亚纳帕特·詹塔纳、帕丽莎·侯赛因扎德  \n[bioRxiv 2026.01.31.702993](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.31.702993v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F31\u002F2026.01.31.702993\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FParisaH-Lab\u002FCyclicMPNN)\n\n**介观结构水增强ProteinMPNN设计的泛素折叠稳定性**  \n陈璐怡、陆伟林、坦维·帕塔尼亚、楚宜萱、霍梦茹、庄伟辰、楼元超、洪太一、宫野井洋平、张嘉恩、吴坤 Phon  \n[J. Am. Chem. Soc. 2026](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacs.5c19875) • 基于ProteinMPNN\n\n\n\n### 4.6 基于GAN的方法\n\n**利用引导式条件Wasserstein生成对抗网络进行新折叠的从头蛋白设计**\n穆斯塔法·卡里米、朱绍文、曹越、沈洋\n[化学信息与建模杂志60.12(2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.0c00593) • [gcWGAN](https:\u002F\u002Fgithub.com\u002FShen-Lab\u002FgcWGAN)\n\n**HelixGAN：一种具有潜在空间搜索功能的双向生成对抗网络，用于约束条件下的生成**\n谢学志、金菲利普·M.\n[NeurIPS 2021结构生物学机器学习研讨会](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_HelixGAN:_A_bidirectional_Generative.pdf)\u002F[生物信息学，2023年，btad036](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtad036\u002F6991169) • [代码](https:\u002F\u002Fgithub.com\u002Fxxiexuezhi\u002Fhelix_gan)\n\n### 4.7 基于Transformer的方法\n\n**用于基于图的蛋白设计的生成模型**\n[约翰·英格拉汉](https:\u002F\u002Fopenreview.net\u002Fprofile?email=ingraham%40csail.mit.edu)、维卡斯·K·加格、雷吉娜·巴尔齐莱博士、汤米·雅科拉\n[NeurIPS 2019](https:\u002F\u002Fopenreview.net\u002Fforum?id=ByMEAHrgLB) • [GraphTrans](https:\u002F\u002Fgithub.com\u002Fjingraham\u002Fneurips19-graph-protein-design)\n\n**Fold2Seq：一种基于联合序列（1D）-折叠（3D）嵌入的蛋白设计生成模型**  \n曹越、达斯·帕耶尔、陈特哈马拉克尚·维吉尔、陈品宇、伊戈尔·梅尔尼克、沈洋  \n[国际机器学习会议.PMLR，2021年](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.13058)\n\n**基于深度学习和自洽性的无旋转异构体蛋白质序列设计**\n刘宇峰、张璐、王伟伦、朱敏、王晨晨、李福东、张嘉海、李厚强、陈权&刘海燕\n[自然科研（2022）](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-1209166\u002Fv1)\u002F[自然计算科学（2022）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43588-022-00273-6) • [补充材料](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs43588-022-00273-6\u002FMediaObjects\u002F43588_2022_273_MOESM1_ESM.pdf) • [评论](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs43588-022-00274-5) • [代码](https:\u002F\u002Fcodeocean.com\u002Fcapsule\u002F6949436\u002Ftree\u002Fv1)\n\n**用于学习反向蛋白质折叠的深度SE(3)等变模型**\n马修·麦克帕特隆、本·赖、徐金波\n[bioRxiv（2022）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.15.488492v1)\n\n**从数百万预测结构中学习反向折叠**\n克洛伊·许、罗伯特·维尔库伊尔、杰森·刘、林泽明、布赖恩·希、汤姆·塞尔库、亚当·莱雷、亚历山大·里夫斯\n[bioRxiv（2022）](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2022.04.10.487779) • [esm](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fesm)\n\n**借助能够理解与任何分子相互作用的新AI模型，突破蛋白质设计的界限**\nLucianoSphere\n[Towards Data Science](https:\u002F\u002Ftowardsdatascience.com\u002Fbreaking-boundaries-in-protein-design-with-a-new-ai-model-that-understands-interactions-with-any-388fd747ee40)\n\n**通过学习残基的简洁局部环境实现准确高效的蛋白质序列设计**\n黄斌、范廷文、王凯越、张海沧、于春功、聂淑玉、齐阳朔、郑伟谋、韩健、范正、孙世伟、叶盛、杨怀义、卜东波\n[bioRxiv（2022）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.25.497605v4)\u002F[生物信息学39.3（2023）](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F39\u002F3\u002Fbtad122\u002F7077134) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F06\u002F30\u002F2022.06.25.497605\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [网站](http:\u002F\u002F81.70.37.223) • [代码](https:\u002F\u002Fgithub.com\u002Fbigict\u002FProDESIGN-LE)\n\n**PeTriBERT：通过三维编码增强BERT，用于反向蛋白质折叠和设计**\n鲍德温·杜莫蒂耶、安托万·留特库斯、克莱芒·卡雷、加布里埃尔·克鲁克\n[bioRxiv 2022.08.10.503344](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.10.503344v1)\n\n**利用语言模型进行原子级蛋白质结构的进化规模预测**\n林泽明、哈利勒·阿金、罗尚·拉奥、布赖恩·希、朱仲凯、陆文婷、尼基塔·斯梅塔宁、罗伯特·维尔库伊尔、奥里·卡贝利、亚尼夫·舒梅利、艾伦·多斯桑托斯科斯塔、玛丽亚姆·法泽尔扎兰迪、汤姆·塞尔库、萨尔瓦托雷·坎迪多、亚历山大·里夫斯\n[bioRxiv 2022.07.20.500902](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.20.500902v2) • [博客](https:\u002F\u002Fai.facebook.com\u002Fblog\u002Fprotein-folding-esmfold-metagenomics\u002F) • [github](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fesm)\n\n**结构感知的语言模型即为蛋白质设计师**\n郑在祥、邓一凡、薛冬宇、周毅、叶飞、顾全全\n[arXiv:2302.01649](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.01649) • [代码::ByProt](https:\u002F\u002Fgithub.com\u002FBytedProtein\u002FByProt)\n\n**将预训练范式融入抗体序列-结构协同设计**\n高凯元、吴立军、朱金华、彭天博、夏英策、何亮、谢淑芳、秦涛、刘海光、何坤、刘铁严\n[arXiv:2211.08406](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.08406) • [代码](https:\u002F\u002Fgithub.com\u002FKyGao\u002FABGNN)\n\n**一种文本引导的蛋白质设计框架**\n刘圣超、朱宇涛、陆佳睿、许钊、聂伟力、安东尼·吉特、肖超伟、唐健、郭洪宇、阿尼玛·阿南德库马尔\n[arXiv:2302.04611](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.04611)\u002F[自然机器智能（2025）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01011-z) • [代码](https:\u002F\u002Fgithub.com\u002Fchao1224\u002FProteinDT)\n\n**一种端到端的深度学习方法，用于蛋白质侧链堆积和反向折叠**\n麦克帕特隆、马修和徐金波\n[美国国家科学院院刊120.23（2023）](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2216438120) • [代码](https:\u002F\u002Fgithub.com\u002FMattMcPartlon\u002FAttnPacker) • [补充材料](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002Fsuppl\u002F10.1073\u002Fpnas.2216438120\u002Fsuppl_file\u002Fpnas.2216438120.sapp.pdf)\n\n**面向蛋白质序列设计的上下文感知几何深度学习**\n吕西安·克拉普、费尔南多·梅雷莱斯、卢西亚诺·阿布里亚塔、马泰奥·达尔·佩拉罗\n[bioRxiv 2023.06.19.545381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.19.545381v1)\u002F[自然通讯，2024年](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-50571-y) • [代码](https:\u002F\u002Fgithub.com\u002FLBM-EPFL\u002FCARBonARa) • [新闻](https:\u002F\u002Factu.epfl.ch\u002Fnews\u002Fa-new-ai-approach-to-protein-design\u002F)\n\n**仅凭序列从头生成并优先排序靶标结合肽基序**\n苏哈斯·巴特、卡良·帕莱普、维维安·尤迪斯特拉、劳伦·洪、文卡塔·斯里卡尔·卡维拉尤尼、陈天来、赵琳、王天、索菲娅·文科夫、普拉南·查特吉\n[bioRxiv 2023.06.26.546591](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.26.546591v1) • [代码](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fpepprclip) • [colab](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Fu\u002F0\u002Ffolders\u002F1A4kQXjsG5j3OrO0XQtzBWWZu9Zm7c0ak) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F06\u002F28\u002F2023.06.26.546591\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**ProstT5：蛋白质序列与结构的双语语言模型**  \n迈克尔·海因辛格  \n康斯坦丁·魏森诺、华金·戈麦斯·桑切斯、阿德里安·亨克尔、马丁·施泰内格尔、布尔哈德·罗斯特  \n[bioRxiv 2023.07.23.550085](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.23.550085v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F07\u002F25\u002F2023.07.23.550085\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fmheinzinger\u002FProstT5)\n\n**基于深度学习的从头蛋白质序列设计及CalB水解酶上的验证**\n穆俊熙、李正新、张博、张琪、贾姆谢德·伊克巴尔、阿卜杜勒·瓦杜德、魏婷、冯艳、陈海峰  \n[bioRxiv 2023.08.01.551444](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.01.551444v1) • [代码](https:\u002F\u002Fgithub.com\u002Fweitinging\u002FGPD)\n\n**用于蛋白质侧链堆积和设计的不变点消息传递**\n尼古拉斯·Z·兰道夫、布赖恩·库尔曼  \n[bioRxiv 2023.08.03.551328](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.03.551328v1) • [代码](https:\u002F\u002Fgithub.com\u002FKuhlman-Lab\u002FPIPPack)\n\n**利用语言模型逐原子生成蛋白质及其他应用**\n丹尼尔·弗拉姆-谢泼德、凯文·朱、阿兰·阿斯普鲁-古齐克  \n[arXiv:2308.09482](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.09482)\n\n**SaProt：具有结构感知词汇表的蛋白质语言建模**\n金素、韩晨晨、周宇洋、单俊杰、周锡彬、袁发杰  \n[bioRxiv 2023.10.01.560349](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.01.560349v5) • [代码](https:\u002F\u002Fgithub.com\u002Fwestlake-repl\u002FSaProt)\n\n**SaprotHub：让所有生物学家都能轻松进行蛋白质建模**\nJin Su、Zhikai Li、Chenchen Han、Yuyang Zhou、Yan He、Junjie Shan、Xibin Zhou、Xing Chang、Shiyu Jiang、Dacheng Ma、The OPMC、Martin Steinegger、Sergey Ovchinnikov、Fajie Yuan\n[bioRxiv 2024.05.24.595648](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.24.595648)  •  [代码](https:\u002F\u002Fgithub.com\u002Fwestlake-repl\u002FSaprotHub) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fwestlake-repl\u002FSaprotHub\u002Fblob\u002Fmain\u002Fcolab\u002FSaprotHub_v2.ipynb)\n\n**AntiFold：利用反向折叠改进抗体结构设计**\nMagnus Høie、Alissa Hummer、Tobias Olsen、Morten Nielsen、Charlotte Deane\n[GenBio@NeurIPS2023 Spotlight](https:\u002F\u002Fopenreview.net\u002Fforum?id=bxZMKHtlL6)\u002F[Bioinformatics Advances (2025)](https:\u002F\u002Facademic.oup.com\u002Fbioinformaticsadvances\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioadv\u002Fvbae202\u002F8090019) • [代码](https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fdata\u002Fdownloads\u002FAntiFold\u002F)、[GitHub](https:\u002F\u002Fgithub.com\u002Foxpig\u002FAntiFold) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1TTfgjoZx3mzF5u4e9b4Un9Y7b_rqXc_4)、[网站](https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fantifold\u002F)\n\n**MMDesign：用于生成式蛋白质设计的多模态迁移学习**\nJiangbin Zheng、Siyuan Li、Yufei Huang、Zhangyang Gao、Cheng Tan、Bozhen Hu、Jun Xia、Ge Wang、Stan Z. Li\n[arXiv预印本 arXiv:2312.06297 (2023)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.06297)\n\n**ShapeProt：基于3D蛋白质形状生成模型的自顶向下蛋白质设计**\nLee、Youhan 和 Jaehoon Kim\n[bioRxiv (2023)：2023-12](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.03.567710v3)\n\n**X-LoRA：低秩适配器专家混合体，一种适用于大型语言模型的灵活框架，可用于蛋白质力学与设计**\nEric L. Buehler、Markus J. Buehler\n[arXiv:2402.07148](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.07148) • [代码](https:\u002F\u002Fgithub.com\u002FEricLBuehler\u002Fxlora) • [模型及权重](https:\u002F\u002Fhuggingface.co\u002Flamm-mit\u002Fx-lora)\n\n**AntiFold：利用反向折叠改进基于抗体结构的设计**\nMagnus Haraldson Høie、Alissa Hummer、Tobias H. Olsen、Broncio Aguilar-Sanjuan、Morten Nielsen、Charlotte M. Deane\n[arXiv:2405.03370](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.03370) • [代码](https:\u002F\u002Fgithub.com\u002Foxpig\u002FAntiFold) • [网站](https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fantifold\u002F) • 基于ESM-IF\n\n**使用StructureGPT进行蛋白质设计：一种用于蛋白质结构到序列转换的深度学习模型**\nNicanor Zalba Sr.、Pablo Ursua-Medrano Sr.、Humberto Bustince Sr.\n[bioRxiv 2024.06.03.597105](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.03.597105v1) • [代码](https:\u002F\u002Fgithub.com\u002FStructureGPT) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F06\u002F07\u002F2024.06.03.597105\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**将蛋白质语言模型调整为基于结构的设计**\nJeffrey A Ruffolo、Aadyot Bhatnagar、Joel Beazer、Stephen Nayfach、Jordan Russ、Emily Hill、Riffat Hussain、Joseph Gallagher、Ali Madani\n[bioRxiv 2024.08.03.606485](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.03.606485v1) • [代码](https:\u002F\u002Fgithub.com\u002FProfluent-AI\u002FproseLM-public) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F03\u002F2024.08.03.606485\u002FDC1\u002Fembed\u002Fmedia-1.zip) • [新闻](https:\u002F\u002Fwww.genengnews.com\u002Ftopics\u002Fartificial-intelligence\u002Fgiving-structure-to-language-profluents-ai-models-move-toward-precise-and-steerable-protein-design\u002F) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=MkwM3t80XpQ)\n\n**EMOCPD：基于注意力机制的高效计算蛋白质设计模型，利用氨基酸微环境**\nXiaoqi Ling、Cheng Cai、Demin Kong、Zhisheng Wei、Jing Wu、Lei Wang、Zhaohong Deng\n[arXiv:2410.21069](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.21069)\u002F[《化学信息与建模杂志》(2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c00378) • [数据](https:\u002F\u002Fgithub.com\u002Flingxqqqqq\u002FDataSet)\n\n**专家混合体助力高效且有效的蛋白质理解与设计**\nNing Sun、Shuxian Zou、Tianhua Tao、Sazan Mahbub、Dian Li、Yonghao Zhuang、Hongyi Wang、Xingyi Cheng、Le Song、Eric P. Xing\n[bioRxiv 2024.11.29.625425](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.29.625425v1) • [代码](https:\u002F\u002Fgithub.com\u002Fgenbio-ai\u002FAIDO\u002F)\n\n**通过对比偏好优化对ESM3进行微调，用于抗原特异性抗体设计**\nAnirudh Venkatraman、Gopinath Balaji、Veeresh Kande\n[UIUC 2024年秋季CS582 MLCB](https:\u002F\u002Fopenreview.net\u002Fforum?id=wDpvm3TrhE) • [代码](https:\u002F\u002Fgithub.com\u002Fanirudhvenk\u002Fantibody-dpo)\n\n**Protein CREATE实现从头合成蛋白结合剂的闭环设计**\nAlec Lourenço、Arjuna Subramanian、Ryan Spencer、Michael Anaya、Jiapei Miao、William Fu、Eric Chow、Matt Thomson\n[bioRxiv 2024.12.20.629847](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.20.629847v1) • 基于ESM-IF\n\n**DS-ProGen：用于功能型蛋白质设计的双结构深度语言模型**  \nYanting Li、Jiyue Jiang、Zikang Wang、Ziqian Lin、Dongchen He、Yuheng Shan、Yanruisheng Shao、Jiayi Li、Xiangyu Shi、Jiuming Wang、Yanyu Chen、Yimin Fan、Han Li、Yu Li  \n[arXiv:2505.12511](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.12511)\n\n**基于结构的抗体设计，结合亲和力优化的反向折叠**  \nXinyan Zhao、Yi-Ching Tang、Rivaaj Monsia、Victor J. Cantu、Ashwin Kumar Ramesh、Xiaozhong Liu、Zhiqiang An、Xiaoqian Jiang、Yejin Kim  \n[arXiv:2512.17815](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.17815) • 基于ESM-IF\n\n\n\n### 4.8 基于ResNet的方法\n\n**DenseCPD：利用DenseNet提升基于神经网络的计算蛋白质序列设计精度**\nQi、Yifei 和 John ZH Zhang\n[《化学信息与建模杂志》60.3期 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fpdf\u002F10.1021\u002Facs.jcim.0c00043) • 代码不可用\n\n**DeepUSPS：深度学习赋能的无约束结构蛋白质序列设计**  \nZhichong Ma、Jiawen Yang  \n[《蛋白质：结构、功能与生物信息学》(2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fprot.26847) • [代码](https:\u002F\u002Fgithub.com\u002Fmazhichong\u002FMZC) • [数据](https:\u002F\u002Fzenodo.org\u002Frecords\u002F10811470)\n\n### 4.9 基于扩散的方法\n\n**基于带有结构先验和对抗训练的扩散模型的从头蛋白质骨架生成**  \n刘宇峰、陈凌辉、刘海燕  \n[bioRxiv 2022.12.17.520847](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.17.520847v1)\u002F[Nat Methods (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-024-02437-w) • [代码](https:\u002F\u002Fgithub.com\u002Fliuyf020419\u002FSCUBA-D)\n\n**基于注意力机制扩散模型，结合二级结构约束的从头蛋白质生成设计**  \n倪博、大卫·L·卡普兰、马库斯·J·布勒尔  \n[Chem,(2023)](https:\u002F\u002Fwww.cell.com\u002Fchem\u002Ffulltext\u002FS2451-9294(23)00139-0) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProteinDiffusionGenerator) • [新闻](https:\u002F\u002Fnews.mit.edu\u002F2023\u002Fai-system-can-generate-novel-proteins-structural-design-0420)\n\n**用于反向蛋白质折叠的图去噪扩散模型**  \n易凯、周冰欣、沈一清、皮耶特罗·利奥、王昱光  \n[arXiv:2306.16819](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.16819)\u002F[NeurIPS 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=u4YXKKG5dX) • [代码](https:\u002F\u002Fgithub.com\u002Fykiiiiii\u002FGraDe_IF)\n\n**条件蛋白去噪扩散模型生成可编程内切核酸酶**  \n周冰欣、郑丽蓉、吴邦浩、易凯、钟博子涛、皮耶特罗·利奥、洪亮  \n[bioRxiv 2023.08.10.552783](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.10.552783v1)\n\n**在量化向量空间中的扩散生成非理想化的蛋白质结构并预测构象分布**  \n刘海燕、刘宇峰、陈凌辉  \n[bioRxiv 2023.11.18.567666](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.18.567666v1)\n\n**基于离散扩散的快速非自回归反向折叠**  \n杨约翰、Jason Yim、雷吉娜·巴尔齐莱、汤米·雅科拉  \n[arXiv:2312.02447](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.02447) • [代码](https:\u002F\u002Fgithub.com\u002Fjohnyang101\u002Fpmpnndiff)\n\n**扩散语言模型是多功能的蛋白质学习者**  \n王新友、郑在祥、叶飞、薛东宇、黄树坚、顾全全  \n[arXiv:2402.18567](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.18567)\n\n**LéxFusion**  \n莱文塔尔  \n论文未公开 • [新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FIex0YndimhLDM0mASp1MtA) • 商业化\n\n**条件蛋白扩散模型生成具有增强活性的人工可编程内切核酸酶序列**  \n周冰欣、郑丽蓉、吴邦浩、易凯、钟博子涛、谭阳、刘倩、皮耶特罗·利奥、洪亮  \n[bioRxiv 2023.08.10.552783](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.10.552783v2)\u002F[Cell Discovery 10.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41421-024-00728-2) • [代码](https:\u002F\u002Fgithub.com\u002Fbzho3923\u002FCPDiffusion)\n\n**LaGDif：用于高效自集成式蛋白质反向折叠的潜在图扩散模型**  \n吴涛宇、王昱光、沈一清  \n[arXiv:2411.01737](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.01737) • [代码](https:\u002F\u002Fgithub.com\u002FTaoyuW\u002FLaGDif)\n\n**Bridge-IF：利用马尔可夫桥学习反向蛋白质折叠**  \n朱一恒、吴嘉璐、李秋怡、严家欢、尹明泽、吴伟、李明阳、叶杰平、王正、吴健  \n[arXiv:2411.02120](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.02120) • [代码](https:\u002F\u002Fgithub.com\u002Fviolet-sto\u002FBridge-IF)\n\n**掩码先验引导的去噪扩散改进反向蛋白质折叠**  \n白培珍、菲利普·米利科维奇、刘宪元、莱昂纳多·德·玛利亚、丽贝卡·克罗斯代尔-伍德、欧文·拉坎、陆海平  \n[arXiv:2412.07815](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.07815)\u002F[Nature Machine Intelligence (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01042-6) • [代码](https:\u002F\u002Fgithub.com\u002Fpeizhenbai\u002FMapDiff)\n\n**使用语言扩散模型进行端到端的定制动力学从头蛋白质设计**  \n倪博、马库斯·J·布勒尔  \n[arXiv预印本 arXiv:2502.10173 (2025)](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2502.10173) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FModeShapeDiffusionDesign)，[模型](https:\u002F\u002Fhuggingface.co\u002Flamm-mit\u002FVibeGen)\n\n**利用离散扩散模型进行全原子蛋白质序列设计**  \n阿梅莉亚·比列加斯-莫尔西略、吉斯·J·阿德米拉尔、马塞尔·J.T. 雷因德斯、雅娜·M. 韦伯  \n[bioRxiv 2025.06.13.659451](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.13.659451v1) • [代码](https:\u002F\u002Fgithub.com\u002FIntelligent-molecular-systems\u002FAll-Atom-Protein-Sequence-Generation)\n\n**通过ABACUS-T多模态反向折叠提升功能性蛋白质性能**  \n刘宇峰、吴睿、王鑫宇、王晟、陈凌辉、李福东、陈权与刘海燕  \n[Nat Commun 16, 10177 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-65175-3) • [代码](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.17089342)\n\n### 4.10 基于贝叶斯的方法\n\n**利用深度贝叶斯优化进行反向蛋白质折叠**  \n娜塔莉·莫斯、曾益萌、丹尼尔·艾伦·安德森、菲利普·马费托内、亚伦·所罗门、佩顿·格林赛德、奥斯伯特·巴斯塔尼、雅各布·R·加德纳  \n[arXiv:2305.18089](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.18089) • [代码](https:\u002F\u002Fgithub.com\u002Fnataliemaus\u002Fbo-if)\n\n**设计具有精确调控动力学性质的蛋白质序列**  \nZ. 费伊登·布罗察基斯、米歇莱·文德鲁斯科洛、乔治奥斯·斯克雷塔斯  \n[bioRxiv 2025.02.13.638027](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.13.638027v1)\n\n**IgCraft：用于抗体发现与工程的多功能序列生成框架**  \n马修·格林尼格、赵浩文、弗拉基米尔·拉登科维奇、奥宾·拉蒙、皮耶特罗·索尔曼尼  \n[arXiv:2503.19821](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.19821) • [代码](https:\u002F\u002Fgithub.com\u002Fmgreenig\u002FIgCraft)\n\n### 4.11 基于流的方法\n\n**用于多配体对接和结合位点设计的谐波自条件流匹配**  \n汉内斯·施塔克、景博文、雷吉娜·巴尔齐莱、汤米·雅科拉  \n[arXiv:2310.05764](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.05764) • [代码](https:\u002F\u002Fgithub.com\u002FHannesStark\u002FFlowSite)\n\n### 4.12 基于强化学习的方法\n\n**通过奖励优化微调离散扩散模型及其在DNA和蛋白质设计中的应用**  \n王晨宇、上原昌俊、何一春、王艾米、汤马索·比安卡拉尼、阿万蒂卡·拉尔、汤米·雅科拉、谢尔盖·列维、王汉臣、阿维夫·雷格夫  \n[arXiv:2410.13643](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.13643) • [代码](https:\u002F\u002Fgithub.com\u002FChenyuWang-Monica\u002FDRAKES)\n\n**基于结构条件的分类扩散模型上的强化学习应用于反向蛋白质折叠**  \n雅沙·埃克特法耶、奥利维娅·维斯曼、西达尔特·纳拉亚南、德鲁·德雷斯尔、金J·马克、阿尔缅·姆克尔奇扬  \n[arXiv:2410.17173](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.17173) • [代码](https:\u002F\u002Fgithub.com\u002Fflagshippioneering\u002Fpi-rldif)\n\n**ProtInvTree：基于奖励引导的树搜索进行审慎的反向蛋白质折叠**  \n刘梦迪、程晓雪、高张洋、常宏、谭成、单世光、陈希林  \n[arXiv:2506.00925](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.00925)\n\n**ProteinZero：通过在线强化学习实现自我改进的蛋白质生成**  \n王梓文、范佳俊、郭瑞涵、阮氏桃、季恒、刘戈  \n[arXiv:2506.07459](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.07459)\n\n**ProDCARL：与强化学习对齐的扩散模型用于从头抗菌肽设计**  \n盛芳、穆罕默德·诺埃恩、扎赫拉·沙克里  \n[arXiv:2602.00157](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00157)\n\n### 4.13 训练方法\n\n**基于结构反馈的蛋白质逆折叠**  \n徐俊德、高子俊、周欣怡、胡杰、程星毅、宋乐、陈广勇、彭安恒、邱洁中  \n[arXiv:2506.03028](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.03028v1)\n\n**通过可设计性偏好优化改进蛋白质序列设计**  \n薛方雷、安德鲁·库巴内、郭志春、约瑟夫·K·闵、刘戈、杨毅、戴维·贝克  \n[arXiv:2506.00297](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.00297) • 基于LigandMPNN\n\n**EnerBridge-DPO：利用马尔可夫桥与直接偏好优化的能量引导型蛋白质逆折叠**  \n荣鼎毅、陆浩天、郑文卓、张帆、郑双嘉、刘宁  \n[arXiv:2506.09496](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.09496) • [代码](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FEnerBridge-DPO)\n\n**针对深度生成序列模型的归因分配，可在仅使用正样本数据的情况下实现可解释性分析**  \n罗伯特·弗兰克、迈克尔·维德里希、拉赫马德·阿克巴尔、君特·克拉姆鲍尔、盖尔·凯蒂尔·桑德韦、菲利普·A·罗伯特、维克多·格莱夫  \n[arXiv:2506.23182](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.23182)\n\n**自适应蛋白质设计协议与中间件**  \n艾曼·阿尔萨迪、乔纳森·阿什、米哈伊尔·季托夫、马泰奥·图里利、安德烈·梅尔茨基、尚滕努·贾、萨加尔·卡雷  \n[arXiv:2510.06396](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.06396)\n\n**解析蛋白质设计模型中分类学偏好背后的物理化学基础**  \n劳拉·B·迪伦、奥利弗·克鲁克、亚伦·迈瓦尔德  \n[bioRxiv 2025.10.21.683350](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.21.683350v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F10\u002F21\u002F2025.10.21.683350\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n## 5. 从功能到序列\n\n> 这些模型可根据预期的功能生成序列。\n\n### 5.1 基于CNN的方法\n\n**利用高容量机器学习设计抗体互补决定区**  \n刘戈、曾浩洋、乔纳斯·穆勒、布兰登·卡特、王子恒、乔纳斯·希尔茨、杰拉尔丁·霍尼、迈克尔·E·伯恩鲍姆、斯特凡·埃韦特、大卫·K·吉福德  \n[Bioinformatics 36.7 (2020): 2126–2133](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F36\u002F7\u002F2126\u002F5645171) • [代码](https:\u002F\u002Fgithub.com\u002Fgifford-lab\u002Fantibody-2019)\n\n**利用自回归生成模型进行蛋白质设计与变异预测**  \n申贞恩、亚当·J·里塞尔曼、亚伦·W·科拉斯奇、康纳·麦克马洪、伊莱娜·西蒙、克里斯·桑德、阿希什·曼格利克、安德鲁·C·克鲁斯及黛博拉·S·马克斯  \n[Nature Communications 12.1 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-22732-w.pdf) • [代码：SeqDesign](https:\u002F\u002Fgithub.com\u002Fdebbiemarkslab\u002FSeqDesign) • 突变效应预测 • 序列生成 • 2021年4月\n\n**通过深度学习从抗体序列预测抗原特异性以优化治疗性抗体**  \n德里克·M·梅森、西蒙·弗里登索恩、塞德里克·R·韦伯、克里斯蒂安·约尔迪、巴斯蒂安·瓦格纳、西蒙·M·门格、罗伊·A·埃林、露西亚·博纳蒂、扬·达欣登、巴勃罗·盖因萨、布鲁诺·E·科雷亚及赛·T·雷迪  \n[Nature Biomedical Engineering 5.6 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41551-021-00699-9) • [代码](https:\u002F\u002Fgithub.com\u002Fdahjan\u002FDMS_opt)\n\n**通过混合仿生—从头预测分子设计加速ELP基材料的工程化**  \n蒂莫·拉科、安蒂·科尔凯阿拉克索、布尔楚·菲拉特利吉尔·耶尔迪里尔、皮奥特尔·巴蒂斯、维勒·利利斯特伦、阿里·霍卡宁、诺纳帕、梅尔雅·彭蒂拉、安西·劳卡宁、阿里·米塞雷斯、卡伊·索德加德、佩日曼·穆罕默迪  \n[Advanced Materials (2024)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadma.202312299)\n\n### 5.2 基于VAE的方法\n\n**机器学习辅助设计与筛选合成细胞中的新兴蛋白质功能**  \n小山俊史、贝拉·P·弗罗恩、莱昂·巴布尔及佩特拉·施维勒  \n[Nature Communications 15, 2010 (2024)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41467-024-46203-0) • [代码](https:\u002F\u002Fgithub.com\u002FBelaFrohn\u002FsynMinE)\n\n**蛋白质序列的变分自编码**  \n萨姆·西奈、埃里克·凯尔西克、乔治·M·丘奇、马丁·A·诺瓦克  \n[arXiv预印本 arXiv:1712.03346 (2017)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.03346)\n\n**基于适应性采样的设计**  \n布鲁克斯、大卫·H·和詹妮弗·利斯特加滕  \n[arXiv预印本 arXiv:1810.03714 (2018)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.03714)\n\n**Pepcvae：半监督定向设计抗菌肽序列**  \n帕耶尔·达斯、卡希尼·瓦达万、奥斯卡·张、汤姆·塞尔库、西塞罗·多斯桑托斯、马修·里默、维吉尔·琴塔马拉克尚、英基特·帕迪、亚历山德拉·莫伊西洛维奇  \n[arXiv预印本 arXiv:1810.07743 (2018)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.07743)\n\n**用于T细胞受体蛋白序列的深度生成模型**  \n克里斯蒂安·戴维森、布兰登·J·奥尔森、威廉·S·德威特三世、让·冯、伊利亚斯·哈金斯、菲利普·布拉德利、弗雷德里克·A·马森四世  \n[Elife 8 (2019)](https:\u002F\u002Felifesciences.org\u002Farticles\u002F46935)\n\n**如何“幻觉”出功能性蛋白质**  \n科斯特洛、扎克及埃克托·加西亚·马丁  \n[arXiv预印本 arXiv:1903.00458 (2019)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.00458)\n\n**深度学习揭示抗体库中的趋同选择**  \n西蒙·弗里登索恩、丹尼尔·诺伊迈尔、塔里克·A·汗、露西亚·切普雷吉、克里斯蒂娜·帕罗拉、阿瑟·R·戈尔特尔·德·弗里斯、莉娜·埃尔拉赫、德里克·M·梅森、赛·T·雷迪  \n[BioRxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.02.25.965673v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2020\u002F02\u002F26\u002F2020.02.25.965673\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 文章发表后提供代码\n\n**用于生成抗菌肽的变分自编码器**  \n迪恩、斯科特·N·和斯科特·A·沃尔珀  \n[ACS omega 5.33 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facsomega.0c00442)\n\n**利用变分自编码器生成功能性蛋白质变体**  \n亚历克斯·霍金斯-胡克尔、弗洛伦斯·德帕迪厄、塞巴斯蒂安·鲍尔、纪尧姆·库瓦隆、阿瑟·陈、戴维·比卡尔  \n[PLoS computational biology 17.2 (2021)](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1008736)\n\n**通过深度生成模型与分子动力学模拟加速抗菌药物发现**  \n帕耶尔·达斯、汤姆·塞尔库、卡希尼·瓦达万、英基特·帕迪、塞巴斯蒂安·格尔曼、弗拉维乌·齐普西甘、维吉尔·琴塔马拉克尚、亨德里克·斯特罗贝尔、西塞罗·多斯桑托斯、品宇·陈、严毅杨、杰里米·P·K·谭、詹姆斯·海德里克、杰森·克雷恩及亚历山德拉·莫伊西洛维奇  \n[Nature Biomedical Engineering 5.6 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41551-021-00689-x)\n\n**深度生成模型创造新颖且多样的蛋白质结构**  \n泽明、汤姆、扬及亚历山大  \n[NeurIPS 2021](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2021\u002FMLSB2021_Deep_generative_models_create.pdf)\n\n**PepVAE：用于抗菌肽生成与活性预测的变分自编码框架**  \n斯科特·N·迪恩、杰罗姆·安东尼·E·阿尔瓦雷斯、丹·扎贝塔基斯、斯科特·A·沃尔珀及安东尼·P·马拉诺斯基  \n[Frontiers in microbiology 12 (2021)](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffmicb.2021.725727\u002Ffull) • [代码](https:\u002F\u002Fgithub.com\u002Fzswitten\u002FAntimicrobial-Peptides) • [补充材料](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffmicb.2021.725727\u002Ffull#supplementary-material)\n\n**HydrAMP：用于抗菌肽发现的深度生成模型**\n保利娜·西姆扎克、马尔钦·莫热伊科、托马什·格热戈热克、玛尔塔·鲍尔、达米安·诺伊鲍尔、米哈尔·米哈尔斯基、雅切克·斯罗卡、皮奥特尔·塞特尼、沃伊切赫·卡米什、埃娃·什丘雷克\n[bioRxiv（2022）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.01.27.478054v2) • [代码](https:\u002F\u002Fgithub.com\u002Fszczurek-lab\u002Fhydramp)\n\n**利用生成式神经网络进行治疗性酶工程**\n安德鲁·吉塞尔、阿塔纳西奥斯·杜西斯、坎查纳·拉维昌德兰、凯文·史密斯、斯雷约希·苏尔、伊恩·麦克法登、魏征和斯图尔特·利希特\n[《科学报告》12.1（2022）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-022-05195-x)\n\n**GM-Pep：从头设计功能性肽序列的高效策略**\n陈曲硕、杨昌彦、谢一浩、王宇强、李晓旭、王凯荣、黄锦奇和颜文进\n[《化学信息与建模杂志》（2022）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.2c00089) • [代码](https:\u002F\u002Fgithub.com\u002FTimothyChen225\u002FGM-Pep)\n\n**蛋白质序列生成模型的平均维度**\n克里斯托夫·费瑙尔、埃马努埃莱·博尔戈诺沃\n[bioRxiv 2022.12.12.520028](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.12.520028v1) • [代码](https:\u002F\u002Fgithub.com\u002Fchristophfeinauer\u002FProteinMeanDimension)\n\n**利用生成式深度学习预测用于DNA编辑的定制重组酶**\n卢卡斯·西奥·施密特、马切伊·帕什科夫斯基-罗加茨、弗洛里安·尤格和弗兰克·布赫霍尔茨\n[Nat Commun 13, 7966（2022）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-35614-6) • [代码](https:\u002F\u002Fgithub.com\u002Fltschmitt\u002FRecGen) • [补充材料](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41467-022-35614-6\u002FMediaObjects\u002F41467_2022_35614_MOESM1_ESM.pdf)\n\n**ProT-VAE：用于功能蛋白设计的蛋白质Transformer变分自编码器**\n埃姆雷·塞夫根、乔舒亚·莫勒、艾德里安·朗格、约翰·帕克、肖恩·奎格利、杰夫·梅耶、普纳姆·斯里瓦斯塔瓦、西塔拉姆·盖亚特里、大卫·霍斯菲尔德、玛丽亚·科尔舒诺娃、米哈·利夫内、米歇尔·吉尔、拉马·兰加纳坦、安东尼·B·科斯塔、安德鲁·L·弗格森\n[bioRxiv 2023.01.23.525232](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.23.525232v1)\u002F[美国国家科学院院刊122（41）e2408737122](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2408737122)\n\n**利用潜在空间近似轨迹收集器进行靶向肽设计**\n林彤、陈思杰、鲁奇拉·巴苏、裴德虎、程晓林、莱文特·布拉克·卡拉\n[arXiv:2302.01435](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.01435)\n\n**深度学习生成模型助力信号蛋白合成同源物的设计**\n连欣然、尼克萨·普拉利亚克、安德鲁·L·弗格森、拉马·兰加纳坦\n[《生物物理杂志》122.3（2023）：311a](https:\u002F\u002Fwww.cell.com\u002Fbiophysj\u002Ffulltext\u002FS0006-3495(22)02664-9)\n\n**通过体外、体内及计算筛选相结合设计具有新功能的蛋白质**\n小山俊史、贝拉·保罗·弗罗恩、莱昂·巴布尔、佩特拉·施维勒\n[bioRxiv 2023.02.16.528840](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.16.528840v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F02\u002F19\u002F2023.02.16.528840\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**ProteinVAE：用于转化型蛋白质设计的变分自编码器**\n吕素月、沙欣·索瓦拉蒂-哈什金、迈克尔·加顿\n[bioRxiv 2023.03.04.531110](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.04.531110v1)\u002F[《自然机器智能》（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-023-00787-2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F03\u002F05\u002F2023.03.04.531110\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fhuggingface.co\u002FRostlab\u002Fprot_bert)\n\n**ProtWave-VAE：将自回归采样与基于潜在空间的推理相结合，实现数据驱动的蛋白质设计**\n尼克萨·普拉利亚克、连欣然、拉马·兰加纳坦、安德鲁·弗格森\n[bioRxiv 2023.04.23.537971](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.04.23.537971v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F04\u002F23\u002F2023.04.23.537971\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FPraljakReps\u002FProtWaveVAE)\n\n**利用深度生成模型设计T细胞受体序列有意义的连续表征**\n艾伦·Y·利里、达里乌斯·斯科特、纳米塔·T·古普塔、贾内尔·C·韦特、迪米特里斯·斯科科斯、古林德·S·阿特瓦尔、彼得·G·霍金斯\n[bioRxiv 2023.06.17.545423](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.17.545423v1) • [代码](https:\u002F\u002Fgithub.com\u002Fpeterghawkins-regn\u002Ftcrvalid)\n\n**语言模型与基于物理的方法在修饰MHC I类免疫可见性以用于疫苗和治疗药物设计中的应用**\n汉斯-克里斯托夫·加瑟、迭戈·奥亚尔孙、阿吉塔·拉詹、哈维尔·阿尔法罗\n[bioRxiv 2023.07.10.548300](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.10.548300v1)\n\n**无细胞生物合成结合深度学习加速抗菌肽的从头开发**\n阿米尔·潘迪、戴维·亚当、阿米尔·扎雷、范端郑、斯特凡·L·谢弗、玛丽·伯特、比约恩·克拉本德、叶丽莎维塔·波布科娃、马尼什·库什瓦哈、耶加内·福鲁吉贾巴里、彼得·布劳恩、克里斯托夫·施潘、克里斯蒂安·普罗伊瑟、埃尔克·波格·冯·施特兰德曼、赫尔格·B·博德、海纳·冯·布特拉尔、威廉·贝尔特拉姆、安娜·莉娜·容格、弗兰克·阿本德罗特、伯恩德·施梅克、格哈德·胡默、奥拉娅·巴斯克斯和托比亚斯·J·埃尔布\n[《自然通讯》14.1（2023）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-023-42434-9) • [代码](https:\u002F\u002Fgithub.com\u002Famirpandi\u002FDeep_AMP)\n\n**利用生成式深度学习和分子动力学模拟设计靶向肽抑制剂**\n陈思杰、林彤、鲁奇拉·巴苏、杰里米·里奇、沈旺、易川罗、邢灿李、德华裴、莱文特·布拉克·卡拉和程晓林\n[Nat Commun 15, 1611（2024）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-45766-2) • [代码](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.10587692)\n\n**基于深度学习设计SH3信号结构域的合成同源物**\n连欣然、尼克萨·普拉利亚克、苏布·K·苏布拉马尼扬、莎拉·瓦辛格、拉马·兰加纳坦、安德鲁·L·弗格森\n[《细胞系统》（2024）](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Fabstract\u002FS2405-4712(24)00204-7)\n\n**CMADiff：跨模态对齐扩散用于可控蛋白质生成**\n周长健、邱悦熙、凌通通、李嘉峰、刘双河、王湘京、宋佳、向文胜\n[arXiv:2503.21450](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.21450) • [代码](https:\u002F\u002Fgithub.com\u002FHPC-NEAU\u002FPhysChemDiff)\n\n**HER3高效Affilin®蛋白结合剂的设计**\n安娜·玛丽亚·迪亚斯-罗维拉、乔纳森·洛策、格雷戈尔·霍夫曼、基亚拉·帕拉拉、亚历克西斯·莫利纳、伊娜·科堡尔、曼雅·格洛泽-布赖尼格、马伦·迈辛、马德伦·茨瓦格、露西娅·迪亚斯、维克多·瓜亚尔、伊娃·博瑟-多恩克、塞尔吉·罗达\n[bioRxiv 2025.04.02.646551](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.02.646551v1) • [代码](https:\u002F\u002Fgithub.com\u002Fannadiarov\u002FProtVAE) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F04\u002F02\u002F2025.04.02.646551\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**一种结构感知的生成框架，用于探索蛋白质序列与功能空间**  \n迪万舒·舒克拉、乔纳森·马丁、法鲁克·莫尔科斯、达维特·A·波托扬  \n[bioRxiv 2025.09.18.676787](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.18.676787v1)\n\n**基于多模态深度学习的从头多机制抗菌肽设计**  \n李晓娟、龚海帆、王岳、赵一诺、李立祥、包佩静、孔庆洲、付佳璐、万博尧、张雨萌、张景辉、倪杰坤、韩中雪、南学平、鞠坤平、孙龙飞、马跃睿、常慧君、郑梦琪、于彦波、杨晓云、左秀丽、王海娜、李艳青  \n[Advanced Science](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202515835) • [代码](https:\u002F\u002Fgithub.com\u002Fhaifangong\u002FM3CAD)\n\n\n\n### 5.3 基于GAN的方法\n\n**用于优化蛋白质功能的反馈式生成对抗网络**\n古普塔，安维塔，和詹姆斯·邹  \n[Nature Machine Intelligence 1.2 (2019)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-019-0017-4) • [代码](https:\u002F\u002Fgithub.com\u002Fav1659\u002Ffbgan)\n\n**利用生成对抗网络从抗生素耐药基因数据生成蛋白质序列**\n奇巴尔，普拉巴尔，和阿尔皮特·乔希  \n[arXiv预印本 arXiv:1904.13240 (2019)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.13240)\n\n**ProGAN：用于深度神经网络框架中数据增强的蛋白质溶解度生成对抗网络**\n韩曦、张立恒、周康、王晓楠  \n[Computers & Chemical Engineering 131 (2019)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0098135419304922)\n\n**GANDALF：使用序列和结构生成对抗网络进行药物设计的肽生成**\n罗塞托，艾莉森，和周文进  \n[第11届ACM国际生物信息学、计算生物学与健康信息学会议论文集，2020年](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3388440.3412487)\n\n**利用生成对抗网络设计特征可控的人源化抗体发现库**\n蒂莱利·阿米穆尔、杰里米·M·谢弗、兰达尔·R·凯切姆、J·亚历克斯·泰勒、鲁提利奥·H·克拉克、乔什·史密斯、丹妮尔·范·西特斯、克里斯汀·C·西斯卡、保琳·施密特、梅根·斯普拉格、布鲁斯·A·克尔温、迪恩·佩蒂特  \n[BioRxiv (2020)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.04.12.024844v2)\n\n**利用活性感知生成对抗网络生成具有氨苄西林水平活性的抗菌肽**\n安德烈斯·图茨、杜伊·福克·陈、秋子弓元、伊藤义弘、宇泽隆则和津田浩二  \n[ACS Omega 5.36 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facsomega.0c02088) • [代码](https:\u002F\u002Fgithub.com\u002Ftsudalab\u002FPepGAN)\n\n**用于具有层次功能的从头蛋白质设计的条件生成模型**  \n库切拉，蒂姆、马泰奥·托尼纳利和莱蒂西亚·门格-帕帕桑托斯  \n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.11.10.467885v1)\u002F[Bioinformatics 38.13 (2022)](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F38\u002F13\u002F3454\u002F6593486) • [代码](https:\u002F\u002Fgithub.com\u002Ftimkucera\u002Fproteogan)\n\n**利用生成对抗网络扩展功能性蛋白质序列空间**  \n多纳塔斯·雷佩卡、维金塔斯·扬尼斯基斯、劳里纳斯·卡尔普斯、埃尔日别塔·伦贝扎、伊尔曼塔斯·罗凯蒂斯、扬·兹里梅茨、西莫娜·波维洛涅内、奥德里乌斯·劳里纳纳斯、桑德拉·维克南德尔、维萨姆·阿布阿吉瓦、奥托·萨沃莱宁、罗兰达斯·梅斯基斯、马丁·K·M·英奎斯特以及阿列克谢·泽列兹尼亚克  \n[Nature Machine Intelligence 3.4 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-021-00310-5) • [代码](https:\u002F\u002Fgithub.com\u002FBiomatter-Designs\u002FProteinGAN)\n\n**精准抗菌肽设计的生成方法。**  \n乔纳森·B·费雷尔、雅各布·M·雷明顿、科林·M·范·奥特、莫娜·沙拉菲、瑞姆·阿布舒沙、伊冯娜·扬森-海宁格、塞维林·T·施内贝利、马修·J·瓦戈、萨夫万·瓦沙、贾宁·李  \n[BioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.10.02.324087v2) • [代码](https:\u002F\u002Fgitlab.com\u002Fvail-uvm\u002Famp-gan\u002F-\u002Ftree\u002Ftest_samples\u002F)\n\n**AMPGAN v2：机器学习指导下的抗菌肽设计**  \n科林·M·范·奥特、乔纳森·B·费雷尔、雅各布·M·雷明顿、萨夫万·瓦沙和贾宁·李  \n[Journal of Chemical Information and Modeling 61.5 (2021)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.0c01441)\n\n**DeepImmuno：基于深度学习的免疫原性肽预测与生成，用于T细胞免疫**  \n李广远、巴拉吉·艾耶尔、V B 苏里亚·普拉萨特、倪一兆、内森·萨洛莫尼斯  \n[Briefings in Bioinformatics 22.6 (2021)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle-abstract\u002F22\u002F6\u002Fbbab160\u002F6261914) • [代码](https:\u002F\u002Fgithub.com\u002Ffrankligy\u002FDeepImmuno) • [网站](https:\u002F\u002Fdeepimmuno.research.cchmc.org\u002F)\n\n**PandoraGAN：利用生成对抗网络生成抗病毒肽**  \n施拉达·苏拉纳、普贾·阿罗拉、迪维·辛格、迪普蒂·萨哈斯拉布德、贾亚拉曼·瓦拉迪  \n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.02.15.431193v2)\n\n**Feedback-AVPGAN：反馈引导的生成对抗网络，用于生成抗病毒肽**  \n加野长谷川、吉隆真若、照丸寺田、曹伟和清水健太郎  \n[Journal of Bioinformatics and Computational Biology (2022)](https:\u002F\u002Fwww.worldscientific.com\u002Fdoi\u002F10.1142\u002FS0219720022500263) • [代码](https:\u002F\u002Fgithub.com\u002FKanoHase\u002FAVP-Generator)\n\n**利用深度学习和分子动力学模拟设计抗菌肽**  \n曹秋实、葛成、王雪洁、佩塔·J·哈维、张子轩、马源、王向红、贾欣颖、梅赫迪·莫布利、大卫·J·克雷克、蒋涛、杨金波、魏志强、王燕、常山、余利利  \n[Briefings in Bioinformatics (2023)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle-abstract\u002F24\u002F2\u002Fbbad058\u002F7066348)\n\n**基于残基理化性质景观的β-转角生成设计**  \n瓦尔丹·萨塔尔卡尔、盖梅奇斯·D·德加加、李伟、潘玉婷、安德鲁·C·麦克尚、詹姆斯·C·冈巴特、朱莉·C·米切尔和马修·P·托雷斯  \n[Biophysical Journal(2024)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0006349524000705) • [代码](https:\u002F\u002Fgithub.com\u002Fjuliecmitchell\u002FbeGAN)\n\n**基于反馈式生成对抗网络的从头抗菌肽设计**  \n米凯拉·阿雷蒂·泽尔武、埃夫罗西尼·杜特西、扬尼斯·潘塔齐斯、帕纳约蒂斯·察卡利德斯  \n[International Journal of Molecular Sciences 25.10 (2024)](https:\u002F\u002Fwww.mdpi.com\u002F1422-0067\u002F25\u002F10\u002F5506) • [代码](https:\u002F\u002Fgithub.com\u002Faretiz\u002Fde_novo_design_GAN)\n\n**二元判别器促进基于GPT的蛋白质设计**  \n曾子硕、徐如芳、郭晋、罗小舟  \n[bioRxiv 2023.11.20.567789](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.20.567789v3) • [代码](https:\u002F\u002Fgithub.com\u002Fzishuozeng\u002FGPT_protein_design) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F12\u002F21\u002F2023.11.20.567789\u002FDC1\u002Fembed\u002Fmedia-1.xlsx)\n\n**基于蛋白质语言模型引导的生成对抗网络的多种微塑料结合肽从头设计**  \n王思远、迈克尔·T·伯格曼、卡罗尔·K·霍尔、杨峰奇  \n[Journal of Chemical Information and Modeling 65.16 (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c01401)\n\n**人工智能驱动的子宫内膜癌肽类药物发现：大数据时代下的深度生成建模与分子模拟**  \n伊斯拉尔·法蒂玛、阿卜杜尔·雷赫曼、王志博、哈菲兹·乌尔·雷赫曼、穆罕默德·阿尔达乌、达伍德·艾哈迈德·瓦赖奇、孟宇轩、李燕和廖明志  \n[J Comput Aided Mol Des 40, 47 (2026)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10822-025-00735-9)\n\n### 5.4 基于 Transformer 的方法\n\n> 包括蛋白质大型语言模型（pLLM）和自回归语言模型。\n\n**Progen：用于蛋白质生成的语言建模** \u002F **大型语言模型可在不同家族中生成功能性蛋白质序列**\n阿里·马达尼、布莱恩·麦肯、尼基尔·奈克、尼提什·希里什·凯斯卡、纳姆拉塔·阿南德、拉斐尔·R·江口、普苏·黄、理查德·索彻\n[arXiv 预印本 arXiv:2004.03497 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.03497)\u002F[Nat Biotechnol (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-022-01618-2) • [ProGen](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Fprogen), [CTRL](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Fctrl)\n\n**基于注意力机制的神经网络生成信号肽**\n扎卡里·吴、凯文·K·杨、迈克尔·J·利斯卡、艾丽西亚·李、阿丽娜·巴齐拉、大卫·韦尼克、大卫·P·韦纳以及弗朗西丝·H·阿诺德\n[ACS Synthetic Biology 9.8 (2020)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Facssynbio.0c00219)\n\n**ProtTrans：通过自监督深度学习和高性能计算破解生命密码的语言**\n艾哈迈德·埃尔纳加尔、迈克尔·海因辛格、克里斯蒂安·达拉戈、加利亚·雷哈维、王宇、利昂·琼斯、汤姆·吉布斯、塔马斯·费赫尔、克里斯托夫·安格勒、马丁·施泰内格尔、德布辛杜·鲍米克以及布尔克哈德·罗斯特\n[arXiv 预印本 arXiv:2007.06225 (2020)](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9477085) • [代码](https:\u002F\u002Fgithub.com\u002Fagemagician\u002FProtTrans)\n\n**用于抗体设计的生成式语言建模**\nShuai, Richard W., 杰弗里·A·鲁弗洛以及杰弗里·J·格雷\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.12.13.472419v2)\u002F[Cell Systems](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Fpdf\u002FS2405-4712(23)00271-5.pdf) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F20\u002F2021.12.13.472419\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FGraylab\u002FIgLM)\n\n**深度神经网络语言建模实现跨家族的功能性蛋白质生成**\n阿里·马达尼、本·克劳斯、埃里克·R·格林、苏布·苏布拉马尼安、本杰明·P·莫尔、詹姆斯·M·霍尔顿、何塞·路易斯·奥尔莫斯二世、蔡明雄、扎卡里·Z·孙、理查德·索彻、詹姆斯·S·弗雷泽、尼基尔·奈克\n[bioRxiv (2021)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.07.18.452833v1)\n\n**基于结构数据的蛋白质序列采样与预测**\n加布里埃尔·A·奥雷利亚纳、哈维尔·卡塞雷斯-德尔皮亚诺、罗伯托·伊巴涅斯、迈克尔·P·邓恩、莱昂纳多·阿尔瓦雷斯\n[bioRxiv 2021.09.06.459171](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.09.06.459171v3)\n\n**基于 Transformer 的蛋白质生成，结合正则化潜在空间优化**\n埃格伯特·卡斯特罗、阿比纳夫·戈达瓦尔蒂、朱利安·鲁宾菲恩、凯文·吉维奇安、丹纳贾伊·巴斯卡尔以及史密塔·克里希纳斯瓦米\n[Nat Mach Intell (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-022-00532-1)\u002F[arXiv:2201.09948](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.09948) • [代码](https:\u002F\u002Fgithub.com\u002FKrishnaswamyLab\u002FReLSO-Guided-Generative-Protein-Design-using-Regularized-Transformers)\n\n**BioPhi：基于天然抗体库和深度学习的抗体设计、人源化及人源性评估平台**\n大卫·普里霍达、贾德·马马里、安德鲁·韦特、维罗妮卡·胡安、劳伦斯·法亚达特-迪尔曼、丹尼尔·斯沃齐尔、丹尼·A·比特顿\n[mAbs. 第14卷第1期. 泰勒与弗朗西斯，2022年](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F19420862.2021.2020203)\n\n**利用正则化 Transformer 进行引导式蛋白质生成设计**\n埃格伯特·卡斯特罗、阿比纳夫·戈达瓦尔蒂、朱利安·鲁宾菲恩、凯文·B·吉维奇安、丹纳贾伊·巴斯卡尔以及史密塔·克里希纳斯瓦米\n[arXiv 预印本 arXiv:2201.09948 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.09948)\n\n**利用条件 Transformer 实现可控蛋白质设计**\n诺埃利亚·费鲁兹、比尔特·霍克尔\n[arXiv 预印本 arXiv:2201.07338 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.07338)\u002F[Nature Machine Intelligence (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-022-00499-z) • 对[第5.4节](#54-transformer-based)的综述\n\n**ProteinBERT：一种通用的蛋白质序列与功能深度学习模型**\n纳达夫·布兰德斯、丹·奥弗、雅姆·佩莱格、纳达夫·拉波波特、米哈尔·利尼亚尔\n[Bioinformatics，2022年3月](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F38\u002F8\u002F2102\u002F6502274) • [代码](https:\u002F\u002Fgithub.com\u002Fnadavbra\u002Fprotein_bert)\n\n**ProtGPT2 是一种用于蛋白质设计的深度无监督语言模型**\n诺埃利亚·费鲁兹、施特芬·施密特、比尔特·霍克尔\n[bioRxiv](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.03.09.483666v1.full)\u002F[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-022-32007-7) • [模型：huggingface](https:\u002F\u002Fhuggingface.co\u002Fnferruz\u002FProtGPT2) [数据集：huggingface](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fnferruz\u002FUR50_2021_04) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BA5C0kLcErM) • [研究亮点](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-022-01518-5) • [新闻](https:\u002F\u002Fcen.acs.org\u002Fphysical-chemistry\u002Fprotein-folding\u002FGenerative-AI-dreaming-new-proteins\u002F101\u002Fi12#)\n\n**少量样本蛋白质生成**\n拉姆、苏米娅以及特里斯坦·贝普勒\n[arXiv 预印本 arXiv:2204.01168 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.01168)\n\n**RITA：关于扩展生成式蛋白质序列模型的研究**\n丹尼尔·赫斯洛、尼科洛·扎尼凯利、帕斯卡尔·诺坦、雅科波·波利、黛博拉·马克斯\n[arXiv 预印本 arXiv:2205.05789 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.05789) • [代码](https:\u002F\u002Fhuggingface.co\u002Flightonai\u002FRITA_xl)\n\n**ProGen2：探索蛋白质语言模型的边界**\n埃里克·尼扬克、杰弗里·鲁弗洛、伊莱·N·温斯坦、尼基尔·奈克、阿里·马达尼\n[arXiv:2206.13517](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.13517) • [代码](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002Fprogen) • [指南](https:\u002F\u002Fgithub.com\u002FZeeSid\u002FBioLM_Tutes\u002Ftree\u002Fmain)\n\n**AbLang：用于完成抗体序列的抗体语言模型**\n托比亚斯·H·奥尔森、伊恩·H·莫尔、夏洛特·M·迪恩\n[Bioinformatics Advances，第2卷第1期，2022年，vbac046](https:\u002F\u002Facademic.oup.com\u002Fbioinformaticsadvances\u002Farticle\u002F2\u002F1\u002Fvbac046\u002F6609807)\n\n**重新编程预训练语言模型以进行抗体序列补全**\n伊戈尔·梅尔尼克、维吉尔·琴塔马拉克尚、陈品宇、帕耶尔·达斯、阿米特·杜兰达尔、英基特·帕迪以及黛芙琳娜·达斯\n[arXiv:2210.07144](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.07144) • [代码](https:\u002F\u002Fgithub.com\u002FIBM\u002FReprogBERT)\n\n**AbBERT：通过掩码语言建模学习抗体的人源性**\n丹尼斯·瓦申科、萨姆·阮、安德烈·贡卡尔维斯、费利佩·莱诺·达席尔瓦、布伦登·彼得森、托马斯·德索特尔斯以及丹尼尔·费索尔\n[bioRxiv 2022.08.02.502236](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2022.08.02.502236)\n\n**利用主动学习加速抗体设计**\n徐承佑、郭敏宇、姜恩智、金彩恩、朴恩英、姜泰贤以及金振汉\n[bioRxiv 2022.09.12.507690](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.12.507690v1)\n\n**重新编程大型预训练语言模型以进行抗体序列补全**\n伊戈尔·梅尔尼克、维吉尔·琴塔马拉克尚、陈品宇、帕耶尔·达斯、阿米特·杜兰达尔、英基特·帕迪以及黛芙琳娜·达斯\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=axFCgjTKP45)\u002F[arXiv:2210.07144](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.07144)\n\n**机器学习优化候选抗体，生成高度多样化的亚纳摩尔级亲和力抗体文库**\n林莉、埃丝特·古普塔、约翰·斯佩思、莱斯利·辛格、拉斐尔·海梅斯、拉蒙达·苏洛·卡塞雷斯、特里斯坦·贝普勒、马修·E·沃尔什\n[bioRxiv 2022.10.07.502662](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.10.07.502662v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F10\u002F07\u002F2022.10.07.502662\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 代码即将公开\n\n**ZymCTRL：用于可控生成人工酶的条件语言模型**\n诺埃利亚·费鲁兹\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FZymCTRL_a_conditional_language_model_for_the_controllable_generation_of_artificial_enzymes.pdf)\u002F[bioRxiv 2024.05.03.592223](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.03.592223v1) • [Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fnferruz\u002FZymCTRL) • [海报](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002F59047.png?t=1669864213.082831)\n\n**通过编码器-解码器语言模型进行互补链配对序列的生成式抗体设计**\n朱、西蒙和凯茜·魏\n[NeurIPS 2023 生成式人工智能与生物学（GenBio）研讨会，2023年](https:\u002F\u002Fopenreview.net\u002Fforum?id=QrH4bhWhwY)\u002F[arXiv:2301.02748](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.02748)\n\n**利用生成式人工智能解锁从头设计抗体**\n阿米尔·沙内萨扎德、马特·麦克帕特隆、乔治·卡孙、安德烈娅·K·施泰格、约翰·M·萨顿、埃德里斯·亚辛、凯伦·麦克斯洛基、罗贝尔·海尔、理查德·帅、朱利安·阿尔韦里奥、戈兰·拉科切维奇、西蒙·莱文、约万·切约维奇、贾希尔·M·古铁雷斯、亚历克斯·莫雷黑德、奥列克谢·杜布罗夫斯基、切尔西·钟、布雷安娜·K·卢顿、尼古拉斯·迪亚斯、克里斯塔·科恩内特、丽贝卡·康斯布鲁克、海莉·卡特、蔡斯·拉孔布、伊蒂·比斯特、佩特萨迈·维莱恰克、扎赫拉·安德森、李晨秀、保罗·布林加斯、金伯利·阿拉尔孔、贝利·奈特、梅西·拉达奇、凯瑟琳·巴特曼、盖琳·科佩克-贝利沃、达尔顿·查普曼、乔舒亚·本内特、阿比盖尔·B·文图拉、古斯塔沃·M·卡纳莱斯、穆塔帕·高瓦、克里安妮·A·杰克逊、罗丹特·卡圭亚特、安珀·布朗、道格拉斯·加尼尼·达席尔瓦、哲远·郭、沙希德·阿卜杜勒哈克、莉莲·R·克鲁格、迈尔斯·甘德尔、恩京·亚皮奇、乔舒亚·迈尔、莎罗尔·巴查斯\n[bioRxiv（2023）：2023-01](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.08.523187v4) • [数据](https:\u002F\u002Fgithub.com\u002FAbSciBio\u002Funlocking-de-novo-antibody-design) • [新闻](https:\u002F\u002Fwww.genengnews.com\u002Ftopics\u002Fdrug-discovery\u002Fantibodies\u002Fabsci-eyes-ind-for-platforms-first-de-novo-antibody-within-two-years\u002F) • [博客](https:\u002F\u002Fwww.science.org\u002Fcontent\u002Fblog-post\u002Fcomputing-our-way-antibodies) • 商业化\n\n**一种用于锌指蛋白设计的通用深度学习模型，可实现转录因子重编程**\n大卫·M·伊奇川、奥萨马·阿卜丁、纳德尔·阿莱拉苏尔、曼朱纳塔·科根努鲁、艾普丽尔·L·穆勒、韩文、大卫·O·吉甘蒂、格雷戈里·W·戈德堡、萨曼莎·亚当斯、杰弗里·M·斯宾塞、罗齐塔·拉扎维、萨特拉·尼姆、洪正、考特妮·吉翁科、芬尼根·T·克拉克、阿列克谢·斯特罗卡奇、蒂莫西·R·休斯、蒂莫泰·利奥内、米科·泰帕莱、菲利普·M·金和马库斯·B·诺耶斯\n[Nat Biotechnol（2023）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-022-01624-4)\n\n**XuperNovo®\u002FProteinGPT**\nXtalPi\n[新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs?__biz=MzI4MzUwNjI5OQ==&mid=2247499137&sn=d8c9e006cdb131dcf5639db6824bb0e3&chksm=eb8b1e95dcfc97835268d9e66636e63a4c6eb2f6fde780a4d45180872ea8d79bbd1d29363aff) • [新闻2](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002Fh_mpZXnQQ_o8vSWzXl3wcQ) • [官网](https:\u002F\u002Fwww.xtalpi.com\u002Fen\u002Fmacromolecular-drug-discovery) • 商业化\n\n**评估提示调优在条件蛋白序列生成中的应用**\n安德烈娅·纳坦森、凯文·克莱因、伯恩哈德·Y·雷纳德、梅拉尼亚·诺维茨卡、雅库布·M·巴托舍维奇\n[bioRxiv 2023.02.28.530492](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.02.28.530492v1) • [代码](https:\u002F\u002Fgitlab.com\u002Fdacs-hpi\u002Fprotein-prompt-tuning)\n\n**AB-Gen：基于生成式预训练Transformer和深度强化学习的抗体文库设计**\n肖鹏·徐、天田·徐、觉晓·周、星宇·廖、若驰·张、宇·王、陆·张、欣·高\n[bioRxiv 2023.03.17.533102](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.17.533102v1) • [代码](https:\u002F\u002Fgithub.com\u002Fcharlesxu90\u002Fab-gen) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F03\u002F21\u002F2023.03.17.533102\u002FDC1\u002Fembed\u002Fmedia-1.docx) • [数据](https:\u002F\u002Fzenodo.org\u002Frecord\u002F7657016)\n\n**基于深度学习和对抗性注意力神经网络的无监督跨域翻译及其在音乐启发的蛋白质设计中的应用**\n布勒，马库斯·J\n[Patterns 4.3（2023）](https:\u002F\u002Fwww.cell.com\u002Fpatterns\u002Ffulltext\u002FS2666-3899(23)00023-5) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FAttentionCrossTranslation)\n\n**ProtFIM：基于蛋白质语言模型的中间填充式蛋白序列设计**\n李、尤翰和哈孙·于\n[arXiv预印本 arXiv:2303.16452（2023）](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2303.16452.pdf)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=9XAZBUfnefS)\n\n**REXzyme：用于生成自然界中不存在的新酶的翻译机器**\n塞巴斯蒂安·林德纳、迈克尔·海因辛格、诺埃利亚·费鲁兹\n论文即将发表 • [Hugging Face](https:\u002F\u002Fhuggingface.co\u002FAI4PD\u002FREXzyme)\n\n**一种通用的蛋白质设计机器学习模型，可生成功能性的从头设计蛋白质**\n蒂莫西·P·赖利、普里亚·卡兰塔里、伊斯梅尔·纳德里、库希亚尔·阿齐米安、凯茜·Y·魏、奥列格·马图索夫斯基、穆罕默德·S·帕尔萨\n[bioRxiv 2025.03.21.644400](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.21.644400v1) • [新闻](https:\u002F\u002Fmedium.com\u002F310-ai\u002Fmpm4-ai-text2protein-breakthrough-tackles-the-molecule-programming-challenge-870045a8c1ad) • [仓库](https:\u002F\u002F310.ai\u002Fmpm\u002Frepo) • 商业化\n\n**利用对比语言建模为构象多样的靶标设计从头合成的肽类结合剂**\n苏哈斯·巴特、卡良·帕莱普、劳伦·洪、乔伊·毛、田正·叶、蕾玛·艾耶尔、林·赵、天来·陈、索菲娅·文科夫、里奥·沃森、田王、迪维亚·斯里贾伊、文卡塔·斯里卡尔·卡维拉尤尼、克谢尼娅·霍利娜、施雷·戈埃尔、普拉纳伊·武雷、阿尼鲁达·H·德什潘德、斯科特·索德林、马修·德丽莎、普拉南·查特吉\n[bioRxiv 2023.06.26.546591](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.26.546591v2) • [代码](https:\u002F\u002Fzenodo.org\u002Fdoi\u002F10.5281\u002Fzenodo.10971077) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F22\u002F2023.06.26.546591\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**xTrimoPGLM：统一的1000亿参数规模预训练Transformer，用于破译蛋白质的语言**\n博·陈、兴义·程、李傲·耿阳、申·李、新·曾、博彦·王、龚·景、迟明·刘、奥汉·曾、宇晓·董、杰·唐、乐·宋\n[bioRxiv 2023.07.05.547496](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.05.547496v1)\u002F[Nat Methods（2025）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-025-02636-z) • [新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FXQn8je49z23UYby8pR7fkA) • [官网](https:\u002F\u002Fwww.biomap.com\u002Faigp-light-beta\u002Fform) • [代码](https:\u002F\u002Fgithub.com\u002Fbiomap-research\u002FxTrimoPGLM) • [模型](https:\u002F\u002Fhuggingface.co\u002Fbiomap-research) • 商业化\n\n**TULIP——一种基于Transformer的无监督语言模型，用于相互作用的肽和T细胞受体，可泛化至未见表位**\n巴特勒米·梅纳尔-皮加诺、克里斯托夫·费瑙尔、马丁·魏格特、亚历山德拉·M·瓦尔察克、蒂埃里·莫拉\n[bioRxiv 2023.07.19.549669](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.19.549669v1) • [代码](https:\u002F\u002Fgithub.com\u002Fbarthelemymp\u002FTULIP-TCR\u002F)\n\n**利用小型蛋白质语言模型高效准确地生成序列**\n雅伊萨·塞拉诺、塞尔吉·罗达、维克托·瓜利亚尔、阿莱克西斯·莫利纳\n[bioRxiv 2023.08.04.551626](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.04.551626v1)\n\n**利用实验室数据结合语言模型指导设计提升抗体亲和力**\n本·克劳斯、苏布·苏布拉马尼安、汤姆·袁、玛丽莎·杨、亚伦·萨托、尼基尔·奈克\n[bioRxiv 2023.09.13.557505](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.13.557505v1)\n\n**NL2ProGPT：驯服大型语言模型以实现对话式蛋白质设计**\n匿名\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=sFJr7okOBi)\n\n**PepMLM：通过掩码语言模型进行靶向序列条件下的肽结合物生成**\n陈天来、萨拉·佩尔采姆利迪斯、里奥·沃森、文卡塔·斯里卡尔·卡维拉尤尼、艾什莉·许、普拉纳伊·武雷、里沙布·普卢古尔塔、索菲娅·文科夫、劳伦·洪、王天、维维安·尤迪斯特拉、埃琳娜·哈雷尔、赵琳、普拉南·查特吉\n[arXiv:2310.03842](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.03842) • [代码](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fpepmlm)\n\n**利用预训练生成式大型语言模型从头设计抗体CDRH3**\n何浩怀、何兵、关磊、赵宇、陈冠兴、朱庆戈、陈育谦、李婷、姚建华\n[bioRxiv 2023.10.17.562827](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.17.562827v1)\u002F[Nature Communications 15.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-50903-y) • [代码](https:\u002F\u002Fgithub.com\u002FTencentAILabHealthcare\u002FPALM) • [数据](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.7794583)\n\n**SaLT&PepPr是一种界面预测型语言模型，用于设计肽引导的蛋白质降解剂**\n加里克·布里希、叶天正、劳伦·洪、王天、康纳·蒙蒂切洛、娜塔莉亚·洛佩斯-巴博萨、索菲娅·文科夫、维维安·尤迪斯特拉、赵琳、埃琳娜·哈雷尔、陈天来、萨拉·佩尔采姆利迪斯、卡良·帕莱普、苏哈斯·巴特、贾亚尼·克里斯托弗、李欣宁、刘彤、张苏、莉莲·彼得森、马修·P·德丽莎以及普拉南·查特吉\n[Commun Biol 6, 1081 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42003-023-05464-z) • [代码](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fsaltnpeppr)\n\n**ProteinNPT：利用非参数化Transformer改进蛋白质性质预测与设计**\n帕斯卡尔·诺丁、鲁本·魏茨曼、黛博拉·S·马克斯、亚林·加尔\n[bioRxiv 2023.12.06.570473](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.06.570473v1) • [代码](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FProteinNPT)\n\n**大型语言模型在蛋白质设计与建模中的前景**\n乔治欧·瓦伦蒂尼、达里奥·马尔基奥迪、杰西卡·格利奥佐、马尔科·梅西蒂、毛里西奥·索托-戈麦斯、阿尔贝托·卡布里、贾斯汀·里斯、埃莱娜·卡西拉吉以及彼得·N·罗宾逊\n[Frontiers in Bioinformatics 3 (2023)](https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffbinf.2023.1304099\u002Ffull)\n\n**基于检索与领域反馈的对话式药物编辑**\n刘盛超、王炯晓、杨一金、王成鹏、刘玲、郭宏宇、肖朝伟\n[ICLR (2024)](https:\u002F\u002Fopenreview.net\u002Fforum?id=yRrPfKyJQ2) • [代码](https:\u002F\u002Fgithub.com\u002Fchao1224\u002FChatDrug) • [网站](https:\u002F\u002Fchao1224.github.io\u002FChatDrug)\n\n**ProtAgents：结合物理学与机器学习的大型语言模型多智能体协作进行蛋白质发现**\n阿里雷扎·加法罗拉希、马库斯·J·布勒\n[arXiv:2402.04268](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.04268) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProtAgents)\n\n**利用语言模型设计蛋白质**\n鲁弗洛，J.A.，马达尼，A\n[Nat Biotechnol 42, 200–202 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02123-4) • 综述\n\n**ProLLaMA：用于多任务蛋白质语言处理的蛋白质大型语言模型**\n吕志浩、林宗英、李浩、刘宇阳、崔嘉熙、陈育谦、袁立、田永红\n[arXiv:2402.16445](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.16445) • [代码](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.16445.pdf)\n\n**将机器学习与基于结构的蛋白质设计相结合，以预测和工程化蛋白质的翻译后修饰**\n莫里茨·埃尔特尔、维克拉姆·希普尔·穆利根、杰克·B·麦圭尔、谢尔盖·雷斯科夫、罗科·莫雷蒂、托本·席夫纳、延斯·迈勒、克拉拉·T·舍德尔\n[PLOS Computational Biology 20(3): e1011939](https:\u002F\u002Fjournals.plos.org\u002Fploscompbiol\u002Farticle?id=10.1371\u002Fjournal.pcbi.1011939) • [代码](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002FPTMPrediction)\n\n**以进化规模模型（ESM）为约束，结合Rosetta序列设计与蛋白质语言模型预测**\n莫里茨·埃尔特尔、延斯·迈勒以及克拉拉·T·舍德尔\n[ACS Synth. Biol. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.3c00753) • [代码](https:\u002F\u002Fgithub.com\u002Fmeilerlab\u002FPLM_restraint)\n\n**利用AI和胚系模板设计抗原特异性抗体CDRH3序列**\n托马·M·马里诺夫、亚历山德拉·A·阿布-什迈斯、亚历克西斯·K·扬克、伊韦林·S·格奥尔基耶夫\n[bioRxiv 2024.03.22.586241](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.22.586241v1.full)\n\n**通过建模CRISPR-Cas序列宇宙设计高功能基因组编辑工具**\n杰弗里·A·鲁弗洛、斯蒂芬·奈法奇、约瑟夫·加拉格尔、阿迪约特·巴特纳加尔、乔尔·比泽尔、里法特·侯赛因、乔丹·罗斯、珍妮弗·叶普、艾米丽·希尔、马丁·佩塞萨、亚历山大·J·米斯克、彼得·卡梅隆、阿里·马达尼\n[bioRxiv 2024.04.22.590591](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.22.590591v1) • [代码](https:\u002F\u002Fgithub.com\u002FProfluent-AI\u002FOpenCRISPR)\n\n**基于局部域对齐的功能性蛋白质设计**\n袁超浩、李松友、叶格彦、张义坤、黄龙凯、黄文兵、刘伟、姚建华、荣宇\n[arXiv:2404.16866](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.16866)\n\n**蛋白质结构的连续语言**\n卢卡斯·比列拉、安东·奥雷斯坦、阿隆·斯塔尔马克、佐藤健太、马特乌什·卡杜克、本·默雷尔\n[bioRxiv 2024.05.11.593685](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.11.593685v1) • [代码](https:\u002F\u002Fgithub.com\u002FMurrellGroup\u002FInvariantPointAttention.jl)\n\n**由功能重要位点和小分子底物引导的生成式酶设计**\n宋振桥、赵云龙、石文贤、金文功、杨洋、李磊\n[arXiv:2405.08205](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.08205)\u002F[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fpdf\u002Fb349f5504ef1e6143231064979e2e96feaf5a6a9.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FLeiLiLab\u002FEnzyGen)\n\n**用于抗体序列理解的生成式基础模型**\n贾斯汀·巴顿、阿雷塔斯·加斯帕里乌纳斯、大卫·A·亚丁、豪尔赫·迪亚斯、弗朗西斯卡·L·奈斯、丹妮尔·H·明斯、奥利维亚·斯纳登、切尔西·波瓦尔、萨拉·瓦列·托马斯、哈里·多布森、詹姆斯·HR·法默里、李镇宇、雅各布·D·加尔森\n[bioRxiv 2024.05.22.594943](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.22.594943v1) • [huggingface](https:\u002F\u002Fhuggingface.co\u002Falchemab)\n\n**用于现实抗体设计的解耦序列与结构生成**\n金娜英、金珉洙、安成洙、朴晋九\n[arXiv:2402.05982](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.05982)\u002F[正在TMLR审稿中](https:\u002F\u002Fopenreview.net\u002Fforum?id=CTkABQvnkm) • [代码](https:\u002F\u002Fgithub.com\u002Flkny123\u002FASSD_public)\n\n**解决抗体胚系偏倚及其对语言模型的影响，以改进抗体设计**\n托比亚斯·H·奥尔森、伊恩·H·莫尔、夏洛特·M·迪恩\n[bioRxiv 2024.02.02.578678](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.02.578678v1)\u002F[Bioinformatics (2024): btae618](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Farticle\u002F40\u002F11\u002Fbtae618\u002F7845256) • [代码](https:\u002F\u002Fgithub.com\u002Foxpig\u002FAbLang2)\n\n**MoFormer：基于条件Transformer联合多模态融合描述符的多目标抗菌肽生成**\n王丽、付向征、杨嘉豪、张欣怡、叶秀才、刘一平、樱井哲也、曾祥祥\n[arXiv:2406.00735](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.02610)\n\n**HELM-GPT：利用生成式预训练Transformer进行从头宏环肽设计**\n许晓鹏、许晨程、何文佳、魏乐松、李浩洋、周珏骁、张若驰、王宇、熊元鹏、高鑫\n[Bioinformatics (2024): btae364](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtae364\u002F7691994) • [代码](https:\u002F\u002Fgithub.com\u002Fcharlesxu90\u002Fhelm-gpt)\n\n**统一序列、结构与描述，实现任意蛋白质生成——基于大型多模态模型HelixProtX**\n陈志远、陈天昊、谢成刚、薛阳、张晓楠、周景波、方小敏\n[arXiv:2407.09274](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.09274) • [代码](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FPaddleHelix\u002Ftree\u002Fdev\u002Fapps\u002Fhelixprotx)\n\n**人工智能驱动科学发现时代下，以基础模型方法指导抗菌肽设计**\n王继科、冯建文、康宇、潘培臣、葛静轩、王燕、王明阳、吴振兴、张星彩、于佳萌、张旭君、王天悦、温利荣、严广宁、邓亚峰、史辉、谢昌宇、蒋志辉、侯廷军\n[arXiv:2407.12296](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.12296) • [代码](https:\u002F\u002Fgithub.com\u002Fjkwang93\u002FAMP-Designer)\n\n**条件序列—结构整合：一种用于精准抗体工程与亲和力优化的新方法**\n贝尼亚明·贾米阿拉赫马迪、马赫穆德·查曼卡赫、穆罕默德·科汉德尔、阿里·戈德西\n[bioRxiv 2024.07.16.603820](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.16.603820v1) • [博客](https:\u002F\u002Fsimplescience.ai\u002Fen\u002F2024-08-28-advancements-in-antibody-design-with-aida-method--an1v4d)\n\n**moPPIt：利用蛋白质语言模型从头生成基序特异性结合体**\n陈彤、张依诺、普拉南·查特吉\n[bioRxiv 2024.07.31.606098](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.31.606098v1) • [代码](https:\u002F\u002Fhuggingface.co\u002FChatterjeeLab\u002FmoPPIt)\n\n**迈向基于自然语言的从头蛋白质设计**\n戴丰源、范玉良、苏瑾、王晨桐、韩晨晨、周锡彬、刘建明、钱慧、王顺志、曾安平、王雅洁、袁发杰\n[bioRxiv 2024.08.01.606258](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.01.606258v5) • [代码](https:\u002F\u002Fgithub.com\u002Fwestlake-repl\u002FDenovo-Pinal) • [演示](http:\u002F\u002Fwww.denovo-pinal.com\u002F)\n\n**利用大型语言模型设计蛋白质：改进与比较分析**\n卡米亚尔·泽纳利普尔、内达·詹希迪、莫妮卡·比安奇尼、马可·马吉尼、马可·戈里\n[arXiv:2408.06396](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.06396) • [代码](https:\u002F\u002Fgithub.com\u002FKamyarZeinalipour\u002Fprotein-design-LLMs)\n\n**使用Raygun微型化、改造并增强天然蛋白质**\n卡皮尔·德夫科塔、庄内大智、毛乔伊、斯科特·H·索德林、罗希特·辛格\n[bioRxiv 2024.08.13.607858](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.13.607858v1) • [代码](https:\u002F\u002Fgithub.com\u002Frohitsinghlab\u002Fraygun)\n\n**TourSynbio：多模态大模型与智能体框架，用于连接文本与蛋白质序列以进行蛋白质工程**\n沈毅青、陈赞、米哈伊尔·马马拉基斯、刘云耕、李天斌、苏延州、何俊俊、皮耶特罗·利奥、王宇光\n[arXiv:2408.15299](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.15299) • [代码](https:\u002F\u002Fgithub.com\u002Ftsynbio\u002FTourSynbio) • [模型](https:\u002F\u002Fhuggingface.co\u002Ftsynbio\u002FToursynbio) • [网站](http:\u002F\u002Fprdtst.tsynbio.com:51443\u002F) • [新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FIROlGdP04uLUUipNAd7YOg) • 商业化\n\n**AbGPT：通过生成式语言建模进行从头抗体设计**\n德斯蒙德·关、阿米尔·巴拉蒂·法里马尼\n[arXiv:2409.06090](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.06090v1) • [代码](https:\u002F\u002Fgithub.com\u002Fdeskk\u002FAbGPT)\n\n**PepINVENT：超越天然氨基酸的生成式肽设计**\n格克切·盖兰、琼·保罗·珍妮特、亚历山德罗·蒂博、何佳真、阿塔纳斯·帕特罗诺夫、米哈伊尔·卡别绍夫、弗洛里安·大卫、维尔加德·切希茨基、奥拉·恩格奎斯特、莱昂纳多·德·玛利亚\n[arXiv:2409.14040](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.14040)\n\n**利用带有适配器的蛋白质语言模型进行条件酶生成**\n杰森·杨、阿迪约特·巴特纳加尔、杰弗里·A·鲁弗洛、阿里·马达尼\n[arXiv:2410.03634](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.03634) • [代码](https:\u002F\u002Fgithub.com\u002FProfluent-Internships\u002FProCALM)\n\n**重新审视机器学习的成功指标：从公平性与可解释性到蛋白质设计**\n弗朗西斯·丁\n[加州大学伯克利分校2024年博士论文](https:\u002F\u002Fwww2.eecs.berkeley.edu\u002FPubs\u002FTechRpts\u002F2024\u002FEECS-2024-156.html) • 博士论文\n\n**利用TransformerBeta计算设计靶向线性肽结合体**\n赵浩文、弗朗切斯科·A·阿普里莱、芭芭拉·布拉维\n[arXiv:2410.16302](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.16302) • [代码](https:\u002F\u002Fgithub.com\u002FHZ3519\u002FTransformerBeta_project)\n\n**用于蛋白质构象生成的结构语言模型**\n陆嘉睿、陈晓音、卢思哲文、施辰策、郭洪宇、约书亚·本吉奥、唐健\n[arXiv:2410.18403](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.18403) • [代码](https:\u002F\u002Fgithub.com\u002Flujiarui\u002Fesmdiff)\n\n**Peptide-GPT：利用生成式预训练Transformer与生物信息学监督进行肽的生成式设计**\n阿尤什·沙阿、查克拉达尔·贡图博伊纳、阿米尔·巴拉蒂·法里马尼\n[arXiv:2410.19222](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.19222) • [代码](https:\u002F\u002Fgithub.com\u002Faayush-shah14\u002FPeptideGPT)\n\n**一种自适应自回归扩散方法，用于设计活性人源化抗体与纳米抗体**\n马健、吴凡迪、徐挺扬、徐少勇、刘伟、迪文·颜、白启峰、姚建华\n[bioRxiv 2024.10.22.619416](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.22.619416v1) • [代码](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002FHuDiff)\n\n**用于蛋白质设计的概念瓶颈语言模型**\n阿亚·阿卜杜勒萨拉姆·伊斯梅尔、图奥马斯·奥伊卡里宁、艾米·王、朱利叶斯·阿德巴约、塞缪尔·斯坦顿、泰勒·乔伦、约瑟夫·克莱因亨茨、艾伦·古德曼、埃克托·科拉达·布拉沃、姜庆贤、内森·C·弗雷\n[arXiv:2411.06090](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.06090)\n\n**利用生成式语言模型从头设计三磷酸异构酶**  \n塞尔吉奥·罗梅罗-罗梅罗、亚历山大·E·布劳恩、蒂莫·科森代、诺埃利亚·费鲁斯、施特芬·施密特、比尔特·霍克尔  \n[bioRxiv 2024.11.10.622869](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.10.622869v1)\n\n**自然语言提示引导新型功能蛋白质序列的设计**  \n尼克沙·普拉利亚克、休·叶、米兰达·摩尔、迈克尔·索科利奇、拉马·兰加纳坦、安德鲁·L·弗格森  \n[bioRxiv 2024.11.11.622734](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.11.622734v1)\n\n**通过提示式语言模型实现多用途可控蛋白质生成**  \n王泽远、陈彬彬、丁可言、曹嘉文、秦明、牛雅丹、庄翔、李晓彤、冯克华、徐通、张宁宇、于浩然、张强、陈华军  \n[bioRxiv 2024.11.17.624051](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.17.624051v1)\n\n**抗病毒肽——生成式预训练变换器（AVP-GPT）：一种基于深度学习的抗病毒肽设计模型，具备高通量发现能力和卓越效力**  \n赵华健、宋耿申  \n[Viruses 16.11 (2024)](https:\u002F\u002Fwww.mdpi.com\u002F1999-4915\u002F16\u002F11\u002F1673)\n\n**泛蛋白质设计学习实现低资源酶设计的任务自适应泛化能力**  \n郑江斌、王戈、张翰、Stan Z. Li  \n[arXiv:2411.17795](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.17795)\n\n**ProtDAT：一种基于任意蛋白质文本描述的统一蛋白质序列设计框架**  \n郭小宇、李一凡、刘源、潘晓勇、沈洪斌  \n[arXiv:2412.04069](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.04069) • [代码](https:\u002F\u002Fgithub.com\u002FGXY0116\u002FProtDAT)\n\n**基于注释指导的蛋白质设计与多级结构域对齐**  \n袁超浩、李松友、叶革彦、张益坤、黄龙凯、黄文兵、刘伟、姚建华、荣宇  \n[arXiv:2404.16866](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.16866)\n\n**用于功能预测和蛋白质设计的开源蛋白质语言模型**  \n希瓦桑卡兰·瓦纳贾·潘迪、巴拉特·拉姆孙达尔  \n[arXiv:2412.13519](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.13519)\n\n**利用超活性转座酶的发现及语言模型引导设计**  \n马克·居埃尔、季米特里耶·伊万契奇、亚历杭德罗·阿古德洛、乔纳森·林德斯特罗姆-沃特里、杰西卡·哈拉巴-华莱士、玛丽亚·加洛、亚历杭德罗·拉赫尔、伊蕾妮·伊格拉斯、费德里科·比列奇、玛尔塔·桑维森特、保罗·佩塔齐、诺埃利亚·费鲁斯、阿文西亚·桑切斯-梅希亚斯、拉维·达斯  \n[预印本](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-5536951\u002Fv1) • [代码](https:\u002F\u002Fgithub.com\u002FIntegra-tx\u002FPiggybac_bioprospecting_pipeline) • 基于Progen2\n\n**利用大型语言模型生成抗原特异性重链-轻链配对抗体序列**  \n佩里·T·瓦斯丁、妮可·V·约翰逊、亚历克西斯·K·扬克、索菲娅·赫尔德、托马·M·马里诺夫、格温·乔丹、莱娜·范登阿贝尔、法尼·潘图利、丽贝卡·A·吉莱斯皮、马修·J·武科维奇、克林顿·M·霍尔特、金正烈、格兰特·汉斯曼、珍妮弗·洛格、海伦·Y·楚、莎拉·F·安德鲁斯、真守兼喜、朱塞佩·A·索托、泰德·M·罗斯、丹尼尔·J·谢沃德、杰森·S·麦克莱伦、亚历山德拉·A·阿布-什迈斯、伊韦林·S·格奥尔基耶夫  \n[bioRxiv 2024.12.20.629482](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.20.629482v1) • [补充资料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F22\u002F2024.12.20.629482\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于LLM偏好优化的可控蛋白质序列生成**  \n刘向宇、刘毅、陈思磊、胡伟  \n[arXiv:2501.15007](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.15007) • [代码](https:\u002F\u002Fgithub.com\u002Fnju-websoft\u002FCtrlProt)\n\n**基于LLM基础模型发现具有显著抗菌效力的抗菌肽**  \n王继科、冯建文、康宇、潘培晨、葛静萱、王燕、王明阳、吴振兴、张兴才、于佳萌、张旭俊、王天悦、文立荣、严广宁、邓亚峰、石慧、谢昌宇、蒋志辉以及侯廷军  \n[Sci. Adv.11,eads8932(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fsciadv.ads8932) • [代码](https:\u002F\u002Fgithub.com\u002Fjkwang93\u002FAMP-Designer)\n\n**CasGen：一种具有分类与基于间隔优化的CRISPR Cas蛋白设计正则化生成模型**  \n巴拉尼·南米、文迪·M·贾亚辛格-阿拉奇奇格、西塔·希里莎·马杜古拉、玛丽亚·阿蒂莱斯、夏琳·诺根·拉德勒、泰勒·范、刘津、王寿义  \n[bioRxiv 2025.02.28.640911](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.28.640911v1) • [代码](https:\u002F\u002Fgithub.com\u002Fshouyisxty\u002FCasGen)\n\n**用于蛋白质设计的语言模型**  \n李镇燮、奥斯马·阿卜丁和菲利普·M·金  \n[Current Opinion in Structural Biology 92 (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0959440X25000454) • 综述\n\n**基于结构约束的生成式语言模型进行抗原特异性抗体的从头设计**  \n贾雨然、何冰、吕天旭、杨晓、赵天一、姚建华  \n[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=8F2JrQC2DJ)\n\n**SOAPI：基于连体模型生成避免脱靶效应的蛋白质相互作用**  \n索菲娅·文科夫、奥斯卡·戴维斯、亚历山大·汤、乔伊·博斯、普拉南·查特吉  \n[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=mUp7mfNfXz)\n\n**Prot42：一类新型蛋白质语言模型，用于目标导向的蛋白质结合剂生成**  \n穆罕默德·阿曼·赛义德、恩京·泰金、玛丽亚姆·纳迪姆、南希·A·埃尔纳克、阿汗·辛格、娜塔莉娅·瓦西里耶娃、布尔巴巴·本·阿莫尔  \n[arXiv:2504.04453](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.04453) • [模型](https:\u002F\u002Fhuggingface.co\u002Finceptionai)\n\n**定制蜘蛛丝：基于机械性能条件的生成模型在蛋白质工程中的应用**  \n尼鲁·杜贝、埃琳·卡尔松、米格尔·安赫尔·雷东多、约翰·雷梅加德、安娜·瑞辛、赫德维格·谢尔斯特伦  \n[arXiv:2504.08437](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.08437) • 基于ProtGPT2\n\n**用于可控蛋白质生成和表征学习的多模态基础模型**  \n小提摩西·费伊·张二世、特里斯坦·贝普勒  \n[博客](https:\u002F\u002Fwww.openprotein.ai\u002Fa-multimodal-foundation-model-for-controllable-protein-generation-and-representation-learning) • 商业化\n\n**阐明多模态蛋白质语言模型的设计空间**  \n谢承延、王新友、张岱恒、薛冬宇、叶飞、黄书坚、郑再祥、顾全全  \n[arXiv:2504.11454](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.11454)\n\n**规模扩展解锁更广泛的蛋白质生成与更深层次的功能理解**  \n阿迪约特·巴特纳加尔、萨尔塔克·贾因、乔尔·比泽尔、塞缪尔·C·库兰、亚历山大·M·霍夫纳格尔、凯尔·青、迈克尔·马尔廷、斯蒂芬·奈法奇、杰弗里·A·鲁弗洛、阿里·马达尼  \n[bioRxiv 2025.04.15.649055](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.15.649055v1) • [代码](https:\u002F\u002Fgithub.com\u002FProfluent-AI\u002Fprogen3)\n\n**Sparks：多智能体人工智能模型揭示蛋白质设计原则**  \n阿里雷扎·加法罗拉希、马库斯·J·布勒  \n[arXiv:2504.19017](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.19017) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FSparks\u002F)\n\n**基于动态蛋白质词汇表的蛋白质设计**  \n刘诺威、匡家豪、刘艳婷、孙长志、季涛、吴元彬、满兰  \n[arXiv:2505.18966](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.18966) • [代码](https:\u002F\u002Fgithub.com\u002FsornkL\u002FProDVa)\n\n**ProtMamba：一种兼顾同源性但无需比对的蛋白质状态空间模型**  \n达米亚诺·斯加博萨、西里尔·马尔布朗克、安妮-弗洛伦斯·比特博尔  \n[bioRxiv 2024.05.24.595730](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.24.595730v4) • [代码](https:\u002F\u002Fgithub.com\u002FBitbol-Lab\u002FProtMamba)\n\n**自然语言引导的配体结合蛋白设计**  \n宋振乔、拉米思·赫蒂亚拉奇、李川、谢建文、李磊  \n[arXiv:2506.09332](https:\u002F\u002Fwww.arxiv.org\u002Fabs\u002F2506.09332)\n\n**面向序列设计的蛋白质语言模型可解释性研究**  \n安德烈娅·洪克林格、诺埃利亚·费鲁兹  \n[arXiv:2506.19532](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.19532)\n\n**Metalorian：基于分类器引导扩散采样的重金属性结合肽从头生成**  \n张一诺、迪维娅·斯里贾伊、扎卡里·奎因、普拉南·查特吉  \n[bioRxiv 2025.07.10.664242](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.10.664242v1) • 基于ESM2\n\n**ProteinReasoner：具有思维链推理能力的多模态蛋白质语言模型，用于高效蛋白质设计**  \n刘超中、曹琳琳、季绍敏、王浩、蒋涛睿、高章阳、郭宇成、杨明、张晓明  \n[bioRxiv 2025.07.21.665832](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.21.665832v1)\n\n**戴霍夫图谱：扩展序列多样性以提升蛋白质生成质量**  \n凯文·K·杨、萨拉·阿拉姆达里、亚历克斯·J·李、凯莉·凯马克-洛夫莱斯、萨米尔·查尔、加里克·布里克西、卡尔莱斯·多明戈-恩里奇、王晨彤、吕苏悦、尼科洛·富西、尼尔·滕亨霍尔茨、艾娃·P·阿米尼  \n[bioRxiv 2025.07.21.665991](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.21.665991v1) • [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdayhoff) • [数据集](https:\u002F\u002Fhuggingface.co\u002Fcollections\u002Fmicrosoft\u002Fdayhoff-atlas-6866d679465a2685b06ee969)\n\n**AI智能体虚拟实验室设计出新型SARS-CoV-2纳米抗体**  \n凯尔·斯旺森、韦斯利·吴、纳什·L·布拉昂、约翰·E·帕克及詹姆斯·邹  \n[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09442-9)\n\n**通过知识偏好优化提升蛋白质生成的安全性和可控性**  \n王宇豪、丁可然、冯克华、王泽远、秦明、李晓彤、张强、陈华俊  \n[arXiv:2507.10923](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.10923) • [代码](https:\u002F\u002Fgithub.com\u002FHICAI-ZJU\u002FKPO)\n\n**基于掩码语言模型的目标序列条件化肽类结合物设计**  \n陈天来、扎卡里·奎因、玛德琳·杜马斯、彭克里斯蒂娜、洪劳伦、洛佩斯-冈萨雷斯·莫伊塞斯、梅斯特雷·亚历山大、沃森·里奥、文科夫·索菲娅、赵琳、吴建利、斯塔夫兰德·奥黛丽、谢珀斯-丘·真弓、王天子、斯里贾伊·迪维娅、蒙蒂切洛·康纳、普拉奈·武雷、普卢古尔塔·里沙布、佩尔采姆利迪斯·萨拉、霍利娜·克谢尼娅、戈埃尔·施雷伊、德丽莎·马修·P、阿什利·齐·詹-坦、特鲁安·雷伊、阿吉拉尔·赫克托·C及查特吉·普拉南  \n[Nat Biotechnol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-025-02761-2) • [代码](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Fpepmlm) • [模型](https:\u002F\u002Fhuggingface.co\u002FChatterjeeLab\u002FPepMLM-650M)\n\n**ICEPIC：从序列中发现冰结合蛋白的工具包**  \n张吉米、苏布拉克什米·苏雷什、施穆埃尔·格莱泽、索菲娅·尤文斯、阿亚里亚·文卡特、瓦伦丁·祖尔科韦尔、托马斯·比尔纳基、温丹尼尔、李凯瑟琳、埃斯拉米·穆罕默德、巴克豪特-怀特·苏珊  \n[bioRxiv 2025.08.08.669420](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.08.669420v2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F08\u002F14\u002F2025.08.08.669420\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fnetrias\u002FICEPIC)\n\n**基于EiRA的改进型多模态蛋白质语言模型驱动的通用生物分子结合蛋白设计**  \n曾文武、邹海涛、李晓宇、王小琪、彭绍亮  \n[bioRxiv 2025.09.02.673615](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.02.673615v2) • [代码](https:\u002F\u002Fgithub.com\u002Fpengsl-lab\u002FEiRA)\n\n**LSMTCR：用于表位特异性T细胞受体从头设计的可扩展多架构模型**  \n张瑞豪、刘晓  \n[arXiv:2509.07627](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.07627)\n\n**PRIME：用于协调蛋白质工程中动态计算工作流的多智能体环境**  \n周宇洋、苏瑾、张嘉伟、胡万阳、陶天立、李冠琦、周锡彬、范力、袁发杰  \n[bioRxiv 2025.09.22.677756](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.22.677756v1)\n\n**使用Agent Rosetta进行蛋白质设计：专用科学智能体的案例研究**  \n雅各波·特内吉、塔尼亚·马尔瓦、阿尔贝托·比埃蒂、P·道格拉斯·伦弗鲁、维克拉姆·希普尔·穆利根、西亚瓦什·戈尔卡尔  \n[NeurIPS 2025海报](https:\u002F\u002Fopenreview.net\u002Fforum?id=7U3RQRisyb)\n\n**超活性转座酶的发现及其蛋白质语言模型指导下的设计**  \n季米特里耶·伊万契奇、亚历杭德罗·阿古德洛、乔纳森·林德斯特罗姆-沃特兰、杰西卡·哈拉巴-华莱士、玛丽亚·加洛、拉维·达斯、亚历杭德罗·拉格尔、豪尔赫·埃雷罗-维森特、伊蕾妮·伊格拉斯、费德里科·比列奇、玛尔塔·桑维森特-加西亚、保罗·佩塔齐、诺埃利亚·费鲁兹、阿文西亚·桑切斯-梅希亚斯及马克·圭尔  \n[Nat Biotechnol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-025-02816-4) • [代码](https:\u002F\u002Fgithub.com\u002FIntegra-tx\u002FPiggybac_bioprospecting_pipeline) • 基于Progen2\n\n**通过合成与可编程的功能特征进行抗体Fc变体的生成式设计**  \n爱德华·B·欧文、托马斯·比基亚斯、埃万格洛斯·斯坦科普洛斯、莱斯特·弗雷、尼克·舒尔曼、安玛丽·K·沃伦德、海伦·施密德、迪米特里·库科斯、杨慧琳、米农·梅森、威廉·凯尔顿、赛·T·雷迪  \n[bioRxiv 2025.10.10.681689](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.10.681689v1)\n\n**推理模型在蛋白质从头设计中优于标准语言模型**  \n阿尔弗雷德·格赖森、丛龙飞、格赖森·小珀、谢尔盖·奥夫钦尼科夫  \n[Agents4Science](https:\u002F\u002Fopenreview.net\u002Fforum?id=yXYEbPQp8x)\n\n**DLFea4AMPGen：通过整合深度学习模型所学特征进行抗菌肽的从头设计**  \n高汉、关菲菲、罗博文、张东东、刘伟、沈玉英、范凌熙、徐国顺、王元、涂涛、吴宁峰、姚斌、罗慧英、滕岳、田健及黄霍庆  \n[Nat Commun 16, 9134 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-64378-y) • [代码](https:\u002F\u002Fgithub.com\u002Fhgao12345\u002FDLFea4AMPGen)\n\n**高性能Sec型信号肽的混合深度学习架构从头设计**  \n戴小鹏、孟向春、周英俊、李志敏、于继、乌尔里希·施瓦内贝格、李宗林  \n[JACS Au 5.10 (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacsau.5c00757) • [代码](https:\u002F\u002Fgithub.com\u002Flzlinn801\u002FSPgo)\n\n**MOFormer：基于帕累托多目标Transformer导航抗菌肽设计空间**  \n王丽、傅向正、杨佳豪、张欣怡、叶秀才、樱井哲也、曾祥祥、刘一平  \n[Briefings in Bioinformatics 26.6 (2025)](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F26\u002F6\u002Fbbaf376\u002F8315069) • [代码](https:\u002F\u002Fgithub.com\u002Fwl-wl\u002FMOFormer\u002Ftree\u002Fmaster)\n\n**利用大型语言模型生成抗原特异性配对链抗体**  \n佩里·T·瓦斯丁、妮可·V·约翰逊、亚历克西斯·K·扬克、索菲娅·赫尔德、托马·M·马里诺夫、格温·约尔丹、丽贝卡·A·吉莱斯皮、勒娜·范登阿贝尔、法尼·潘图利、奥利维亚·C·鲍尔斯、马修·J·武科维奇、克林顿·M·霍尔特、郑烈尔·金、格兰特·汉斯曼、珍妮弗·洛格、海伦·Y·楚、莎拉·F·安德鲁斯、真守兼喜、朱塞佩·A·索托、泰德·M·罗斯、丹尼尔·J·舍沃德、杰森·S·麦克莱伦、亚历山德拉·A·阿布-施迈斯以及伊韦林·S·格奥尔基耶夫  \n[Cell（2025）](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(25)01135-3) • [代码](https:\u002F\u002Fgithub.com\u002FIGlab-VUMC\u002FMAGE_ab_generation) • [模型](https:\u002F\u002Fhuggingface.co\u002Fperrywasdin\u002FMAGE_V1)\n\n**超越蛋白质语言模型：用于机制性酶设计的代理式LLM框架**  \n布鲁诺·雅各布、库什布·阿加瓦尔、马塞尔·贝尔、彼得·赖斯、西蒙内·劳盖伊  \n[arXiv:2511.19423](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.19423v1)\n\n**通用型大型语言模型，如DeepSeek V3.2，已具备蛋白质设计能力**  \n李嘉伟、董欣秀  \n[bioRxiv 2025.11.23.689994](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.23.689994v1) • [代码](https:\u002F\u002Fgithub.com\u002FLIJIAWEI040301\u002FGLLMs_for_protein)\n\n**基于实验验证的大型语言模型智能体群用于蛋白质序列设计**  \n菲奥娜·Y·王、迪·盛·李、大卫·L·卡普兰、马库斯·J·布勒  \n[arXiv:2511.22311](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.22311v1) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FProteinSwarm)\n\n**蛋白质语言模型的自蒸馏微调提升蛋白质设计的通用性**  \n阿敏·塔瓦科利、拉斯万特·穆鲁甘、奥赞·戈克代米尔、阿尔文德·拉马纳坦、弗朗西斯·阿诺德、阿尼玛·阿南德库马尔  \n[arXiv:2512.09329](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.09329v1)\n\n**TCRdesign：一种抗原特异性生成式语言模型，用于从头设计T细胞受体**  \n李晓坤、杨强、徐龙、董卫和、王宽泉、董苏宇、王伟、罗功宁、张宪宇、杨天松、高鑫、王国华  \n[Briefings in Bioinformatics，第26卷，第6期，2025年11月，bbaf691](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F26\u002F6\u002Fbbaf691\u002F8405050) • [数据](https:\u002F\u002Fgithub.com\u002Flixiaokun2020\u002FTCRdesign) • [代码](https:\u002F\u002Fgithub.com\u002Flixiaokun2020\u002FTCRdesign)\n\n**TcrDesign：表位特异性全长T细胞受体的从头设计**  \n刁凯旋、陈静、赵向宇、吴涛、邱蝶、王伟良、王浩鹏、刘雪松  \n[bioRxiv 2026.01.15.699824](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.15.699824v1) • [代码](https:\u002F\u002Fgithub.com\u002FXSLiuLab\u002FTcrDesign)\n\n**TCRAD：面向抗原靶向的T细胞受体设计端到端框架**  \n李晨奥、郭耀驰、关欣、陈辉、张勇、杨鹏远、楼继忠  \n[bioRxiv 2026.01.21.700513](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.21.700513v1)\n\n**从头功能蛋白质序列生成：通过再生与大型语言模型克服数据稀缺性**  \n任晨宇、何大海、黄健  \n[Briefings in Bioinformatics](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F27\u002F2\u002Fbbag095\u002F8510708) • [数据](https:\u002F\u002Fgithub.com\u002FChenyuzZZ73\u002FProteinRG\u002Fdata)\n\n### 5.5 基于贝叶斯的方法\n\n**用于组合型贝叶斯优化的乐观博弈及其在蛋白质设计中的应用**\n梅利斯·伊莱达·巴尔、皮埃尔·朱塞佩·塞萨、莫米尔·穆特尼、安德烈亚斯·克劳斯\n[NeurIPS 2023 实际世界中的自适应实验设计与主动学习研讨会，2023年](https:\u002F\u002Fopenreview.net\u002Fforum?id=ScOvmGz4xH)\u002F[arXiv:2409.18582](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.18582)\n\n**利用机器学习发现酶的新肽类底物**\n洛里莉·塔洛林、王嘉磊、金宇柱、斯瓦加特·萨胡、尼古拉斯·M·科萨、杨璞、马修·汤普森、迈克尔·K·吉尔森、彼得·I·弗雷泽、迈克尔·D·伯卡特及内森·C·吉安内斯基\n[Nature Communications 9.1 (2018)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-018-07717-6) • [代码](https:\u002F\u002Fgithub.com\u002Fpeter-i-frazier\u002Fpool)\n\n**基于批处理贝叶斯优化的生物序列设计**\n大卫·贝兰格、苏哈尼·沃拉、泽尔达·马里埃特、拉米娅·德什潘德、大卫·多汉、克里斯托夫·安格缪勒、凯文·墨菲、奥利维埃·沙佩尔、露西·科尔韦尔\n[机器学习与物理科学研讨会（NeurIPS 2019）](https:\u002F\u002Fml4physicalsciences.github.io\u002F2019\u002Ffiles\u002FNeurIPS_ML4PS_2019_141.pdf)\n\n**利用贝叶斯学习进行晶格蛋白设计**\n高桥、友荣、乔治·奇肯吉和德喜时田\n[arXiv:2003.06601](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.06601)\u002F[Physical Review E 104.1 (2021): 014404](https:\u002F\u002Fjournals.aps.org\u002Fpre\u002Fabstract\u002F10.1103\u002FPhysRevE.104.014404)\n\n**接下来是什么序列？用于蛋白质序列贝叶斯优化的预训练集成模型**\n齐悦·杨、卡塔琳娜·A·米拉斯、安德鲁·D·怀特\n[bioRxiv 2022.08.05.502972](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.05.502972v2) • [代码](https:\u002F\u002Fgithub.com\u002Fur-whitelab\u002Fwazy) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F08\u002F06\u002F2022.08.05.502972\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fur-whitelab\u002Fwazy\u002Fblob\u002Fmaster\u002Fcolab\u002FWazyAlphaFold2.ipynb)\n\n**AntBO：通过组合型贝叶斯优化实现现实世界的自动化抗体设计**\n阿西夫·汗、亚历山大·I·考温-里弗斯、安托万·格罗尼特、德里克-戈-欣·戴克、菲利普·A·罗伯特、维克托·格雷夫、伊娃·斯莫罗迪娜、普尼特·拉瓦特、卡米尔·德雷茨科夫斯基、拉赫马德·阿克巴尔、拉斯乌尔·图图诺夫、丹尼·布-阿玛尔、王俊、阿莫斯·斯托基、海瑟姆·布-阿玛尔\n[arXiv 预印本（2022）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.12570)\u002F[Cell Reports Methods (2023): 100374](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2667237522002764)\n\n**利用去噪自编码器加速生物序列设计的贝叶斯优化**\n塞缪尔·斯坦顿、韦斯利·麦道克斯、内特·格鲁弗、菲利普·马费托内、艾米丽·德拉尼、佩顿·格林赛德、安德鲁·戈登·威尔逊\n[ICML 2022](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.12742) • [代码](https:\u002F\u002Fgithub.com\u002Fsamuelstanton\u002Flambo)\n\n**蛋白质设计的统计力学**\n高桥、友荣、乔治·奇肯吉和德喜时田\n[arXiv 预印本 arXiv:2205.03696 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.03696)\n\n**PropertyDAG：面向生物序列设计的偏序混合变量属性的多目标贝叶斯优化**\n朴智源、塞缪尔·斯坦顿、萨义德·萨雷米、安德鲁·沃特金斯、亨利·德怀尔、弗拉基米尔·格里戈里耶维奇、理查德·邦诺、史蒂芬·拉、京贤·乔\n[arXiv:2210.04096](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.04096)\n\n**蛋白质稳定性、构象特异性和设计的概率视角**\n雅各布·A·斯特恩、泰勒·J·弗里、金伯利·L·斯特恩、斯宾塞·加迪纳、尼古拉斯·A·达利、布拉德利·C·邦迪、约书亚·L·普赖斯、大卫·温盖特、丹尼斯·德拉科尔特\n[bioRxiv 2022.12.28.521825](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.28.521825v1)\u002F[Scientific Reports 13.1 (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-023-42032-1) • [代码](https:\u002F\u002Fgithub.com\u002Fdellacortelab\u002Fbayes_design) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F30\u002F2022.12.28.521825\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用多目标贝叶斯优化设计含非蛋白质氨基酸的抗菌肽**\n村上Y、石田S、出水Y、寺山K\n[ChemRxiv. 剑桥：剑桥开放参与；2023年](https:\u002F\u002Fchemrxiv.org\u002Fengage\u002Fchemrxiv\u002Farticle-details\u002F645f192ef2112b41e97720f3) • [代码](https:\u002F\u002Fgithub.com\u002Fycu-iil\u002FMODAN)\n\n**Vaxformer：抗原性可控的Transformer模型用于针对SARS-CoV-2的疫苗设计**\n阿里奥·普拉迪普塔·杰马、米哈尔·科比埃拉、阿希尔·弗雷斯、阿吉塔·拉詹、迭戈·A·奥亚尔孙、哈维尔·安东尼奥·阿尔法罗\n[arXiv:2305.11194](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.11194) • [代码](https:\u002F\u002Fgithub.com\u002Faryopg\u002Fvaxformer)\n\n**基于蛋白质语言模型的风险感知批处理贝叶斯优化实现高效抗体设计**\n严正旺、博越旺、天宇石、杰富、易周、志卓张\n[bioRxiv 2023.11.06.565922](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.06.565922v1)\n\n**整合蛋白质结构预测与贝叶斯优化用于肽设计**\n内金·曼绍尔、何飞、王多林、徐东\n[NeurIPS 2023 生成式AI与生物学（GenBio）研讨会，2023年](https:\u002F\u002Fopenreview.net\u002Fforum?id=CsjGuWD7hk)\n\n**蛋白质序列设计的贝叶斯优化：具有零样本蛋白质语言模型先验均值的高斯过程**\n卡罗琳·本贾明斯、希卡·苏拉纳、奥利弗·本特、马里乌斯·林道尔、保罗·达克沃思\n[机器学习与结构生物学研讨会，NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FBayesian_Optimisation_for_Protein_Sequence_Design:_Gaussian_Processes_with_Zero-Shot_Protein_Language_Model_Prior_Mean.pdf)\n\n**通过Profile贝叶斯流引导蛋白质家族设计**\n宫静静、裴宇、龙思宇、宋宇轩、张哲、黄文浩、曹子瑶、张淑怡、周浩、马伟英\n[arXiv:2502.07671](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.07671)\n\n**AMix-1：通往测试时可扩展蛋白质基础模型的道路**  \n昌泽·吕、周江、龙思宇、王立豪、冯江涛、薛东宇、裴宇、王浩、张哲睿、蔡宇晨、高志强、马子渊、胡家凯、高超臣、宫静静、宋宇轩、张淑怡、郑晓青、熊德义、白雷、欧阳万力、张雅琴、马伟英、周博文、周浩  \n[arXiv:2507.08920](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.08920) • [代码](https:\u002F\u002Fgensi-thuair.github.io\u002FAMix-1\u002F)\n\n### 5.6 基于强化学习\n\n**基于模型的强化学习在生物序列设计中的应用**\n克里斯托夫·安格穆勒、大卫·多汉、大卫·贝兰杰、拉米娅·德什潘德、凯文·墨菲、露西·科尔韦尔\n[国际表征学习会议。2019年](https:\u002F\u002Fopenreview.net\u002Fforum?id=HklxbgBKvr&fileGuid=3xgr169o12oUrbxS)\n\n**用于抗体设计的结构化Q学习**\n亚历山大·I·考温-里弗斯、菲利普·约翰·戈林斯基、艾瓦尔·索特拉、阿西夫·汗、刘福瑞、王军、扬·彼得斯、海萨姆·布·安马尔\n[arXiv预印本 arXiv:2209.04698 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.04698)\n\n**基于模型的强化学习在潜在空间中进行蛋白质序列设计**\n李敏智、路易斯·费利佩·维基耶蒂、郑贤奎、卢贤珠、金浩珉、车美英\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=OhjGzRE5N6o)\u002F[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FProtein_Sequence_Design_in_a_Latent_Space_via_Model_based_Reinforcement_Learning.pdf) • [补充材料](https:\u002F\u002Fopenreview.net\u002Fattachment?id=OhjGzRE5N6o&name=supplementary_material)\n\n**通过元强化学习和贝叶斯优化设计生物序列**\n利奥·冯、帕迪德·努里、阿内里·穆尼、约书亚·本吉奥、皮埃尔-吕克·培肯\n[arXiv:2209.06259](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.06259)\u002F[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FDesigning_Biological_Sequences_via_Meta_Reinforcement_Learning_and_Bayesian_Optimization.pdf) • [海报](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002F58993.png?t=1669588933.2017226)\n\n**自对弈强化学习指导蛋白质工程**\n王毅、唐辉、黄立超、潘璐璐、杨立祥、杨焕明、穆峰、杨猛\n[自然机器智能（2023）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-023-00691-9) • [代码](https:\u002F\u002Fgithub.com\u002Fmelobio\u002FEvoPlay)\n\n**基于强化学习的好奇心驱动蛋白质序列生成**\n匿名\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=tPjVRmHqCg)\n\n**用于抗体CDRH3区设计的稳定在线与离线强化学习**\n扬尼克·沃格特、梅迪·纳瓦尔、玛丽亚·卡尔韦特、克里斯托夫·科尔内利乌斯·米廷、尤斯图斯·杜斯特、罗兰·梅特尔斯曼、加布里埃尔·卡尔韦特、约施卡·博德克尔\n[arXiv:2401.05341](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.05341)\n\n**基于进化多目标优化的肽疫苗设计**\n刘丹轩、许一恒、钱超\n[arXiv:2406.05743](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.05743)\n\n**利用蛋白质语言模型的强化学习进行序列设计**\n吉滕达拉·苏布拉马尼安、希瓦坎特·苏吉特、尼洛伊·伊尔提萨姆、乌蒙·赛恩、德里克·诺鲁泽扎赖、萨米拉·埃布拉希米·卡胡、里亚沙特·伊斯兰\n[arXiv:2407.03154](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.03154)\n\n**BetterBodies：强化学习引导的扩散模型用于抗体序列设计**\n扬尼克·沃格特、梅迪·纳瓦尔、玛丽亚·卡尔韦特、克里斯托夫·科尔内利乌斯·米廷、尤斯图斯·杜斯特、约施卡·博德克尔、加布里埃尔·卡尔韦特\n[arXiv:2409.16298](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.16298)\n\n**强化学习驱动的肽空间探索：加速类药物肽的生成**\n王谦、胡晓彤、魏志强、陆浩、刘浩\n[生物信息学简报 25.5 (2024): bbae444](https:\u002F\u002Facademic.oup.com\u002Fbib\u002Farticle\u002F25\u002F5\u002Fbbae444\u002F7754450) • [代码](https:\u002F\u002Fgithub.com\u002Fp1acemker\u002FMomdTDSRL)\n\n**用强化学习引导生成式蛋白质语言模型**\n菲利波·斯托科、玛丽亚·阿尔蒂格斯-列沙、安德烈亚·洪克林格、塔拉勒·维达塔拉、马克·古埃尔、诺埃利亚·费鲁兹\n[arXiv:2412.12979](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.12979) • [代码](https:\u002F\u002Fgithub.com\u002FAI4PDLab\u002FDPO_pLM)\n\n**DOTA：开发性优化的抗体生成**\n陶阮、刘家腾、安娜·哈特\n[UIUC 2024年秋季 CS582 MLCB](https:\u002F\u002Fopenreview.net\u002Fforum?id=H4430Z0HfD)\n\n**PepTune：多目标引导的离散扩散模型用于治疗性肽的从头生成**\n索菲娅·唐、尹诺·张、普拉南·查特吉\n[arXiv:2412.17780](https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.17780)\n\n**PepINVENT：超越天然氨基酸的生成式肽设计**\n格克切·盖兰、乔恩·保罗·珍妮特、亚历山德罗·蒂博、贾振赫、阿塔纳斯·帕特罗诺夫、米哈伊尔·卡别绍夫、维尔加德·切赫蒂茨基、弗洛里安·戴维、奥拉·恩格奎斯特和莱昂纳多·德·玛利亚\n[化学科学（2025）](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlelanding\u002F2025\u002Fsc\u002Fd4sc07642g) • [代码](https:\u002F\u002Fgithub.com\u002FMolecularAI\u002FPepINVENT\u002F)\n\n**用于抗生素发现的深度强化学习平台**\n曹汉群、马塞洛·D·T·托雷斯、张静洁、高子俊、吴芳、顾春斌、朱雷·莱斯科韦克、崔艺珍、塞萨尔·德拉富恩特-努涅斯、陈广勇、彭安·亨\n[bioRxiv 2025.09.23.678086](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.23.678086v1)\n\n**通过策略优化设计减少T细胞表位的蛋白质**  \n曼维塔·庞纳帕蒂、萨普娜·辛哈、布莱恩·林奇、爱德华·S·博伊登、约瑟夫·雅各布森  \n[bioRxiv 2025.09.27.678937](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.27.678937v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F29\u002F2025.09.27.678937\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**强化学习引导的生成式蛋白质语言模型实现了高度多样化的AAV衣壳的从头设计**  \n卢卡斯·费拉兹、安娜·F·罗德里格斯、佩德罗·吉埃斯特拉·科托维奥、马法尔达·文图拉、加布里埃拉·席尔瓦、安娜·索菲亚·科罗阿丁哈、米格尔·马丘凯罗、卡蒂娅·佩斯基塔  \n[arXiv:2603.19473](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.19473) • [代码](https:\u002F\u002Fgithub.com\u002Fliseda-lab\u002FgenAAV)\n\n### 5.7 基于流的方法\n\n**利用GFlowNets进行生物序列设计**\nMoksh Jain、Emmanuel Bengio、Alex-Hernandez Garcia、Jarrid Rector-Brooks、Bonaventure F. P. Dossou、Chanakya Ekbote、Jie Fu、Tianyu Zhang、Micheal Kilgour、Dinghuai Zhang、Lena Simine、Payel Das、Yoshua Bengio\n[arXiv预印本 arXiv:2203.04115 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.04115) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=YRbFDThaAmo)\n\n**ProtFlow：基于压缩蛋白质语言模型嵌入的流匹配实现快速蛋白质序列设计**\nZitai Kong、Yiheng Zhu、Yinlong Xu、Hanjing Zhou、Mingzhe Yin、Jialu Wu、Hongxia Xu、Chang-Yu Hsieh、Tingjun Hou、Jian Wu\n[arXiv:2504.10983](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.10983)\n\n**GFlowNet与蛋白质语言模型的协同作用打造多样化抗体设计师**  \nMingze Yin、Hanjing Zhou、Yiheng Zhu、Jialu Wu、Wei Wu、Mingyang Li、Kun Fu、Zheng Wang、Chang-Yu Hsieh、Tingjun Hou、Jian Wu  \n[AAAI人工智能会议论文集，第39卷，第21期，2025年](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F34370)\n\n**多目标引导的离散流匹配用于可控生物序列设计**  \nTong Chen、Yinuo Zhang、Sophia Tang、Pranam Chatterjee  \n[arXiv:2505.07086](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.07086v2) • [模型](https:\u002F\u002Fhuggingface.co\u002FChatterjeeLab\u002FMOG-DFM)\n\n**利用TriFlow对大规模蛋白质设计中的结构条件序列空间进行建模**  \nHarish Srinivasan、Rongqing Yuan、Qian Cong、Jian Zhou  \n[bioRxiv 2025.11.30.691458](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.11.30.691458v1) • [代码](https:\u002F\u002Fgithub.com\u002Fjzhoulab\u002FTriFlow)\n\n**ProtFlow：基于流匹配的蛋白质序列设计，兼具全面的蛋白质语义分布学习与高质量生成能力**  \nZitai Kong、Yiheng Zhu、Yinlong Xu、Mingze Yin、Tingjun Hou、Jian Wu、Hongxia Xu、Chang-Yu Hsieh  \n[bioRxiv 2026.02.14.705870](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.14.705870v1) • [代码](https:\u002F\u002Fgithub.com\u002FHiracharleFranklin\u002FProtFlow)\n\n### 5.8 基于RNN的方法\n\n**深度学习设计核靶向非生物迷你蛋白质**\nCarly K. Schissel、Somesh Mohapatra、Justin M. Wolfe、Colin M. Fadzen、Kamela Bellovoda、Chia-Ling Wu、Jenna A. Wood、Annika B. Malmberg、Andrei Loas、Rafael Gómez-Bombarelli及Bradley L. Pentelute\n[Nature Chemistry 13.10 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41557-021-00766-3) • [代码](https:\u002F\u002Fgithub.com\u002Flearningmatter-mit\u002Fpeptimizer)\n\n**用于构建性肽设计的循环神经网络模型**\nMüller, Alex T.、Jan A. Hiss和Gisbert Schneider\n[化学信息与建模杂志 58.2 (2018)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.7b00414)\n\n**机器学习设计非溶血性抗菌肽**\nAlice Capecchi、Xingguang Cai、Hippolyte Personne、Thilo Köhler、Christian van Delden和Jean-Louis Reymond\n[Chemical Science 12.26 (2021)](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlehtml\u002F2021\u002Fsc\u002Fd1sc01713f)\n\n**利用分子动力学模拟优先筛选并理解人工智能生成的细胞穿透肽**\nDuy Phuoc Tran、Seiichi Tada、Akiko Yumoto、Akio Kitao、Yoshihiro Ito、Takanori Uzawa及Koji Tsuda\n[Scientific Reports 11.1 (2021)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-021-90245-z)\n\n**通过机器学习与DFT研究从头设计抗氧化肽**\nParsa Hesamzadeh、Abdolvahab Seif、Kazem Mahmoudzadeh、Mokhtar Ganjali Koli、Amrollah Mostafazadeh、Kosar Nayeri、Zohreh Mirjafary及Hamid Saeidian\n[Scientific Reports 14.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-024-57247-z) • [代码](https:\u002F\u002Fgithub.com\u002Fmephisto121\u002FDeepGenAntiOxidantPeptide)\n\n### 5.9 基于LSTM\n\n**基于深度学习的抗微生物肽设计及其对多重耐药临床分离菌株的评估**\n迪佩什·纳加拉詹、图沙尔·纳加拉詹、娜塔莎·罗伊、奥姆卡尔·库尔卡尼、萨提亚巴拉蒂·拉维昌德兰、马杜利卡·米什拉\n迪普希卡·查克拉沃蒂、纳加苏玛·钱德拉\n[《生物化学杂志》293.10（2018）](https:\u002F\u002Fwww.jbc.org\u002Farticle\u002FS0021-9258(20)40390-4\u002Ffulltext)\n\n**深度学习助力功能性从头设计抗微生物蛋白**\n哈维尔·卡塞雷斯-德尔皮亚诺、罗伯托·伊巴涅斯、帕特里西奥·阿莱格雷、辛西娅·桑韦萨、罗穆阿尔多·帕斯-菲布拉斯、西蒙·科雷亚、佩德罗·雷塔马尔、胡安·克里斯托瓦尔·希门尼斯、莱昂纳多·阿尔瓦雷斯\n[bioRxiv（2020）](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2020.08.26.266940v1.full)\n\n**ECNet：一种融合进化背景信息的深度学习蛋白质工程框架**\n罗云楠、蒋广德、于天浩、刘洋、林武、丁汉田、苏宇峰、韦斯利·魏谦、赵慧敏及彭健\n[《自然通讯》12.1（2021）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-25976-8)\n\n**基于深度学习的新颖抗微生物肽设计**\n王、克里斯蒂娜、萨姆·加里克和米雷·佐洛\n[《生物分子》11.3（2021）](https:\u002F\u002Fwww.mdpi.com\u002F2218-273X\u002F11\u002F3\u002F471)\n\n**利用基于LSTM的深度生成模型从噬菌体展示文库中进行亲和力成熟的抗体设计**\n小池五郎、角崎太郎、梅次正一、柏木大辉、吉田健二、和田学、津野田博之及寺本礼治\n[《科学报告》11.1（2021）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-021-85274-7)\n\n**无约束规模下基于机器学习的抗体设计的计算机模拟原理验证**\n阿克巴尔、拉赫马德等\n[Mabs，第14卷，第1期，泰勒与弗朗西斯出版社，2022年](https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fpmc\u002Farticles\u002FPMC8986205\u002Fpdf\u002FKMAB_14_2031482.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fcsi-greifflab\u002Fmanuscript_insilico_antibody_generation)\n\n**仅基于序列模型的大规模稳定蛋白质设计与优化**\n杰迪迪亚·M·辛格、斯科特·诺沃特尼、德文·斯特里克兰、休·K·哈多克斯、尼古拉斯·莱比、加布里埃尔·J·罗克林、卡梅伦·M·周、阿尼迪亚·罗伊、阿西姆·K·贝拉、弗朗西斯·C·莫塔、龙兴曹、伊娃-玛丽亚·施特劳赫、塔穆卡·M·奇迪亚乌西库、亚历克斯·福特、伊森·霍、亚历山大·扎伊采夫、克雷格·O·麦肯齐、哈迈德·埃拉米安、弗兰克·迪马约、格沃尔格·格里戈里扬、马修·沃恩、兰斯·J·斯图尔特、大卫·贝克、埃里克·克拉文斯\n[PloS one 17.3（2022）](https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle?id=10.1371\u002Fjournal.pone.0265020) • [代码](https:\u002F\u002Fzenodo.org\u002Frecord\u002F4906529)\n\n**基于深度学习的生物活性治疗肽生成与筛选**\n海平张、孔达·马尼·萨拉瓦南、严杰伟、杨娇、杨阳、易潘、徐丽吴、约翰·Z.H.张\n[bioRxiv 2022.11.14.516530](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.11.14.516530v1) • [代码](https:\u002F\u002Fgithub.com\u002Fhaiping1010\u002FNew_peptide_iteration) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F11\u002F16\u002F2022.11.14.516530\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于深度学习的生物活性肽生成及针对黄嘌呤氧化酶的筛选**\n海平张、孔达·马尼·萨拉瓦南、约翰·Z.H. 张、徐丽吴\n[bioRxiv 2023.01.11.523536](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.11.523536v1)\n\n**基于深度学习的生物活性治疗肽生成与筛选**\n海平张、孔达·马尼·萨拉瓦南、严杰伟、杨娇、杨阳、易潘、徐丽吴以及约翰·Z.H. 张\n[《化学信息与建模杂志》63.3（2023）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.2c01485) • [代码](https:\u002F\u002Fgithub.com\u002Fhaiping1010\u002FNew_peptide_iteration\u002Ftree\u002Fmaster\u002Fiteration_main_protease_Antiviral_pep)\n\n**Bio-xLSTM：生物与化学序列的生成式建模、表征及上下文学习**\n尼克拉斯·施密丁格、丽莎·施内肯赖特、菲利普·赛德尔、约翰内斯·希穆内克、彼得-扬·霍特、约翰内斯·布兰德施泰特、安德烈亚斯·迈尔、索赫维·卢科宁、塞普·霍赫赖特、君特·克兰鲍尔\n[arXiv:2411.04165](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.04165)\n\n### 5.10 自回归模型\n\n**利用简单自回归模型高效生成蛋白质序列**\n珍妮·特兰基耶、圭多·乌古佐尼、安德烈亚·帕尼亚尼、弗朗切斯科·赞波尼及马丁·魏格特\n[《自然通讯》12.1（2021）：1–11页](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-25756-4) • [代码](https:\u002F\u002Fgithub.com\u002Fpagnani\u002FArDCA.jl)\n\n**用于设计问题的共形预测**\n克拉拉·范江、史蒂芬·贝茨、阿纳斯塔西奥斯·N·安杰洛普洛斯、珍妮弗·利斯特加滕、迈克尔·I·乔丹\n[arXiv:2202.03613v4](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.03613) • [代码](https:\u002F\u002Fgithub.com\u002Fclarafy\u002Fconformal-for-design)\n\n**通过水印化蛋白质设计增强生物安全中的隐私保护**\n闫硕陈、郑勉胡、义涵吴、瑞波陈、永睿金、马库斯詹、成进谢、伟陈、恒黄\n[Bioinformatics，2025年，btaf141](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtaf141\u002F8124073) • [代码](https:\u002F\u002Fgithub.com\u002Fposeidonchan\u002FProteinWatermark)\n\n**基于自回归直接耦合分析并以主成分条件控制的可调控蛋白质设计**  \n弗朗切斯科·卡雷达、安德烈亚·帕尼亚尼、保罗·德·洛斯·里奥斯、丽莎·盖尼  \n[bioRxiv 2025.08.18.669886](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.669886v1) • [代码](https:\u002F\u002Fgithub.com\u002Ffrancescocaredda\u002FFeatureDCA.jl)\n\n**ProChoreo：基于构象集合的生成式深度学习从头设计结合蛋白**  \n赛赛丁、易张  \n[bioRxiv 2026.01.23.701298](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.23.701298v1)\n\n### 5.11 基于玻尔兹曼机的\n\n**成对共进化模型如何捕捉蛋白质中残基的集体变异性？**\nFigliuzzi, Matteo、Pierre Barrat-Charlaix 和 Martin Weigt\n[分子生物学与进化 35.4 (2018): 1018-1027](https:\u002F\u002Facademic.oup.com\u002Fmbe\u002Farticle\u002F35\u002F4\u002F1018\u002F4815777) • [代码](https:\u002F\u002Fgithub.com\u002Fmatteofigliuzzi\u002FbmDCA)\n\n**用于蛋白质序列采样和优化的帕累托最优组成能量模型**\nNataša Tagasovska、Nathan C. Frey、Andreas Loukas、Isidro Hötzel、Julien Lafrance-Vanasse、Ryan Lewis Kelly、Yan Wu、Arvind Rajpal、Richard Bonneau、Kyunghyun Cho、Stephen Ra、Vladimir Gligorijević\n[arXiv:2210.10838](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.10838) • [幻灯片](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1spTU-iZ4EEq8ZICRHBw8CstpYQXCxMy8\u002Fview)\n\n**利用基于进化的建模和结构质量评估进行新型 Cas9 PAM 相互作用域的计算设计**\nCyril Malbranke、William Rostain、Florence Depardieu、Simona Cocco、Remi Monasson、David Bikard\n[bioRxiv 2023.03.20.533501](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.20.533501v1) • [代码](https:\u002F\u002Fgithub.com\u002FCyrilMa\u002FDesignCas9WithCLD) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.03.20.533501v1.supplementary-material)\n\n**基于离散行走—跳跃采样的蛋白质发现**\nNathan C. Frey、Daniel Berenberg、Karina Zadorozhny、Joseph Kleinhenz、Julien Lafrance-Vanasse、Isidro Hotzel、Yan Wu、Stephen Ra、Richard Bonneau、Kyunghyun Cho、Andreas Loukas、Vladimir Gligorijevic、Saeed Saremi\n[arXiv:2306.12360](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.12360)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=zMPHKOmQNb) • [代码](https:\u002F\u002Fgithub.com\u002FGenentech\u002Fwalk-jump) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=r28m5Vk77Wk)\n\n### 5.12 基于扩散的\n\n**去噪扩散蛋白质序列**\nZhangzhi Peng\n论文不可用 • [github](https:\u002F\u002Fgithub.com\u002Fpengzhangzhi\u002Fprotein-sequence-diffusion-model)\n\n**引导式离散扩散的蛋白质设计**\nNate Gruver、Samuel Stanton、Nathan C. Frey、Tim G. J. Rudner、Isidro Hotzel、Julien Lafrance-Vanasse、Arvind Rajpal、Kyunghyun Cho、Andrew Gordon Wilson\n[arXiv:2305.20009](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.20009)\u002F[神经信息处理系统进展，2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=MfiK69Ga6p) • [代码](https:\u002F\u002Fgithub.com\u002Fngruver\u002FNOS) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Hm8Z0SIyLqw)\n\n**PRO-LDM：基于条件潜扩散模型的蛋白质序列生成**\nZixuan Jiang、Sitao Zhang、Rundong Huang、Shaoxun Mo、Letao Zhu、Peiheng Li、Ziyi Zhang、Xi Chen、Yunfei Long、Renjing Xu、Rui Qing\n[bioRxiv 2023.08.22.554145](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.22.554145v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F08\u002F23\u002F2023.08.22.554145\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于进化扩散的蛋白质生成：序列就是一切**\nSarah Alamdari、Nitya Thakkar、Rianne van den Berg、Alex Xijie Lu、Nicolo Fusi、Ava Pardis Amini、Kevin K Yang\n[bioRxiv 2023.09.11.556673](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.11.556673v1) • [代码](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fevodiff) • [数据](https:\u002F\u002Fzenodo.org\u002Frecord\u002F8045076) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=e1e-_SkyNjw)，[讲座2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=iV_7mgxe4OI)\n\n**AntiBARTy 指导属性的抗体扩散设计**\nJordan Venderley\n[arXiv:2309.13129](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.13129)\n\n**使用 AI 蛋白质扩散技术发现 PD-1 靶向抗体**\nColby T. Ford\n[bioRxiv 2024.01.18.576323](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.01.18.576323v2) • [代码](https:\u002F\u002Fgithub.com\u002Ftuplexyz\u002FPD-1_Fab_Diffusion)\n\n**ProT-Diff：通过整合蛋白质语言模型和扩散模型实现抗菌肽序列从头生成的模块化高效方法**\nXue-Fei Wang、Jing-Ya Tang、Han Liang、Jing Sun、Sonam Dorje、Bo Peng、Xu-Wo Ji、Zhe Li、Xian-En Zhang、Dian-Bing Wang\n[bioRxiv 2024.02.22.581480](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.22.581480v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F02\u002F23\u002F2024.02.22.581480\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**TaxDiff：用于蛋白质序列生成的分类学指导扩散模型**\nLin Zongying、Li Hao、Lv Liuzhenghao、Lin Bin、Zhang Junwu、Chen Calvin Yu-Chian、Yuan Li、Tian Yonghong\n[arXiv:2402.17156](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.17156) • [代码](https:\u002F\u002Fgithub.com\u002FLinzy19\u002FTaxDiff)\n\n**基于语言模型嵌入的扩散用于蛋白质序列生成**\nViacheslav Meshchaninov、Pavel Strashnov、Andrey Shevtsov、Fedor Nikolaev、Nikita Ivanisenko、Olga Kardymon、Dmitry Vetrov\n[arXiv:2403.03726](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.03726)\n\n**AMP-Diffusion：将潜扩散与蛋白质语言模型结合用于抗菌肽生成**\nTianlai Chen、Pranay Vure、Rishab Pulugurta、Pranam Chatterjee\n[bioRxiv 2024.03.03.583201](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.03.583201v1)\n\n**原子级精确的单域抗体从头设计**\nNathaniel R. Bennett、Joseph L. Watson、Robert J. Ragotte、Andrew J. Borst、DeJenae L. See、Connor Weidle、Riti Biswas、Ellen L. Shrock、Philip J. Y. Leung、Buwei Huang、Inna Goreshnik、Russell Ault、Kenneth D. Carr、Benedikt Singer、Cameron Criswell、Dionne Vafeados、Mariana Garcia Sanchez、Ho Min Kim、Susana Vazquez Torres、Sidney Chan、David Baker\n[bioRxiv 2024.03.14.585103](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.14.585103v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09721-5) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F03\u002F18\u002F2024.03.14.585103\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于等变扩散生成模型的复合物结合配体蛋白重新设计**\nViet Thanh Duy Nguyen、Nhan Nguyen、Truong Son Hy\n[bioRxiv 2024.04.17.589997](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.17.589997v1) • [代码](https:\u002F\u002Fgithub.com\u002FHySonLab\u002FProtein_Redesign)\n\n**通过在扩散模型中约束催化口袋设计细胞色素 P450 酶**\nQian Wang、Xiaonan Liu、Hejian Zhang、Huanyu Chu、Chao Shi、Lei Zhang、Jie Bai、Pi Liu、Jing Li、Xiaoxi Zhu、Yuwan Liu、Zhangxin Chen、Rong Huang、Hong Chang、Tian Liu、Zhenzhan Chang、Jian Cheng 和 Huifeng Jiang\n[Research (2024)](https:\u002F\u002Fspj.science.org\u002Fdoi\u002F10.34133\u002Fresearch.0413) • [代码](https:\u002F\u002Fgithub.com\u002FJiangLab2020\u002FP450Diffusion)\n\n**面向分布外分子和蛋白质设计的上下文引导扩散**\nLeo Klarner、Tim G. J. Rudner、Garrett M. Morris、Charlotte M. Deane、Yee Whye Teh\n[arXiv:2407.11942](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.11942) • [代码](https:\u002F\u002Fgithub.com\u002Fleojklarner\u002Fcontext-guided-diffusion)\n\n**基于二级结构引导的潜图扩散新蛋白质序列生成**\nYutong Hu、Yang Tan、Andi Han、Lirong Zheng、Liang Hong、Bingxin Zhou\n[arXiv:2407.07443](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.07443) • [代码](https:\u002F\u002Fgithub.com\u002Friacd\u002FCPDiffusion-SS)\n\n**AI生成的小型结合剂提升了原位编辑效率**\n朴柱灿、严熙秀、金容宇、吴艺恩、裴尚洙  \n[bioRxiv 2024.09.11.612443](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.11.612443v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F09\u002F14\u002F2024.09.11.612443\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**MeMDLM：基于掩码离散扩散蛋白质语言模型的从头设计膜蛋白**\nShrey Goel、Vishrut Thoutam、Edgar Mariano Marroquin、Aaron Gokaslan、Arash Firouzbakht、Sophia Vincoff、Volodymyr Kuleshov、Huong T. Kratochvil、Pranam Chatterjee  \n[arXiv:2410.16735](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.16735)\u002F[ICLR 2025 工作坊 LMRL](https:\u002F\u002Fopenreview.net\u002Fforum?id=ZnEx3GbU9C)\n\n**用于结构指导抗体设计与优化的检索增强扩散模型**\n王子辰、季耀坤、田佳宁、郑双嘉  \n[arXiv:2410.15040](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.15040)\n\n**ProtDiff：面向功能条件的掩码扩散模型，用于稳健的定向蛋白质生成**\nVishrut Thoutam、Yair Schiff、Sergey Ovchinnikov、Pranam Chatterjee  \n[NeurIPS 2024 科学基础模型研讨会：进展、机遇与挑战](https:\u002F\u002Fopenreview.net\u002Fforum?id=POrk2Cc7Ux)\n\n**基于语言模型编码的扩散模型用于蛋白质序列生成**\nViacheslav Meshchaninov、Pavel Strashnov、Andrey Shevtsov、Fedor Nikolaev、Nikita Ivanisenko、Olga Kardymon、Dmitry Vetrov  \n[ICLR 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=LoXJlAW3gU)\n\n**基于奖励引导的测试时迭代精炼扩散模型及其在蛋白质和DNA设计中的应用**\nMasatoshi Uehara、苏星宇、赵玉来、李希讷、Aviv Regev、季水旺、Sergey Levine、Tommaso Biancalani  \n[arXiv:2502.14944](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.14944) • [代码](https:\u002F\u002Fgithub.com\u002Fmasa-ue\u002FProDifEvo-Refinement)\n\n**在残基二级结构约束下，融合LSTM与注意力机制的轻量级扩散模型用于大型多肽的从头设计**\n廖思盛、徐刚、金力、马建鹏  \n[Molecules 30.5 (2025)](https:\u002F\u002Fwww.mdpi.com\u002F1420-3049\u002F30\u002F5\u002F1116) • [代码](https:\u002F\u002Fgithub.com\u002Fdaedaluser\u002FPPD)\n\n**基于AI的抗体设计，靶向近期H5N1禽流感病毒株**  \nNicholas Santolla、Colby T. Ford  \n[bioRxiv 2025.04.24.650061](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.24.650061v1) • [代码](https:\u002F\u002Fgithub.com\u002FSantollan\u002FFrankies) • 基于EvoDiff\n\n**CFP-Gen：通过扩散语言模型实现组合式功能性蛋白质生成**  \n尹俊波、查超、何文佳、许晨程、高鑫  \n[arXiv:2505.22869](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22869)\n\n**AMPGen：一种保留进化信息且由扩散驱动的生成模型，用于抗菌肽的从头设计**  \n金淑雯、曾志涵、熊曦妍、黄柏成、唐莉、王洪生、马晓、唐小春、邵国清、黄兴旭及林峰  \n[Communications Biology 8.1 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42003-025-08282-7) • [代码](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.15454482.7433980)\n\n**用于增强蛋白质表征与生成的扩散序列模型**  \nLogan Hallee、Nikolaos Rafailidis、David B. Bichara、Jason P. Gleghorn  \n[arXiv:2506.08293](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08293) • [代码](https:\u002F\u002Fgithub.com\u002FGleghorn-Lab\u002FDSM)\n\n**不确定性感知的离散扩散技术提升蛋白质设计效果**  \nSazan Mahbub、Christoph Feinauer、Caleb N. Ellington、宋乐、Eric P. Xing  \n[bioRxiv 2025.06.30.662407](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.30.662407v1)\n\n**针对可开发性抗体的引导生成**  \n赵思琪、Joshua Moller、Porfi Quintero-Cadena、Lood van Niekerk  \n[arXiv:2507.02670](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.02670) • 基于ESM-2\n\n**PRO‐LDM：用于蛋白质序列设计与功能优化的条件潜扩散模型**  \n张思涛、蒋子轩、黄润东、黄文婷、彭思远、莫绍勋、朱乐陶、李培恒、张子怡、潘艾米丽、陈曦、龙云飞、梁奇、唐进、徐仁静、秦睿  \n[Advanced Science (2025)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202502723) • 基于ESM-2\n\n**基于广义扩散模型的类似Protein A的肽类生成**  \n周天谦、张世博、宋慧佳、何强、方纯及林小竹  \n[J Comput Aided Mol Des 39, 76 (2025)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10822-025-00653-w) • [代码](https:\u002F\u002Fgithub.com\u002FPotatoGan\u002FProteinGeneration-GeneralizedDiffusion)\n\n**PepCCD：用于靶向特异性肽类生成的对比条件扩散框架**  \n张军、周阳阳、朱天田、朱泽轩  \n[bioRxiv 2025.09.01.673427](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.01.673427v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F04\u002F2025.09.01.673427\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**生成式潜在扩散语言建模产生抗感染合成肽**  \nMarcelo D.T. Torres、Leo Tianlai Chen、万芳平、Pranam Chatterjee、Cesar de la Fuente-Nunez  \n[Cell Biomaterials (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell-biomaterials\u002Ffulltext\u002FS3050-5623(25)00174-6) • [代码](https:\u002F\u002Fgithub.com\u002Fprogrammablebio\u002Famp-diffusion)\n\n**通过知识感知提示扩散模型可控地生成病原体特异性抗菌肽**  \n王永康、李梦露、黄峰、邱敏瑶、张文  \n[Advanced Science（德国巴登-符腾堡州魏因海姆）](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202507457)\n\n**High-PepBinder：基于pLM引导的潜扩散框架，用于亲和力导向的靶向肽类设计**  \n毛庆义、翟思龙、曹森、朱仁杰、徐文、张承云、朱宁、郭晶晶、段宏亮  \n[bioRxiv 2026.01.12.69898](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.12.698988v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F19\u002F2026.01.12.698988\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n\n\n### 5.13 基于GNN的方法\n\n**生成式预训练自回归Transformer图神经网络在新型蛋白质分析与发现中的应用**  \nMarkus J. Buehler  \n[arXiv:2305.04934](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.04934) • [代码](https:\u002F\u002Fgithub.com\u002Flamm-mit\u002FMateriomicTransformer)\n\n### 5.14 基于评分的方法\n\n**微滴筛选快速评估生物催化剂，以支持其AI辅助工程改造**  \nMaximilian Gantz、Simon V. Mathis、Friederike E. H. Nintzel、Paul J. Zurek、Tanja Knaus、Elie Patel、Daniel Boros、Friedrich-Maximilian Weberling、Matthew R. A. Kenneth、Oskar J. Klein、Elliot J. Medcalf、Jacob Moss、Michael Herger、Tomasz S. Kaminski、Francesco G. Mutti、Pietro Lio、Florian Hollfelder  \n[bioRxiv (2024.04.08)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.08.588565v1.full.pdf)\n\n**基于评分条件的生成器的自举训练，用于生物序列的离线设计**  \nMinsu Kim、Federico Berto、安成洙、朴镇九  \n[arXiv:2306.03111](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.03111) • [代码](https:\u002F\u002Fgithub.com\u002Fkaist-silab\u002Fbootgen)\n\n## 6. 基于功能的结构生成\n\n> 这些模型可以根据预期的功能生成蛋白质结构（包括侧链），或者恢复蛋白质结构的一部分（即**图像修复**）。\n\n### 6.0 回顾\n\n**迈向用于蛋白质设计的深度学习序列-结构联合生成**\n王晨桐、萨拉·阿拉姆达里、卡莱斯·多明戈-恩里奇、艾娃·阿米尼、凯文·K·杨\n[arXiv:2410.01773](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.01773)\u002F[Current Opinion in Structural Biology (2025)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0959440X25000363)\n\n### 6.1 基于LSTM的方法\n\n**利用深度学习进行蛋白质-蛋白质相互作用基序的单侧设计**\nSyrlybaeva、Raulia 和 Eva-Maria Strauch\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.03.30.486144v2) • [代码](https:\u002F\u002Fgithub.com\u002Fstrauchlab\u002FiNNterfaceDesign) • [我们的笔记](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F521613546) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bSWkXy56rt8)\n\n### 6.2 基于扩散的方法\n\n**使用等变去噪扩散概率模型生成蛋白质结构和序列**\nNamrata Anand、Tudor Achim\n[GitHub (2022)](https:\u002F\u002Fnanand2.github.io\u002Fproteins\u002F)\u002F[arXiv (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.15019) • [我们的笔记](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F520488133) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=i8fGzddGbU8)\n\n**基于扩散生成模型的抗原特异性抗体设计与优化——用于蛋白质结构的生成**\nShitong Luo、Yufeng Su、Xingang Peng、Sheng Wang、Jian Peng、Jianzhu Ma\n[bioRxiv 2022.07.10.499510](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.07.10.499510v5)\u002F[ICML (2023)](https:\u002F\u002Ficml-compbio.github.io\u002F2023\u002Fpapers\u002FWCBICML2023_paper143.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fluost26\u002Fdiffab) • [Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fluost26\u002FDiffAb)\n\n**用可编程生成模型照亮蛋白质空间**\nJohn Ingraham、Max Baranov、Zak Costello、Vincent Frappier、Ahmed Ismail、Shan Tie、Wujie Wang、Vincent Xue、Fritz Obermeyer、Andrew Beam、Gevorg Grigoryan\n[Generate Biomedicines 预印本](https:\u002F\u002Fcdn.generatebiomedicines.com\u002Fassets\u002Fingraham2022.pdf)\u002F[bioRxiv 2022.12.01.518682](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.01.518682v1)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-06728-8) • [官网](https:\u002F\u002Fgeneratebiomedicines.com\u002Fchroma) • [新闻](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-023-01705-y) • [代码](https:\u002F\u002Fgithub.com\u002Fgeneratebio\u002Fchroma) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fgeneratebio\u002Fchroma\u002Fblob\u002Fmain\u002Fnotebooks\u002FChromaTutorial.ipynb) • 商业化\n\n**基于物理启发的蛋白质编码器预训练：通过暹罗序列-结构扩散轨迹预测**\nZuobai Zhang、Minghao Xu、Aurélie Lozano、Vijil Chenthamarakshan、Payel Das、Jian Tang\n[arXiv:2301.12068](https:\u002F\u002Farxiv.org\u002Fabs\u002F2301.12068) • [代码](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FSiamDiff)\n\n**TRDiffusion**\n[TIANRANG XLab](https:\u002F\u002Fxlab.tianrang.com\u002F)\n[新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002F9rJ6IoJbf6cvz3UqE-rpIg) • [官网](https:\u002F\u002Fxlab.tianrang.com\u002FxCREATOR) • 商业化\n\n**一种全原子蛋白质生成模型**\nAlexander E Chu、Lucy Cheng、Gina El Nesr、Minkai Xu、Po-Ssu Huang\n[bioRxiv 2023.05.24.542194](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.24.542194v1)\u002F[美国国家科学院院刊 121.27 (2024)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002Ffull\u002F10.1073\u002Fpnas.2311500121) • [代码](https:\u002F\u002Fgithub.com\u002Falexechu\u002Fprotpardelle)\n\n**DiffPack：用于自回归式蛋白质侧链堆积的扭转扩散模型**\nYangtian Zhan、Zuobai Zhang、Bozitao Zhong、Sanchit Misra、Jian Tang\n[arXiv 2023.06.01](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.01794) • [代码](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FDiffPack)\n\n**AbDiffuser：体外功能抗体的全原子生成**\nKarolis Martinkus、Jan Ludwiczak、Kyunghyun Cho、Wei-Ching Lian、Julien Lafrance-Vanasse、Isidro Hotzel、Arvind Rajpal、Yan Wu、Richard Bonneau、Vladimir Gligorijevic、Andreas Loukas\n[arXiv:2308.05027](https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.05027) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=95w0Ht3m0JY)\n\n**用于抗体设计、对接和优化的生成式扩散模型**\nZhangzhi Peng、Chenchen Han、Xiaohan Wang、Dapeng Li、Fajiie Yuan\n[bioRxiv 2023.09.25.559190](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.25.559190v1) • [代码](https:\u002F\u002Fgithub.com\u002Fpengzhangzhi\u002Fab_opt) • [网站](https:\u002F\u002Fpengzhangzhi.github.io\u002Fab_opt_homepage\u002F)\n\n**连接序列与结构：用于条件性蛋白质生成的潜在扩散模型**\n匿名\n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=DP4NkPZOpD)\n\n**指导扩散模型进行具有开发可行性的抗体序列和结构联合设计**\nAmelia Villegas-Morcillo、Jana M. Weber、Marcel J.T. Reinders\n[bioRxiv 2023.11.22.568230](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.22.568230v1)\u002F[NeurIPS 2023 生成式AI与生物学研讨会](https:\u002F\u002Fopenreview.net\u002Fforum?id=bPcgbKDCUQ) • [代码](https:\u002F\u002Fgithub.com\u002Famelvim\u002Fantibody-diffusion-properties)\n\n**用于治疗性肽生成的多模态对比扩散模型**\nYongkang Wang、Xuan Liu、Feng Huang、Zhankun Xiong、Wen Zhang\n[arXiv:2312.15665](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.15665) • [代码](https:\u002F\u002Fgithub.com\u002Fwyky481l\u002FMMCD)\n\n**迈向核酸与蛋白质复合物的联合序列-结构生成：SE(3)-离散扩散**\nAlex Morehead、Jeffrey Ruffolo、Aadyot Bhatnagar、Ali Madani\n[arXiv:2401.06151](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.06151) • [代码](https:\u002F\u002Fgithub.com\u002FProfluent-Internships\u002FMMDiff)\n\n**Proteus：探索蛋白质结构生成以提升可设计性和效率**\n王晨桐、Yannan Qu、Peng Zhangzhi、Wang Yukai、Zhu Hongli、Chen Dachuan、Cao Longxing\n[bioRxiv 2024.02.10.579791](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.10.579791v3) • [代码](https:\u002F\u002Fgithub.com\u002FWangchentong\u002FProteus)\n\n**基于几何潜在扩散的全原子肽设计**\nXiangzhe Kong、Wenbing Huang、Yang Liu\n[arXiv:2402.13555](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.13555)\n\n**用于稳定、亲和力驱动且具备受体感知能力的肽生成的混合扩散模型**\nR Vishva Saravanan、Soham Choudhuri、Bhaswar Ghosh\n[bioRxiv 2024.03.14.584934](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.14.584934v1) • [代码](https:\u002F\u002Fgithub.com\u002FBhaswarGhoshLab\u002FHYDRA) • [数据集](http:\u002F\u002Fhuanglab.phys.hust.edu.cn\u002Fpepbdb\u002F)\n\n**通过直接基于能量的偏好优化进行抗原特异性抗体设计**\nXiangxin Zhou、Dongyu Xue、Ruizhe Chen、Zaixiang Zheng、Liang Wang、Quanquan Gu\n[arXiv:2403.16576](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.16576)\n\n**HelixDiff：一种基于分数的扩散模型，用于生成全原子α-螺旋结构**\nXuezhi Xie、Pedro A Valiente、Jisun Kim 和 Philip M Kim\n[ACS Central Science (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Facscentsci.3c01488) • [代码](https:\u002F\u002Fgithub.com\u002Fxxiexuezhi\u002FHelixDiff)\n\n**结合Transformer与3DCNN模型，以扩散方式实现抗体结构与序列的协同设计**\n胡悦、陶峰、兰俊文、张静\n[bioRxiv 2024.04.25.587828](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.25.587828v1) • [代码](https:\u002F\u002Fgithub.com\u002FYueHuLab\u002FAlphaPanda)\n\n**基于DiffPepBuilder的靶向特异性从头肽结合物设计**\n王帆浩、王宇哲、冯来义、张长生、赖陆华\n[arXiv:2405.00128](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.00128)\u002F[J. Chem. Inf. Model. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Fabs\u002F10.1021\u002Facs.jcim.4c00975) • [代码](https:\u002F\u002Fgithub.com\u002FYuzheWangPKU\u002FDiffPepBuilder)\n\n**利用扩散模型中的力引导采样改进抗体设计**\n保利娜·库利特、弗朗西斯科·巴尔加斯、西蒙·瓦伦丁·马蒂斯、王昱光、何塞·米格尔·埃尔南德斯-洛巴托、皮耶特罗·利奥\n[arXiv:2406.05832](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.05832)\n\n**基于进化、物理及几何约束指导的评分式扩散模型用于抗体设计**\n朱天、任米龙、张海沧\n[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=1YsQI04KaN) • [代码](https:\u002F\u002Fgithub.com\u002Fzhanghaicang\u002Fcarbonmatrix_public)\n\n**Antibody-SGM：一种基于评分的生成模型，用于抗体重链设计**\n谢学智、佩德罗·A·瓦连特、李镇燮、金智善、菲利普·M·金\n[化学信息与建模杂志（2024）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.4c00711) • [代码](https:\u002F\u002Fgithub.com\u002Fxxiexuezhi\u002FABSGM)\n\n**用于稳定、亲和力驱动且具有受体感知能力的肽生成的混合扩散模型**\n维什瓦·萨拉瓦南·R、索哈姆·乔杜里、巴斯瓦尔·戈什\n[J. Chem. Inf. Model. 2024](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.4c01020) • [代码](https:\u002F\u002Fgithub.com\u002FComputationalBiologyLab-IIITH\u002FHYDRA)\n\n**使用AlphaProteo进行高亲和力蛋白质结合物的从头设计**\n维尼修斯·赞巴尔迪、大卫·拉、亚历山大·E·楚、哈什尼拉·帕塔尼、艾米·E·丹森、特里斯坦·O·C·关、托马斯·弗雷里克斯、罗莎莉娅·G·施耐德、大卫·萨克顿、阿肖克·蒂莱顺达拉姆、扎卡里·吴、伊莎贝尔·莫拉埃斯、奥斯卡·兰格、埃利塞奥·帕帕、加布里埃拉·斯坦顿、维克多·马丁、苏赫迪普·辛格、赖H·王、拉斯·贝茨、西蒙·A·科尔、乔什·阿布拉姆森、安德鲁·W·塞尼尔、尤尔马兹·阿尔古埃尔、玛丽·Y·吴、伊莲娜·M·阿斯帕尔特、凯蒂·本特利、大卫·L.V·鲍尔、彼得·切列帕诺夫、德米斯·哈萨比斯、普什米特·科利、罗布·费格斯以及王珏\n[DeepMind预印本](https:\u002F\u002Fstorage.googleapis.com\u002Fdeepmind-media\u002FDeepMind.com\u002FBlog\u002Falphaproteo-generates-novel-proteins-for-biology-and-health-research\u002FProtein_Design_White_Paper_2024.pdf)\u002F[arXiv:2409.08022](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.08022) • [博客](https:\u002F\u002Fdeepmind.google\u002Fdiscover\u002Fblog\u002Falphaproteo-generates-novel-proteins-for-biology-and-health-research\u002F)\n\n**DPLM-2：多模态扩散蛋白质语言模型**\n王新友、郑在祥、叶飞、薛东宇、黄树坚、管全权\n[arXiv:2410.13782](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.13782) • [代码](https:\u002F\u002Fgithub.com\u002Fbytedance\u002Fdplm) • [网站](https:\u002F\u002Fbytedance.github.io\u002Fdplm\u002Fdplm-2)\n\n**E(3)不变性扩散模型用于口袋感知肽生成**\n梁博宇、白军\n[arXiv:2410.21335](https:\u002F\u002Farxiv.org\u002Fabs\u002F2410.21335) • [代码](https:\u002F\u002Fgithub.com\u002FLabJunBMI\u002FE3-invaraint-diffusion-model-for-pocket-aware-peptide-generation)\n\n**仅基于序列训练数据生成全原子蛋白质结构** \u002F **利用潜在扩散生成全原子蛋白质**\n卢艾米X、颜威尔逊、罗宾逊莎拉A、杨凯文K、格里戈里耶维奇弗拉基米尔、曹庆贤、邦诺理查德、阿贝尔彼得、弗雷内森\n[bioRxiv 2024.12.02.626353](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.02.626353v2)\u002F[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=5zNRgNMxIS) • [代码](https:\u002F\u002Fgithub.com\u002Famyxlu\u002Fplaid) • [博客](https:\u002F\u002Fwww.matricedigitale.it\u002Ftech\u002Fintelligenza-artificiale\u002Fplaid-intelligenza-artificiale-proteine-3d\u002F)\n\n**利用稀疏去噪模型高效生成蛋白质结构**\n迈克尔·延德鲁施、扬O·科尔贝尔\n[bioRxiv 2025.01.31.635780](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.01.31.635780v1)\u002F[自然机器智能7, 1429–1445 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-025-01100-z) • [代码](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.14711580), [github](https:\u002F\u002Fgithub.com\u002Fmjendrusch\u002Fsalad)\n\n**Neo-1**\n[VANTAI](https:\u002F\u002Fwww.vant.ai\u002Fteam)\n论文未公开 • [网站](https:\u002F\u002Fwww.vant.ai\u002Fneo-1) • 商业化\n\n**UniMoMo：统一的3D分子生成建模，用于从头结合物设计**\n孔翔哲、张子深、张子婷、焦锐、马建竹、刘凯、黄文兵、刘洋\n[arXiv:2503.19300](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.19300v1)\n\n**PPDiff：在混合序列-结构空间中扩散，用于蛋白质-蛋白质复合物设计**\n宋振桥、李条晓、李磊、闵仁强马丁\n[arXiv:2506.11420](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.11420)\n\n**利用多尺度等变图扩散模型进行抗体设计与优化，以实现对复杂抗原的精准结合**\n陈佳萌、蔡先涛、吴嘉、胡文斌\n[arXiv:2506.20957](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.20957v1) • [代码](https:\u002F\u002Fgithub.com\u002FPatrick221215\u002FAbMEGD)\n\n**借助层次化条件扩散模型揭秘蛋白质生成**\n凌子楠、史毅、严达、周阳、惠博\n[arXiv:2507.18603](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.18603)\n\n**PXDesign：快速、模块化且精准的蛋白质结合物从头设计**\n任米龙、孙金元、关家琪、刘聪、龚成悦、王宇哲、王兰、蔡启旭、陈新石、肖文志\n[技术报告](https:\u002F\u002Fprotenix.github.io\u002Fpxdesign\u002Ftechnical_report.pdf)\u002F[bioRxiv 2025.08.15.670450](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.15.670450v1) • [代码](https:\u002F\u002Fgithub.com\u002Fbytedance\u002FPXDesignBench) • [服务器](https:\u002F\u002Fprotenix-server.com\u002F) • [数据]([supplements\u002F670450_file03.zip])\n\n**基于深度学习的联合序列-结构从头膜蛋白设计**\n卢卡斯·鲁登、雷莫·巴蒂格、文尼·安德鲁斯、朱莉·阮、马丁·斯托尔、洛伦佐·斯库特里、米哈尔·温尼基、梅丽莎·J·卡尔、马修·E·卡尔、达米安·泰韦宁、帕特里克·巴斯\n[bioRxiv 2025.08.15.670493](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.15.670493v1)\n\n**利用Protpardelle-1C进行条件式蛋白质结构生成**\n陆天宇、理查德·帅、彼得·寇巴、李兆阳、陈怡琳、白井明雄、金镇浩、黄宝书\n[bioRxiv 2025.08.18.670959](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.670959v2) • [代码](https:\u002F\u002Fgithub.com\u002FProteinDesignLab\u002Fprotpardelle-1c\u002Ftree\u002Fmain)\n\n**利用多模态扩散Transformer生成功能性和多态蛋白质**\n景博文、安娜·萨平顿、米希尔·巴夫纳、拉维·沙阿、阿德里娜·唐、罗希特·克里希纳、亚当·克利万斯、丹尼尔·J·迪亚斯、邦妮·伯格\n[bioRxiv 2025.09.03.672144](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.03.672144v2) • [代码](https:\u002F\u002Fgithub.com\u002Fbjing2016\u002FProDiT)\n\n**利用扩散桥模型联合设计蛋白质表面与主链**\n李冠略、赵旭峰、吴芳、劳厄索伦\n[NeurIPS 2025海报](https:\u002F\u002Fopenreview.net\u002Fforum?id=QqCv9SI0X3)\n\n**通过结合界面模拟进行肽设计：PepMimic**  \n孔祥哲、焦锐、林浩伟、郭瑞涵、黄文兵、马伟英、王子华、刘洋及马建竹  \n[Nat. Biomed. Eng (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41551-025-01507-4) • [代码](https:\u002F\u002Fgithub.com\u002Fkxz18\u002FPepMimic)\n\n**基于GeoFlow-V3的快速从头抗体设计**  \nBioGeometry团队  \n[技术报告](https:\u002F\u002Fopen-res.biogeom.com\u002F2025\u002Fgeoflowv3\u002FGeoFlow_V3_report.pdf) • [网站](https:\u002F\u002Fprot.design) • 商业化\n\n**AbEgDiffuser：利用等变图神经网络与扩散模型实现抗体序列—结构协同设计**  \n朱一博、石秀敏、张静娟、孙伟中、王璐  \n[J. Chem. Theory Comput.(2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jctc.5c00990) • [代码](https:\u002F\u002Fgithub.com\u002FShiLab-GitHub\u002FAbEgDiffuser)\n\n**ODesign：用于生物分子相互作用设计的世界模型**  \nODesign团队  \n[技术报告](https:\u002F\u002Fodesign1.github.io\u002Fstatic\u002Fpdfs\u002Ftechnical_report.pdf) • [网站](https:\u002F\u002Fodesign.lglab.ac.cn\u002F) • [代码](https:\u002F\u002Fgithub.com\u002FThe-Institute-for-AI-Molecular-Design\u002FODesign)\n\n**BoltzGen：迈向通用结合剂设计**  \n汉内斯·斯塔克、费利克斯·法尔廷斯、崔珉奎、谢宇欣、许恩洙、蒂莫西·奥唐奈尔、安东·布舒耶夫、塔利普·乌恰尔、萨罗·帕萨罗、毛伟安、马特奥·雷韦伊斯、罗曼·布舒耶夫、托马什·普卢斯卡尔、约瑟夫·西维奇、卡斯滕·克莱斯、阿拉什·瓦赫达特、沙玛耶塔·雷、乔纳森·T·戈德斯坦、安德鲁·萨维诺夫、雅各布·A·汉巴莱克、安希卡·古普塔、迭戈·A·塔基里-迪亚斯、张耀天、A·凯瑟琳·哈特斯塔特、安杰莉卡·阿拉达、金南亨、埃塞尔·塔基耶-亚尔博伊、迪伦·博塞利、李·施奈德、刘昌C、李基因伟、德内斯·赫尼兹、大卫·M·萨巴蒂尼、威廉·F·德格拉多、杰里米·沃尔温德、加布里埃莱·科尔索、雷吉娜·巴尔齐莱、汤米·S·雅科拉\n[技术报告](https:\u002F\u002Fhannes-stark.com\u002Fassets\u002Fboltzgen.pdf) • [网站](https:\u002F\u002Fboltz.bio\u002Fboltzgen) • [模型](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fludocomito\u002Fanatomy-of-boltzgen)\n\n**用于蛋白质序列与结构联合设计的多模态扩散模型**  \n朱绍文、西丹特·古拉蒂、刘宇轩、西迪·科特尼斯、孙青、沈阳  \n[Protein Science 34.12 (2025)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70340) • [代码](https:\u002F\u002Fgithub.com\u002FShen-Lab\u002FJointDiff)\n\n**Peptide2Mol：一种生成小分子以作为肽类模拟物用于靶向蛋白结合的扩散模型**  \n何新恒、张义嘉、林浩伟、彭星刚、孔祥哲、李明宇、马建竹  \n[arXiv:2511.04984](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.04984)\n\n**利用扩散桥模型进行蛋白质表面与结构的联合设计**  \n李冠略、赵旭峰、吴芳、索伦·劳厄  \n[arXiv:2511.16675](https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.16675v1) • [代码](https:\u002F\u002Fgithub.com\u002Fguanlueli\u002FPepbridge)\n\n**SeedProteo：精确的从头全原子蛋白质结合剂设计**  \n屈伟、马一鸣、叶飞、陆婵、周毅、张可欣、王兰、桂敏睿、顾权权  \n[arXiv:2512.24192](http:\u002F\u002Farxiv.org\u002Fabs\u002F2512.24192) • [GitHub](https:\u002F\u002Fseedfold.github.io\u002F)\n\n**用于靶向切割淀粉样β蛋白的金属蛋白酶从头设计**  \n曲燕楠、王晨彤、朱红丽、王艳军、曹隆兴  \n[bioRxiv 2026.01.06.697903](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.06.697903v1)\n\n\n\n### 6.3 基于RoseTTAFold的方法\n\n**利用深度学习方法设计具有功能位点的蛋白质支架** \u002F **使用深度学习设计蛋白质功能位点支架**  \n王珏、西德尼·利桑扎、大卫·尤尔根斯、道格·提舍尔、伊万·阿尼申科、白珉京、约瑟夫·L·沃森、春正浩、卢卡斯·F·米勒斯、尤斯塔斯·道帕拉斯、马克·埃克斯波西特、杨伟、阿米贾伊·萨拉戈维、谢尔盖·奥夫钦尼科夫、戴维·贝克\n[bioRxiv(2021)](https:\u002F\u002Feuropepmc.org\u002Farticle\u002Fppr\u002Fppr419387)\u002F[Science(2022)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.abn2100) • [RFDesign](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRFDesign) • [我们的笔记](https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F477854488) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-EJ8SXTBin0) • [RoseTTAFold](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRoseTTAFold) • [补充材料](https:\u002F\u002Fwww.science.org\u002Fdoi\u002Fsuppl\u002F10.1126\u002Fscience.abn2100\u002Fsuppl_file\u002Fscience.abn2100_sm.pdf), [其他补充材料](https:\u002F\u002Fwww.science.org\u002Fdoi\u002Fsuppl\u002F10.1126\u002Fscience.abn2100\u002Fsuppl_file\u002Fscience.abn2100_data_s1_and_s2.zip)\n\n**通过整合结构预测网络和扩散生成模型实现广泛适用且准确的蛋白质设计** \u002F **利用RFdiffusion进行蛋白质结构与功能的从头设计**  \n约瑟夫·L·沃森、大卫·尤尔根斯、纳撒尼尔·R·贝内特、布莱恩·L·特里普、杰森·尹、海伦·E·艾森纳赫、伍迪·阿亨、安德鲁·J·博斯特、罗伯特·J·拉戈特、卢卡斯·F·米勒斯、巴西勒·I·M·威基、尼基塔·哈尼克尔、塞缪尔·J·佩洛克、亚历克西斯·库尔贝、威廉·谢弗勒、王珏、普里塔姆·文卡特什、艾萨克·萨平顿、苏珊娜·巴斯克斯·托雷斯、安娜·劳科、瓦伦丁·德·博尔托利、埃米尔·马修、雷吉娜·巴尔齐莱、汤米·S·雅科拉、弗兰克·迪马约、白珉京、戴维·贝克\n[Bakerlab预印本](https:\u002F\u002Fwww.bakerlab.org\u002Fwp-content\u002Fuploads\u002F2022\u002F11\u002FDiffusion_preprint_12012022.pdf)\u002F[bioRxiv 2022.12.09.519842](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.09.519842v2)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-06415-8) • [新闻](https:\u002F\u002Fwww.bakerlab.org\u002F2022\u002F11\u002F30\u002Fdiffusion-model-for-protein-design\u002F)、[新闻2](https:\u002F\u002Fwww.ipd.uw.edu\u002F2023\u002F03\u002Frf-diffusion-now-free-and-open-source\u002F)、[新闻3](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-023-02227-y) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F10\u002F2022.12.10.519862\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=wIHwHDt2NoI)、[讲座2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=828WPIIOwaA) • [RFdiffusion：代码](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRFdiffusion)、[Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fsokrypton\u002FColabDesign\u002Fblob\u002Fv1.1.1\u002Frf\u002Fexamples\u002Fdiffusion.ipynb) • [博客](https:\u002F\u002Fwww.science.org\u002Fcontent\u002Fblog-post\u002Fprotein-design-ai-way)\n\n**针对生物活性螺旋肽的高亲和力蛋白质结合剂从头设计**  \n苏珊娜·巴斯克斯·托雷斯、菲利普·J·Y·梁、艾萨克·D·卢茨、普里塔姆·文卡特什、约瑟夫·L·沃森、法比安·欣克、胡-贤·阮、安迪·Hsien-Wei 叶、大卫·尤尔根斯、纳撒尼尔·R·贝内特、安德鲁·N·胡夫纳格尔、埃里克·黄、迈克尔·J·麦科斯、马克·埃克斯波西特、李圭里、埃利夫·尼哈尔·科尔克马兹、杰夫·尼瓦拉、兰斯·斯图尔特、约瑟夫·M·罗杰斯、戴维·贝克\n[bioRxiv 2022.12.10.519862](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.10.519862v1)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-06953-1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F12\u002F10\u002F2022.12.10.519862\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用 RoseTTAFold 序列空间扩散联合生成蛋白质序列与结构**\n西德尼·利亚尤加·利桑扎、雅各布·默尔·格什恩、萨姆·韦恩·肯莫尔·蒂普斯、卢卡斯·阿诺尔特、塞缪尔·亨德尔、杰里迈亚·纳尔逊·西姆斯、李欣婷、大卫·贝克\n[bioRxiv 2023.05.08.539766](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.05.08.539766v1)\u002F[Nat Biotechnol (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-024-02395-w) • [代码](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002Fprotein_generator#proteingenerator-generate-sequence-structure-pairs-with-rosettafold) • [hugging face](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fmerle\u002FPROTEIN_GENERATOR) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bS71K2U0amA)\n\n**通过大规模从头设计揭示免疫球蛋白折叠的结构景观**\n豪尔赫·罗埃尔-托里斯、洛尔德斯·卡尔塞伦、恩里克·马科斯\n[bioRxiv 2023.10.03.560637](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.03.560637v1)\u002F[Protein Science (2024)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.4936) • [补充材料](https:\u002F\u002Fonlinelibrary.wiley.com\u002Faction\u002FdownloadSupplement?doi=10.1002%2Fpro.4936&file=pro4936-sup-0001-supinfo.docx) • [代码](https:\u002F\u002Fgithub.com\u002FJorgeRoel\u002Fbetasandwich) • [数据](https:\u002F\u002Fzenodo.org\u002Frecord\u002F8380285)\n\n**基于 RoseTTAFold 全原子模型的通用生物分子建模与设计**\n罗希特·克里希纳、王珏、伍迪·艾恩、帕斯卡尔·施图尔姆费尔斯、普里塔姆·文卡特什、因德雷克·卡尔韦特、李圭丽、菲利克斯·S·莫雷-伯罗斯、伊万·阿尼申科、伊恩·R·汉弗里斯、瑞安·麦休、狄俄涅·瓦菲阿多斯、李欣婷、乔治·A·萨瑟兰、安德鲁·希奇科克、C·尼尔·亨特、白敏京、弗兰克·迪马约、大卫·贝克\n[bioRxiv 2023.10.09.561603](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.10.09.561603v1)\u002F[Science](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adl2528) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F10\u002F09\u002F2023.10.09.561603\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fbaker-laboratory\u002FRoseTTAFold-All-Atom)\n\n**Amalga：结合折叠与逆向折叠指导的设计可编程蛋白质骨架生成**\n陈书高、李子瑶、曾湘湘、柯国林\n[bioRxiv 2023.11.07.565939](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.07.565939v1)\n\n**通过合成蛋白质支架定位活性位点以复制酶活性**\n丁宇婧、张珊珊、亨利·赫斯、孔贤、张一飞\n[bioRxiv 2024.01.31.577620](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.01.31.577620v1)\u002F[Advanced Science (2025)](https:\u002F\u002Fadvanced.onlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fadvs.202500859) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F01\u002F31\u002F2024.01.31.577620\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于 RFjoint\u002FProteinMPNN\n\n**利用深度学习精准搭建三个非重叠蛋白质表位的单域支架**\n卡拉·M·卡斯特罗、约瑟夫·L·沃森、王珏、乔舒亚·索瑟恩、雷哈内·阿亚杜拉比、桑德琳·乔治昂、斯蒂芬·罗塞、大卫·贝克、布鲁诺·E·科雷亚\n[bioRxiv 2024.05.07.592871](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.07.592871v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F05\u002F10\u002F2024.05.07.592871\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**通过幻觉多样化从头设计 TIM 桶状结构**\n贝克、朱利安、苏鲁班·尚穆加拉特南和比尔特·霍克尔\n[Protein Science 33.6 (2024)](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.5001)\n\n**从头设计的蛋白质可中和致命蛇毒毒素**\n苏珊娜·巴斯克斯·托雷斯、梅丽莎·贝纳德·巴列、斯蒂芬·P·麦克西、斯蒂法妮·K·门齐斯、尼古拉斯·R·卡斯威尔、希林·艾哈迈迪、尼克·J·伯莱特、埃丁·穆拉特沙皮奇、以撒·萨平顿、马克·D·欧弗拉思、埃斯佩兰萨·里韦拉-德-托雷、扬·莱德格贝尔、安德烈亚斯·H·劳斯特森、金·博杜姆、阿西姆·K·贝拉、亚历克斯·康、埃文斯·布拉肯布罗、伊亚拉·A·卡多索、爱德华·P·克里滕登、丽贝卡·J·埃奇、贾斯汀·德卡罗、罗伯特·J·拉戈特、阿尔温德·S·皮莱、穆罕默德·阿贝迪、汉娜·L·韩、斯泰西·R·格尔本、阿纳莉萨·默里、丽贝卡·斯科海姆、琳达·斯图尔特、兰斯·斯图尔特、托马斯·J·A·弗莱尔、蒂莫西·P·詹金斯、大卫·贝克\n[预印本（第1版）可在 Research Square 上获取](https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-4402792\u002Fv1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-08393-x)\n\n**金属氧化物模板化蛋白质的从头设计**\n阿米贾伊·萨拉戈维、哈利·派尔斯、蒂莫西·F·哈迪、温兆戴、李新奇、安德鲁·J·博斯特、尼基塔·哈尼克尔、亚历克西斯·库尔贝、保罗·权、法蒂玛·A·达维拉-埃尔南德斯、瑞安·基布勒、狄俄涅·K·瓦菲阿多斯、阿扎·艾伦、肯尼斯·D·卡尔、阿西姆·K·贝拉、亚历克斯·康、埃文斯·布拉肯布罗、萨克希·施密德、尹娜·裴、兰斯·斯图尔特、帅张、詹姆斯·德·约雷奥、大卫·贝克\n[bioRxiv 2024.06.24.600095](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.24.600095v2)\n\n**向固有无序蛋白质扩散蛋白质结合剂**\n蔡轩刘、凯嘉吴、浩俊崔、汉娜·韩、薛丽张、约瑟夫·L·沃森、萨拉·希乔、阿西姆·K·贝拉、亚历克斯·康、埃文斯·布拉肯布罗、布莱恩·科文特里、德里克·R·希克、安德鲁·N·胡夫纳格尔、平珠、李欣婷、贾斯汀·德卡罗、斯泰西·R·格尔本、魏杨、王鑫茹、米拉·兰普、阿纳莉萨·默里、马格努斯·鲍尔、大卫·贝克\n[bioRxiv 2024.07.16.603789](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.16.603789v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09248-9) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F16\u002F2024.07.16.603789\u002FDC1\u002Fembed\u002Fmedia-1.mov)\n\n**利用深度学习进行参数化引导的β桶和跨膜纳米孔设计**\n大卫·E·金、约瑟夫·L·沃森、大卫·尤尔根斯、萨加迪普·马朱姆达尔、斯泰西·R·格尔本、亚历克斯·康、阿西姆·K·贝拉、李欣婷、大卫·贝克\n[bioRxiv 2024.07.22.604663](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.22.604663v1)\u002F[Proc. Natl. Acad. Sci. U.S.A. 122 (38) e2425459122](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2425459122) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F07\u002F23\u002F2024.07.22.604663\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码1](https:\u002F\u002Fgithub.com\u002Fdavidekim\u002Fparametric_barrels)、[代码2](https:\u002F\u002Fgithub.com\u002Fsagardipm\u002FdenovoPores)\n\n**高度活性从头设计酶的计算设计**\n马库斯·布劳恩、艾德里安·特里普、莫拉科特·查卡托克、西格丽德·卡尔滕布鲁纳、马西莫·G·托塔罗、大卫·斯托尔、亚历山大·比耶利奇、瓦埃尔·埃莱伊利、什洛莫·亚基尔·亚基尔·霍赫、马特奥·阿莱奥蒂、梅拉妮·霍尔、古斯塔夫·奥伯多尔费尔\n[bioRxiv 2024.08.02.606416](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.02.606416v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F08\u002F03\u002F2024.08.02.606416\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**丝氨酸水解酶的计算设计**\n安娜·劳科、塞缪尔·J·佩洛克、伊万·阿尼申卡、基拉·H·苏米达、大卫·尤尔根斯、伍迪·艾恩、亚历克斯·志田、安德鲁·亨特、因德雷克·卡尔韦特、克里斯托弗·诺恩、伊恩·R·汉弗里斯、库珀·S·杰米森、亚历克斯·康、埃文斯·布拉肯布罗、巴努马蒂·桑卡兰、K·N·侯克、大卫·贝克\n[bioRxiv 2024.08.29.610411](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.29.610411v1)\u002F[Science0,eadu2454](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adu2454) • [新闻](https:\u002F\u002Fwww.asimov.press\u002Fp\u002Fai-enzymes)\n\n**从头设计Ras同工型选择性结合剂**\n张兆兴、李欣婷、刘彩萱、姜翰伦、吴可嘉、大卫·贝克\n[bioRxiv 2024.08.29.610300](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.29.610300v1)\u002F[Cell Chemical Biology](https:\u002F\u002Fwww.cell.com\u002Fcell-chemical-biology\u002Ffulltext\u002FS2451-9456(26)00063-2)\n\n**利用β-配对靶向的RFdiffusion改进蛋白质结合剂设计**\n艾萨克·萨平顿、马丁·托尔、戴维·S·李、斯蒂芬妮·A·罗宾逊、因娜·戈列什尼克、克拉拉·麦克迪、陈东清、尼克·布赫霍尔茨、黄步伟、狄奥妮·瓦菲阿多斯、玛丽亚娜·加西亚-桑切斯、妮可·鲁耶、马蒂亚斯·格勒格尔、克里斯·金、约瑟夫·L·沃森、苏珊娜·巴斯克斯·托雷斯、科恩·H·G·费尔斯胡伦、肯尼思·弗斯特拉特、辛西娅·S·欣克、梅丽莎·贝纳德-瓦列、布莱恩·考文特里、杰里迈亚·尼尔森·西姆斯、格林·安、王鑫如、安德鲁·P·欣克、蒂莫西·P·詹金斯、汉内莱·鲁霍拉-贝克、史蒂文·M·巴尼克、萨瓦斯·N·萨维德斯、大卫·贝克\n[bioRxiv 2024.10.11.617496](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.10.11.617496v1)\u002F[预印本](https:\u002F\u002Fassets-eu.researchsquare.com\u002Ffiles\u002Frs-5473963\u002Fv1_covered_81143f0e-3579-4f09-86c3-c0e316288e3a.pdf) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F10\u002F12\u002F2024.10.11.617496\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**Afpdb——用于AI蛋白质设计的高效结构操作工具包**\n周英尧、柯熙怡、周斌、朱天成、钟阳、格伦·斯普拉贡\n[Bioinformatics (2024): btae654](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtae654\u002F7876263) • [代码](https:\u002F\u002Fgithub.com\u002Fdata2code\u002Fafpdb) • [网站](https:\u002F\u002Fpypi.org\u002Fproject\u002Fafpdb)\n\n**GRACE：人工智能计算酶学中的生成式重新设计**\n芮恩、胡奇华、吴伊孙\n[ACS Synthetic Biology (2024)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.4c00624) • [代码](https:\u002F\u002Fgithub.com\u002FRyan-Hu-Hu-Hu\u002FGRACE)\n\n**金属水解酶的计算设计**\n金东孝、塞思·M·伍德伯里、伍迪·艾亨、因德雷克·卡尔韦特、尼基塔·哈尼克尔、萨曼·萨利克、塞缪尔·J·佩洛克、安娜·劳科、唐纳德·希尔弗特、大卫·贝克\n[bioRxiv 2024.11.13.623507](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.13.623507v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09746-w) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F14\u002F2024.11.13.623507\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**促进解离的设计实现对细胞因子信号持续时间的控制**\n亚当·J·布罗尔曼、克里斯托夫·波尔曼、毛里茨·A·利希滕斯坦、马克·D·杰克逊、麦克斯·H·泰斯默、柳元熙、穆罕默德·H·阿贝迪、丹尼·D·萨托、阿扎·艾伦、亚历克斯·康、乔什敏·德拉克鲁兹、埃文斯·布拉肯布罗、巴努马蒂·桑卡兰、阿西姆·K·贝拉、丹尼尔·M·祖克曼、施特凡·施托尔、弗洛里安·普雷托里乌斯、雅各布·皮勒、大卫·贝克\n[bioRxiv 2024.11.15.623900](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.15.623900v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09549-z) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F16\u002F2024.11.15.623900\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用深度学习精确从头设计高亲和力蛋白质结合大环化合物**\n斯蒂芬·A·雷蒂、大卫·尤尔根斯、维克多·阿德博米、延西·弗洛雷斯·布埃索、赵琴琴、亚历山德拉·N·勒维尔、安迪·刘、阿西姆·K·贝拉、乔安娜·A·维尔姆斯、阿莉娜·于芬、亚历克斯·康、埃文斯·布拉肯布罗、米拉·兰布、斯泰西·R·格尔本、阿纳丽萨·默里、保罗·M·莱文、迈卡·施奈德、维芭·瓦西雷迪、谢尔盖·奥夫钦尼科夫、奥利弗·H·魏尔格拉伯、迪特尔·维尔博尔德、约书亚·A·克里策、约瑟夫·D·莫古斯、大卫·贝克、弗兰克·迪马约、加拉夫·巴德瓦杰\n[bioRxiv 2024.11.18.622547](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.18.622547v1)\u002F[Nat Chem Biol (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-01929-w) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F11\u002F18\u002F2024.11.18.622547\u002FDC1\u002Fembed\u002Fmedia-1.zip) • [代码](https:\u002F\u002Fzenodo.org\u002Frecords\u002F15264344)\n\n**利用生成式AI工程化从头设计CAR-T细胞疗法的结合剂**\n马库斯·梅尔根、丹妮拉·阿贝尔、奈勒·科莱奇、阿尔巴·施马尔·费尔南德斯、玛雅·萨格登、诺亚·霍尔茨莱特纳、安德烈亚斯·卡尔、莱昂妮·里格尔、瓦伦蒂娜·莱昂、马克西米利安·赖歇特、卡尔-路德维希·劳格维茨、弗洛里安·巴瑟曼、迪尔克·H·布施、朱利安·格吕内瓦尔德、安德烈亚·施密茨\n[bioRxiv 2024.11.25.625151](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.25.625151v1) • 基于RFDiffusion\u002FProteinMPNN\n\n**CycleDesigner：利用RFdiffusion和HighFold设计针对特定靶标的环肽结合剂**\n张晨浩、徐振宇、林康、张承云、许文、段洪亮\n[bioRxiv 2024.11.27.625581](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.27.625581v1) • 基于RFDiffusion\u002FProteinMPNN\n\n**从头设计的pMHC结合剂促进T细胞介导的癌细胞杀伤**\n克里斯托弗·豪鲁姆·约翰森、达里安·斯蒂芬·沃尔夫、贝亚特丽丝·斯卡波洛、莫妮卡·L·费尔南德斯·昆特罗、夏洛特·里萨格尔·克里斯滕森、约翰内斯·R·洛夫勒、埃斯佩兰萨·里韦拉-德-托雷、马克思·D·欧弗拉特、卡米拉·克亚尔加德·蒙克、奥利弗·莫雷尔、玛丽·克里斯汀·维夫、阿尔贝特·T·达姆·恩格伦、玛蒂尔德·杜埃、斯特法诺·福尔利、艾玛·青洁·安德森、乔丹·西尔维斯特·费尔南德斯、苏提蒙·通特乔、安德鲁·B·沃德、玛丽亚·奥尔姆霍伊、西涅·雷克尔·哈德鲁普、蒂莫西·P·詹金斯\n[bioRxiv 2024.11.27.624796](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.27.624796v1)\u002F[Science389,380-385(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adv0422) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F03\u002F2024.11.27.624796\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**针对肽-MHC-I复合物的高特异性结合剂设计**\n刘炳旭、内森·F·格林伍德、朱莉娅·E·邦扎尼尼、阿米尔·莫特曼、贾兹敏·夏普、王春宇、吉安·马可·维萨尼、狄奥妮·K·瓦菲阿多斯、妮可·鲁耶、阿尔米塔·努尔穆罕默德、K·克里斯托弗·加西亚、大卫·贝克\n[bioRxiv 2024.11.28.625793](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.28.625793v1)\u002F[Science389,386-391(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adv0185)\n\n**靶标条件扩散生成强效TNFR超家族拮抗剂和激动剂**\n马蒂亚斯·格勒格尔、阿迪蒂亚·克里希纳库马尔、罗伯特·J·拉戈特、因娜·戈列什尼克、布莱恩·考文特里、阿西姆·K·贝拉、亚历克斯·康、艾米丽·乔伊斯、格林·安、黄步伟、杨伟、陈伟、玛丽亚娜·加西亚·桑切斯、布莱恩·科普尼克、大卫·贝克\n[Science 386.6726 (2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adp1779)\n\n**基于计算表位支架设计水溶性CD20抗原**\n姚志远、布莱恩·库尔曼\n[bioRxiv 2024.12.05.627087](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.05.627087v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F06\u002F2024.12.05.627087\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F06\u002F2024.12.05.627087\u002FDC2\u002Fembed\u002Fmedia-2.zip) • 基于RFDiffusion\n\n**利用从头设计的蛋白质抑制致病性大肠杆菌对血红素的劫持**\n丹尼尔·R·福克斯、卡泽姆·阿萨多利、伊莫金·G·塞缪尔斯、布拉德利·斯派瑟、阿什莉·克罗普、克里斯·卢普顿、凯文·林、王春晓、哈里普拉萨德·维努戈帕尔、玛丽亚·德拉米恰宁、加文·J·诺特、瑞斯·格林特\n[bioRxiv 2024.12.05.626953](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.05.626953v1)\u002F[Nat Commun 16, 6066 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-60612-9) • 基于RFDiffusion\u002FProteinMPNN\n\n**高效CRISPR-Cas13抑制剂的从头设计**\n辛西娅·塔韦诺、何翔柴、乔维塔·迪席尔瓦、丽贝卡·S·巴默特、布鲁克·K·海耶斯、罗兰·W·卡尔弗特、丹尼尔·J·柯温、法比安·蒙德尔、利桑德拉·L·马丁、杰里米·J·巴尔、瑞斯·格林特、加文·J·诺特\n[bioRxiv 2024.12.05.626932](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.05.626932v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F06\u002F2024.12.05.626932\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于RFDiffusion\u002FProteinMPNN\n\n**开发一种能够抑制α激酶eEF2K的从头设计蛋白质结合剂**\n科迪·A·克鲁普特、伊森·贝尔罗斯、贾宗超\n[bioRxiv 2024.12.10.627789](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.10.627789v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F11\u002F2024.12.10.627789\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于RFDiffusion\u002FProteinMPNN\n\n**为蛋白质骨架生成并评估多样化的序列**\n青木洋、谢尔盖·奥夫钦尼科夫\n[机器学习在结构生物学中的应用研讨会，NeurIPS 2024](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FGenerating_and_evaluating_diverse_sequences_for_protein_backbones.pdf) • 基于RFDiffusion\u002FProteinMPNN\n\n**以肽为中心的TCR模拟结合模块的从头设计与结构解析**\n卡斯滕·D·豪斯霍尔德、向鑫宇、凯文·M·朱德、阿瑟·邓、马蒂亚斯·奥本瑙斯、史蒂文·C·威尔逊、陈晓静、王楠、K·克里斯托弗·加西亚\n[bioRxiv 2024.12.16.628822](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.16.628822v1)\u002F[Science389,375-379(2025)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adv3813) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F20\u002F2024.12.16.628822\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于RFDiffusion\u002FProteinMPNN\n\n**伪对称蛋白质异二聚体的自下而上设计**\n瑞安·D·基布勒、李相珉、麦迪逊·A·肯尼迪、巴西勒·I·M·威基、斯特拉·M·莱、马里乌斯·M·科斯特利奇、安妮·卡尔、李欣婷、卡梅伦·M·周、丁娜·K·阮、劳伦·卡特、维姬·H·维索基、巴里·L·斯托达德及大卫·贝克\n[Nat Commun 15, 10684 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-54913-8) • [代码](https:\u002F\u002Fgithub.com\u002Frdkibler\u002FStepwise-design-of-pseudosymmetric-protein-hetero-oligomers)\n\n**基于明确选择性过滤器几何结构的钙通道自下而上设计**\n刘玉来、康纳·魏德尔、柳比察·米哈列维奇、约瑟夫·L·沃森、李哲、乐·特蕾西·余、萨加迪普·马朱姆达尔、安德鲁·J·博斯特、肯尼斯·D·卡尔、瑞安·D·基布勒、塔米尔·M·加马尔·埃尔丁、威廉·A·卡特罗尔、大卫·贝克\n[bioRxiv 2024.12.19.629320](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.19.629320v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F12\u002F20\u002F2024.12.19.629320\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • 基于RFDiffusion\u002FProteinMPNN\n\n**利用设计的蛋白质WRAPS实现膜蛋白的可溶化**\n柳比察·米哈列维奇、戴维·E·金、海伦·E·艾森纳赫、普贾·D·班达万、安德鲁·J·博斯特、阿莱克西·库尔贝、埃弗顿·贝廷、刘秋实、康纳·魏德尔、萨加迪普·马朱姆达尔、李欣婷、米拉·兰布、阿纳丽莎·妮可·阿斯卡拉加·穆雷、拉什米·拉维昌德兰、伊丽莎白·C·威廉姆斯、胡书远、琳达·斯图尔特、琳达·格里洛娃、尼古拉斯·R·汤姆森、常鹏翔、梅丽莎·J·凯曼诺、凯莉·L·霍利、尼尔·P·金、大卫·贝克\n[bioRxiv 2025.02.04.636539](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.04.636539v1) • 基于RFDiffusion\u002FProteinMPNN\n\n**用设计的无扭转螺旋重复蛋白抑制冰的再结晶**\n罗伯特·J·德哈斯、哈利·派尔斯、蒂莫西·F·哈迪、扬尼克·范奥森布鲁根、郑传宝、丹妮埃尔·范登布鲁克、安妮·卡尔、阿西姆·K·贝拉、亚历克斯·康、埃文斯·布拉肯布罗、艾米丽·乔伊斯、巴努马蒂·桑卡兰、大卫·贝克、伊利亚·K·沃茨、伦科·德弗里斯\n[bioRxiv 2025.03.09.642278](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.09.642278v1)\u002F[美国国家科学院院刊 122.48 (2025)](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2514871122) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F13\u002F2025.03.09.642278\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.13763849) • 基于RFDiffusion\u002FProteinMPNN\n\n**RoseTTAFold扩散引导下的短肽设计：以针对Keap1\u002FNrf2的结合剂为例**\n弗朗切斯科·莫雷纳、基亚拉·琴奇尼亚、卡拉·埃米利亚尼、萨巴塔·马蒂诺阿\n[计算与结构生物技术杂志 (2025)](https:\u002F\u002Fwww.csbj.org\u002Farticle\u002FS2001-0370(25)00061-3\u002Ffulltext) • 基于RFDiffusion\u002FProteinMPNN\n\n**靶向G蛋白偶联受体的迷你蛋白激动剂和拮抗剂的从头设计**\n埃丁·穆拉特沙皮奇、大卫·费尔德曼、戴维·E·金、曲祥立、安娜-玛丽亚·布拉托维阿努、保拉·里韦拉-桑切斯、费德丽卡·季米特里、杰森·曹、布莱恩·P·卡里、马修·J·贝洛索夫、彼得·凯欧、陈清超、任悦、贾斯汀·法因、以撒·萨平顿、托马斯·施利希泰尔、张志中、阿尔文德·皮莱、柳比察·米哈列维奇、马格努斯·鲍尔、苏珊娜·巴斯克斯·托雷斯、阿米尔·莫特曼、李圭丽、龙·陈、王欣茹、英娜·戈列什尼克、狄俄涅·K·瓦菲阿多斯、贾斯汀·E·斯文森、帕丽萨·侯赛因扎德、尼古拉·林德加德、马特豪斯·布兰特、扬·瓦尔滕斯普尔、克里斯蒂娜·代布勒、卢克·奥斯蒂迪克、威廉·曹、拉克什米·阿南塔拉曼、兰斯·斯图尔特、劳伦·霍洛兰、杰米·B·斯潘格勒、帕特里克·M·塞克斯顿、布莱恩·L·罗斯、布莱恩·E·克鲁姆、丹妮丝·伍滕、克里斯托弗·G·泰特、克里斯托弗·诺恩、大卫·贝克\n[bioRxiv 2025.03.23.644666](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.03.23.644666v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F23\u002F2025.03.23.644666\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用RFdiffusion2进行原子级酶活性位点支架构建**\n伍迪·阿亨、杰森·尹、道格·提舍尔、萨曼·萨利克、塞思·伍德伯里、金东孝、因德雷克·卡尔韦特、雅科夫·基普尼斯、布莱恩·科文特里、韩·阿尔泰-陈、马格努斯·鲍尔、雷吉娜·巴尔齐莱、汤米·贾科拉、罗希特·克里希纳、戴维·A·贝克\n[bioRxiv 2025.04.09.648075](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.04.09.648075v2)\u002F[Nat Methods (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-025-02975-x) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F04\u002F10\u002F2025.04.09.648075.1\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bd6bFXRmEGA&pp=ygUMcmZkaWZmdXNpb24y) • [代码](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002FRFdiffusion2)\n\n**生成式蛋白质设计与合成卟啉组装的结合**\n稻叶弘明、小野田浩树、内桥隆之、大岛敦则及庄司央美\n[ChemRxiv. 2025](https:\u002F\u002Fchemrxiv.org\u002Fengage\u002Fchemrxiv\u002Farticle-details\u002F67f4f96381d2151a0284768f) • 基于RFDiffusion\u002FProteinMPNN\n\n**基于人工智能设计的蛋白质结合剂在癌症细胞表面蛋白检测与靶向中的开发**  \n比安卡·布罗斯克、索菲·C·宾德、本杰明·A·麦克恩罗、蒂姆·N·肯普琴、卡罗琳·I·范德雷、朱莉娅·M·梅斯默、伊丽莎白·谭、彼得·科诺普卡、多米尼克·费尔伯、米歇尔·C·R·容、玛丽·克莱内特、亚历山大·霍赫、卡佳·布鲁门斯托克、扬·M·P·托特曼、约翰内斯·奥尔登堡、海科·鲁尔、亚历山大·塞曼、马里埃塔·I·托马、克里斯蒂娜·马尔科娃、塞巴斯蒂安·科博尔德、蒂姆·罗伦斯克、马蒂亚斯·盖耶、施特凡·门策尔、托比亚斯·巴尔德、乔纳森·L·施密德-布尔格克、格雷戈尔·哈格吕肯、迈克尔·霍尔策尔  \n[bioRxiv 2025.05.11.652819](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.11.652819v1) • [代码](https:\u002F\u002Fgithub.com\u002FHoelzelLab\u002FIEO_AI_Binder_cancer_surface_2025) • 基于RFDiffusion\u002FProteinMPNN\n\n**痘病毒被RFdiffusion肽类结合剂靶向**  \nJ. Coll  \n[bioRxiv 2025.05.14.654163](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.14.654163v1) • 基于RFDiffusion\u002FProteinMPNN\n\n**人工智能辅助设计针对脂质运载蛋白-2的配体**  \n雅各波·斯格里尼亚尼、萨拉·布斯卡里尼、帕特里齐娅·洛卡泰利、孔切塔·格拉、阿尔贝托·富尔兰、陈英怡、贾达·佐皮、安德烈亚·卡瓦利  \n[bioRxiv 2025.05.18.654718](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.18.654718v1)\u002F[Frontiers in Immunology, 2025](https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fimmunology\u002Farticles\u002F10.3389\u002Ffimmu.2025.1631868) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F05\u002F19\u002F2025.05.18.654718\u002FDC1\u002Fembed\u002Fmedia-1.docx) • 基于RFDiffusion\u002FProteinMPNN\n\n**从头设计的荧光素酶实现多重生物发光成像**  \n朱莉·易萱·陈、青石、雪鹏、让·德·迪厄·哈比马纳、詹姆斯·王、威廉·索博列夫斯基、安迪·贤伟·叶  \n[Chem 11.3 (2025)](https:\u002F\u002Fwww.cell.com\u002Fchem\u002Ffulltext\u002FS2451-9294(24)00539-4) • 基于RFjoint\u002FProteinMPNN\n\n**MgtE Mg2+通道的生物信息学分类及用于稳定其新型亚类的从头蛋白质设计**  \n赵志轩、小前希美穗、岩崎亘、张子义、潘发志、李恩珍、服部元幸  \n[bioRxiv 2025.05.26.656215](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.26.656215v1) • [代码](https:\u002F\u002Fgithub.com\u002F0mae\u002Fmgte_short) • 基于RFDiffusion\u002FProteinMPNN\n\n**基于结构的TEM-171 β-内酰胺酶蛋白抑制剂的从头设计：整合深度学习与多尺度模拟以对抗细菌耐药性**  \n克里希夫·波特卢里  \n[bioRxiv 2025.06.23.661177](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.06.23.661177v1) • [代码](https:\u002F\u002Fgithub.com\u002Fkishpish\u002Ftem171-inhibitor-pipeline) • 基于RFDiffusion\u002FProteinMPNN\n\n**利用扩散模型生成结构引导的pMHC-I文库**  \n塞尔吉奥·马雷斯、阿里埃尔·埃斯皮诺萨·韦因伯格、尼拉·M·伊万尼迪斯  \n[arXiv:2507.08902](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.08902v1) • [代码](https:\u002F\u002Fgithub.com\u002Fsermare\u002Fstruct-mhc-dev) • 基于RFDiffusion\u002FProteinMPNN\n\n**CycleDesigner：利用CycRFdiffusion和HighFold设计针对特定靶标的环肽结合剂**  \n陈浩、张振宇、林康、朱宁、张成云、徐文、郭晶晶、苏安、李成熙、段洪亮  \n[J. Chem. Inf. Model. 2025](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.5c00227)\n\n**从头设计蛋白质结合剂以稳定单体TDP-43并抑制其病理性聚集**  \n孙刚宇、李翔、胡娇娇、杨天彬、刘聪、王志志、李丹、许文清  \n[Proc. Natl. Acad. Sci. U.S.A. 122 (36) e2505320122](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2505320122)\n\n**人工智能生成的小分子MLH1结合剂提高先导编辑效率**  \n朴柱灿、严熙秀、金勇武、吴艺恩、李章贤、杨智允、金京美、裴尚洙  \n[Cell (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell\u002Ffulltext\u002FS0092-8674(25)00799-8) • [代码](https:\u002F\u002Fgithub.com\u002Fbaelab\u002FPE-SB)\n\n**利用深度学习从头设计光调控动态蛋白质**  \n帕特里克·巴斯、洛伦佐·斯库特里、卢恰诺·阿布里亚塔、张书豪、艾西玛·哈西苏莱曼、凯尔文·劳、弗洛伦斯·波耶尔、萨汉德·贾马尔·拉希  \n[bioRxiv 2025.08.12.669910](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.12.669910v1) • 基于RFDiffusion\u002FProteinMPNN\n\n**细菌黏附素的小型蛋白抑制剂的从头设计**  \n亚当·M·查津-格雷、图斯坎·R·汤普森、爱德华·D·B·洛帕托、珀尔·马加拉、帕特里克·W·埃里克森、安德鲁·C·亨特、安娜·曼琴科、帕维尔·阿普里基扬、维罗妮卡·切什诺科娃、伊琳娜·巴索娃、丹尼斯·A·萨尼克、凯文·O·塔马东法尔、摩根·R·蒂姆、杰罗姆·S·平克纳、卡伦·W·多德森、亚历克斯·康、艾米丽·乔伊斯、阿西姆·K·贝拉、亚伦·J·施密茨、阿里·H·埃勒贝迪、凯莉·L·霍沃雷尼、马克·J·卡特赖特、安迪娜·韦内特、萨赖·巴尔达莱斯、德斯蒙德·怀特、瑞秋·E·克利维特、叶夫根尼·V·索库连科、斯科特·J·胡尔特格伦、大卫·贝克  \n[bioRxiv 2025.08.18.670751](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.18.670751v1) • 基于RFDiffusion\u002FProteinMPNN\n\n**计算设计的纳米结合剂作为诊断与治疗应用中的亲和配体**  \n全珠恩、Q. 约翰·刘、禹贤庆、伊莎贝尔·巴斯、崔允贞、L. 杰西卡·桑、李学浩  \n[J. Am. Chem. Soc.(2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Fjacs.5c11289) • 基于RFDiffusion\u002FProteinMPNN\n\n**使用BinderFlow实现自动化且模块化的蛋白质结合剂设计**  \n卡洛斯·查孔-桑切斯、纳伊姆·冈萨雷斯-罗德里格斯、奥斯卡·略尔卡、拉斐尔·费尔南德斯-莱罗  \n[bioRxiv 2025.09.10.675490](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.10.675490v2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F18\u002F2025.09.10.675490\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fbinderflow) • 基于RFDiffusion\u002FProteinMPNN\n\n**使用RFdiffusion3进行全原子级生物分子相互作用的从头设计**  \n贾斯珀·肯尼思·维耶·布彻、罗希特·克里希纳、拉克提姆·米特拉、拉斐尔·艾萨克·布伦特、李燕京、纳撒尼尔·科尔利、保罗·金、乔纳森·芬克、西蒙·瓦伦丁·马蒂斯、萨曼·萨利克、爱子·村石、海伦·艾森纳赫、图斯坎·洛克·汤普森、陈洁、尤利娅·波利坦斯卡、恩尼莎·塞加尔、布莱恩·科文特里、奥丁·张、薄强、基兰·迪迪、麦克斯韦尔·卡兹曼、弗兰克·迪马约、大卫·贝克  \n[bioRxiv 2025.09.18.676967](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.18.676967v2) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F18\u002F2025.09.18.676967\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FRosettaCommons\u002Ffoundry)\n\n**基于人工智能指导的环肽结合剂设计，靶向TREM2：利用CycleRFdiffusion并经实验验证**  \n曹成佑、朱仁杰、卡塔日娜·昆采维奇、段洪亮、穆斯塔法·加布尔  \n[bioRxiv 2025.09.18.676322](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.18.676322v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F09\u002F21\u002F2025.09.18.676322\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**ProteinDJ：高性能且模块化的蛋白质设计流程**  \n迪伦·希尔克、朱莉·伊斯坎德尔、潘俊奇、安德鲁·P·汤普森、安东尼·T·帕彭福斯、伊莎贝尔·S·卢塞特、乔舒亚·M·哈迪  \n[bioRxiv 2025.09.24.678028](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.24.678028v1)\u002F[Protein Science. 2026](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70464)\n\n**基于计算的表位图谱分析与人工智能驱动的蛋白质工程，实现结核分枝杆菌多表位疫苗的理性设计**  \n李新峰、陶欣宇、钟明月、王一瑶、薛恒、宾达·T·安东马、周善浩、魏洪平、何进、杨航  \n[计算与结构生物技术杂志（2025年）](https:\u002F\u002Fwww.csbj.org\u002Farticle\u002FS2001-0370(25)00375-7)\n\n**pH敏感结合蛋白的计算设计**  \n格林·安、布赖恩·科文特里、艾拉·海夫纳、沙扬·萨德雷、珍妮·胡、米莫萨·范、黄步伟、艾萨克·萨平顿、亚当·J·布罗尔曼、毛里茨·A·利希滕斯坦、马蒂亚斯·格勒格尔、因娜·戈列什尼克、迪昂妮·瓦菲阿多斯、大卫·贝克  \n[bioRxiv 2025.09.29.678932](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.29.678932v1)\n\n**从头设计磷酸化酪氨酸肽结合蛋白**  \n马格努斯·S·鲍尔、张志坚、吴凯嘉、李圭丽、布赖恩·科文特里、科迪·A·克鲁普特、史久涵、拉斐尔·I·布伦特、李欣婷、卡罗琳娜·莫勒、妮可·鲁耶、迪昂妮·K·瓦菲阿多斯、因德雷克·卡尔韦特、丽贝卡·K·斯科特海姆、朱思宇、阿米尔·莫特曼、卢卡·C·赫尔曼、帕斯卡尔·施图尔姆费尔斯、道格·提舍尔、韩·劳特·阿尔泰-特兰、大卫·尤尔根斯、罗希特·克里希纳、伍迪·阿亨、詹森·尹、阿西姆·K·贝拉、亚历克斯·康、艾米莉·乔伊斯、安德鲁·卢、兰斯·斯图尔特、弗兰克·迪马约、大卫·贝克  \n[bioRxiv 2025.09.29.678898](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.09.29.678898v1)\n\n**RNA及核蛋白复合物的从头设计**  \n安德鲁·H·法沃、莱利·奎哈诺、叶利扎维塔·切尔诺娃、安德鲁·库巴内伊、康纳·魏德尔、摩根·A·埃斯勒、莉莲·麦克休、安·卡尔、夏阳、大卫·尤尔根斯、肯尼思·D·卡尔、保罗·T·金、尤利娅·波利坦斯卡、埃尼莎·塞加尔、保罗·S·权、罗伯特·J·佩科拉罗、卡梅隆·格拉斯科克、安德鲁·J·博斯特、弗兰克·迪马约、巴里·L·斯托达德、大卫·贝克  \n[bioRxiv 2025.10.01.679929](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.01.679929v1)\n\n**细胞因子受体相互作用的几何调控可调节合成激动剂信号传导**  \n马克·埃克斯波西特、穆罕默德·阿贝迪、阿迪蒂亚·克里希纳库马尔、舒鲁蒂·贾因、余太乙、蒂莫西·R·赫库斯、迪维杰·马修、索菲·格雷-盖亚尔、陈志杰、威廉·S·格鲁布、安德鲁·法沃、温妮·L·坎、托马斯·施利希特哈尔勒、陈伟、迈克尔·W·帕克、胡安·L·门多萨、安赫尔·F·洛佩斯、E·约翰·韦里、大卫·贝克  \n[bioRxiv 2025.10.12.681819](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.12.681819v1)\n\n**高通量从头蛋白质设计产生新型免疫调节激动剂**  \n穆罕默德·阿贝迪、马克·埃克斯波西特、布赖恩·科文特里、迪维杰·马修、舒鲁蒂·贾因、阿迪蒂亚·克里希纳库马尔、因娜·戈列什尼克、索菲·L·格雷-盖亚尔、玛格丽特·伦恩-哈尔伯特、余太乙、马蒂亚斯·格勒格尔、乌玛·米切尔、里亚·凯什里、春重浩、汉内勒·鲁霍拉-贝克、E·约翰·韦里、大卫·贝克  \n[bioRxiv 2025.10.12.681920](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.12.681920v1)\n\n**自下而上设计具有明确选择性滤器几何结构的Ca2+通道**  \n刘玉来、康纳·魏德尔、柳比察·米哈列维奇、约瑟夫·L·沃森、李哲、乐·特蕾西·余、萨加迪普·马朱姆达尔、安德鲁·J·博斯特、肯尼思·D·卡尔、瑞安·D·基布勒、塔梅尔·M·加马尔·埃尔丁、威廉·A·卡特罗尔以及大卫·贝克  \n[自然杂志（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09646-z) • [代码](https:\u002F\u002Fgithub.com\u002Fylliu15\u002F2025_Ca_channel)\n\n**利用设计的CEA结合蛋白递送p53蛋白和TCF\u002FLEF转录因子诱饵DNA，靶向抑制结直肠癌**  \n王文、孙璇和吴耿  \n[国际分子科学杂志，2025年](https:\u002F\u002Fwww.mdpi.com\u002F1422-0067\u002F26\u002F20\u002F9846) • [补充材料](https:\u002F\u002Fwww.mdpi.com\u002Farticle\u002F10.3390\u002Fijms26209846\u002Fs1) • 基于RFDiffusion\u002FProteinMPNN\n\n**用于迷你蛋白结合剂优先级排序的混合AI\u002F物理流程：以BRD3 ET结构域为例**  \n乔肯特·加萨、莫妮卡·J·罗斯、盖塔诺·T·蒙特利奥内和阿尔贝托·佩雷斯  \n[化学通讯（2025年）](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlelanding\u002F2025\u002Fcc\u002Fd5cc05032d) • [代码](https:\u002F\u002Fgithub.com\u002FPDNALab\u002FMiniprotein_Design)\n\n**通过最大化氢键作用进行超稳定蛋白质的计算设计**  \n郑斌、陆卓健、王尚辰、刘立超、敖明俊、周雨睿、唐国静、王瑞石、刘元昊、张瀚天、孟银英、邱军、冯天富、王子怡、刘仁明、肖跃龙、刘宇彤、王梓凌、黄依芬、姜雅君及郑鹏  \n[自然化学（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41557-025-01998-3)\n\n**高亲和力HER2靶向蛋白迷你结合剂的从头设计**  \n赵义泽、魏文平、程子俊、杨敏和严云俊  \n[生物分子第15卷第11期（2025年）](https:\u002F\u002Fwww.mdpi.com\u002F2218-273X\u002F15\u002F11\u002F1587)\n\n**用于探测气体通道并提高[NiFe]氢酶氧耐受性的蛋白质结合剂的从头设计**  \n孙璇、李文瑾、李旺哲、罗航、肖琪、张乐言、范怡琳、蒋培宇、吴耿、张丽云  \n[bioRxiv 2025.11.19.689374](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.19.689374v1)\n\n**金属蛋白酶的计算设计**  \n陈安琪、吴凯嘉、崔浩宰、普里塔姆·文卡特什、塞缪尔·J·佩洛克、尼基塔·哈尼克尔、布赖恩·科文特里、金东孝、塞思·M·伍德伯里、季鹏飞、本田真吾、李欣婷、斯泰西·格尔本、勒穆埃尔·张、萧燕、安东尼·A·海曼、唐纳德·希尔弗特、大卫·贝克  \n[bioRxiv 2025.11.20.689622](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.20.689622v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F11\u002F22\u002F2025.11.21.689622\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**半胱氨酸蛋白酶的计算设计**  \n崔浩宰、布赖恩·科文特里、马格努斯·鲍尔、普里塔姆·文卡特什、陈安琪、金东孝、阿西姆·K·贝拉、亚历克斯·康、汉娜·阮、艾米莉·乔伊斯、巴努马蒂·香卡拉恩、图斯坎·洛克·汤普森、雅各布·默尔·格什恩、亚历山大·F·希达、李圭丽、唐纳德·希尔弗特、塞缪尔·J·佩洛克、大卫·贝克  \n[bioRxiv 2025.11.21.689808](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.21.689808v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F11\u002F22\u002F2025.11.21.689808\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**肽掩蔽的从头设计实现条件活性迷你蛋白结合剂的快速生成**  \n蒙塞拉特·埃斯科巴尔-罗萨莱斯、克里斯蒂娜·蒙塔内尔、马克·埃克斯波西特、罗伯塔·卢奇、克里斯蒂娜·迪亚斯-佩尔拉斯、大卫·贝克、本哈米·奥列尔-萨尔维亚  \n[美国化学会杂志（2025年）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002Ffull\u002F10.1021\u002Fjacs.5c16108)\n\n**Ovo：一个用于从头蛋白质设计的开源生态系统**  \n大卫·普里霍达、马可·安科纳、特蕾莎·卡洛诺娃、亚当·克拉尔、卢卡斯·波拉克、雨果·赫尔班、尼古拉斯·J·狄更斯、丹尼·阿舍·比特顿  \n[bioRxiv 2025.11.27.691041](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.11.27.691041v1) • [代码](https:\u002F\u002Fgithub.com\u002FMSDLLCpapers\u002Fovo)\n\n**机器学习助力恶性疟原虫环子孢子蛋白从头多表位设计，以靶向三聚体L9抗体**  \nJ. Andrew D. Nelson、Samuel E. Garfinkle、Zi Jie Lin、Joyce Park、Amber J. Kim、Kelly Bayruns、Madison E. McCanna、Kylie M. Konrath、Colby J. Agostino、Daniel W. Kulp、Daniel.Kulp、Audrey R. Odom John及Jesper Pallesen  \n[《美国国家科学院院刊》122卷第49期（2025年）](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2512358122)\n\n**利用深度学习精确搭建三个非重叠蛋白质表位的单域支架**  \nKarla M. Castro、Joseph L. Watson、Jue Wang、Joshua Southern、Reyhaneh Ayardulabi、Sandrine Georgeon、Stéphane Rosset、David Baker及Bruno E. Correia  \n[Nat Chem Biol（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-02083-z)\n\n**基于催化基序支架的酶计算设计**  \nMarkus Braun、Adrian Tripp、Morakot Chakatok、Sigrid Kaltenbrunner、Celina Fischer、David Stoll、Aleksandar Bijelic、Wael Elaily、Massimo G. Totaro、Melanie Moser、Shlomo Y. Hoch、Horst Lechner、Federico Rossi、Matteo Aleotti、Mélanie Hall及Gustav Oberdorfer  \n[Nature（2025年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09747-9) • [代码链接](https:\u002F\u002Fgithub.com\u002Fmabr3112\u002Friff_diff_protflow)\n\n**集成功能基序的蛋白质纳米颗粒从头设计**  \nCyrus M Haas、Sanela Rankovic、Hanul K Lewis、Kenneth D Carr、Connor Weidle、Sophie S Gerdes、Lily R Nuss、Felicitas Ruiz、Syed Moiz、Maggie Fiorelli、Emily Grey、Jackson McGowan、Nikhila Kumar、Adrian Creanga、Alex Kang、Hannah Nguyen、Yanqing Wang、Banumathi Sankaran、Annie Dosey、Rashmi Ravichandran、Asim K Bera、Elizabeth M Leaf、Cole A DeForest、Masaru Kanekiyo、Andrew J Borst、Neil P King  \n[bioRxiv 2025.12.19.695620](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.19.695620v2) • [代码链接](https:\u002F\u002Fgithub.com\u002Fkinglab-uiuc\u002FDeNovoNano-2026)\n\n**靶向DELE1以抑制线粒体应激反应的蛋白质结合剂从头设计**  \nRui Yang、Kaiyuan Zheng、McGuire Metts、Yiluo Wang、Danyan Yin、Kevin P. Li、Agnieszka A. Prazmowska、David F. Kashatus、Brian Kuhlman、Jie Yang  \n[bioRxiv 2025.12.22.695711](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2025.12.22.695711v1)\n\n**作为潜在甜味蛋白的人类甜味受体靶向蛋白质结合剂的从头设计**  \nSaisai Ding、Yi Zhang  \n[arXiv:2601.14574](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.14574)\n\n**在设计的蛋白质组装体中模板化并限制磷酸钙矿化**  \nLe Tracy Yu、Harley Pyles、Xinqi Li、Andrew J. Borst、Neville P. Bethel、Paul S. Kwon、Connor Weidle、Ryan D. Kibler、Kenneth D. Carr、Yulai Liu、Stanislav Moroz、Shuai Zhang、James De Yoreo、David Baker  \n[bioRxiv 2026.01.14.699524](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.01.14.699524v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F01\u002F14\u002F2026.01.14.699524\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**强效CRISPR–Cas13抑制剂的从头设计**  \nCyntia Taveneau、Her Xiang Chai、Jovita D’Silva、Rebecca S. Bamert、Honglin Chen、Brooke K. Hayes、Roland W. Calvert、Jacob Purcell、Daniel J. Curwen、Fabian Munder、Lisandra L. Martin、Jeremy J. Barr、Joseph Rosenbluh、Mohamed Fareh、Rhys Grinter及Gavin J. Knott  \n[Nat Chem Biol（2026年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41589-025-02136-3)\n\n**RFdiffusion设计的小型蛋白质结合SARS-CoV-2核衣壳蛋白的实验分析**  \nZeenat Khakerwala、Ashwani Kumar、Sujay S Gaikwad、Truptimayee Barik、Shweta Singh、Gagan Deep Gupta、Ravindra D Makde  \n[Protein Engineering, Design and Selection，2026年](https:\u002F\u002Facademic.oup.com\u002Fpeds\u002Fadvance-article-abstract\u002Fdoi\u002F10.1093\u002Fprotein\u002Fgzag004\u002F8471194)\n\n**基于肽基序支架的蓝色黑色素计算设计**  \nDi Sheng Lee、Bomi Park、Sergio Salgado、James Dolgin、David L. Kaplan  \n[bioRxiv 2026.02.02.703104](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.02.703104v1.full)\n\n**GPCR外框架调节剂的从头设计**  \nShizhuo Cheng、Jia Guo、Yun-li Zhou、Xumei Luo、Gufang Zhang、Ya-zhi Zhang、Yixin Yang、Jiannan Xie、Ping Xu、Dan-dan Shen、Shaokun Zang、Huicui Yang、Xuechu Zhen、Min Zhang及Yan Zhang  \n[Nature（2026年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-025-09957-1)\n\n**用设计的bioPROTAC重新编程CAR T细胞**  \nVivek S Peche、Sebastian Kenny、Tae Gun Kang、Brian Coventry、Tian Mi、Inna Goreshnik、Mariana Garcia Sanchez、Reid Martin、Macey Smith、Dionne Vafeados、Rahul S Kathayat、Yu Kaiwen、Zuo-Fei Yuan、Long Wu、Anthony High、Andrew Nemecek、Elizabeth Wickmann、Adeleye Adeshakin、Francesca Ferrara、Robert E Throm、Taosheng Chen、Benjamin Youngblood、David Baker、Stephen Gottschalk  \n[bioRxiv 2026.02.21.706835](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.21.706835v1)\n\n**金黄色葡萄球菌外排转运蛋白NorA的小型蛋白质抑制剂**  \nPriyanka Mishra、Adam Chazin-Gray、Gaëlle Lamon、David Kim、David Baker、Nathaniel J. Traaseth  \n[bioRxiv 2026.03.05.709893](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.05.709893v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F05\u002F2026.03.05.709893\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**靶向补体C9以阻断膜攻击复合物组装的小型蛋白质抑制剂设计**  \nBing He、Chenchen Qin、Yu Zhao、Long-Kai Huang、Zihan Wu、Fang Wang、Fandi Wu、Fan Yang及Jianhua Yao  \n[Nat Commun（2026年）](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-026-70667-x)\n\n### 6.4 基于CNN\n\n**利用表面指纹从头设计位点特异性蛋白质结合剂**\nPablo Gainza、Sarah Wehrle、Alexandra Van Hall-Beauvais、Anthony Marchand、Andreas Scheck、Zander Harteveld、Stephen Buckley、Dongchun Ni、Shuguang Tan、Freyr Sverrisson、Casper Goverde、Priscilla Turelli、Charlène Raclot、Alexandra Teslenko、Martin Pacesa、Stéphane Rosset、Sandrine Georgeon、Jane Marsden、Aaron Petruzzella、Kefang Liu、Zepeng Xu、Yan Chai、Pu Han、George F. Gao、Elisa Oricchio、Beat Fierz、Didier Trono、Henning Stahlberg、Michael Bronstein、Bruno E. Correia\n[Protein Science 30.CONF (2021)](https:\u002F\u002Finfoscience.epfl.ch\u002Frecord\u002F290120)\u002F[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.06.16.496402v2)\u002F[Nature (2023)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-05993-x) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2022\u002F06\u002F17\u002F2022.06.16.496402\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [masif_seed](https:\u002F\u002Fgithub.com\u002FLPDI-EPFL\u002Fmasif_seed) • [masif](https:\u002F\u002Fgithub.com\u002FLPDI-EPFL\u002Fmasif) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4S4J7gbhAa0)\n\n**利用可泛化的深度学习方法靶向蛋白质-配体新表面**\nAnthony Marchand、Stephen Buckley、Arne Schneuing、Martin Pacesa、Pablo Gainza、Evgenia Elizarova、Rebecca Manuela Neeser、Pao-Wan Lee、Luc Reymond、Maddalena Elia、Leo Scheller、Sandrine Georgeon、Joseph Schmidt、Philippe Schwaller、Sebastian Josef Maerkl、Michael Bronstein、Bruno Emmanuel Correia\n[bioRxiv 2024.03.25.585721](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.25.585721v1)\u002F[Nature (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-024-08435-4) • [补充材料](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41586-024-08435-4\u002FMediaObjects\u002F41586_2024_8435_MOESM1_ESM.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FLPDI-EPFL\u002Fmasif-neosurf) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=setIzkcEAVs)\n\n**绘制人类表面组中可靶向位点以设计新型结合剂**\nPetra E. M. Balbi、Ahmed Sadek、Anthony Marchand、Ta-Yi Yu、Sandrine Georgeon、Joseph Schmidt、Simone Fulle、Che Yang、Hamed Khakzad 和 Bruno E. Correia  \n[bioRxiv 2024.12.16.628626](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.12.16.628626v1)\u002F[Proc. Natl. Acad. Sci.](https:\u002F\u002Fwww.pnas.org\u002Fdoi\u002F10.1073\u002Fpnas.2506269123) • [代码](https:\u002F\u002Fgithub.com\u002Fhamedkhakzad\u002FSURFACE-Bind) • [网站](https:\u002F\u002Fsurface-bind.inria.fr\u002F)\n\n**AutoBinder Agent：基于MCP的端到端蛋白质结合剂设计代理**  \nFukang Ge、Jiarui Zhu、Linjie Zhang、Haowen Xiao、Xiangcheng Bao、Fangnan Xie、Danyang Chen、Yanrui Lu、Yuting Wang、Ziqian Guan、Lin Gu、Jinhao Bi、Yingying Zhu\n[arXiv:2602.00019](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.00019)\n\n### 6.5 基于GNN\n\n**用于抗体序列-结构协同设计的迭代精炼图神经网络**\nWengong Jin、Jeremy Wohlwend、Regina Barzilay、Tommi Jaakkola\n[arXiv预印本 arXiv:2110.04624 (2021)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.04624) • [RefineGNN](https:\u002F\u002Fgithub.com\u002Fwengong-jin\u002FRefineGNN) • [讲座1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=uDTccbg_Ai4)、[讲座2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=px5iC79jtfc)\n\n**利用约束能量模型设计抗体互补决定区（CDR）**\nFu、Tianfan 和 Jimeng Sun\n[第28届ACM SIGKDD知识发现与数据挖掘会议论文集，2022年](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3534678.3539285) • [代码](https:\u002F\u002Fgithub.com\u002Ffutianfan\u002Fenergy_model4antibody_design)\n\n**作为3D等变图转换的条件性抗体设计**\nXiangzhe Kong、Wenbing Huang、Yang Liu\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=LFHFQbjxIiP)\u002F[arXiv:2208.06073](https:\u002F\u002Farxiv.org\u002Fabs\u002F2208.06073)\n\n**端到端全原子抗体设计**\nXiangzhe Kong、Wenbing Huang、Yang Liu\n[arXiv:2302.00203](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.00203) • [代码](https:\u002F\u002Fgithub.com\u002FTHUNLP-MT\u002FdyMEAN)\n\n**AbODE：利用联合ODE从头设计抗体**\nYogesh Verma、Markus Heinonen、Vikas Garg\n[arXiv:2306.01005](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.01005)\n\n**基于基序的蛋白质序列与结构联合设计**\nZhenqiao Song、Yunlong Zhao、Yufei Song、Wenxian Shi、Yang Yang、Lei Li\n[arXiv:2310.02546](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.02546)\n\n**利用几何矢量场网络从头设计蛋白质**\nWeian Mao、Muzhi Zhu、Zheng Sun、Shuaike Shen、Lin Yuanbo Wu、Hao Chen、Chunhua Shen\n[arXiv:2310.11802](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.11802)\u002F[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=9UIGyJJpay)\n\n**几何图神经网络综述：数据结构、模型与应用**\nJiaqi Han、Jiacheng Cen、Liming Wu、Zongzhao Li、Xiangzhe Kong、Rui Jiao、Ziyang Yu、Tingyang Xu、Fandi Wu、Zihe Wang、Hongteng Xu、Zhewei Wei、Yang Liu、Yu Rong、Wenbing Huang\n[arXiv:2403.00485](https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.00485) • 综述\n\n**GeoAB：迈向更真实的抗体设计与可靠的亲和力成熟**\nHaitao LIN、Lirong Wu、Huang Yufei、Yunfan Liu、Odin Zhang、Yuanqing Zhou、Rui Sun、Stan Z Li\n[bioRxiv 2024.05.15.594274](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.15.594274v1)\u002F[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=6pHP51F55x) • [代码](https:\u002F\u002Fgithub.com\u002FEdapinenut\u002FGeoAB)\n\n**拓扑神经网络走向持久化、等变性和连续性**\nYogesh Verma、Amauri H Souza、Vikas Garg\n[arXiv:2406.03164](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.03164) • [代码](https:\u002F\u002Fgithub.com\u002FAalto-QuML\u002FTopNets)\n\n**面向表位未知抗体设计及特异性优化的关系感知等变图网络**\nLirong Wu、Haitao Lin、Yufei Huang、Zhangyang Gao、Cheng Tan、Yunfan Liu、Tailin Wu、Stan Z. Li\n[arXiv:2501.00013](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.00013) • [代码](https:\u002F\u002Fgithub.com\u002FLirongWu\u002FRAAD)\n\n**迈向更精确的全原子抗体协同设计**\nJiayang Wu、Xingyi Zhang、Xiangyu Dong、Kun Xie、Ziqi Liu、Wensheng Gan、Sibo Wang、Le Song\n[arXiv:2502.19391](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.19391)\u002F[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=1VLdFJFWhL)\n\n**NanoDesigner：通过迭代精炼解决复杂–CDR相互依赖问题**\nMelissa Maria Rios Zertuche、Şenay Kafkas、Dominik Renn、Magnus Rueping、Robert Hoehndorf\n[bioRxiv 2025.02.25.640028](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.02.25.640028v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F03\u002F01\u002F2025.02.25.640028\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fbio-ontology-research-group\u002FNanoDesigner) • 基于dyMEAN\n\n### 6.6 基于 Transformer 的方法\n\n**具有等变平移不变性的蛋白质序列与结构协同设计**  \n史辰策、王传睿、陆嘉睿、钟博子涛、唐健  \n[arXiv:2210.08761](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.08761)\u002F[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=pRCMXcfdihq) • [补充材料](https:\u002F\u002Fopenreview.net\u002Fattachment?id=pRCMXcfdihq&name=supplementary_material) • [代码](https:\u002F\u002Fgithub.com\u002Fshichence\u002FProtSeed)\n\n**用于灵活且位点特异性蛋白质对接与设计的深度学习**  \n马特·麦克帕特隆、许进波  \n[bioRxiv 2023.04.01.535079](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.04.01.535079v1) • [代码](https:\u002F\u002Fgithub.com\u002Fdrorlab\u002FDIPS)\n\n**通过迭代精炼进行全原子蛋白质口袋设计**  \n张在熙、卢泽普、郝仲凯、马林卡·齐特尼克、刘琪  \n[arXiv:2310.02553](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.02553) • [代码](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FFAIR)\n\n**基于功能几何引导的蛋白质序列与主链结构协同设计**  \n匿名  \n[ICLR 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=Dr4qD9bzZd)\n\n**利用 tFold 快速准确地建模与设计抗体-抗原复合物**  \n吴凡迪、赵宇、吴家祥、姜彪斌、何兵、黄龙凯、秦晨晨、杨帆、黄宁乔、肖阳、王汝波、贾华贤、荣宇、刘宇义、赖厚廷、徐挺洋、刘伟、赵培琳、姚建华  \n[bioRxiv 2024.02.05.578892](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.05.578892v1) • [官网](https:\u002F\u002Fdrug.ai.tencent.com\u002Fcn)\n\n**PocketGen：生成全原子配体结合蛋白质口袋**  \n张在熙、沈万翔、刘琪、马林卡·齐特尼克  \n[bioRxiv 2024.02.25.581968](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.02.25.581968v1)\u002F[Nature Machine Intelligence, 2024](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-024-00920-9) • [代码](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FPocketGen) • [官网](https:\u002F\u002Fzitniklab.hms.harvard.edu\u002Fprojects\u002FPocketGen\u002F)\n\n**用语言模型模拟五亿年的进化**  \n托马斯·海耶斯、罗山·拉奥、哈利尔·阿金、尼古拉斯·詹姆斯·索弗罗涅夫、德尼兹·奥克泰、林泽明、罗伯特·维尔库伊尔、文森特·奎·陈、乔纳森·迪顿、马里乌斯·维格特、罗希尔·巴德昆德里、伊鲁姆·沙夫卡特、龚俊、亚历山大·德里、劳尔·圣地亚哥·莫利纳、尼尔·托马斯、优素福·汗、切坦·米什拉、卡罗琳·金、利亚姆·J·巴蒂、帕特里克·D·许、汤姆·塞尔库、萨尔瓦托雷·坎迪多、亚历山大·里夫斯  \n[预印本](https:\u002F\u002Fevolutionaryscale-public.s3.us-east-2.amazonaws.com\u002Fresearch\u002Fesm3.pdf)\u002F[bioRxiv 2024.07.01.600583](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.01.600583v1)\u002F[Science (2025): eads0018](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.ads0018) • [官网](https:\u002F\u002Fwww.evolutionaryscale.ai\u002Fblog\u002Fesm3-release) • [代码](https:\u002F\u002Fgithub.com\u002Fevolutionaryscale\u002Fesm) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fevolutionaryscale\u002Fesm\u002Fblob\u002Fmain\u002Fexamples\u002Fgenerate.ipynb) • [新闻](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-02214-x)\n\n**迈向基于多模态语言模型的蛋白质序列与结构协同设计**  \n卢哲文、Stephen_Zhewen_Lu、陆嘉睿、郭洪宇、唐健  \n[ICLR 2025 工作坊 LMRL](https:\u002F\u002Fopenreview.net\u002Fforum?id=QLszcahdXR) • 基于 ESM3\n\n**利用 ProteinZen 进行 SE(3) 流匹配的全原子蛋白质设计**  \n亚历克斯·J·李、坦雅·科尔特梅  \n[bioRxiv 2025.10.18.683228](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.10.18.683228v1) • [代码](https:\u002F\u002Fgithub.com\u002Falexjli\u002Fproteinzen)\n\n**基于蛋白质文本描述从头设计氨基酸序列——ProtDAT**  \n郭晓宇、李一凡、刘源、潘晓勇及沈鸿彬  \n[Nat Commun 16, 10544 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-025-65562-w) • [代码](https:\u002F\u002Fgithub.com\u002FGXY0116\u002FProtDAT\u002Ftree\u002Fv1.0.0) • [官网](http:\u002F\u002Fwww.csbio.sjtu.edu.cn\u002Fbioinf2\u002FProtDAT\u002F)\n\n**配体指导的从头功能性酶序列—结构协同设计**  \n宋振桥、刘慧冲、赵云龙、杨阳、李磊  \n[bioRxiv 2026.03.02.709205](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.02.709205v1) • [代码](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F04\u002F2026.03.02.709205\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n### 6.7 基于 MLP 的方法\n\n**具有交叉门控 MLP 的蛋白质复合物不变性嵌入是一次性抗体设计师**  \n陈诚、高章阳、Stan Z. Li  \n[arXiv:2305.09480](https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.09480)\n\n**基于热点驱动的多片段自回归扩展肽段设计**  \n李佳涵、陈彤、罗世通、程超然、关佳琪、郭瑞涵、王晟、刘戈、彭健、马建柱  \n[arXiv:2411.18463](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.18463)\n\n### 6.8 基于流的方法\n\n**离散状态空间上的生成流：实现多模态流并应用于蛋白质协同设计**\nAndrew Campbell、Jason Yim、Regina Barzilay、Tom Rainforth、Tommi Jaakkola\n[arXiv:2402.04997](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.04997) • [代码](https:\u002F\u002Fgithub.com\u002Fandrew-cr\u002Fdiscrete_flow_models) • [讲座](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=yzc29vhM2Aw)\n\n**PPFlow：基于扭转流匹配的靶向肽设计**\nHaitao Lin、Odin Zhang、Huifeng Zhao、Dejun Jiang、Lirong Wu、Zicheng Liu、Yufei Huang、Stan Z. Li\n[bioRxiv 2024.03.07.583831](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.07.583831v1)\u002F[arXiv:2405.06642](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.06642) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2024\u002F03\u002F08\u002F2024.03.07.583831\u002FDC1\u002Fembed\u002Fmedia-1.zip) • [代码](https:\u002F\u002Fgithub.com\u002FEDAPINENUT\u002Fppflow)\n\n**基于多模态流匹配的全原子肽设计**\nJiahan Li、Chaoran Cheng、Zuofan Wu、Ruihan Guo、Shitong Luo、Zhizhou Ren、Jian Peng、Jianzhu Ma\n[arXiv:2406.00735](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.00735) • [代码](https:\u002F\u002Fgithub.com\u002FCed3-han\u002FPepFlowww)\n\n**AntibodyFlow：用于设计抗体互补决定区的归一化流模型**\nBohao Xu、Yanbo Wang、Wenyu Chen、Shimin Shan\n[arXiv:2406.13162](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.13162)\n\n**基于先验信息流匹配的通用蛋白质口袋生成**\nZaixi Zhang、Marinka Zitnik、Qi Liu\n[arXiv:2409.19520](https:\u002F\u002Farxiv.org\u002Fabs\u002F2409.19520)\n\n**D-Flow：用于D-肽设计的多模态流匹配**\nFang Wu、Tinson Xu、Shuting Jin、Xiangru Tang、Zerui Xu、James Zou、Brian Hie\n[arXiv:2411.10618](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.10618) • [代码](https:\u002F\u002Fgithub.com\u002Fsmiles724\u002FPeptideDesign)\n\n**FlowDesign：通过流匹配和更优的先验分布改进抗体CDR的设计**\nJun Wu、Xiangzhe Kong、Ningguan Sun、Jing Wei、Sisi Shan、Fuli Feng、Feng Wu、Jian Peng、Linqi Zhang、Yang Liu、Jianzhu Ma\n[bioRxiv 2024.11.07.622422](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.11.07.622422v2)\u002F[Cell Systems (2025)](https:\u002F\u002Fwww.cell.com\u002Fcell-systems\u002Fabstract\u002FS2405-4712(25)00103-6) • [代码](https:\u002F\u002Fgithub.com\u002Fnohandsomewujun\u002FFlowDesign)\n\n**反应条件驱动的从头酶设计与GENzyme**\nChenqing Hua、Jiarui Lu、Yong Liu、Odin Zhang、Jian Tang、Rex Ying、Wengong Jin、Guy Wolf、Doina Precup、Shuangjia Zheng\n[arXiv:2411.16694](https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.16694) • [代码](https:\u002F\u002Fgithub.com\u002FWillHua127\u002FGENzyme)\n\n**ProteinZen：结合潜在空间与SE(3)流匹配，用于全原子蛋白质生成**\nAlex Li、Tanja Kortemme\n[2024年NeurIPS结构生物学机器学习研讨会](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FProteinZen:_combining_latent_and_SE(3)_flow_matching_for_all-atom_protein_generation.pdf)\n\n**HelixFlow：SE(3)等变的全原子肽设计，采用流匹配模型**\nXuezhi Xie、Pedro A Valiente、Jisun Kim、Jin Sub Lee、Philip Kim\n[2024年NeurIPS结构生物学机器学习研讨会](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FHelixFlow,_SE(3)–equivariant_Full-atom_Design_of_Peptides_With_Flow-matching_Models.pdf)\n\n**IgFlow：用于从头抗体设计的流匹配**\nSanjay Nagaraj、Amir Shanehsazzadeh、Hyun Park、Jonathan King、Simon Levine\n[2024年NeurIPS结构生物学机器学习研讨会](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2024\u002FIgFlow:_Flow_Matching_for_De_Novo_Antibody_Design.pdf)\n\n**基于表面的多模态流匹配肽设计**\nFang Wu、Shuting Jin、xiangxiang Zeng、Jure Leskovec、Jinbo Xu\n[ICLR 2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=MeCPwqrm19)\n\n**用于全原子肽设计的非线性流匹配**\nDengdeng Huang、Shikui Tu\n[arXiv:2502.15855](https:\u002F\u002Farxiv.org\u002Fabs\u002F2502.15855)\n\n**dyAb：基于AlphaFold驱动的抗原预结合，用于柔性抗体设计的流匹配**\nCheng Tan、Yijie Zhang、Zhangyang Gao、Yufei Huang、Haitao Lin、Lirong Wu、Fandi Wu、Mathieu Blanchette、Stan. Z. Li\n[arXiv:2503.01910](https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.01910) • [代码](https:\u002F\u002Fgithub.com\u002FA4Bio\u002FdyAb)\n\n**GeoFlow-V2：统一的原子扩散模型，用于蛋白质结构预测和从头设计**\nBioGeometry团队\n[预印本](https:\u002F\u002Fopen-res.biogeom.com\u002Fgeoflow-v2\u002Ftechnical-report.pdf) • [网站](https:\u002F\u002Fprot.design\u002F) • 商业化\n\n**通过离散流匹配进行全原子逆向蛋白质折叠**\nKai Yi、Kiarash Jamali、Sjors HW Scheres\n[ICML 2025海报](https:\u002F\u002Fopenreview.net\u002Fforum?id=8tQdwSCJmA)\n\n**通过生成流在离散空间中协同设计蛋白质序列和结构**\nSen Yang、Lingli Ju、Cheng Peng、JiangLin Zhou、Yamin Cai、Dawei Feng\n[Bioinformatics, 2025](https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtaf248\u002F8123382) • [代码](https:\u002F\u002Fgithub.com\u002FLtECoD\u002FCoFlow) • [模型](https:\u002F\u002Fzenodo.org\u002Frecords\u002F14842367)\n\n**La-Proteina：通过部分潜在流匹配进行原子级蛋白质生成**\nTomas Geffner、Kieran Didi、Zhonglin Cao、Danny Reidenbach、Zuobai Zhang、Christian Dallago、Emine Kucukbenli、Karsten Kreis、Arash Vahdat\n[arXiv:2507.09466](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.09466) • [网站](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fla-proteina\u002F)\n\n**利用流匹配设计含有非经典氨基酸的肽**\nJin Sub Lee、Philip M Kim\n[bioRxiv 2025.07.31.667780](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.31.667780v1)\n\n**探究侧链对从头蛋白质设计的影响**\nCooper Svajda、Joshua Yuan\n[bioRxiv 2025.08.08.669410](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.08.08.669410v1)\n\n**基于潜在靶点ATP5A的胶质母细胞瘤治疗性肽的生成设计与验证**\nHao Qian、Pu You、Lin Zeng、Jingyuan Zhou、Dengdeng Huang、Kaicheng Li、Shikui Tu、Lei Xu\n[arXiv:2512.02030](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.02030v1)\n\n**AbFlow：基于交互增强流匹配的端到端互补位中心抗体设计**\nWenda Wang、Yang Zhang、Zhewei Wei、Wenbing Huang\n[arXiv:2602.07084](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.07084) • [代码](https:\u002F\u002Fgithub.com\u002FWangWenda87\u002FAbFlow)\n\n**面向蛋白质设计与构象集合的刚性感知几何预训练**\nZhanghan Ni、Yanjing Li、Zeju Qiu、Bernhard Schölkopf、Hongyu Guo、Weiyang Liu、Shengchao Liu\n[arXiv:2603.02406](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.02406)\n\n**通过生成式预训练与测试时计算扩展原子级蛋白质结合剂设计**\nKieran Didi、Zuobai Zhang、Guoqing Zhou、Danny Reidenbach、Zhonglin Cao、Sooyoung Cha、Tomas Geffner、Christian Dallago、Jian Tang、Michael M. Bronstein、Martin Steinegger、Emine Kucukbenli、Arash Vahdat、Karsten Kreis\n[ICLR 2026口头报告](https:\u002F\u002Fopenreview.net\u002Fforum?id=qmCpJtFZra)\u002F[湿实验论文](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fproteina-complexa\u002Fassets\u002Fproteina_complexa_validation.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FNVIDIA-Digital-Bio\u002Fproteina-complexa) • [网站](https:\u002F\u002Fresearch.nvidia.com\u002Flabs\u002Fgenair\u002Fproteina-complexa\u002F)\n\n### 6.9 基于AlphaFold\n\n**CarbonNovo：基于统一能量模型的蛋白质结构与序列联合设计**\nRen、Milong、Tian Zhu 和 Haicang Zhang\n[ICML 2024](https:\u002F\u002Fopenreview.net\u002Fforum?id=FSxTEvuFa7) • [代码](https:\u002F\u002Fgithub.com\u002Fzhanghaicang\u002Fcarbonmatrix_public)\n\n**P（全原子）正在为蛋白质设计开辟新路径**\nWei Qu、Jiawei Guan、Rui Ma、Ke Zhai、Weikun Wu、Haobo Wang\n[bioRxiv 2024.08.16.608235](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.08.16.608235v1) • [代码](https:\u002F\u002Fgithub.com\u002Flevinthal\u002FPallatom) • [新闻](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002Fj86-ncoYMM2gfbvTJX6I7w)\n\n**EnzymeFlow：通过流匹配和共进化动力学生成反应特异性酶催化口袋**\nChenqing Hua\n论文暂未公开 • [代码](https:\u002F\u002Fgithub.com\u002FWillHua127\u002FEnzymeFlow)\n\n**IgGM：用于功能性抗体和纳米抗体设计的生成模型**\nRubo Wang、Fandi Wu、Xingyu Gao、Jiaxiang Wu、Peilin Zhao、Jianhua Yao\n[bioRxiv 2024.09.19.613838](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.09.19.613838v1) • [代码](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002FIgGM)\n\n**一种用于设计蛋白质复合物的全原子生成模型**\nRuizhe Chen、Dongyu Xue、Xiangxin Zhou、Zaixiang Zheng、Xiangxiang Zeng、Quanquan Gu\n[arXiv:2504.13075](https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.13075) • [代码](https:\u002F\u002Fgithub.com\u002Fbytedance\u002Fapm)\n\n**将类似AlphaFold3的蛋白质折叠模型重新用于抗体序列与结构的协同设计**\nNianzu Yang、Nianzu_Yang、Jian Ma、Songlin Jiang、Huaijin Wu、Shuangjia Zheng、Wengong Jin、Junchi Yan\n[OpenReview](https:\u002F\u002Fopenreview.net\u002Fforum?id=Ja2le9YnqN)\n\n**针对治疗性单域抗体定制化设计的协同生成-排序框架**\nYu Kong、Jiale Shi、Fandi Wu、Ting Zhao、Rubo Wang、Xiaoyi Zhu、Qingyuan Xu、Yidong Song、Quanxiao Li、Yulu Wang、Xingyu Gao、Yuedong Yang、Yi Feng、Zifei Wang、Weifeng Ge、Yanling Wu、Zhenlin Yang、Jianhua Yao 和 Tianlei Ying\n[Cell Discovery 11, 85 (2025)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41421-025-00843-8)\n\n**CONFIDE：用于可靠生物分子结构预测与设计的幻觉评估**\nZijun Gao、Mutian He、Shijia Sun、Hanqun Cao、Jingjie Zhang、Zihao Luo、Xiaorui Wang、Xiaojun Yao、Chang-Yu Hsieh、Chunbin Gu、Pheng Ann Heng\n[arXiv:2512.02033](https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.02033) • [代码](https:\u002F\u002Fgithub.com\u002Fzjgao02\u002FCONFIDE)\n\n## 7. 其他任务\n\n### 7.1 突变效应与适应度景观\n\n**遗传变异的深度生成模型能够捕捉突变效应**\nAdam J. Riesselman、John B. Ingraham 和 Debora S. Marks\n[Nature Methods](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-018-0138-4) • [代码：DeepSequence](https:\u002F\u002Fgithub.com\u002Fdebbiemarkslab\u002FDeepSequence) • 2018年10月\n\n**利用潜在空间模型解析蛋白质进化与适应度景观**\nXinqiang Ding、Zhengting Zou 和 Charles L. Brooks III\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-019-13633-0) • [代码：PEVAE](https:\u002F\u002Fgithub.com\u002Fxqding\u002FPEVAE_Paper) • 2019年12月\n\n**蛋白质景观预测是否需要迁移学习？**\nShanehsazzadeh、Amir、David Belanger 和 David Dohan\n[arXiv 预印本 arXiv:2011.03443 (2020)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.03443)\n\n**Epistatic Net 可实现深度神经网络的稀疏谱正则化，用于推断适应度函数**\nAmirali Aghazadeh、Hunter Nisonoff、Orhan Ocal、David H. Brookes、Yijie Huang、O. Ozan Koyluoglu、Jennifer Listgarten 和 Kannan Ramchandran\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-25371-3) • [代码](https:\u002F\u002Fgithub.com\u002Famirmohan\u002Fepistatic-net) • 2021年9月\n\n**概率型蛋白质序列模型的生成能力**\nFrancisco McGee、Sandro Hauri、Quentin Novinger、Slobodan Vucetic、Ronald M. Levy、Vincenzo Carnevale 和 Allan Haldane\n[Nature Communications](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-021-26529-9) • [代码：generation_capacity_metrics](https:\u002F\u002Fgithub.com\u002Falagauche\u002Fgenerative_capacity_metrics) • [代码：sVAE](https:\u002F\u002Fgithub.com\u002Fahaldane\u002FMSA_VAE) • 2021年11月\n\n**利用卷积神经网络学习蛋白质结构的局部景观**\nAnastasiya V. Kulikova、Daniel J. Diaz、James M. Loy、Andrew D. Ellington 和 Claus O. Wilke\n[生物物理学杂志 47.4 (2021)](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10867-021-09593-6)\n\n**基于深度突变扫描数据学习蛋白质序列-功能关系的神经网络**\nSam Gelman、Sarah A. Fahlberg、Pete Heinzelman、Philip A. Romero 和 Anthony Gitter\n[美国国家科学院院刊](https:\u002F\u002Fdoi.org\u002F10.1073\u002Fpnas.2104878118) • [代码](https:\u002F\u002Fgithub.com\u002Fgitter-lab\u002Fnn4dms) • 2021年11月\n\n**从进化数据和实验标记数据中学习蛋白质适应度模型**\nChloe Hsu、Hunter Nisonoff、Clara Fannjiang、Jennifer Listgarten\n[Nature Biotechnology (2022)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41587-021-01146-5) • [补充信息](https:\u002F\u002Fstatic-content.springer.com\u002Fesm\u002Fart%3A10.1038%2Fs41587-021-01146-5\u002FMediaObjects\u002F41587_2021_1146_MOESM1_ESM.pdf) • [代码](https:\u002F\u002Fgithub.com\u002Fchloechsu\u002Fcombining-evolutionary-and-assay-labelled-data)\n\n**基于模型指导的蛋白质序列设计中的近端探索**\nZhizhou Ren、Jiahan Li、Fan Ding、Yuan Zhou、Jianzhu Ma、Jian Peng\n[BioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.12.487986v1) • [代码](https:\u002F\u002Fgithub.com\u002FHeliXonProtein\u002Fproximal-exploration) • 商业用途\n\n**仅凭通用蛋白质语言模型和序列信息即可高效进化人类抗体**\nBrian L. Hie、Duo Xu、Varun R. Shanker、Theodora U.J. Bruun、Payton A. Weidenbacher、Shaogeng Tang、Peter S. Kim\n[bioRxiv (2022)](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.04.10.487811v1) • [代码](https:\u002F\u002Fgithub.com\u002Fbrianhie\u002Fefficient-evolution)\n\n**Tranception：基于自回归Transformer和推理时检索的蛋白质适应度预测**\nNotin、P.、Dias、M.、Frazer、J.、Marchena-Hurtado、J.、Gomez、A.、Marks、D.S.、Gal、Y\n[ICML (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13760)\u002F[arXiv:2205.13760](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.13760) • [代码](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FTranception) • [Hugging Face](https:\u002F\u002Fhuggingface.co\u002FICML2022\u002FTranception)\n\n**通过贝叶斯优化引导的进化算法和机器人实验进行蛋白质工程**\nRuyun Hu、Lihao Fu、Yongcan Chen、Junyu Chen、Yu Qiao、Tong Si\n[bioRxiv 2022.08.11.503535](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.11.503535v1)\n\n**基于人工智能预测结合亲和力和自然性的抗体优化**\nSharrol Bachas、Goran Rakocevic、David Spencer、Anand V. Sastry、Robel Haile、John M. Sutton、George Kasun、Andrew Stachyra、Jahir M. Gutierrez、Edriss Yassine、Borka Medjo、Vincent Blay、Christa Kohnert、Jennifer T. Stanton、Alexander Brown、Nebojsa Tijanic、Cailen McCloskey、Rebecca Viazzo、Rebecca Consbruck、Hayley Carter、Simon Levine、Shaheed Abdulhaqq、Jacob Shaul、Abigail B. Ventura、Randal S. Olson、Engin Yapici、Joshua Meier、Sean McClain、Matthew Weinstock、Gregory Hannum、Ariel Schwartz、Miles Gander、Roberto Spreafico\n[bioRxiv 2022.08.16.504181](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.08.16.504181v1) • [海报](https:\u002F\u002Fnips.cc\u002Fmedia\u002FPosterPDFs\u002FNeurIPS%202022\u002F58999.png?t=1668022673.3853557)\n\n**用于蛋白质物理的深度神经网络能量函数构建**\nYang、Huan、Xiong Zhaoping 和 Francesco Zonta\n[《化学理论与计算杂志》（2022）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jctc.2c00069)\n\n**从实验室进化实验中推断蛋白质适应度景观**\nSameer D’Costa、Emily C. Hinds、Chase R. Freschlin、Hyebin Song、Philip A. Romero\n[bioRxiv 2022.09.01.506224](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.01.506224v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.09.01.506224v1.supplementary-material)\n\n**BayeStab：利用不确定性量化预测突变对蛋白质稳定性的影响**\nShuyu Wang、Hongzhou Tang、Yuliang Zhao、Lei Zuo\n[《蛋白质科学》（2022）](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fabs\u002F10.1002\u002Fpro.4467) • [代码](https:\u002F\u002Fgithub.com\u002FHongzhouTang\u002FBayeStab) • [网站](http:\u002F\u002Fwww.bayestab.com)\n\n**用于基准测试模型引导蛋白质设计的调谐适应度景观**\nNeil Thomas、Atish Agarwala、David Belanger、Yun S. Song、Lucy Colwell\n[bioRxiv 2022.10.28.514293](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.10.28.514293v1) • [代码](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fslip)\n\n**基于结构的残基偏好进行蛋白质设计**\nDavid Ding、Ada Y Shaw、Sam Sinai、Nathan J Rollins、Noam Prywes、David Savage、Michael T Laub、Debora S Marks\n[bioRxiv 2022.10.31.514613](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.10.31.514613v2) • [代码](https:\u002F\u002Fgithub.com\u002Fddingding\u002FCoVES)\n\n**利用RoseTTAFold准确预测突变效应**\nSanaa Mansoor、Minkyung Baek、David Juergens、Joseph L Watson、David Baker\n[bioRxiv 2022.11.04.515218](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.11.04.515218v1)\n\n**用全息卷积神经网络学习蛋白质微环境的形状**\nMichael N. Pun、Andrew Ivanov、Quinn Bellamy、Zachary Montague、Colin LaMont、Philip Bradley、Jakub Otwinowski、Armita Nourmohammad\n[bioRxiv（2022）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.02936) • [代码](https:\u002F\u002Fgithub.com\u002FStatPhysBio\u002Fprotein_holography)\n\n**全局推断，局部预测：基于序列数据的蛋白质适应度预测中的数量-质量权衡**\nLorenzo Posani、Francesca Rizzato、Rémi Monasson、Simona Cocco\n[bioRxiv 2022.12.12.520004](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2022.12.12.520004v1)\n\n**通过计算机模拟折叠和熔解验证从头设计的水溶性和跨膜蛋白**\nAlvaro Martin、Carolin Berner、Sergey Ovchinnikov、Anastassia Andreevna Vorobieva\n[bioRxiv 2023.06.06.543955](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.06.06.543955v1) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fvorobieva\u002FColabFold\u002Fblob\u002Fmain\u002Fbeta\u002FESMFold_melting.ipynb)\n\n**PoET：作为序列序列的蛋白质家族生成模型**\nTimothy F. Truong Jr、Tristan Bepler\n[arXiv:2306.06156](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.06156) • [代码](https:\u002F\u002Fgithub.com\u002FOpenProteinAI\u002FPoET)\n\n**利用深度学习表征快速预测蛋白质稳定性**\nLasse M Blaabjerg、Maher M Kassem、Lydia L Good、Nicolas Jonsson、Matteo Cagiada、Kristoffer E Johansson、Wouter Boomsma、Amelie Stein、Kresten Lindorff-Larsen\n[eLife 12:e82593](https:\u002F\u002Felifesciences.org\u002Farticles\u002F82593) • [代码](https:\u002F\u002Fgithub.com\u002FKULL-Centre\u002F_2022_ML-ddG-Blaabjerg\u002F)\n\n**一种通用的温度引导语言模型，用于工程化增强蛋白质的稳定性和活性**\nPan Tan、Mingchen Li、Yuanxi Yu、Fan Jiang、Lirong Zheng、Banghao Wu、Xinyu Sun、Liqi Kang、Jie Song、Liang Zhang、Yi Xiong、Wanli Ouyang、Zhiqiang Hu、Guisheng Fan、Yufeng Pei、Liang Hong\n[arXiv:2307.12682](https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.12682)\n\n**迁移学习以利用更大数据集改进蛋白质稳定性变化的预测**\nHenry Dieckhaus、Michael Brocidiacono、Nicholas Randolph、Brian Kuhlman\n[bioRxiv 2023.07.27.550881](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.27.550881v1) • [代码](https:\u002F\u002Fgithub.com\u002FKuhlman-Lab\u002FThermoMPNN) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F07\u002F30\u002F2023.07.27.550881\u002FDC1\u002Fembed\u002Fmedia-1.docx)\n\n**基于结构的自监督学习可在蛋白质宇宙尺度上超快速预测突变引起的稳定性变化**\nJinyuan Sun、Tong Zhu、Yinglu Cui、Bian Wu\n[bioRxiv 2023.08.09.552725](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.08.09.552725v1) • [代码](https:\u002F\u002Fgithub.com\u002FWublab\u002FPythia)\n\n**提升基于AND\u002FOR的计算蛋白质设计：动态启发式与可泛化的UFO**\nBobak Pezeshki、Radu Marinescu、Alexander Ihler、Rina Dechter\n[arXiv:2309.00408](https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.00408)\n\n**使用RoseTTAFold进行蛋白质稳定性和功能的零样本突变效应预测**\nSanaa Mansoor、Minkyung Baek、David Juergens、Joseph L. Watson、David Baker\n[《蛋白质科学》](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.4780) • [学位论文](https:\u002F\u002Fwww.proquest.com\u002Fopenview\u002Fdba5569e5efd0dc60fc7bedccb6afee3\u002F)\n\n**利用AlphaMissense准确预测全蛋白质组错义突变效应**\nJun Cheng、Guido Novati、Joshua Pan、Clare Bycroft、Akvile Žemgulyte、Taylor Applebaum、Alexander Pritzel、Lai Hong Wong、Michal Zielinski、Tobias Sargeant、Rosalia G. Schneider、Andrew W. Senior、John Jumper、Demis Hassabis、Pushmeet Kohli、Žiga Avsec\n[《科学》0,eadg7492DOI:10.1126\u002Fscience.adg7492](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adg7492) • [代码](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Falphamissense) • [数据](https:\u002F\u002Fconsole.cloud.google.com\u002Fstorage\u002Fbrowser\u002Fdm_alphamissense)\n\n**酶结构与突变效应的可预测性相关**\nFloris Julian van der Flier、Dave Estell、Sina Pricelius、Lydia Dankmeyer、Sander van Stigt Thans、Harm Mulder、Rei Otsuka、Frits Goedegebuur、Laurens Lammerts、Diego Staphorst、Aalt D.J. van Dijk、Dick de Ridder、Henning Redestig\n[bioRxiv 2023.09.25.559319](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.09.25.559319v2)\u002F[《计算与结构生物技术杂志》（2024）](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.csbj.2024.09.007) • [代码](https:\u002F\u002Fgithub.com\u002Fflorisvdf\u002Fmutation-predictability)\n\n**利用结构建模快速、准确地按靶标结合倾向对工程化蛋白质进行排序**\n丁晓哲、陈欣红、艾琳·E·沙利文、蒂莫西·F·谢伊、维维安娜·格拉迪纳鲁\n[bioRxiv 2023.01.11.523680](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.01.11.523680v2)\u002F[分子治疗（2024）](https:\u002F\u002Fwww.cell.com\u002Fmolecular-therapy-family\u002Fmolecular-therapy\u002Ffulltext\u002FS1525-0016(24)00219-3) • [代码](https:\u002F\u002Fgithub.com\u002FGradinaruLab\u002FAPPRAISE) • [Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002FGradinaruLab\u002FAPPRAISE\u002Fblob\u002Fmain\u002FColab_APPRAISE.ipynb)\n\n**神经网络外推至蛋白质适应度景观的遥远区域**\n萨拉·A·法尔贝格、切斯·R·弗雷斯克林、皮特·海因策尔曼、菲利普·A·罗梅罗\n[bioRxiv 2023.11.08.566287](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.08.566287v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F11\u002F09\u002F2023.11.08.566287\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**利用适应度景观建模与强化学习加速蛋白质工程**\n孙浩然、何亮、邓攀、刘国清、刘海光、曹川、鞠福松、吴立军、秦涛、刘铁燕\n[bioRxiv 2023.11.16.565910](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.16.565910v1)\n\n**由大型语言模型引导的定向进化进行蛋白质设计**\nTrong Thanh Tran、Truong Son Hy\n[bioRxiv 2023.11.29.568945](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.11.28.568945v1) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F11\u002F29\u002F2023.11.28.568945\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [代码](https:\u002F\u002Fgithub.com\u002FHySonLab\u002FDirected_Evolution)\n\n**高通量机器学习指导下的多样化单域抗体设计，用于对抗SARS-CoV-2**\n克里斯托夫·安格尔穆勒、泽尔达·玛丽、本杰明·杰斯特、艾米丽·恩格尔哈特、瑞安·埃默森、巴巴克·阿里帕纳希、扎卡里·瑞安·麦考、吉姆·罗伯茨、兰多夫·M·洛佩兹、大卫·扬格、露西·科尔韦尔\n[bioRxiv 2023.12.01.569227](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.01.569227v1)\n\n**利用大型语言模型高效预测单点突变引起的蛋白质稳定性变化**\n张一杰、高章阳、谭成、Stan Z.Li\n[arXiv预印本 arXiv:2312.04019（2023）](https:\u002F\u002Farxiv.org\u002Fabs\u002F2312.04019)\n\n**DSMBind：SE(3)去噪分数匹配用于无监督结合能预测和纳米抗体设计**\n金文功、陈迅、阿米塔·维蒂卡登、西拉努什·萨尔齐科娃、拉克蒂玛·雷乔德胡里、卡罗琳·乌勒、尼尔·哈科亨\n[bioRxiv 2023.12.10.570461](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.10.570461v1) • [补充材料1](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F12\u002F10\u002F2023.12.10.570461\u002FDC1\u002Fembed\u002Fmedia-1.xlsx) • [补充材料2](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2023\u002F12\u002F10\u002F2023.12.10.570461\u002FDC2\u002Fembed\u002Fmedia-2.pdf)\n\n**基于结构信息的语言模型进行蛋白质复合物逆折叠，实现无监督抗体进化**\n瓦伦·R·尚克、西奥多拉·U.J·布鲁恩、布莱恩·L·希、彼得·S·金\n[bioRxiv 2023.12.19.572475](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.19.572475v2)\n\n**EvolMPNN：通过进化编码预测同源蛋白上的突变效应**\n钟志强、达维德·莫廷\n[arXiv:2402.13418](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.13418)\n\n**通过对抗性学习生成亲和力单调递增、与更强蛋白质复合物结合的突变体**\n田岚、苏书泉、平鹏尧、久尔吉·胡特瓦格纳、刘涛、潘毅和李金燕\n[Nat Mach Intell 6, 315–325 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-024-00803-z) • [代码](https:\u002F\u002Fgithub.com\u002Ftianlt\u002FDeepdirect)\n\n**基于生物物理学的蛋白质语言模型用于蛋白质工程**\n萨姆·盖尔曼、布莱斯·约翰逊、切斯·弗雷斯克林、萨米尔·德科斯塔、安东尼·吉特和菲利普·A·罗梅罗\n[bioRxiv 2024.03.15.585128](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2024.03.15.585128) • [代码](https:\u002F\u002Fgithub.com\u002Fgitter-lab\u002Fmetl)\n\n**基于潜在空间的定向进化，以梯度上升加速蛋白质序列设计** \u002F **LatentDE：基于潜在空间的定向进化用于蛋白质序列设计**\nNhat Khang Ngo、Thanh V. T. Tran、Viet Thanh Duy Nguyen、Truong Son Hy\n[bioRxiv 2024.04.13.589381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.13.589381v1)\u002F[NeurIPS 2024](https:\u002F\u002Fopenreview.net\u002Fpdf?id=4YkbQGVWGF)\u002F[机器学习：科学与技术（2025）](https:\u002F\u002Fiopscience.iop.org\u002Farticle\u002F10.1088\u002F2632-2153\u002Fadc2e2) • [代码](https:\u002F\u002Fgithub.com\u002FHySonLab\u002FLatentDE)\n\n**AAVDiff：通过扩散生成增强重组腺相关病毒（AAV）衣壳的存活率和多样性——实验验证**\n刘立军、杨佳莉、宋建飞、杨兴林、牛乐乐、蔡泽奇、施慧、侯廷俊、谢昌宇、沈伟然、邓亚峰\n[arXiv:2404.10573](https:\u002F\u002Farxiv.org\u002Fabs\u002F2404.10573)\n\n**使用轻量级图去噪神经网络进行蛋白质工程**\n周冰心、郑丽蓉、吴邦浩、谭洋、吕欧彤怡、易凯、范贵生和洪亮\n[化学信息与建模杂志（2024）](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facs.jcim.4c00036) • [代码](https:\u002F\u002Fgithub.com\u002Fbzho3923\u002FProtLGN)\n\n**VespaG：专家指导的蛋白质语言模型实现准确且极快的适应度预测**\n塞琳·马尔凯、尤利乌斯·施伦索克、玛丽娜·阿巴卡罗娃、布尔哈德·罗斯特、艾洛迪·莱恩\n[bioRxiv 2024.04.24.590982](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.24.590982v1) • [代码](https:\u002F\u002Fgithub.com\u002FJSchlensok\u002FVespaG)\n\n**SARS-CoV-2对称nsp7二聚体的界面设计及机器学习指导下的nsp7序列预测揭示了nsp7稳定性和适应性的理化性质与热点，为治疗设计提供依据**\n阿马尔·吉特·亚达夫、希万克·库马尔、施韦塔·茂里亚、库什布·巴加特和阿迪提亚·K·帕迪\n[物理化学化学物理（2024）](https:\u002F\u002Fpubs.rsc.org\u002Fen\u002Fcontent\u002Farticlelanding\u002F2024\u002Fcp\u002Fd4cp01014k)\n\n**通过直接偏好优化将蛋白质生成模型与实验适应度对齐**\n塔拉勒·维达塔拉、拉斐尔·拉法伊洛夫、布莱恩·希\n[bioRxiv 2024.05.20.595026](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.20.595026v1) • [代码](https:\u002F\u002Fgithub.com\u002Fevo-design\u002Fprotein-dpo)\n\n**ProBASS——一种结合序列和结构特征的语言模型，用于预测突变对结合亲和力的影响**\n萨加拉·N.S. 古鲁辛格、吴义兵、威廉·德格拉多、朱莉娅·M·希夫曼\n[bioRxiv 2024.06.21.600041](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.06.21.600041v1) • [代码](https:\u002F\u002Fgithub.com\u002Fsagagugit\u002FProBASS)\n\n**利用结构信息语言模型进行蛋白质和抗体复合物的无监督进化**\n瓦伦·R·尚克、西奥多拉·U.J·布鲁恩、布莱恩·L·希、彼得·S·金\n[Science385,46-53(2024)](https:\u002F\u002Fwww.science.org\u002Fdoi\u002F10.1126\u002Fscience.adk8946) • [代码](https:\u002F\u002Fgithub.com\u002Fvarun-shanker\u002Fstructural-evolution)\n\n**通过少量样本学习，在极少湿实验室数据的情况下提升蛋白质语言模型效率**\n周子怡、张亮、于元熙、吴邦浩、李明晨、洪亮和谭攀\n[Nat Commun 15, 5566 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-49798-6) • [代码](https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FTranception)\n\n**基于蛋白质语言模型的少样本学习实现蛋白质快速进化**\n姜凯毅、闫兆青、马泰奥·迪·贝尔纳多、萨曼莎·R·斯格里齐、卢卡斯·维利格、阿里桑·卡亚博伦、金炳志、约瑟芬·K·卡斯卡登、平泉昌弘、西政久、乔纳森·S·古滕贝格、奥马尔·O·阿布戴耶\n[bioRxiv 2024.07.17.604015](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.07.17.604015v1) • [代码1](https:\u002F\u002Fgithub.com\u002Fmat10d\u002FEvolvePro)、[代码2](https:\u002F\u002Fgithub.com\u002Fidmjky\u002FEvolvePro)\n\n**利用多模态深度表征学习进行零样本突变效应预测，指导蛋白质工程**\n程鹏、毛聪、唐进、杨森、程宇、王武科、顾秋曦、韩伟、陈浩、李思涵、陈耀峰、周江林、李五举、潘爱民、赵素文、黄兴旭、朱世强、张军、舒文杰和王圣奇\n[Cell Research (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41422-024-00989-2) • [代码](https:\u002F\u002Fgithub.com\u002Fwenjiegroup\u002FProMEP)\n\n**机器学习引导的适应度与多样性协同优化促进酶工程中的组合文库设计**\n丁克尔、迈克尔·秦、赵云龙、黄伟、梅彬康、王焕楠、刘鹏、杨洋和罗云安\n[Nature Communications 15.1 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-50698-y) • [代码](https:\u002F\u002Fgithub.com\u002Fluo-group\u002FMODIFY)、[模型](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.12715542)\n\n**狄利克雷潜在建模实现功能性蛋白质设计空间的有效学习与采样**\n叶夫根尼·洛布扎耶夫、乔瓦尼·斯特拉夸达尼奥\n[Nat Commun 15, 9309 (2024)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-024-53622-6) • [代码](https:\u002F\u002Flicensing.edinburgh-innovations.ed.ac.uk\u002Fproduct\u002Fproton)\n\n**MProt-DPO：通过直接偏好优化突破多模态蛋白质设计工作流的ExaFLOPS瓶颈**\n高塔姆·达鲁曼、凯尔·希佩、亚历山大·布雷斯、萨姆·福尔曼、韦诺·哈坦帕、瓦鲁尼·K·萨斯特里、郑辉霍、洛根·沃德、塞尔维什·穆拉利达兰、阿奇特·瓦桑、巴拉特·卡莱、卡拉·M·曼恩、马恒、程云轩、尤莉安娜·萨莫拉、刘盛超、肖朝伟、埃马尼·穆拉利、汤姆·吉布斯、马希达尔·塔蒂内尼、迪帕克·坎奇、杰罗姆·米切尔、山田浩一、玛丽亚·加尔萨兰、迈克尔·E·帕普卡、伊恩·福斯特、里克·史蒂文斯、阿尼玛·阿南德库马尔、文卡特拉姆·维什瓦纳特、阿尔温德·拉马纳坦\n[国际高性能计算、网络、存储与分析大会 SC. IEEE计算机协会，2024年](https:\u002F\u002Fwww.computer.org\u002Fcsdl\u002Fproceedings-article\u002Fsc\u002F2024\u002F529100a074\u002F21HUV88n1F6)\n\n**基于评分辅助的蛋白质生成式探索（SAGE-Prot）：一种通过迭代序列生成与评估实现多目标蛋白质优化的框架**\n林浩哲、李健浩、卢京泰\n[arXiv:2505.01277](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.01277) • [代码](https:\u002F\u002Fgithub.com\u002Fhclim0213\u002FSAGE-Prot)\n\n**人工智能与第一性原理方法在蛋白质重新设计中的应用：一场权宜之计？**\n达米亚诺·钱费罗尼、大卫·比萨拉加、安娜·玛丽亚·费尔南德斯-埃斯卡米利亚、伊格纳西奥·菲塔、拉赫玛·哈姆达尼、劳尔·雷切、哈维尔·德尔加多、路易斯·塞拉诺\n[bioRxiv 2025.05.12.653318](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.12.653318v1)\u002F[Protein Science](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002F10.1002\u002Fpro.70210) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2025\u002F05\u002F15\u002F2025.05.12.653318\u002FDC1\u002Fembed\u002Fmedia-1.pdf)\n\n**基于似然的蛋白质语言模型微调用于少样本适应度预测和设计**\n亚历克斯·霍金斯-胡克、希卡·苏拉纳、杰克·西蒙斯、雅库布·克梅茨、奥利弗·本特、保罗·达克沃思\n[bioRxiv 2024.05.28.596156](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.05.28.596156v3)\n\n**ProSpero：超越野生型邻域的稳健蛋白质设计主动学习**\n米哈尔·克米奇基维奇、文森特·福图因、埃娃·什丘雷克\n[arXiv:2505.22494](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.22494v1)\n\n**使用掩码蛋白质语言模型进行蛋白质序列设计的启发式多位点优化**\n王丽娟、王宇泽、邱晨、肖立伟、刘宪亮、陈俊杰\n[bioRxiv 2025.07.31.668012](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.07.31.668012v1)\n\n**利用蛋白质语言模型设计不稳定型RNase A**\n加布里埃尔·翁基亚特·怀伊、孔思恩、冯天荣、吴益祺、萧温斯顿\n[ACS Synthetic Biology (2025)](https:\u002F\u002Fpubs.acs.org\u002Fdoi\u002F10.1021\u002Facssynbio.5c00287)\n\n**零样本深度学习结合多目标优化提升玉米赤霉烯酮水解酶和木聚糖酶的热稳定性**\n吴凡、吴睿、陈玲慧、陈权、刘海燕\n[New Biotechnology (2026)](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1871678426000099)\n\n**用于功能发现与设计的蛋白质词离散语言**\n郭正阳、王梓、柴永平、许凯明、李明、李伟、欧广硕\n[bioRxiv 2026.02.14.705947](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.02.14.705947v1) • [代码](https:\u002F\u002Fgithub.com\u002Fyoung55775\u002FProtWord)\n\n**预训练嵌入在机器引导蛋白质设计中的极限探索：以预测AAV载体活性为例**\n安娜·F·罗德里格斯、卢卡斯·费拉兹、劳拉·巴尔比、佩德罗·吉埃斯特拉·科托维奥、卡蒂娅·佩斯基塔\n[arXiv:2602.14828](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.14828) • [代码](https:\u002F\u002Fgithub.com\u002FlasigeBioTM\u002FAAV-embeddings)\n\n**深度学习引导的进化优化用于蛋白质设计**\n埃里克·哈特曼、唐迪、约翰·马尔姆斯特伦\n[arXiv:2603.02753](https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.02753)\n\n**基于本体论强化迭代的功能性蛋白质设计与增强**\n毕亨、秦晨晨、赵宇、黄龙凯、吴子涵、王芳、吴范迪、杨帆和姚建华\n[Nat Commun (2026)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41467-026-69855-6) • [代码](https:\u002F\u002Fgithub.com\u002FTencentAI4S\u002Fori)\n\n**CombinGym：一个用于机器学习辅助设计组合蛋白变体的基准平台**\n陈勇灿、傅利浩、陆旭超、李文卓、高远、王一博、阮志成、宋彤\n[bioRxiv 2026.03.24.714074](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.03.24.714074v1) • [代码](https:\u002F\u002Fgithub.com\u002Fsitonglab\u002FCombinGym) • [补充材料](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F03\u002F25\u002F2026.03.24.714074\u002FDC1\u002Fembed\u002Fmedia-1.pdf) • [网站](https:\u002F\u002Fwww.combingym.org)\n\n### 7.2 蛋白质语言模型（pLM）与表示学习\n\n> 更详细的蛋白质表示学习列表：\n> [Lirong Wu](https:\u002F\u002Fgithub.com\u002FLirongWu) 的 [awesome-protein-representation-learning](https:\u002F\u002Fgithub.com\u002FLirongWu\u002Fawesome-protein-representation-learning)\n\n**基于序列的深度表示学习实现统一的理性蛋白质工程**\nEthan C. Alley、Grigory Khimulya、Surojit Biswas、Mohammed AlQuraishi 和 George M. Church\n[《自然方法》16.12 (2019)](https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41592-019-0598-1)\n\n**通过几何预训练进行蛋白质结构表示学习**\nZuobai Zhang、Minghao Xu、Arian Jamasb、Vijil Chenthamarakshan、Aurelie Lozano、Payel Das、Jian Tang\n[arXiv](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.06125) • 2022年1月\n\n**利用蛋白质语言模型研究进化速度**\nBrian L. Hie、Kevin K. Yang 和 Peter S. Kim\n[bioRxiv](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2021.06.07.447389v1.full.pdf)\n\n**借助语言学推进蛋白质语言模型：提升可解释性的路线图**\nMai Ha Vu、Rahmad Akbar、Philippe A. Robert、Bartlomiej Swiatczak、Victor Greiff、Geir Kjetil Sandve、Dag Trygve Truslew Haug\n[arXiv:2207.00982](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.00982)\n\n**利用自监督学习破译抗体的语言**\nJinwoo Leem、Laura S. Mitchell、James H.R. Farmery、Justin Barton、Jacob D. Galson\n[Patterns (2022): 100513](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2666389922001052) • [代码](https:\u002F\u002Fgithub.com\u002Falchemab\u002Fantiberta)\n\n**关于抗体的语言模型预训练**\n匿名（论文处于双盲评审中）\n[ICLR 2023](https:\u002F\u002Fopenreview.net\u002Fforum?id=zaq4LV55xHl) • [补充材料](https:\u002F\u002Fopenreview.net\u002Fattachment?id=zaq4LV55xHl&name=supplementary_material)\n\n**用于药物发现的抗体表示学习**\nLin Li、Esther Gupta、John Spaeth、Leslie Shing、Tristan Bepler、Rajmonda Sulo Caceres\n[arXiv:2210.02881](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.02881)\n\n**通过序列与结构的深度耦合学习完整的蛋白质表示**\nBozhen Hu、Cheng Tan、Jun Xia、Jiangbin Zheng、Yufei Huang、Lirong Wu、Yue Liu、Yongjie Xu、Stan Z. Li\n[bioRxiv 2023.07.05.547769](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.07.05.547769v1)\n\n**利用祖先序列重建进行蛋白质表示学习**\nD. S. Matthews、M. A. Spence、A. C. Mater、J. Nichols、S. B. Pulsford、M. Sandhu、J. A. Kaczmarski、C. M. Miton、N. Tokuriki、C. J. Jackson\n[bioRxiv 2023.12.20.572683](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2023.12.20.572683v1) • [代码](https:\u002F\u002Fgithub.com\u002FRSCJacksonLab\u002Flocal-ancestral-sequence-embeddings)\n\n**蛋白质语言模型因生命树上序列采样的不均衡而存在偏差**\nFrances Ding、Jacob Steinhardt\n[bioRxiv 2024.03.07.584001](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.03.07.584001v1)\n\n**InstructPLM：使蛋白质语言模型遵循蛋白质结构指令**\nJiezhong Qiu、Junde Xu、Jie Hu、Hanqun Cao、Liya Hou、Zijun Gao、Xinyi Zhou、Anni Li、Xiujuan Li、Bin Cui、Fei Yang、Shuang Peng、Ning Sun、Fangyu Wang、Aimin Pan、Jie Tang、Jieping Ye、Junyang Lin、Jin Tang、Xingxu Huang、Pheng Ann Heng、Guangyong Chen\n[bioRxiv 2024.04.17.589642](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2024.04.17.589642v1)\n\n### 7.3 分子设计模型\n\n> 与蛋白质设计中的“功能-骨架-序列”范式不同，基于该范式的深度学习分子设计主要从三个层次展开：**原子级**、**片段级**和**反应级**。这些方法可以分为[梯度优化](#731-gradient-optimization)和[优化采样](#732-optimized-sampling)（无梯度）两类。[点击此处查看详细综述](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1359644621002531) 为了更好地了解多样化的生成模型在设计中的应用，以下推荐的最新分子设计模型或许对蛋白质设计有所启发，甚至可以直接迁移应用。\n> 更多论文列表如下：\n>\n> 1. [CondaPereira](https:\u002F\u002Fgithub.com\u002FCondaPereira) 的 GitHub 仓库：[Essay_For_Molecular_Generation](https:\u002F\u002Fgithub.com\u002FCondaPereira\u002FEssay_For_Molecular_Generation)。\n> 2. [AspirinCode](https:\u002F\u002Fgithub.com\u002FAspirinCode) 的：[papers-for-molecular-design-using-DL](https:\u002F\u002Fgithub.com\u002FAspirinCode\u002Fpapers-for-molecular-design-using-DL)、[awesome-AI4MolConformation-MD](https:\u002F\u002Fgithub.com\u002FAspirinCode\u002Fawesome-AI4MolConformation-MD)\n> 3. [Alex Morehead](https:\u002F\u002Fgithub.com\u002Famorehead) 的：[awesome-molecular-generation](https:\u002F\u002Fgithub.com\u002Famorehead\u002Fawesome-molecular-generation)\n\n#### 7.3.1 梯度优化\n\n**用于分子优化的可微骨架树**\nFu, T., Gao, W., Xiao, C., Yasonik, J., Coley, C. W., & Sun, J\n[arXiv 预印本 arXiv:2109.10469](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.10469) • [代码](https:\u002F\u002Fgithub.com\u002Ffutianfan\u002FDST) • 9月21日\n\n**等变能量引导的随机微分方程用于逆向分子设计**\nFan Bao, Min Zhao, Zhongkai Hao, Peiyao Li, Chongxuan Li, Jun Zhu\n[arXiv:2209.15408](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15408)\n\n**基于配体的药物设计中，等变形状条件下的三维分子生成**\nKeir Adams, Connor W. Coley\n[arXiv:2210.04893](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.04893) • [代码](https:\u002F\u002Fgithub.com\u002Fkeiradams\u002FSQUID)\n\n**基于结构的药物设计与等变扩散模型**\nArne Schneuing, Yuanqi Du, Charles Harris, Arian Jamasb, Ilia Igashov, Weitao Du, Tom Blundell, Pietro Lió, Carla Gomes, Max Welling, Michael Bronstein, Bruno Correia\n[NeurIPS 2022](https:\u002F\u002Fwww.mlsb.io\u002Fpapers_2022\u002FStructure_based_Drug_Design_with_Equivariant_Diffusion_Models.pdf)\u002F[arXiv:2210.13695](https:\u002F\u002Farxiv.org\u002Fabs\u002F2210.13695) • [代码](https:\u002F\u002Fgithub.com\u002Farneschneuing\u002FDiffSBDD)\n\n#### 7.3.2 优化采样\n\n**针对靶蛋白结合的三维分子生成**\nMeng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, Shuiwang Ji\n[国际机器学习大会第39次会议 (2022)](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fliu22m.html) • [GraphBP](https:\u002F\u002Fgithub.com\u002Fdivelab\u002Fgraphbp)\n\n**Pocket2Mol：基于三维蛋白质口袋的高效分子采样**\nPeng, Xingang, 等\n[国际机器学习大会第39次会议 (2022)](https:\u002F\u002Fproceedings.mlr.press\u002Fv162\u002Fpeng22b.html) • [代码](https:\u002F\u002Fgithub.com\u002Fpengxingang\u002FPocket2Mol)\n\n**强化遗传算法用于结构基药物设计**\nFu, Tianfan, 等\n[arXiv 预印本 arXiv:2211.16508 (2022)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2211.16508)\u002F[ICML22](https:\u002F\u002Fopenreview.net\u002Fforum?id=_Sfd-icezCa) • [代码](https:\u002F\u002Fgithub.com\u002Ffutianfan\u002Freinforced-genetic-algorithm) • [网站](https:\u002F\u002Fdeepai.org\u002Fpublication\u002Freinforced-genetic-algorithm-for-structure-based-drug-design)\n\n**带有结构基元的靶蛋白结合分子生成**\nZhang, Zaixi, 等\n[国际表征学习大会第11次会议 (2023)](https:\u002F\u002Fopenreview.net\u002Fforum?id=Rq13idF0F73) • [代码](https:\u002F\u002Fgithub.com\u002Fzaixizhang\u002FFLAG)\n\n**面向靶标的三维等变扩散及亲和力预测**\nGuan, Jiaqi, 等\n[国际表征学习大会第11次会议 (2023)](https:\u002F\u002Fopenreview.net\u002Fforum?id=kJqXEPXMsE0) • [代码](https:\u002F\u002Fgithub.com\u002Fguanjq\u002Ftargetdiff)\n\n### 7.4 未分类\n\n**针对可溶性和跨膜蛋白的表位特异性抗体从头设计，具有高特异性、可开发性和功能性**\n[Nabla Bio](https:\u002F\u002Fwww.nabla.bio\u002F)\n[预印本](https:\u002F\u002Fnabla-public.s3.us-east-1.amazonaws.com\u002F2024_Nabla_JAM_de_novo_antibodies.pdf) • [博客](https:\u002F\u002Fwww.nabla.bio\u002Fnews\u002Fdenovo) • [新闻](https:\u002F\u002Fwww.science.org\u002Fcontent\u002Farticle\u002Fai-conjures-potential-new-antibody-drugs-matter-months) • 商业化\n\n**JAM-2：完全计算驱动的药物类抗体设计，成功率极高**\n[Nabla Bio](https:\u002F\u002Fwww.nabla.bio\u002F)\n[白皮书](https:\u002F\u002Fnabla-public.s3.us-east-1.amazonaws.com\u002F2025_Nabla_JAM2.pdf)\n\n**Chai-2：在24孔板中实现零样本抗体发现**\nChai Discovery 团队  \n[技术报告](https:\u002F\u002Fchaiassets.com\u002Fchai-2\u002Fpaper\u002Ftechnical_report.pdf) • [新闻](https:\u002F\u002Fwww.chaidiscovery.com\u002Fnews\u002Fintroducing-chai-2) • 商业化\n\n**以原子精度针对挑战性靶点的药物类抗体设计**\nChai Discovery 团队  \n[技术报告](https:\u002F\u002Fchaiassets.com\u002Fchai-2\u002Fpaper\u002Ftechnical_report_challenging_targets.pdf) • [新闻](https:\u002F\u002Fwww.chaidiscovery.com\u002Fnews\u002Fchai-2-mab)\n\n**Latent-X：原子级别前沿模型，用于从头设计蛋白质结合剂**\nLatent Labs 团队  \n[技术报告](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2025\u002F07\u002FLatent-X-Technical-Report.pdf) • [官网](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-x\u002F) • 商业化\n\n**使用 Latent-X2 设计的低免疫原性人源抗体**\nLatent Labs 团队  \n[技术报告](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2025\u002F12\u002FLatent-X2-Technical-Report.pdf) • [官网](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-x2\u002F) • 商业化\n\n**Latent-Y：实验室验证的自主型从头药物设计代理**\nLatent Labs 团队  \n[技术报告](https:\u002F\u002Fwww.latentlabs.com\u002Fwp-content\u002Fuploads\u002F2026\u002F03\u002FLatent-Y-Technical-Report.pdf) • [官网](https:\u002F\u002Fwww.latentlabs.com\u002Flatent-y\u002F) • 商业化","# papers_for_protein_design_using_DL 快速上手指南\n\n`papers_for_protein_design_using_DL` 并非一个可执行的软件工具或代码库，而是一个** curated（精选）的学术论文与资源列表**。它旨在为使用深度学习进行蛋白质设计的研究人员和开发者提供最新的文献索引、基准测试（Benchmarks）和数据集链接。\n\n因此，本指南将指导你如何获取该资源列表，并如何利用其中链接的具体项目（如代码库、数据集）开始你的研究。\n\n## 1. 环境准备\n\n由于本项目主要是文档和资源索引，无需特定的运行时环境。但为了运行列表中链接的具体论文代码（通常基于 PyTorch 或 TensorFlow），建议准备以下基础环境：\n\n*   **操作系统**: Linux (推荐 Ubuntu 20.04+) 或 macOS。Windows 用户建议使用 WSL2。\n*   **Python**: 3.8 或更高版本。\n*   **包管理工具**: `pip` 或 `conda` (推荐 Miniconda)。\n*   **GPU 支持**: 大多数深度学习蛋白质设计模型需要 NVIDIA GPU，请确保已安装对应的 CUDA 驱动和 Toolkit。\n*   **Git**: 用于克隆仓库及列表中提到的其他代码库。\n\n## 2. 获取资源列表\n\n你可以通过克隆 GitHub 仓库来获取最新的论文列表和本地浏览权限。\n\n### 克隆仓库\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FPeldom\u002Fpapers_for_protein_design_using_DL.git\ncd papers_for_protein_design_using_DL\n```\n\n### 国内加速方案\n如果访问 GitHub 速度较慢，可以使用国内镜像源或加速服务进行克隆（以 Gitee 镜像为例，若存在）：\n```bash\n# 注意：需确认是否有同步的 Gitee 镜像，若无则直接使用上方官方命令\n# 示例（假设存在镜像）：\n# git clone https:\u002F\u002Fgitee.com\u002Fmirror\u002Fpapers_for_protein_design_using_DL.git\n```\n*注：若无私有镜像，建议在终端配置代理或使用 GitHub 加速工具下载。*\n\n## 3. 基本使用与工作流\n\n本项目的核心用法是**查阅分类目录**，找到你感兴趣的研究方向（如“抗体设计”、“扩散模型”等），然后点击链接跳转到具体的论文页面或代码仓库。\n\n### 步骤一：浏览分类目录\n打开本地克隆的 `README.md` 文件，或直接访问 GitHub 页面。资源按以下逻辑分类：\n*   **0) Benchmarks and datasets**: 查找序列\u002F结构数据集和评估基准（如 `FLIP`, `ProteinGym`）。\n*   **1) Reviews and surveys**: 阅读综述，了解领域现状。\n*   **2) - 6) Design Paradigms**: 根据技术路线查找论文，例如：\n    *   `Diffusion-based`: 基于扩散模型的设计。\n    *   `Transformer-based`: 基于 Transformer 架构的设计。\n    *   `Function to Structure`: 从功能到结构的生成任务。\n\n### 步骤二：运行具体项目示例\n假设你在列表中对 **\"ProteinGym\"** (大规模蛋白质设计基准) 感兴趣，以下是基于该项目链接的典型启动流程：\n\n1.  **获取项目代码** (从列表中的 code 链接获取):\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002FOATML-Markslab\u002FProteinGym.git\n    cd ProteinGym\n    ```\n\n2.  **创建虚拟环境并安装依赖**:\n    ```bash\n    conda create -n proteingym python=3.9\n    conda activate proteingym\n    \n    # 推荐使用国内镜像源加速安装 (如清华源)\n    pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n    ```\n\n3.  **运行简单示例** (参考该项目具体的 README):\n    ```bash\n    # 示例：运行一个简单的基准测试脚本\n    python run_benchmark.py --task fitness_prediction --model esm1b\n    ```\n\n### 步骤三：利用中文社区资源\n该项目 README 特别提到了相关的中文笔记专栏，适合中国开发者深入理解论文细节：\n*   **知乎专栏**: 访问项目中提到的 [Zhihu Column](https:\u002F\u002Fwww.zhihu.com\u002Fcolumn\u002Fc_1475864742820929537) 查看论文的中文解读和笔记。\n*   **RosettAI**: 获取更多关于 Rosetta 和相关算法的建议笔记。\n\n---\n**提示**: 此仓库会每周更新（最新更新时间见 README 顶部），请定期执行 `git pull` 以获取最新的论文列表。","某生物制药公司的 AI 研发团队正致力于利用深度学习技术，从头设计一种能特异性结合无序蛋白的新型抗体药物，急需追踪该领域的最新算法突破。\n\n### 没有 papers_for_protein_design_using_DL 时\n- **文献检索大海捞针**：研究人员需在 PubMed、arXiv 和 GitHub 等多个平台手动搜索关键词，极易遗漏如\"Reinforcement-guided generative protein language models\"等跨学科的最新预印本。\n- **代码复现门槛高**：找到论文后，往往难以快速定位对应的开源代码仓库或基准测试平台（如 CombinGym），导致验证新算法的时间成本高达数周。\n- **领域视野受限**：缺乏系统性的分类整理，团队难以全面掌握从“序列数据集”到“酶设计”等细分方向的全貌，容易陷入局部技术盲区。\n- **前沿动态滞后**：无法及时获取像\"Latent-Y\"这样经过实验室验证的自主智能体报告，导致研发路线可能落后于社区最新进展。\n\n### 使用 papers_for_protein_design_using_DL 后\n- **一站式精准获取**：团队直接在该库中查阅按“抗体设计”、“结合物设计”分类的更新列表，瞬间锁定上周发布的关于无序蛋白结合物设计的前沿综述。\n- **资源链接直达**：每篇论文旁均附带官方代码、补充材料甚至在线演示网站链接，研究人员可立即克隆\"genAAV\"等项目的代码进行微调实验。\n- **知识体系结构化**：借助清晰的目录导航，团队迅速梳理出从“功能到结构”再到“序列”的各种设计范式，明确了技术选型的最佳路径。\n- **同步社区脉搏**：通过每周更新的列表，团队第一时间掌握了商业化技术报告和高影响力基准测试，确保研发策略始终处于行业最前沿。\n\npapers_for_protein_design_using_DL 将原本分散且耗时的文献调研工作转化为高效的战略情报获取，显著加速了蛋白质药物从概念验证到实验设计的转化周期。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FPeldom_papers_for_protein_design_using_DL_4f4d6762.jpg","Peldom","Sean Peldom Zhang","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FPeldom_7b71eb73.jpg","Official name:  Yanzhe Zhang","Westlake University","Hangzhou, Zhejiang, China",null,"PeldomZ","https:\u002F\u002Fgithub.com\u002FPeldom",1917,216,"2026-04-10T08:54:19","GPL-3.0",1,"","未说明",{"notes":89,"python":87,"dependencies":90},"该仓库是一个关于“使用深度学习进行蛋白质设计”的论文列表和资源索引，并非一个可执行的软件工具或代码库。因此，它没有特定的操作系统、GPU、内存、Python 版本或依赖库要求。用户仅需浏览器即可访问其中的链接，或根据列表中引用的具体论文对应的独立代码仓库去配置相应的运行环境。",[],[14],[93,94],"deep-learning","protein-design","2026-03-27T02:49:30.150509","2026-04-11T18:32:46.316130",[],[]]