Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design
Prescient Design（普雷赛特设计公司）；Genentech（基因泰克公司）；New York University（纽约大学）
Nataša Tagasovska, Ji Won Park, Matthieu Kirchmeyer, Nathan C. Frey, Andrew Martin Watkins, Aya Abdelsalam Ismail, Arian Rokkum Jamasb, Edith Lee, Tyler Bryson,… 展开作者
Nataša 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
机器学习（ML）在加速药物设计方面已展现出显著前景。治疗性分子的主动 ML 引导优化通常依赖一个代理模型来预测感兴趣的目标性质。模型预测被用于决定在实验室中评估哪些设计，随后模型根据新的测量结果进行更新，以指导下一轮决策。一个关键挑战在于，每一轮的实验反馈会引发下一轮候选方案或实验方案的改变，从而导致分布偏移。为提升对这些偏移的鲁棒性，我们必须在模型训练中显式地考虑它们。我们应用领域泛化（DG）方法，在由设计轮次定义的五个领域上对抗体与抗原之间相互作用的稳定性进行分类。我们的结果表明，基础模型和集成方法能够提升在分布外领域上的预测性能。我们公开发布了扩展 DG 基准“DomainBed”的代码库，以及模拟跨设计轮次分布偏移的抗体序列与结构相关数据集。
英文摘要：
Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model predicting the target property of interest. The model predictions are used to determine which designs to evaluate in the lab, and the model is updated on the new measurements to inform the next cycle of decisions. A key challenge is that the experimental feedback from each cycle inspires changes in the candidate proposal or experimental protocol for the next cycle, which lead to distribution shifts. To promote robustness to these shifts, we must account for them explicitly in the model training. We apply domain generalization (DG) methods to classify the stability of interactions between an antibody and antigen across five domains defined by design cycles. Our results suggest that foundational models and ensembling improve predictive performance on out-of-distribution domains. We publicly release our codebase extending the DG benchmark ``DomainBed,'' and the associated dataset of antibody sequences and structures emulating distribution shifts across design cycles.
Best practices for machine learning in antibody discovery and development
LabGenius Ltd.（LabGenius有限公司）；University College London（伦敦大学学院）；Sanofi Deutschland GmbH（赛诺菲德国有限公司）；AstraZeneca（阿斯利康）；Moderna Therapeutics（莫德纳治疗公司）；Oslo University Hospital（奥斯陆大学医院）；University of Oslo（奥斯陆大学）
AbRank: A Benchmark Dataset and Metric-Learning Framework for Antibody-Antigen Affinity Ranking
Structural Molecular Biology, Division of Biosciences, University College London（伦敦大学学院生物结构分子生物学系）；Institute of Computational Life Sciences, Zürich University of Applied Sciences (ZHAW)（苏黎世应用科学大学计算生命科学研究所）；Biomedical Informatics and Data Science, Yale School of Medicine（耶鲁医学院生物医学信息学与数据科学）；Centre for Artificial Intelligence, University College London（伦敦大学学院人工智能中心）
Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design
University of Freiburg（弗赖堡大学）；Collaborative Research Institute Intelligent Oncology (CRIION)（智能肿瘤学合作研究所（CRIION））；University Medical Center Freiburg（弗赖堡大学医学中心）；BrainLinks-BrainTools（脑连接-脑工具研究中心）
Conditional Antibody Design as 3D Equivariant Graph Translation
Tsinghua University（清华大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Renmin University of China（中国人民大学）
Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；ByteDance Research（字节跳动研究院）；College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）
BetterBodies: Reinforcement Learning guided Diffusion for Antibody Sequence Design
University of Freiburg（弗莱堡大学）；Collaborative Research Institute Intelligent Oncology (CRIION)（智能肿瘤学合作研究所（CRIION））；University Medical Center Freiburg（弗莱堡大学医学中心）；BrainLinks-BrainTools
Structure-Aware Antibody Design with Affinity-Optimized Inverse Folding
University of Texas Health Science Center at Houston（休斯顿德克萨斯大学健康科学中心）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Worcester Polytechnic Institute（伍斯特理工学院）
AntBO: Towards Real-World Automated Antibody Design with Combinatorial Bayesian Optimisation
University of Edinburgh（爱丁堡大学）；Technische Universität Darmstadt（达姆施塔特工业大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Oslo（奥斯陆大学）；American University of Beirut Medical Centre（贝鲁特美国大学医学中心）；University College London（伦敦大学学院）
