用于真实抗体设计的解耦序列与结构生成
Decoupled Sequence and Structure Generation for Realistic Antibody Design
AI总结：
针对抗体联合生成序列与结构的架构限制及非自回归生成的token重复问题，提出ASSD解耦框架与基于组成的目标函数，提升了抗体设计性能并缓解重复问题。
摘要：
近年来，深度学习在抗体设计领域取得快速进展，而抗体设计对治疗药物的研发起着关键作用。当前主流范式是训练模型联合生成抗体序列与结构作为候选方案。然而，联合生成要求模型同时生成离散的氨基酸类别和连续的3D坐标，这限制了可行的架构空间，还可能导致性能欠佳。针对这一问题，我们提出抗体序列-结构解耦（antibody sequence-structure decoupling，ASSD）框架，将序列生成与结构预测分离开来。尽管我们的方法原理简单，但这一思路能够采用功能强大的神经网络架构，并实现了显著的性能提升。我们还发现，广泛使用的非自回归生成器会生成存在过度重复token的序列，这类序列不仅属于分布外样本，还容易具备不良的可开发性，可能在患者体内引发有害的免疫反应。为解决该问题，我们引入了一种基于组成的目标函数，能够在高性能与低token重复度之间实现高效权衡。ASSD在多项抗体设计实验中表现出性能提升，而基于组成的目标函数成功缓解了非自回归模型的token重复问题。
英文摘要：
Recently, deep learning has made rapid progress in antibody design, which plays a key role in the advancement of therapeutics. A dominant paradigm is to train a model to jointly generate the antibody sequence and the structure as a candidate. However, the joint generation requires the model to generate both the discrete amino acid categories and the continuous 3D coordinates; this limits the space of possible architectures and may lead to suboptimal performance. In response, we propose an antibody sequence-structure decoupling (ASSD) framework, which separates sequence generation and structure prediction. Although our approach is simple, our idea allows the use of powerful neural architectures and demonstrates notable performance improvements. We also find that the widely used non-autoregressive generators promote sequences with overly repeating tokens. Such sequences are both out-of-distribution and prone to undesirable developability properties that can trigger harmful immune responses in patients. To resolve this, we introduce a composition-based objective that allows an efficient trade-off between high performance and low token repetition. ASSD shows improved performance in various antibody design experiments, while the composition-based objective successfully mitigates token repetition of non-autoregressive models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
