Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called \textsc{PPFlow}, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing.

翻译：治疗性肽在近几十年来已被证明具有巨大的药物价值和潜力。然而，人工智能辅助的肽药物发现方法尚未得到充分探索。为填补这一空白，我们提出了一种名为 \textsc{PPFlow} 的目标感知肽设计方法，该方法基于环面流形上的条件流匹配，以建模肽结构设计中扭转角的内在几何结构。此外，我们建立了一个名为 PPBench2024 的蛋白质-肽结合数据集，以填补基于结构的肽药物设计任务中海量数据的空白，并支持深度学习方法的训练。大量实验表明，与基线模型相比，PPFlow 在肽药物生成和优化任务中达到了最先进的性能，并且可以推广到包括对接和侧链堆积在内的其他任务。