arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.06642q-bio.BMcs.AIcs.LG
收藏

PPFlow: 基于扭转流匹配的靶点感知肽设计

PPFlow: Target-aware Peptide Design with Torsional Flow Matching

Zhejiang University(浙江大学);Westlake University(西湖大学)

Haitao Lin, Odin Zhang, Huifeng Zhao, Dejun Jiang, Lirong Wu, Zicheng Liu, Yufei Huang, Stan Z. Li

AI总结:

本研究提出基于环面流形条件流匹配的靶点感知肽设计方法PPFlow,构建蛋白质-肽结合数据集PPBench2024,实验证明其在肽药物生成优化等任务上达SOTA且可推广至多任务。

摘要:

近几十年来,治疗性肽已被证明具有极高的药用价值和潜力。然而,人工智能辅助肽药物发现的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PPFlow的靶点感知肽设计方法,该方法基于环面流形上的条件流匹配,通过建模扭转角的内部几何结构实现肽结构设计。此外,我们构建了一个名为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的大规模数据空白,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在肽药物生成与优化任务上达到了当前最优性能,并且可推广至对接、侧链组装等其他任务。

英文摘要:

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.

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。

↑