arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.11459q-bio.BMcs.AIcs.LGphysics.chem-ph
收藏

Re-Dock:利用扩散桥实现灵活且真实的分子对接

Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge

Zhejiang University(浙江大学);Westlake University(西湖大学);University of Washington(华盛顿大学)

Yufei Huang, Odin Zhang, Lirong Wu, Cheng Tan, Haitao Lin, Zhangyang Gao, Siyuan Li, Stan. Z. Li

AI总结:

本文提出Re-Dock扩散桥生成模型,通过能量到几何映射联合建模结合能与构象,解决灵活分子对接中同时预测配体和口袋侧链构象的问题,在apo-dock和cross-dock基准上表现优于现有方法。

摘要:

准确预测蛋白质-配体结合结构(即分子对接任务)对药物设计至关重要,但仍具挑战性。尽管深度学习已展现出潜力,现有方法通常依赖全息蛋白结构(已对接,在真实任务中不可获取)或忽略口袋侧链构象,导致实际应用价值有限且构象预测不真实。为填补这些空白,我们引入一项尚未充分探索的任务——灵活对接,以同时预测配体和口袋侧链的构象,并提出 Re-Dock,一种扩展至几何流形的新型扩散桥生成模型。具体而言,我们提出受牛顿-欧拉方程启发的能量到几何映射,以联合建模结合能与构象,从而反映受能量约束的对接生成过程。在包括 apo-dock 和 cross-dock 在内的设计基准数据集上的综合实验表明,我们的模型在有效性和效率上均优于当前方法。

英文摘要:

Accurate prediction of protein-ligand binding structures, a task known as molecular docking is crucial for drug design but remains challenging. While deep learning has shown promise, existing methods often depend on holo-protein structures (docked, and not accessible in realistic tasks) or neglect pocket sidechain conformations, leading to limited practical utility and unrealistic conformation predictions. To fill these gaps, we introduce an under-explored task, named flexible docking to predict poses of ligand and pocket sidechains simultaneously and introduce Re-Dock, a novel diffusion bridge generative model extended to geometric manifolds. Specifically, we propose energy-to-geometry mapping inspired by the Newton-Euler equation to co-model the binding energy and conformations for reflecting the energy-constrained docking generative process. Comprehensive experiments on designed benchmark datasets including apo-dock and cross-dock demonstrate our model's superior effectiveness and efficiency over current methods.

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。

↑