Skip to main content
QUICK REVIEW

[论文解读] Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge

Yufei Huang, Odin Zhang|arXiv (Cornell University)|Feb 18, 2024
Molecular Communication and Nanonetworks被引用 6
一句话总结

Re-Dock 在几何流形上引入扩散-桥框架,用于预测柔性配体和口袋侧链构型,并具有显式的相互作用先验,从而在apo和跨对接情景中提升现实感的对接。

ABSTRACT

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.

研究动机与目标

  • 激励同时建模配体与口袋侧链构象的柔性对接这一尚未充分探索的任务。
  • 在几何流形(旋转、平移、扭转)上开发具有能量到几何先验的扩散-桥生成模型。
  • 将显式的蛋白质-配体相互作用先验融入,以引导基于几何的生成。
  • 在apo-dock和cross-dock数据集上对该方法进行基准测试,以评估其真实感与效率。

提出的方法

  • 将扩散桥的概念扩展到非欧几里得几何流形(平移、旋转、扭转)以用于对接。
  • 通过受牛顿-欧拉刚体力学启发的能量到几何映射,引入带有相互作用先验的几何先验桥。
  • 自回归地建模口袋侧链,使其在生成过程中遵循序列扭转动力学。
  • 通过能量到几何耦合将三维相互作用能量先验嵌入扩散过程。
  • 将学习得到的漂移项参数化为 s_t^θ = β f̂_t + f̂_t^θ,支持结合建模结合结合?——使得结合能和构型的协同建模成为可能。
(a) Flexible docking and priori leakage
(a) Flexible docking and priori leakage

实验结果

研究问题

  • RQ1在现实场景(apo 与跨对接)下,Re-Dock 能否准确预测配体和口袋侧链的柔性对接构型?
  • RQ2与基线相比,Re-Dock 在生成真实的侧链构象方面表现如何?
  • RQ3Re-Dock 在跨对接和apo对接等具有挑战性的对接任务中,如何在不产生 holo-pocket 漏出(leakage)的情况下实现泛化?
  • RQ4关键设计选择(侧链自回归、能量先验、采样步数)对对接质量和效率有何影响?

主要发现

  • 与基线相比,Re-Dock 在柔性重对接和apo对接基准测试中显示出更优的性能,采用口袋感知的预测。
  • 该模型在侧链构象生成方面达到准确水平,在侧链的Angstrom尺度 RMSD-like 指标上优于基线。
  • 能量到几何的先验以及几何上的扩散桥机制使得对接具备相互作用感知的诱导拟合,现实感提升。
  • 消融研究显示,侧链生成与先验能量项对维持物理合理性和减少冲突的重要性。
  • 该方法扩展到跨对接任务,表明在药物发现流程中的实际应用性。
Figure 2: The illustration of Re-Dock Framework. We aim to simulate the induced fitting process with geometric prior bridges. Our key designs are threefold: \raisebox{-.9pt} {1}⃝ The pocket sidechains displace the most flexibility for inducing interactions. Thus, we generate the sidechain conformati
Figure 2: The illustration of Re-Dock Framework. We aim to simulate the induced fitting process with geometric prior bridges. Our key designs are threefold: \raisebox{-.9pt} {1}⃝ The pocket sidechains displace the most flexibility for inducing interactions. Thus, we generate the sidechain conformati

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。