Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge
CoRR(2024)
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要