Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction
DeepRLI: A Multi-objective Framework for Universal Protein--Ligand Interaction Prediction
DiffBindFR: An SE(3) Equivariant Network for Flexible Protein-Ligand Docking
Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.