DiffBindFR: An SE(3) Equivariant Network for Flexible Protein-Ligand Docking

TL;DR

DiffBindFR is a novel SE(3) equivariant diffusion-based neural network that improves flexible protein-ligand docking accuracy by modeling ligand movements and protein side chain flexibility, outperforming existing methods especially with Apo and AlphaFold2 structures.

Contribution

This work introduces DiffBindFR, a full-atom diffusion model explicitly considering protein side chain flexibility and ligand movement, advancing flexible docking accuracy in structure-based drug design.

Findings

DiffBindFR achieves higher accuracy in native-like binding structure prediction.

It produces physically plausible and detailed atomic interactions.

Demonstrates superior performance on Apo and AlphaFold2 modeled structures.

Abstract

Molecular docking, a key technique in structure-based drug design, plays pivotal roles in protein-ligand interaction modeling, hit identification and optimization, in which accurate prediction of protein-ligand binding mode is essential. Conventional docking approaches perform well in redocking tasks with known protein binding pocket conformation in the complex state. However, in real-world docking scenario without knowing the protein binding conformation for a new ligand, accurately modeling the binding complex structure remains challenging as flexible docking is computationally expensive and inaccurate. Typical deep learning-based docking methods do not explicitly consider protein side chain conformations and fail to ensure the physical plausibility and detailed atomic interactions. In this study, we present DiffBindFR, a full-atom diffusion-based flexible docking model that operates over the product space of ligand overall movements and flexibility and pocket side chain torsion changes. We show that DiffBindFR has higher accuracy in producing native-like binding structures with physically plausible and detailed interactions than available docking methods. Furthermore, in the Apo and AlphaFold2 modeled structures, DiffBindFR demonstrates superior advantages in accurate ligand binding pose and protein binding conformation prediction, making it suitable for Apo and AlphaFold2 structure-based drug design. DiffBindFR provides a powerful flexible docking tool for modeling accurate protein-ligand binding structures.