Binding-Adaptive Diffusion Models for Structure-Based Drug Design

TL;DR

BindDM is a novel diffusion model framework that adaptively captures protein-ligand interactions in 3D space, improving the realism and binding affinity of generated molecules for structure-based drug design.

Contribution

The paper introduces BindDM, a hierarchical, binding-adaptive diffusion model utilizing SE(3)-equivariant networks to better incorporate binding site interactions in molecule generation.

Findings

Generates molecules with more realistic 3D structures.

Achieves higher binding affinities with up to -5.92 Avg. Vina Score.

Maintains proper molecular properties during generation.

Abstract

Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D space for molecular generation. To address this problem, we propose a novel framework, namely Binding-Adaptive Diffusion Models (BindDM). In BindDM, we adaptively extract subcomplex, the essential part of binding sites responsible for protein-ligand interactions. Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information. We iterate this hierarchical complex-subcomplex process with cross-hierarchy interaction node for adequately fusing global binding context between the complex and its corresponding subcomplex. Empirical studies on the CrossDocked2020 dataset show BindDM can generate molecules with more realistic 3D structures and higher binding affinities towards the protein targets, with up to -5.92 Avg. Vina Score, while maintaining proper molecular properties. Our code is available at https://github.com/YangLing0818/BindDM