DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design

TL;DR

DecompDiff introduces a diffusion model that decomposes ligands into arms and scaffold, enhancing structure-based drug design by generating high-affinity molecules with improved properties and stability.

Contribution

The paper presents a novel diffusion model with decomposed priors for arms and scaffold, improving efficiency and effectiveness in structure-based drug design.

Findings

Achieves state-of-the-art performance in generating high-affinity molecules.

Maintains proper molecular properties and conformational stability.

Up to -8.39 Avg. Vina Dock score and 24.5 Success Rate.

Abstract

Designing 3D ligands within a target binding site is a fundamental task in drug discovery. Existing structured-based drug design methods treat all ligand atoms equally, which ignores different roles of atoms in the ligand for drug design and can be less efficient for exploring the large drug-like molecule space. In this paper, inspired by the convention in pharmaceutical practice, we decompose the ligand molecule into two parts, namely arms and scaffold, and propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold. In order to facilitate the decomposed generation and improve the properties of the generated molecules, we incorporate both bond diffusion in the model and additional validity guidance in the sampling phase. Extensive experiments on CrossDocked2020 show that our approach achieves state-of-the-art performance in generating high-affinity molecules while maintaining proper molecular properties and conformational stability, with up to -8.39 Avg. Vina Dock score and 24.5 Success Rate. The code is provided at https://github.com/bytedance/DecompDiff