Timezone: »

DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
Jiaqi Guan · Xiangxin Zhou · Yuwei Yang · Yu Bao · Jian Peng · Jianzhu Ma · Qiang Liu · Liang Wang · Quanquan Gu

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #543
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

Author Information

Jiaqi Guan (UIUC)
Xiangxin Zhou
Yuwei Yang (ByteDance AI Lab)
Yu Bao (ByteDance AI Lab)
Jian Peng (UIUC)
Jianzhu Ma (Tsinghua University, Tsinghua University)
Qiang Liu (Institute of Automation, Chinese Academy of Sciences)
Liang Wang (CASIA)
Quanquan Gu (University of California, Los Angeles)

More from the Same Authors