Target-aware 3D molecular generation based on guided equivariant diffusion
Qiaoyu Hu, Changzhi Sun, Huan He, Jiazheng Xu, Danlin Liu, Wenqing Zhang, Sumeng Shi, Kai Zhang, Honglin Li
Abstract
Recent molecular generation models for structure-based drug design (SBDD) often produce unrealistic 3D molecules due to the neglect of structural feasibility and drug-like properties. In this paper, we introduce DiffGui, a target-conditioned E(3)-equivariant diffusion model that integrates bond diffusion and property guidance, to address the above challenges. The combination of atom diffusion and bond diffusion guarantees the concurrent generation of both atoms and bonds by explicitly modeling their interdependencies. Property guidance incorporates the binding affinity and drug-like properties of molecules into the training and sampling processes. Extensive experiments prove that DiffGui outperforms existing methods in generating molecules with high binding affinity, rational chemical structure, and desirable properties. Ablation studies confirm the importance of bond diffusion and property guidance modules. DiffGui demonstrates effectiveness in both de novo drug design and lead optimization, with validation through wet-lab experiments. A guided diffusion model - DiffGui is designed here to generate molecules conditioned on protein targets. It simultaneously models both atoms and bonds with molecular property guidance, producing structurally realistic and high potential compounds.