MDM: Molecular Diffusion Model for 3D Molecule Generation
This addresses a fundamental task in drug design for researchers and practitioners, offering improved molecule generation with enhanced diversity, though it appears incremental as it builds upon existing diffusion models.
The paper tackled the problem of generating 3D molecular geometries with unsatisfactory performance and low diversity in existing diffusion-based methods, particularly for large molecules, by proposing a novel diffusion model that incorporates interatomic forces and a distributional controlling variable, resulting in significant outperformance on multiple benchmarks.
Molecule generation, especially generating 3D molecular geometries from scratch (i.e., 3D \textit{de novo} generation), has become a fundamental task in drug designs. Existing diffusion-based 3D molecule generation methods could suffer from unsatisfactory performances, especially when generating large molecules. At the same time, the generated molecules lack enough diversity. This paper proposes a novel diffusion model to address those two challenges. First, interatomic relations are not in molecules' 3D point cloud representations. Thus, it is difficult for existing generative models to capture the potential interatomic forces and abundant local constraints. To tackle this challenge, we propose to augment the potential interatomic forces and further involve dual equivariant encoders to encode interatomic forces of different strengths. Second, existing diffusion-based models essentially shift elements in geometry along the gradient of data density. Such a process lacks enough exploration in the intermediate steps of the Langevin dynamics. To address this issue, we introduce a distributional controlling variable in each diffusion/reverse step to enforce thorough explorations and further improve generation diversity. Extensive experiments on multiple benchmarks demonstrate that the proposed model significantly outperforms existing methods for both unconditional and conditional generation tasks. We also conduct case studies to help understand the physicochemical properties of the generated molecules.