SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning

TL;DR

SubGDiff introduces a diffusion model that incorporates molecular substructure information to improve 3D molecular representation learning, leading to better performance in downstream drug discovery tasks.

Contribution

It proposes a novel diffusion model, SubGDiff, that explicitly integrates subgraph information into molecular diffusion processes, addressing limitations of previous atom-independent models.

Findings

Superior performance on downstream tasks

Effective incorporation of substructural information

Enhanced perception of molecular substructure

Abstract

Molecular representation learning has shown great success in advancing AI-based drug discovery. The core of many recent works is based on the fact that the 3D geometric structure of molecules provides essential information about their physical and chemical characteristics. Recently, denoising diffusion probabilistic models have achieved impressive performance in 3D molecular representation learning. However, most existing molecular diffusion models treat each atom as an independent entity, overlooking the dependency among atoms within the molecular substructures. This paper introduces a novel approach that enhances molecular representation learning by incorporating substructural information within the diffusion process. We propose a novel diffusion model termed SubGDiff for involving the molecular subgraph information in diffusion. Specifically, SubGDiff adopts three vital techniques: i) subgraph prediction, ii) expectation state, and iii) k-step same subgraph diffusion, to enhance the perception of molecular substructure in the denoising network. Experimentally, extensive downstream tasks demonstrate the superior performance of our approach. The code is available at https://github.com/youjibiying/SubGDiff.