Work

SGEDiff: a subgraph-enriched diffusion model for structure-based 3D molecular generation

Year: 2025

Type: article

Abstract: Structure-based molecular generation is an emerging approach in computer-aided drug discovery, enabling the design of compounds that that complement the three-dimensional structure of target proteins. However, most diffusion-based 3D molecular generative models still face several limitations, such as imbalanced protein–ligand representations or reliance on predefined binding pockets. To address these limitations, we propose SGEDiff, a novel subgraph enriched generative framework for 3D molecule generation. Our model hierarchically fuses subgraph and global graph representations to capture both local binding patterns and key structural features of protein pockets. Furthermore, an integrated pocket prediction module identifies binding regions in unseen proteins, eliminating reliance on predefined pocket coordinates. Experimental results show that SGEDiff outperforms baseline diffusion-based methods in generating high-affinity molecules across diverse targets. Moreover, practical applications in de novo drug design demonstrate improved success rates in generating compounds for novel protein targets, underscoring its potential to advance structure-based drug discovery. This study presents SGEDiff, a 3D molecular generative model that employs subgraph-enriched hierarchical fusion to capture local and global structural features. It incorporates a pocket prediction module, enabling structure-aware molecule generation in the absence of predefined binding pockets. SGEDiff achieves improved affinity-based performance across diverse targets and demonstrates strong applicability in de novo drug design for unseen proteins.

Source: Journal of Cheminformatics

DOI: 10.1186/s13321-025-01123-z