Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with Guidance

2025-02-09

AI Summary

This work addresses the challenge of ligand shape-guided 3D molecular generation. We propose DiffSMol—the first 3D diffusion generative model jointly conditioned on ligand shape embeddings and protein binding pockets. Our method employs a pre-trained geometric-aware shape encoder to extract conformational features of ligands and integrates pocket structural information to jointly optimize geometric fidelity and binding affinity during diffusion. We introduce an iterative shape-pocket co-guided sampling strategy and embed a unified 3D conformation generation and optimization module. On standard benchmarks, DiffSMol achieves a shape-matching success rate of 61.4%—a +50.2 percentage point improvement over the state-of-the-art baseline—and improves predicted binding affinity by 17.7% under pocket guidance. Generated molecules exhibit high structural novelty, strong target adaptability, and favorable drug-likeness.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Drug development is a critical but notoriously resource- and time-consuming process. In this manuscript, we develop a novel generative artificial intelligence (genAI) method DiffSMol to facilitate drug development. DiffSmol generates 3D binding molecules based on the shapes of known ligands. DiffSMol encapsulates geometric details of ligand shapes within pre-trained, expressive shape embeddings and then generates new binding molecules through a diffusion model. DiffSMol further modifies the generated 3D structures iteratively via shape guidance to better resemble the ligand shapes. It also tailors the generated molecules toward optimal binding affinities under the guidance of protein pockets. Here, we show that DiffSMol outperforms the state-of-the-art methods on benchmark datasets. When generating binding molecules resembling ligand shapes, DiffSMol with shape guidance achieves a success rate 61.4%, substantially outperforming the best baseline (11.2%), meanwhile producing molecules with novel molecular graph structures. DiffSMol with pocket guidance also outperforms the best baseline in binding affinities by 13.2%, and even by 17.7% when combined with shape guidance. Case studies for two critical drug targets demonstrate very favorable physicochemical and pharmacokinetic properties of the generated molecules, thus, the potential of DiffSMol in developing promising drug candidates.

Problem

• Generates 3D binding molecules
• Improves drug development efficiency
• Enhances binding affinity accuracy

Innovation

• Shape-conditioned diffusion models
• 3D binding molecule generation
• Protein pocket guidance optimization