A 3D pocket-aware and evolutionary conserved interaction guided diffusion model for molecular optimization

2025-05-09

AI Summary

This study addresses the critical challenge in structure-based drug design of generating optimized molecules that specifically engage evolutionarily conserved functional residues of target proteins to enhance bioactivity and target selectivity. We propose the first 3D equivariant diffusion model that explicitly incorporates residue evolutionary conservation throughout the entire generative process, integrating protein pocket geometry, ligand–protein interaction features, and a conservation-weighted potential energy field for guidance. To enable synergistic optimization of molecular scaffolds and binding poses, we introduce pocket-aware coordinate encoding and an intermolecular attention mechanism. In multi-target benchmarking experiments, our method achieves a 42% increase in non-covalent interactions between generated ligands and highly conserved residues compared to DiffDec, accompanied by significantly improved predicted binding affinity and superior drug-likeness properties.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Evolutionary Computation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Generating molecules that bind to specific protein targets via diffusion models has shown good promise for structure-based drug design and molecule optimization. Especially, the diffusion models with binding interaction guidance enables molecule generation with high affinity through forming favorable interaction within protein pocket. However, the generated molecules may not form interactions with the highly conserved residues, which are important for protein functions and bioactivities of the ligands. Herein, we developed a new 3D target-aware diffusion model DiffDecip, which explicitly incorporates the protein-ligand binding interactions and evolutionary conservation information of protein residues into both diffusion and sampling process, for molecule optimization through scaffold decoration. The model performance revealed that DiffDecip outperforms baseline model DiffDec on molecule optimization towards higher affinity through forming more non-covalent interactions with highly conserved residues in the protein pocket.

Problem

• Generating molecules binding to protein targets effectively
• Incorporating evolutionary conservation in molecule-protein interactions
• Optimizing molecules for higher affinity via scaffold decoration

Innovation

• 3D target-aware diffusion model for molecule optimization
• Incorporates protein-ligand binding interactions explicitly
• Utilizes evolutionary conservation information in diffusion