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

TL;DR

This work addresses the challenge of generating protein-pocket–binding molecules that engage highly conserved residues by introducing DiffDecip, a 3D target-aware diffusion model that jointly leverages evolutionary conservation and a pretrained interaction-prior network. The method augments the forward and reverse diffusion steps with a Conservation-Aware Condition and an Interaction-Prior Guidance mechanism, enabling R-group decorations that form more non-bonded interactions with conserved pocket residues. Empirical results show DiffDecip outperforms DiffDec on Vina score and high-affinity generation, with more interactions formed in conserved regions across most targets, underscoring the practical value for structure-based drug design. The approach advances scaffold-decoration workflows by prioritizing conserved-pocket interactions, potentially yielding more potent and functionally robust ligands.

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.

Figures (2)

• Figure 1: Model Overview.
• Figure 2: Performance of DiffDecip and comparison with DiffDec.