In-Pocket 3D Graphs Enhance Ligand-Target Compatibility in Generative Small-Molecule Creation

TL;DR

This paper introduces a 3D graph-based generative model that encodes protein-ligand contacts to produce molecules with improved binding compatibility, advancing structure-based drug discovery.

Contribution

It presents a novel 3D relational graph architecture integrating contact predictions with a variational autoencoder for targeted molecule generation.

Findings

Generated molecules show higher docking scores and stereochemistry accuracy.

Model outperforms 2D ligand-based methods in binding pocket compatibility.

High recovery rate of predicted contacts in docking poses.

Abstract

Proteins in complex with small molecule ligands represent the core of structure-based drug discovery. However, three-dimensional representations are absent from most deep-learning-based generative models. We here present a graph-based generative modeling technology that encodes explicit 3D protein-ligand contacts within a relational graph architecture. The models combine a conditional variational autoencoder that allows for activity-specific molecule generation with putative contact generation that provides predictions of molecular interactions within the target binding pocket. We show that molecules generated with our 3D procedure are more compatible with the binding pocket of the dopamine D2 receptor than those produced by a comparable ligand-based 2D generative method, as measured by docking scores, expected stereochemistry, and recoverability in commercial chemical databases. Predicted protein-ligand contacts were found among highest-ranked docking poses with a high recovery rate. This work shows how the structural context of a protein target can be used to enhance molecule generation.