Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Models

TL;DR

This paper introduces a novel deep learning approach using a conditional variational autoencoder to generate 3D molecules conditioned on receptor binding sites, advancing structure-based drug discovery.

Contribution

It is the first to generate 3D molecules conditioned on protein binding sites using deep learning, enabling end-to-end bioactive molecule prediction from protein structures.

Findings

Generated molecules vary with receptor mutations

Conditional generation produces plausible drug-like structures

Latent space exploration reveals meaningful chemical variations

Abstract

The goal of structure-based drug discovery is to find small molecules that bind to a given target protein. Deep learning has been used to generate drug-like molecules with certain cheminformatic properties, but has not yet been applied to generating 3D molecules predicted to bind to proteins by sampling the conditional distribution of protein-ligand binding interactions. In this work, we describe for the first time a deep learning system for generating 3D molecular structures conditioned on a receptor binding site. We approach the problem using a conditional variational autoencoder trained on an atomic density grid representation of cross-docked protein-ligand structures. We apply atom fitting and bond inference procedures to construct valid molecular conformations from generated atomic densities. We evaluate the properties of the generated molecules and demonstrate that they change significantly when conditioned on mutated receptors. We also explore the latent space learned by our generative model using sampling and interpolation techniques. This work opens the door for end-to-end prediction of stable bioactive molecules from protein structures with deep learning.