Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models

TL;DR

This paper introduces a deep generative model capable of creating 3D molecular structures conditioned on a receptor binding site, enabling targeted drug design with novel molecules that interact reasonably with the target site.

Contribution

It is the first model to generate 3D molecular structures conditioned on a receptor binding pocket using convolutional neural networks and variational latent spaces.

Findings

Valid and unique molecules can be sampled from the model.

Generated molecules show reasonable interactions with the binding site.

Novel structures increase with distance in latent space, but binding affinity decreases.

Abstract

Deep generative models have been applied with increasing success to the generation of two dimensional molecules as SMILES strings and molecular graphs. In this work we describe for the first time a deep generative model that can generate 3D molecular structures conditioned on a three-dimensional (3D) binding pocket. Using convolutional neural networks, we encode atomic density grids into separate receptor and ligand latent spaces. The ligand latent space is variational to support sampling of new molecules. A decoder network generates atomic densities of novel ligands conditioned on the receptor. Discrete atoms are then fit to these continuous densities to create molecular structures. We show that valid and unique molecules can be readily sampled from the variational latent space defined by a reference `seed' structure and generated structures have reasonable interactions with the binding site. As structures are sampled farther in latent space from the seed structure, the novelty of the generated structures increases, but the predicted binding affinity decreases. Overall, we demonstrate the feasibility of conditional 3D molecular structure generation and provide a starting point for methods that also explicitly optimize for desired molecular properties, such as high binding affinity.