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

By Tomohide Masuda, Matthew Ragoza, David Ryan Koes. 2020

61 citations recorded by the source corpus.

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.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, background): “, 2020) or de novo binder generation (Masuda et al., 2020; Imrie et al., 2021; Drotár et al., 2021).”
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design (2022, background): “Representative work : liGAN [180] proposes to represent 3D molecules by 3D atomic density maps which are more smooth than the discrete graph structures and devises a conditional VAE-based approach with 3D CNN as back-bone models.”
A 3D Generative Model for Structure-Based Drug Design (2022, methodology): “Another line of work studies generating molecules directly in 3D space [8, 28, 29, 20, 30, 15].”
Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets (2022, unknown): “Conditional generative models are developed to model the 3D atomic density distributions within the 3D pocket structures (Masuda et al., 2020; Luo et al., 2021).”