Auto-Encoding Molecular Conformations

TL;DR

This paper introduces an autoencoder model for molecular conformations that encodes discrete atomic arrangements into a continuous latent space, enabling clustering, generation, and optimization of molecular conformations.

Contribution

The work presents a novel autoencoder architecture for molecular conformations, facilitating clustering, generation, and optimization in a continuous latent space.

Findings

Similar conformations cluster together in latent space

Model can generate diverse energetically favorable conformations

Latent space enables optimization of molecular conformations

Abstract

In this work we introduce an Autoencoder for molecular conformations. Our proposed model converts the discrete spatial arrangements of atoms in a given molecular graph (conformation) into and from a continuous fixed-sized latent representation. We demonstrate that in this latent representation, similar conformations cluster together while distinct conformations split apart. Moreover, by training a probabilistic model on a large dataset of molecular conformations, we demonstrate how our model can be used to generate diverse sets of energetically favorable conformations for a given molecule. Finally, we show that the continuous representation allows us to utilize optimization methods to find molecules that have conformations with favourable spatial properties.