Auto-Encoding Molecular Conformations
This work addresses the challenge of representing and generating molecular conformations, which is crucial for drug discovery and materials science.
This paper introduces an Autoencoder that transforms discrete molecular conformations into a continuous latent representation. The model successfully clusters similar conformations and can generate diverse, energetically favorable conformations, and enables optimization for molecules with desired spatial properties.
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.