CUED Publications database

Constrained Bayesian optimization for automatic chemical design using variational autoencoders

Griffiths, RR and Hernández-Lobato, JM (2020) Constrained Bayesian optimization for automatic chemical design using variational autoencoders. Chemical Science, 11. pp. 577-586. ISSN 2041-6520

Full text not available from this repository.

Abstract

© 2020 The Royal Society of Chemistry. Automatic Chemical Design is a framework for generating novel molecules with optimized properties. The original scheme, featuring Bayesian optimization over the latent space of a variational autoencoder, suffers from the pathology that it tends to produce invalid molecular structures. First, we demonstrate empirically that this pathology arises when the Bayesian optimization scheme queries latent space points far away from the data on which the variational autoencoder has been trained. Secondly, by reformulating the search procedure as a constrained Bayesian optimization problem, we show that the effects of this pathology can be mitigated, yielding marked improvements in the validity of the generated molecules. We posit that constrained Bayesian optimization is a good approach for solving this kind of training set mismatch in many generative tasks involving Bayesian optimization over the latent space of a variational autoencoder.

Item Type: Article
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 31 Jan 2020 20:32
Last Modified: 15 Sep 2020 04:27
DOI: 10.1039/c9sc04026a