Constrained Bayesian Optimization for Automatic Chemical Design

By Ryan-Rhys Griffiths, José Miguel Hernández-Lobato. 2017

78 citations recorded by the source corpus.

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 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 class of training set mismatch in many generative tasks involving Bayesian optimization over the latent space of a variational autoencoder.

Subfields: Computational Theory and Mathematics, Materials Chemistry

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 Materials Chemistry

Citations in the corpus

BoTorch: Programmable Bayesian Optimization in PyTorch (2019, background): “…(Feurer et al., 2015; Shahriari et al., 2016; Wu et al., 2019), robotic control (Ca-landra et al., 2016; Antonova et al., 2017), chemical de-sign (Grifﬁths & Hernández-Lobato, 2017; Li et al., 2017), and internet-scale ranking systems and infrastructure (Agar-wal et al., 2018; Letham et al.,…”
Recent Advances in Bayesian Optimization (2022, background): “As a promising selection criterion in the presence of constraints, EIC has been studied in a variety of settings [91, 139].”
Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection (2019, background): “…space Z too far away from the training data, which might yield latent points z that decode to semantically meaningless and/or syntactically invalid inputs x (Kusner et al., 2017; Grifﬁths & Hern´andez-Lobato, 2017; Brookes et al., 2019; Mahmood & Hern´andez-Lobato, 2019; Alperstein et al., 2019).”
GFlowNet Foundations (2021, unknown): “, 2010), which have also been used for searching in the space of molecules (Griffiths and Hernández-Lobato, 2017).”