Constrained Bayesian Optimization for Automatic Chemical Design

back to our research

Constrained Bayesian Optimization for Automatic Chemical Design

4-9 December, Long Beach, California, USA

Advances in Neural Information Processing Systems 30 (NIPS 2017)

Authors: Ryan-Rhys Griffiths (PROWLER.io), José Miguel Hernández-Lobato (Cambridge)

Abstract: Automatic Chemical Design leverages recent advances in deep generative modelling to provide a framework for performing continuous optimization of molecular properties. Although the provision of a continuous representation for prospective lead drug candidates has opened the door to gradient-based optimization, some challenges remain for the design process. One known pathology is the model’s tendency to decode invalid molecular structures. The goal of this paper is to test the hypothesis that the origin of the pathology is rooted in the current formulation of Bayesian optimization. Recasting the optimization procedure as a constrained Bayesian optimization problem allows the model to produce novel drug compounds consistently ranking in the 100th percentile of the distribution over training set scores.

Bayesian Optimisation

NIPS

Probabilistic Modelling


See paper