How Much of the Chemical Space Has Been Covered? Measuring and Improving the Variety of Candidate Set in Molecular Generation

Forming a high-quality molecular candidate set that contains a wide range of dissimilar compounds is crucial to the success of drug discovery. However, comparing to the research aiming at optimizing chemical properties, how to measure and improve the variety of drug candidates is relatively understudied. In this paper, we first investigate the problem of properly measuring the molecular variety through both an axiomatic analysis framework and an empirical study. Our analysis suggests that many existing measures are not suitable for evaluating the variety of molecules. We also propose new variety measures based on our analysis. We further explicitly integrate the proposed variety measures into the optimization objective of molecular generation models. Our experiment results demonstrate that this new optimization objective can guide molecular generation models to find compounds that cover a lager chemical space, providing the downstream phases with more distinctive drug candidate choices.