Molecule optimization via multi-objective evolutionary in implicit chemical space

TL;DR

MOMO is a novel multi-objective evolutionary framework that efficiently searches implicit chemical space for molecules optimized across multiple properties, significantly advancing molecule design with limited labeled data.

Contribution

It introduces a self-supervised codec to learn chemical representations and combines it with Pareto-based evolutionary search for multi-objective molecule optimization.

Findings

Outperforms previous methods in multi-objective optimization tasks.

Effectively explores chemical space for molecules with desired properties.

Demonstrates high success rate in lead molecule optimization.

Abstract

Machine learning methods have been used to accelerate the molecule optimization process. However, efficient search for optimized molecules satisfying several properties with scarce labeled data remains a challenge for machine learning molecule optimization. In this study, we propose MOMO, a multi-objective molecule optimization framework to address the challenge by combining learning of chemical knowledge with Pareto-based multi-objective evolutionary search. To learn chemistry, it employs a self-supervised codec to construct an implicit chemical space and acquire the continues representation of molecules. To explore the established chemical space, MOMO uses multi-objective evolution to comprehensively and efficiently search for similar molecules with multiple desirable properties. We demonstrate the high performance of MOMO on four multi-objective property and similarity optimization tasks, and illustrate the search capability of MOMO through case studies. Remarkably, our approach significantly outperforms previous approaches in optimizing three objectives simultaneously. The results show the optimization capability of MOMO, suggesting to improve the success rate of lead molecule optimization.