Molecule Optimization by Explainable Evolution

Optimizing molecules for desired properties is a fundamental yet challenging task in chemistry, material science and drug discovery. In this paper, we develop a novel algorithm for optimizing molecule properties via an Expectation Maximization (EM)-like explainable evolutionary process. Our algorithm is designed to mimic human experts in the process of searching for desirable molecules and alternate between two stages: the first stage on explainable local search which identifies rationales, , critical subgraph patterns accounting for desired molecular properties, and the second stage on molecule completion which explores the larger space of molecules containing good rationales. We test our method against various baselines on a real-world multi-property optimization task where each method is given the same number of queries to the property oracle. We show that our evolution-by-explanation algorithm is 79% better than the best baseline in terms of a generic metric combining aspects such as success rate, novelty and diversity. Human expert evaluation on optimized molecules shows that 60% of top molecules obtained from our methods are deemed as successful ones.