Guiding Deep Molecular Optimization with Genetic Exploration
This work addresses the challenge of efficiently searching chemical space for drug-like molecules, representing a strong specific gain in molecular optimization.
The paper tackles the problem of de novo molecular design by proposing a genetic expert-guided learning (GEGL) framework to train deep neural networks for generating molecules with desired properties, achieving a score of 31.40 on penalized octanol-water partition coefficient optimization and the highest score for 19 out of 20 tasks on the GuacaMol benchmark.
De novo molecular design attempts to search over the chemical space for molecules with the desired property. Recently, deep learning has gained considerable attention as a promising approach to solve the problem. In this paper, we propose genetic expert-guided learning (GEGL), a simple yet novel framework for training a deep neural network (DNN) to generate highly-rewarding molecules. Our main idea is to design a "genetic expert improvement" procedure, which generates high-quality targets for imitation learning of the DNN. Extensive experiments show that GEGL significantly improves over state-of-the-art methods. For example, GEGL manages to solve the penalized octanol-water partition coefficient optimization with a score of 31.40, while the best-known score in the literature is 27.22. Besides, for the GuacaMol benchmark with 20 tasks, our method achieves the highest score for 19 tasks, in comparison with state-of-the-art methods, and newly obtains the perfect score for three tasks.