Timezone: »

Guiding Deep Molecular Optimization with Genetic Exploration
Sungsoo Ahn · Junsu Kim · Hankook Lee · Jinwoo Shin

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #724

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. Our training code is available at https://github.com/sungsoo-ahn/genetic-expert-guided-learning.

Author Information

Sungsoo Ahn (KAIST)
Junsu Kim (KAIST)
Hankook Lee (Korea Advanced Institute of Science and Technology)
Jinwoo Shin (KAIST)

More from the Same Authors