Abstract: Discovering meaningful molecules in the vast combinatorial chemical space has been a long-standing challenge in many fields, from materials science to drug design. Recent progress in machine learning, especially with generative models, shows great promise for automated molecule synthesis. Nevertheless, most molecule generative models remain black-boxes, whose utilities are limited by a lack of interpretability and human participation in the generation process. In this work, we propose \textbf{Chem}ical \textbf{Spac}e \textbf{E}xplorer (ChemSpacE), a simple yet effective method for exploring the chemical space with pre-trained deep generative models. Our method enables users to interact with existing generative models and steer the molecule generation process. We demonstrate the efficacy of ChemSpacE on the molecule optimization task and the latent molecule manipulation task in single-property and multi-property settings. On the molecule optimization task, the performance of ChemSpacE is on par with previous black-box optimization methods yet is considerably faster and more sample efficient. Furthermore, the interface from ChemSpacE facilitates human-in-the-loop chemical space exploration and interactive molecule design. Code and demo are available at \url{https://github.com/yuanqidu/ChemSpacE}.
Submission Length: Regular submission (no more than 12 pages of main content)
Code: https://github.com/yuanqidu/ChemSpacE
Assigned Action Editor: ~Ekin_Dogus_Cubuk1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 630
Loading