De Novo Drug Design Using Reinforcement Learning with Graph- Based Deep Generative Models
Journal article, 2022

Machine learning provides effective computational tools for exploring the chemical space via deep generative models. Here, we propose a new reinforcement learning scheme to finetune graph-based deep generative models for de novo molecular design tasks. We show how our computational framework can successfully guide a pretrained generative model toward the generation of molecules with a specific property profile, even when such molecules are not present in the training set and unlikely to be generated by the pretrained model. We explored the following tasks: generating molecules of decreasing/increasing size, increasing drug-likeness, and increasing bioactivity. Using the proposed approach, we achieve a model which generates diverse compounds with predicted DRD2 activity for 95% of sampled molecules, outperforming previously reported methods on this metric.

Author

Sara Romeo Atance

AstraZeneca AB

Student at Chalmers

Juan Viguera Diez

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

Ola Engkvist

Chalmers, Computer Science and Engineering (Chalmers)

Simon Olsson

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

Rocio Mercado

AstraZeneca R&D

Journal of Chemical Information and Modeling

1549-9596 (ISSN) 1549960x (eISSN)

Vol. 62 20 4863-4872

Subject Categories

Bioinformatics (Computational Biology)

Computer Science

Computer Systems

DOI

10.1021/acs.jcim.2c00838

PubMed

36219571

More information

Latest update

3/7/2024 9