De novo drug design using reinforcement learning with graph-based deep generative models

Abstract

Machine learning methods have proven to be effective tools for molecular design, allowing for efficient exploration of the vast chemical space via deep molecular generative models. Here, we propose a graph-based deep generative model for de novo molecular design using reinforcement learning. We demonstrate how the reinforcement learning framework can successfully fine-tune the generative model towards molecules with various desired sets of properties, even when few molecules have the goal attributes initially. We explored the following tasks: decreasing/increasing the size of generated molecules, increasing their drug-likeness, and increasing protein-binding activity. Using our model, we are able to generate 95% predicted active compounds for a common benchmarking task, outperforming previously reported methods on this metric.

Graph neural networks for materials science and chemistry

“…In this setting, the agent explores the chemical space and generates new molecular graphs by modifying the starting molecules according to the reward function, representing the molecular property to optimize. Atance et al recently introduced a similar RL approach based on Gated GNNs 155 , outperforming other GNN-based approaches in molecular graph generation tasks 156 . Another sequential approach based on conditional graph generative models has been used by Li et al on drug design tasks 157 .…”