Automatic optimization methods for compounds in the vast compound space are important for drug discovery and material design. Several machine learning-based molecular generative models for drug discovery have been proposed, but most of these methods generate compounds from scratch and are not suitable for exploring and optimizing around arbitrary compounds. In this study, we developed a compound optimization method based on molecular graphs using deep reinforcement learning. This method searches for compounds on a fragment-by-fragment basis and at high density by generating fragments to be added atom by atom. Experimental results confirmed that the QED, the optimization target set in this study, was enhanced by searching around the starting compound. This means that the generated compounds are structurally similar to the starting compounds, indicating that the method is suitable for starting generation from a given compound. The source code is available at https://github.com/sekijima-lab/GARGOYLES.
Gargoyles: An Open Source Graph-based molecular optimization method based on Deep Reinforcement Learning
02 February 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.