DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach

Khemchandani, Yash ORCID: 0000-0001-5645-3509, O'Hagan, Steve ORCID: 0000-0001-6235-5462, Samanta, Soumitra ORCID: 0000-0003-2200-3061, Swainston, Neil ORCID: 0000-0001-7020-1236, Roberts, Timothy ORCID: 0000-0002-1464-0151, Bollegala, Danushka ORCID: 0000-0003-4476-7003 and Kell, Douglas ORCID: 0000-0001-5838-7963 (2020) DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach ISSN 2693-5015

Text v2_stamped (1).pdf - Published version Download (1MB) | Preview

Abstract

<title>Abstract</title> <p>We address the problem of generating novel molecules with desired interaction properties as a multi-objective optimization problem. Interaction binding models are learned from binding data using graph convolution networks (GCNs). Since the experimentally obtained property scores are recognised as having potentially gross errors, we adopted a robust loss for the model. Combinations of these terms, including drug likeness and synthetic accessibility, are then optimized using reinforcement learning based on a graph convolution policy approach. Some of the molecules generated, while legitimate chemically, can have excellent drug-likeness scores but appear unusual. We provide an example based on the binding potency of small molecules to dopamine transporters. We extend our method successfully to use a multi-objective reward function, in this case for generating novel molecules that bind with dopamine transporters but not with those for norepinephrine. Our method should be generally applicable to the generation <italic>in silico</italic> of molecules with desirable properties.</p>

Item Type:	Article
Uncontrolled Keywords:	46 Information and Computing Sciences, 4602 Artificial Intelligence, 1.1 Normal biological development and functioning, Generic health relevance
Depositing User:	Symplectic Admin
Date Deposited:	18 Sep 2020 10:05
Last Modified:	26 May 2025 23:03
DOI:	10.21203/rs.3.rs-32446/v2
Related Websites:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3101668
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.