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

Abstract

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 in silico of molecules with desirable properties.

Deep learning and generative methods in cheminformatics and chemical biology: navigating small molecule space intelligently

“…Yasonik [97] combined de novo molecular generation in silico (using RNNs) with a multi-objective evolutionary algorithm in an iterative method for selecting suitable molecules subjective to constraints on their physicochemical properties. Finally, here, our own laboratory has developed methods [151] based on molecular graphs and reinforcement learning for generating molecules predicted (from existing binding assays) to have a specific set of differential activities; the methods are entirely general.…”