DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology

Abstract In polypharmacology drugs are required to bind to multiple specific targets, for example to enhance efficacy or to reduce resistance formation. Although deep learning has achieved a breakthrough in de novo design in drug discovery, most of its applications only focus on a single drug target...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xuhan Liu, Kai Ye, Herman W. T. van Vlijmen, Michael T. M. Emmerich, Adriaan P. IJzerman, Gerard J. P. van Westen
Formato: article
Lenguaje:EN
Publicado: BMC 2021
Materias:
Acceso en línea:https://doaj.org/article/0871ce20cd084c358f772f94aba024a5
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0871ce20cd084c358f772f94aba024a5
record_format dspace
spelling oai:doaj.org-article:0871ce20cd084c358f772f94aba024a52021-11-14T12:33:31ZDrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology10.1186/s13321-021-00561-91758-2946https://doaj.org/article/0871ce20cd084c358f772f94aba024a52021-11-01T00:00:00Zhttps://doi.org/10.1186/s13321-021-00561-9https://doaj.org/toc/1758-2946Abstract In polypharmacology drugs are required to bind to multiple specific targets, for example to enhance efficacy or to reduce resistance formation. Although deep learning has achieved a breakthrough in de novo design in drug discovery, most of its applications only focus on a single drug target to generate drug-like active molecules. However, in reality drug molecules often interact with more than one target which can have desired (polypharmacology) or undesired (toxicity) effects. In a previous study we proposed a new method named DrugEx that integrates an exploration strategy into RNN-based reinforcement learning to improve the diversity of the generated molecules. Here, we extended our DrugEx algorithm with multi-objective optimization to generate drug-like molecules towards multiple targets or one specific target while avoiding off-targets (the two adenosine receptors, A1AR and A2AAR, and the potassium ion channel hERG in this study). In our model, we applied an RNN as the agent and machine learning predictors as the environment. Both the agent and the environment were pre-trained in advance and then interplayed under a reinforcement learning framework. The concept of evolutionary algorithms was merged into our method such that crossover and mutation operations were implemented by the same deep learning model as the agent. During the training loop, the agent generates a batch of SMILES-based molecules. Subsequently scores for all objectives provided by the environment are used to construct Pareto ranks of the generated molecules. For this ranking a non-dominated sorting algorithm and a Tanimoto-based crowding distance algorithm using chemical fingerprints are applied. Here, we adopted GPU acceleration to speed up the process of Pareto optimization. The final reward of each molecule is calculated based on the Pareto ranking with the ranking selection algorithm. The agent is trained under the guidance of the reward to make sure it can generate desired molecules after convergence of the training process. All in all we demonstrate generation of compounds with a diverse predicted selectivity profile towards multiple targets, offering the potential of high efficacy and low toxicity.Xuhan LiuKai YeHerman W. T. van VlijmenMichael T. M. EmmerichAdriaan P. IJzermanGerard J. P. van WestenBMCarticleDeep learningAdenosine receptorsCheminformaticsReinforcement learningMulti-objective optimizationExploration strategyInformation technologyT58.5-58.64ChemistryQD1-999ENJournal of Cheminformatics, Vol 13, Iss 1, Pp 1-15 (2021)
institution DOAJ
collection DOAJ
language EN
topic Deep learning
Adenosine receptors
Cheminformatics
Reinforcement learning
Multi-objective optimization
Exploration strategy
Information technology
T58.5-58.64
Chemistry
QD1-999
spellingShingle Deep learning
Adenosine receptors
Cheminformatics
Reinforcement learning
Multi-objective optimization
Exploration strategy
Information technology
T58.5-58.64
Chemistry
QD1-999
Xuhan Liu
Kai Ye
Herman W. T. van Vlijmen
Michael T. M. Emmerich
Adriaan P. IJzerman
Gerard J. P. van Westen
DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology
description Abstract In polypharmacology drugs are required to bind to multiple specific targets, for example to enhance efficacy or to reduce resistance formation. Although deep learning has achieved a breakthrough in de novo design in drug discovery, most of its applications only focus on a single drug target to generate drug-like active molecules. However, in reality drug molecules often interact with more than one target which can have desired (polypharmacology) or undesired (toxicity) effects. In a previous study we proposed a new method named DrugEx that integrates an exploration strategy into RNN-based reinforcement learning to improve the diversity of the generated molecules. Here, we extended our DrugEx algorithm with multi-objective optimization to generate drug-like molecules towards multiple targets or one specific target while avoiding off-targets (the two adenosine receptors, A1AR and A2AAR, and the potassium ion channel hERG in this study). In our model, we applied an RNN as the agent and machine learning predictors as the environment. Both the agent and the environment were pre-trained in advance and then interplayed under a reinforcement learning framework. The concept of evolutionary algorithms was merged into our method such that crossover and mutation operations were implemented by the same deep learning model as the agent. During the training loop, the agent generates a batch of SMILES-based molecules. Subsequently scores for all objectives provided by the environment are used to construct Pareto ranks of the generated molecules. For this ranking a non-dominated sorting algorithm and a Tanimoto-based crowding distance algorithm using chemical fingerprints are applied. Here, we adopted GPU acceleration to speed up the process of Pareto optimization. The final reward of each molecule is calculated based on the Pareto ranking with the ranking selection algorithm. The agent is trained under the guidance of the reward to make sure it can generate desired molecules after convergence of the training process. All in all we demonstrate generation of compounds with a diverse predicted selectivity profile towards multiple targets, offering the potential of high efficacy and low toxicity.
format article
author Xuhan Liu
Kai Ye
Herman W. T. van Vlijmen
Michael T. M. Emmerich
Adriaan P. IJzerman
Gerard J. P. van Westen
author_facet Xuhan Liu
Kai Ye
Herman W. T. van Vlijmen
Michael T. M. Emmerich
Adriaan P. IJzerman
Gerard J. P. van Westen
author_sort Xuhan Liu
title DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology
title_short DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology
title_full DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology
title_fullStr DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology
title_full_unstemmed DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology
title_sort drugex v2: de novo design of drug molecules by pareto-based multi-objective reinforcement learning in polypharmacology
publisher BMC
publishDate 2021
url https://doaj.org/article/0871ce20cd084c358f772f94aba024a5
work_keys_str_mv AT xuhanliu drugexv2denovodesignofdrugmoleculesbyparetobasedmultiobjectivereinforcementlearninginpolypharmacology
AT kaiye drugexv2denovodesignofdrugmoleculesbyparetobasedmultiobjectivereinforcementlearninginpolypharmacology
AT hermanwtvanvlijmen drugexv2denovodesignofdrugmoleculesbyparetobasedmultiobjectivereinforcementlearninginpolypharmacology
AT michaeltmemmerich drugexv2denovodesignofdrugmoleculesbyparetobasedmultiobjectivereinforcementlearninginpolypharmacology
AT adriaanpijzerman drugexv2denovodesignofdrugmoleculesbyparetobasedmultiobjectivereinforcementlearninginpolypharmacology
AT gerardjpvanwesten drugexv2denovodesignofdrugmoleculesbyparetobasedmultiobjectivereinforcementlearninginpolypharmacology
_version_ 1718429147737358336