MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning

Abstract The hit-to-lead process makes the physicochemical properties of the hit molecules that show the desired type of activity obtained in the screening assay more drug-like. Deep learning-based molecular generative models are expected to contribute to the hit-to-lead process. The simplified mole...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Daiki Erikawa, Nobuaki Yasuo, Masakazu Sekijima
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Molecular generation Lead Optimization Hit-to-Lead Monte Carlo Tree Search Drug Discovery Information technology T58.5-58.64 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/25b685331a2b4355b8bd8e12c68c8c7d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:25b685331a2b4355b8bd8e12c68c8c7d
record_format	dspace
spelling	oai:doaj.org-article:25b685331a2b4355b8bd8e12c68c8c7d2021-11-28T12:30:19ZMERMAID: an open source automated hit-to-lead method based on deep reinforcement learning10.1186/s13321-021-00572-61758-2946https://doaj.org/article/25b685331a2b4355b8bd8e12c68c8c7d2021-11-01T00:00:00Zhttps://doi.org/10.1186/s13321-021-00572-6https://doaj.org/toc/1758-2946Abstract The hit-to-lead process makes the physicochemical properties of the hit molecules that show the desired type of activity obtained in the screening assay more drug-like. Deep learning-based molecular generative models are expected to contribute to the hit-to-lead process. The simplified molecular input line entry system (SMILES), which is a string of alphanumeric characters representing the chemical structure of a molecule, is one of the most commonly used representations of molecules, and molecular generative models based on SMILES have achieved significant success. However, in contrast to molecular graphs, during the process of generation, SMILES are not considered as valid SMILES. Further, it is quite difficult to generate molecules starting from a certain molecule, thus making it difficult to apply SMILES to the hit-to-lead process. In this study, we have developed a SMILES-based generative model that can be generated starting from a certain molecule. This method generates partial SMILES and inserts it into the original SMILES using Monte Carlo Tree Search and a Recurrent Neural Network. We validated our method using a molecule dataset obtained from the ZINC database and successfully generated molecules that were both well optimized for the objectives of the quantitative estimate of drug-likeness (QED) and penalized octanol-water partition coefficient (PLogP) optimization. The source code is available at https://github.com/sekijima-lab/mermaid .Daiki ErikawaNobuaki YasuoMasakazu SekijimaBMCarticleMolecular generationLead OptimizationHit-to-LeadMonte Carlo Tree SearchDrug DiscoveryInformation technologyT58.5-58.64ChemistryQD1-999ENJournal of Cheminformatics, Vol 13, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Molecular generation Lead Optimization Hit-to-Lead Monte Carlo Tree Search Drug Discovery Information technology T58.5-58.64 Chemistry QD1-999
spellingShingle	Molecular generation Lead Optimization Hit-to-Lead Monte Carlo Tree Search Drug Discovery Information technology T58.5-58.64 Chemistry QD1-999 Daiki Erikawa Nobuaki Yasuo Masakazu Sekijima MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning
description	Abstract The hit-to-lead process makes the physicochemical properties of the hit molecules that show the desired type of activity obtained in the screening assay more drug-like. Deep learning-based molecular generative models are expected to contribute to the hit-to-lead process. The simplified molecular input line entry system (SMILES), which is a string of alphanumeric characters representing the chemical structure of a molecule, is one of the most commonly used representations of molecules, and molecular generative models based on SMILES have achieved significant success. However, in contrast to molecular graphs, during the process of generation, SMILES are not considered as valid SMILES. Further, it is quite difficult to generate molecules starting from a certain molecule, thus making it difficult to apply SMILES to the hit-to-lead process. In this study, we have developed a SMILES-based generative model that can be generated starting from a certain molecule. This method generates partial SMILES and inserts it into the original SMILES using Monte Carlo Tree Search and a Recurrent Neural Network. We validated our method using a molecule dataset obtained from the ZINC database and successfully generated molecules that were both well optimized for the objectives of the quantitative estimate of drug-likeness (QED) and penalized octanol-water partition coefficient (PLogP) optimization. The source code is available at https://github.com/sekijima-lab/mermaid .
format	article
author	Daiki Erikawa Nobuaki Yasuo Masakazu Sekijima
author_facet	Daiki Erikawa Nobuaki Yasuo Masakazu Sekijima
author_sort	Daiki Erikawa
title	MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning
title_short	MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning
title_full	MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning
title_fullStr	MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning
title_full_unstemmed	MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning
title_sort	mermaid: an open source automated hit-to-lead method based on deep reinforcement learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/25b685331a2b4355b8bd8e12c68c8c7d
work_keys_str_mv	AT daikierikawa mermaidanopensourceautomatedhittoleadmethodbasedondeepreinforcementlearning AT nobuakiyasuo mermaidanopensourceautomatedhittoleadmethodbasedondeepreinforcementlearning AT masakazusekijima mermaidanopensourceautomatedhittoleadmethodbasedondeepreinforcementlearning
_version_	1718407940016177152

MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning

Ejemplares similares