3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models

Detalhes bibliográficos
Autor(a) principal: Silverio, Priscilla S. S. N.
Data de Publicação: 2023
Outros Autores: Viana, Jéssika de Oliveira, Guimarães, Euzébio B.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Brazilian Journal of Pharmaceutical Sciences
Texto Completo: https://www.revistas.usp.br/bjps/article/view/212200
Resumo: Quantitative Structure-Activity Relationship (QSAR) is a computer-aided technology in the field of medicinal chemistry that seeks to clarify the relationships between molecular structures and their biological activities. Such technologies allow for the acceleration of the development of new compounds by reducing the costs of drug design. This work presents 3D-QSARpy, a flexible, user-friendly and robust tool, freely available without registration, to support the generation of QSAR 3D models in an automated way. The user only needs to provide aligned molecular structures and the respective dependent variable. The current version was developed using Python with packages such as scikit-learn and includes various techniques of machine learning for regression. The diverse techniques employed by the tool is a differential compared to known methodologies, such as CoMFA and CoMSIA, because it expands the search space of possible solutions, and in this way increases the chances of obtaining relevant models. Additionally, approaches for select variables (dimension reduction) were implemented in the tool. To evaluate its potentials, experiments were carried out to compare results obtained from the proposed 3D-QSARpy tool with the results from already published works. The results demonstrated that 3D-QSARpy is extremely useful in the field due to its expressive results.
id USP-31_8755218b453d390cb7df4103019f9557
oai_identifier_str oai:revistas.usp.br:article/212200
network_acronym_str USP-31
network_name_str Brazilian Journal of Pharmaceutical Sciences
repository_id_str
spelling 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR modelsDrug Design3D-QSAR; Machine learningVariable selectionQuantitative Structure-Activity Relationship (QSAR) is a computer-aided technology in the field of medicinal chemistry that seeks to clarify the relationships between molecular structures and their biological activities. Such technologies allow for the acceleration of the development of new compounds by reducing the costs of drug design. This work presents 3D-QSARpy, a flexible, user-friendly and robust tool, freely available without registration, to support the generation of QSAR 3D models in an automated way. The user only needs to provide aligned molecular structures and the respective dependent variable. The current version was developed using Python with packages such as scikit-learn and includes various techniques of machine learning for regression. The diverse techniques employed by the tool is a differential compared to known methodologies, such as CoMFA and CoMSIA, because it expands the search space of possible solutions, and in this way increases the chances of obtaining relevant models. Additionally, approaches for select variables (dimension reduction) were implemented in the tool. To evaluate its potentials, experiments were carried out to compare results obtained from the proposed 3D-QSARpy tool with the results from already published works. The results demonstrated that 3D-QSARpy is extremely useful in the field due to its expressive results.Universidade de São Paulo. Faculdade de Ciências Farmacêuticas2023-05-19info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://www.revistas.usp.br/bjps/article/view/21220010.1590/s2175-97902023e22373Brazilian Journal of Pharmaceutical Sciences; Vol. 59 (2023)Brazilian Journal of Pharmaceutical Sciences; v. 59 (2023)Brazilian Journal of Pharmaceutical Sciences; Vol. 59 (2023)2175-97901984-8250reponame:Brazilian Journal of Pharmaceutical Sciencesinstname:Universidade de São Paulo (USP)instacron:USPenghttps://www.revistas.usp.br/bjps/article/view/212200/194316Copyright (c) 2023 Brazilian Journal of Pharmaceutical Scienceshttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccess Silverio, Priscilla S. S. N.Viana, Jéssika de OliveiraGuimarães, Euzébio B.2023-05-19T17:43:50Zoai:revistas.usp.br:article/212200Revistahttps://www.revistas.usp.br/bjps/indexPUBhttps://old.scielo.br/oai/scielo-oai.phpbjps@usp.br||elizabeth.igne@gmail.com2175-97901984-8250opendoar:2023-05-19T17:43:50Brazilian Journal of Pharmaceutical Sciences - Universidade de São Paulo (USP)false
dc.title.none.fl_str_mv 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
title 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
spellingShingle 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
Silverio, Priscilla S. S. N.
Drug Design
3D-QSAR; Machine learning
Variable selection
title_short 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
title_full 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
title_fullStr 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
title_full_unstemmed 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
title_sort 3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models
author Silverio, Priscilla S. S. N.
author_facet Silverio, Priscilla S. S. N.
Viana, Jéssika de Oliveira
Guimarães, Euzébio B.
author_role author
author2 Viana, Jéssika de Oliveira
Guimarães, Euzébio B.
author2_role author
author
dc.contributor.author.fl_str_mv Silverio, Priscilla S. S. N.
Viana, Jéssika de Oliveira
Guimarães, Euzébio B.
dc.subject.por.fl_str_mv Drug Design
3D-QSAR; Machine learning
Variable selection
topic Drug Design
3D-QSAR; Machine learning
Variable selection
description Quantitative Structure-Activity Relationship (QSAR) is a computer-aided technology in the field of medicinal chemistry that seeks to clarify the relationships between molecular structures and their biological activities. Such technologies allow for the acceleration of the development of new compounds by reducing the costs of drug design. This work presents 3D-QSARpy, a flexible, user-friendly and robust tool, freely available without registration, to support the generation of QSAR 3D models in an automated way. The user only needs to provide aligned molecular structures and the respective dependent variable. The current version was developed using Python with packages such as scikit-learn and includes various techniques of machine learning for regression. The diverse techniques employed by the tool is a differential compared to known methodologies, such as CoMFA and CoMSIA, because it expands the search space of possible solutions, and in this way increases the chances of obtaining relevant models. Additionally, approaches for select variables (dimension reduction) were implemented in the tool. To evaluate its potentials, experiments were carried out to compare results obtained from the proposed 3D-QSARpy tool with the results from already published works. The results demonstrated that 3D-QSARpy is extremely useful in the field due to its expressive results.
publishDate 2023
dc.date.none.fl_str_mv 2023-05-19
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://www.revistas.usp.br/bjps/article/view/212200
10.1590/s2175-97902023e22373
url https://www.revistas.usp.br/bjps/article/view/212200
identifier_str_mv 10.1590/s2175-97902023e22373
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://www.revistas.usp.br/bjps/article/view/212200/194316
dc.rights.driver.fl_str_mv Copyright (c) 2023 Brazilian Journal of Pharmaceutical Sciences
https://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2023 Brazilian Journal of Pharmaceutical Sciences
https://creativecommons.org/licenses/by/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade de São Paulo. Faculdade de Ciências Farmacêuticas
publisher.none.fl_str_mv Universidade de São Paulo. Faculdade de Ciências Farmacêuticas
dc.source.none.fl_str_mv Brazilian Journal of Pharmaceutical Sciences; Vol. 59 (2023)
Brazilian Journal of Pharmaceutical Sciences; v. 59 (2023)
Brazilian Journal of Pharmaceutical Sciences; Vol. 59 (2023)
2175-9790
1984-8250
reponame:Brazilian Journal of Pharmaceutical Sciences
instname:Universidade de São Paulo (USP)
instacron:USP
instname_str Universidade de São Paulo (USP)
instacron_str USP
institution USP
reponame_str Brazilian Journal of Pharmaceutical Sciences
collection Brazilian Journal of Pharmaceutical Sciences
repository.name.fl_str_mv Brazilian Journal of Pharmaceutical Sciences - Universidade de São Paulo (USP)
repository.mail.fl_str_mv bjps@usp.br||elizabeth.igne@gmail.com
_version_ 1800222918104317952