Cargando…

MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics

The selection of the most relevant molecular descriptors to describe a target variable in the context of QSAR (Quantitative Structure-Activity Relationship) modelling is a challenging combinatorial optimization problem. In this paper, a novel software tool for addressing this task in the context of...

Descripción completa

Detalles Bibliográficos
Autores principales: Martínez, María Jimena, Razuc, Marina, Ponzoni, Ignacio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6398071/
https://www.ncbi.nlm.nih.gov/pubmed/30906770
http://dx.doi.org/10.1155/2019/2905203
_version_ 1783399521848393728
author Martínez, María Jimena
Razuc, Marina
Ponzoni, Ignacio
author_facet Martínez, María Jimena
Razuc, Marina
Ponzoni, Ignacio
author_sort Martínez, María Jimena
collection PubMed
description The selection of the most relevant molecular descriptors to describe a target variable in the context of QSAR (Quantitative Structure-Activity Relationship) modelling is a challenging combinatorial optimization problem. In this paper, a novel software tool for addressing this task in the context of regression and classification modelling is presented. The methodology that implements the tool is organized into two phases. The first phase uses a multiobjective evolutionary technique to perform the selection of subsets of descriptors. The second phase performs an external validation of the chosen descriptors subsets in order to improve reliability. The tool functionalities have been illustrated through a case study for the estimation of the ready biodegradation property as an example of classification QSAR modelling. The results obtained show the usefulness and potential of this novel software tool that aims to reduce the time and costs of development in the drug discovery process.
format Online
Article
Text
id pubmed-6398071
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-63980712019-03-24 MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics Martínez, María Jimena Razuc, Marina Ponzoni, Ignacio Biomed Res Int Research Article The selection of the most relevant molecular descriptors to describe a target variable in the context of QSAR (Quantitative Structure-Activity Relationship) modelling is a challenging combinatorial optimization problem. In this paper, a novel software tool for addressing this task in the context of regression and classification modelling is presented. The methodology that implements the tool is organized into two phases. The first phase uses a multiobjective evolutionary technique to perform the selection of subsets of descriptors. The second phase performs an external validation of the chosen descriptors subsets in order to improve reliability. The tool functionalities have been illustrated through a case study for the estimation of the ready biodegradation property as an example of classification QSAR modelling. The results obtained show the usefulness and potential of this novel software tool that aims to reduce the time and costs of development in the drug discovery process. Hindawi 2019-02-17 /pmc/articles/PMC6398071/ /pubmed/30906770 http://dx.doi.org/10.1155/2019/2905203 Text en Copyright © 2019 María Jimena Martínez et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Martínez, María Jimena
Razuc, Marina
Ponzoni, Ignacio
MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics
title MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics
title_full MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics
title_fullStr MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics
title_full_unstemmed MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics
title_short MoDeSuS: A Machine Learning Tool for Selection of Molecular Descriptors in QSAR Studies Applied to Molecular Informatics
title_sort modesus: a machine learning tool for selection of molecular descriptors in qsar studies applied to molecular informatics
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6398071/
https://www.ncbi.nlm.nih.gov/pubmed/30906770
http://dx.doi.org/10.1155/2019/2905203
work_keys_str_mv AT martinezmariajimena modesusamachinelearningtoolforselectionofmoleculardescriptorsinqsarstudiesappliedtomolecularinformatics
AT razucmarina modesusamachinelearningtoolforselectionofmoleculardescriptorsinqsarstudiesappliedtomolecularinformatics
AT ponzoniignacio modesusamachinelearningtoolforselectionofmoleculardescriptorsinqsarstudiesappliedtomolecularinformatics