Cargando…

Graph-Based Feature Selection Approach for Molecular Activity Prediction

[Image: see text] In the construction of QSAR models for the prediction of molecular activity, feature selection is a common task aimed at improving the results and understanding of the problem. The selection of features allows elimination of irrelevant and redundant features, reduces the effect of...

Descripción completa

Detalles Bibliográficos
Autores principales: Cerruela-García, Gonzalo, Cuevas-Muñoz, José Manuel, García-Pedrajas, Nicolás
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9006223/
https://www.ncbi.nlm.nih.gov/pubmed/35315648
http://dx.doi.org/10.1021/acs.jcim.1c01578
_version_ 1784686621529997312
author Cerruela-García, Gonzalo
Cuevas-Muñoz, José Manuel
García-Pedrajas, Nicolás
author_facet Cerruela-García, Gonzalo
Cuevas-Muñoz, José Manuel
García-Pedrajas, Nicolás
author_sort Cerruela-García, Gonzalo
collection PubMed
description [Image: see text] In the construction of QSAR models for the prediction of molecular activity, feature selection is a common task aimed at improving the results and understanding of the problem. The selection of features allows elimination of irrelevant and redundant features, reduces the effect of dimensionality problems, and improves the generalization and interpretability of the models. In many feature selection applications, such as those based on ensembles of feature selectors, it is necessary to combine different selection processes. In this work, we evaluate the application of a new feature selection approach to the prediction of molecular activity, based on the construction of an undirected graph to combine base feature selectors. The experimental results demonstrate the efficiency of the graph-based method in terms of the classification performance, reduction, and redundancy compared to the standard voting method. The graph-based method can be extended to different feature selection algorithms and applied to other cheminformatics problems.
format Online
Article
Text
id pubmed-9006223
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-90062232022-04-13 Graph-Based Feature Selection Approach for Molecular Activity Prediction Cerruela-García, Gonzalo Cuevas-Muñoz, José Manuel García-Pedrajas, Nicolás J Chem Inf Model [Image: see text] In the construction of QSAR models for the prediction of molecular activity, feature selection is a common task aimed at improving the results and understanding of the problem. The selection of features allows elimination of irrelevant and redundant features, reduces the effect of dimensionality problems, and improves the generalization and interpretability of the models. In many feature selection applications, such as those based on ensembles of feature selectors, it is necessary to combine different selection processes. In this work, we evaluate the application of a new feature selection approach to the prediction of molecular activity, based on the construction of an undirected graph to combine base feature selectors. The experimental results demonstrate the efficiency of the graph-based method in terms of the classification performance, reduction, and redundancy compared to the standard voting method. The graph-based method can be extended to different feature selection algorithms and applied to other cheminformatics problems. American Chemical Society 2022-03-22 2022-04-11 /pmc/articles/PMC9006223/ /pubmed/35315648 http://dx.doi.org/10.1021/acs.jcim.1c01578 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Cerruela-García, Gonzalo
Cuevas-Muñoz, José Manuel
García-Pedrajas, Nicolás
Graph-Based Feature Selection Approach for Molecular Activity Prediction
title Graph-Based Feature Selection Approach for Molecular Activity Prediction
title_full Graph-Based Feature Selection Approach for Molecular Activity Prediction
title_fullStr Graph-Based Feature Selection Approach for Molecular Activity Prediction
title_full_unstemmed Graph-Based Feature Selection Approach for Molecular Activity Prediction
title_short Graph-Based Feature Selection Approach for Molecular Activity Prediction
title_sort graph-based feature selection approach for molecular activity prediction
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9006223/
https://www.ncbi.nlm.nih.gov/pubmed/35315648
http://dx.doi.org/10.1021/acs.jcim.1c01578
work_keys_str_mv AT cerruelagarciagonzalo graphbasedfeatureselectionapproachformolecularactivityprediction
AT cuevasmunozjosemanuel graphbasedfeatureselectionapproachformolecularactivityprediction
AT garciapedrajasnicolas graphbasedfeatureselectionapproachformolecularactivityprediction