Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery

Abstract Quantitative structure–activity relationship modeling using machine learning techniques constitutes a complex computational problem, where the identification of the most informative molecular descriptors for predicting a specific target property plays a critical role. Two main general appro...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ignacio Ponzoni, Víctor Sebastián-Pérez, Carlos Requena-Triguero, Carlos Roca, María J. Martínez, Fiorella Cravero, Mónica F. Díaz, Juan A. Páez, Ramón Gómez Arrayás, Javier Adrio, Nuria E. Campillo
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d95973b8023d4de68ded65e398e04d19
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d95973b8023d4de68ded65e398e04d19
record_format	dspace
spelling	oai:doaj.org-article:d95973b8023d4de68ded65e398e04d192021-12-02T15:05:05ZHybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery10.1038/s41598-017-02114-32045-2322https://doaj.org/article/d95973b8023d4de68ded65e398e04d192017-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-02114-3https://doaj.org/toc/2045-2322Abstract Quantitative structure–activity relationship modeling using machine learning techniques constitutes a complex computational problem, where the identification of the most informative molecular descriptors for predicting a specific target property plays a critical role. Two main general approaches can be used for this modeling procedure: feature selection and feature learning. In this paper, a performance comparative study of two state-of-art methods related to these two approaches is carried out. In particular, regression and classification models for three different issues are inferred using both methods under different experimental scenarios: two drug-like properties, such as blood-brain-barrier and human intestinal absorption, and enantiomeric excess, as a measurement of purity used for chiral substances. Beyond the contrastive analysis of feature selection and feature learning methods as competitive approaches, the hybridization of these strategies is also evaluated based on previous results obtained in material sciences. From the experimental results, it can be concluded that there is not a clear winner between both approaches because the performance depends on the characteristics of the compound databases used for modeling. Nevertheless, in several cases, it was observed that the accuracy of the models can be improved by combining both approaches when the molecular descriptor sets provided by feature selection and feature learning contain complementary information.Ignacio PonzoniVíctor Sebastián-PérezCarlos Requena-TrigueroCarlos RocaMaría J. MartínezFiorella CraveroMónica F. DíazJuan A. PáezRamón Gómez ArrayásJavier AdrioNuria E. CampilloNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-19 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ignacio Ponzoni Víctor Sebastián-Pérez Carlos Requena-Triguero Carlos Roca María J. Martínez Fiorella Cravero Mónica F. Díaz Juan A. Páez Ramón Gómez Arrayás Javier Adrio Nuria E. Campillo Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery
description	Abstract Quantitative structure–activity relationship modeling using machine learning techniques constitutes a complex computational problem, where the identification of the most informative molecular descriptors for predicting a specific target property plays a critical role. Two main general approaches can be used for this modeling procedure: feature selection and feature learning. In this paper, a performance comparative study of two state-of-art methods related to these two approaches is carried out. In particular, regression and classification models for three different issues are inferred using both methods under different experimental scenarios: two drug-like properties, such as blood-brain-barrier and human intestinal absorption, and enantiomeric excess, as a measurement of purity used for chiral substances. Beyond the contrastive analysis of feature selection and feature learning methods as competitive approaches, the hybridization of these strategies is also evaluated based on previous results obtained in material sciences. From the experimental results, it can be concluded that there is not a clear winner between both approaches because the performance depends on the characteristics of the compound databases used for modeling. Nevertheless, in several cases, it was observed that the accuracy of the models can be improved by combining both approaches when the molecular descriptor sets provided by feature selection and feature learning contain complementary information.
format	article
author	Ignacio Ponzoni Víctor Sebastián-Pérez Carlos Requena-Triguero Carlos Roca María J. Martínez Fiorella Cravero Mónica F. Díaz Juan A. Páez Ramón Gómez Arrayás Javier Adrio Nuria E. Campillo
author_facet	Ignacio Ponzoni Víctor Sebastián-Pérez Carlos Requena-Triguero Carlos Roca María J. Martínez Fiorella Cravero Mónica F. Díaz Juan A. Páez Ramón Gómez Arrayás Javier Adrio Nuria E. Campillo
author_sort	Ignacio Ponzoni
title	Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery
title_short	Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery
title_full	Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery
title_fullStr	Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery
title_full_unstemmed	Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery
title_sort	hybridizing feature selection and feature learning approaches in qsar modeling for drug discovery
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/d95973b8023d4de68ded65e398e04d19
work_keys_str_mv	AT ignacioponzoni hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT victorsebastianperez hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT carlosrequenatriguero hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT carlosroca hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT mariajmartinez hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT fiorellacravero hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT monicafdiaz hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT juanapaez hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT ramongomezarrayas hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT javieradrio hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery AT nuriaecampillo hybridizingfeatureselectionandfeaturelearningapproachesinqsarmodelingfordrugdiscovery
_version_	1718388986656849920

Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery

Ejemplares similares