An ensemble method for predicting subnuclear localizations from primary protein structures.

<h4>Background</h4>Predicting protein subnuclear localization is a challenging problem. Some previous works based on non-sequence information including Gene Ontology annotations and kernel fusion have respective limitations. The aim of this work is twofold: one is to propose a novel indi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo Sheng Han, Zu Guo Yu, Vo Anh, Anaththa P D Krishnajith, Yu-Chu Tian
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2013
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/3c6730d3dbd840c8b04b6d6f85b8859e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3c6730d3dbd840c8b04b6d6f85b8859e
record_format	dspace
spelling	oai:doaj.org-article:3c6730d3dbd840c8b04b6d6f85b8859e2021-11-18T07:55:50ZAn ensemble method for predicting subnuclear localizations from primary protein structures.1932-620310.1371/journal.pone.0057225https://doaj.org/article/3c6730d3dbd840c8b04b6d6f85b8859e2013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/23460833/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Background</h4>Predicting protein subnuclear localization is a challenging problem. Some previous works based on non-sequence information including Gene Ontology annotations and kernel fusion have respective limitations. The aim of this work is twofold: one is to propose a novel individual feature extraction method; another is to develop an ensemble method to improve prediction performance using comprehensive information represented in the form of high dimensional feature vector obtained by 11 feature extraction methods.<h4>Methodology/principal findings</h4>A novel two-stage multiclass support vector machine is proposed to predict protein subnuclear localizations. It only considers those feature extraction methods based on amino acid classifications and physicochemical properties. In order to speed up our system, an automatic search method for the kernel parameter is used. The prediction performance of our method is evaluated on four datasets: Lei dataset, multi-localization dataset, SNL9 dataset and a new independent dataset. The overall accuracy of prediction for 6 localizations on Lei dataset is 75.2% and that for 9 localizations on SNL9 dataset is 72.1% in the leave-one-out cross validation, 71.7% for the multi-localization dataset and 69.8% for the new independent dataset, respectively. Comparisons with those existing methods show that our method performs better for both single-localization and multi-localization proteins and achieves more balanced sensitivities and specificities on large-size and small-size subcellular localizations. The overall accuracy improvements are 4.0% and 4.7% for single-localization proteins and 6.5% for multi-localization proteins. The reliability and stability of our classification model are further confirmed by permutation analysis.<h4>Conclusions</h4>It can be concluded that our method is effective and valuable for predicting protein subnuclear localizations. A web server has been designed to implement the proposed method. It is freely available at http://bioinformatics.awowshop.com/snlpred_page.php.Guo Sheng HanZu Guo YuVo AnhAnaththa P D KrishnajithYu-Chu TianPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 2, p e57225 (2013)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Guo Sheng Han Zu Guo Yu Vo Anh Anaththa P D Krishnajith Yu-Chu Tian An ensemble method for predicting subnuclear localizations from primary protein structures.
description	<h4>Background</h4>Predicting protein subnuclear localization is a challenging problem. Some previous works based on non-sequence information including Gene Ontology annotations and kernel fusion have respective limitations. The aim of this work is twofold: one is to propose a novel individual feature extraction method; another is to develop an ensemble method to improve prediction performance using comprehensive information represented in the form of high dimensional feature vector obtained by 11 feature extraction methods.<h4>Methodology/principal findings</h4>A novel two-stage multiclass support vector machine is proposed to predict protein subnuclear localizations. It only considers those feature extraction methods based on amino acid classifications and physicochemical properties. In order to speed up our system, an automatic search method for the kernel parameter is used. The prediction performance of our method is evaluated on four datasets: Lei dataset, multi-localization dataset, SNL9 dataset and a new independent dataset. The overall accuracy of prediction for 6 localizations on Lei dataset is 75.2% and that for 9 localizations on SNL9 dataset is 72.1% in the leave-one-out cross validation, 71.7% for the multi-localization dataset and 69.8% for the new independent dataset, respectively. Comparisons with those existing methods show that our method performs better for both single-localization and multi-localization proteins and achieves more balanced sensitivities and specificities on large-size and small-size subcellular localizations. The overall accuracy improvements are 4.0% and 4.7% for single-localization proteins and 6.5% for multi-localization proteins. The reliability and stability of our classification model are further confirmed by permutation analysis.<h4>Conclusions</h4>It can be concluded that our method is effective and valuable for predicting protein subnuclear localizations. A web server has been designed to implement the proposed method. It is freely available at http://bioinformatics.awowshop.com/snlpred_page.php.
format	article
author	Guo Sheng Han Zu Guo Yu Vo Anh Anaththa P D Krishnajith Yu-Chu Tian
author_facet	Guo Sheng Han Zu Guo Yu Vo Anh Anaththa P D Krishnajith Yu-Chu Tian
author_sort	Guo Sheng Han
title	An ensemble method for predicting subnuclear localizations from primary protein structures.
title_short	An ensemble method for predicting subnuclear localizations from primary protein structures.
title_full	An ensemble method for predicting subnuclear localizations from primary protein structures.
title_fullStr	An ensemble method for predicting subnuclear localizations from primary protein structures.
title_full_unstemmed	An ensemble method for predicting subnuclear localizations from primary protein structures.
title_sort	ensemble method for predicting subnuclear localizations from primary protein structures.
publisher	Public Library of Science (PLoS)
publishDate	2013
url	https://doaj.org/article/3c6730d3dbd840c8b04b6d6f85b8859e
work_keys_str_mv	AT guoshenghan anensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT zuguoyu anensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT voanh anensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT anaththapdkrishnajith anensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT yuchutian anensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT guoshenghan ensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT zuguoyu ensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT voanh ensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT anaththapdkrishnajith ensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures AT yuchutian ensemblemethodforpredictingsubnuclearlocalizationsfromprimaryproteinstructures
_version_	1718422722414903296

An ensemble method for predicting subnuclear localizations from primary protein structures.

Ejemplares similares