HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.

Protein subcellular localization prediction, as an essential step to elucidate the functions in vivo of proteins and identify drugs targets, has been extensively studied in previous decades. Instead of only determining subcellular localization of single-label proteins, recent studies have focused on...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shibiao Wan, Man-Wai Mak, Sun-Yuan Kung
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2014
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/13a150305c114475bdd5ce32166cb083
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:13a150305c114475bdd5ce32166cb083
record_format	dspace
spelling	oai:doaj.org-article:13a150305c114475bdd5ce32166cb0832021-11-18T08:27:19ZHybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.1932-620310.1371/journal.pone.0089545https://doaj.org/article/13a150305c114475bdd5ce32166cb0832014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24647341/pdf/?tool=EBIhttps://doaj.org/toc/1932-6203Protein subcellular localization prediction, as an essential step to elucidate the functions in vivo of proteins and identify drugs targets, has been extensively studied in previous decades. Instead of only determining subcellular localization of single-label proteins, recent studies have focused on predicting both single- and multi-location proteins. Computational methods based on Gene Ontology (GO) have been demonstrated to be superior to methods based on other features. However, existing GO-based methods focus on the occurrences of GO terms and disregard their relationships. This paper proposes a multi-label subcellular-localization predictor, namely HybridGO-Loc, that leverages not only the GO term occurrences but also the inter-term relationships. This is achieved by hybridizing the GO frequencies of occurrences and the semantic similarity between GO terms. Given a protein, a set of GO terms are retrieved by searching against the gene ontology database, using the accession numbers of homologous proteins obtained via BLAST search as the keys. The frequency of GO occurrences and semantic similarity (SS) between GO terms are used to formulate frequency vectors and semantic similarity vectors, respectively, which are subsequently hybridized to construct fusion vectors. An adaptive-decision based multi-label support vector machine (SVM) classifier is proposed to classify the fusion vectors. Experimental results based on recent benchmark datasets and a new dataset containing novel proteins show that the proposed hybrid-feature predictor significantly outperforms predictors based on individual GO features as well as other state-of-the-art predictors. For readers' convenience, the HybridGO-Loc server, which is for predicting virus or plant proteins, is available online at http://bioinfo.eie.polyu.edu.hk/HybridGoServer/.Shibiao WanMan-Wai MakSun-Yuan KungPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 3, p e89545 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Shibiao Wan Man-Wai Mak Sun-Yuan Kung HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
description	Protein subcellular localization prediction, as an essential step to elucidate the functions in vivo of proteins and identify drugs targets, has been extensively studied in previous decades. Instead of only determining subcellular localization of single-label proteins, recent studies have focused on predicting both single- and multi-location proteins. Computational methods based on Gene Ontology (GO) have been demonstrated to be superior to methods based on other features. However, existing GO-based methods focus on the occurrences of GO terms and disregard their relationships. This paper proposes a multi-label subcellular-localization predictor, namely HybridGO-Loc, that leverages not only the GO term occurrences but also the inter-term relationships. This is achieved by hybridizing the GO frequencies of occurrences and the semantic similarity between GO terms. Given a protein, a set of GO terms are retrieved by searching against the gene ontology database, using the accession numbers of homologous proteins obtained via BLAST search as the keys. The frequency of GO occurrences and semantic similarity (SS) between GO terms are used to formulate frequency vectors and semantic similarity vectors, respectively, which are subsequently hybridized to construct fusion vectors. An adaptive-decision based multi-label support vector machine (SVM) classifier is proposed to classify the fusion vectors. Experimental results based on recent benchmark datasets and a new dataset containing novel proteins show that the proposed hybrid-feature predictor significantly outperforms predictors based on individual GO features as well as other state-of-the-art predictors. For readers' convenience, the HybridGO-Loc server, which is for predicting virus or plant proteins, is available online at http://bioinfo.eie.polyu.edu.hk/HybridGoServer/.
format	article
author	Shibiao Wan Man-Wai Mak Sun-Yuan Kung
author_facet	Shibiao Wan Man-Wai Mak Sun-Yuan Kung
author_sort	Shibiao Wan
title	HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
title_short	HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
title_full	HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
title_fullStr	HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
title_full_unstemmed	HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
title_sort	hybridgo-loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.
publisher	Public Library of Science (PLoS)
publishDate	2014
url	https://doaj.org/article/13a150305c114475bdd5ce32166cb083
work_keys_str_mv	AT shibiaowan hybridgolocmininghybridfeaturesongeneontologyforpredictingsubcellularlocalizationofmultilocationproteins AT manwaimak hybridgolocmininghybridfeaturesongeneontologyforpredictingsubcellularlocalizationofmultilocationproteins AT sunyuankung hybridgolocmininghybridfeaturesongeneontologyforpredictingsubcellularlocalizationofmultilocationproteins
_version_	1718421725061840896

HybridGO-Loc: mining hybrid features on gene ontology for predicting subcellular localization of multi-location proteins.

Ejemplares similares