An ensemble framework for identifying essential proteins
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1186/s12859-016-1166-7 http://hdl.handle.net/11449/173406 |
Resumo: | Background: Many centrality measures have been proposed to mine and characterize the correlations between network topological properties and protein essentiality. However, most of them show limited prediction accuracy, and the number of common predicted essential proteins by different methods is very small. Results: In this paper, an ensemble framework is proposed which integrates gene expression data and protein-protein interaction networks (PINs). It aims to improve the prediction accuracy of basic centrality measures. The idea behind this ensemble framework is that different protein-protein interactions (PPIs) may show different contributions to protein essentiality. Five standard centrality measures (degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, and subgraph centrality) are integrated into the ensemble framework respectively. We evaluated the performance of the proposed ensemble framework using yeast PINs and gene expression data. The results show that it can considerably improve the prediction accuracy of the five centrality measures individually. It can also remarkably increase the number of common predicted essential proteins among those predicted by each centrality measure individually and enable each centrality measure to find more low-degree essential proteins. Conclusions: This paper demonstrates that it is valuable to differentiate the contributions of different PPIs for identifying essential proteins based on network topological characteristics. The proposed ensemble framework is a successful paradigm to this end. |
id |
UNSP_9204eafaeb231c26fe53b029ec40d96d |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/173406 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
An ensemble framework for identifying essential proteinsCentrality measureEnsemble learningEssential proteinGene expressionProtein-protein interaction networksBackground: Many centrality measures have been proposed to mine and characterize the correlations between network topological properties and protein essentiality. However, most of them show limited prediction accuracy, and the number of common predicted essential proteins by different methods is very small. Results: In this paper, an ensemble framework is proposed which integrates gene expression data and protein-protein interaction networks (PINs). It aims to improve the prediction accuracy of basic centrality measures. The idea behind this ensemble framework is that different protein-protein interactions (PPIs) may show different contributions to protein essentiality. Five standard centrality measures (degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, and subgraph centrality) are integrated into the ensemble framework respectively. We evaluated the performance of the proposed ensemble framework using yeast PINs and gene expression data. The results show that it can considerably improve the prediction accuracy of the five centrality measures individually. It can also remarkably increase the number of common predicted essential proteins among those predicted by each centrality measure individually and enable each centrality measure to find more low-degree essential proteins. Conclusions: This paper demonstrates that it is valuable to differentiate the contributions of different PPIs for identifying essential proteins based on network topological characteristics. The proposed ensemble framework is a successful paradigm to this end.National Natural Science Foundation of ChinaSystems Biology Core NHLBI NIH, 9000 Rockville PikeXiangNan University Department of Computer Science, Eastern Wangxian ParkUNESP-S�o Paulo State University Department of Physics and Biophysics Institute of Biosciences of BotucatuNorwegian University of Science and Technology (NTNU) Department of Cancer Research and Molecular Medicine, P.B. 8905UNESP-S�o Paulo State University Department of Physics and Biophysics Institute of Biosciences of BotucatuNational Natural Science Foundation of China: 51378243National Natural Science Foundation of China: 61402423National Natural Science Foundation of China: 61502343NIHXiangNan UniversityUniversidade Estadual Paulista (Unesp)Norwegian University of Science and Technology (NTNU)Zhang, XueXiao, WangxinAcencio, Marcio Luis [UNESP]Lemke, Ney [UNESP]Wang, Xujing2018-12-11T17:05:03Z2018-12-11T17:05:03Z2016-08-25info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://dx.doi.org/10.1186/s12859-016-1166-7BMC Bioinformatics, v. 17, n. 1, 2016.1471-2105http://hdl.handle.net/11449/17340610.1186/s12859-016-1166-72-s2.0-849835676632-s2.0-84983567663.pdf7977035910952141Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengBMC Bioinformatics1,479info:eu-repo/semantics/openAccess2023-11-08T06:15:25Zoai:repositorio.unesp.br:11449/173406Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:11:27.469380Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
An ensemble framework for identifying essential proteins |
title |
An ensemble framework for identifying essential proteins |
spellingShingle |
An ensemble framework for identifying essential proteins Zhang, Xue Centrality measure Ensemble learning Essential protein Gene expression Protein-protein interaction networks |
title_short |
An ensemble framework for identifying essential proteins |
title_full |
An ensemble framework for identifying essential proteins |
title_fullStr |
An ensemble framework for identifying essential proteins |
title_full_unstemmed |
An ensemble framework for identifying essential proteins |
title_sort |
An ensemble framework for identifying essential proteins |
author |
Zhang, Xue |
author_facet |
Zhang, Xue Xiao, Wangxin Acencio, Marcio Luis [UNESP] Lemke, Ney [UNESP] Wang, Xujing |
author_role |
author |
author2 |
Xiao, Wangxin Acencio, Marcio Luis [UNESP] Lemke, Ney [UNESP] Wang, Xujing |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
NIH XiangNan University Universidade Estadual Paulista (Unesp) Norwegian University of Science and Technology (NTNU) |
dc.contributor.author.fl_str_mv |
Zhang, Xue Xiao, Wangxin Acencio, Marcio Luis [UNESP] Lemke, Ney [UNESP] Wang, Xujing |
dc.subject.por.fl_str_mv |
Centrality measure Ensemble learning Essential protein Gene expression Protein-protein interaction networks |
topic |
Centrality measure Ensemble learning Essential protein Gene expression Protein-protein interaction networks |
description |
Background: Many centrality measures have been proposed to mine and characterize the correlations between network topological properties and protein essentiality. However, most of them show limited prediction accuracy, and the number of common predicted essential proteins by different methods is very small. Results: In this paper, an ensemble framework is proposed which integrates gene expression data and protein-protein interaction networks (PINs). It aims to improve the prediction accuracy of basic centrality measures. The idea behind this ensemble framework is that different protein-protein interactions (PPIs) may show different contributions to protein essentiality. Five standard centrality measures (degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, and subgraph centrality) are integrated into the ensemble framework respectively. We evaluated the performance of the proposed ensemble framework using yeast PINs and gene expression data. The results show that it can considerably improve the prediction accuracy of the five centrality measures individually. It can also remarkably increase the number of common predicted essential proteins among those predicted by each centrality measure individually and enable each centrality measure to find more low-degree essential proteins. Conclusions: This paper demonstrates that it is valuable to differentiate the contributions of different PPIs for identifying essential proteins based on network topological characteristics. The proposed ensemble framework is a successful paradigm to this end. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-08-25 2018-12-11T17:05:03Z 2018-12-11T17:05:03Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1186/s12859-016-1166-7 BMC Bioinformatics, v. 17, n. 1, 2016. 1471-2105 http://hdl.handle.net/11449/173406 10.1186/s12859-016-1166-7 2-s2.0-84983567663 2-s2.0-84983567663.pdf 7977035910952141 |
url |
http://dx.doi.org/10.1186/s12859-016-1166-7 http://hdl.handle.net/11449/173406 |
identifier_str_mv |
BMC Bioinformatics, v. 17, n. 1, 2016. 1471-2105 10.1186/s12859-016-1166-7 2-s2.0-84983567663 2-s2.0-84983567663.pdf 7977035910952141 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
BMC Bioinformatics 1,479 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128769217527808 |