File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: On Network-based Kernel Methods for Protein-Protein Interactions with Applications in Protein Functions Prediction

TitleOn Network-based Kernel Methods for Protein-Protein Interactions with Applications in Protein Functions Prediction
Authors
Issue Date2010
PublisherSpringer Verlag. The Journal's web site is located at http://link.springer.com/journal/11424
Citation
Journal of Systems Science and Complexity, 2010, v. 23 n. 5, p. 917-930 How to Cite?
AbstractPredicting protein functions is an important issue in the post-genomic era. This paper studies several network-based kernels including local linear embedding (LLE) kernel method, diffusion kernel and laplacian kernel to uncover the relationship between proteins functions and protein-protein interactions (PPI). The author first construct kernels based on PPI networks, then apply support vector machine (SVM) techniques to classify proteins into different functional groups. The 5-fold cross validation is then applied to the selected 359 GO terms to compare the performance of different kernels and guilt-by-association methods including neighbor counting methods and Chi-square methods. Finally, the authors conduct predictions of functions of some unknown genes and verify the preciseness of our prediction in part by the information of other data source.
Persistent Identifierhttp://hdl.handle.net/10722/129255
ISSN
2015 Impact Factor: 0.542
2015 SCImago Journal Rankings: 0.347
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLi, Len_US
dc.contributor.authorChing, Wen_US
dc.contributor.authorChan, Yen_US
dc.contributor.authorMamitsuka, Hen_US
dc.date.accessioned2010-12-23T08:34:14Z-
dc.date.available2010-12-23T08:34:14Z-
dc.date.issued2010en_US
dc.identifier.citationJournal of Systems Science and Complexity, 2010, v. 23 n. 5, p. 917-930en_US
dc.identifier.issn1009-6124-
dc.identifier.urihttp://hdl.handle.net/10722/129255-
dc.description.abstractPredicting protein functions is an important issue in the post-genomic era. This paper studies several network-based kernels including local linear embedding (LLE) kernel method, diffusion kernel and laplacian kernel to uncover the relationship between proteins functions and protein-protein interactions (PPI). The author first construct kernels based on PPI networks, then apply support vector machine (SVM) techniques to classify proteins into different functional groups. The 5-fold cross validation is then applied to the selected 359 GO terms to compare the performance of different kernels and guilt-by-association methods including neighbor counting methods and Chi-square methods. Finally, the authors conduct predictions of functions of some unknown genes and verify the preciseness of our prediction in part by the information of other data source.-
dc.languageengen_US
dc.publisherSpringer Verlag. The Journal's web site is located at http://link.springer.com/journal/11424en_US
dc.relation.ispartofJournal of Systems Science and Complexityen_US
dc.rightsThe original publication is available at www.springerlink.comen_US
dc.subject.meshDiffusion kernel-
dc.subject.meshKernel method-
dc.subject.meshLaplacians-
dc.subject.meshLocal Linear Embedding-
dc.subject.meshProtein function prediction-
dc.titleOn Network-based Kernel Methods for Protein-Protein Interactions with Applications in Protein Functions Predictionen_US
dc.typeArticleen_US
dc.identifier.emailChing, W: wching@hkucc.hku.hken_US
dc.identifier.emailChan, Y: wtymchan@hku.hken_US
dc.identifier.authorityChing, WK=rp00679en_US
dc.identifier.doi10.1007/s11424-010-0207-y-
dc.identifier.scopuseid_2-s2.0-84866672238-
dc.identifier.hkuros183321en_US
dc.identifier.volume23en_US
dc.identifier.issue5-
dc.identifier.spage917en_US
dc.identifier.epage930en_US
dc.identifier.isiWOS:000284074000005-
dc.publisher.placeChina-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats