File Download
Supplementary

Conference Paper: A study of network-based kernel methods on protein-protein interaction for protein functions prediction

TitleA study of network-based kernel methods on protein-protein interaction for protein functions prediction
Authors
KeywordsProtein function prediction
Kernel method
Local linear embedding (LLE) kernel
Laplacian kernel
Diffusion kernel
Issue Date2009
PublisherAPORC.
Citation
The 3rd International Symposium on Optimization and Systems Biology (OSB 2009), Zhangjiajie, China, 20-22 September 2009. In Lecture Notes in Operations Research, 2009, v. 11, p. 25-32 How to Cite?
AbstractPredicting protein functions is an important issue in the post-genomic era. In this paper, we studied 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). We first construct kernels based on PPI networks, we then apply Support Vector Machine (SVM) techniques to classify proteins into different functional groups. 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 Chisquare methods. Finally we made predictions of functions of some unknown genes and verified the preciseness of our prediction in part by the information of other data source.
Persistent Identifierhttp://hdl.handle.net/10722/119231
ISBN

 

DC FieldValueLanguage
dc.contributor.authorChing, WKen_HK
dc.contributor.authorLi, Len_HK
dc.contributor.authorChan, YMen_HK
dc.contributor.authorMamitsuka, Hen_HK
dc.date.accessioned2010-09-26T08:42:01Z-
dc.date.available2010-09-26T08:42:01Z-
dc.date.issued2009en_HK
dc.identifier.citationThe 3rd International Symposium on Optimization and Systems Biology (OSB 2009), Zhangjiajie, China, 20-22 September 2009. In Lecture Notes in Operations Research, 2009, v. 11, p. 25-32-
dc.identifier.isbn978-7-5100-0549-7-
dc.identifier.urihttp://hdl.handle.net/10722/119231-
dc.description.abstractPredicting protein functions is an important issue in the post-genomic era. In this paper, we studied 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). We first construct kernels based on PPI networks, we then apply Support Vector Machine (SVM) techniques to classify proteins into different functional groups. 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 Chisquare methods. Finally we made predictions of functions of some unknown genes and verified the preciseness of our prediction in part by the information of other data source.-
dc.languageengen_HK
dc.publisherAPORC.-
dc.relation.ispartofLecture Notes in Operations Research-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectProtein function prediction-
dc.subjectKernel method-
dc.subjectLocal linear embedding (LLE) kernel-
dc.subjectLaplacian kernel-
dc.subjectDiffusion kernel-
dc.titleA study of network-based kernel methods on protein-protein interaction for protein functions predictionen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=978-7-5100-0549-7/O764&volume=11&spage=25&epage=32&date=2009&atitle=A+study+of+network-based+kernel+methods+on+protein-protein+interaction+for+protein+functions+prediction-
dc.identifier.emailChing, WK: wching@HKUCC.hku.hken_HK
dc.identifier.emailLi, L: liminli@HKUSUA.hku.hk, liminli321@msn.comen_HK
dc.identifier.emailChan, YM: ymchan@maths.hku.hken_HK
dc.identifier.emailMamitsuka, H: mami@kuicr.kyoto-u.ac.jp-
dc.description.naturepostprint-
dc.identifier.hkuros167673en_HK
dc.identifier.volume11en_HK
dc.identifier.spage25en_HK
dc.identifier.epage32en_HK
dc.description.otherThe 3rd International Symposium on Optimization and Systems Biology (OSB 2009), Zhangjiajie, China, 20-22 September 2009. In Lecture Notes in Operations Research, 2009, v. 11, p. 25-32-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats