000013095 001__ 13095
000013095 005__ 20200402205938.0
000013095 0247_ $$2pmid$$apmid:20823334
000013095 0247_ $$2pmc$$apmc:PMC2935441
000013095 0247_ $$2DOI$$a10.1093/bioinformatics/btq394
000013095 0247_ $$2WOS$$aWOS:000281714100035
000013095 037__ $$aPreJuSER-13095
000013095 041__ $$aeng
000013095 082__ $$a004
000013095 084__ $$2WoS$$aBiochemical Research Methods
000013095 084__ $$2WoS$$aBiotechnology & Applied Microbiology
000013095 084__ $$2WoS$$aComputer Science, Interdisciplinary Applications
000013095 084__ $$2WoS$$aMathematical & Computational Biology
000013095 084__ $$2WoS$$aStatistics & Probability
000013095 1001_ $$0P:(DE-HGF)0$$aQi, Y.$$b0
000013095 245__ $$aSemi-Supervised Multi-Task Learning for Predicting Interactions between HIV-1 and Human Proteins
000013095 260__ $$aOxford$$bOxford University Press$$c2010
000013095 300__ $$a1645 - 1652
000013095 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article
000013095 3367_ $$2DataCite$$aOutput Types/Journal article
000013095 3367_ $$00$$2EndNote$$aJournal Article
000013095 3367_ $$2BibTeX$$aARTICLE
000013095 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000013095 3367_ $$2DRIVER$$aarticle
000013095 440_0 $$013881$$aBioinformatics$$v26$$x1367-4803$$y18
000013095 500__ $$aRecord converted from VDB: 12.11.2012
000013095 520__ $$aProtein-protein interactions (PPIs) are critical for virtually every biological function. Recently, researchers suggested to use supervised learning for the task of classifying pairs of proteins as interacting or not. However, its performance is largely restricted by the availability of truly interacting proteins (labeled). Meanwhile, there exists a considerable amount of protein pairs where an association appears between two partners, but not enough experimental evidence to support it as a direct interaction (partially labeled).We propose a semi-supervised multi-task framework for predicting PPIs from not only labeled, but also partially labeled reference sets. The basic idea is to perform multi-task learning on a supervised classification task and a semi-supervised auxiliary task. The supervised classifier trains a multi-layer perceptron network for PPI predictions from labeled examples. The semi-supervised auxiliary task shares network layers of the supervised classifier and trains with partially labeled examples. Semi-supervision could be utilized in multiple ways. We tried three approaches in this article, (i) classification (to distinguish partial positives with negatives); (ii) ranking (to rate partial positive more likely than negatives); (iii) embedding (to make data clusters get similar labels). We applied this framework to improve the identification of interacting pairs between HIV-1 and human proteins. Our method improved upon the state-of-the-art method for this task indicating the benefits of semi-supervised multi-task learning using auxiliary information.http://www.cs.cmu.edu/~qyj/HIVsemi.
000013095 536__ $$0G:(DE-Juel1)FUEK505$$2G:(DE-HGF)$$aBioSoft: Makromolekulare Systeme und biologische Informationsverarbeitung$$cP45$$x0
000013095 588__ $$aDataset connected to Web of Science, Pubmed
000013095 650_2 $$2MeSH$$aAlgorithms
000013095 650_2 $$2MeSH$$aArtificial Intelligence
000013095 650_2 $$2MeSH$$aComputational Biology: methods
000013095 650_2 $$2MeSH$$aData Interpretation, Statistical
000013095 650_2 $$2MeSH$$aHIV-1: physiology
000013095 650_2 $$2MeSH$$aHuman Immunodeficiency Virus Proteins: metabolism
000013095 650_2 $$2MeSH$$aHumans
000013095 650_2 $$2MeSH$$aModels, Statistical
000013095 650_2 $$2MeSH$$aProtein Interaction Mapping: methods
000013095 650_2 $$2MeSH$$aProteins: metabolism
000013095 650_7 $$00$$2NLM Chemicals$$aHuman Immunodeficiency Virus Proteins
000013095 650_7 $$00$$2NLM Chemicals$$aProteins
000013095 650_7 $$2WoSType$$aJ
000013095 7001_ $$0P:(DE-HGF)0$$aTastan, O.$$b1
000013095 7001_ $$0P:(DE-HGF)0$$aCarbonell, J.G.$$b2
000013095 7001_ $$0P:(DE-Juel1)VDB44599$$aKlein-Seetharaman, J.$$b3$$uFZJ
000013095 7001_ $$0P:(DE-HGF)0$$aWeston, J.$$b4
000013095 773__ $$0PERI:(DE-600)1468345-3$$a10.1093/bioinformatics/btq394$$gVol. 26, p. 1645 - 1652$$p1645 - 1652$$q26<1645 - 1652$$tBioinformatics$$v26$$x1367-4803$$y2010
000013095 8567_ $$2Pubmed Central$$uhttp://www.ncbi.nlm.nih.gov/pmc/articles/PMC2935441
000013095 909CO $$ooai:juser.fz-juelich.de:13095$$pVDB
000013095 9131_ $$0G:(DE-Juel1)FUEK505$$bSchlüsseltechnologien$$kP45$$lBiologische Informationsverarbeitung$$vBioSoft: Makromolekulare Systeme und biologische Informationsverarbeitung$$x0
000013095 9132_ $$0G:(DE-HGF)POF3-551$$1G:(DE-HGF)POF3-550$$2G:(DE-HGF)POF3-500$$aDE-HGF$$bKey Technologies$$lBioSoft  Fundamentals for future Technologies in the fields of Soft Matter and Life Sciences$$vFunctional Macromolecules and Complexes$$x0
000013095 9141_ $$y2010
000013095 915__ $$0StatID:(DE-HGF)0010$$aJCR/ISI refereed
000013095 9201_ $$0I:(DE-Juel1)ISB-2-20090406$$d31.12.2010$$gISB$$kISB-2$$lMolekulare Biophysik$$x0
000013095 970__ $$aVDB:(DE-Juel1)124922
000013095 980__ $$aVDB
000013095 980__ $$aConvertedRecord
000013095 980__ $$ajournal
000013095 980__ $$aI:(DE-Juel1)ICS-6-20110106
000013095 980__ $$aUNRESTRICTED
000013095 981__ $$aI:(DE-Juel1)IBI-7-20200312
000013095 981__ $$aI:(DE-Juel1)ICS-6-20110106
000013095 981__ $$aI:(DE-Juel1)ISB-2-20090406