Predicting Co-Complexed Protein Pairs from Heterogeneous Data 英文参考文献.docVIP

下载本文档

3
0
约6.02万字
约 10页
2017-05-12 发布于上海
举报
版权申诉

Predicting Co-Complexed Protein Pairs from Heterogeneous Data 英文参考文献.doc

1、本文档共10页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Predicting Co-Complexed Protein Pairs from Heterogeneous Data 英文参考文献

PredictingCo-ComplexedProteinPairsfrom HeterogeneousData JianQiu1,WilliamStaffordNoble1,2* 1Department of Genome Sciences, University of Washington, Seattle, Washington, United States of America, 2Department of Computer Science and Engineering, UniversityofWashington,Seattle,Washington,UnitedStatesofAmerica Abstract Proteinsdonotcarryouttheirfunctionsalone.Instead,theyoftenactbyparticipatinginmacromolecularcomplexesand playdifferentfunctionalrolesdependingontheothermembersofthecomplex.Itisthereforeinterestingtoidentifyco- complex relationships. Although protein complexes can be identified in a high-throughput manner by experimental technologiessuchasaffinitypurificationcoupledwithmassspectrometry (APMS),theselarge-scaledatasetsoftensuffer from high false positive andfalse negativerates. Here, wepresent acomputational method thatpredicts co-complexed proteinpair(CCPP)relationshipsusingkernelmethodsfromheterogeneousdatasources.Weshowthatadiffusionkernel basedonrandomwalksonthefullnetworktopologyyieldsgoodperformanceinpredictingCCPPsfromproteininteraction networks.Inthesettingofdirectranking,adiffusionkernelperformsmuchbetterthanthemutualclusteringcoefficient.In thesettingofSVMclassifiers,adiffusionkernelperformsmuchbetterthanalinearkernel.Wealsoshowthatcombination ofcomplementaryinformationimprovestheperformanceofourCCPPrecognizer.Asummationofthreediffusionkernels based on two-hybrid, APMS, and genetic interaction networks and three sequence kernels achieves better performance thanthesequencekernelsordiffusionkernelsalone.InclusionofadditionalfeaturesachievesastillbetterROC50of0.937. Assuminganegative-to-positiveratioof600:1,thefinalclassifierachieves89.3%coverageatanestimatedfalsediscovery rateof10%.Finally,weappliedourpredictionmethodtotworecentlydescribedAPMSdatasets.Wefindthatourpredicted positives are highly enriched with CCPPs that are identified by both datasets, suggesting that our method successfully identifiestrueCCPPs.AnSVMclassifiertrainedfromheterog