返回
Cancer classification and prediction using logistic regression with Bayesian gene selection

Cancer classification and prediction using logistic regression with Bayesian gene selection

ID：37943443

大小：348.55 KB

页数：11页

时间：2019-06-03

Cancer classification and prediction using logistic regression with Bayesian gene selection_第1页
Cancer classification and prediction using logistic regression with Bayesian gene selection_第2页
Cancer classification and prediction using logistic regression with Bayesian gene selection_第3页
Cancer classification and prediction using logistic regression with Bayesian gene selection_第4页
Cancer classification and prediction using logistic regression with Bayesian gene selection_第5页
资源描述：

《Cancer classification and prediction using logistic regression with Bayesian gene selection》由会员上传分享，免费在线阅读，更多相关内容在行业资料-天天文库。

1、JournalofBiomedicalInformatics37(2004)249–259www.elsevier.com/locate/yjbinCancerclassificationandpredictionusinglogisticregressionwithBayesiangeneselectiona,ba,ba,b,*XiaoboZhou,Kuang-YuLiu,StephenT.C.WongaHarvardCenterforNeurodegenerationandRepair—CenterforBioinformatics,HarvardMedicalSchool,220Longw

2、oodAvenue,Boston,MA02115,USAbRadiologyDepartment,HarvardMedicalSchoolandBrighamandWomenÕsHospital,77FrancisStreet,Boston,MA02115,USAReceived13June2004Availableonline11September2004AbstractInmicroarray-basedcancerclassificationandprediction,geneselectionisanimportantresearchproblemowingtothelargenum-b

3、erofgenesandthesmallnumberofexperimentalconditions.Inthispaper,weproposeaBayesianapproachtogeneselectionandclassificationusingthelogisticregressionmodel.Thebasicideaofourapproachisinconjunctionwithalogisticregressionmodeltorelatethegeneexpressionwiththeclasslabels.WeuseGibbssamplingandMarkovchainMont

4、eCarlo(MCMC)methodstodis-coverimportantgenes.ToimplementGibbsSamplerandMCMCsearch,wederiveaposteriordistributionofselectedgenesgiventheobserveddata.Aftertheimportantgenesareidentified,thesamelogisticregressionmodelisthenusedforcancerclassificationandprediction.Issuesforefficientimplementationforthepropo

5、sedmethodarediscussed.Theproposedmethodisevaluatedagainstseverallargemicroarraydatasets,includinghereditarybreastcancer,smallroundblue-celltumors,andacuteleukemia.Theresultsshowthatthemethodcaneffectivelyidentifyimportantgenesconsistentwiththeknownbiologicalfindingswhiletheaccuracyoftheclassificationis

6、alsohigh.Finally,therobustnessandsensitivitypropertiesoftheproposedmethodarealsoinvestigated.Ó2004ElsevierInc.Allrightsreserved.Keywords:Genemicroarray;Logisticregression;Bayesiangeneselection;Cancerclassification1.Introductionformodelselection[12],andthelogisticregressionmod-el[3].Thelogisticregress

7、ionmodel,alsoknownaslogitCancerclassificationandpredictionhasbecomeoneintheliterature,isoneofthemostcommonmodelsforofthemostimportantapplicationsofDNAmicroarrayprediction,regression,andclassificationofd

当前文档最多预览五页，下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页，下载文档查看全文
温馨提示：
1. 部分包含数学公式或PPT动画的文件，查看预览时可能会显示错乱或异常，文件下载后无此问题，请放心下载。
2. 本文档由用户上传，版权归属用户，天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容，确认文档内容符合您的需求后进行下载，若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误，付费完成后未能成功下载的用户请联系客服处理。