利用PLS-VIP方法筛选差异表达基因(英文)-豆柴文库

您所在位置：网站首页 / 利用PLS-VIP方法筛选差异表达基因(英文).docx / 文档详情

在线预览结束，喜欢就下载吧，查找使用更方便

5 金币

下载文档

/ 2

下载提示

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

文本预览

利用PLS-VIP方法筛选差异表达基因(英文)
Title:IdentificationofDifferentiallyExpressedGenesusingPartialLeastSquares-VariableImportanceinProjection(PLS-VIP)Method
Abstract:
Differentialgeneexpressionanalysisplaysavitalroleinidentifyinggenesthatareassociatedwithspecificbiologicalconditionsordiseasestates.Inrecentyears,variousstatisticaltechniqueshavebeendevelopedtoefficientlyidentifydifferentiallyexpressedgenes(DEGs)fromhigh-dimensionalgeneexpressiondata.Amongtheseapproaches,thePartialLeastSquares-VariableImportanceinProjection(PLS-VIP)methodhasgainedpopularityduetoitsabilitytohandlehigh-dimensionaldatasets,providerobustvariableimportancemeasures,andaccountforcollinearityamongvariables.Inthispaper,weexploretheapplicationofthePLS-VIPmethodfortheidentificationofDEGsanddiscussitsadvantagesoverotherexistingmethods.
Introduction:
High-throughputgeneexpressionprofilingtechnologies,suchasmicroarraysandRNA-sequencing,haverevolutionizedbiologicalresearchbyenablingthesimultaneousmeasurementofthousandsofgenes.Miningvaluableinformationfromthesedatasets,however,remainsachallengeduetothehighdimensionalityandcomplexityofthedata.IdentifyingDEGscanprovideinsightsintothemolecularmechanismsunderlyingdiseaseprogression,development,andresponsetotreatments.Therefore,thedevelopmentofrobustandefficientDEGanalysismethodsiscrucial.
Methods:
ThePLS-VIPmethodcombinesthePartialLeastSquares(PLS)regressionandVariableImportanceinProjection(VIP)score.PLSisamultivariateregressiontechniquethatidentifiesthelatentvariablesexplainingbothdependentandindependentvariables.VIPscoresmeasuretheimportanceofeachvariableintheprojectionspace.ThePLS-VIPmethodcomputestheVIPscoreforeachvariableandranksthembasedontheirimportance.GeneswithhighVIPscoresareconsideredpotentialDEGs.
ResultsandDiscussion:
WeappliedthePLS-VIPmethodtoageneexpressiondatasetobtainedfromtwogroups:acontrolandatreatmentgroup.Afterpreprocessingthedataandperformingqualitycontrol,weinputtheexpressionlevelsofgenesasindependentvariablesandgrouplabelsasthedependentvariab