Dear All, I have a question about limma model. We have 5 subjects, each subject has 9 time points data, so I want to find DE gene. Based on limma manual, it reported time-course data, but not time-course data with duplication. So I wanna know that How to set function or parameters that build this correlation between time points in one subject, not been processed as independent data? Thanks a lot! Joe [[alternative HTML version deleted]]

Dear Joe, You can either treat the subjects as blocks (see Section 8.4 of the limma User's Guide), or use the duplicateCorrelation() function (see for example Section 8.7 in the limma User's Guide): http://www.bioconductor.org/packages/release/bioc/vignettes/limma/inst /doc/usersguide.pdf You will need to adapt the code a little. Best wishes Gordon > Date: Sun, 16 Dec 2012 13:58:10 +0800 > From: "joseph" <joseph.houjue at="" gmail.com=""> > To: <bioconductor at="" r-project.org=""> > Subject: [BioC] limma time-course dependent data > > Dear All, > > I have a question about limma model. > > We have 5 subjects, each subject has 9 time points data, so I want to > find DE gene. Based on limma manual, it reported time-course data, but > not time-course data with duplication. So I wanna know that How to set > function or parameters that build this correlation between time points > in one subject, not been processed as independent data? > > Thanks a lot! > Joe ______________________________________________________________________ The information in this email is confidential and intend...{{dropped:4}}