Dear All, I am wondering about the construction of a design matrix for identify diff erentially expressed genes with Lumi package. I am asking this beacause I obtain strange results when i compare between groups. I have 4 sample, each one in triplicate. I substracted bkg, normalized and vst transformed. dataMatrix <- exprs(lumi.N.Q) presentCount <- detectionCall(x.lumi) selDataMatrix <- dataMatrix[presentCount > 1,] probeList <- rownames(selDataMatrix) sampleType <- c('CME','ES','CMA','CMN','CME','ES','CMA','CMN','CME','E S','CMA','CMN') design <- model.matrix(~ factor(sampleType)) colnames(design) <- c('CME','ES','CMA','CMN') fit1 <- lmFit(selDataMatrix, design) constrast.matrix <- makeContrasts (ES-CMN,ES-CME,ES-CMA,levels=design) fit1_2 <- contrasts.fit(fit1,constrast.matrix) fit1_2 <- eBayes(fit1_2) If now I try to check how the matrix is designed: design() CME ES CMA CMN 1 1 1 0 0 2 1 0 0 1 3 1 0 0 0 4 1 0 1 0 5 1 1 0 0 6 1 0 0 1 7 1 0 0 0 8 1 0 1 0 9 1 1 0 0 10 1 0 0 1 11 1 0 0 0 12 1 0 1 0 attr(,"assign") [1] 0 1 1 1 attr(,"contrasts") attr(,"contrasts")$`factor(sampleType)` [1] "contr.treatment" and this seems not be the one I designed, where am I wrong? Thanks, Paolo ssionInfo() R version 2.15.0 (2012-03-30) Platform: i386-pc-mingw32/i386 (32-bit) locale: [1] LC_COLLATE=Italian_Italy.1252 LC_CTYPE=Italian_Italy.1252 LC_MONETARY=Italian_Italy.1252 [4] LC_NUMERIC=C LC_TIME=Italian_Italy.1252 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] annotate_1.34.1 lumiMouseAll.db_1.18.0 org.Mm.eg.db_2.7.1 limma_3.12.1 [5] lumiMouseIDMapping_1.10.0 RSQLite_0.11.1 DBI_0.2-5 AnnotationDbi_1.18.1 [9] lumi_2.8.0 nleqslv_1.9.3 methylumi_2.2.0 ggplot2_0.9.1 [13] reshape2_1.2.1 scales_0.2.1 Biobase_2.16.0 BiocGenerics_0.2.0 loaded via a namespace (and not attached): [1] affy_1.34.0 affyio_1.24.0 bigmemory_4.2.11 BiocInstaller_1.4.7 [5] Biostrings_2.24.1 bitops_1.0-4.1 BSgenome_1.24.0 colorspace_1.1-1 [9] dichromat_1.2-4 digest_0.5.2 DNAcopy_1.30.0 GenomicRanges_1.8.7 [13] genoset_1.6.0 grid_2.15.0 hdrcde_2.16 IRanges_1.14.4 [17] KernSmooth_2.23-8 labeling_0.1 lattice_0.20-6 MASS_7.3-19 [21] Matrix_1.0-7 memoise_0.1 mgcv_1.7-18 munsell_0.3 [25] nlme_3.1-104 plyr_1.7.1 preprocessCore_1.18.0 proto_0.3-9.2 [29] RColorBrewer_1.0-5 RCurl_1.91-1.1 Rsamtools_1.8.5 rtracklayer_1.16.2 [33] stats4_2.15.0 stringr_0.6 tools_2.15.0 XML_3.9-4.1 [37] xtable_1.7-0 zlibbioc_1.2.0 >

Hi Paolo, Your command: colnames(design) <- c('CME','ES','CMA','CMN') is wrong (i.e. this is not what model.matrix produces). Do the two previous commands, i.e. sampleType <- c('CME','ES','CMA','CMN','CME','ES','CMA','CMN','CME','ES','CMA','CMN' ) design <- model.matrix(~ factor(sampleType)) and then look at design (i.e. type design). You will see what you get. You can also try design <- model.matrix(~ 0 + factor(sampleType)) instead and again see what you get. Best regards, Moshe. > Dear All, > I am wondering about the construction of a design matrix for identify > diff erentially expressed genes with Lumi package. > I am asking this beacause I obtain strange results when i compare > between groups. > > I have 4 sample, each one in triplicate. > I substracted bkg, normalized and vst transformed. > > > dataMatrix <- exprs(lumi.N.Q) > presentCount <- detectionCall(x.lumi) > selDataMatrix <- dataMatrix[presentCount > 1,] > probeList <- rownames(selDataMatrix) > > > > sampleType <- > c('CME','ES','CMA','CMN','CME','ES','CMA','CMN','CME','ES','CMA','CM N') > design <- model.matrix(~ factor(sampleType)) > colnames(design) <- c('CME','ES','CMA','CMN') > > > fit1 <- lmFit(selDataMatrix, design) > constrast.matrix <- makeContrasts (ES-CMN,ES-CME,ES- CMA,levels=design) > fit1_2 <- contrasts.fit(fit1,constrast.matrix) > fit1_2 <- eBayes(fit1_2) > > > > If now I try to check how the matrix is designed: > > design() > > CME ES CMA CMN > 1 1 1 0 0 > 2 1 0 0 1 > 3 1 0 0 0 > 4 1 0 1 0 > 5 1 1 0 0 > 6 1 0 0 1 > 7 1 0 0 0 > 8 1 0 1 0 > 9 1 1 0 0 > 10 1 0 0 1 > 11 1 0 0 0 > 12 1 0 1 0 > attr(,"assign") > [1] 0 1 1 1 > attr(,"contrasts") > attr(,"contrasts")$`factor(sampleType)` > [1] "contr.treatment" > > > and this seems not be the one I designed, where am I wrong? > > > Thanks, > Paolo > > > ssionInfo() > R version 2.15.0 (2012-03-30) > Platform: i386-pc-mingw32/i386 (32-bit) > > locale: > [1] LC_COLLATE=Italian_Italy.1252 LC_CTYPE=Italian_Italy.1252 > LC_MONETARY=Italian_Italy.1252 > [4] LC_NUMERIC=C LC_TIME=Italian_Italy.1252 > > attached base packages: > [1] stats graphics grDevices utils datasets methods base > > other attached packages: > [1] annotate_1.34.1 lumiMouseAll.db_1.18.0 > org.Mm.eg.db_2.7.1 limma_3.12.1 > [5] lumiMouseIDMapping_1.10.0 RSQLite_0.11.1 DBI_0.2-5 > AnnotationDbi_1.18.1 > [9] lumi_2.8.0 nleqslv_1.9.3 > methylumi_2.2.0 ggplot2_0.9.1 > [13] reshape2_1.2.1 scales_0.2.1 > Biobase_2.16.0 BiocGenerics_0.2.0 > > loaded via a namespace (and not attached): > [1] affy_1.34.0 affyio_1.24.0 bigmemory_4.2.11 > BiocInstaller_1.4.7 > [5] Biostrings_2.24.1 bitops_1.0-4.1 BSgenome_1.24.0 > colorspace_1.1-1 > [9] dichromat_1.2-4 digest_0.5.2 DNAcopy_1.30.0 > GenomicRanges_1.8.7 > [13] genoset_1.6.0 grid_2.15.0 hdrcde_2.16 > IRanges_1.14.4 > [17] KernSmooth_2.23-8 labeling_0.1 lattice_0.20-6 > MASS_7.3-19 > [21] Matrix_1.0-7 memoise_0.1 mgcv_1.7-18 > munsell_0.3 > [25] nlme_3.1-104 plyr_1.7.1 preprocessCore_1.18.0 > proto_0.3-9.2 > [29] RColorBrewer_1.0-5 RCurl_1.91-1.1 Rsamtools_1.8.5 > rtracklayer_1.16.2 > [33] stats4_2.15.0 stringr_0.6 tools_2.15.0 > XML_3.9-4.1 > [37] xtable_1.7-0 zlibbioc_1.2.0 >> > > _______________________________________________ > Bioconductor mailing list > Bioconductor at r-project.org > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: > http://news.gmane.org/gmane.science.biology.informatics.conductor > ______________________________________________________________________ The information in this email is confidential and intend...{{dropped:4}}