Hi All: Even after going through hand full of posts on log fold change, I could not figure out how exactly it is calculated in LIMMA. Please see following example. Arrays 3 and 4 are dye swaps for arrays 1 and 2 (Arrays 1 and 2 are rep 1 and rep 2). For Gene 1; The M values are, 1 2 3 4 -1.1907 -1.00507 0.68244023 0.815401 And the A values are, 1 2 3 4 7.693117 6.218356 7.59435237 6.671801 After computing the linear model fit the output is, logFC AveExpr t P.Value adj.P.Val B -0.9234 7.044406 -8.0598372 0.000229 0.00306 0.868682 I am wondering how the logFC (-0.9234) is gotten. LIMMA user guide says M values are simply the log2 fold changes between conditions. Any help is appreciated. Thanks Jay [[alternative HTML version deleted]]

Assuming your design matrix is c(1,1,-1,-1) then the latter two M values are multiplied by -1: > mean(c(-1.1907,-1.00507,-0.68244023,-0.815401)) [1] -0.9234028 ________________________________________ From: bioconductor-bounces@stat.math.ethz.ch [bioconductor- bounces@stat.math.ethz.ch] On Behalf Of Jay [jboddu@uiuc.edu] Sent: 16 March 2010 21:29 To: bioconductor at stat.math.ethz.ch Subject: [BioC] log Fold Change Hi All: Even after going through hand full of posts on log fold change, I could not figure out how exactly it is calculated in LIMMA. Please see following example. Arrays 3 and 4 are dye swaps for arrays 1 and 2 (Arrays 1 and 2 are rep 1 and rep 2). For Gene 1; The M values are, 1 2 3 4 -1.1907 -1.00507 0.68244023 0.815401 And the A values are, 1 2 3 4 7.693117 6.218356 7.59435237 6.671801 After computing the linear model fit the output is, logFC AveExpr t P.Value adj.P.Val B -0.9234 7.044406 -8.0598372 0.000229 0.00306 0.868682 I am wondering how the logFC (-0.9234) is gotten. LIMMA user guide says M values are simply the log2 fold changes between conditions. Any help is appreciated. Thanks Jay [[alternative HTML version deleted]] _______________________________________________ Bioconductor mailing list Bioconductor at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/bioconductor Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor