The commands below are the R scripts that are used to analyze my microarray data. I want to know which lines are responsible for 1-Replacing replicated probes with the mean 2-Background correction
# Differential expression analysis with limma
library(Biobase)
library(GEOquery)
library(limma)
# load series and platform data from GEO
gset <- getGEO("GSE116959", GSEMatrix =TRUE, AnnotGPL=FALSE)
if (length(gset) > 1) idx <- grep("GPL17077", attr(gset, "names")) else idx <- 1
gset <- gset[[idx]]
# make proper column names to match toptable
fvarLabels(gset) <- make.names(fvarLabels(gset))
# group names for all samples
gsms <- "00010000000100000000000000000000011110000010000000000000000011010010"
sml <- c()
for (i in 1:nchar(gsms)) { sml[i] <- substr(gsms,i,i) }
# log2 transform
ex <- exprs(gset)
qx <- as.numeric(quantile(ex, c(0., 0.25, 0.5, 0.75, 0.99, 1.0), na.rm=T))
LogC <- (qx[5] > 100) ||
(qx[6]-qx[1] > 50 && qx[2] > 0) ||
(qx[2] > 0 && qx[2] < 1 && qx[4] > 1 && qx[4] < 2)
if (LogC) { ex[which(ex <= 0)] <- NaN
exprs(gset) <- log2(ex) }
# set up the data and proceed with analysis
sml <- paste("G", sml, sep="") # set group names
fl <- as.factor(sml)
gset$description <- fl
design <- model.matrix(~ description + 0, gset)
colnames(design) <- levels(fl)
fit <- lmFit(gset, design)
cont.matrix <- makeContrasts(G1-G0, levels=design)
fit2 <- contrasts.fit(fit, cont.matrix)
fit2 <- eBayes(fit2, 0.01)
tT <- topTable(fit2, adjust="fdr", sort.by="B", number=250)