I have 4 samples. 2 control and 2 gene_oe (over expression) samples.
I wanted to do differential analysis between Gene_OE vs Control samples. I have the samples column data like following:
coldata: Samples Type Time SampleA Control Day1 SampleB Control Day2 SampleD Gene_OE Day1 SampleE Gene_OE Day2
edgeR I did like following:
library(edgeR) group <- factor(paste0(coldata$Type))
And created design matrix like following:
design2 <- model.matrix(~ 0 + group + coldata$Time) desgin2 Control Gene_OE day1 day2 1 1 0 0 0 2 1 0 1 0 3 0 1 0 0 4 0 1 1 0
I see some warning message :
y <- estimateDisp(y, design2, robust=TRUE) Warning message: In estimateDisp.default(y = y$counts, design = design, group = group, : No residual df: setting dispersion to NA
And an error like below:
fit <- glmQLFit(y, design2, robust=TRUE) Error in glmFit.default(y, design = design, dispersion = dispersion, offset = offset, : Design matrix not of full rank. The following coefficients not estimable: day2
What could be the reason for this error? And how to resolve this error?