Dear Bioconductors, I am wondering whether it makes sense to use genes with log odds less than 0 generated from Limma. There are only a handful of genes with B>0. I observe the volcano plot of log odds vs. log ratios, and it seems to me that even with B = -2, there is a pretty distinct group of genes that can be separated from majority of other genes. However, if I understand it correctly, any gene with B<0 has <50% probability to be differentially expressed. My questions is what is the best way to choose the right B statistics, using volcano plot as a guide or use arbitratry cutoffs like 0. Thanks, Xiwei "EMF <coh.org>" made the following annotations. ---------------------------------------------------------------------- -------- SECURITY/CONFIDENTIALITY WARNING: This message and any atta...{{dropped}}