I would like to ask about design matrix in GLM model in edgeR. I have group of transgenic down regulate gene. We have 3 lines of transgnics per down regulate gene which different level (event) of down regulate gene and in each line we have 3 replicate. This means we have 9 sample per 1 gene downregulate. This experiment also have double down regulate (2 genes down regulate at the same time). We would like to find gene that change when we down regulate target gene. I create event1-9 to seperate the transgenic event. I try design matrix as show below and can't perform GLM. It show " Error in solve.default(R, t(beta)) : system is computationally singular: reciprocal condition number = 3.13057e-17 If i change the design metric to column1-3 (effect of mean,geneA and geneB), this new design matric work well. How can i desing matric that account for effect of transgnic event? mean geneA geneB event1 event2 event3 event4 event5 event6 event7 event8 event9 wt 1 0 0 0 0 0 0 0 0 0 0 0 wt 1 0 0 0 0 0 0 0 0 0 0 0 wt 1 0 0 0 0 0 0 0 0 0 0 0 down_a 1 1 0 1 0 0 0 0 0 0 0 0 down_a 1 1 0 1 0 0 0 0 0 0 0 0 down_a 1 1 0 1 0 0 0 0 0 0 0 0 down_a 1 1 0 0 1 0 0 0 0 0 0 0 down_a 1 1 0 0 1 0 0 0 0 0 0 0 down_a 1 1 0 0 1 0 0 0 0 0 0 0 down_a 1 1 0 0 0 1 0 0 0 0 0 0 down_a 1 1 0 0 0 1 0 0 0 0 0 0 down_a 1 1 0 0 0 1 0 0 0 0 0 0 down_b 1 0 1 0 0 0 1 0 0 0 0 0 down_b 1 0 1 0 0 0 1 0 0 0 0 0 down_b 1 0 1 0 0 0 1 0 0 0 0 0 down_b 1 0 1 0 0 0 0 1 0 0 0 0 down_b 1 0 1 0 0 0 0 1 0 0 0 0 down_b 1 0 1 0 0 0 0 1 0 0 0 0 down_b 1 0 1 0 0 0 0 0 1 0 0 0 down_b 1 0 1 0 0 0 0 0 1 0 0 0 down_b 1 0 1 0 0 0 0 0 1 0 0 0 down_ab 1 1 1 0 0 0 0 0 0 1 0 0 down_ab 1 1 1 0 0 0 0 0 0 1 0 0 down_ab 1 1 1 0 0 0 0 0 0 1 0 0 down_ab 1 1 1 0 0 0 0 0 0 0 1 0 down_ab 1 1 1 0 0 0 0 0 0 0 1 0 down_ab 1 1 1 0 0 0 0 0 0 0 1 0 down_ab 1 1 1 0 0 0 0 0 0 0 0 1 down_ab 1 1 1 0 0 0 0 0 0 0 0 1 down_ab 1 1 1 0 0 0 0 0 0 0 0 1 Thank you very much Sermsawat T. [[alternative HTML version deleted]]