Dear members and developers, I have performed a time series experiment with 5 time points on treatment and controls. I used limma linear model for the differential expression analysis. In the design matrix, I included also other parameters (sex, weight and heterophiles/lymphocytes ratio). I find a few significant genes as I see from the top table output (called all coefficients). The code is following:
W2 <- model.matrix(~ Treatment*Time + Sex + dWeight + HL, data=PLSet)
fit <- lmFit(PLSet, W2)
class(fit)
fit <- eBayes(fit)
fit$coefficients[1:5,]
topTable(fit, n=13, coef=2:7)
# corresponding output
> topTable(fit, n=5, coef=2:7,confint=TRUE)
TreatmentT Time SexM dWeight HL TreatmentT.Time AveExpr
HPS5 4.11164704 -0.067986721 -0.78529467 -0.302848969 0.0043545345 0.076088166 23.71151
PLG.1 -0.46781188 0.002707286 -0.21489308 0.039849887 -0.0011381361 0.048460583 22.32991
AMY2A -0.66830973 -0.018069170 0.53177497 0.244178510 -0.0061577553 0.106497055 18.74018
MLF1 5.97939600 0.002833836 0.01591788 0.093259276 -0.0151262312 -0.135961018 18.95155
LCP1 0.88863607 -0.025327153 -0.34550418 -0.018652540 0.0040227853 0.003003491 19.74808
F P.Value adj.P.Val
HPS5 18.990758 3.134997e-08 6.395394e-06
PLG.1 9.812850 1.336712e-05 1.363446e-03
AMY2A 8.209525 5.571538e-05 3.788646e-03
MLF1 6.516355 3.040451e-04 1.458770e-02
LCP1 6.365580 3.575417e-04 1.458770e-02
I was wondering: How can I extract the p-value for each coefficient (treatment, time etc. ) for each gene? I know the coefficient column gives an estimate of the importance of the parameter in the result, but is there a way for this estimate to be expressed as a p-value?
Thanks!