[BioC] topTable question in limma

[Matthew Ritchie]

Try using eBayes() instead of ebayes() and topTable() instead of
toptable(), ie

PMAfit<-lmFit(subM,design,ndups=2,spacing=1,correlation=mycor$cor,weights=NULL)
PMAfit<-eBayes(PMAfit)
topT<-topTable(PMAfit,number=200,sort.by="P",genelist=genelist,adjust="fdr")

Also be sure that your genelist is the right size (half as many rows as
the original gal file, since you have averaged over the duplicate spots in
the linear model fit).  The function uniquegenelist() will do this for
you.

Best wishes,

Matt Ritchie

> Hi,
>   I am using limma. Here is a error I met
>
> SubM is a 19k by 6 matrix
>  > design
> [1]  1  1  1 -1 -1 -1
>  >
> PMAfit<-lmFit(subM,design,ndups=2,spacing=1,correlation=mycor$cor,weights=NULL)
>  > PMAfit<-ebayes(PMAfit)
>  >
> topT<-toptable(PMAfit,number=200,sort.by="P",genelist=genelist,adjust="fdr")
> Error in array(x, c(length(x), 1), if (!is.null(names(x)))
> list(names(x),  :
>          attempt to set an attribute on NULL
>
> Thanks