[BioC] multtest data preprocessing questions

ulas karaoz ulask at bu.edu
Mon May 24 20:26:28 CEST 2004

i am trying to use multest R package(source package) and i am puzzled 
by the following:
1-What kind of initial processing is done to the data?
I thought you get the golub.RData under the /multtest/data directory by 
running golub.R script that is attached(in the inst/doc directory) but 
when I run that script on the original data, and do "golub[1:4, 1:4]" i 
cannot get the same thing as in the documentation, i get:
  Gene.Accession.Number     call   call.1   call.2
36              2.000000 2.000000 2.017033 2.000000
37              2.332438 2.064458 2.677607 2.190332
38              2.901458 2.636488 3.168497 2.618048
39              4.162505 2.788875 3.753506 3.685742

2- My other question is, why is the need to  center, and to scale the 
data in the golub.R script, is it ever used?

3-Also in the same script, the class labels are initialized to 1,  and 
2(i.e. golub.cl<-c(rep(1,27),rep(2,11))
) although all the statistical tests upstream require 0, or 1 as 
labels. Am I wrong?

Is anyone running into similar problems.

More information about the Bioconductor mailing list