[BioC] hyperGTest

Naomi Altman naomi at stat.psu.edu
Tue May 1 16:11:57 CEST 2007

Specifically the change that I want to make is to allow duplicates.

We are using novel species.  Several genes from our species may hit 
the same gene from the closest model species due to duplication 
events since diversion.  So, I need to allow duplicates in both the 
universe and the test set.  I'll play with the code a bit - using 
weights might be the simplest.


At 06:13 PM 4/30/2007, Seth Falcon wrote:
>Naomi Altman <naomi at stat.psu.edu> writes:
> > I am having some problems with hyperGTest.  See below.  Also, I
> > wanted to modify hyperGTest for my project, but I cannot seem to find
> > any relevant code.  There must be some secret to names for functions
> > for this type of thing - please point me in the right direction.
>As Jim pointed out, you need the Matrix package.  This should have
>come along with an install of GOstats via biocLite(), but perhaps you
>installed using another mechanism.
>As for modifying the code for your project, you will want to download
>and unpack the source packages (.tar.gz) for Category and GOstats.
>The code is split between these packages since much of the
>Hypergeometric testing is not GO specific.
>There are a few notes in the man page for hyperGTest for how to extend
>to other category types if that is what you want to do.
>Given that you didn't have GOstats properly loaded, I imagine all of
>its functions would be rather invisible ;-)
>+ seth
>Seth Falcon | Computational Biology | Fred Hutchinson Cancer Research Center
>Bioconductor mailing list
>Bioconductor at stat.math.ethz.ch
>Search the archives: 

Naomi S. Altman                                814-865-3791 (voice)
Associate Professor
Dept. of Statistics                              814-863-7114 (fax)
Penn State University                         814-865-1348 (Statistics)
University Park, PA 16802-2111

More information about the Bioconductor mailing list