[BioC] about siggenes

[Holger Schwender]

There is a problem with the vignette (some chunk does not work) when the
package is built under R 2.0.0. Thus, there is also no manual in the devel
version of siggenes even though I have written one (the Release 1.4 version
does not contain a manual). Since everything else works and since I will
write a new manual/vignette for the new rewritten version of siggenes this
week-end, I have not corrected this. So you will not get the pdf using
openVignette(). However, you can get the chunks in the vignette using the
function vExplorer() of the tkWidget package.

To the problem with the fudge factor (the error message you get): This
happens if there are less than 101 genes with differing standard deviations.
Since SAM is actually thought for the analysis of several hundred genes I
have not corrected this "bug" up to now. This means it will be corrected in
the next version. There you must have at least 25 genes with differing
standard deviations (this limit was set by me, actually the computation
would work for less than 10 genes) to compute Tusher's fudge factor.
Otherwise, another method is used. The new version is also much, much
faster. While the old version needs about 1 min to compute the fudge factor
for the Plus2 chip of Affymetrix, the new one needs less than 10 seconds --
even if you specify more values for alpha.

HTH,
Holger


> The vignette comes with the package, if it was properly installed. 
> You should be able to do something like:
>  see either vignette,
>  or openVignette (in Biobase)
> 
>  Robert
> 
> On Wed, Sep 15, 2004 at 10:54:41AM -0500, haojie wrote:
> > Hi, all
> >  
> > I need to run sam function in the siggenes package, but I can't find the
> > vignette of siggenes package in bioconductor website (
> > <http://www.bioconductor.org/> http://www.bioconductor.org/). Is there
> > any detailed manual about the siggenes package?  
> >  
> > The problem I encountered is when I run sam function, for example : 
> > sam(mydata,cl) 
> > there is an error : 
> > Error in var(v) : missing observations in cov/cor. 
> > How can I find the problem? And what should I do to shape my dataset for
> > sam function?
> >  
> > Thanks for your help!
> > haojie
> >  
> > 
> > 	[[alternative HTML version deleted]]
> > 
> > _______________________________________________
> > Bioconductor mailing list
> > Bioconductor at stat.math.ethz.ch
> > https://stat.ethz.ch/mailman/listinfo/bioconductor
> 
> -- 
>
+---------------------------------------------------------------------------+
> | Robert Gentleman                 phone : (617) 632-5250                 
>  |
> | Associate Professor              fax:   (617)  632-2444                 
>  |
> | Department of Biostatistics      office: M1B20                          
>  |
> | Harvard School of Public Health  email: rgentlem at jimmy.harvard.edu      
>  |
>
+---------------------------------------------------------------------------+
> 
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> 

-- 

+++ Empfehlung der Redaktion +++ Internet Professionell 10/04 +++