[BioC] Results file LIMMA

Gordon K Smyth smyth at wehi.EDU.AU
Fri Jan 26 12:36:27 CET 2007


Dear Andreas,

I am guessing that by a "results file" you mean the output from the write.fit() function. 
Sections 10.1 and 10.2 of the limma User's Guide give a detailed explanation of the columns from
the topTable() function, and this pretty much explains everything from write.fit() as well.

Yes, the p-values are FDR adjusted, although not the F.p.values.  Yes, you can make your own cut.

Best wishes
Gordon

> Date: Thu, 25 Jan 2007 16:25:28 -0500
> From: "James W. MacDonald" <jmacdon at med.umich.edu>
> Subject: Re: [BioC] Results file LIMMA
> To: Andres Gutierrez <andresguty at yahoo.com>
> Cc: bioconductor at stat.math.ethz.ch
> Message-ID: <45B92048.1070408 at med.umich.edu>
> Content-Type: text/plain;  charset="utf-8";  format=flowed
>
> Andres Gutierrez wrote:
>> Hello,
>>
>> I'm new using LIMMA for the analysis of two color arrays. I have been following
>> the user guide but I have questions regarding the meaning of the values and
>> columns of the output "results" file.
>>
>> Where can I find an detailed explanation of the output file?, I mean the
>> statistical definition of each column: A, Coef., t., p.value, F and Res. I guess
>> that since I'm using adjust="fdr" in the code, the p values for each contrast
>> are already adjusted for fdr and I can make my own cut (e.g. 5% or 1%) to find
>> the MOST significant ones. Am I right?.
>
> The output from topTable is already sorted with the genes most likely to
> be significant at the top, so you can set your cutoff to select genes
> with an FDR less than a certain level.
>
> As for a statistical definition, you might look at the Bioconductor
> Monograph. I thought the Limma User's Manual covered that pretty well too.
>
> Best,
>
> Jim
>
>
>>
>> Thanks,
>>
>> Andres
>> Texas A&M University
>>
>> _______________________________________________
>> Bioconductor mailing list
>> Bioconductor at stat.math.ethz.ch
>> https://stat.ethz.ch/mailman/listinfo/bioconductor
>> Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor
>
>
> --
> James W. MacDonald, M.S.
> Biostatistician
> Affymetrix and cDNA Microarray Core
> University of Michigan Cancer Center
> 1500 E. Medical Center Drive
> 7410 CCGC
> Ann Arbor MI 48109
> 734-647-5623



More information about the Bioconductor mailing list