[BioC] access Limma objects

[James W. MacDonald]

Hi Chuming,

On 7/16/2012 9:25 AM, Chuming Chen wrote:
> Hi All,
>
> Is there a way to get the normalized log mean intensity values from the limma analysis, and then to rank order these values from 1 to 100?

It depends on what you mean by 'the normalized log mean intensity 
values'. After the lmFit() step, your MArrayLM object will have a 
coefficients list item (e.g., if you do fit <- lmFit(mydata), then 
fit$coefficients is what you want), which will contain all the estimated 
coefficients from your model fit.

What those coefficients represent is dependent on how you specified your 
model, and what type of data you are using (single color or two-color 
data). So if you are using single-color data, and you fit a cell means 
model, and you normalized and took logs, then the coefficients will be 
the normalized log mean intensities for each sample type, by gene.

And rank ordering of data is trivial - see the Introduction to R if you 
need help with that.

Best,

Jim

>
> Thanks,
>
> Chuming
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at r-project.org
> 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
University of Washington
Environmental and Occupational Health Sciences
4225 Roosevelt Way NE, # 100
Seattle WA 98105-6099