[BioC] R: visualization of Loess smoothing curve

[James W. MacDonald]

Hi Erika,

Please don't take things off-list. The list archives are intended to be 
a searchable repository of answered questions, and if things go 
off-list, that function is invalidated.

Erika Melissari wrote:
> Hi Jim,
> 
> I am talking about plotMA() function that resides in the LIMMA package.

This function doesn't have an internal method to add loess lines. 
However, it isn't difficult to do so.

If you specifically want a loess line, you can do

plotMA(MAobj)
lines(predict(loess(MAobj$M~MAobj$A)))

you might need to play with the span and degree arguments to get a 
smoother line. Although the loess() function is recommended over the 
lowess() function, I actually prefer the results from lowess().

lines(lowess(MAobj$M~MAobj$A))

Best,

Jim


> Thank you
> 
> Erika
> 
> -----Messaggio originale-----
> Da: James W. MacDonald [mailto:jmacdon at med.umich.edu] 
> Inviato: lunedì 3 maggio 2010 21:13
> A: Erika Melissari
> Cc: bioconductor at stat.math.ethz.ch
> Oggetto: Re: [BioC] visualization of Loess smoothing curve
> 
> Hi Erika,
> 
> Erika Melissari wrote:
>> Dear Bioconductor list,
>>
>>  
>>
>> is there any possibility to overlap the loess smoothing curve of  an MA
>> object  visualized by an MAplot?
> 
> Well, that's not much to go on, now is it? If I start making 
> assumptions, that a) you are talking about a specific function called 
> MAplot(), and b) that you are talking about the particular function 
> called MAplot() that resides in the affy package, then the answer is yes.
> 
> ?MAplot
> 
> Best,
> 
> Jim
> 
> 
>>  
>>
>> Thank you
>>
>>  
>>
>> Erika
>>
>>
>> 	[[alternative HTML version deleted]]
>>
>> _______________________________________________
>> 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
Douglas Lab
University of Michigan
Department of Human Genetics
5912 Buhl
1241 E. Catherine St.
Ann Arbor MI 48109-5618
734-615-7826
**********************************************************
Electronic Mail is not secure, may not be read every day, and should not be used for urgent or sensitive issues