[BioC] about two way anova on time and treatment

[Ana Conesa]

Hi James,

You might like to have a look to a paper we recently published where
we address this problem
(http://bioinformatics.oxfordjournals.org/cgi/reprint/btm251v1). We
describe here the ASCA-genes methodology to analyze multiple series
time course microarray data. Basically, first ANOVA is applied to
each gene and then perform PCA for each of the matrix coffecients of
the ANOVA model. We use then PCA scores to discover main expression
patterns associated to each experimental factor and we propose aswell
a gene-selection criterium. You also obtain the % variability
associated to each experimental factor (and noise) so you can use
this to unswer your question of the factor (time or treatment) with
the highest effect. R scripts with the algorithm are avialable.

Best regards

Ana

----------------------------------------
Ana Conesa, PhD
Bioinformatics Department
Centro de Investigacion Principe Felipe
Avd. Saler 16, 46013 Valencia (Spain)
http://bioinfo.cipf.es
----------------------------------------
========================================
CAMDA 2007 Conference in Valencia, 
13-14 December 2007
http://camda.bioinfo.cipf.es
========================================




>
>
>---- Mensaje Original ----
>De: janderson_net at yahoo.com
>Para: bioconductor at stat.math.ethz.ch
>Asunto: RE: [BioC] about two way anova on time and treatment
>Fecha: Fri, 29 Jun 2007 13:56:22 -0700 (PDT)
>
>>Hi, 
>>
>>I have affy data for time and treatment, I did a two way anova for
>each gene. What's the correct way to evaluate whether time effect is
>more imporant or treatment effect is more important? I think
>averaging the variance component of each gene is not a very good way,
>since not all genes are equally important, in addition, most of the
>genes are noisy genes. I am thinking of doing a PCA and take the
>first several components, instead of doing anova on each gene, I can
>do two way anova on the scores of the first several component, then I
>can use a weighted average (weight is determined by the amount of
>variance each PC captured), is this a good way? Can somebody give me
>some suggestions on this? Thanks. 
>>
>>James
>>
>>       
>>---------------------------------
>>Luggage? GPS? Comic books? 
>>
>>	[[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.inf
>ormatics.conductor
>>