Hi to all, I'm new using R and CMA. I want to create some classifiers/biomarker from peach microarray data using using the different classification methods implemented in CMA. My problem is that I don't kown how to prepare data and introduce class labels given all examples are based in the prepared dataset golub, but no in a raw gene expression matrix. My goal is to create classifiers based in genotypes and the observed phenotypes. I have a gene expression matrix with 3533 genes (rows) and 48 microarrays corresponding to 16 samples (replicates each). Out of them 8 are from a sensitive and 8 from a tolerant cultivars. Samples are taken at harvest and ripe and two different treatments (3 points each). Please can somebody tell me wich commands I should type to define labels? Thanks a lot in advance Clara

This is actually the sort of situation where you might be better off with limma, since the tools for dealing with technical replicates in a nested factorial design (cultivar*resistance) are much better documented in the Limma user's guide. CMA, in my experience, excels at one-way classification problems, but it sounds like you are looking to model which genes change expression according to cultivar, which change according to resistance, and which change as a function of both. Using lmFit() and eBayes() then ranking the top results for each factor might be a more fruitful approach than shoehorning your problem into CMA. But, that's just my opinion, based on my understanding of your experiment. --t On Fri, Jun 24, 2011 at 3:03 AM, Clara Pons <cpons@upvnet.upv.es> wrote: > Hi to all, > I'm new using R and CMA. I want to create some classifiers/biomarker from > peach microarray data using using the different classification methods > implemented in CMA. My problem is that I don't kown how to prepare data and > introduce class labels given all examples are based in the prepared dataset > golub, but no in a raw gene expression matrix. > My goal is to create classifiers based in genotypes and the observed > phenotypes. I have a gene expression matrix with 3533 genes (rows) and 48 > microarrays corresponding to 16 samples (replicates each). Out of them 8 are > from a sensitive and 8 from a tolerant cultivars. Samples are taken at > harvest and ripe and two different treatments (3 points each). > Please can somebody tell me wich commands I should type to define labels? > > Thanks a lot in advance > > Clara > > ______________________________**_________________ > Bioconductor mailing list > Bioconductor@r-project.org > https://stat.ethz.ch/mailman/**listinfo/bioconductor<https: stat.et="" hz.ch="" mailman="" listinfo="" bioconductor=""> > Search the archives: http://news.gmane.org/gmane.** > science.biology.informatics.**conductor<http: news.gmane.org="" gmane.="" science.biology.informatics.conductor=""> > -- If people do not believe that mathematics is simple, it is only because they do not realize how complicated life is. John von Neumann<http: www-groups.dcs.st-="" and.ac.uk="" ~history="" biographies="" von_neumann.html=""> [[alternative HTML version deleted]]