Hei, I am using MaSigPro to analyze different sets of genes. Amongst the outputs provided in MaSigPro is R-sq, for each fitted gene . Is there a way to combine the significant genes in a single model and obtain a single measure of the variance explained, R-sq (adj), using all the genes. My main aim is to be able to compare different genesets, and if possible rank them in order of variance explained by each geneset. Maybe this is already provided for in the package, but I haven't been able to figure it out. Are there any other packages in Bioconductor that might be useful for this purpose. Thanks Narinder S. Sahni Narinder Singh Sahni Associate Professor School of Information Technology Jawaharlal Nehru University New Delhi - 110067 India Ph: +91-11-26704173 Fax: +91-11-26717586

Hello, We have an adaptation of maSigPro that applies the method to groups of genes classified in similar categories. If you are interested in applying this adaptation we can send you the script . But if you apply the method to heterogeneous groups, the fitted model is not going to be a good fit. Each gene can have its own profile and obtaining a good model for significant, but different genes can be impossible. If you are interested in applying this adaptation, let me know and we will send you. Kind regards. Mar?a. ----- Original Message ----- From: "Narinder Singh Sahni" <narinder@mail.jnu.ac.in> To: <bioconductor at="" stat.math.ethz.ch=""> Sent: Friday, October 26, 2007 10:47 AM Subject: [BioC] MaSigPro > Hei, > > I am using MaSigPro to analyze different sets of genes. > Amongst the outputs provided in MaSigPro is R-sq, for each fitted gene . > > Is there a way to combine the significant genes in > a single model and obtain a single measure of the variance explained, R-sq (adj), > using all the genes. My main aim is to be able to compare different genesets, and > if possible rank them in order of variance explained by each geneset. > > Maybe this is already provided for in the package, but I haven't been able to figure it out. > Are there any other packages in Bioconductor that might be useful for this purpose. > > Thanks > > Narinder S. Sahni > > Narinder Singh Sahni > Associate Professor > School of Information Technology > Jawaharlal Nehru University > New Delhi - 110067 > India > Ph: +91-11-26704173 > Fax: +91-11-26717586 > > _______________________________________________ > 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