I'm ccing Aedin (package author) in case she hasn't seen this. Valerie On 04/28/12 21:07, Barbara Shih wrote: > Dear all, > I am wondering how I should label the quadrants in the coa plot generated by made4 package (see figure 3, top right in http://www.bioc onductor.org/packages/2.9/bioc/vignettes/made4/inst/doc/introduction.p df ). Also, what does the "d" value on the top right hand corner mean? > > Thank you very much for your help > > Barbara > > [[alternative HTML version deleted]] > > _______________________________________________ > 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

Dear Barbara and Valerie Thanks for forward this to me Valerie, I had missed it in my Bioc daily digest ;-) The d indicates the scale of the grid squares on the plot For example # Load some test data and perform a correspondence analysis require(made4) data(khan) khan.coa<-ord(khan$train, classvec=khan$train.classes, type="coa", ord.nf=5) plotgenes(khan.coa) #This is the same as plotgenes(khan.coa$ord$li, axis1=1,axis2=2) #Now lets look at this in more detail. The correspondence analysis results are in $ord, and # the coordinates for the axis (eigenvectors/principal components) are in $ord$li and $ord$co # where li are the lines (rows) and co are the columns. So if we want to examine the genes in more detail, these are in the rows # so we look at $ord$li # Note if we scale the data, d changes in the plot to reflect the scale par(mfrow=c(2,2)) plotgenes(khan.coa$ord$li, axis1=1,axis2=2) plotgenes(khan.coa$ord$li*10, axis1=1,axis2=2) plotgenes(khan.coa$ord$li*100, axis1=1,axis2=2) plotgenes(khan.coa$ord$li/100, axis1=1,axis2=2) Hope this helps, please let me know if you have any further questions Regards Aedin > > On 04/28/12 21:07, Barbara Shih wrote: >> Dear all, >> I am wondering how I should label the quadrants in the coa plot >> generated by made4 package (see figure 3, top right in >> http://www.bioconductor.org/packages/2.9/bioc/vignettes/made4/inst/ doc/introduction.pdf >> ). Also, what does the "d" value on the top right hand corner mean? >> >> Thank you very much for your help >> >> Barbara >> >> [[alternative HTML version deleted]] >> >> _______________________________________________ >> 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 > -- Aedin Culhane Computational Biology and Functional Genomics Laboratory Harvard School of Public Health, Dana-Farber Cancer Institute web: http://www.hsph.harvard.edu/research/aedin-culhane/ email: aedin at jimmy.harvard.edu phone: +1 617 632 2468 Fax: +1 617 582 7760 Mailing Address: Attn: Aedin Culhane, SM822C 450 Brookline Ave. Boston, MA 02215