Hello I've three stupid questions. I work with Microarrays and use the affy package to analyse cel Files. I'm not very familiar with R. Here are my questions: 1. If I use the expresso(w=T) ,there is a error: Error in normalize(listcel.n,cdf,method=normalize.method,...): object "listcel.n" not found What is the reason that there is the error? 2. I don't know how I can install the rhdf5 package, respectively how to install the hdf5, which I have downloaded. Must I set a path or so in R? 3. If I want to summary my expression with the normalisation method from li and wong there is a error: Error in density (x, kernel="epanechnikov", n=n.pts): x contains missing values I don't know how to work with the invariantset method because I can't work with this normalized data. With best regards Tanja Hölter Dipl. Statistikerin Tanja Hölter Institut für Medizinische Informatik, Biometrie und Epidemiologie Universitätsklinikum Essen D-45122 Essen Tel:(49)201-723-4654 FAX: (49)201-723-5933

> 2. I don't know how I can install the rhdf5 package, respectively how to > install the hdf5, which I have downloaded. Must I set a path or so in > R? You most likely need to install the HDF5 library. See: http://hdf.ncsa.uiuc.edu/HDF5/ -J

On Thu, Aug 22, 2002 at 01:54:38PM +0200, "Hölter, Tanja" wrote: > Hello I've three stupid questions. I work with Microarrays and use the > affy package to analyse cel Files. I'm not very familiar with R. Here > are my questions: All of your questions are sensible. > > 1. If I use the expresso(w=T) ,there is a error: > Error in normalize(listcel.n,cdf,method=normalize.method,...): > object "listcel.n" not found > What is the reason that there is the error? Uh, uh... this question is not stupid... it means that something is wrong (my settings here are a bit complex, and it happens more than it should that a file that should be transfered to the bioconductor server slips out of the net)... (it should be on the website on Monday... (I can mail you the package if urgent needs))... (note: you are using the 'devel' version of the package... the stability goes through various stages. sorry for the inconvenience) > > 2. I don't know how I can install the rhdf5 package, respectively how to > install the hdf5, which I have downloaded. Must I set a path or so in > R? If you use linux, you may prefer a package made for your distribution (like rpm)... > > 3. If I want to summary my expression with the normalisation method from > li and wong there is a error: > Error in density (x, kernel="epanechnikov", n=n.pts): > x contains missing values > (?!) I do not remember kernel density estimation being used in li-wong... I think kernel density estimation is used for background correction (method "rma" or "bg.correct.rma")... > I don't know how to work with the invariantset method because I can't > work with this normalized data. > ...could you detail what happens ? Regards, Laurent > > > With best regards > Tanja Hölter > > > Dipl. Statistikerin Tanja Hölter > Institut für Medizinische Informatik, > Biometrie und Epidemiologie > Universitätsklinikum Essen > D-45122 Essen > Tel:(49)201-723-4654 > FAX: (49)201-723-5933 > > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor -- -------------------------------------------------------------- Laurent Gautier CBS, Building 208, DTU PhD. Student DK-2800 Lyngby,Denmark tel: +45 45 25 24 89 http://www.cbs.dtu.dk/laurent