[BioC] Segmentation Demo - problem in normalization

[Krys Kelly]

Hi Wolfgang,

I'm sorry I did not include specific information. I have attached my code.
Below is the output from my terminal session, including the output from
SessionInfo() at the end. I just downloaded a new version of R and all these
packages last week, so they should be up-to-date (but maybe I missed
something, or introduced an error in the code).

Thanks for looking at this for me.

Best wishes

Krys

> source("C:/Documents and Settings/Krys/Desktop/Segmentation demo/Stuff for
Wolfgang/SegmentationDemoCode.R")
Loading required package: Biobase
Loading required package: tools

Welcome to Bioconductor

    Vignettes contain introductory material. To view, type
    'openVignette()' or start with 'help(Biobase)'. For details
    on reading vignettes, see the openVignette help page.

Loading required package: affy
Loading required package: affyio
Loading required package: RColorBrewer
Loading required package: grid
Loading required package: strucchange
Loading required package: zoo
Loading required package: sandwich
Loading required package: colorspace

Attaching package: 'colorspace'


        The following object(s) are masked from package:grDevices :

         hcl 

Loading required package: vsn
Loading required package: genefilter
Loading required package: survival
Loading required package: splines
Loading required package: geneplotter
Loading required package: annotate
KernSmooth 2.22 installed
Copyright M. P. Wand 1997
Loading required package: GO
Error in vsn(xn, lts.quantile = 0.95, subsample = 2e+05, verbose = verbose)
: 
        
The likelihood optimization did not converge. A likely reason is that the
normalization parameters are not uniquely identifiable from the provided
data.
Possibly, the columns of the data matrix are exactly co-linear or affine
dependent - please verify the data to make sure there were no mix-ups.
> session.info()
Error: could not find function "session.info"
> sessionInfo()
Version 2.3.1 (2006-06-01) 
i386-pc-mingw32 

attached base packages:
 [1] "splines"   "grid"      "tools"     "methods"   "stats"     "graphics" 
 [7] "grDevices" "utils"     "datasets"  "base"     

other attached packages:
 davidTiling           GO  tilingArray  geneplotter     annotate
genefilter 
     "1.0.4"     "1.12.0"     "1.10.0"     "1.10.0"     "1.10.0"
"1.10.1" 
    survival          vsn   colorspace  strucchange     sandwich
zoo 
      "2.28"     "1.10.0"        "0.9"      "1.3-0"      "2.0-0"
"1.2-0" 
RColorBrewer         affy       affyio      Biobase 
     "0.2-3"     "1.10.0"      "1.0.0"     "1.10.1" 
>

 
Dr Krystyna A Kelly
University of Cambridge
Department of Pathology
Molteno Building, Tennis Court Road
Cambridge CB2 1QP
Tel:    01223 333331
Email: kak28 at cam.ac.uk
 

-----Original Message-----
From: Wolfgang Huber [mailto:huber at ebi.ac.uk] 
Sent: 13 September 2006 10:46
To: Krys Kelly
Cc: bioconductor at stat.math.ethz.ch
Subject: Re: [BioC] Segmentation Demo - problem in normalization

Dear Krys,

please can you provide

1. a script that allows us to reproduce the error condition you get, and
2. the output of sessionInfo()

Otherwise I am afraid your question is too unspecific to do anything
about it.

 Best wishes
 Wolfgang



Krys Kelly wrote:
> I am trying to run the Segmentation Demo. I have been cutting and pasting
> the commands from the Segmentation Demo document. 
> 
> I get an error during the normalization.  When I run this command:
> 
> xn = normalizeByReference(davidTiling[, isRNA], davidTiling[, isDNA], pm =
> PMind, background = isbg)
> 
> I get the following error message:
> 
> The likelihood optimization did not converge. A likely reason is that the
> normalization parameters are not uniquely identifiable from the provided
> data.
> Possibly, the columns of the data matrix are exactly co-linear or affine
> dependent - please verify the data to make sure there were no mix-ups.
> 
> Please can you help.
> 
> Thanks
> 
> Krys
> 
> 
> Dr Krystyna A Kelly
> University of Cambridge
> Department of Pathology
> Molteno Building, Tennis Court Road
> Cambridge CB2 1QP
> Tel:    01223 333331
> Email: kak28 at cam.ac.uk
> 
> _______________________________________________
> 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


-- 
------------------------------------------------------------------
Wolfgang Huber  EBI/EMBL  Cambridge UK  http://www.ebi.ac.uk/huber