[BioC] Adaptive background correction error
smyth at wehi.edu.au
Wed Apr 6 01:00:53 CEST 2005
>Date: Mon, 04 Apr 2005 12:10:48 +0200
>From: Anja Schiel <a.e.schiel at lumc.nl>
>Subject: [BioC] Adaptive background correction error
>To: bioconductor at stat.math.ethz.ch
>I tried to use the adaptive background correction for a set of 22 arrays
>(2 colour). For array no 17 I get the following error
>RGb<-backgroundCorrect(RG, method="normexp", offset=50)
>Error in fit.normexp(foreground = RG$R[, j], background = RG$Rb[, j]) :
> optim failure: degeneracy of the Nelder-Mead simplex
>There is nothing obviously wrong with that array so is it the array
>that's causing the problem or something else?
Adaptive background correction requires an iterative algorithm to estimate
the background, and this algorithm sometimes fails. It is unlikely to be a
problem with your data. This problem has been discussed before on this
mailing list -- search the archives for "normexp".
Newer versions of limma use a different iterative algorithm to estimate the
"normexp" background. Try upgrading and see if the new version works for you:
>And what is the Nelder-Mead simplex????
The online help tells you that the Nelder-Mead simplex algorithm is being
used for the optimization -- follow the link which says "for more details
see fit.normexp". You do not need to know the details of the algorithm.
>I am running R 2.0.1 + Bioconductor under Debian testing and limma
>Anja E. Schiel, Ph.D.
>Departments of General Internal Medicine and Human Genetics
>Leiden University Medical Center
>PO Box 9503
>2300 RA Leiden
More information about the Bioconductor