Entering edit mode
Dear List Members,
I use Mfuzz package. I've successfully clustered two data sets.
I wanted to cluster third data set (very similar to those two)
and I encountered following error in both cselection and partcoef:
> roznice=read.table("allstop",header=T,row.names=1,sep="\t")
> rozn_set=new("ExpressionSet",exprs=as.matrix(roznice))
> dim(roznSR)
Features Samples
902 7
> class(rozn_set)
[1] "ExpressionSet"
attr(,"package")
[1] "Biobase"
> roznS=standardise(rozn_set)
> roznSR=randomise(roznS)
x=cselection(roznSR,m=1.25,crange=seq(4,40,1),repeats=5,visu=T)
Error in cmeans(exprs(eset), centers = centers, method = "cmeans", m =
m, :
NA/NaN/Inf in foreign function call (arg 1)
> traceback()
4: .C("cmeans", as.double(x), as.integer(xrows), as.integer(xcols),
centers = as.double(centers), as.integer(ncenters),
as.double(weights),
as.double(m), as.integer(dist - 1), as.integer(iter.max),
as.double(reltol), as.integer(verbose), u = double(xrows *
ncenters), ermin = double(1), iter = integer(1), PACKAGE =
"e1071")
3: cmeans(exprs(eset), centers = centers, method = "cmeans", m = m,
...)
2: mfuzz(eset, centers = c, m = m)
1: cselection(roznSR, m = 1.25, crange = seq(4, 40, 1), repeats = 5,
visu = T)
> partcoef(roznSR, crange=seq(4,40,1),mrange=seq(1.25,3,0.05))
Error in cmeans(exprs(eset), centers = centers, method = "cmeans", m =
m, :
NA/NaN/Inf in foreign function call (arg 1)
> traceback()
4: .C("cmeans", as.double(x), as.integer(xrows), as.integer(xcols),
centers = as.double(centers), as.integer(ncenters),
as.double(weights),
as.double(m), as.integer(dist - 1), as.integer(iter.max),
as.double(reltol), as.integer(verbose), u = double(xrows *
ncenters), ermin = double(1), iter = integer(1), PACKAGE =
"e1071")
3: cmeans(exprs(eset), centers = centers, method = "cmeans", m = m,
...)
2: mfuzz(eset, centers = c, m = m, ...)
1: partcoef(roznSR, crange = seq(4, 40, 1), mrange = seq(1.25, 3,
0.05))
> sessionInfo()
R version 2.11.1 (2010-05-31)
i686-pc-linux-gnu
locale:
[1] LC_CTYPE=pl_PL.UTF-8 LC_NUMERIC=C
[3] LC_TIME=pl_PL.UTF-8 LC_COLLATE=pl_PL.UTF-8
[5] LC_MONETARY=C LC_MESSAGES=pl_PL.UTF-8
[7] LC_PAPER=pl_PL.UTF-8 LC_NAME=C
[9] LC_ADDRESS=C LC_TELEPHONE=C
[11] LC_MEASUREMENT=pl_PL.UTF-8 LC_IDENTIFICATION=C
attached base packages:
[1] tcltk stats graphics grDevices utils datasets
methods
[8] base
other attached packages:
[1] Mfuzz_2.6.0 DynDoc_1.26.0 widgetTools_1.26.0
e1071_1.5-25
[5] class_7.3-2 Biobase_2.8.0
loaded via a namespace (and not attached):
[1] tkWidgets_1.26.0
I suppose that it's problem with my imput data, but it's organised in
the
same manner as other datasets, for which no error occured.
I'd checked this data for missing values but there aren't any. It's
looks ok.
Thanks,
Maciej Jo?czyk, MSc
Department of Plant Molecular Ecophysiology
Institute of Plant Experimental Biology
Faculty of Biology, University of Warsaw
02-096 Warszawa, Miecznikowa 1
___________________________________
NOCC, http://nocc.sourceforge.net
--
This email was Anti Virus checked by Astaro Security Gateway.
http://www.astaro.com
Hi! I've tried but can't do it solve this problem. I have a matrix with genes (col = 1) and expression values (col = 2, 3 and 4). I try to use the soft clustering library Mfuzz, but an error in cmeans don't let me plot the clusters. Anyone to give me a hand, please?
Thanks!
You can have this problem (lines with variance equal to zero) when you run experiments and obtain the data with more samples and use fewer (for example 3 initial treatments, and use only two in the analysis). When you don't use some samples, you run the risk of some gene/protein only being detected in the samples you didn't use. So, if you replace the NA with the mean, or with an extremely low value (which is what I think is most correct), all the samples in the line for that gene will have the same value as the one that replaced the NA, generating a variance equal to zero. Perhaps filtering the data, looking for equal values in the repetitions, or variance equal to zero will allow you to obtain the analysis/figure. I hope I've helped.