[R] pvclust Error:NA/NaN/Inf in foreign function call (arg 11)

[Richard Birnie]

Hi all,

I'm new to R and I'm struggling to decipher an error message. Briefly, I am trying to use the pvclust package to do hierarchical clustering of some CGH data. The data is from the Progenetix CGH database. It is arranged as a table where each column is a single case and each row is a single chromosome band. The value in each cell is either 0, 1, 2, or -1. Corresponding to no change, gain, high level amplification, or loss respectively Based on the documentation for the pvclust package I came up with this code.

>ProgenetixCRC.all.pvclust <- pvclust(ProgenetixCRC.all, method.dist="cor", method.hclust="average",use.cor="pairwise.complete.obs",nboot=1000)

this results in the following error

Bootstrap (r = 0.5)... Error in hclust(distance, method = method.hclust) : 
	NA/NaN/Inf in foreign function call (arg 11)
In addition: Warning message:
the standard deviation is zero in: cor(x, y, na.method, method == "kendall"

I'm not really clear on what this means. I have searched the mailing list archive and as best I can tell this is caused by missing values in the dataset. This is confusing because my dataset does not have any missing values. The only thing I can think of is that the function is treating 0 as a missing value. Is this the case and if so what is the best way to handle this? 

I also found something about using 'traceback()' to trace failed function calls, so I tried that, the output means little to me but here it is.

>traceback()
4: hclust(distance, method = method.hclust)
3: FUN(X[[1]], ...)
2: lapply(r, boot.hclust, data = data, object.hclust = data.hclust, 
       nboot = nboot, method.dist = method.dist, use.cor = use.cor, 
       method.hclust = method.hclust, store = store)
1: pvclust(ProgenetixCRC.all, method.dist = "cor", method.hclust = "average", 
       use.cor = "pairwise.complete.obs", nboot = 1000)

and my session info
> sessionInfo()
R version 2.2.1, 2005-12-20, i686-redhat-linux-gnu 

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

other attached packages:
pvclust 
"1.1-0" 

Can someone please advise how to handle this. If any more info is needed just tell me what commands.
regards,
Richard
Dr Richard Birnie
Scientific Officer
Section of Pathology and Tumour Biology
Welcome Brenner Building, LIMM
St James University Hospital
Beckett St, Leeds, LS9 7TF
Tel:0113 3438624
e-mail: r.birnie at leeds.ac.uk