Dear ALL,
i tried to implement the R package "cancerclass" with a microarray colon cancer dataset to evaluate and create possible predictors in order to classify cancer vs control samples, as described in the vignette. My pData(ExpressionSet) is the below:
pData(data.trusted.eset)
condition Meta_factor
7_Tesch.CEL Normal 0
8_Tesch.CEL Cancer 0
0687_04_Blauth.CEL Normal 0
0687_04_Blauth_1.CEL Cancer 0
0863_03_Schmidt.CEL Normal 0
0863_03_Schmidt_1.CEL Cancer 0
0948_04_Leiber.CEL Normal 0
0948_04_Leiber_1.CEL Cancer 0
1043_04_Nagel.CEL Normal 0
1043_04_Nagel_1.CEL Cancer 0
1103_03_Braun.CEL Normal 1
1103_03_Braun_1.CEL Cancer 1
1234_06_Floersch.CEL Normal 0
1234_06_Floersch_1.CEL Cancer 0
1235_06_Hey.CEL Normal 0
1235_06_Hey_1.CEL Cancer 0
1236_06_Liebich.CEL Normal 1
1236_06_Liebich_1.CEL Cancer 1
1410_03_Urbaniak.CEL Normal 1
1410_03_Urbaniak_1.CEL Cancer 1
1430_04_Patschke.CEL Normal 0
1430_04_Patschke_1.CEL Cancer 0
1518_03_Dege.CEL Normal 0
1518_03_Dege_1.CEL Cancer 0
1554_03_Gemmer.CEL Normal 1
1554_03_Gemmer_1.CEL Cancer 1
However, when i use the function
gene.validation <- nvalidate(data.trusted.eset,class=pData(data.trusted.eset)[1], ngenes=c(5, 10, 20, 50, 100, 200), method="wilcoxon.test")
it gives me the following error:
WARNING: class is not defined for all samples!
Removing 26 samples from the data set.
WARNING: Data set contains missing genes!
Removing 7904 genes from the data set.
Error in .subset(x, j) : invalid subscript type 'list'
In addition: Warning message:
In is.na(pData(eset)[[class]]) :
is.na() applied to non-(list or vector) of type 'NULL'
i also tried different inputs for argument "class", but nothing happens and the same error appears !!
Any help or suggestions ?