Error in R package "cancerclass" with function nvalidate
0
0
Entering edit mode
svlachavas ▴ 830
@svlachavas-7225
Last seen 6 months ago
Germany/Heidelberg/German Cancer Resear…

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 ?

 

 

cancerclass bioconductor machinelearning classification • 1.4k views
ADD COMMENT

Login before adding your answer.

Traffic: 1011 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6