Gene expression data from Khan et al. (2001)

Share:

Description

Gene expression data (2308 genes for 83 samples) from the microarray experiments of Small Round Blue Cell Tumors (SRBCT) of childhood cancer study of Khan et al. (2001).

Usage

1

Details

This data set contains 83 samples with 2308 genes: 29 cases of Ewing sarcoma (EWS), coded 1, 11 cases of Burkitt lymphoma (BL), coded 2, 18 cases of neuroblastoma (NB), coded 3, 25 cases of rhabdomyosarcoma (RMS), coded 4. A total of 63 training samples and 25 test samples are provided in Khan et al. (2001). Five of the test set are non-SRBCT and are not considered here. The training sample indexes correspond to 1:65 and the test sample indexes (without non-SRBCT sample) correspond to 66:83.

Value

A list with the following elements:

X

a (88 x 2308) matrix giving the expression levels of 2308 genes for 88 SRBCT patients. Each row corresponds to a patient, each column to a gene.

Y

a numeric vector of length 88 giving the cancer class of each patient.

gene.names

a matrix containing the names of the 2308 genes for the gene expression matrix X. The two columns correspond to the gene 'Image.Id.' and 'Gene.Description', respectively.

Source

The data are described in Khan et al. (2001) and can be freely downloaded from http://research.nhgri.nih.gov/microarray/Supplement/.

References

Khan, J. and Wei, J. S. and Ringner, M. and Saal, L. H. and Ladanyi, M. and Westermann, F. and Berthold, F. and Schwab, M. and Antonescu, C. R. and Peterson, C. and Meltzer, P. S. (2001). Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks, Nature Medecine, 7, 673–679.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
# load plsgenomics library
library(plsgenomics)

# load data set
data(SRBCT)

# how many samples and how many genes ?
dim(SRBCT$X)

# how many samples of class 1, 2, 3 and 4, respectively ?
sum(SRBCT$Y==1)
sum(SRBCT$Y==2)
sum(SRBCT$Y==3)
sum(SRBCT$Y==4)

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.