Childhood Cancer Study of Khan et al. (2001)
Gene expression data (2308 genes for 88 samples) from the microarray study of Khan et al. (2001).
data(khan2001)
khan2001$x is a 88 x 2308 matrix containing the expression levels. Note that
rows correspond to samples, and columns to genes. The row names are the original
image IDs, and the column names the orginal probe labels.
khan2001$y is a factor containing the diagnosis for each sample ("BL", "EWS", "NB", "non-SRBCT", "RMS").
khan2001$descr provides some annotation for each gene.
This data set contains measurements of the gene expression of 2308 genes for 88 observations: 29 cases of Ewing sarcoma (EWS), 11 cases of Burkitt lymphoma (BL), 18 cases of neuroblastoma (NB), 25 cases of rhabdomyosarcoma (RMS), and 5 other (non-SRBCT) samples.
The data are described in Khan et al. (2001). Note that the values in
khan.data$x are logarithmized (using natural log) for normalization.
Khan et al. 2001. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature Medicine 7:673–679.
# load sda library
library("sda")
# load full Khan et al (2001) data set
data(khan2001)
dim(khan2001$x) # 88 2308
hist(khan2001$x)
khan2001$y # 5 levels
# data set containing the SRBCT samples
get.srbct = function()
{
data(khan2001)
idx = which( khan2001$y == "non-SRBCT" )
x = khan2001$x[-idx,]
y = factor(khan2001$y[-idx])
descr = khan2001$descr[-idx]
list(x=x, y=y, descr=descr)
}
srbct = get.srbct()
dim(srbct$x) # 83 2308
hist(srbct$x)
srbct$y # 4 levelsPlease choose more modern alternatives, such as Google Chrome or Mozilla Firefox.