gencve (version 0.3)

SinghTest: Singh Prostate Microarray Test Data

Description

Microarray data for 25 prostate tumors and 9 nontumors from patients undergoing surgery.

Usage

data("SinghTest")

Format

A data frame with 102 observations on the following 101 variables.

gene1

a numeric vector

gene2

a numeric vector

gene3

a numeric vector

gene4

a numeric vector

gene5

a numeric vector

gene6

a numeric vector

gene7

a numeric vector

gene8

a numeric vector

gene9

a numeric vector

gene10

a numeric vector

gene11

a numeric vector

gene12

a numeric vector

gene13

a numeric vector

gene14

a numeric vector

gene15

a numeric vector

gene16

a numeric vector

gene17

a numeric vector

gene18

a numeric vector

gene19

a numeric vector

gene20

a numeric vector

gene21

a numeric vector

gene22

a numeric vector

gene23

a numeric vector

gene24

a numeric vector

gene25

a numeric vector

gene26

a numeric vector

gene27

a numeric vector

gene28

a numeric vector

gene29

a numeric vector

gene30

a numeric vector

gene31

a numeric vector

gene32

a numeric vector

gene33

a numeric vector

gene34

a numeric vector

gene35

a numeric vector

gene36

a numeric vector

gene37

a numeric vector

gene38

a numeric vector

gene39

a numeric vector

gene40

a numeric vector

gene41

a numeric vector

gene42

a numeric vector

gene43

a numeric vector

gene44

a numeric vector

gene45

a numeric vector

gene46

a numeric vector

gene47

a numeric vector

gene48

a numeric vector

gene49

a numeric vector

gene50

a numeric vector

gene51

a numeric vector

gene52

a numeric vector

gene53

a numeric vector

gene54

a numeric vector

gene55

a numeric vector

gene56

a numeric vector

gene57

a numeric vector

gene58

a numeric vector

gene59

a numeric vector

gene60

a numeric vector

gene61

a numeric vector

gene62

a numeric vector

gene63

a numeric vector

gene64

a numeric vector

gene65

a numeric vector

gene66

a numeric vector

gene67

a numeric vector

gene68

a numeric vector

gene69

a numeric vector

gene70

a numeric vector

gene71

a numeric vector

gene72

a numeric vector

gene73

a numeric vector

gene74

a numeric vector

gene75

a numeric vector

gene76

a numeric vector

gene77

a numeric vector

gene78

a numeric vector

gene79

a numeric vector

gene80

a numeric vector

gene81

a numeric vector

gene82

a numeric vector

gene83

a numeric vector

gene84

a numeric vector

gene85

a numeric vector

gene86

a numeric vector

gene87

a numeric vector

gene88

a numeric vector

gene89

a numeric vector

gene90

a numeric vector

gene91

a numeric vector

gene92

a numeric vector

gene93

a numeric vector

gene94

a numeric vector

gene95

a numeric vector

gene96

a numeric vector

gene97

a numeric vector

gene98

a numeric vector

gene99

a numeric vector

gene100

a numeric vector

health

a factor with levels normal tumor

Source

Nathalie Pochet, Frank De Smet, Johan A.K. Suykens and Bart L.R. De Moor (2004). Systematic benchmarking of microarray data classification: assessing the role of nonlinearity and dimensionality reduction. Bioinformatics Advance Access published July 1, 2004.

Details

The data have been standardized by patient. The best 100 genes out of 12600 genes in the original have been selected. Pochet et al. (2004) suggested this test dataset. It was also mentioned in Speed's book.

References

Terry Speed

See Also

featureSelect, churnTrain

Examples

require("MASS")
data(SinghTest)
BestGenes <- 10
XTr <- SinghTrain[,1:BestGenes]
yTr <- SinghTrain$health
ans <- lda(x=XTr, grouping=yTr)
XTe <- SinghTest[,1:BestGenes]
yH <- predict(ans, newdata=XTe)$class
yTe <- SinghTest$health
table(yTe, yH)