Skip to main content

Table 11 Colon cancer data set

From: Identification of differentially expressed genes by means of outlier detection

  

Ns

  

12

49

59

I

ORdensity (A)

88.71

90.32

90.32

 

limma (B)

91.94

88.71

88.71

 

SAM (C)

85.48

88.71

88.71

II

A vs B

7

32

38

 

A vs C

0

14

22

 

B vs C

2

26

29

III

ORdensity

7.5 (1.27)

35.4 (4.09)

43.0 (3.56)

 

limma

0.1 (0.32)

3.5 (0.85)

4.1 (0.57)

 

SAM

1.8 (1.14)

23.7 (2.98)

29.4 (3.57)

  

Ns

  

166

186

366

I

ORdensity (A)

87.10

87.10

-

 

limma (B)

87.10

87.10

87.10

 

SAM (C)

87.10

-

-

II

A vs B

119

134

-

 

A vs C

118

-

-

 

B vs C

155

-

-

III

ORdensity

127.2 (4.49)

142.5 (4.84)

-

 

limma

13.1 (1.37)

16.7 (2.21)

72.1 (4.72)

 

SAM

136.7 (5.23)

-

-

  1. Results for different number (Ns) of selected genes: 12 with ORdensity strong selection; 49 with limma and Bonferroni; 59 with ORdensity relaxed selection; 166 with SAM; 186 total potential DE genes and 366 with limma and BH. Rows I present the leave-one-out cross-validation correct classification rate. In bold, the results for the genes selected under standard criteria for ORdensity, limma and SAM procedures; in rows II, number of common selected genes between the ORdensity, limma and SAM approaches. In rows III, mean and standard deviation (in brackets) of the number of genes that for 10 subsamples were always kept selected