Skip to main content

Table 12 Prostate cancer data set

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

  

Ns

  

131

263

990

I

ORdensity (A)

75.49

74.51

70.59

 

limma (B)

86.27

82.35

71.57

 

SAM (C)

82.35

76.47

70.59

II

A vs B

64

170

691

 

A vs C

64

159

746

 

B vs C

54

211

791

III

ORdensity

72.4 (7.12)

184.1 (23.56)

787.6 (29.40)

 

limma

108.6 (4.99)

220.2 (10.07)

827.2 (39.17)

 

SAM

0.7 (0.67)

4.4 (0.84)

66.1 (4.38)

  

Ns

  

1531

2684

3322

I

ORdensity (A)

66.67

-

-

 

limma (B)

70.59

68.63

-

 

SAM (C)

70.59

66.67

65.69

II

A vs B

961

-

-

 

A vs C

1035

-

-

 

B vs C

1321

2422

-

III

ORdensity

1215.4 (99.66)

-

-

 

limma

1297.9 (50.64)

2299.5 (86.19)

-

 

SAM

165.1 (6.15)

563 (19.87)

862.2 (19.41)

  1. Results for different number (Ns) of selected genes: 131 with ORdensity strong selection; 263 with limma and Bonferroni; 990 with ORdensity relaxed selection; 1531 total potential DE genes; 2684 with limma and BH, and 3322 with SAM. 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