Skip to main content

Table 3 Colon cancer data sets for train and test (genes with missing entries were excluded).

From: Improving the prediction accuracy in classification using the combined data sets by ranks of gene expressions

Data name

Experimental sources

# of genes

# of total samples

Normal group

Tumor group

Train data sets a

Data A

Total RNA

12319

78

35

43

Data B

Amplified RNA

12319

76

37

39

Data AB

Combined data set

12319

154

72

82

Test data sets a

Tumor 86

Amplified RNA (Batch I)

17104

86

0

86

Tumor 211

Amplified RNA (Batch II)

17104

211

0

211

Train and Test data set (Notterman et al., 2001)

Affy

Affymetrix HU6800

7464

36

18

18

  1. a: Cancer Metastasis Research Center of Yonsei University, Seoul, Korea.