Skip to main content

Table 1 Summary of GEO breast cancer microarray datasets and results of class prediction analysis for the meta-gene lists, DN (Ductal/Normal) and LN (Lobular/Normal).

From: A resampling-based meta-analysis for detection of differential gene expression in breast cancer

Study GEO ID

Class

Meta gene-list

   

DN

LN

 

N

T

Accuracy

(%)

Number of genes

rDN

Accuracy

(%)

Number of genes

rLN

Turashvili [5] GDS2635

10

10

93

57

0.85

80

49

0.87

Richardson [7] GDS2250

7

40

100

145

0.86

100

96

0.78

Karnoub [8] GSE8977

15

7

95.5

109

0.72

95.5

89

0.81

  1. Normal (N) and tumor (T) sample sizes, accuracy of prediction from binary tree algorithm (% accuracy), and the number of genes in classifier (number of genes) were shown for each study, separately. Correlation (rDN, rLN) of the classifier expression from each study with the DN and LN meta-gene expressions were also indicated (Pearson correlation, Minitab®; p < 0.001).
Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us