Skip to main content

Table 1 Dataset details

From: ForestSubtype: a cancer subtype identifying approach based on high-dimensional genomic data and a parallel random forest

Dataset

      

The public breast cancer dataset

      

Label

Basal

Her2

LumA

LumB

Normal

 

Num

204

121

198

567

121

 

Ratio

17%

10%

16%

47%

10%

 

METABRIC

      

Label

1

2

3

4

5

6

Num

330

239

721

491

202

150

Ratio

15.5%

11.2%

33.8%

23%

9.5%

7%

BLCA

      

Label

C1

C2

C3

C4

C5

C6

Num

172

90

22

34

91

18

Ratio

40.2%

21.1%

5.2%

8%

21.3%

4.2%

ACC

      

Label

C1

C2

C3

C4

C5

C6

Num

31

33

5

4

5

1

Ratio

39.2%

42%

6.3%

5%

6.3%

1.2%