Skip to main content

Table 1 Summary of the six cancer gene expression datasets used to test the NMF-MCC algorithm

From: Non-negative matrix factorization by maximizing correntropy for cancer clustering

Dataset name

Diagnostic task

Samples ( N)

Genes ( D)

 Cancer Classes ( K)

Ref

Leukemia

Acute myelogenous leukemia

72

5327

3

[25]

Brain Tumor

5 human brain tumor types

90

5920

5

[26]

Lung Cancer

4 lung cancer types and normal tissues

203

12600

5

[27]

9 Tumors

9 various human tumor types

60

5726

9

[28]

SRBCT

Small, round blue cell tumors

83

2308

4

[29]

DLBCL

Diffuse large B-cell lymphomas

77

5469

2

[24]