Skip to main content

Table 1 Number of samples and variants of two data sets

From: Feature selection algorithm based on dual correlation filters for cancer-associated somatic variants

SKCM

Number of sample

Negative class

Positive class

All

Primary tumor

Metastatic tumor

363

104

467

Number of variant

All

After filtering

Step1

Step2

Step3

1,298,172

414,954

409,389

200,814

BRCA

Number of sample

Negative class

Positive class

All

Stage IIA

Stage IIB

314

223

537

Number of variant

All

After filtering

Step1

Step2

Step3

424,415

88,514

75,161

37,449