Skip to main content

Table 2 Summary statistics for πcc values when classifying 31 tumor types and ignoring sex of the samples across 1000 GA/KNN runs for each of two training/testing partitions (2000 runs total)

From: A comprehensive genomic pan-cancer classification using The Cancer Genome Atlas gene expression data

Type

Minimum

1st Quartile

Median

Mean

3rd Quartile

Maximum

Modal Prediction Accuracy

ACC

0.23

0.76

0.88

0.83

0.92

0.97

0.97

BLCA

0.01

0.51

0.81

0.71

0.96

1.00

0.91

CHOL

0.00

0.01

0.40

0.37

0.50

0.66

0.73

COAD

0.18

0.77

0.85

0.83

0.91

0.98

0.99

DLBC

0.65

0.82

0.89

0.87

0.94

0.98

1.00

GBM

0.46

0.86

0.96

0.91

0.98

1.00

0.99

HNSC

0.04

0.91

0.98

0.93

1.00

1.00

0.99

KICH

0.00

0.88

0.92

0.86

0.96

0.99

0.96

KIRC

0.00

0.98

1.00

0.93

1.00

1.00

0.96

KIRP

0.00

0.79

0.97

0.85

1.00

1.00

0.92

LAML

0.89

1.00

1.00

0.99

1.00

1.00

1.00

LGG

0.56

0.99

1.00

0.97

1.00

1.00

1.00

LHIC

0.04

0.97

0.99

0.94

1.00

1.00

0.98

LUAD

0.00

0.88

0.96

0.88

0.99

1.00

0.96

LUSC

0.03

0.67

0.92

0.78

0.97

1.00

0.88

MESO

0.00

0.72

0.87

0.76

0.93

1.00

0.90

PAAD

0.03

0.84

0.96

0.85

0.99

1.00

0.95

PCPG

0.71

0.98

1.00

0.98

1.00

1.00

1.00

READ

0.03

0.09

0.14

0.15

0.19

0.28

0.00

SARC

0.03

0.78

0.91

0.83

0.96

1.00

0.96

SKCM

0.00

0.93

0.97

0.90

0.99

1.00

0.97

THCA

0.37

1.00

1.00

0.99

1.00

1.00

1.00

THYM

0.08

0.90

0.99

0.89

1.00

1.00

0.94

UCS

0.01

0.06

0.26

0.27

0.41

0.62

0.62

UVM

0.52

0.95

0.99

0.95

1.00

1.000

1.00

BRCA

0.01

0.98

0.99

0.97

1.00

1.00

0.99

CESC

0.00

0.52

0.76

0.68

0.87

0.98

0.94

OV

0.36

0.95

0.98

0.95

0.99

1.00

1.00

PRAD

0.53

1.00

1.00

0.99

1.00

1.00

1.00

TGCT

0.25

0.97

1.00

0.94

1.00

1.00

1.00

UCEC

0.04

0.52

0.71

0.68

0.86

1.00

0.96

  1. The rightmost column labeled “Modal Prediction Accuracy” is not based on πcc but instead on a prediction using the tumor type to which each sample was assigned most often