Table 1

Performance statistics of classification models based on 10-fold cross validation

Method

10-fold cross-validation test result, 39 features, Promoters = 8793, NonPromoters = 34686


# of true positive

# of false negative

# of true negative

# of false positive

Sensitivity (%)

Positive predictive value (PPV)

Mathew correlation coefficient

True positive cost

ROC Area


Bagging

7603

1190

34354

332

86.47

95.82

0.89

0.04

0.97


LogitBoost

7638

1155

34252

434

86.86

94.62

0.88

0.06

0.97


Random Forest

7626

1167

34921

395

86.73

95.08

0.89

0.05

0.97


Rotational Forest

7153

1640

34198

488

81.35

93.61

0.84

0.07

0.96


Gupta et al. BMC Bioinformatics 2010 11(Suppl 1):S65   doi:10.1186/1471-2105-11-S1-S65

Open Data