Skip to main content

Table 1 Performance statistics of classification models based on 10-fold cross validation

From: Annotation of gene promoters by integrative data-mining of ChIP-seq Pol-II enrichment data

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