Skip to main content

Table 6 Resulting performance measures for the phosphorylation dataset, using k-NN or C4.5 as the classifiers (instead of the SVM) for all feature selection and classification tasks, including identification of optimized sets of indices and features

From: A machine learning strategy for predicting localization of post-translational modification sites in protein-protein interacting regions

Classifier

Dataset

Information gain

PPV

Sn

Sp

ACC

AUC

MCC

CPS

SVM

Phosphorylation

0.99

0.83

1.00

0.91

0.93

0.84

2.68

k-NN

Phosphorylation

0.95

0.85

0.95

0.89

0.92

0.79

2.60

C4.5

Phosphorylation

0.96

0.87

0.97

0.91

0.92

0.84

2.67