Identification of Protein Pupylation Sites Using Bi-Profile Bayes Feature Extraction and Ensemble Learning

Table 4

The comparison of predictive performance between our method and GPS-PUP using the leave-one-out cross validation on Dataset 2.

Prediction method	Sensitivity (%)	Specificity (%)	Accuracy (%)	MCC	𝐴ROC
GPS-PUP	63.78	80.21	78.85	0.286	0.708
SinglePup	73.91	78.95	76.19	0.526	0.825
EnsemblePup	80.00	83.33	82.00	0.629	0.873