Skip to main content

Table 1 Five-fold cross validation results of the DT, RF and SVM models trained on single type of features

From: iDPGK: characterization and identification of lysine phosphoglycerylation sites based on sequence-based features

Training feature Classifier Sensitivity (%) Specificity (%) Accuracy (%) MCC
AAC DT 59.6 55.6 56.9 0.14
RF 59.6 59.0 59.2 0.18
SVM 56.2 59.6 58.4 0.15
AAPC DT 59.6 47.8 51.7 0.07
RF 48.3 62.9 58.1 0.11
SVM 60.7 47.8 52.1 0.08
B62 DT 44.9 70.8 62.2 0.16
RF 55.1 55.1 55.1 0.10
SVM 51.7 43.3 46.1 − 0.05
PSSM DT 34.8 71.9 59.6 0.07
RF 58.4 52.2 54.3 0.10
SVM 39.3 59.6 52.8 − 0.01
PCAAC DT 50.6 71.3 64.4 0.22
RF 50.6 50.6 50.6 0.01
SVM 58.4 68.0 64.8 0.25