Skip to main content

Table 2 Performance metrics for N-linked glycosylation prediction using GPP and ProtDCal features using Random Forest and Naïve Bayes classifiers

From: ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins

 

Random Forest

Naïve Bayes

 

CCI (%)

Sensitivity (%)

Specificity (%)

CCI (%)

Sensitivity (%)

Specificity (%)

GPP

92.8

96.6

91.8

90.3

83.8

94.6

ProtDCal

91.6

93.2

91.4

91.1

97.6

90.6

  1. CCI = Correctly classified instances. GPP results from Hamby & Hirst [59].