Skip to main content

Table 1 Comparative performance of LibSVM and RF using Amino Acid and Dipeptide as feature inputs for binary classification

From: Prediction of peptidoglycan hydrolases- a new class of antibacterial proteins

 

Sensitivity

Specificity

Accuracy

MCC

 

AAC

DPC

AAC

DPC

AAC

DPC

AAC

DPC

SVM

53.81

78.76

93.63

94.67

82.94

90.40

0.53

0.75

RF

74.14

75.08

97.79

99.48

91.44

92.93

0.77

0.82

  1. AAC = Amino acid composition and DPC = Dipeptide composition
  2. SVM = Support Vector Machine at t = 0 and c = 1 for both AAC and DPC
  3. RF = Random Forest; for AAC mtry = 4, ntree = 500 and for DPC mtry = 64, ntree = 500
Back to article page

BMC Genomics

ISSN: 1471-2164

Contact us