Skip to main content

Table 6 Overall performance of various feature classifiers in 5-fold cross-validation for the identification of plastid vs. non-plastid proteins (phase- I)

From: Identification and characterization of plastid-type proteins from sequence-attributed features using machine learning

Feature type Sensitivity
(%)
Specificity
(%)
Accuracy
(%)
MCC Precision (%) RFP (%) SVM kernel type
AAC 85.37 85.65 85.51 0.71 85.61 14.39 RBF (γ = 370, C = 3, j = 1)
PseAA 89.45 82.95 86.20 0.73 83.99 16.01 RBF (γ = 385, C = 2, j = 2)
Dipep 88.08 85.51 86.80 0.74 85.88 14.12 RBF (γ = 265, C = 6, j = 1)
NCC 84.14 89.66 86.90 0.74 89.06 10.94 RBF (γ = 20, C = 3, j = 2)
Phys-Chem 79.57 81.05 80.31 0.61 80.76 19.24 RBF (γ = 135, C = 2, j = 1)
  1. *best values obtained at ≥ 0.0 threshold, individual performance of these classifiers can be seen in supplementary material; AAC = amino acid composition, PseAA = Pseudo amino acid composition, Dipep = Dipeptide composition, NCC = Nterminal-Center-Cterminal composition (sequence divided into 3 parts), Phys-Chem = Protein physicochemical properties, MCC = Matthews Correlation Coefficient, RFP = Rate of False Predictions, RBF = Radial Basis Function of SVM.