Table 7.
Overall performance of various feature classifiers on an 'independent test' dataset for the identification of plastid vs. non-plastid proteins (phase-I)
| Feature type | Sensitivity (%) |
Specificity (%) |
Accuracy (%) |
MCC | Precision (%) | RFP (%) |
|---|---|---|---|---|---|---|
| AAC | 69.30 | 87.03 | 78.16 | 0.57 | 84.23 | 15.77 |
| PseAA | 68.35 | 87.34 | 77.85 | 0.57 | 84.38 | 15.62 |
| Dipep | 60.44 | 92.72 | 76.58 | 0.56 | 89.25 | 10.75 |
| NCC | 65.82 | 87.97 | 76.90 | 0.55 | 84.55 | 15.45 |
| Phys-Chem | 68.35 | 84.49 | 76.42 | 0.54 | 81.51 | 18.49 |
*individual performance of these classifiers can be seen in supplementary material; AAC = amino acid composition (best values at ≥ 0.0 threshold), PseAA = Pseudo amino acid composition (best values at ≥ 0.1 threshold), Dipep = Dipeptide composition (best values at ≥ 0.2 threshold), NCC = Nterminal-Center-Cterminal composition (sequence divided into 3 parts), Phys-Chem = Protein physicochemical properties, MCC = Matthews Correlation Coefficient, RFP = Rate of False Predictions.