Table 3 Performance of dipeptide composition-based SVM models for predicting hemotoxicity of peptides using five-fold cross-validation.
From: A Web Server and Mobile App for Computing Hemolytic Potency of Peptides
Approach | Sn (%) | Sp (%) | Acc (%) | MCC |
|---|---|---|---|---|
HemoPI-1 main dataset | ||||
Whole peptide | 94.6 | 94.3 | 94.5 | 0.89 |
NT10 | 87.0 | 96.8 | 92.5 | 0.85 |
CT10 | 87.5 | 90.1 | 89.0 | 0.78 |
NTCT10 | 94.1 | 94.0 | 94.0 | 0.88 |
NT15 | 92.7 | 94.7 | 93.8 | 0.88 |
CT15 | 90.4 | 92.8 | 91.6 | 0.83 |
NTCT15 | 94.8 | 95.1 | 95.0 | 0.90 |
HemoPI-2 main dataset | ||||
Whole peptide | 77.6 | 79.2 | 78.3 | 0.57 |
NT10 | 69.8 | 69.7 | 69.8 | 0.39 |
CT10 | 69.1 | 69.8 | 69.4 | 0.39 |
NTCT10 | 73.2 | 81.7 | 77.0 | 0.55 |
NT15 | 75.3 | 72.5 | 74.1 | 0.48 |
CT15 | 71.2 | 78.3 | 74.3 | 0.49 |
NTCT15 | 78.6 | 79.5 | 79.0 | 0.58 |
