Table 3.
Comparing the five-fold cross-validation performance of LPI-Pred and other machine learning classifiers on three gold standard datasets.
| Datasets | Methods | Acc (%) | Sens (%) | Spec (%) | Pre (%) | MCC (%) |
|---|---|---|---|---|---|---|
| RPI369 | SVM | 65.17 | 66.20 | 64.34 | 65.48 | 30.61 |
| LR | 58.37 | 44.06 | 73.12 | 62.51 | 18.05 | |
| LPI-Pred | 73.06 | 75.32 | 71.14 | 72.64 | 46.67 | |
| RPI488 | SVM | 88.68 | 81.97 | 95.17 | 94.26 | 77.95 |
| LR | 88.68 | 81.97 | 95.17 | 94.26 | 77.95 | |
| LPI-Pred | 89.92 | 82.75 | 96.72 | 96.32 | 80.59 | |
| RPI1807 | SVM | 92.35 | 94.11 | 90.17 | 92.29 | 84.52 |
| LR | 87.26 | 90.17 | 83.56 | 87.39 | 74.17 | |
| LPI-Pred | 97.10 | 97.89 | 96.14 | 96.91 | 94.13 |
The boldface indicates this measure performance is the best among the compared methods for individual dataset.