Table 1 Cross-validation performance (data set S1676) of our previous work, the single-model method, and the three methods with multiple models.
From: Feature-based multiple models improve classification of mutation-induced stability changes
Method | AUC | MCC | Q2 | Se | Sp | PPV | NPV |
|---|---|---|---|---|---|---|---|
EASE-AA | 0.76 | 0.35 | 67.11 | 74.93 | 64.22 | 43.68 | 87.37 |
EASE-AA2 | 0.77 | 0.38 | 72.67 | 65.54 | 75.31 | 49.58 | 85.51 |
EASE-ASA | 0.80 | 0.40 | 72.62 | 71.07 | 73.19 | 49.55 | 87.23 |
EASE-SS | 0.80 | 0.42 | 73.57 | 72.13 | 74.11 | 50.79 | 87.77 |
EASE-MM | 0.82 | 0.44 | 74.71 | 73.14 | 75.28 | 52.30 | 88.33 |