Table 1 Detailed performance metrics of top performing models.
From: Protein feature engineering framework for AMPylation site prediction
Model | Representations | Feat types | Offsets | Nfeat | Accuracy | Precision | Recall | F1 score | AUC ROC | MCC |
|---|---|---|---|---|---|---|---|---|---|---|
ANN | (‘conform’, ‘no_reduction’) | (‘mat’,) | (1, 3) | 898 | 0.804552 | 0.718347 | 0.757692 | 0.734459 | 0.853464 | 0.583993 |
XGB | (‘no_reduction’, ‘hydro’) | (‘counts’, ‘mat’) | (1, 3) | 875 | 0.791181 | 0.698694 | 0.736264 | 0.714020 | 0.857740 | 0.553493 |
LGBM | (‘conform’, ‘no_reduction’) | (‘counts’, ‘mat’) | (1, 2, 3) | 1374 | 0.799075 | 0.745368 | 0.691758 | 0.707679 | 0.859776 | 0.565576 |
RF | (‘conform’, ‘no_reduction’, ‘hydro’) | (‘counts’, ‘mat’) | (1, 3) | 980 | 0.809744 | 0.829522 | 0.606044 | 0.687253 | 0.885388 | 0.580302 |
SVM | (‘no_reduction’,) | (‘counts’, ‘mat’) | (1, 2) | 820 | 0.788834 | 0.741946 | 0.648352 | 0.686790 | 0.863235 | 0.536218 |
Linear | (‘no_reduction’, ‘hydro’) | (‘tfeat’, ‘pro2vec’) | (3,) | 360 | 0.756757 | 0.655678 | 0.706044 | 0.672372 | 0.808359 | 0.488660 |
