Table 1.
Analysis of the prediction performance of individual features
| Feature | AUC | CA | F1-score | Precision | Recall |
|---|---|---|---|---|---|
| + Literature |
0.781 |
0.722 |
0.723 |
0.721 |
0.726 |
| + Sequence |
0.877 |
0.784 |
0.790 |
0.768 |
0.813 |
| + GO |
0.817 |
0.742 |
0.748 |
0.735 |
0.760 |
| + COGs |
0.663 |
0.652 |
0.537 |
0.806 |
0.402 |
| + DDIs |
0.620 |
0.617 |
0.424 |
0.861 |
0.281 |
| Final Model | 0.926 | 0.850 | 0.851 | 0.848 | 0.854 |
For each line the metrics are obtained by considering only that cluster of features on the classifier. AUC, area under the receiver operating characteristic (ROC) curve; CA, classification accuracy.