Table 1 The prediction effect of supervised contrastive learning on three tasks of Dataset1
From: MDDI-SCL: predicting multi-type drug-drug interactions via supervised contrastive learning
| Â | ACC | AUPR | AUC | F1 | Precision | Recall |
|---|---|---|---|---|---|---|
Task1 | ||||||
 With SCL | 0.9378 | 0.9782 | 0.9983 | 0.8755 | 0.8804 | 0.8767 |
 Without SCL | 0.9308 | 0.9746 | 0.9982 | 0.8712 | 0.8762 | 0.8752 |
Task2 | ||||||
 With SCL | 0.6767 | 0.6947 | 0.9634 | 0.5304 | 0.6254 | 0.4814 |
 Without SCL | 0.6667 | 0.6765 | 0.9513 | 0.5314 | 0.5685 | 0.5177 |
Task3 | ||||||
 With SCL | 0.4589 | 0.3938 | 0.9053 | 0.1919 | 0.2585 | 0.1678 |
 Without SCL | 0.4553 | 0.3772 | 0.8740 | 0.2273 | 0.2571 | 0.2177 |