Table 2 Predictive performance comparisons with different learning methods in Dataset 2.
From: Improved Classification of Blood-Brain-Barrier Drugs Using Deep Learning
Prediction performance in dataset 2 | Method | Sigmoid-SVM | Poly-SVM | RBF-SVM | ||||||
Side Effects(SE) | Indications | SE + Indications | Side Effects(SE) | Indications | SE + Indications | Side Effects(SE) | Indications | SE + Indications | ||
| Â | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | |
AUC | 0.452 ± 0.08 | 0.53 ± 0.09 | 0.535 ± 0.13 | 0.6111 ± 0.08 | 0.61 ± 0.07 | 0.66 ± 0.09 | 0.398 ± 0.13 | 0.45 ± 0.09 | 0.45 ± 0.08 | |
Accuracy | 0.51 ± 0.11 | 0.691 ± 0.13 | 0.52 ± 0.11 | 0.602 ± 0.13 | 0.591 ± 0.11 | 0.59 ± 0.24 | 0.41 ± 0.12 | 0.432 ± 0.13 | 0.45 ± 0.11 | |
F1 | 0.474 ± 0.13 | 0.51 ± 0.1 | 0.5221 ± 0.08 | 0.5201 ± 0.14 | 0.51 ± 0.12 | 0.47 ± 0.23 | 0.531 ± 0.14 | 0.512 ± 0.08 | 0.41 ± 0.13 | |
Method | KNN | Decision Tree (DT) | Deep Learning | |||||||
Side Effects(SE) | Indications | SE + Indications | Side Effects(SE) | Indications | SE + Indications | Side Effects(SE) | Indications | SE + Indications | ||
| Â | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | Prediction | |
AUC | 0.421 ± 0.15 | 0.47 ± 0.18 | 0.472 ± 0.15 | 0.56 ± 0.15 | 0.51 ± 0.12 | 0.51 ± 0.12 | 0.97 ± 0.02 | 0.9523 ± 0.03 | 0.971 ± 0.02 | |
Accuracy | 0.415 ± 0.16 | 0.445 ± 0.14 | 0.51 ± 0.15 | 0.57 ± 0.11 | 0.52 ± 0.15 | 0.52 ± 0.15 | 0.9621 ± 0.02 | 0.9235 ± 0.06 | 0.968 ± 0.03 | |
F1 | 0.541 ± 0.09 | 0.535 ± 0.17 | 0.53 ± 0.21 | 0.54 ± 0.15 | 0.56 ± 0.16 | 0.45 ± 0.25 | 0.9008 ± 0.06 | 0.889 ± 0.08 | 0.911 ± 0.05 | |
