Table 1 Classification results of the baseline models, MLP with NS, and MLP with PLANS using ECFP for the representation of chemical structures
| Â | Â | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|
Cyp450 | SVM | 56.37 ± 0.93 | 0.53 ± 0.01 | 0.81 ± 0.01 | 0.64 ± 0.01 |
|  | RF | 54.44 ± 0.98 | 0.42 ± 0.01 | 0.81 ± 0.02 | 0.55 ± 0.01 |
|  | AdaBoost | 52.40 ± 1.01 | 0.25 ± 0.02 | 0.89 ± 0.01 | 0.39 ± 0.02 |
|  | XGBoost | 55.13 ± 1.21 | 0.57 ± 0.01 | 0.75 ± 0.01 | 0.65 ± 0.01 |
|  | MLP | 51.97 ± 1.12 | 0.64 ± 0.03 | 0.72 ± 0.02 | 0.68 ± 0.02 |
|  | MLP + mixup | 54.28 ± 0.79 | 0.60 ± 0.02 | 0.73 ± 0.01 | 0.66 ± 0.01 |
|  | MLP + NS | 56.11 ± 1.63 | 0.64 ± 0.01 | 0.76 ± 0.02 | 0.69 ± 0.01 |
|  | MLP + mixup + NS | 56.48 ± 1.45 | 0.60 ± 0.04 | 0.76 ± 0.02 | 0.67 ± 0.02 |
|  | MLP + PLANS | 58.94 ± 0.96 | 0.72 ± 0.02 | 0.78 ± 0.01 | 0.75 ± 0.01 |
|  | MLP + PLANS + mixup | 58.04 ± 0.70 | 0.69 ± 0.02 | 0.76 ± 0.01 | 0.72 ± 0.01 |
|  | MLP + PLANS + balancing | 59.02 ± 1.12 | 0.73 ± 0.03 | 0.76 ± 0.02 | 0.75 ± 0.01 |
|  | MLP + PLANS + balancing + mixup | 59.25 ± 1.04 | 0.68 ± 0.03 | 0.78 ± 0.01 | 0.73 ± 0.01 |
| Â | Â | AP | F1 |
|---|---|---|---|
Tox21 | MLP | 0.03 ± 0.01 | – |
|  | MLP + mixup | 0.12 ± 0.01 | 0.02 ± 0.01 |
|  | MLP + NS | 0.03 ± 0.004 | – |
|  | MLP + mixup + NS | 0.13 ± 0.01 | 0.08 ± 0.03 |
|  | MLP + PLANS | 0.14 ± 0.01 | 0.04 ± 0.01 |
|  | MLP + PLANS + mixup | 0.20 ± 0.03 | 0.25 ± 0.02 |
|  | MLP + PLANS + balancing | 0.16 ± 0.02 | 0.09 ± 0.04 |
|  | MLP + PLANS + balancing + mixup | 0.20 ± 0.02 | 0.20 ± 0.02 |