Table 6.
Performance achieved by scikit ML on the 2D, 3D, and fingerprints descriptors.
| Methods (Parameters) | Main Dataset | Validation Dataset | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Sen | Spc | Acc | MCC | AUC | Sen | Spc | Acc | MCC | AUC | |
| RF (n_estimators = 200) | 77.73 | 79.09 | 78.42 | 0.57 | 0.86 | 79.83 | 77.09 | 78.46 | 0.57 | 0.84 |
| KNN (n_neighbors = 10,algorithm = ‘kd_tree',weights = ‘distance') | 62.88 | 62.5 | 62.69 | 0.25 | 0.67 | 49.57 | 58.97 | 54.27 | 0.09 | 0.60 |
| Ridge (alpha = 1) | 62.45 | 53.02 | 57.7 | 0.16 | 0.61 | 63.25 | 48.72 | 55.98 | 0.12 | 0.58 |
| Extratree (n_estimator = 1000) | 80.35 | 74.35 | 77.33 | 0.55 | 0.85 | 82.05 | 72.31 | 77.18 | 0.55 | 0.83 |