Table 3.
Performance achieved by scikit ML on the 2D descriptors.
| Methods (Parameters) | Main Dataset | Validation Dataset | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Sen | Spc | Acc | MCC | AUC | Sen | Spc | Acc | MCC | AUC | |
| RF (n_estimators = 1000) | 79.37 | 72.49 | 75.88 | 0.52 | 0.83 | 76.76 | 75.69 | 76.21 | 0.52 | 0.81 |
| KNN (n_neighbors = 8,algorithm = ‘kd_tree',weights = ‘distance') | 67.94 | 61.35 | 64.6 | 0.29 | 0.72 | 61.26 | 63.79 | 62.56 | 0.25 | 0.67 |
| Ridge (alpha = 1) | 71.08 | 78.38 | 74.78 | 0.5 | 0.81 | 58.56 | 82.76 | 70.93 | 0.43 | 0.74 |
| Extratree (n_estimator = 40) | 76.01 | 73.8 | 74.89 | 0.5 | 0.82 | 73.87 | 77.07 | 75.51 | 0.51 | 0.80 |