Table 3 Average performance metrics of different ML algorithms based on 10 runs of split training and testing sets
From: Improved cytokine–receptor interaction prediction by exploiting the negative sample space
SE | SP | ACC | MCC | AUC | g-means | |
|---|---|---|---|---|---|---|
Random (70% training, 30% testing) | ||||||
NB | 63.7 | 53.5 | 58.4 | 0.178 | 0.595 | 56.8 |
A1DE | 70.7 | 57.5 | 62.2 | 0.255 | 0.674 | 63.4 |
SMO-RBF | 79.3 | 72.5 | 75.7 | 0.520 | 0.759 | 75.6 |
SMO-PolyK | 66.7 | 50.0 | 55.2 | 0.194 | 0.583 | 57.1 |
SMO-PuK | 74.8 | 77.8 | 76.3 | 0.529 | 0.763 | 76.0 |
IBK | 79.8 | 68.9 | 74.1 | 0.491 | 0.743 | 73.9 |
Bagging | 65.5 | 58.9 | 62.0 | 0.244 | 0.682 | 62.0 |
RF | 74.5 | 64.2 | 69.1 | 0.390 | 0.779 | 68.9 |
K-means (70% training, 30% testing) | ||||||
NB | 79.7 | 50.0 | 63.6 | 0.299 | 0.742 | 62.3 |
A1DE | 77.6 | 87.2 | 82.9 | 0.659 | 0.857 | 82.4 |
SMO-RBF | 89.5 | 89.0 | 89.2 | 0.785 | 0.890 | 89.2 |
SMO-PolyK | 88.1 | 78.9 | 83.2 | 0.692 | 0.828 | 83.2 |
SMO-PuK | 82.9 | 85.1 | 84.1 | 0.683 | 0.845 | 83.8 |
IBK | 82.2 | 87.0 | 84.2 | 0.692 | 0.841 | 84.0 |
Bagging | 84.8 | 92.3 | 88.7 | 0.776 | 0.934 | 88.4 |
RF | 90.3 | 93.9 | 92.2 | 0.844 | 0.959 | 92.0 |