Table 3 Performance comparison between the hybrid predictor and Kuznetsov' s predictor
From: A sequence-based hybrid predictor for identifying conformationally ambivalent regions in proteins
Predictor | TP | FP | TN | FN | accuracy | sensitivity | specificity | precision | F-score | MCC |
|---|---|---|---|---|---|---|---|---|---|---|
The hybrid predictor with only the RVKDE based classifier enabled | 1236 | 9697 | 34877 | 1033 | 0.771 | 0.545 | 0.782 | 0.113 | 0.187 | 0.166 |
The hybrid predictor with both the QUICKRBF and RVKDE based classifiers enabled | 813 | 4792 | 39782 | 1456 | 0.867 | 0.358 | 0.892 | 0.145 | 0.207 | 0.166 |
Kuznetsov' s predictor With false positive rate = 20 | 1020 | 9205 | 35369 | 1249 | 0.777 | 0.450 | 0.793 | 0.100 | 0.163 | 0.126 |
Kuznetsov' s predictor With false positive rate = 10 | 633 | 4676 | 39898 | 1636 | 0.865 | 0.279 | 0.895 | 0.119 | 0.167 | 0.118 |