Table 3.
Performance of tools derived from contingency table with Ensembl dataset (n = 114,868,082)
| SVM-BPfinder | BPP | Branchpointer | LaBranchoR | RNABPS | |
|---|---|---|---|---|---|
| Cutoff | 0.706 | 5.384 | – | 0.653 | 0.653 |
| TP | 166,135 | 198,708 | 252,967 | 171,511 | 193,430 |
| FP | 36,526,998 | 28,315,554 | 583,920 | 40,370,908 | 30,878,750 |
| TN | 72,145,972 | 86,003,592 | 114,019,375 | 74,232,290 | 83,724,448 |
| FN | 84,113 | 65,422 | 11,820 | 93,276 | 71,357 |
| Missing data | 5,944,864 | 284,806 | 0 | 97 | 97 |
| AUC | 0.728 | 0.819 | – | 0.711 | 0.811 |
| Accuracy | 66.39% | 75.23% | 99.48% | 64.77% | 73.06% |
| Sensitivity | 66.39% | 75.23% | 95.54% | 64.77% | 73.05% |
| Specificity | 66.39% | 75.23% | 99.49% | 64.77% | 73.06% |
| PPV | 0.45% | 0.70% | 30.23% | 0.42% | 0.62% |
| NPV | 99.88% | 99.92% | 99.99% | 99.87% | 99.91% |
TP (True Positive), FP (False Positive), TN (True Negative), FN (False Negative), AUC (Area Under the Curve), PPV (Positive Predictive Value), NPV (Negative predictive value)