Table 2 Prediction accuracies, sensitivities, specificities, AUC values and Matthew's correlation coefficients (MCC) compared between methods (based on TCGA dataset)
Tool | Accuracy | Sensitivity | Specificity | AUC | MCC |
|---|---|---|---|---|---|
CHASM | 50% | 0% | 100% | 0.34 | 0.05 |
MutationAssessor | 74% | 86% | 62% | 0.79 | 0.49 |
Condel | 68% | 66% | 66% | 0.72 | 0.37 |
PolyPhen-2 | 66% | 76% | 56% | 0.68 | 0.34 |
SIFT | 65% | 74% | 56% | 0.66 | 0.30 |
SNAP | 62% | 43% | 79% | 0.59 | 0.26 |
mCluster | 54% | 8% | 99% | 0.50 | 0.17 |
logRE | 52% | 39% | 64% | 0.50 | 0.07 |