Table 1.
Comparison Between UMD‐Predictor and Other Predictors Using the Varibench–dbSNP [Sherry et al., 2001; Sasidharan Nair and Vihinen, 2013] Dataset (n = 17,329)
| SIFT | PPH2 | Provean | Mutation assessor | CONDEL | MutationTaster | CADD | UMD‐Predictor | |
|---|---|---|---|---|---|---|---|---|
| TP | 9,596 | 10,290 | 9,638 | 9,775 | 8,797 | 11,174 | 10,182 | 10,727 |
| TN | 2,805 | 3,045 | 3,088 | 3,162 | 3,287 | 2,937 | 3,214 | 4,024 |
| FP | 1,229 | 1,189 | 1,147 | 1,073 | 948 | 1,298 | 1,021 | 211 |
| FN | 3,498 | 2,803 | 3,456 | 3,319 | 4,297 | 1,920 | 2,912 | 2,367 |
| PPV | 0.89 | 0.90 | 0.89 | 0.90 | 0.90 | 0.90 | 0.91 | 0.98 |
| NPV | 0.45 | 0.52 | 0.47 | 0.49 | 0.43 | 0.60 | 0.52 | 0.63 |
| Sensitivity | 0.73 | 0.79 | 0.74 | 0.75 | 0.67 | 0.85 | 0.78 | 0.82 |
| Specificity | 0.70 | 0.72 | 0.73 | 0.75 | 0.78 | 0.69 | 0.76 | 0.95 |
| Accuracy | 0.72 | 0.77 | 0.73 | 0.75 | 0.70 | 0.81 | 0.77 | 0.85 |
| MCC | 0.38 | 0.46 | 0.41 | 0.44 | 0.39 | 0.52 | 0.48 | 0.69 |
| DOR | 6.3 | 9.7 | 7.7 | 9.0 | 7.2 | 12.6 | 11.2 | 86.6 |
| log(DOR) | 1.84 | 2.27 | 2.04 | 2.20 | 1.97 | 2.53 | 2.42 | 4.46 |
TP, true positives; TN, true negatives; FP, false positives; FN, false negatives; PPV, positive predictive value; NPV, negative predictive value; MCC, Matthews correlation coefficient; DOR, diagnostic odds ratio.