Table 3.
Selecting more accurate predictions.
Method | Q2 | P[D] | S[D] | P[N] | S[N] | C | AUC | PM |
---|---|---|---|---|---|---|---|---|
SeqProf | 0.64 | 0.66 | 0.58 | 0.63 | 0.70 | 0.28 | 0.70 | 100 |
F-Cancer | 0.92 | 0.92 | 0.93 | 0.93 | 0.92 | 0.85 | 0.97 | 100 |
SPF-Cancer | 0.93 | 0.93 | 0.93 | 0.93 | 0.93 | 0.86 | 0.98 | 100 |
Consensus | 0.96 | 0.96 | 0.95 | 0.96 | 0.97 | 0.92 | 0.99 | 62 |
NotConsensus | 0.88 | 0.90 | 0.90 | 0.87 | 0.87 | 0.76 | 0.95 | 38 |
Overall accuracy (Q2), positive predictive value (P) Sensitivity, Correlation coefficient (C) and area under the ROC curve (AUC) are defined in Methods section. D (Disease) and N (Neutral) are referred to cancer-causing and neutral variants. PM is the percentage predicted variants of CNO dataset.