Table 1. Threshold for Variablesa.
| protein |
||||||||
|---|---|---|---|---|---|---|---|---|
| variable | β-lactamase | APH(3′)-II | Hsp90 | MAPK1 | UBE2I | TPK1 | average threshold | standard deviation |
| fitness cutoff | –0.5 | –2.5 | –0.3 | 0.5 | 0.2 | 0.4 | ||
| conservation | 0.35 | 0.5 | 0.85 | 0.9 | 0.45 | 0.55 | 0.6 | 0.2 |
| SASA (nm2) | 0.3 | 0.2 | 0.2 | 0.1 | 0.2 | 0.4 | 0.2 | 0.1 |
| contacts | 14 | 19 | 25 | 20 | 18 | 14 | 18 | 4 |
| BLOSUM | –1 | –3 | –3 | –3 | –2 | –1 | –2 | 1 |
a
Thresholds for different variables were obtained by maximizing F1avg, which is the average of F1 scores of neutral and deleterious class predictions. The thresholds were obtained for each variable and data from every single protein. For a variable, the average of thresholds obtained for the six proteins was calculated to obtain the average threshold.