Table 4 Predictive performance of classifiers constructed using the optimal subsets of sequence features.
From: Sequence feature-based prediction of protein stability changes upon amino acid substitutions
Features | AC (%) | SN (%) | SP (%) | ST (%) | MCC | ROC AUC |
|---|---|---|---|---|---|---|
S3 | 82.53 | 72.19 | 87.15 | 79.67 | 0.5922 | 0.8835 |
Bu, Co | 83.00 | 74.10 | 86.98 | 80.54 | 0.6057 | 0.8872 |
B, Co, S3 | 84.12 | 69.33 | 90.72 | 80.03 | 0.6194 | 0.8924 |
B, Co, H, S3 | 84.29 | 69.33 | 90.98 | 80.16 | 0.6231 | 0.8940 |
A, Aa, B, Co, P | 84.47 | 70.48 | 90.72 | 80.60 | 0.6287 | 0.8954 |
A, Aa, B, Co, No, P | 84.59 | 70.29 | 90.98 | 80.63 | 0.6310 | 0.8961 |