From: Prediction of protein binding sites in protein structures using hidden Markov support vector machine
Data set | Specificity+ | Sensitivity+ | F1 | Accuracy | MCC | AUC |
---|---|---|---|---|---|---|
Hetero-complex I | 43.8% | 58.3% | 49.5% | 66.7% | 26.5% | 69.1% |
Homo-complex I | 44.9% | 58.4% | 49.9% | 68.4% | 29.0% | 71.9% |
Mix I | 42.8% | 62.0% | 49.6% | 65.7% | 27.2% | 70.5% |
Hetero-complex II | 53.7% | 56.1% | 54.2% | 67.4% | 29.4% | 70.3% |
Homo-complex II | 53.7% | 55.4% | 53.0% | 69.0% | 31.3% | 72.4% |
Mix II | 54.5% | 54.9% | 54.5% | 69.6% | 31.8% | 72.0% |