Figure 3
From: Feature-based multiple models improve classification of mutation-induced stability changes
ROC curves performance of the three methods with multiple models, the single-model method, and our previous work. The true positive rate is shown as a function of the false positive rate at different prediction thresholds. These are cross-validation results with the S1676 data set. EASE-MM, EASE-SS, EASE-ASA, EASE-AA2, and EASE-AA achieved the area under the ROC curve (AUC) of 0.82, 0.80, 0.80, 0.77 and 0.76, respectively.