Fig. 3
From: RExPRT: a machine learning tool to predict pathogenicity of tandem repeat loci
Results from ensemble of SVM and XGB with LOOCV on training dataset. a Confusion matrix outlining the number of true positives, false positives, false negatives, and true negatives on the training set. b Calculations of the accuracy, precision, recall, and F1 scores. c The ROC curve for the ensemble model and its AUC value. d PRC curve for the ensemble model and its AUC value. e Permutation importance, indicating features that allow decision-making in the SVM model and f the XGB model