Fig. 2
From: Learning protein binding affinity using privileged information
ROC curves showing a performance comparison between LUPI-SVM (with 2-mers as input-space features and Moal Descriptors as the privileged features) and the baseline classifiers (XGBoost, classical SVM (SVM), and Random Forest (RF) with 2-mer features). The average area under the ROC curve (AUC) is shown in parenthesis