Figure 4From: Kinome-wide interaction modelling using alignment-based and alignment-independent approaches for kinase description and linear and non-linear data analysis techniquesROC curves for SVM, PLS, and k-NN models. Shown are ROC curves for SVM, PLS, and k-NN models built on data for 80% (solid lines) and for 10% (dashed lines) of 317 protein kinases. The area under the ROC curve (AUC) is a measure of the discriminatory power of a classifier.Back to article page