Fig. 6From: GraphDTI: A robust deep learning predictor of drug-target interactions from multiple heterogeneous dataCross-validated performance of algorithms to predict DTIs. Receiver Operating Characteristic (ROC) plots showing the true positive rate (TPR) against the false positive rate (FPR) are calculated for AÂ random-split and BÂ cluster-based cross-validation benchmarks against the GraphDTI dataset. The performance of several DTI predictors is presented, GraphDTI (solid blue lines), EnsemDT (dashed pink lines), EnsemKRR (dashed-dotted green lines), RLS-Kron (dotted red lines), and Vina (dashed yellow line). The gray area corresponds to the performance of a random classifierBack to article page