Fig. 1
From: An ensemble learning approach for modeling the systems biology of drug-induced injury
Results of the Classifiers in the testing set and the independent hold-out test set. The machine learning algorithm used was a Random Forest. The features that were used in the models of DisGeNET, GUILDify, DisGeNET+SMILES and GUILDify+SMILES are only from the phenotype “Biliary cirrhosis” (C0023892). The results of using different phenotypes are given in the Fig. 3. The results for gradient boosting machine classifier are given in the Supplementary Fig. 8