The tcbb2014 dataset is collected from DrugBank, KEGG Drug, DCDB and Matador, and contains 315 drugs, 250 targets, 5 similarity categories between drugs and 3 similarity categories between targets. The similarity between drugs includes similarity in chemistry, ligand, expression, side effects and annotation. The similarity between targets includes similarity in sequence, protein-protein interaction network and gene ontology. The original task of this dataset is to predict new interactions between drugs and targets based on different types of similarity in the network.