Table 1. Drug-related data sets used in this study.

	ChEMBL	SIDER	STITCH	drugs.com
Drug	257,867	888	55,503	5591
Protein	2,733	–	14,732	–
Drug-Protein	584,516	–	897,803	–
SE	–	1,450	–	–
Drug-SE	–	62,269	–	–
DDIAE or DDIPharm	–	–	47,911	4442

Row names represent the following data: ‘Drug’ is # of drugs with target interactions, Protein’ is # of proteins from humans, ‘Drug-Protein’ is # of drug-target pairs, ‘SE’ is # of side effects, ‘Drug-SE’ is # of drug-side effect pairs, and ‘’ or ‘’ is # of drugs having DDI. The two superscripts in the last column represent the following: is # of drugs with matched identifiers from ChEMBL drugs with target interactions and SIDER side effects, and is # of drugs having DDI in .