Table 3. List of highly ranked unknown drug-protein pairs in ChEMBL.

Drug similarity	Drugs	Proteins	Prob.	Evidence
DDIPharm	Nifedipine	SLC22A1	0.678445	CTD
	Verapamil	ADRB1	0.672712	CTD
	Phenytoin	CYP3A4	0.656528	STITCH
	Diphenhydramine	SLC22A1	0.632571	DrugBank
	Amitriptyline	SLC6A2	0.576068	DrugBank
	Midazolam	SLC22A1	0.569028	DrugBank
	Valium	ERG1	0.521953	CTD
	Nifedipine	ADRB1	0.513618	CTD
	Phenytoin	ABCB1	0.503147	STITCH
	Midazolam	GABRA1	0.498508	STITCH
	Fenoprofen	PTGS1	0.494015	DrugBank
	Oxaprozin	PTGS1	0.494015	STITCH
	Metoprolol	HTR1A	0.478448	STITCH
Chem. struc.	Amoxicillin	SLC15A1	0.644264	STITCH
	Midazolam	GABRA5	0.614966	DrugBank
	Midazolam	GABRA3	0.614966	DrugBank
	Midazolam	GABRA2	0.556632	DrugBank
	Midazolam	GABRA1	0.503353	STITCH
	Midazolam	GABRA6	0.414876	KEGG
	Alprazolam	GABRA6	0.408056	DrugBank
	Aspirin	ADRB2	0.339491	CTD
	Rabeprazole	ATP4A	0.33869	STITCH
	Rabeprazole	ATP4B	0.33869	STITCH
	Terbutaline	ADRB1	0.315024	CTD

Among all 270,540 drug-protein pairs from the ChEMBL data set, the top 50 unknown pairs determined by the KL1LR method using data sets were checked, and the unknown pair was listed if it was found in the STITCH [4], DrugBank [1], KEGG [2], BindingDB [36], and CTD [35] data sets. Drugs in the second column and proteins in the third column are likely to interact, based on the probabilities shown in the fourth column. If interactions are found in more than two data sets, only one source is listed. Similarly, the results obtained using chemical structure similarities are shown.