Table 1.

The first and second columns show each subset of drug features and the number of drugs which these features are available in the database, respectively. The third column indicates the number of drug-disease associations where the features are available in the database and the fourth one identifies the number of unknown drug-disease associations

Subset E	No. of Drugs	No. of drug associations ($\mathcal{A}$)	No. of unknown drug-disease association	Avg. of AUC	AUC
{s}	4240	13,916	25,235,284	0.942	0.944
{g}	729	6175	4,335,020	0.894	0.888
{e}	671	10,950	3,984,855	0.927	0.926
{p}	6233	16,846	37,100,669	0.942	0.943
{g,s}	729	6175	4,335,020	0.936	0.933
{e,s}	471	8398	2,796,407	0.870	0.871
{s,p}	3226	13,159	19,197,671	0.941	0.941
{e,g}	155	4065	918,960	0.856	0.844
{g,p}	337	5928	2,000,907	0.857	0.864
{e,p}	600	10,305	3,562,695	0.909	0.906
{e,g,s}	155	4065	918,960	0.849	0.848
{g,p,s}	337	5928	2,000,907	0.876	0.877
{g,p,e}	146	3944	865,486	0.834	0.844
{e,p,s}	440	8162	2,612,038	0.868	0.870
{s,e,g,p}	146	3944	865,486	0.840	0.846