Using informative features in machine learning based method for COVID-19 drug repurposing

Table 2 The first row shows the number of proteins in sets T, \(\hbox {Cut}_{2}\), \(\hbox {Cut}_{{1}}\), \(\hbox {Cut}_{{intersect}}\) and \(\hbox {Cut}_{{union}}\), respectively.

	T	\(\hbox {Cut}_{2}\)	\(\hbox {Cut}_{{1}}\)	\(\hbox {Cut}_{{intersect}}\)	\(\hbox {Cut}_{{union}}\)
No. Protein	332	2017	2100	1115	3002
IBP Go terms	1374	1279	1197	1120	1306
No. targets in Covid-Drug	1	22	20	15	27
No. targets in Clinical-Drug	15	218	217	154	281
No. approved drugs in Covid-Drug	2	15	15	14	16
No. approved drugs in Clinical-Drug	30	246	260	225	273

The number of IBP GO terms overlapped with these subsets collected in the second row. The number of drug targets in each drug group that are associated with these subsets are reported in the third, fourth and fifth rows, respectively. The number of drugs in each drug group that are associated with these subsets are reported in the sixth, seventh and eighth rows, respectively

ISSN: 1758-2946