Table 7.

The COX-2 inhibitors candidates from the MFH database found by virtual screening using the related ML models built in this work.

Candidates	Origins	IC50 μM a	SOM HP b	Effects
cmp_A1	Radix Salviae	1.74	0.91	Anti-inflammation [25]
cmp_A2	Gigeriae Galli Endothelium	2.69	0.82
cmp_A3	Panax Ginseng	3.47	1	COX-2 inhibition [24]
cmp_A4	Angelica sinensis Radix	3.69	1
cmp_A5	Jujubae Fructus	4.24	1	Antibacterial [28]
cmp_A6	Atractylodes macrocephala	4.37	0.91	Anti-inflammation [26]
cmp_A7	Lycii Fructus	4.60	0.91	Anti-inflammation [27]
cmp_A8	Fagopyrum esculentum	5.20	0.82
cmp_A9	Mori Follum	5.92	0.82
cmp_A10	Glycyrrhiza glabra L.	6.97	1	Anti-oxidation [29]

^a: the average predicted IC₅₀ values by a series of optimal regression models. ^b: the percentage of highly active inhibitors mapped to the target molecules in the same position during the self-organized map (SOM) training. It can also be taken as the probability of being predicted by an unsupervised algorithm as a highly active COX-2 inhibitor.