Table 1.

Overview of the different datasets used for the validation of the fingerprints.

Task	Description	n Natural	n Synthetic	n Natural Active	n Synthetic Active	n Targets	Total n Compounds
NP Identification*	Distinguish between natural and synthetic compounds	1000	1000	-	-	-	1000
Target*	Distinguish between active and inactive natural products	896	0	312	0	7	896
NP & Target	Identify active natural products among active and inactive synthetic compounds and natural products	2321	91002	444	1877	14	93323

*published by Seo et al.[11].