TABLE 4.

Publicly available datasets for RNA-protein interaction prediction.

Dataset	# Of positive interactions	# Of negative interactions	Description	Negative set strategy	References
RPI2241	2241	2241	Structure-based dataset, containing RNA-protein interactions enriched in ribosomal RPIs	Random Pairing	Muppirala et al. (2011)
RPI369	369	369	Structure-based dataset, obtained from RPI2241 after removal of interactions derived from ribosomal complexes	Random Pairing	Muppirala et al. (2011)
RPI488	243	245	Structure-based dataset, comprising interactions between proteins and different classes of RNAs	Least atom distance	Pan et al. (2016)
RPI1807	1807	1436	Structure-based dataset, comprising interactions between proteins and different classes of RNAs	Least atom distance	Suresh et al. (2015)
NPInter10412	10,412	-	Non structure-based dataset, comprising RNA-protein interactions integrated from literature mining and other databases	-	Yuan et al. (2014);
					Suresh et al. (2015)