Table 1.

Datasets of ncRNAs and CDS of microalgae

Group of microalgae	Types of sequences	Training dataset	Training dataset after balancing	Test dataset
Diatom	ncRNAs	1234	1125a	308
	CDS	356	1125*	88
Golden algae	ncRNAs	168	1125*	41
	CDS	60	1125*	15
Green algae	ncRNAs	1973	1125a	493
	CDS	6818	1125a	1704
Cyanobacteria	ncRNAs	13,116	3375a	3280
	CDS	5448	3375a	1363

^aData generated by random selection; * Data generated by SMOTE