A genetic algorithm-based weighted ensemble method for predicting transposon-derived piRNAs

BMC Bioinformatics

Table 9 Performances of GA-WE and the state-of-the-art methods in the cross-species prediction

Dataset	Species	Method	AUC	ACC	SN	SP
Balanced	Human	Piano	0.431	0.558	0.878	0.238
		piRNApredictor	0.850	0.783	0.781	0.784
		Ensemble Learning	0.845	0.774	0.764	0.784
		GA-WE	0.863	0.788	0.796	0.781
	Drosophila	Piano	0.367	0.587	0.905	0.270
		piRNApredictor	0.728	0.650	0.630	0.669
		Ensemble Learning	0.682	0.628	0.512	0.745
		GA-WE	0.687	0.668	0.639	0.698
Imbalanced	Human	Piano	0.426	0.747	0.000	1.000
		piRNApredictor	0.856	0.823	0.507	0.931
		Ensemble Learning	0.856	0.783	0.300	0.946
		GA-WE	0.868	0.811	0.425	0.942
	Drosophila	Piano	0.369	0.713	0.000	1.000
		piRNApredictor	0.783	0.773	0.422	0.915
		Ensemble Learning	0.750	0.736	0.275	0.921
		GA-WE	0.746	0.774	0.370	0.936

ISSN: 1471-2105