Table 3. Comparison of proposed RGBM and RGENIE techniques with ENNET, GENIE and ARACNE GRN inference methods w.r.t. evaluation metrics AU_roc and AU_pr for reverse-engineering GRNs from RNA-Seq counts where the underlying ground-truth network follows a BA preferential attachment model with exponent α. Here no additional information (ABN or knockout or knockdown) is available.

Methods	RNA-Seq experiments
	Exponent α = 1.75		Exponent α = 2		Exponent α = 2.25		Exponent 2.5		Exponent 2.75
	AU pr	AU roc	AU pr	AU roc	AU pr	AU roc	AU pr	AU roc	AU pr	AU roc
RGBM	0.575	0.808	0.470	0.789	0.498	0.700	0.500	0.695	0.506	0.709
ENNET	0.566	0.802	0.454	0.780	0.495	0.685	0.494	0.684	0.494	0.684
RGENIE	0.605	0.846	0.528	0.785	0.270	0.652	0.272	0.626	0.274	0.641
GENIE	0.622	0.822	0.507	0.777	0.235	0.607	0.245	0.610	0.241	0.601
ARACNE	0.065	0.575	0.053	0.556	0.056	0.600	0.055	0.600	0.055	0.600