. 2018 Jan 19;46(7):e39. doi: 10.1093/nar/gky015

Table 1. Comparison of RGBM and RGENIE with a other of inference methods on DREAM3 and DREAM4 networks of size 100.

Methods	Data used	DREAM3 experiments
		Network 1		Network 2		Network 3		Network 4		Network 5
		AU _pr	AU _roc	AU _pr	AU _roc	AU _pr	AU _roc	AU _pr	AU _roc	AU _pr	AU _roc
RGBM (LS-Boost)	KO,KD,WT	0.699	0.903	0.888	0.965	0.597	0.900	0.571	0.861	0.460	0.787
RGBM (LAD-Boost)	KO,KD,WT	0.683	0.903	0.870*	0.963*	0.562*	0.900	0.535*	0.853*	0.400	0.770
ENNET	KO,KD,WT,MTS	0.627	0.901	0.865⁺	0.963⁺	0.552⁺	0.892	0.522⁺	0.842	0.384	0.765
RGENIE	KO,KD,WT	0.521	0.870	0.821⁻	0.899	0.456	0.812	0.478⁻	0.778	0.356	0.718
GENIE	KO,KD,WT	0.430	0.850	0.782	0.883	0.372	0.729	0.423	0.724	0.314	0.656
iRafNet	KO,KD,WT	0.528	0.878	0.812	0.901	0.484	0.864	0.482	0.772	0.364	0.736
ARACNE	KO,KD,WT	0.348	0.781	0.656	0.813	0.285	0.669	0.396	0.662	0.274	0.583
Winner (72)	KO, WT	0.694	0.948	0.806	0.960	0.493	0.915	0.469	0.853	0.433	0.783
Methods	Data Used	DREAM4 Experiments
		Network 1		Network 2		Network 3		Network 4		Network 5
		AU_pr	AU_roc	AU_pr	AU_roc	AU_pr	AU_roc	AU_pr	AU_roc	AU_pr	AU_roc
RGBM (LS-Boost)	KO,KD,WT,MTS	0.709	0.936	0.561	0.878*	0.525	0.911	0.616	0.903	0.450	0.893
RGBM (LAD-Boost)	KO,KD,WT,MTS	0.682*	0.924*	0.525*	0.895	0.490*	0.907*	0.566*	0.903	0.413*	0.885*
ENNET	KO,KD,WT	0.604⁺	0.893	0.456⁺	0.856⁺	0.421⁺	0.865⁺	0.506⁺	0.878⁺	0.264⁺	0.828⁺
RGENIE	KO,WT	0.448	0.902	0.330	0.792	0.374	0.834⁻	0.362⁻	0.840	0.218⁻	0.773⁻
GENIE	KO,WT	0.338	0.864	0.309	0.748	0.277	0.782	0.267	0.808	0.114	0.720
iRafNet	KO,TS	0.552	0.901	0.337	0.799	0.414	0.835	0.421	0.847	0.298	0.792
ARACNE	KO,KD,WT	0.279	0.781	0.256	0.691	0.205	0.669	0.196	0.699	0.074	0.583
Winner (73)	KO	0.536	0.914	0.377	0.801	0.390	0.833	0.349	0.842	0.213	0.759

Here, we provide the mean AU_pr and AU_roc values for 10 random runs of different inference methods. Here, KO, knockout; KD, knockdown; WT, wildtype; MTS, modified smoothed version of the time-series data. The best results are highlighted in bold. *, +, − represent the quality metric values where RGBM (LAD-Boost), ENNET and RGENIE techniques, respectively outperform the winner of DREAM3 and DREAM4 challenges.