PFBNet: a priori-fused boosting method for gene regulatory network inference

BMC Bioinformatics

Table 2 Comparison of different methods on the DREAM4 in-silico size 100 challenge networks (without utilizing the information from prior data)

Method	GENIE-lag		Jump3		BiXGBoost		PFBNet
Data used	TS		TS		TS		TS
Metrics	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC
Network_1	0.183	0.791	0.270	0.772	0.235	0.806	0.360	0.831
Network_2	0.109	0.708	0.110	0.665	0.152	0.730	0.210	0.768
Network_3	0.224	0.765	0.200	0.741	0.261	0.765	0.343	0.794
Network_4	0.163	0.745	0.180	0.699	0.204	0.735	0.302	0.788
Network_5	0.148	0.796	0.174	0.735	0.214	0.769	0.337	0.829

The highest averaged AUPR and AUROC values are marked in bold for each network. TS, time-series expression data

ISSN: 1471-2105