Gene regulatory network inference using PLS-based methods

BMC Bioinformatics

Table 3 Performance comparisons of different GRN inference methods on the DREAM4 networks, challenge size 100 Multifactorial

Method	Network 1		Network2		Network 3		Network 4		Network 5		Overall Score
Method	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	Overall Score
GENIE3	0.161	0.750	0.154	0.734	0.234	0.776	0.211	0.800	0.200	0.795	38.033
TIGRESS	0.158	0.747	0.161	0.703	0.233	0.761	0.225	0.774	0.233	0.754	36.590
CLR	0.143	0.701	0.117	0.695	0.174	0.744	0.181	0.753	0.175	0.723	29.112
ARACNE	0.122	0.605	0.102	0.603	0.201	0.691	0159	0.713	0.167	0.661	23.478
NIMEFI	0.157	0.758	0.157	0.731	0.248	0.776	0.225	0.806	0.241	0.801	40.762
PLSNET	0.118	0.713	0.290	0.828	0.202	0.794	0.228	0.819	0.206	0.786	46.046
Winner of the Challenge
GENIE3	0.154	0.745	0.155	0.733	0.231	0.775	0.208	0.791	0.197	0.798	37.428
2nd	0.108	0.739	0.147	0.694	0.185	0.748	0.161	0.736	0.111	0.745	28.165
3rd	0.140	0.658	0.098	0.626	0.215	0.717	0.201	0.693	0.194	0.719	27.053

The best results for each column are in bold. Numbers in the “Winner of competition” part of the table correspond to the best methods participating in the challenge as listed on the DREAM web site

ISSN: 1471-2105