ENNET: inferring large gene regulatory networks from expression data using gradient boosting

BMC Systems Biology

Table 2 Results of the different inference methods on DREAM3 networks, challenge size 100

Method	Network (AUPR/AUROC respectively)										Overall
Method	1		2		3		4		5		Overall
Experimental results
ENNET	0.627	0.901	0.865	0.963	0.568	0.892	0.522	0.842	0.384	0.765	>300
Winner of the challenge
Yip et al.	0.694	0.948	0.806	0.960	0.493	0.915	0.469	0.856	0.433	0.783	>300
2nd	0.209	0.854	0.249	0.845	0.184	0.783	0.192	0.750	0.161	0.667	45.443
3nd	0.132	0.835	0.154	0.879	0.189	0.839	0.179	0.738	0.164	0.667	42.240

Results of the different inference methods on DREAM3 networks, challenge size 100. An area under the ROC curve (AUROC) and an area under the Precision-Recall curve (AUPR) are given for each network respectively. The overall Score for all the networks is given in the last column. The best results for each column are in bold. Numbers in the “Experimental results” part of the table were collected after running the algorithms with the default sets of parameters on pre-processed data. However, ADANET, GENIE3, CLR, C3NET, MRNET, and ARACNE methods, as they are originally defined, take a multifactorial matrix as an input, which is unavailable in this challenge. Therefore they were excluded from the comparison. Numbers in the “Winner of the challenge” part of the table correspond to the best methods participating in the challenge.

ISSN: 1752-0509