BMC Bioinformatics

Table 3 Performance comparison over five datasets in the S^D task

From: DTI-HeNE: a novel method for drug-target interaction prediction based on heterogeneous network embedding

Methods	Performance indicators	Datasets
Methods	Performance indicators	E	IC	GPCR	NR	DrugBank
DTI-HeNE	PR-AUC	0.908	0.912	0.982	0.980	0.921
	ROC-AUC	0.980	0.981	0.998	0.997	0.995
NEDD	PR-AUC	0.896	0.879	0.951	0.953	0.578
	ROC-AUC	0.986	0.982	0.998	0.993	0.959
DDR	PR-AUC	0.897	0.888	0.857	0.874	0.598
	ROC-AUC	0.972	0.983	0.958	0.941	0.895
NRLMFβ	PR-AUC	0.313	0.322	0.324	0.471	0.249
	ROC-AUC	0.679	0.735	0.824	0.892	0.669
DTINet	PR-AUC	0.270	0.320	0.298	0.250	0.316
	ROC-AUC	0.772	0.727	0.764	0.685	0.896
CMF	PR-AUC	0.193	0.190	0.355	0.450	0.047
	ROC-AUC	0.793	0.701	0.854	0.817	0.600
BLM-NII	PR-AUC	0.076	0.209	0.099	0.417	0.185
	ROC-AUC	0.752	0.754	0.593	0.792	0.884
NetLapRLS	PR-AUC	0.112	0.178	0.223	0.416	0.120
	ROC-AUC	0.782	0.750	0.806	0.782	0.855
BiNE	PR-AUC	0.766	0.751	0.588	0.724	0.316
	ROC-AUC	0.944	0.962	0.944	0.936	0.856

Best performing methods under the current dataset and performance indicator are indicated in bold

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com