HPOAnnotator: improving large-scale prediction of HPO annotations by low-rank approximation with HPO semantic similarities and multiple PPI networks

Table 3 The results of the eight criteria obtained by 5 ×5-fold cross-validation over Data-201706 for the nine competing methods in total

Method	AUC	AUPR	micro-AUC	micro-AUPR	macro-AUC	macro-AUPR	leaf-AUC	leaf-AUPR
LR	0.775	0.028	0.760	0.072	0.579	0.052	0.532	0.020
BiRW	0.875	0.066	0.826	0.096	0.732	0.056	0.597	0.031
OGL	0.785	0.051	0.776	0.078	0.603	0.034	0.536	0.014
DLP	0.902	0.073	0.875	0.100	0.736	0.094	0.659	0.055
NMF	0.961	0.496	0.900	0.273	0.753	0.139	0.701	0.089
NMF-PPN	0.963	0.525	0.902	0.281	0.756	0.142	0.703	0.089
NMF-NHPO	0.965	0.541	0.903	0.290	0.756	0.144	0.702	0.094
AiPA	0.970	0.559	0.905	0.295	0.760	0.146	0.705	0.096
HPOAnnotator	0.971	0.562	0.907	0.296	0.760	0.152	0.706	0.097

ISSN: 1755-8794