Skip to main content

Table 4 Macro-AUC obtained by 5 ×5-fold cross-validation over Data-201706 for the nine competing methods

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

Method[1-10][11-30][31-100][101-300][ ≥301]
LR0.5260.5530.6330.7350.755
BiRW0.6080.8540.8750.8350.815
OGL0.5860.6700.7880.8120.806
DLP0.6220.8800.9140.8630.834
NMF0.6490.9080.9420.9480.911
NMF-PPN0.6510.9110.9430.9510.916
NMF-NHPO0.6530.9190.9460.9470.919
AiPA0.6540.9220.9430.9570.931
HPOAnnotator0.6550.9250.9470.9580.931
  1. Method performs best in terms of this evaluation metric are in boldface