Skip to main content

Table 13 Macro-AUC obtained by focusing on Organ abnormality

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]
NMF-Organ0.6450.8970.9240.9450.922
NMF-PPN-Organ0.6540.9210.9430.9560.934
NMF-NHPO-Organ0.6520.9260.9420.9580.936
NMF-All0.6450.9060.9390.9410.912
NMF-PPN-All0.6510.9240.9410.9540.919
NMF-NHPO-All0.6500.9280.9400.9530.935
HPOAnnotator-All0.6550.9290.9460.9550.938
  1. The three rows with “Organ" use only organ abnormality for training, while the others with “All" take all sub-ontologies for training.
  2. Method performs best in terms of this evaluation metric are in boldface