Skip to main content

Table 6 Performance of NMF-PPN with individual PPNs

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

Data scourceAUPRmicro-AUPRmacro-AUPR
STRING0.5250.2810.142
GeneMANIA0.5230.2800.143
BioGRID0.5170.2800.140
Reactome0.5050.2780.139
All0.5450.2830.145
  1. Results are for each PPN on the Data-201706. “All” means all four PPNs are used.
  2. Method performs best in terms of this evaluation metric are in boldface