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 scource

AUPR

micro-AUPR

macro-AUPR

STRING

0.525

0.281

0.142

GeneMANIA

0.523

0.280

0.143

BioGRID

0.517

0.280

0.140

Reactome

0.505

0.278

0.139

All

0.545

0.283

0.145

  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
Back to article page

BMC Medical Genomics

ISSN: 1755-8794

Contact us