Skip to main content

Table 1 List of categories for each dataset used to evaluate FAUN classification performance. GC is the gene count per category.

From: Discovering gene functional relationships using FAUN (Feature Annotation Using Nonnegative matrix factorization)

Dataset 1 (50TG)
GC Category
15 Cancer
11 Alzheimer
5 Development
16 Cancer & Development
3 Alzheimer & Development
Dataset 2 (BGM)
GC Category
21 Biocarta: Caspase cascade in apoptosis
8 Biocarta: Sonic hedgehog pathway
10 Biocarta: Adhesion and diapedesis of lymphocytes
10 GO: Biological process: telomere maintenance
7 GO: Cellular constituent: cornified cell envelope
20 GO: Molecular function: DNA helicase
8 MeSH: Disease: retinitis pigmentosa
8 MeSH: Disease: retinitis pancreatitis
10 MeSH: Disease: nephroblastoma (Wilm’s tumor)
Dataset 3 (NatRev)
GC Category
26 Autism
10 Diabetes
25 Translation
37 Mammary Gland Development
12 Fanconi Anemia