Skip to main content

Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 3 GO terms giving a high prediction quality using only one data source

From: Integrative approaches to the prediction of protein functions based on the feature selection

Data source GO Term NPWGD NPWG AUC P20R DA
OPHID (PPI) 0048489 synaptic vesicle transport 13 14 0.92 0.39 0.17
  0006887 exocytosis 21 27 0.91 0.87 0.12
Interpro (Domain) 0006071 glycerol metabolism 10 11 0.87 0.8 0.44
  0000160 two-component signal transduction system (phosphorelay) 10 10 1 1 0.41
  0006801 superoxide metabolism modification-dependent 10 10 0.93 1 0.31
  0043632 macromolecule catabolism 47 47 0.96 0.5 0.28
  0006508 proteolysis 233 240 0.92 0.69 0.28
  0006812 cation transport 173 176 0.90 0.93 0.15
Pfam (Domain) 0016311 dephosphorylation 48 51 0.97 0.81 0.35
  0006338 chromatin remodeling 21 22 0.91 0.28 0.33
  0031497 chromatin assembly protein amino acid 29 30 0.97 0.63 0.32
  0006470 Dephosphorylation 46 49 0.98 0.69 0.31
  0006333 chromatin assembly or disassembly 41 42 0.96 0.71 0.3
MGI (Phenotype) 0008344 adult locomotory behavior 14 19 0.9 0.21 0.31
  0030534 adult behaviour 18 23 0.9 0.21 0.3
  0007605 sensory perception of sound 26 40 0.94 0.55 0.27
  0048232 male gamete generation 44 70 0.93 0.34 0.26
  0007283 spermatogenesis 44 70 0.94 0.28 0.25
  0000003 reproduction 101 152 0.87 0.52 0.20
OMIM (Diseases) 0008643 carbohydrate transport 11 30 0.94 0.87 0.15
Zhang et al. (Gene expression) 0001502 cartilage condensation 10 10 0.85 0.23 0.15
  1. GO terms and data sources displaying the outstanding contributions to the prediction of the given GO term are listed, where only part of the lists among the GO terms covering greater than or equal to 10 proteins are presented. NPWGD stands for number of proteins having the given GO term and the given data source, NPWG is the number of proteins with the given GO term, and DA is the difference between the AUC score and the second highest accuracy.