Skip to main content

Table 3 Relative coverage of protein-protein interactions present in the training and test data by individual feature clusters

From: Computational prediction of the human-microbial oral interactome

  Training data Classification
  #Interactions % of total #Interactions % of total
Literature 22,720 61.9% 4,698,390 69.9%
Sequence 35,379 96.4% 6,703,945 99.8%
GO 23,769 64.8% 5,130,103 76.4%
COGs 9,636 26.3% 1,324,230 19.7%
DDIs 5,994 16.3% 516,609 7.7%
Total 36,698 100.0% 6,716,792 100.0%
  1. GO, gene ontology; COGs, clusters of orthologous groups; DDIs, domain-domain interactions.