Skip to main content

Table 4 Evaluation on the datasets DS56bound and DS56unbound

From: Predicting protein-protein interface residues using local surface structural similarity

Dataset Predictor Precision% Recall% F1% Accuracy% CC% AUC%
  Promate 31.9 27.3 29.4 76.7 15.6 63.3
  PINUP 37.3 31.9 34.4 78.4 21.7 63.7
DS56bound Cons-PPISP 39.8 36.1 37.9 78.9 25.2 72.6
  Meta-PPISP 43.3 25.8 32.3 80.8 22.9 74.4
  PrISE C spe. 46.1 45.4 45.7 80.9 34.1 77.6
  PrISE C hom. 43.6 42.4 43.0 80.0 30.9 76.3
  Promate 28.7 27.3 28.0 76.6 14.0 62.7
  PINUP 30.4 30.1 30.2 76.9 16.4 60.0
Ds56unbound Cons-PPISP 37.4 34.5 35.9 79.5 23.8 71.2
  Meta-PPISP 38.9 24.0 29.7 81.1 20.2 71.5
  PrISE C spe. 43.7 44.0 43.8 81.2 32.6 75.5
  PrISE C hom. 40.5 40.0 40.2 80.2 28.4 73.7
  1. "PrISE C spe." refers to the performance computed after filtering out from the repository samples extracted from homologs from the same species. "PrISE C hom." indicates that samples extracted from homologs were not considered in the prediction process.