Skip to main content

Table 2 Results for SVMs trained on a subset of features

From: Prediction of hot spot residues at protein-protein interfaces by combining machine learning and energy-based methods

Method Precision Recall F1 score MCC
SVM-sc 0.47 ± 0.02 0.64 ± 0.03 0.54 ± 0.02 0.38 ± 0.02
SVM-env 0.43 ± 0.03 0.72 ± 0.05 0.54 ± 0.03 0.37 ± 0.04
  1. SVM-sc: only side chains terms included; SVM-env: only environment terms included.