Skip to main content

Table 8 Results of the 10-fold cross-validation of our Graph Kernel/SVM model

From: Learning from biomedical linked data to suggest valid pharmacogenes

  F-measure Avg. F-measure AUC-ROC
Balanced 0.770 0.761 0.840
Unbalanced 0.746 0.807 0.905
  1. Models are trained with 91 positive and 91 negative examples for the Balanced model and 91 and 182 for the Unbalanced