Skip to main content

Table 3 Comparison between MTT and Barman—a method that relies on the protein domain information

From: A multitask transfer learning framework for the prediction of virus-human protein–protein interactions

Model AUC AP Precision Recall F1
Barman 0.7300 67.00 69.41
MTT 0.9804 0.9802 93.53 94.05 93.79
  1. Due to data and code availability issues, for the Barman method, we only have results for the Barman ’s dataset, which are also taken from the original paper. ‘−’ indicates that the result is not available