Skip to main content

Table 2 Our bacteria-human PPI benchmark datasets’ statistics

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

  Training data Testing data
\(|{\mathbf{E}}^{+}|\) \(|{\mathbf{E}}^{-}|\) \(|{\mathbf{V}}^{\mathbf{h}}|\) \(|{\mathbf{V}}^{\mathbf{b}}|\) \(|{\mathbf{E}}^{+}|\) \(|{\mathbf{E}}^{-}|\) \(|{\mathbf{V}}^{\mathbf{h}}|\) \(|{\mathbf{V}}^{\mathbf{b}}|\)
Bacillus anthracis 5366 15,590 1559 2674 3057 9440 944 1705
Yersinia pestis 4403 12,880 1288 2278 4020 12,150 1215 2147
Francisella tularensis 7077 21,590 2159 3041 1346 3440 344 1023
  1. \(|E^{+}|\) and \(|E^{-}|\) refer to the number of positive and negative interactions, respectively. \(|V^{h}|\) and \(|V^{b}|\) are the number of human proteins and bacteria proteins