Table 3 Average test scores (± standard deviation) obtained by the different models in the pathway hold out use case (UC3). The suffix +emb indicates that protein sequence embeddings were concatenated to the I/O features. Best results are boldfaced
From: Sensitivity analysis on protein-protein interaction networks through deep graph networks
Model | MCC | F1 | ACC | AUROC |
|---|---|---|---|---|
Null | \(.000{\scriptstyle \pm .000}\) | \(.000{\scriptstyle \pm .000}\) | \(.678{\scriptstyle \pm .014}\) | \(.500{\scriptstyle \pm .000}\) |
DeepSets | \(.048\scriptstyle \pm .037\) | \(.259\scriptstyle \pm .169\) | \(.565\scriptstyle \pm .174\) | \(.634\scriptstyle \pm .037\) |
DeepSets+emb | \(.104\scriptstyle \pm .094\) | \(.320\scriptstyle \pm .186\) | \(.637\scriptstyle \pm .047\) | \(.554\scriptstyle \pm .087\) |
DGN | \(.230\scriptstyle \pm .074\) | \(\mathbf {.528\scriptstyle \pm .029}\) | \(.581\scriptstyle \pm .098\) | \(.631\scriptstyle \pm .086\) |
DGN+emb | \(\mathbf {.277\scriptstyle \pm .058}\) | \(.515\scriptstyle \pm .040\) | \(\mathbf {.682\scriptstyle \pm .030}\) | \(\mathbf {.657\scriptstyle \pm .041}\) |