Table 2 The comparison results of different models on GCIset, with bold values indicating the best performance among all competitive methods
From: EnGCI: enhancing GPCR-compound interaction prediction via large molecular models and KAN network
Baseline | AUC | PRC | Precision | Recall |
|---|---|---|---|---|
GraphDTA | 0.80153 | 0.78246 | 0.75234 | 0.70251 |
MGraphDTA | 0.84219 | 0.83757 | 0.76245 | 0.73156 |
TransformerCPI | 0.86135 | 0.85291 | 0.77753 | 0.81254 |
MFD-GDrug | 0.86294 | 0.86147 | 0.79125 | 0.75219 |
EnGCI | 0.88789 | 0.87732 | 0.82259 | 0.81377 |