Skip to main content

Table 3 Performance comparison on Drugbank and Twosides datasets for the random split scheme

From: On the robustness of generalization of drug–drug interaction models

Dataset

Method

AUROC

AUPRC

Drugbank

DeepDDI [17]

0.994

0.866

NDD [32]

0.954

0.922

1D-CNN (Ours)

0.999

0.96

SSI-DDI [28]

0.983

0.981

Twosides

MHCADDI [19]

0.882

GENN [51]

0.886

0.260

1D-CNN (Ours)

0.889

0.420