Skip to main content

Table 3 The prediction result of multi-type DDIs

From: Predict multi-type drug–drug interactions in cold start scenario

Method Multi-type
\(S1\) \(S2\)
AUC AUPR F1-micro AUC AUPR F1-micro
TransE + RandomForest 0.8163 0.2853 0.5163 0.3843 0.0926 0.4040
DeepDDI(S) 0.8864 0.4638 0.6042 0.4500 0.1720 0.4825
DDIMDL(SP) 0.8832 0.4597 0.6292 0.4337 0.2062 0.5173
CSMDDI-RESCAL 0.8658 0.5865 0.7168 0.4313 0.2003 0.5103
  1. (S) denotes that the inputs of the prediction method are chemical substructures
  2. (P) denotes that the inputs of the prediction method are drug-associated proteins