Skip to main content

Table 1 The experimental results of CNN-DDI on three similarity measures

From: CNN-DDI: a learning-based method for predicting drug–drug interactions using convolution neural networks

Similarity

ACC

AUPR

AUC

F1

Precision

Recall

Jaccard

0.8871

0.9251

0.9980

0.7496

0.8556

0.7220

Cosine

0.8871

0.9251

0.9979

0.7492

0.8855

0.7721

Gaussian

0.8870

0.9248

0.9979

0.7489

0.8859

0.7720