Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data

Fig. 3

The number of identified testing interactions (a) top 10,000 predictions; (b) top 15, 000 predictions. 1: Vilar’s substructure-based model (6626, 7527); 2: Vilar’s CN index-based model (6667, 7639); 3: Substructure-based label propagation model (6597, 7515); 4: Side effect-based Label propagation model (6641, 7573); 5: Off side effect-based label propagation model (6693,7591); 6: Weighted average ensemble method (6923, 7842); 7: L1 Classifier ensemble method (7027, 7972); 8: L2 Classifier ensemble method (6980, 7942)

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us