Skip to main content

Table 2 Comparison of white-box methods on the task of DTI prediction, using 10-fold cross-validation on a balanced positive-to-negative ratio (1538:1538=1:1). Maximum length for SemaTyP DTD paths was set to \(l=4\)

From: Comparing methods for drug–gene interaction prediction on the biomedical literature knowledge graph: performance versus explainability

Metric

AnyBURL

SemaTyP

BLGPA

BLGPA PR

BLGPA PR+FS

Precision

0.86

0.84

0.90

0.90

0.90

Recall

0.44

0.80

0.88

0.89

0.89

F1-Score

0.58

0.82

0.89

0.90

0.89

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us