Skip to main content

Table 1 The number of triples, entities and relation types related to each knowledge sources to be used for embedding learning

From: Evaluation of knowledge graph embedding approaches for drug-drug interaction prediction in realistic settings

Dataset

# of triples

# of entities

# of relation types

DrugBank

2,588,933

574,152

76

KEGG

14,362,294

4,362,395

301

PharmGKB

2,976,202

830,433

78

DrugBank + KEGG + PharmGKB

19,806,314

5,645,847

445

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us