The OREGANO knowledge graph for computational drug repurposing

Drug repositioning is a faster and more affordable solution than traditional drug discovery approaches. From this perspective, computational drug repositioning using knowledge graphs is a very promising direction. Knowledge graphs constructed from drug data and information can be used to generate hypotheses (molecule/drug - target links) through link prediction using machine learning algorithms. However, it remains rare to have a holistically constructed knowledge graph using the broadest possible features and drug characteristics, which is freely available to the community. The OREGANO knowledge graph aims at filling this gap. The purpose of this paper is to present the OREGANO knowledge graph, which includes natural compounds related data. The graph was developed from scratch by retrieving data directly from the knowledge sources to be integrated. We therefore designed the expected graph model and proposed a method for merging nodes between the different knowledge sources, and finally, the data were cleaned. The knowledge graph, as well as the source codes for the ETL process, are openly available on the GitHub of the OREGANO project (https://gitub.u-bordeaux.fr/erias/oregano).

Automated summary

Drug repositioning is a faster and more affordable solution than traditional drug discovery approaches. Computational drug repositioning using knowledge graphs shows great promise. However, there is a lack of a holistically constructed knowledge graph with the broadest possible features and drug characteristics that is freely available to the community. The OREGANO knowledge graph aims to fill this gap.