Provenance-Centered Dataset of Drug-Drug Interactions

TL;DR

This paper introduces LIDDI, a comprehensive RDF dataset of drug-drug interactions that integrates multiple sources and prediction methods, facilitating research and comparison in drug interaction studies.

Contribution

The paper presents LIDDI, a linked dataset with curated mappings and integration of key prediction sources, enhancing reproducibility and data sharing in drug interaction research.

Findings

LIDDI includes multiple prediction sources and mappings.

The dataset uses trusty URIs for data integrity.

LIDDI enables better comparison of drug interaction data.

Abstract

Over the years several studies have demonstrated the ability to identify potential drug-drug interactions via data mining from the literature (MEDLINE), electronic health records, public databases (Drugbank), etc. While each one of these approaches is properly statistically validated, they do not take into consideration the overlap between them as one of their decision making variables. In this paper we present LInked Drug-Drug Interactions (LIDDI), a public nanopublication-based RDF dataset with trusty URIs that encompasses some of the most cited prediction methods and sources to provide researchers a resource for leveraging the work of others into their prediction methods. As one of the main issues to overcome the usage of external resources is their mappings between drug names and identifiers used, we also provide the set of mappings we curated to be able to compare the multiple sources we aggregate in our dataset.