Home // DBKDA 2015, The Seventh International Conference on Advances in Databases, Knowledge, and Data Applications // View article

Towards Implementing Semantic Literature-Based Discovery with a Graph Database

Authors:
Dimitar Hristovski
Andrej Kastrin
Dejan Dinevski
Thomas C Rindflesch

Keywords: Data science; Databases; Data mining; Semantics; Literature-based discovery

Abstract:
Literature-based discovery (LBD) combines known facts in the scientific literature to generate discoveries, or hypotheses. Potential discoveries have the form of relations between concepts; for example, in the biomedical domain (on which we concentrate), a drug may be determined to treat a disease other than the one for which it was intended. We view the domain knowledge underpinning LBD as a network consisting of a set of concepts along with the relations connecting them. In the study presented here, we used SemMedDB, a database of semantic relations between biomedical concepts extracted with SemRep from MEDLINE. SemMedDB is distributed as a MySQL relational database, which is not optimal for dealing with network data. We transformed and uploaded SemMedDB into a Neo4j graph database, and implemented the basic LBD discovery algorithms with the Cypher query language. We conclude that storing the data needed for semantic LBD is facilitated by a graph database. Also, implementing LBD discovery algorithms is conceptually simpler with a graph query language when compared with standard SQL.

Pages: 180 to 184

Copyright: Copyright (c) IARIA, 2015

Publication date: May 24, 2015

Published in: conference

ISSN: 2308-4332

ISBN: 978-1-61208-408-4

Location: Rome, Italy

Dates: from May 24, 2015 to May 29, 2015