A comparison of approaches to accessing existing biological and chemical relational databases via SPARQL

0573624 - ÚOCHB 2024 RIV GB eng J - Journal Article
Galgonek, Jakub - Vondrášek, Jiří
A comparison of approaches to accessing existing biological and chemical relational databases via SPARQL.
Journal of Cheminformatics. Roč. 15, č. 1 (2023), č. článku 61. ISSN 1758-2946. E-ISSN 1758-2946
R&D Projects: GA MŠMT(CZ) LM2018131
Institutional support: RVO:61388963
Keywords : Resource Description Framework * relational database * RDB-to-RDF mapping * SPARQL
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 8.6, year: 2022
Method of publishing: Open access
https://doi.org/10.1186/s13321-023-00729-5

Current biological and chemical research is increasingly dependent on the reusability of previously acquired data, which typically come from various sources. Consequently, there is a growing need for database systems and databases stored in them to be interoperable with each other. One of the possible solutions to address this issue is to use systems based on Semantic Web technologies, namely on the Resource Description Framework (RDF) to express data and on the SPARQL query language to retrieve the data. Many existing biological and chemical databases are stored in the form of a relational database (RDB). Converting a relational database into the RDF form and storing it in a native RDF database system may not be desirable in many cases. It may be necessary to preserve the original database form, and having two versions of the same data may not be convenient. A solution may be to use a system mapping the relational database to the RDF form. Such a system keeps data in their original relational form and translates incoming SPARQL queries to equivalent SQL queries, which are evaluated by a relational-database system. This review compares different RDB-to-RDF mapping systems with a primary focus on those that can be used free of charge. In addition, it compares different approaches to expressing RDB-to-RDF mappings. The review shows that these systems represent a viable method providing sufficient performance. Their real-life performance is demonstrated on data and queries coming from the neXtProt project.
Permanent Link: https://hdl.handle.net/11104/0344026


Research data: Zenodo, GitHub