Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings
journal contributionposted on 05.12.2018 by Maxat Kulmanov, Şenay Kafkas, Andreas Karwath, Alexander Malic, Georgios V Gkoutos, Michel Dumontier, Robert Hoehndorf
Any type of content formally published in an academic journal, usually following a peer-review process.
Recent developments in machine learning have led to a rise of large
number of methods for extracting features from structured data. The features
are represented as vectors and may encode for some semantic aspects of data.
They can be used in a machine learning models for different tasks or to com-
pute similarities between the entities of the data. SPARQL is a query language
for structured data originally developed for querying Resource Description Frame-
work (RDF) data. It has been in use for over a decade as a standardized NoSQL
query language. Many different tools have been developed to enable data shar-
ing with SPARQL. For example, SPARQL endpoints make your data interopera-
ble and available to the world. SPARQL queries can be executed across multi-
ple endpoints. We have developed a Vec2SPARQL, which is a general frame-
work for integrating structured data and their vector space representations.
Vec2SPARQL allows jointly querying vector functions such as computing sim-
ilarities (cosine, correlations) or classifications with machine learning models
within a single SPARQL query. We demonstrate applications of our approach
for biomedical and clinical use cases. Our source code is freely available at
https://github.com/bio-ontology-research-group/vec2sparql and we make a
Vec2SPARQL endpoint available at http://sparql.bio2vec.net/