Mining Linked Open Data: a Case Study with Genes Responsible for Intellectual Disability
Résumé
Increasing amounts of life sciences data are made available through the Linked Open Data (Bio2RDF, EMBL-EBI RDF platforms).We propose an approach to use Linked Open Data in order to answer a biological question. First, we select, collect and integrate Linked Open Data. We then mine the collected data using Inductive Logic Programming, a relational data mining method.We apply our approach on the task of characterization of genes responsible for Intellectual Disability, and build a model (or theory) predicting whether a gene is responsible for Intellectual Disability or not. We present obtained theories and evaluate them.Finally we assess the contribution of domain knowledge (Gene Ontology) to the quality of the characterization and prediction of these theories.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|