Mining Linked Open Data: a Case Study with Genes Responsible for Intellectual Disability

Gabin Personeni 1, * Simon Daget 1 Céline Bonnet 2 Philippe Jonveaux 2 Marie-Dominique Devignes 1 Malika Smaïl-Tabbone 1 Adrien Coulet 1
* Auteur correspondant
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : 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.
Type de document :
Poster
ECCB'14 (European Conference on Computational Biology 2014), Sep 2014, Strasbourg, France. 2014, 〈http://www.eccb14.org/〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01092800
Contributeur : Gabin Personeni <>
Soumis le : mardi 9 décembre 2014 - 15:02:07
Dernière modification le : jeudi 11 janvier 2018 - 06:25:24
Document(s) archivé(s) le : mardi 10 mars 2015 - 11:51:15

Fichier

Poster.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01092800, version 1

Collections

Citation

Gabin Personeni, Simon Daget, Céline Bonnet, Philippe Jonveaux, Marie-Dominique Devignes, et al.. Mining Linked Open Data: a Case Study with Genes Responsible for Intellectual Disability. ECCB'14 (European Conference on Computational Biology 2014), Sep 2014, Strasbourg, France. 2014, 〈http://www.eccb14.org/〉. 〈hal-01092800〉

Partager

Métriques

Consultations de la notice

252

Téléchargements de fichiers

158