Contributions à l'extraction de connaissances à partir de données biologiques

Malika Smaïl-Tabbone 1
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : One challenge for scientists consists in optimally exploiting the data stored in numerous public resources. This challenge is especially crucial in life sciences regarding the extraordinary multiplicity and heterogeneity of biological data. Our aim is to assist biologists for analysing such data and efficiently extract useful knowledge for solving problems such as charaterizing genes responsible for a disease or understanding drug-side-effect profiles. Our contribution can be summarised with respect to the three key steps of the Knowledge Discovery from Databases (KDD) process : (1) resource discovery and model-driven data integration, (2) relational data mining deployment based on inductive logic programming for extracting explicit rules in first-order logic, and (3) contribution to the interpretation of the mining results thanks to inductive batabases principles. We could show on real world problems how the third point facilitates further iterations of the KDD process.
Complete list of metadatas

https://hal.inria.fr/tel-01093943
Contributor : Malika Smail-Tabbone <>
Submitted on : Friday, January 23, 2015 - 2:15:32 PM
Last modification on : Monday, September 23, 2019 - 5:12:17 PM
Long-term archiving on : Saturday, April 15, 2017 - 8:31:09 PM

Identifiers

  • HAL Id : tel-01093943, version 2

Citation

Malika Smaïl-Tabbone. Contributions à l'extraction de connaissances à partir de données biologiques. Apprentissage [cs.LG]. Université de Lorraine, 2014. ⟨tel-01093943v2⟩

Share

Metrics

Record views

1365

Files downloads

482