Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data - Archive ouverte HAL Accéder directement au contenu
Poster De Conférence Année : 2016

Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data

Dhouha Grissa
  • Fonction : Auteur
  • PersonId : 771971
  • IdRef : 179415352
Mélanie Pétéra
Amedeo Napoli
Blandine Comte
Estelle Pujos-Guillot

Résumé

Untargeted metabolomics is a powerful phenotyping tool for better understanding biological mechanisms involved in human pathology development and identifying early predictive biomarkers. This approach, based on powerful analytical platforms, such as mass spectrometry, chemometrics and bioinformatics, generates massive and complex data that need appropriate analyses to extract biologically meaningful information [1]. In this context, this work consists in designing a workflow describing the general feature selection process, using knowledge discovery and data mining methodologies to propose advanced solutions for predictive biomarker discovery.
2016_Grissa_Feature selection_4th workshop_Thessalonique_{04FEB331-E9B8-413C-AA87-FBE7DD808304}.pdf (106.75 Ko) Télécharger le fichier
Format : Poster

Dates et versions

hal-01581591 , version 1 (04-09-2017)

Identifiants

  • HAL Id : hal-01581591 , version 1
  • PRODINRA : 354323

Citer

Dhouha Grissa, Mélanie Pétéra, Marion Brandolini-Bunlon, Amedeo Napoli, Blandine Comte, et al.. Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data. 4. Workshop on Holistic Analytical Methods for Systems Biology Studies, Apr 2016, Thessaloniki, Greece. , 2016, Metabolomics Workshop 2016. ⟨hal-01581591⟩
125 Consultations
56 Téléchargements

Partager

Gmail Facebook X LinkedIn More