Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data
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.
| Format | Poster |
|---|