arrow drop search cross

Data Sciences for Deep Phenotyping and Precision Medicine

Seminar held on October 24 by Dr. Etienne Thévenot at the MSI's premises in Sophia Antipolis

24/10/2019   :   10h00
MSI (Salle des séminaires) 1361 Route des Lucioles, 06560 Valbonne, France
 Speaker: Dr. Etienne Thévenot (CEA Paris-Saclay)
Publication : 24/10/2019
Partager cet article :

Speaker: Dr. Etienne Thévenot (CEA Paris-Saclay)

Abstract: Data sciences provide powerful approaches and algorithms (signal processing, data mining, machine learning, artificial intelligence) for the processing and analysis of high-dimensional data, such as omics datasets. Metabolomics (untargeted analysis of small molecules involved in biochemical reactions) is of major interest for phenotype characterization and biomarker discovery. High-resolution mass spectrometry (HRMS) is a technology of choice for metabolomics (and also for proteomics), due to its sensitivity and resolution.

Metabolomics data science is challenging for many reasons, including:

  •  The specificity of the signal generated by mass spectrometry instruments (retention time dimension, heteroscedastic noise, analytical drift);
  •  The high-dimension and correlation between variables;
  •  The complexity of structural characterization of the metabolites based on their mass and fragmentation patterns.

For the past 10 years, our team has been developing innovative methods and tools to tackle these challenges.