Anne Siegel (CNRS, IRISA – Rennes, France): AI+ Science Schmidt Fellows Speaker Series

Organized by the University of Chicago’s Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship Program.

Agenda
4:00pm – 4:45pm:  Presentation
4:45pm – 5:00pm:  Q&A
5:00pm – 5:30pm: Reception

Meeting location
William Eckhardt Research Center. Room 401
5640 S Ellis Avenue, Chicago, IL 60637
Map It

Abstract: Life and environmental sciences generate vast amounts of biomolecular data, from genomes to environmental measurements. While these data offer valuable insights, their quality heterogeneity limits their use in comparative analyses and the identification of key signals. A critical challenge—spanning health and environmental sciences—is identifying discriminant biomarkers between ecosystems using diversity measures (metabarcoding). Although machine learning can highlight characteristic species biomarkers, its performance declines when shifting from species identification (“who”) to functional explanations (“why”), leading to reduced classification accuracy.

This presentation explores how combining symbolic data science (knowledge management and reasoning over dynamical systems) with machine learning enhances the analysis of large, heterogeneous data. This approach improves flexibility, robustness, performance, and interpretability in metabarcoding. Applications include identifying species driving key functions in bioreactors, classifying patients by microbiome composition, and pinpointing essential species in extreme environments based on their functions.

Bio: Anne Siegel, Deputy Scientific Director, CNRS. Anne graduated from the Ecole Normale Superieure de Lyon and is a research director in computer science at the CNRS. Following her thesis in mathematics, her research focused in theoretical computer sciences and then shifted to bioinformatics, at the IRISA laboratory (Institute For Research In IT And Random Systems), where she develops methods combining dynamic systems analysis and reasoning on data and knowledge to model in silico the capacity of species to produce molecules of interest in the context of various interdisciplinary programs.

She created and directed the research team Dyliss in her laboratory, then headed a department of the laboratory, before becoming Deputy Scientific Director of the CNRS division of Information Sciences and their Interaction (INS2I). At CNRS-INS2I, she promotes interdisicplinarity between computer sciences and other disciplines, she monitors research networks, and is in charge of the gender-equality policy.

Parking
Campus North Parking
5505 S Ellis Ave
Map It