I’m broadly interested in data science and machine learning, both from a theoretical perspective and through its application to environmental sciences. Applications I’m involved in mainly focus on microbial metagenomics, but also include climate change impact on biodiversity and glacier mass balance modelling.
From geochemical cycles to human health, microbiomes play key roles in ecosystems. By sampling genomic DNA information directly from the environment - coined as metagenomics - we are able to study the associations, diversity and functions of micro-organisms.
I am interested in developing data science methods to study microbiomes through the lens of DNA information. More specifically, I am currently interested by:
- Theory of auto-encoders
- Optimal transport
- Properties of some optimization algorithms
- (Viral) metagenomics
- Phage-host interactions
- Metagenomic gene binning
- Human gut MWAS
- High throughput metagenomic sequence annotation
- Climate change impact on biodiversity
- Glacier mass balance modelling
- Benjamin Fayolle (2020-): Quantifying the Impact of Environmental Parameters on Biodiversity.
- LSc internship (6 months): R. Bucio
- MSc1 internships: M. Roux, M. Schneider
- PhD student (visitor): B. Matougui
- MSc1 internships: M. Hérault, A. Poché
- Msc2 internships: V. Zinchenko, C. Norroy
- MSc1 internships: R. Zhang
- MSc1 internships: V. Mudryi, V. Zinchenko (M1)
See my Scholar page.
I have a collaboration with In&Motion for large-scale classification of temporal sequences.
- 2020: Maimosine (17k€), PersyvalLab (108k€)
- 2019: GdR Stat&Santé (4k€), Grenoble DataInstitute (10k€)