Artificial Intelligence for Single-Cell Data Analysis (SCAI)
The Artificial Intelligence for Single-Cell Data Analysis (SCAI) team develops new statistical, machine learning, and artificial intelligence methods to address the challenges raised by single-cell and spatial omics data.
Recent advances in single-cell sequencing and spatial transcriptomics provide unprecedented views of the molecular processes that shape cells and tissues. At the same time, the increasing dimensionality, heterogeneity, and resolution of these data create major methodological challenges: distinguishing biological from technical variation, integrating multiple molecular and spatial measurements, and extracting robust and interpretable biological information.
Our research focuses on AI-driven statistical inference and explainable AI, with a particular emphasis on statistical risk control, scalability, and interpretability. Our goal is to develop methods that can characterize molecular and cellular variability across multiple scales, from individual cells to tissues, organisms, and cohorts.
We work in close collaboration with experimental and computational biologists, to develop methods driven by concrete biological questions and complex single-cell datasets.
We are part of the Laboratory of Biology and Modeling of the Cell (LBMC) in Lyon, France, a joint research institute of ENS de Lyon, CNRS, Inserm, and Université Claude Bernard Lyon 1.
News
Publications
See the dedicated publication page.
Software
See the dedicated software page.