Team presentation

Our overall goal is to develop innovative numerical methods for neuropharmacology, the search of new drug candidates to treat brain diseases. We use machine learning to integrate multiscale information sources (molecular data from cell cultures, brain imaging, clinical data) into a coherent stream of data and expert knowledge. We also develop mechanistic modeling approaches (multiscale quantitative systems biology/pharmacology) to produce explanations for the predictions of the machine learning algorithms, that can be rooted in neurobiology. Another central aspect of AIstroSight is to widen the focus of neuropharmacology beyond neurons, that constitute only one part of the nerve cells in the brain, and also take into account the other half, that is made up by glial cells. In particular, we consider the pharmacology of astrocytes, one major subtype of glial cells, in interaction with the pharmacology of neurons. 

To accelerate cross-fertilization between digital science and medical research, AIstroSight is built as a joint team between:


Research themes

  • In vitro and in vivo experimental models of neurology diseases. Producton of preclinical molecular and imaging data to better delineate the perturbations that brain diseases cause at a cellular and tissue level
  • Identification of multi-source multi-scale biomarkers. Integration of cellular and molecular data (omics), neuroimaging data and clinical data for brain diseases.
  • Multi-patient query for care pathway characterization and clinical trials. Computational phenotyping, i.e. the querying of patients according to complex predefined criterions from a large population of hospital electronic health records.
  • Characterizing the mechanisms of action of candidate drugs. Mechanistic models of regulatory networks or intracellular signaling pathways specific to the action of the candidate drugs, in neurons, astrocytes and their interactions.  

AIStroSight roapmap

Comments are closed.