Eric KrejciCNRS research director at Centre Borelli - Université Paris Cité & ENS Paris saclay
Thibaut GermainPhD student at Centre Borelli - Université Paris Cité & ENS Paris saclay
- 30 Jan 2023
- 11 h 00 min - 12 h 00 min
- INCC Seminar Series
Interpretable classification of ventilation behaviors based on machine learning, by Eric Krejci and Thibaut Germain
Interpretable classification of ventilation behaviors based on machine learning
Ventilation is a simple physiological function that ensures the vital supply of oxygen and the elimination of CO2. The recording of the airflow through the nostrils of a mouse over time makes it possible to calculate the position of critical points, based on the shape of the signals, to compute the respiratory frequency and the volume of air exchanged. These descriptors only account for a part of the dynamics of respiratory exchanges. We will present a new algorithm that directly compares the shapes of signals and considers meaningful information about the breathing dynamics omitted by the previous descriptors. The algorithm leads to a new classification of inspiration and expiration, which reveals that mice respond and adapt differently to inhibition of cholinesterases, enzymes targeted by nerve gas, pesticide, or drug intoxication.
Eric Krejci is a CNRS research director at Centre Borelli. He has been interested in cholinesterases for many years. After identifying the genes that ensure the localization of the enzymes in the brain, muscles, and most tissues, he has developed genetic approaches targeting the enzymatic activity of these enzymes to find out where acetylcholine is toxic. He is currently developing strategies to quantify the alterations caused by the mutations in mice. These approaches are possible thanks to the new technologies for classifying biological signals developed in Centre Borelli.
Thibaut Germain is a PhD student at Centre Borelli under the supervision of Charles Truong and Laurent Oudre. His work focuses on developing methods to characterize and simplify signals (time series) based on fine descriptions of their local shapes.