Machine learning methods for integrated analysis of discrete neurophysiological and behavioral symptoms of chronic stress in preclinical studies

Chronic stress is a risk factor for mental disorders, including depression, whose treatment remains a medical challenge. Current research strategies focus on uncovering the links between specific symptoms of the disease and dysfunctions in brain structures, networks, cells, and molecular processes. Understanding these relationships requires combining pharmacological and genetic manipulations with precise behavioral and physiological measurements in preclinical animal studies.

The goal is to enhance an existing system for automated analysis of social behavior in mice by incorporating neurophysiological recordings using non-invasive EEG. The project also involves developing machine learning methods for integrated data analysis, leveraging these tools to identify discrete stress-induced phenotypes and assess their modifiability by tested drugs. The unique platform and precise phenotyping algorithms will be applied in both research and commercial projects.

Duration: 01.10.2024 - 30.09.2028

Funding: 387 222,82 PLN