ID 2343: Developing Machine Learning Methods for Genetic and Physiological Analysis in Depression

Master’s Thesis


In recent years, there has been increasing focus on the immune system’s involvement in psychiatric disorders, including Major Depressive Disorders (MDD). Genetic variants associated with MDD have been linked to immune response pathways. Additionally, genetic factors have been found to influence sleep profiles in depressed patients. Despite advances in genomics and real-world physiological data, the relationship between genomic factors and sleep in depression remains underexplored. This project aims to contribute to health data science by developing machine learning methods for depression-subgroup analysis.



Investigate a sample of n~350 individuals from studies at the Max Planck Institute of Psychiatry. Leverage -omics data (immune markers, transcriptomics, genetics) and physiological data recordings to design, implement, and validate algorithms for joint analysis.



  • Familiarize with physiological and genomic data analysis approaches.
  • Extend an existing physiological data analysis framework with a focus on sleep in depressed patients.
  • Validate the framework using real-world physiological data, combining actigraphy with ECG data (HR, HRV, and ECG features).
  • Integrate existing genomic analysis methods (partially available in Dr. Knauer-Arloth’s group) into a joint framework.
  • Address the research question on transcriptomic effects of decreased sleep to establish a potential link between sleep deprivation and immune-related depression.



  • Strong interest in interdisciplinary challenges in mental health.
  • Ability to work effectively in an interdisciplinary team.
  • Background in computer science/data science (recommended).
  • Experience in machine learning, genomics, physiological data, or mental health (a plus).
  • Familiarity with frameworks like TensorFlow, Keras, and PyTorch (preferred).

This Master’s thesis offers an excellent opportunity to contribute to cutting-edge research at the intersection of machine learning, genomics, and mental health.


Robert Richer, M. Sc.

PhD Candidate & Group Head

Prof. Dr. Björn Eskofier

Head of the Chair

Dr. Janine Knauer-Arloth

Max Planck Institute of Psychiatry

Please use the application form to apply for the topic. We will then get in contact with you.