Context:
Patient and other healthcare data are a treasure trove for advanced analytics and automated prediction techniques, such as machine learning models. However, this type of data is sensitive and thus subject to many ethical and legal regulations that often restrict the use of the data outside their host institution. This consequently hampers large, multi-site studies in fields like oncology.
An approach that mitigates these challenges is federated machine learning, a concept that facilitates training site-specific models that are then integrated in a broader, multi-site predictive model without exposing the original data on which it was trained.

Goals:
- Review the state of the art in federated machine learning.
- Review the Vantage6 federated machine learning infrastructure.
- Compile a dataset specifically focusing on a sample of non-small cell, early stage lung cancer patients from TCGA (https://portal.gdc.cancer.gov/) and split the data into a number of multi-site cohorts (either using site data, if available, or artificially).
- Deploy the Vantage6 system on the sample data emulating multi-site analysis of oncological data and involving a clinically-relevant predictive task (e.g., patient clustering based on their overall genomic profiles, genomic variations or mutation burden).
- Write up the results in a thesis form.

Requirements:
- Keen interest in the topic.
- Ability to read and comprehend scientific publications in English.
- Basic knowledge of computational biology, bioinformatics or medicine is a plus, but certainly not a must - the interest and willingness to learn are the only essential requirements, really.
- While the thesis can be written and defended in Czech, its elaboration and presentation in English will be supported enthusiastically.
- Monthly (or more frequent, if needed) progress review meetings with the supervisor will be expected.
- The student(s) will also be expected to develop and document any related code using the FI MU Gitlab platform, and (if applicable) re-use and interact with other related projects there.

Notes:
- This work will be part of an interdisciplinary collaboration between the Faculty of Informatics and oncologists at Masaryk Memorial Cancer Institute and the student will thus have a chance to work on a real world problem with a tangible societal impact.
- Should they be interested, the student may also tap into the resources and informal feedback of a broader international group of biomedical AI researchers and practitioners based in the Czech Republic, Ireland and elsewhere.