Technical and legal aspects of federated learning in bioinformatics: applications, challenges and opportunities

Daniele Malpetti^1,2Marco Scutari^1*Francesco Gualdi^1,2Jessica Van Setten³Sander W. van der Laan^4,5Saskia Haitjema⁴Aaron Lee⁶Isabelle Hering⁷Francesca Mangili^1,2

• ¹SUPSI, Dalle Molle Institute for Artificial Intelligence Research, Lugano, Switzerland
• ²Swiss Institute of Bioinformatics, Lausanne, Switzerland
• ³Department of Cardiology, University Medical Center Utrecht, University of Utrecht, Utrecht, Netherlands
• ⁴Central Diagnostics Laboratory, University Medical Center Utrecht, University of Utrecht, Utrecht, Netherlands
• ⁵Department of Genome Sciences, University of Virginia, Charlottesville, United States
• ⁶Queen Mary University of London William Harvey Research Institute, London, United Kingdom
• ⁷Etude Hering, Nyon, Switzerland

Federated learning leverages data across institutions to improve clinical discovery while complying with data-sharing restrictions and protecting patient privacy. This paper provides a gentle introduction to this approach in bioinformatics, and is the first to review key applications in proteomics, genome-wide association studies (GWAS), single-cell and multi-omics studies in their legal as well as methodological and infrastructural challenges. As the evolution of biobanks in genetics and systems biology has proved, accessing more extensive and varied data pools leads to a faster and more robust exploration and translation of results. More widespread use of federated learning may have a similar impact in bioinformatics, allowing academic and clinical institutions to access many combinations of genotypic, phenotypic and environmental information that are undercovered or not included in existing biobanks.