Flimma: a federated and privacy-aware tool for differential gene expression analysis
Creators
- 1. Chair of Experimental Bioinformatics, TUM School of Life Sciences, Technical University of Munich, Munich, Germany; Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany
- 2. AI in Medicine and Healthcare, Technical University of Munich, Munich, Germany; Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
- 3. Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany
- 4. AI in Medicine and Healthcare, Technical University of Munich, Munich, Germany
- 5. Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark
- 6. Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany
- 7. Chair of Experimental Bioinformatics, TUM School of Life Sciences, Technical University of Munich, Munich, Germany; Sapienza University of Rome, Rome, Italy.
- 8. CNR National Research Council, IAC Institute for Applied Computing, Rome, Italy; Sapienza University of Rome, Rome, Italy.
- 9. AI in Medicine and Healthcare, Technical University of Munich, Munich, Germany; Biomedical Image Analysis Group, Imperial College London, London, UK; OpenMined, Oxford, UK
- 10. AI in Medicine and Healthcare, Technical University of Munich, Munich, Germany; Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Biomedical Image Analysis Group, Imperial College London, London, UK
- 11. Chair of Experimental Bioinformatics, TUM School of Life Sciences, Technical University of Munich, Munich, Germany
- 12. Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany; Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark
Description
Aggregating transcriptomics data across hospitals can increase sensitivity and robustness of differential expression analyses, yielding deeper clinical insights. As data exchange is often restricted by privacy legislation, meta-analyses are frequently employed to pool local results. However, the accuracy might drop if class labels are inhomogeneously distributed among cohorts. Flimma (https://exbio.wzw.tum.de/flimma/) addresses this issue by implementing the state-of-the-art workflow limma voom in a federated manner, i.e. patient data never leaves its source site. Flimma results on distributed datasets are identical to those generated by limma voom on the aggregated dataset even in imbalanced scenarios, where meta-analysis approaches fail.
Files
Flimma.zip
Files
(649.0 MB)
Name | Size | Download all |
---|---|---|
md5:cb6f020c9ccd71863bbd7776bb5ce1cf
|
649.0 MB | Preview Download |
Additional details
Related works
- Cites
- Preprint: https://arxiv.org/abs/2010.16403 (URL)
- Preprint: https://arxiv.org/abs/2105.10545 (URL)