EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NoisyFlow: differentially private optimal transport using neural networks for secure biomedical data sharing across multiple institutions

Yunyang Li, Nikhil Khandekar, Skylar Wang, Varada Khanna, Julian Sanker, Mark B Gerstein iD

Bioinformatics · 01.07.2026 · 42 (Supplement_1)

DOI: 10.1093/bioinformatics/btag239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 07.07.2026. Verfasst von Yunyang Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Yale University, New Haven, CT 06511, United States. Hauptthemen laut MEDLINE: Information Dissemination, Neural Networks, Computer, Computer Security. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, NIH HHS, National Human Genome Research Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Biomedical models improve when trained on data pooled across institutions, but sensitive patient records (e.g. genomics, clinical data, and medical images) are difficult to share due to privacy constraints. Moreover, data collected at different sites often have shifted distributions because of covariate differences (including batch effects), so privacy-preserving sharing alone cannot simply resolve cross-site mismatch. Methods that protect individuals while explicitly aligning distributions are needed to enable reliable multi-institutional analyses. Results We present NoisyFlow, a three-stage differentially private framework for cross-institutional harmonization under distribution shift. In stage I, each site learns a differentially private flow-based generator of its local labeled distribution. In stage II, it learns a neural optimal transport map to a shared reference distribution. In stage III, a central server composes the released models to generate reference-aligned pseudo-data for downstream analysis without accessing raw records. Across four biomedical settings spanning single-cell genomics, histopathology, neurogenomics, and wearable sensing, NoisyFlow reduces distribution shift while preserving downstream utility under formal differential privacy guarantees. Availability and implementation The implementation of NoisyFlow is available at https://github.com/gersteinlab/NoisyFlow.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Information DisseminationNeural Networks, ComputerComputer SecurityHumansGenomicsAlgorithms

Autor:innen und Institutionen

  • Department of Computer Science, Yale University, New Haven, CT 06511, United States.
  • Department of Biostatistics, Yale School of Public Health, New Haven, CT 06511, United States.
  • Program in Computational Biology and Biomedical Informatics, Yale University, New Haven, CT 06511, United States.
  • Department of Statistics and Data Science, Yale University, New Haven, CT 06511, United States.

ORCID-Profile: Mark B Gerstein

Förderung

  • NHGRI NIH HHS
  • NIH HHS
  • National Human Genome Research Institute
  • National Institutes of Health

Zitieren

APA

Li, Y., Khandekar, N., Wang, S., Khanna, V., Sanker, J., & Gerstein, M. B. (2026). NoisyFlow: differentially private optimal transport using neural networks for secure biomedical data sharing across multiple institutions. Bioinformatics, 42(Supplement_1). https://doi.org/10.1093/bioinformatics/btag239

Vancouver

Li Y, Khandekar N, Wang S, Khanna V, Sanker J, Gerstein MB. NoisyFlow: differentially private optimal transport using neural networks for secure biomedical data sharing across multiple institutions. Bioinformatics. 2026;42(Supplement_1). doi:10.1093/bioinformatics/btag239

BibTeX
@article{Li2026,
  author = {Li, Yunyang and Khandekar, Nikhil and Wang, Skylar and Khanna, Varada and Sanker, Julian and Gerstein, Mark B},
  title = {NoisyFlow: differentially private optimal transport using neural networks for secure biomedical data sharing across multiple institutions},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {Supplement_1},
  doi = {10.1093/bioinformatics/btag239}
}
Kostenlos starten →