Authors
Yunyang Li, Nikhil Khandekar, Skylar Wang, Varada Khanna, Julian Sanker, Mark B Gerstein
Published in
Bioinformatics (Oxford, England). Volume 42. Issue Supplement_1. Jul 01, 2026.
Abstract
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.
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.
The implementation of NoisyFlow is available at https://github.com/gersteinlab/NoisyFlow.
PMID:
42412817
Bibliographic data and abstract were imported from PubMed on 08 Jul 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 4
- Comments 0