Harmony-based data integration for distributed single-cell multi-omics data

Ruizhi Yuan, Ziqi Rong, Haoran Hu, Tianhao Liu, Shiyue Tao, Wei Chen and Lu Tang

PLOS Computational Biology, 2025, vol. 21, issue 9, 1-17

Abstract: Large-scale single-cell projects generate rapidly growing datasets, but downstream analysis is often confounded by data sources, requiring data integration methods to do correction. Existing data integration methods typically require data centralization, raising privacy and security concerns. Here, we introduce Federated Harmony, a novel method combining properties of federated learning with Harmony algorithm to integrate decentralized omics data. This approach preserves privacy by avoiding raw data sharing while maintaining integration performance comparable to Harmony. Experiments on various types of single-cell data showcase superior results, highlighting a novel data integration approach for distributed multi-omics data without compromising data privacy or analytical performance.Author summary: In recent years, single-cell technologies have allowed scientists to study individual cells in great detail, helping us understand how tissues and organs function. As researchers around the world generate more data, combining these datasets has become important—but also challenging. One major issue is that data from different sources often vary due to technical differences, making integration tricky. Another growing concern is privacy: many institutions are hesitant to share sensitive biological data due to ethical, legal, and security risks. In our study, we introduce a method called Federated Harmony, which allows researchers to combine single-cell data from different institutions without directly sharing any raw data. By adapting a widely used data integration method (Harmony) into a federated learning framework, our approach preserves privacy while achieving comparable scientific results. We tested Federated Harmony on several types of single-cell data and found that it performs just as well as existing centralized methods, but with improved speed and security. We believe this method could help research teams around the world collaborate more safely and effectively, accelerating discoveries in biology and medicine.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013526 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 13526&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1013526

DOI: 10.1371/journal.pcbi.1013526

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().