EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Federated transfer learning with differential privacy for multi-omics survival analysis

Gang Wen iD, Limin Li iD

Briefings in Bioinformatics · 04.03.2025 · 26 (2)

DOI: 10.1093/bib/bbaf166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 15.04.2025. Verfasst von Gang Wen und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Xi'an Jiaotong University, 28 Xianning West, Xi'an 710049, Shaanxi, China. Hauptthemen laut MEDLINE: Neoplasms, Machine Learning, Privacy, Computational Biology. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-omics data often suffer from the “big $p$, small $n$” problem where the dimensionality of features is significantly larger than the sample size, making the integration of multi-omics data for survival analysis of a specific cancer particularly challenging. One common strategy is to share multi-omics data from other related cancers across multiple institutions and leverage the abundant data from these cancers to enhance survival predictions for the target cancer. However, due to data privacy and data-sharing regulations, it is challenging to aggregate multi-omics data of related cancers from multiple institutions into a centralized database to learn more accurate and robust models for the target cancer. To address the limitation, we propose a multi-omics survival prediction model with self-attention mechanism (MOSAHit), trained within a federated transfer learning framework with differential privacy. This approach enables the learning of a more robust multi-omics survival prediction model for a local target cancer with limited training data by effectively leveraging multi-omics data of related cancers distributed across multiple institutions while preserving individual privacy. Results from the comprehensive experiments on real-world datasets show that the proposed method effectively alleviates data insufficiency and significantly improves the generalization performance of multi-omics survival prediction model for a target cancer while avoiding the direct sharing of multi-omics data for related cancers.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsMachine LearningPrivacyComputational BiologyGenomicsHumansSurvival AnalysisMultiomics

Stichwörter der Autor:innen

differential privacyfederated learningmulti-omics datasurvival analysistransfer learning

Autor:innen und Institutionen

  • School of Mathematics and Statistics, Xi'an Jiaotong University, 28 Xianning West, Xi'an 710049, Shaanxi, China.

ORCID-Profile: Gang Wen, Limin Li

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wen, G., & Li, L. (2025). Federated transfer learning with differential privacy for multi-omics survival analysis. Briefings in Bioinformatics, 26(2). https://doi.org/10.1093/bib/bbaf166

Vancouver

Wen G, Li L. Federated transfer learning with differential privacy for multi-omics survival analysis. Briefings in Bioinformatics. 2025;26(2). doi:10.1093/bib/bbaf166

BibTeX
@article{Wen2025,
  author = {Wen, Gang and Li, Limin},
  title = {Federated transfer learning with differential privacy for multi-omics survival analysis},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {2},
  doi = {10.1093/bib/bbaf166}
}
Kostenlos starten →