Federated deep learning enables cancer subtyping by proteomics
Zhaoxiang Cai, Emma L Boys, Zaynab Noor, Ali T Aref, Dylan Xavier, Natasha Lucas, Steven G Williams, Jennifer M Koh, Rebecca C Poulos, Yangxiu Wu, Michael Dausmann, Karen L MacKenzie, Adriana Aguilar-Mahecha, Carlota Armengol, Marta M Barranco, Mark Basik, Edward D Bowman, Roderick Clifton-Bligh, Elizabeth A Connolly, Roger R Reddel
Abstract
The proteome provides unique insights into disease biology beyond the genome and transcriptome. However, the sharing of raw proteomic data across institutions is hindered by privacy concerns and data volume. Here, we present a federated deep learning framework for cancer subtyping using mass spectrometry-based proteomic data. By training on distributed datasets without centralized data sharing, our approach achieves performance comparable to centralized training. We demonstrate the utility of this framework by classifying 14 cancer subtypes across 7,500 cancer proteomes from multiple centers. This work introduces the first application of federated deep learning to cancer proteomics, enabling collaborative research while preserving data privacy.
BibTeX
@article{cai2025cai2025federated,
title = {{Federated deep learning enables cancer subtyping by proteomics}},
author = {Zhaoxiang Cai and Emma L Boys and Zaynab Noor and Ali T Aref and Dylan Xavier and Natasha Lucas and Steven G Williams and Jennifer M Koh and Rebecca C Poulos and Yangxiu Wu and Michael Dausmann and Karen L MacKenzie and Adriana Aguilar-Mahecha and Carlota Armengol and Marta M Barranco and Mark Basik and Edward D Bowman and Roderick Clifton-Bligh and Elizabeth A Connolly and Roger R Reddel},
journal = {Cancer Discovery},
year = {2025},
doi = {10.1158/2159-8290.CD-24-1488}
}