Federated Deep Learning Enables Cancer Subtyping by Proteomics

A federated deep learning approach applied to human proteomic data, acquired using two distinct proteomic technologies from 40 tumor cohorts across eight countries, enabled accurate cancer histopathologic subtyping while preserving data privacy. This approach will enable the privacy-compliant development of large-scale proteomic artificial intelligence models, including foundation models, across institutions globally.

Authors

Institutions

Publication Details

Journal
Cancer Discovery
Published
2025-06-09
DOI
https://doi.org/10.1158/2159-8290.cd-24-1488
Citations
7
Primary Topic
Advanced Proteomics Techniques and Applications
Type
article
Field-Weighted Citation Impact
4.54

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Federated Deep Learning Enables Cancer Subtyping by Proteomics

Maria M. Barranco, Lucy Morgan, Peter G. Hains, Phillip J. Robinson et al.
7 citations
Cancer Discovery
Advanced Proteomics Techniques and Applications
4.54
article

Federated Deep Learning Enables Cancer Subtyping by Proteomics

Maria M. Barranco, Lucy Morgan, Peter G. Hains, Phillip J. Robinson, Jacob George, Natasha Lucas, Jaswinder Singh Samra, Adriana Aguilar‐Mahecha, Roger R. Reddel, Anna DeFazio, Michael Gnant, Steven G. Williams, Zhaoxiang Cai, Karen L. MacKenzie, Kate Harvey, Yangxiu Wu, Reginald V. Lord, Martin Filipits, Benedict Panizza, Anthony James Gill, Jennifer M.S. Koh, Maija R.J. Kohonen‐Corish, Elise D. Bowman, Alexander Swarbrick, Elizabeth A. Connolly, Qing Zhong, Zainab Noor, Rebecca C. Poulos, Dylan Xavier, Curtis C. Harris, Leigh C. Murphy, Michael Dausmann, Mark Basik, David M. Thomas, Sumanth Nagabushan, Roderick John Clifton-Bligh, Geoffrey W. McCaughan, J. Dinny Graham, Adnan Nagrial, Georgina Venetia Long, Wendy A. Cooper, Emma L. Boys, Peter Flynn, Bhavik Dalal, John Souglakos, Richard A. Scolyer, Rosemary L. Balleine, Lisa Glen Horvath, Adel T. Aref, Graham J. Mann, Elgene Lim, Carolina Armengol, Rosemary Habib, Jia Liu, Jordi Navinés, Christopher C. Jackson
article en
7 citations

Abstract

A federated deep learning approach applied to human proteomic data, acquired using two distinct proteomic technologies from 40 tumor cohorts across eight countries, enabled accurate cancer histopathologic subtyping while preserving data privacy. This approach will enable the privacy-compliant development of large-scale proteomic artificial intelligence models, including foundation models, across institutions globally.

Cancer DiscoveryVol. 15(9)
Australian National University (AU), The University of Sydney (AU), National Institutes of Health (US), Garvan Institute of Medical Research (AU), University of Crete (GR), Children's Medical Research Institute (AU), Royal Prince Alfred Hospital (AU), Royal North Shore Hospital (AU), Woolcock Institute of Medical Research (AU), Nepean Hospital (AU), Princess Alexandra Hospital (AU), Jewish General Hospital (CA), Blacktown & Mount Druitt Hospital (AU), Children's Hospital at Westmead (AU), Westmead Hospital (AU), UNSW Sydney (AU), St Vincent's Hospital Sydney (AU), CancerCare Manitoba (CA), Cooperative Trials Group for Neuro-Oncology (AU), Comprehensive Cancer Center Vienna (AT), Chris O’Brien Lifehouse (AU), Migration Institute of Australia (AU), Melanoma Institute Australia (AU), St Vincent's Clinic (AU), Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol (ES), Westmead Institute (AU), Keogh Institute for Medical Research (AU), University Hospital of Heraklion (GR), Sydney Local Health District (AU), National Cancer Institute (US), Westmead Institute for Medical Research (AU), The Kinghorn Cancer Centre (AU), Hospital Universitari Germans Trias i Pujol (ES), Austrian Breast & Colorectal Cancer Study Group (AT), Medical Research Network (US), Research Institute in Oncology and Hematology (CA), University of Manitoba (CA), McGill University (CA), Western Sydney University (AU), Medical University of Vienna (AT), St Vincents Institute of Medical Research (AU), Cancer Council NSW (AU), Macquarie University (AU)
U.S. Department of Health and Human Services, Children's Medical Research, AstraZeneca, David and Elaine Potter Foundation, Fondation du cancer du sein du Québec, European Commission, Australian Cancer Research Foundation, National Breast Cancer Foundation, Cancer Institute NSW, University of Sydney, State Government of Victoria, NSW Ministry of Health, Tour de Cure, CRIS Cancer Foundation, Horizon 2020 Framework Programme, Medical Research Council, National Health and Medical Research Council, Cancer Council Victoria, Cancer Council NSW, Agència de Gestió d'Ajuts Universitaris i de Recerca, National Cancer Institute
Partnerships for the goals
Openalex Percentile: Top 5%
Advanced Proteomics Techniques and Applications
4.54
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.