PXD056810

PXD056810 is an original dataset announced via ProteomeXchange.

Title	Federated deep learning enables cancer subtyping by proteomics
Description	Artificial intelligence (AI) applications in biomedical settings face challenges such as data privacy and regulatory compliance. Federated Deep Learning (FDL) effectively addresses these issues. We developed ProCanFDL, where local models were trained on simulated sites using proteomic data drawn from a pan-cancer cohort (n = 1,260) and 29 other cohorts (n = 6,265), representing 4,956 patients and 19,930 mass spectrometry (MS) runs, all held behind private firewalls. Local parameter updates were aggregated to build the global model, achieving a 43% performance gain over local models on the hold-out test set (n = 625) in 14 cancer subtyping tasks. Additionally, ProCanFDL preserved data privacy while matching centralized model performance. External validation assessed generalization by retraining the global model with data from two external cohorts (n = 55) and eight (n = 832) using a different MS technology. ProCanFDL presents a solution for internationally collaborative machine learning initiatives using proteomic data while maintaining data privacy.
HostingRepository	PRIDE
AnnounceDate	2025-05-30
AnnouncementXML	Submission_2025-05-30_02:33:42.116.xml
DigitalObjectIdentifier
ReviewLevel	Peer-reviewed dataset
DatasetOrigin	Original dataset
RepositorySupport	Unsupported dataset by repository
PrimarySubmitter	Zainab Noor
SpeciesList	scientific name: Homo sapiens (Human); NCBI TaxID: 9606;
ModificationList	iodoacetamide derivatized residue
Instrument	TripleTOF 6600

Revision	Datetime	Status	ChangeLog Entry
0	2024-10-15 03:24:00	ID requested
⏵ 1	2025-05-30 02:33:43	announced

Dataset with its publication pending

submitter keyword: ProCanFDL,Pan-cancer, Human, SWATH-MS, Proteomics, Federated deep learning

Peter G
contact affiliation	Children's Medical Research Institute, Faculty of Medicine and Health, Westmead, NSW, Australia
contact email	phains@cmri.org.au
lab head
Zainab Noor
contact affiliation	ProCan, Children's Medical Research Institute, Faculty of Medicine and Health, The University of Sydney, Westmead, New South Wales, Australia
contact email	znoor@cmri.org.au
dataset submitter

Dataset FTP location NOTE: Most web browsers have now discontinued native support for FTP access within the browser window. But you can usually install another FTP app (we recommend FileZilla) and configure your browser to launch the external application when you click on this FTP link. Or otherwise, launch an app that supports FTP (like FileZilla) and use this address: ftp://ftp.pride.ebi.ac.uk/pride/data/archive/2025/05/PXD056810

PRIDE project URI

• PRIDE
  1. PXD056810
     1. Label: PRIDE project
     2. Name: Federated deep learning enables cancer subtyping by proteomics