FedRBE -- a decentralized privacy-preserving federated batch effect correction tool for omics data based on limma

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Burankova, Yuliya, Klemm, Julian, Lohmann, Jens J. G., Taheri, Ahmad, Probul, Niklas, Baumbach, Jan, Zolotareva, Olga
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909419505188864
author Burankova, Yuliya
Klemm, Julian
Lohmann, Jens J. G.
Taheri, Ahmad
Probul, Niklas
Baumbach, Jan
Zolotareva, Olga
author_facet Burankova, Yuliya
Klemm, Julian
Lohmann, Jens J. G.
Taheri, Ahmad
Probul, Niklas
Baumbach, Jan
Zolotareva, Olga
contents Batch effects in omics data obscure true biological signals and constitute a major challenge for privacy-preserving analyses of distributed patient data. Existing batch effect correction methods either require data centralization, which may easily conflict with privacy requirements, or lack support for missing values and automated workflows. To bridge this gap, we developed fedRBE, a federated implementation of limma's removeBatchEffect method. We implemented it as an app for the FeatureCloud platform. Unlike its existing analogs, fedRBE effectively handles data with missing values and offers an automated, user-friendly online user interface (https://featurecloud.ai/app/fedrbe). Leveraging secure multi-party computation provides enhanced security guarantees over classical federated learning approaches. We evaluated our fedRBE algorithm on simulated and real omics data, achieving performance comparable to the centralized method with negligible differences (no greater than 3.6E-13). By enabling collaborative correction without data sharing, fedRBE facilitates large-scale omics studies where batch effect correction is crucial.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05894
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FedRBE -- a decentralized privacy-preserving federated batch effect correction tool for omics data based on limma
Burankova, Yuliya
Klemm, Julian
Lohmann, Jens J. G.
Taheri, Ahmad
Probul, Niklas
Baumbach, Jan
Zolotareva, Olga
Quantitative Methods
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
Batch effects in omics data obscure true biological signals and constitute a major challenge for privacy-preserving analyses of distributed patient data. Existing batch effect correction methods either require data centralization, which may easily conflict with privacy requirements, or lack support for missing values and automated workflows. To bridge this gap, we developed fedRBE, a federated implementation of limma's removeBatchEffect method. We implemented it as an app for the FeatureCloud platform. Unlike its existing analogs, fedRBE effectively handles data with missing values and offers an automated, user-friendly online user interface (https://featurecloud.ai/app/fedrbe). Leveraging secure multi-party computation provides enhanced security guarantees over classical federated learning approaches. We evaluated our fedRBE algorithm on simulated and real omics data, achieving performance comparable to the centralized method with negligible differences (no greater than 3.6E-13). By enabling collaborative correction without data sharing, fedRBE facilitates large-scale omics studies where batch effect correction is crucial.
title FedRBE -- a decentralized privacy-preserving federated batch effect correction tool for omics data based on limma
topic Quantitative Methods
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2412.05894