Distribution-preserved compression of single-cell atlases for privacy-protected data dissemination and novel cell type discovery DOI Creative Commons

Zhiping Cai,

Zhimeng Hu, Shiqiang Sun

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 18, 2024

Abstract We introduce SUREv2, a tool for constructing lightweight, transmittable, and privacy-preserving references from single cell atlases. SUREv2 introduces compressed data structure that maintain the distribution of cells within these atlases develops an out-of-reference scoring method identifying novel populations. This user-friendly shall enhance analysis datasets by providing consistent, privacy-focused reference framework.

Language: Английский

SwarmMAP: Swarm Learning for Decentralized Cell Type Annotation in Single Cell Sequencing Data DOI Creative Commons
Oliver Lester Saldanha,

Vivien Goepp,

Kathy Pfeiffer

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 16, 2025

Rapid technological advancements have made it possible to generate single-cell data at a large scale. Several laboratories around the world can now transcriptomic from different tissues. Unsupervised clustering, followed by annotation of cell type identified clusters, is crucial step in analyses. However, there no consensus on marker genes use for annotation, and celltype currently mostly done manual inspection genes, which irreproducible, poorly scalable. Additionally, patient-privacy also critical issue with human datasets. There need standardize automate across datasets privacy-preserving manner. Here, we developed SwarmMAP that uses Swarm Learning train machine learning models cell-type classification based sequencing decentralized way. does not require any exchange raw between centers. has F1-score 0.93, 0.98, 0.88 heart, lung, breast datasets, respectively. Learning-based yield an average performance 0.907 par achieved trained centralized ( p -val= 0.937 , Mann-Whitney U Test). We find increasing number increases prediction accuracy enables handling higher diversity. Together, these findings demonstrate viable approach annotation. available https://github.com/hayatlab/SwarmMAP .

Language: Английский

Citations

0
Recent Advances and Future Challenges in the Immunology of Islet and Stem Cell-Derived Islet Transplantation DOI
Adrian Kee Keong Teo, Kahbing Jasmine Tan, Ye Xin Koh

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Genomic Privacy Risks in GWAS Summary Statistics DOI

Ao Lan,

Xia Shen

Published: Jan. 1, 2025

Language: Английский

Citations

0
Towards a consensus atlas of human and mouse adipose tissue at single-cell resolution DOI
Anne Loft, Margo P. Emont, Ada Weinstock

et al.

Nature Metabolism, Journal Year: 2025, Volume and Issue: unknown

Published: May 13, 2025

Language: Английский

Citations

0
‘Anonymous’ genetic databases vulnerable to privacy leaks DOI

Helena Kudiabor

Nature, Journal Year: 2024, Volume and Issue: 634(8035), P. 764 - 765

Published: Oct. 14, 2024

Language: Английский

Citations

0
Privacy of single-cell gene expression data DOI Creative Commons
Hyunghoon Cho

Patterns, Journal Year: 2024, Volume and Issue: 5(11), P. 101096 - 101096

Published: Nov. 1, 2024

The possibility that single-cell gene expression datasets could leak information about individuals' genotypes has been largely unexplored. Walker et al. showed even noisy genotype predictions derived from these data can be linked to the corresponding profiles with significant accuracy.

Language: Английский

Citations

0
Distribution-preserved compression of single-cell atlases for privacy-protected data dissemination and novel cell type discovery DOI Creative Commons

Zhiping Cai,

Zhimeng Hu, Shiqiang Sun

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 18, 2024

Abstract We introduce SUREv2, a tool for constructing lightweight, transmittable, and privacy-preserving references from single cell atlases. SUREv2 introduces compressed data structure that maintain the distribution of cells within these atlases develops an out-of-reference scoring method identifying novel populations. This user-friendly shall enhance analysis datasets by providing consistent, privacy-focused reference framework.

Language: Английский

Citations

0