PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Lotfollahi, M. ; Naghipourfar, M. ; Luecken, M. ; Khajavi, M. ; Büttner, M. ; Wagenstetter, M. ; Avsec, Z.* ; Gayoso, A.* ; Yosef, N.* ; Interlandi, M.* ; Rybakov, S. ; Misharin, A.V.* ; Theis, F.J.

Mapping single-cell data to reference atlases by transfer learning.

Nat. Biotechnol., DOI: 10.1038/s41587-021-01001-7 (2021)
Publ. Version/Full Text DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
Large single-cell atlases are now routinely generated to serve as references for analysis of smaller-scale studies. Yet learning from reference data is complicated by batch effects between datasets, limited availability of computational resources and sharing restrictions on raw data. Here we introduce a deep learning strategy for mapping query datasets on top of a reference called single-cell architectural surgery (scArches). scArches uses transfer learning and parameter optimization to enable efficient, decentralized, iterative reference building and contextualization of new datasets with existing references without sharing raw data. Using examples from mouse brain, pancreas, immune and whole-organism atlases, we show that scArches preserves biological state information while removing batch effects, despite using four orders of magnitude fewer parameters than de novo integration. scArches generalizes to multimodal reference mapping, allowing imputation of missing modalities. Finally, scArches retains coronavirus disease 2019 (COVID-19) disease variation when mapping to a healthy reference, enabling the discovery of disease-specific cell states. scArches will facilitate collaborative projects by enabling iterative construction, updating, sharing and efficient use of reference atlases.
Impact Factor
Scopus SNIP
Web of Science
Times Cited
Scopus
Cited By
Altmetric
54.908
7.029
5
42
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Identity
Language english
Publication Year 2021
HGF-reported in Year 2021
ISSN (print) / ISBN 1087-0156
e-ISSN 1546-1696
Journal Nature Biotechnology
Publisher Nature Publishing Group
Publishing Place New York, NY
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-503800-001
G-503893-001
Grants Deutsche Forschungsgemeinschaft (German Research Foundation)
DOI 10.1038/s41587-021-01001-7
WOS ID WOS:000691223800003
Scopus ID 85113961878
PubMed ID 34462589
Erfassungsdatum 2021-09-24
[➜Report correction]