Mapping single-cell data to reference atlases by transfer learning

By Mohammad Lotfollahi, Mohsen Naghipourfar, Malte D. Luecken, Matin Khajavi, Maren Büttner, Marco Wagenstetter, Žiga Avsec, Adam Gayoso, Nir Yosef, Marta Interlandi and 3 more. Nature Biotechnology, 2021

497 citations recorded by the source corpus.

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. Single-cell data are readily integrated with cell atlases using scArches.

Subfields: Biophysics, Immunology, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/cec0cf40c589ecaa6d779b8433d96393fdcd9fdc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Immunology

Fabian J Theis

In Molecular Biology

Citations in the corpus

Dictionary learning for integrative, multimodal, and massively scalable single-cell analysis (2022, unknown): “This strategy is enabled by the curation and public release of reference datasets as well as the development of new computational tools, including statistical learning 4–7 and deep learning-based approaches 8,9 , that have been successfully applied toward this goal.”
A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications (2023, background): “High-level generalization is needed for the initially trained model, so new data can be adapted [128, 129, 219].”
Best practices for single-cell analysis across modalities (2023, background): “Failing to account for multiple sources of biological variability for experiments will inflate the FDR 90,91 .”