PuSH - Publication Server of Helmholtz Zentrum München

Willem, T. ; Shitov, V.A. ; Luecken, M. ; Kilbertus, N. ; Bauer, S. ; Piraud, M. ; Buyx, A.* ; Theis, F.J.

Biases in machine-learning models of human single-cell data.

Nat. Cell Biol. 27, 384–392 (2025)
Postprint DOI PMC
Open Access Green
Recent machine-learning (ML)-based advances in single-cell data science have enabled the stratification of human tissue donors at single-cell resolution, promising to provide valuable diagnostic and prognostic insights. However, such insights are susceptible to biases. Here we discuss various biases that emerge along the pipeline of ML-based single-cell analysis, ranging from societal biases affecting whose samples are collected, to clinical and cohort biases that influence the generalizability of single-cell datasets, biases stemming from single-cell sequencing, ML biases specific to (weakly supervised or unsupervised) ML models trained on human single-cell samples and biases during the interpretation of results from ML models. We end by providing methods for single-cell data scientists to assess and mitigate biases, and call for efforts to address the root causes of biases.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Review
Corresponding Author
Keywords Genomics; Racism; Race
ISSN (print) / ISBN 1465-7392
e-ISSN 1476-4679
Journal Nature Cell Biology
Quellenangaben Volume: 27, Issue: , Pages: 384–392 Article Number: , Supplement: ,
Publisher Nature Publishing Group
Publishing Place Heidelberger Platz 3, Berlin, 14197, Germany
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)
Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute of Lung Health and Immunity (LHI)
Grants Helmholtz Association under the joint research school 'Munich School for Data Science'