ImageDoubler: image-based doublet identification in single-cell sequencing

Abstract Single-cell sequencing provides detailed insights into individual cell behaviors within complex systems based on the assumption that each cell is uniquely isolated. However, doublets—where two or more cells are sequenced together—disrupt this assumption and can lead to potential data misint...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaiwen Deng, Xinya Xu, Manqi Zhou, Hongyang Li, Evan T. Keller, Gregory Shelley, Annie Lu, Lana Garmire, Yuanfang Guan
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-024-55434-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850282068341161984
author Kaiwen Deng
Xinya Xu
Manqi Zhou
Hongyang Li
Evan T. Keller
Gregory Shelley
Annie Lu
Lana Garmire
Yuanfang Guan
author_facet Kaiwen Deng
Xinya Xu
Manqi Zhou
Hongyang Li
Evan T. Keller
Gregory Shelley
Annie Lu
Lana Garmire
Yuanfang Guan
author_sort Kaiwen Deng
collection DOAJ
description Abstract Single-cell sequencing provides detailed insights into individual cell behaviors within complex systems based on the assumption that each cell is uniquely isolated. However, doublets—where two or more cells are sequenced together—disrupt this assumption and can lead to potential data misinterpretations. Traditional doublet detection methods primarily rely on simulated genomic data, which may be less effective in homogeneous cell populations and can introduce biases from experimental processes. Therefore, we introduce ImageDoubler in this study, an innovative image-based model that identifies doublets and missing samples leveraging the Fluidigm single-cell sequencing image data. Our approach showcases a notable doublet detection efficacy, achieving a rate up to 93.87% and registering a minimum improvement of 33.1% in F1 scores compared to existing genomic-based methods. This advancement highlights the potential of using imaging to glean insight into developing doublet detection algorithms and exposes the limitations inherent in current genomic-based techniques.
format Article
id doaj-art-349c4a728da94fcfa01f47259af5efc7
institution OA Journals
issn 2041-1723
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-349c4a728da94fcfa01f47259af5efc72025-08-20T01:48:07ZengNature PortfolioNature Communications2041-17232025-01-0116111410.1038/s41467-024-55434-0ImageDoubler: image-based doublet identification in single-cell sequencingKaiwen Deng0Xinya Xu1Manqi Zhou2Hongyang Li3Evan T. Keller4Gregory Shelley5Annie Lu6Lana Garmire7Yuanfang Guan8Gilbert S. Omenn Department of Computational Medicine & Bioinformatics, University of MichiganCollege of Literature, Science, and the Arts, University of MichiganGilbert S. Omenn Department of Computational Medicine & Bioinformatics, University of MichiganGilbert S. Omenn Department of Computational Medicine & Bioinformatics, University of MichiganDepartment of Urology, University of MichiganDepartment of Urology, University of MichiganGilbert S. Omenn Department of Computational Medicine & Bioinformatics, University of MichiganGilbert S. Omenn Department of Computational Medicine & Bioinformatics, University of MichiganGilbert S. Omenn Department of Computational Medicine & Bioinformatics, University of MichiganAbstract Single-cell sequencing provides detailed insights into individual cell behaviors within complex systems based on the assumption that each cell is uniquely isolated. However, doublets—where two or more cells are sequenced together—disrupt this assumption and can lead to potential data misinterpretations. Traditional doublet detection methods primarily rely on simulated genomic data, which may be less effective in homogeneous cell populations and can introduce biases from experimental processes. Therefore, we introduce ImageDoubler in this study, an innovative image-based model that identifies doublets and missing samples leveraging the Fluidigm single-cell sequencing image data. Our approach showcases a notable doublet detection efficacy, achieving a rate up to 93.87% and registering a minimum improvement of 33.1% in F1 scores compared to existing genomic-based methods. This advancement highlights the potential of using imaging to glean insight into developing doublet detection algorithms and exposes the limitations inherent in current genomic-based techniques.https://doi.org/10.1038/s41467-024-55434-0
spellingShingle Kaiwen Deng
Xinya Xu
Manqi Zhou
Hongyang Li
Evan T. Keller
Gregory Shelley
Annie Lu
Lana Garmire
Yuanfang Guan
ImageDoubler: image-based doublet identification in single-cell sequencing
Nature Communications
title ImageDoubler: image-based doublet identification in single-cell sequencing
title_full ImageDoubler: image-based doublet identification in single-cell sequencing
title_fullStr ImageDoubler: image-based doublet identification in single-cell sequencing
title_full_unstemmed ImageDoubler: image-based doublet identification in single-cell sequencing
title_short ImageDoubler: image-based doublet identification in single-cell sequencing
title_sort imagedoubler image based doublet identification in single cell sequencing
url https://doi.org/10.1038/s41467-024-55434-0
work_keys_str_mv AT kaiwendeng imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT xinyaxu imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT manqizhou imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT hongyangli imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT evantkeller imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT gregoryshelley imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT annielu imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT lanagarmire imagedoublerimagebaseddoubletidentificationinsinglecellsequencing
AT yuanfangguan imagedoublerimagebaseddoubletidentificationinsinglecellsequencing