scMUSCL: multi-source transfer learning for clustering scRNA-seq data
Bioinformatics · 2025
DOI: 10.1093/bioinformatics/btaf137 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Arash Khoeini und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing Science, Simon Fraser University, Burnaby, British Columbia V5A 1S6, Canada. Hauptthemen laut MEDLINE: Single-Cell Analysis, Machine Learning, Sequence Analysis, RNA, RNA-Seq. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Motivation Single-cell RNA sequencing (scRNA-seq) analysis relies heavily on effective clustering to facilitate numerous downstream applications. Although several machine learning methods have been developed to enhance single-cell clustering, most are fully unsupervised and overlook the rich repository of annotated datasets available from previous single-cell experiments. Since cells are inherently high-dimensional entities, unsupervised clustering can often result in clusters that lack biological relevance. Leveraging annotated scRNA-seq datasets as a reference can significantly enhance clustering performance, enabling the identification of biologically meaningful clusters in target datasets. Results In this article, we propose Single Cell MUlti-Source CLustering (scMUSCL), a novel transfer learning method designed to identify cell clusters in a target dataset by leveraging knowledge from multiple annotated reference datasets. scMUSCL employs a deep neural network to extract domain- and batch-invariant cell representations, effectively addressing discrepancies across various source datasets and between source and target datasets within the new representation space. Unlike existing methods, scMUSCL does not require prior knowledge of the number of clusters in the target dataset and eliminates the need for batch correction between source and target datasets. We conduct extensive experiments using 20 real-life datasets, demonstrating that scMUSCL consistently outperforms existing unsupervised and transfer learning-based methods. Furthermore, our experiments show that scMUSCL benefits from multiple source datasets as learning references and accurately estimates the number of clusters. Availability and implementation The Python implementation of scMUSCL is available at https://github.com/arashkhoeini/scMUSCL.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computing Science, Simon Fraser University, Burnaby, British Columbia V5A 1S6, Canada.
- Vancouver Prostate Centre, Vancouver, British Columbia V6H 3Z6, Canada.
- Department of Urologic Science, University of British Columbia, Vancouver, British Columbia V5Z 1M9, Canada.
ORCID-Profile: Arash Khoeini, Yen-Yi Lin
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Khoeini, A., Sar, F., Lin, Y. Y., Collins, C., & Ester, M. (2025). scMUSCL: multi-source transfer learning for clustering scRNA-seq data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf137
Vancouver
Khoeini A, Sar F, Lin YY, Collins C, Ester M. scMUSCL: multi-source transfer learning for clustering scRNA-seq data. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf137
BibTeX
@article{Khoeini2025,
author = {Khoeini, Arash and Sar, Funda and Lin, Yen-Yi and Collins, Colin and Ester, Martin},
title = {scMUSCL: multi-source transfer learning for clustering scRNA-seq data},
journal = {Bioinformatics},
year = {2025},
doi = {10.1093/bioinformatics/btaf137}
}
EUVIMED