EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

scValue: value-based subsampling of large-scale single-cell transcriptomic data for machine and deep learning tasks

Li Huang iD, Weikang Gong, Dongsheng Chen iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf279 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Li Huang und 2 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Common Mechanism Research for Major Diseases, Suzhou Institute of Systems Medicine, Chinese Academy of Medical Sciences and P…. Hauptthemen laut MEDLINE: Deep Learning, Single-Cell Analysis, Transcriptome, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: China Postdoctoral Science Foundation, the Postdoctoral Fellowship Program (Grade B), Chinese Academy of Medical Sciences & Peking Union Medical College, Union Medical College Young Scholar Support Program, Special Research Fund for Central Universities, Peking Union Medical College.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large single-cell ribonucleic acid-sequencing (scRNA-seq) datasets offer unprecedented biological insights but present substantial computational challenges for visualization and analysis. While existing subsampling methods can enhance efficiency, they may not ensure optimal performance in downstream machine learning and deep learning (ML/DL) tasks. Here, we introduce scValue, a novel approach that ranks individual cells by ‘data value’ using out-of-bag estimates from a random forest model. scValue prioritizes high-value cells and allocates greater representation to cell types with higher variability in data value, effectively preserving key biological signals within subsamples. We benchmarked scValue on automatic cell-type annotation tasks across four large datasets, paired with distinct ML/DL models. Our method consistently outperformed existing subsampling methods, closely matching full-data performance across all annotation tasks. In three additional case studies—label transfer learning, cross-study label harmonization, and bulk RNA-seq deconvolution—scValue more effectively preserved T-cell annotations across human gut-colon datasets, more accurately reproduced T-cell subtype relationships in a human spleen dataset, and constructed a more reliable single-cell immune reference for cell-type deconvolution in simulated bulk tissue samples. Finally, using 16 public datasets ranging from tens of thousands to millions of cells, we evaluated subsampling quality based on computational time, Gini coefficient, and Hausdorff distance. scValue demonstrated fast execution, well-balanced cell-type representation, and distributional properties akin to uniform sampling. Overall, scValue provides a robust and scalable solution for subsampling large scRNA-seq data in ML/DL workflows. It is available as an open-source Python package installable via pip, with source code at https://github.com/LHBCB/scvalue.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSingle-Cell AnalysisTranscriptomeMachine LearningGene Expression ProfilingSoftwareHumansComputational BiologyAlgorithmsRNA-Seq

Stichwörter der Autor:innen

cell type analysisdata valuationmachine and deep learningsingle-cell transcriptomicssubsampling

Autor:innen und Institutionen

  • State Key Laboratory of Common Mechanism Research for Major Diseases, Suzhou Institute of Systems Medicine, Chinese Academy of Medical Sciences and Peking Union Medical College, 100 Chongwen Road, Suzhou Industrial Park…
  • Center for Artificial Intelligence and Computational Biology, Suzhou Institute of Systems Medicine, Chinese Academy of Medical Sciences and Peking Union Medical College, 100 Chongwen Road, Suzhou Industrial Park, Suzhou…

ORCID-Profile: Li Huang, Dongsheng Chen

Förderung

  • China Postdoctoral Science Foundation, the Postdoctoral Fellowship Program (Grade B)
  • Chinese Academy of Medical Sciences & Peking Union Medical College, Union Medical College Young Scholar Support Program
  • Special Research Fund for Central Universities, Peking Union Medical College
  • NCTIB Fund for R&D Platform for Cell and Gene Therapy, the Suzhou Municipal Key Laboratory
  • Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences
  • CAMS Innovation Fund for Medical Sciences (CIFMS)
  • National Natural Science Foundation of China

Zitieren

APA

Huang, L., Gong, W., & Chen, D. (2025). scValue: value-based subsampling of large-scale single-cell transcriptomic data for machine and deep learning tasks. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf279

Vancouver

Huang L, Gong W, Chen D. scValue: value-based subsampling of large-scale single-cell transcriptomic data for machine and deep learning tasks. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf279

BibTeX
@article{Huang2025,
  author = {Huang, Li and Gong, Weikang and Chen, Dongsheng},
  title = {scValue: value-based subsampling of large-scale single-cell transcriptomic data for machine and deep learning tasks},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf279}
}
Kostenlos starten →