EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating feature selection with unsupervised deep embedding for clustering single-cell RNA-seq data

Cheng Zhong, Siqi Jiang iD, Zhi Wei iD

Briefings in Bioinformatics · 01.03.2026 · 27 (2)

DOI: 10.1093/bib/bbag082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 02.03.2026. Verfasst von Cheng Zhong und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, New Jersey Institute of Technology, 323 Dr Martin Luther King Jr Blvd, Newark, NJ 07102, United States. Hauptthemen laut MEDLINE: Single-Cell Analysis, RNA-Seq, Sequence Analysis, RNA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of gene expression at the individual cell level, with clustering serving as a critical step for identifying distinct cell populations. Due to the high dimensionality and sparsity of scRNA-seq data, existing approaches typically perform gene selection prior to clustering. However, treating feature selection as a separate preprocessing step can overlook latent clustering structure and often results in suboptimal outcomes, as it does not guarantee that the selected genes are informative for clustering. To address this limitation, we propose FSSC (Feature Selection for scRNA-seq Clustering), a unified framework for joint feature selection and clustering in scRNA-seq analysis. FSSC integrates a zero-inflated negative binomial (ZINB) autoencoder with a group Lasso penalty and a dedicated clustering loss. This joint optimization enables the model to simultaneously learn low-dimensional representations and select a compact set of cluster-discriminatory genes, preserving both the statistical characteristics of scRNA-seq data and its underlying cluster structure. Extensive experiments on both simulated and real scRNA-seq datasets demonstrate that FSSC consistently outperforms state-of-the-art methods in clustering accuracy and effectively identifies a compact, biologically meaningful set of marker genes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisRNA-SeqSequence Analysis, RNAClustering AlgorithmsSingle-Cell Gene Expression AnalysisAutoencoderCluster AnalysisHumansGene Expression ProfilingAnimalsAlgorithms

Stichwörter der Autor:innen

deep learningdimension reductiongroup lassoscRNA-seq

Autor:innen und Institutionen

  • Department of Computer Science, New Jersey Institute of Technology, 323 Dr Martin Luther King Jr Blvd, Newark, NJ 07102, United States.

ORCID-Profile: Siqi Jiang, Zhi Wei

Förderung

  • NHGRI NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Zhong, C., Jiang, S., & Wei, Z. (2026). Integrating feature selection with unsupervised deep embedding for clustering single-cell RNA-seq data. Briefings in Bioinformatics, 27(2). https://doi.org/10.1093/bib/bbag082

Vancouver

Zhong C, Jiang S, Wei Z. Integrating feature selection with unsupervised deep embedding for clustering single-cell RNA-seq data. Briefings in Bioinformatics. 2026;27(2). doi:10.1093/bib/bbag082

BibTeX
@article{Zhong2026,
  author = {Zhong, Cheng and Jiang, Siqi and Wei, Zhi},
  title = {Integrating feature selection with unsupervised deep embedding for clustering single-cell RNA-seq data},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {2},
  doi = {10.1093/bib/bbag082}
}
Kostenlos starten →