EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Unveiling patterns: an exploration of machine learning techniques for unsupervised feature selection in single-cell data

Nandini Chatterjee, Aleksandr Taraskin, Hridya Divakaran, Natalia Jaeger, Victor Enriquez, Catherine C Hedrick, Ahmad Alimadadi iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag006 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Nandini Chatterjee und 6 weiteren Autor:innen. Beteiligte Einrichtung: La Jolla Institute for Immunology, 9420 Athena Cir, La Jolla, CA 92037, United States. Hauptthemen laut MEDLINE: Single-Cell Analysis, Unsupervised Machine Learning, Computational Biology, Machine Learning. Die Arbeit nennt 122 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NIH HHS, National Heart, Lung, and Blood Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid evolution of single-cell technologies has generated vast, multimodal datasets encompassing genomic, transcriptomic, proteomic, and spatial information. However, high dimensionality, noise, and computational costs pose significant challenges, often introducing bias through traditional feature selection methods, such as highly variable gene selection. Unsupervised machine learning (ML) provides a solution by identifying informative features without predefined labels, thereby minimizing bias and capturing complex patterns. This paper reviews a diverse array of unsupervised ML techniques tailored for single-cell data. These approaches could enhance downstream analyses, such as clustering, dimensionality reduction, visualization, and data denoising, and reveal biologically relevant gene modules. Despite their advantages, challenges such as data sparsity, parameter tuning, and scalability persist. Future directions include integrating multiomic data, incorporating domain-specific knowledge, and developing scalable and interpretable algorithms. By addressing these challenges, unsupervised ML-based feature selection promises to revolutionize single-cell data analysis, driving unbiased insights into cellular heterogeneity and advancing biological discovery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisUnsupervised Machine LearningComputational BiologyMachine LearningHumansClustering AlgorithmsAlgorithmsDimensionality ReductionAnimalsData Analytics

Stichwörter der Autor:innen

artificial intelligencebioinformaticsmachine learningpattern recognitionsingle-cell dataunsupervised feature selection

Autor:innen und Institutionen

  • La Jolla Institute for Immunology, 9420 Athena Cir, La Jolla, CA 92037, United States.
  • Immunology Center of Georgia, Augusta University, 1410 Laney Walker Blvd, Augusta, GA 30912, United States.

ORCID-Profile: Ahmad Alimadadi

Förderung

  • NHLBI NIH HHS
  • NIH HHS
  • National Heart, Lung, and Blood Institute
  • National Institutes of Health

Zitieren

APA

Chatterjee, N., Taraskin, A., Divakaran, H., Jaeger, N., Enriquez, V., Hedrick, C. C., & Alimadadi, A. (2026). Unveiling patterns: an exploration of machine learning techniques for unsupervised feature selection in single-cell data. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag006

Vancouver

Chatterjee N, Taraskin A, Divakaran H, Jaeger N, Enriquez V, Hedrick CC, et al. Unveiling patterns: an exploration of machine learning techniques for unsupervised feature selection in single-cell data. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag006

BibTeX
@article{Chatterjee2026,
  author = {Chatterjee, Nandini and Taraskin, Aleksandr and Divakaran, Hridya and Jaeger, Natalia and Enriquez, Victor and Hedrick, Catherine C and Alimadadi, Ahmad},
  title = {Unveiling patterns: an exploration of machine learning techniques for unsupervised feature selection in single-cell data},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag006}
}
Kostenlos starten →