EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable models for scRNA-seq data embedding with multi-scale structure preservation

David Novak, Cyril de Bodt, Pierre Lambert, John Aldo Lee, Sofie Van Gassen, Yvan Saeys

Cell Systems · 2026

DOI: 10.1016/j.cels.2026.101760 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cell Systems, 2026. Verfasst von David Novak und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium; Data Mining and Modeling for Biomedicine, Center for In…. Hauptthemen laut MEDLINE: Single-Cell Analysis, Sequence Analysis, RNA, RNA-Seq. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UCLouvain, FWO, Fond National de la Recherche Scientific.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ability to explore high-dimensional single-cell transcriptomics data efficiently is crucial in many biological studies. Dimensionality reduction techniques have therefore emerged as a basic building block of analytical workflows. They generate low-dimensional embeddings that capture important structures in the data and are often used in discovery, quality control, and downstream analysis. However, the trustworthiness of current methods and the rigor of popular evaluation criteria are limited. We tackle this in an empirical study of structure-preserving data embeddings, delivering two tools. First, we introduce ViScore: a robust scoring framework that improves both unsupervised and supervised quality metrics, with emphasis on scalability and fairness. Second, we introduce ViVAE: a deep-learning model that achieves better multi-scale structure preservation and is equipped with new tools for interpretability. We demonstrate the potential of these contributions to advance the trustworthiness of single-cell dimensionality reduction in a quantitative comparison and focused case studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisSequence Analysis, RNARNA-SeqSingle-Cell Gene Expression AnalysisDimensionality ReductionAlgorithmsDeep LearningHumansAnimalsTranscriptomeComputational BiologyGene Expression Profiling

Stichwörter der Autor:innen

deep learningdimensionality reductioninterpretabilityscRNA-seqscalability

Autor:innen und Institutionen

  • Department of Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium; Data Mining and Modeling for Biomedicine, Center for Inflammation Research, VIB-UGent, Ghent, Belgium; Division of Medical On…
  • Mathematics Department, Université de Namur, Namur, Belgium; Namur Institute for Complex Systems (naXys), Université de Namur, Namur, Belgium.
  • ICTEAM/ELEN, Université catholique de Louvain, Louvain-la-Neuve, Belgium.
  • IREC/MIRO, Université catholique de Louvain, Brussels, Belgium.
  • Department of Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium; Data Mining and Modeling for Biomedicine, Center for Inflammation Research, VIB-UGent, Ghent, Belgium.

Förderung

  • UCLouvain
  • FWO
  • Fond National de la Recherche Scientific
  • Flemish Government

Zitieren

APA

Novak, D., de Bodt, C., Lambert, P., Lee, J. A., Van Gassen, S., & Saeys, Y. (2026). Interpretable models for scRNA-seq data embedding with multi-scale structure preservation. Cell Systems. https://doi.org/10.1016/j.cels.2026.101760

Vancouver

Novak D, de Bodt C, Lambert P, Lee JA, Van Gassen S, Saeys Y. Interpretable models for scRNA-seq data embedding with multi-scale structure preservation. Cell Systems. 2026. doi:10.1016/j.cels.2026.101760

BibTeX
@article{Novak2026,
  author = {Novak, David and de Bodt, Cyril and Lambert, Pierre and Lee, John Aldo and Van Gassen, Sofie and Saeys, Yvan},
  title = {Interpretable models for scRNA-seq data embedding with multi-scale structure preservation},
  journal = {Cell Systems},
  year = {2026},
  doi = {10.1016/j.cels.2026.101760}
}
Kostenlos starten →