EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sparse deconvolution of cell type medleys in spatial transcriptomics

Nuray Sogunmez Erdogan iD, Deniz Eroglu

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1013169 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Nuray Sogunmez Erdogan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Natural Sciences and Engineering, Kadir Has University, Istanbul, Turkiye. Hauptthemen laut MEDLINE: Transcriptome, Gene Expression Profiling. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: TUBITAK, BAGEP Award of the Science Academy, Türkiye Bilimsel ve Teknolojik Araştırma Kurumu.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mapping cell distributions across spatial locations with whole-genome coverage is essential for understanding cellular responses and signaling However, current deconvolution models aim to estimate the proportions of distinct cell types in each spatial transcriptomics spot by integrating reference single-cell data. These models often assume strong overlap between the reference and spatial datasets, neglecting biology-grounded constraints such as sparsity and cell-type variations, as well as technical sparsity. As a result, these methods rely on over-permissive algorithms that ignore given constraints leading to inaccurate predictions, particularly in heterogeneous or unmatched datasets. We introduce Weight-Induced Sparse Regression (WISpR), a machine learning algorithm that integrates spot-specific hyperparameters and sparsity-driven modeling. Unlike conventional approaches that neglect biology-grounded constraints, WISpR accurately predicts cell-type distributions while preserving biological coherence, i.e., spatially and functionally consistent cell-type localization, even in unmatched datasets. Benchmarking against five alternative methods across ten datasets, WISpR consistently outperformed competitors and predicted cellular landscapes in both normal and cancerous tissues. By leveraging sparse cell-type arrangements, WISpR provides biologically informed, high-resolution cellular maps. Its ability to decode tissue organization in both healthy and diseased states highlights WISpR’s practical utility for spatial transcriptomics, particularly in challenging settings involving noise, sparsity, or reference mismatches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TranscriptomeGene Expression ProfilingHumansAlgorithmsComputational BiologySingle-Cell AnalysisMachine Learning

Autor:innen und Institutionen

  • Faculty of Natural Sciences and Engineering, Kadir Has University, Istanbul, Turkiye.
  • Department of Mathematics, Imperial College London, London, United Kingdom.

ORCID-Profile: Nuray Sogunmez Erdogan

Förderung

  • TUBITAK
  • BAGEP Award of the Science Academy
  • Türkiye Bilimsel ve Teknolojik Araştırma Kurumu
  • Türkiye Sağlık Enstitüleri Başkanlığı
  • UK Research and Innovation
  • Bilim Akademisi

Zitieren

APA

Erdogan, N. S., & Eroglu, D. (2025). Sparse deconvolution of cell type medleys in spatial transcriptomics. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013169

Vancouver

Erdogan NS, Eroglu D. Sparse deconvolution of cell type medleys in spatial transcriptomics. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1013169

BibTeX
@article{Erdogan2025,
  author = {Erdogan, Nuray Sogunmez and Eroglu, Deniz},
  title = {Sparse deconvolution of cell type medleys in spatial transcriptomics},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1013169}
}
Kostenlos starten →