EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ST-deconv: an accurate deconvolution approach for spatial transcriptome data utilizing self-encoding and contrastive learning

Shurui Dai iD, Jiawei Li, Zhiliang Xia iD, Jingfeng Ou iD, Yan Guo iD, Limin Jiang, Jijun Tang

NAR Genomics and Bioinformatics · 2025

DOI: 10.1093/nargab/lqaf109 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Shurui Dai und 6 weiteren Autor:innen. Beteiligte Einrichtung: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, 518005 Guangdong, China. Hauptthemen laut MEDLINE: Transcriptome, Single-Cell Analysis, Deep Learning, Gene Expression Profiling. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single-cell RNA sequencing (scRNA-seq) has significantly deepened our understanding of cellular heterogeneity and cell type interactions, providing insights into how cell populations adapt to environmental variability. However, its lack of spatial context limits intercellular analysis. Similarly, existing spatial transcriptomics (ST) data often lack single-cell resolution, restricting cellular mapping. To address these limitations, we introduce ST-deconv, a deep learning-based deconvolution model that integrates spatial information. ST-deconv leverages contrastive learning to enhance the spatial representation of adjacent spots, improving spatial relationship inference. It also employs domain-adversarial networks to improve generalization and deconvolution across diverse datasets. Moreover, ST-deconv can generate large-scale, high-resolution spatial transcriptomic data with cell type labels from single-cell input, facilitating the learning of spatial cell type composition. In benchmarking experiments, ST-deconv outperforms traditional methods, reducing the root mean square error (RMSE) by 13% to 60%, with an RMSE as low as 0.03 for high spatial correlation datasets and 0.07 for low spatial correlation datasets across different transcriptomic contexts. Reconstructing real tissue structure, a purity of 0.68 on mouse olfactory bulb (MOB) and a cell type correlation of 0.76 on human pancreatic ductal adenocarcinoma (PDAC) were achieved. These advancements make ST-deconv a powerful tool for enhancing spatial transcriptomics and downstream analyses of intercellular interactions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TranscriptomeSingle-Cell AnalysisDeep LearningGene Expression ProfilingAnimalsMiceHumansRNA-Seq

Autor:innen und Institutionen

  • Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, 518005 Guangdong, China.
  • Department of Public Health Sciences, University of Miami, Miami, FL 33136, United States.

ORCID-Profile: Shurui Dai, Zhiliang Xia, Jingfeng Ou, Yan Guo

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Shenzhen Science and Technology Program
  • Shenzhen KQTD Project

Zitieren

APA

Dai, S., Li, J., Xia, Z., Ou, J., Guo, Y., Jiang, L., & Tang, J. (2025). ST-deconv: an accurate deconvolution approach for spatial transcriptome data utilizing self-encoding and contrastive learning. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf109

Vancouver

Dai S, Li J, Xia Z, Ou J, Guo Y, Jiang L, et al. ST-deconv: an accurate deconvolution approach for spatial transcriptome data utilizing self-encoding and contrastive learning. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf109

BibTeX
@article{Dai2025,
  author = {Dai, Shurui and Li, Jiawei and Xia, Zhiliang and Ou, Jingfeng and Guo, Yan and Jiang, Limin and Tang, Jijun},
  title = {ST-deconv: an accurate deconvolution approach for spatial transcriptome data utilizing self-encoding and contrastive learning},
  journal = {NAR Genomics and Bioinformatics},
  year = {2025},
  doi = {10.1093/nargab/lqaf109}
}
Kostenlos starten →