EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

STRESS: spatial transcriptomics resolution enhancing method based on the state-space model

Xiuyuan Wang iD, Fei Ye iD, Yu Zhao, Fang Wang iD, Lan Ma, Xiao Liu iD

Briefings in Bioinformatics · 03.07.2026 · 27 (4)

DOI: 10.1093/bib/bbag444 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 18.08.2026. Verfasst von Xiuyuan Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biopharmaceutical and Health Engineering, Tsinghua ShenZhen International Graduate School, Tsinghua University, Shenzhen, Guangdong 5180…. Hauptthemen laut MEDLINE: Deep Learning, Gene Expression Profiling, Transcriptome. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Scientific Research Start-up Funds, Shenzhen Science and Technology Program, Shenzhen Universities Stable Funding Key Projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread application of spatially resolved transcriptomics (SRT) has provided a wealth of data for characterizing gene expression patterns within the spatial microenvironments of various tissues. However, the relatively coarse spatial resolution of most SRT platforms limits the continuity and interpretability of spatial expression landscapes, particularly for downstream analysis such as spatial domain identification. To address this limitation, we present STRESS, a deep learning framework for tissue-level spatial expression refinement using only SRT gene expression profiles and spatial coordinates, without relying on histological images or single-cell references. STRESS adopts a 3D state-space modeling architecture to jointly capture spatial dependencies among neighboring locations and transcriptional relationships across genes, enabling the estimation of spatially coherent expression patterns on finer spatial grids. We evaluate STRESS across multiple datasets spanning different platforms and tissue types, and demonstrate that the refined spatial representations consistently enhance spatial domain delineation and stability in downstream analyses. These results highlight STRESS as a practical and reference-free approach for refining tissue-scale spatial transcriptomic patterns and facilitating integrative spatial data analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGene Expression ProfilingTranscriptomeSpatial TranscriptomicsHumansAnimals

Stichwörter der Autor:innen

deep learningspatial resolution enhancementspatial transcriptomicsstate-space model

Autor:innen und Institutionen

  • Institute of Biopharmaceutical and Health Engineering, Tsinghua ShenZhen International Graduate School, Tsinghua University, Shenzhen, Guangdong 518055, China.
  • Tencent AI Lab, Tencent, Shenzhen, Guangdong 518000, China.

ORCID-Profile: Xiuyuan Wang, Fei Ye, Fang Wang, Xiao Liu

Förderung

  • Scientific Research Start-up Funds
  • Shenzhen Science and Technology Program
  • Shenzhen Universities Stable Funding Key Projects

Zitieren

APA

Wang, X., Ye, F., Zhao, Y., Wang, F., Ma, L., & Liu, X. (2026). STRESS: spatial transcriptomics resolution enhancing method based on the state-space model. Briefings in Bioinformatics, 27(4). https://doi.org/10.1093/bib/bbag444

Vancouver

Wang X, Ye F, Zhao Y, Wang F, Ma L, Liu X. STRESS: spatial transcriptomics resolution enhancing method based on the state-space model. Briefings in Bioinformatics. 2026;27(4). doi:10.1093/bib/bbag444

BibTeX
@article{Wang2026,
  author = {Wang, Xiuyuan and Ye, Fei and Zhao, Yu and Wang, Fang and Ma, Lan and Liu, Xiao},
  title = {STRESS: spatial transcriptomics resolution enhancing method based on the state-space model},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {4},
  doi = {10.1093/bib/bbag444}
}
Kostenlos starten →