EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Probabilistic-graph-based spatial context-aware framework for interpretable spatial omics denoising and augmentation

Xianhan Qin, Chang Liu, Fei Gu, Xun Lan

Briefings in Bioinformatics · 01.11.2025 · 26 (6)

DOI: 10.1093/bib/bbaf674 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 22.12.2025. Verfasst von Xianhan Qin und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Basic Medical Sciences, Tsinghua University, Haidian District, Beijing 100084, China. Hauptthemen laut MEDLINE: Computational Biology, Genomics. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Biological Breeding-National Science and Technology Major Project, National Natural Science Foundation of China, Tsinghua University-Peking University Joint Center for Life Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatially resolved omics technologies offer unprecedented insight into tissue organization, yet current analytical methods face challenges in effectively handling technical noise while preserving biological heterogeneity. We present CadaST, an interpretable and unified computational framework that integrates spatially aware feature selection and an adaptive imputation strategy to address this limitation. By inferring the spatial molecular pattern for each feature and conducting pattern-guided aggregation, CadaST effectively denoises and augments spatial omics data while preserving sharp biological boundaries. This gene-centric approach robustly denoises data without the oversmoothing common to other methods. CadaST is versatile and highly effective, outperforming existing methods across diverse spatial technologies. It accurately resolves delicate anatomical layers in the brain, characterizes complex tumor microenvironments, and scales efficiently to large-scale developmental atlases. By providing a more accurate, interpretable, and scalable solution, CadaST represents a significant methodological advance for elucidating the principles of tissue architecture in health and disease.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyGenomicsHumansAlgorithmsTumor MicroenvironmentBrain

Stichwörter der Autor:innen

data denoisinginterpretable learningprobability graphspatial domain identificationspatial omicsspatially variable genes

Autor:innen und Institutionen

  • School of Basic Medical Sciences, Tsinghua University, Haidian District, Beijing 100084, China.
  • MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Tsinghua University, Haidian District, Beijing 100084, China.
  • Damo Academy, Alibaba Group, No. 969 Wenyi West Road, Yuhang District, Hangzhou 310023, China.

Förderung

  • Biological Breeding-National Science and Technology Major Project
  • National Natural Science Foundation of China
  • Tsinghua University-Peking University Joint Center for Life Sciences
  • Beijing Natural Science Foundation
  • Tsinghua University–Peking University Joint Center for Life Sciences

Zitieren

APA

Qin, X., Liu, C., Gu, F., & Lan, X. (2025). Probabilistic-graph-based spatial context-aware framework for interpretable spatial omics denoising and augmentation. Briefings in Bioinformatics, 26(6). https://doi.org/10.1093/bib/bbaf674

Vancouver

Qin X, Liu C, Gu F, Lan X. Probabilistic-graph-based spatial context-aware framework for interpretable spatial omics denoising and augmentation. Briefings in Bioinformatics. 2025;26(6). doi:10.1093/bib/bbaf674

BibTeX
@article{Qin2025,
  author = {Qin, Xianhan and Liu, Chang and Gu, Fei and Lan, Xun},
  title = {Probabilistic-graph-based spatial context-aware framework for interpretable spatial omics denoising and augmentation},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {6},
  doi = {10.1093/bib/bbaf674}
}
Kostenlos starten →