EUVIMEDEUVIMED entdecken
Open Access

spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model

Tianyu Liu, Tinglin Huang, Wengong Jin, Tinyi Chu, Rex Ying, Hongyu Zhao iD

Genome Research · 2026

DOI: 10.1101/gr.281001.125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genome Research, 2026. Verfasst von Tianyu Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, New Haven, Connecticut 06511, USA. Hauptthemen laut MEDLINE: Genomics, Transcriptome, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHGRI NIH HHS, National Human Genome Research Institute, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The analysis of spatial transcriptomic data is hindered by high noise levels and missing gene measurements, challenges that are further compounded by the higher cost of spatial data compared to traditional single-cell data. To overcome this challenge, we introduce spRefine, a deep learning framework that leverages genomic language models to jointly denoise and impute spatial transcriptomic data. Our results demonstrate that spRefine yields more robust cell- and spot-level representations after denoising and imputation, substantially improving data integration. In addition, spRefine serves as a strong framework for model pretraining and the discovery of novel biological signals, as highlighted by multiple downstream applications across data sets of varying scales. Notably, spRefine enhances the accuracy of spatial aging clock estimations and uncovers new aging-related relationships associated with key biological processes, such as neuronal function loss, which offers new insights for analyzing aging effect with spatial transcriptomics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GenomicsTranscriptomeDeep LearningSpatial TranscriptomicsAnimalsAgingHumansGene Expression Profiling

Autor:innen und Institutionen

  • Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, New Haven, Connecticut 06511, USA.
  • Department of Biostatistics, Yale University, New Haven, Connecticut 06511, USA.
  • Department of Computer Science, Yale University, New Haven, Connecticut 06511, USA.
  • Department of Computer Science, Northeastern University, Boston, Massachusetts 02115, USA.
  • Broad Institute, Cambridge, Massachusetts 02142, USA.
  • Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, New Haven, Connecticut 06511, USA; hongyu.zhao@yale.edu.

ORCID-Profile: Hongyu Zhao

Förderung

  • NHGRI NIH HHS
  • National Human Genome Research Institute
  • National Institutes of Health
  • National Science Foundation

Zitieren

APA

Liu, T., Huang, T., Jin, W., Chu, T., Ying, R., & Zhao, H. (2026). spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model. Genome Research. https://doi.org/10.1101/gr.281001.125

Vancouver

Liu T, Huang T, Jin W, Chu T, Ying R, Zhao H. spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model. Genome Research. 2026. doi:10.1101/gr.281001.125

BibTeX
@article{Liu2026,
  author = {Liu, Tianyu and Huang, Tinglin and Jin, Wengong and Chu, Tinyi and Ying, Rex and Zhao, Hongyu},
  title = {spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model},
  journal = {Genome Research},
  year = {2026},
  doi = {10.1101/gr.281001.125}
}
Kostenlos starten →