EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diffusion-based representation integration for foundation models improves spatial transcriptomics analysis

Atishay Jain iD, Tuan M Pham iD, David H Laidlaw iD, Ying Ma iD, Ritambhara Singh iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag259 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Atishay Jain und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Brown University, Providence, RI 02912, United States. Hauptthemen laut MEDLINE: Transcriptome, Computational Biology, Gene Expression Profiling. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, NIMH NIH HHS, National Institute of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation We propose DRIFT, a framework that integrates spatial context into the input representations for foundation models by leveraging diffusion on spatial graphs derived from spatial transcriptomics (ST) data. ST captures gene expression profiles while preserving spatial context, enabling downstream analysis tasks such as cell-type annotation, clustering, and cross-sample alignment. However, due to its emerging nature, there are very few foundation models that can utilize ST data to generate embeddings generalizable across multiple tasks. Meanwhile, well-documented foundational models trained on large-scale single-cell gene expression (scRNA-seq) data have demonstrated generalizable performance across scRNA-seq assays, tissues, and tasks; however, they do not leverage the spatial information in ST data. We use heat kernel diffusion to propagate embeddings across spatial neighborhoods, incorporating the local neighborhood context of the ST data while preserving the transcriptomic representations learned by state-of-the-art single-cell foundation models. Results We systematically benchmark five foundational models (both scRNA-seq and ST-based) across key ST tasks such as annotation, alignment, and clustering, ensuring a comprehensive evaluation of our proposed framework. Our results show that DRIFT significantly improves the performance of existing foundational models on ST data over specialized state-of-the-art methods. Overall, DRIFT is an effective, accessible, and generalizable framework that bridges the gap toward universal models for modeling spatial transcriptomics. Availability and implementation Code and data are available at https://github.com/rsinghlab/DRIFT.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TranscriptomeComputational BiologyGene Expression ProfilingSpatial TranscriptomicsSingle-Cell Gene Expression AnalysisAnimals

Autor:innen und Institutionen

  • Department of Computer Science, Brown University, Providence, RI 02912, United States.
  • Center for Computational Molecular Biology, Brown University, Providence, RI 02912, United States.
  • Department of Biostatistics, Brown University, Providence, RI 02903, United States.

ORCID-Profile: Atishay Jain, Tuan M Pham, David H Laidlaw, Ying Ma, Ritambhara Singh

Förderung

  • NHGRI NIH HHS
  • NIMH NIH HHS
  • National Institute of Health
  • Training Program for Interactionist Cognitive Neuroscience

Zitieren

APA

Jain, A., Pham, T. M., Laidlaw, D. H., Ma, Y., & Singh, R. (2026). Diffusion-based representation integration for foundation models improves spatial transcriptomics analysis. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag259

Vancouver

Jain A, Pham TM, Laidlaw DH, Ma Y, Singh R. Diffusion-based representation integration for foundation models improves spatial transcriptomics analysis. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag259

BibTeX
@article{Jain2026,
  author = {Jain, Atishay and Pham, Tuan M and Laidlaw, David H and Ma, Ying and Singh, Ritambhara},
  title = {Diffusion-based representation integration for foundation models improves spatial transcriptomics analysis},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag259}
}
Kostenlos starten →