GatorST: A Versatile Contrastive Meta‐Learning Framework for Spatial Transcriptomic Data Analysis
Small Methods · 2026-05 · 10 (9)
DOI: 10.1002/smtd.202600006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Small Methods, online erschienen am 08.04.2026. Verfasst von Zhenhao Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, Indiana, USA. Hauptthemen laut MEDLINE: Gene Expression Profiling, Transcriptome, Software, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NIGMS NIH HHS, National Institute of General Medical Sciences of the National Institutes of Health.
Abstract (Originalsprache)
Recent advances in spatial transcriptomics (ST) have revolutionized the understanding of cellular functions by providing gene expression profiles with rich spatial context. Effectively learning spatial representations is essential for downstream analyses and requires robust integration of spatial and transcriptomic information. Although existing methods show promise, they often fail to capture local (neighbor‐level) and global (tissue‐wide) contexts, and methods based on contrastive learning often rely on augmentation strategies that introduce noise and instability. GatorST, a novel and versatile framework, explicitly integrates graph‐based modeling with advanced meta‐learning strategies to generate spatially informed representations of ST data. Locally, a spot‐spot graph connects each node to its nearest neighbors, while two‐hop subgraphs capture fine‐grained spatial context. Globally, gene expression profiles are clustered to produce pseudo‐labels, providing weak supervision for representation learning. An episodic training strategy inspired by meta‐learning further enhances GatorST's ability to generalize to new spatial contexts, ensuring robust integration of local and global spatial information. Comprehensive comparisons with fifteen state‐of‐the‐art methods demonstrate that GatorST consistently outperforms existing approaches in identifying spatial domains, imputing gene expression, removing batch effects, and inferring spatial trajectories. By integrating local spatial topology with global gene expression patterns, GatorST provides biologically meaningful representations that advance key downstream analyses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, Indiana, USA.
- Department of Health Outcomes & Biomedical Informatics, College of Medicine, University of Florida, Gainesville, Florida, USA.
- Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia, USA.
- Department of Biomedical Informatics, College of Medicine, The Ohio State University, Columbus, Ohio, USA.
ORCID-Profile: Yuxi Liu, Qianqian Song
Förderung
- NIH HHS
- NIGMS NIH HHS
- National Institute of General Medical Sciences of the National Institutes of Health
- National Institutes of Health
Zitieren
APA
Zhang, Z., Liu, Y., Wang, S., Ma, Q., Song, Q., & Bian, J. (2026). GatorST: A Versatile Contrastive Meta‐Learning Framework for Spatial Transcriptomic Data Analysis. Small Methods, 10(9). https://doi.org/10.1002/smtd.202600006
Vancouver
Zhang Z, Liu Y, Wang S, Ma Q, Song Q, Bian J. GatorST: A Versatile Contrastive Meta‐Learning Framework for Spatial Transcriptomic Data Analysis. Small Methods. 2026;10(9). doi:10.1002/smtd.202600006
BibTeX
@article{Zhang2026,
author = {Zhang, Zhenhao and Liu, Yuxi and Wang, Song and Ma, Qin and Song, Qianqian and Bian, Jiang},
title = {GatorST: A Versatile Contrastive Meta‐Learning Framework for Spatial Transcriptomic Data Analysis},
journal = {Small Methods},
year = {2026},
volume = {10},
number = {9},
doi = {10.1002/smtd.202600006}
}
EUVIMED