ASTRA enables zero-shot super-resolution of spatial transcriptomics across capture geometries
- 1Peking University
Abstract
Spatial transcriptomic super-resolution recovers tissue organization obscured by coarse sampling, but fitting a model to each section greatly increases computational cost and reduces practicality. We introduce ASTRA, a cross-platform pretrained model that reconstructs expression from histology and measured RNA by zero-shot inference. Training with arbitrarily shaped count-bearing regions, termed parents, enables one frozen model to accommodate dense bins and separated spots. Across six held-out Visium HD sections, ASTRA achieved higher correlations under dense-bin and pseudo-Visium sampling, lower dense-bin errors and substantially shorter processing times than existing methods. It improved colorectal tissue segmentation and tumor-boundary recovery. In real colorectal Visium, reconstruction spatially resolved a stromal transcriptional state supported by measured RNA. The same checkpoint supported regional and nucleus-associated analyses across 43 invasive lobular carcinoma sections and within-spot interpretation across 92 triple-negative breast cancer sections. ASTRA establishes a reusable framework for practical, cohort-scale spatial transcriptomic super-resolution across platforms.
Related
- Decoder-FFPE-seq enables sensitive, genome-wide spatial transcriptomics of archival tissues at single-cell resolution
- OncoSpot enables benchmarking of cancer spatial transcriptomics methods across tumor evolutionary modes
- PRISM: probabilistic cell-type resolution with integrated spatial modelling for simultaneous ambient RNA decontamination and doublet correction in spatial transcriptomics
- Live Spatial Transcriptomics Enables Longitudinal Tissue Mapping
- Cellular-Resolution Spatial Transcriptomics Reveals Laminar VSMC Phenotypic Remodeling and a Hypoxic Medial Core in Human Thoracic Aortic Dissection
BibTeX
@misc{ye2026astra,
title = {{ASTRA enables zero-shot super-resolution of spatial transcriptomics across capture geometries}},
author = {J. Ye and Q. Cui},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.30.755663},
url = {https://www.biorxiv.org/content/10.64898/2026.09.30.755663v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - ASTRA enables zero-shot super-resolution of spatial transcriptomics across capture geometries
AU - J. Ye
AU - Q. Cui
PY - 2026
DA - 2026/09/30
PB - bioRxiv
DO - 10.64898/2026.09.30.755663
UR - https://www.biorxiv.org/content/10.64898/2026.09.30.755663v1
AB - Spatial transcriptomic super-resolution recovers tissue organization obscured by coarse sampling, but fitting a model to each section greatly increases computational cost and reduces practicality. We introduce ASTRA, a cross-platform pretrained model that reconstructs expression from histology and measured RNA by zero-shot inference. Training with arbitrarily shaped count-bearing regions, termed parents, enables one frozen model to accommodate dense bins and separated spots. Across six held-out Visium HD sections, ASTRA achieved higher correlations under dense-bin and pseudo-Visium sampling, lower dense-bin errors and substantially shorter processing times than existing methods. It improved colorectal tissue segmentation and tumor-boundary recovery. In real colorectal Visium, reconstruction spatially resolved a stromal transcriptional state supported by measured RNA. The same checkpoint supported regional and nucleus-associated analyses across 43 invasive lobular carcinoma sections and within-spot interpretation across 92 triple-negative breast cancer sections. ASTRA establishes a reusable framework for practical, cohort-scale spatial transcriptomic super-resolution across platforms.
ER -