SVC: A Vision Transformer-based Spatially and Virtually Embedded Cell Model for Deciphering Subcellular Spatial Transcriptomic Heterogeneity
- 1Yale University
Abstract
Subcellular transcript localization shapes gene regulation and cellular function, yet profiling it at scale remains difficult, limiting our ability to study subcellular heterogeneity across tissues and disease. Here, we present SVC, a Vision Transformer-based spatially and virtually embedded cell model that learns subcellular transcript organization within native tissue context directly from subcellular-resolution spatial transcriptomics. SVC represents each gene's subcellular localization as an image patch and uses other genes within the same cell as context, enabling subcellular contextual learning of spatial dependencies that govern intracellular organization. By integrating gene-function priors, cell morphology, spatial context, and, when available, cell identity, SVC captures unified, spatially grounded representations across genes and cells that connect subcellular organization to cellular state and tissue microenvironment. Across diverse subcellular-resolution spatial transcriptomics datasets, SVC accurately predicts cell-specific subcellular transcript localization and co-organization, generalizes across tissues and technical platforms, and supports subcellular imputation of unmeasured genes and in silico perturbation. Leveraging these capabilities, SVC highlights disease-associated patterns of intracellular transcript reorganization and spatially heterogeneous responses to gene perturbations. Beyond prediction, SVC reveals systematic variation in subcellular transcript organization associated with gene function, cellular states, and tissue microenvironments, uncovering de novo spatial biology that is not accessible by cell-level analysis. SVC's learned representations further transfer to cell- and tissue-level tasks, including cell-level expression imputation, cell clustering, and spatial domain detection. Together, SVC provides a general framework for modeling and interrogating subcellular transcript organization in situ, enabling scalable discovery of subcellular spatial biology.
Related
- Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity
- Deciphering the heterogeneity of chicken gonadal primordial germ cells via single-cell RNA sequencing.
- Spatially guided translation from histology images to transcriptomic profiles using foundation model-driven contrastive learning
- GOLDEN: Gene expression and allele-informed decomposition for genetic heterogeneity in spatial transcriptomic data
- Spatially resolved reaction–diffusion modeling reveals effects of intracellular spatial heterogeneity on yeast galactose network dynamics
BibTeX
@misc{wan2026vision,
title = {{SVC: A Vision Transformer-based Spatially and Virtually Embedded Cell Model for Deciphering Subcellular Spatial Transcriptomic Heterogeneity}},
author = {H. Wan and P. Yang and S. Hou and J. Wang and X. Zhou},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.07.757371},
url = {https://www.biorxiv.org/content/10.64898/2026.10.07.757371v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - SVC: A Vision Transformer-based Spatially and Virtually Embedded Cell Model for Deciphering Subcellular Spatial Transcriptomic Heterogeneity
AU - H. Wan
AU - P. Yang
AU - S. Hou
AU - J. Wang
AU - X. Zhou
PY - 2026
DA - 2026/10/07
PB - bioRxiv
DO - 10.64898/2026.10.07.757371
UR - https://www.biorxiv.org/content/10.64898/2026.10.07.757371v1
AB - Subcellular transcript localization shapes gene regulation and cellular function, yet profiling it at scale remains difficult, limiting our ability to study subcellular heterogeneity across tissues and disease. Here, we present SVC, a Vision Transformer-based spatially and virtually embedded cell model that learns subcellular transcript organization within native tissue context directly from subcellular-resolution spatial transcriptomics. SVC represents each gene's subcellular localization as an image patch and uses other genes within the same cell as context, enabling subcellular contextual learning of spatial dependencies that govern intracellular organization. By integrating gene-function priors, cell morphology, spatial context, and, when available, cell identity, SVC captures unified, spatially grounded representations across genes and cells that connect subcellular organization to cellular state and tissue microenvironment. Across diverse subcellular-resolution spatial transcriptomics datasets, SVC accurately predicts cell-specific subcellular transcript localization and co-organization, generalizes across tissues and technical platforms, and supports subcellular imputation of unmeasured genes and in silico perturbation. Leveraging these capabilities, SVC highlights disease-associated patterns of intracellular transcript reorganization and spatially heterogeneous responses to gene perturbations. Beyond prediction, SVC reveals systematic variation in subcellular transcript organization associated with gene function, cellular states, and tissue microenvironments, uncovering de novo spatial biology that is not accessible by cell-level analysis. SVC's learned representations further transfer to cell- and tissue-level tasks, including cell-level expression imputation, cell clustering, and spatial domain detection. Together, SVC provides a general framework for modeling and interrogating subcellular transcript organization in situ, enabling scalable discovery of subcellular spatial biology.
ER -