Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity
- 1Center for Computational Biology, Whiting School of Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America.
- 2Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America.
Abstract
Imaging-based spatially resolved transcriptomics (imSRT) technologies provide high-throughput molecular-resolution spatial characterization of genes within cells. Conventional analysis methods to identify cell-types and states in imSRT data rely on gene count matrices derived from tallying the number of mRNA molecules detected for each gene per segmented cell, thereby overlooking subcellular heterogeneity that can be useful in defining cell states. To take advantage of the molecular-resolution information in imSRT data and potentially identify cell-states based on subcellular heterogeneity, we developed STARIT (Spatial Transcriptomics As Rasterized Image Tensors). STARIT converts transcripts within segmented cells in imSRT data into an image-based tensor representation that can be combined with deep learning computer vision models for downstream analysis. Using simulated and real imSRT data, we demonstrate that STARIT distinguishes transcriptionally distinct cell-types and further separates cell states based on subcellular transcript localization, which conventional gene count analysis fails to capture. By providing a standardized framework to encode subcellular molecular information in imSRT data, STARIT will enable deeper insights into subcellular heterogeneity and enhance the identification and characterization of cell-types and states that are overlooked by gene count representations. Author summary: Imaging-based spatial transcriptomics technologies can map the locations of individual RNA transcripts within cells, providing an opportunity to study how genes are spatially organized at subcellular resolution. However, most current analysis approaches simplify these data by counting transcripts per cell, reducing rich spatial information into cell-by-gene matrices and potentially overlooking biologically meaningful differences in subcellular transcript organization.
Related
- Kintsugi maps nucleus-poor RNA compartments in subcellular spatial transcriptomics
- Imaging-based spatial isoform transcriptomics resolves transcript diversity at cellular and subcellular resolution
- Temporal organization of shared brain states characterizes heterogeneity in major depressive disorder
- SVC: A Vision Transformer-based Spatially and Virtually Embedded Cell Model for Deciphering Subcellular Spatial Transcriptomic Heterogeneity
- Keloid transcriptomics reveal heterogeneity in fibroblast subtype enrichment, gene expression, and immune cell responses
BibTeX
@article{velazquez2026spatial,
title = {{Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity}},
author = {Dee Velazquez and Caleb Hallinan and Roujin An and Kalen Clifton and Jean Fan},
journal = {PLOS Computational Biology},
year = {2026},
month = oct,
doi = {10.1371/journal.pcbi.1014845},
url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014845},
note = {CC BY},
}
RIS
TY - JOUR
TI - Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity
AU - Dee Velazquez
AU - Caleb Hallinan
AU - Roujin An
AU - Kalen Clifton
AU - Jean Fan
PY - 2026
DA - 2026/10/06
JO - PLOS Computational Biology
DO - 10.1371/journal.pcbi.1014845
UR - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014845
AB - Imaging-based spatially resolved transcriptomics (imSRT) technologies provide high-throughput molecular-resolution spatial characterization of genes within cells. Conventional analysis methods to identify cell-types and states in imSRT data rely on gene count matrices derived from tallying the number of mRNA molecules detected for each gene per segmented cell, thereby overlooking subcellular heterogeneity that can be useful in defining cell states. To take advantage of the molecular-resolution information in imSRT data and potentially identify cell-states based on subcellular heterogeneity, we developed STARIT (Spatial Transcriptomics As Rasterized Image Tensors). STARIT converts transcripts within segmented cells in imSRT data into an image-based tensor representation that can be combined with deep learning computer vision models for downstream analysis. Using simulated and real imSRT data, we demonstrate that STARIT distinguishes transcriptionally distinct cell-types and further separates cell states based on subcellular transcript localization, which conventional gene count analysis fails to capture. By providing a standardized framework to encode subcellular molecular information in imSRT data, STARIT will enable deeper insights into subcellular heterogeneity and enhance the identification and characterization of cell-types and states that are overlooked by gene count representations. Author summary: Imaging-based spatial transcriptomics technologies can map the locations of individual RNA transcripts within cells, providing an opportunity to study how genes are spatially organized at subcellular resolution. However, most current analysis approaches simplify these data by counting transcripts per cell, reducing rich spatial information into cell-by-gene matrices and potentially overlooking biologically meaningful differences in subcellular transcript organization.
SN - 1553-7358
SN - 1553-734X
ER -