{
  "id": 10757147,
  "title": "SpatialTRACE predicts anatomical axes and regions in spatial transcriptomics and microscopy",
  "url": "https://urgent.news/2026/09/29/spatialtrace-predicts-anatomical-axes-and-regions-in-spatial",
  "topic": "science",
  "section": "Science",
  "published": "2026-09-29T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.09.23.753836v1?rss=1"
  },
  "original_language": "en",
  "account": "Spatial transcriptomics measures gene expression within tissue samples. Yet, interpreting the results requires maps that connect gene expression with cellular components to the tissue's structure. Annotating whole sections typically demands significant manual effort. We created SpatialTRACE (Tissue Region and Axis Coordinate Estimation), which integrates graph and image-based models to extend annotations of a few structures to tissue-wide maps of anatomical axes and regions.\n\nSpatialTRACE-Graph merges gene-expression data with spatial connections to forecast anatomical coordinates or groupings across spatial transcriptomic datasets. In mouse small-intestine samples, it forecasted crypt-villus and epithelial-distance axis coordinates using just 10 annotated training villi and recognized Peyer's patches from region labels. SpatialTRACE-Image predicts the same anatomical axis coordinates and regions throughout entire tissue images from DAPI alone. This multiscale vision transformer refines coordinate and region predictions made by SpatialTRACE-Graph. We tested SpatialTRACE-Image on immunofluorescence images to map the anatomical distribution of antigen-specific P14 CD8 T cells responding to Lymphocytic Choriomeningitis Virus (LCMV) infection in mouse small intestines. Compared to a control section, a section treated with a retinoic acid receptor inhibitor showed fewer P14 CD8 T cells overall, with a smaller proportion in the upper-villus lamina propria and a relative increase in the muscularis. In summary, the SpatialTRACE models minimize repeated manual annotation and offer a method to transfer anatomical maps derived from spatial transcriptomics to DAPI-containing microscopy data.",
  "summary": "Spatial transcriptomics measures gene expression in tissue sections. However, interpretation requires anatomical maps that link gene expression and cellular composition to tissue structure. Annotating entire sections often requires extensive manual labor. We developed SpatialTRACE (Tissue Region and Axis Coordinate Estimation), consisting of graph- and image-based models, to extend annotations of…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}