SPATNIC Identifies Individual Cancer Cells Across Spatial and Single-Cell Transcriptomics
Start here
SPATNIC is a variational autoencoder designed to identify individual cancer cells within spatial and single-cell transcriptomic data. It was trained on Xenium cells labeled by pathologist review of matched H&E images, grounding its predictions in histopathology. In colorectal cancer, it matches or exceeds existing tools in primary tumors and in liver and lung metastases. The method also generalizes zero-shot across multiple platforms, including Visium, Visium HD, CosMx, Xenium, MERSCOPE, and single-cell RNA sequencing. The work was posted as a preprint in bioRxiv Cancer Biology on October 22, 2026, and has not yet undergone peer review. Independent validation in other cancer types and clinical datasets remains to be established.
Written by a model from the reports · updated 5 hours ago
Coverage timeline
Follow the coverage to see the different angles.
- biorxiv.orgPickSPATNIC enables H&E-grounded cancer-cell identification across spatial and single-cell transcriptomic modalities in colorectal cancer
SPATNIC is a variational autoencoder trained on Xenium cells labeled by pathologist review of matched H&E images to distinguish individual cancer cells from normal cells. The model matches or exceeds existing tools in primary colorectal cancer and liver and lung metastases, and generalizes zero-shot to Visium, Visium HD, CosMx, Xenium, MERSCOPE, and single-cell RNA sequencing.
Heat trend for this story
Heat now 6·Peak in the comparable set 7 (Oct 22 22:00)·Change over 24h in the comparable set –·Participants now 1
Participants counted above, heat below. The trend compares only the participants observed in full throughout, so its set can be smaller than the heat figure itself. Move the pointer or click the chart for an hour's reading; the left and right arrow keys work too.