segger

GNN-based cell segmentation of spatial transcriptomics data.

segger overview

Segger is a graph neural network (GNN)-based method that formulates cell segmentation in imaging-based spatial transcriptomics (iST) as a problem of transcript–cell assignment. Rather than relying solely on geometric proximity, Segger assumes that a transcript belongs to a cell if it is consistent both with its local spatial context and with the gene expression programs that define cell identity, as captured in a shared latent representation.

—Heidari, Moorman, et al., segger methods description

Important

Latest cuspa-accelerated segger: the version used for the manuscript, which scales to billion-transcript whole-transcriptome datasets (e.g. Atera) using NVIDIA cuspa, is available as release v0.4.0-manuscript. It requires CUDA 13 and Python 3.13 and is not yet stable. Install it with git clone --branch v0.4.0-manuscript https://github.com/dpeerlab/segger.git && cd segger && pixi install.

Methods description | GitHub

Contributing

See CONTRIBUTING.md.

Citation

If you use segger in your research, please cite:

Heidari, E., Moorman, A., et al. Segger: Fast and accurate cell segmentation of imaging-based spatial transcriptomics data. Methods description (2026). https://github.com/dpeerlab/segger/blob/main/segger_methods.pdf

@misc{heidari2026segger,
  title={Segger: Fast and accurate cell segmentation of imaging-based spatial transcriptomics data},
  author={Heidari, Elyas and Moorman, Andrew and others},
  note={Methods description},
  year={2026},
  howpublished={\url{https://github.com/dpeerlab/segger/blob/main/segger_methods.pdf}}
}