Bayesian segmentation of imaging-based spatial transcriptomics data
- Improved integration with 10x Xenium
- Better parallelism
- Optimized speed
- Improved NCV coloring
- Reworked polygon outputs
See the changelog for more detalis.
Baysor is a tool for performing cell segmentation on imaging-based spatial transcriptomics data. It optimizes segmentation considering the likelihood of transcriptional composition, size and shape of the cell. The approach can take into account nuclear or cytoplasm staining, however, can also perform segmentation based on the detected molecules alone. The details of the method are described in the paper, or pre-print (old version of the text). To reproduce the analysis from the paper see BaysorAnalysis repo.
See the documentation for usage instructions.
For more details and alternative ways of installation see the documentation
The easiest way to install Baysor on Linux is to download a binary from the release section (see Assets). There, you can use bin/baysor executable. For other platforms, "Install as a Julia package" is a recommended way.
curl -fsSL https://install.julialang.org | shInstall Baysor:
julia -e 'using Pkg; Pkg.add(PackageSpec(url="https://github.com/kharchenkolab/Baysor.git")); Pkg.build()'If you find Baysor useful for your publication, please cite:
Petukhov V, Xu RJ, Soldatov RA, Cadinu P, Khodosevich K, Moffitt JR & Kharchenko PV.
Cell segmentation in imaging-based spatial transcriptomics.
Nat Biotechnol (2021). https://doi.org/10.1038/s41587-021-01044-w
