segger is a cutting-edge tool for cell segmentation in single-molecule spatial omics datasets. By leveraging graph neural networks (GNNs) and heterogeneous graphs, segger offers unmatched accuracy and scalability.
πΎ Installation Guide
Get started with installing segger on your machine.
π User Guide
Learn how to use segger for cell segmentation tasks.
π» Command-Line Interface (CLI)
Explore the CLI options for working with segger.
π API Reference
Dive into the detailed API documentation for advanced usage.
π Sample Workflow
Check out our tutorial showcasing a sample workflow with segger.
Spatial omics segmentation faces issues like:
segger tackles these with a graph-based approach, achieving superior segmentation accuracy.
Segger highly depends on PyTorch Geometric. One must install its dependencies (such as torch-sparse
and torch-scatter
) based on their systemβs specifications, especially CUDA and PyTorch versions.
Please follow the official PyTorch Geometric Installation Guide to install the correct versions of torch-sparse
, torch-scatter
, and other relevant libraries.
Hereβs how to install them manually, e.g., for torch 2.0.0:
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
pip install torch-sparse -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.0.0+cu120.html
pip install torch-sparse -f https://data.pyg.org/whl/torch-2.0.0+cu120.html
Afterwards choose the installation method that best suits your needs.
To set up Segger with micromamba
and install the required dependencies, use the following commands:
micromamba create -n segger-rapids --channel-priority 1 \
-c rapidsai -c conda-forge -c nvidia -c pytorch -c pyg \
rapids=24.08 python=3.* 'cuda-version>=11.4,<=11.8' jupyterlab \
'pytorch=*=*cuda*' 'pyg=*=*cu118' pyg-lib pytorch-sparse
micromamba install -n segger-rapids --channel-priority 1 --file mamba_environment.yml
micromamba run -n segger-rapids pip install --no-deps ./
For a straightforward local installation from GitHub, clone the repository and install the package using pip
:
git clone https://github.com/EliHei2/segger_dev.git
cd segger_dev
pip install -e "."
For installations requiring RAPIDS and CUDA 11 support, run:
pip install -e ".[rapids11]"
For installations requiring RAPIDS and CUDA 12 support, run:
pip install -e ".[rapids12]"
segger is open-source and welcomes contributions. Join us in advancing spatial omics segmentation!
Source Code
GitHub
Bug Tracker
Report Issues
Full Documentation
API Reference