FlowSOM

The complete FlowSOM package known from R and Bioconductor, now available in Python with scverse integration!

FlowSOM is a clustering and visualization algorithm originally based on a self-organizing map (SOM). FlowSOM is used to distinguish cell populations from cytometry data in an unsupervised way and can help to gain deeper insights in fields such as immunology and oncology.

Getting started

Please refer to the documentation. In particular, the following resources are available:

Installation

You need to have Python 3.9 or newer installed on your system. There are several options to install FlowSOM:

Recommended installation: install the latest release of FlowSOM from PyPI:

pip install flowsom

Alternative 1: install the development version from the GitHub repository:

pip install git+https://github.com/saeyslab/FlowSOM_Python

Alternative 2: install the FlowSOM Conda package via the Conda package manager:

conda install -c conda-forge flowsom

Usage

Starting from an FCS file that is properly transformed, compensated and checked for quality, the following code can be used to run the FlowSOM algorithm:

# Import the FlowSOM package
import flowsom as fs

# Load the FCS file
ff = fs.io.read_FCS("./tests/data/ff.fcs")

# Run the FlowSOM algorithm
fsom = fs.FlowSOM(
    ff, cols_to_use=[8, 11, 13, 14, 15, 16, 17], xdim=10, ydim=10, n_clusters=10, seed=42
)

# Plot the FlowSOM results
p = fs.pl.plot_stars(fsom, background_values=fsom.get_cluster_data().obs.metaclustering)
p.show()

Release notes

See the changelog.

Contact

For questions and help requests or if you found a bug, please use the issue tracker.

Citation

If you use FlowSOM in your work, please cite the following papers:

A. Couckuyt, B. Rombaut, Y. Saeys, and S. Van Gassen, “Efficient cytometry analysis with FlowSOM in Python boosts interoperability with other single-cell tools,” Bioinformatics, vol. 40, no. 4, p. btae179, Apr. 2024, doi: 10.1093/bioinformatics/btae179.

S. Van Gassen et al., “FlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data,” Cytometry Part A, vol. 87, no. 7, pp. 636–645, 2015, doi: 10.1002/cyto.a.22625.