https://github.com/camlab-bioml/astir

astir | Automated cell identity from single-cell multiplexed imaging and proteomics 🖥🔬✨
https://github.com/camlab-bioml/astir

imaging-mass-cytometry machine-learning multiplexed-imaging

Last synced: 4 months ago
JSON representation

astir | Automated cell identity from single-cell multiplexed imaging and proteomics 🖥🔬✨

• Host: GitHub
• URL: https://github.com/camlab-bioml/astir
• Owner: camlab-bioml
• License: gpl-2.0
• Created: 2020-05-04T13:42:31.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2025-06-25T20:16:47.000Z (about 1 year ago)
• Last Synced: 2025-11-21T03:29:38.717Z (7 months ago)
• Topics: imaging-mass-cytometry, machine-learning, multiplexed-imaging
• Language: Python
• Homepage: https://astir.readthedocs.io/en/latest
• Size: 49.4 MB
• Stars: 57
• Watchers: 5
• Forks: 13
• Open Issues: 15
• Metadata Files:
  • Readme: README.rst
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

          
===================================================================================

astir - Automated cell identity from single-cell multiplexed imaging and proteomics

===================================================================================

|Build Status| |PyPI| |Code Style|

.. |Build Status| image:: https://travis-ci.com/camlab-bioml/astir.svg?branch=master

    :target: https://travis-ci.org/camlab-bioml/astir

.. |Code Style| image:: https://img.shields.io/badge/code%20style-black-black

    :target: https://github.com/python/black

.. |PyPI| image:: https://img.shields.io/badge/pypi-v2.1-orange

    :target: https://pypi.org/project/pypi/

``astir`` is a modelling framework for the assignment of cell type across a range of single-cell technologies such as Imaging Mass Cytometry (IMC). ``astir`` is built using `pytorch `_ and uses recognition networks for fast minibatch stochastic variational inference. 

Key applications:

- Automated assignment of cell type and state from highly multiplexed imaging and proteomic data

- Diagnostic measures to check quality of resulting type and state inferences

- Ability to map new data to cell types and states trained on existing data using recognition neural networks

- A range of plotting and data loading utilities

.. image:: https://www.camlab.ca/img/astir.png

    :align: center

    :alt: automated single-cell pathology

Getting started

---------------------

Launch the interactive tutorial: |in collab| |on github|  

.. |in collab| image:: https://camo.githubusercontent.com/52feade06f2fecbf006889a904d221e6a730c194/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667

    :target: https://colab.research.google.com/github/camlab-bioml/Astir-Vignette/blob/main/astir_tutorial.ipynb

.. |on github| image:: https://img.shields.io/badge/on-github-black

    :target: https://github.com/camlab-bioml/Astir-Vignette

See the full `documentation `_ and check out the `tutorials `_.

Authors

---------------------

| Jinyu Hou, Sunyun Lee, Michael Geuenich, Kieran Campbell

| Lunenfeld-Tanenbaum Research Institute & University of Toronto