cellmaps-coembedding

===================== Cell Maps CoEmbedder

The Cell Maps CoEmbedding is part of the Cell Mapping Toolkit

.. image:: https://img.shields.io/pypi/v/cellmaps_coembedding.svg :target: https://pypi.python.org/pypi/cellmaps_coembedding

.. image:: https://app.travis-ci.com/idekerlab/cellmaps_coembedding.svg?branch=main :target: https://app.travis-ci.com/idekerlab/cellmaps_coembedding

.. image:: https://readthedocs.org/projects/cellmaps-coembedding/badge/?version=latest :target: https://cellmaps-coembedding.readthedocs.io/en/latest/?badge=latest :alt: Documentation Status

.. image:: https://zenodo.org/badge/620523316.svg :target: https://zenodo.org/doi/10.5281/zenodo.10651873 :alt: Zenodo DOI badge

Creates Coembedding from Cell Maps ImmunoFluorscent Image Embedder <https://cellmaps-image-embedding.readthedocs.io>__ and Cell Maps PPI Embedder <https://cellmaps-ppi-embedding.readthedocs.io>__ using an implementation of MUSE <https://github.com/AltschulerWu-Lab/MUSE>__

• Free software: MIT license
• Documentation: https://cellmaps-coembedding.readthedocs.io.

Dependencies

• cellmaps_utils <https://pypi.org/project/cellmaps-utils>__
• phenograph <https://pypi.org/project/phenograph>__
• numpy <https://pypi.org/project/numpy>__
• torch <https://pypi.org/project/torch>__
• pandas <https://pypi.org/project/pandas>__
• matplotlib <https://pypi.org/project/matplotlib>__
• dill <https://pypi.org/project/dill>__
• tqdm <https://pypi.org/project/tqdm>__
• scipy <https://pypi.org/project/scipy/>__

Compatibility

• Python 3.8 - 3.11

Installation

.. code-block::

git clone https://github.com/idekerlab/cellmaps_coembedding cd cellmaps_coembedding pip install -r requirements_dev.txt make dist pip install dist/cellmaps_coembedding*whl

Run make command with no arguments to see other build/deploy options including creation of Docker image

.. code-block::

make

Output:

.. code-block::

clean remove all build, test, coverage and Python artifacts clean-build remove build artifacts clean-pyc remove Python file artifacts clean-test remove test and coverage artifacts lint check style with flake8 test run tests quickly with the default Python test-all run tests on every Python version with tox coverage check code coverage quickly with the default Python docs generate Sphinx HTML documentation, including API docs servedocs compile the docs watching for changes testrelease package and upload a TEST release release package and upload a release dist builds source and wheel package install install the package to the active Python's site-packages dockerbuild build docker image and store in local repository dockerpush push image to dockerhub

Before running tests, please install pip install -r requirements_dev.txt.

For developers

To deploy development versions of this package

Below are steps to make changes to this code base, deploy, and then run
against those changes.

#. Make changes

   Modify code in this repo as desired

#. Build and deploy

.. code-block::

    # From base directory of this repo cellmaps_coembedding
    pip uninstall cellmaps_coembedding -y ; make clean dist; pip install dist/cellmaps_coembedding*whl



Needed files
------------

The output directories for the image embeddings (see `Cell Maps Image Embedding <https://github.com/idekerlab/cellmaps_image_embedding/>`__) and protein-protein interaction network embeddings (see `Cell Maps PPI Embedding <https://github.com/idekerlab/cellmaps_ppi_embedding/>`__) are required.


Usage
-----

For information invoke :code:`cellmaps_coembeddingcmd.py -h`

**Example usage**

.. code-block::

   cellmaps_coembeddingcmd.py ./cellmaps_coembedding_outdir --embeddings ./cellmaps_image_embedding_outdir ./cellmaps_ppi_embedding_outdir



Via Docker
~~~~~~~~~~~~~~~~~~~~~~

**Example usage**


.. code-block::

   Coming soon...

Credits
-------

This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.

.. _Cookiecutter: https://github.com/audreyr/cookiecutter
.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage
.. _NDEx: http://www.ndexbio.org


=======
History
=======

1.3.0 (2025-05-29)
-------------------

* Create flags for parameters of proteingps coembedding algorithm

1.2.2 (2025-05-15)
-------------------

* Updated to PEP 517 compliant build system
* Bug fixes: update constants, add back L2 normalization and fix separator issue for proteinGPS

1.2.1 (2025-04-14)
-------------------

* Fix scipy package version

1.2.0 (2025-03-19)
-------------------

* Added functionality to generate umap of embeddings (in cellmaps_coembedding.utils)

1.1.0 (2025-03-05)
-------------------

* Added functionality to evaluate embeddings using statistical analysis and visualization (functions
  `get_embedding_eval_data` and `generate_embedding_evaluation_figures` in cellmaps_coembedding.utils).

* Update defauls (EPOCHS and DROPOUT)

1.0.0 (2025-01-28)
-------------------

* Rename auto coembedding name and proteinGPS. `--algorithm auto` option is depreacted and `--algorithm proteingps`
  should be used. The coembedding implementation was moved to `ProteinGPSCoEmbeddingGenerator` class and
  `AutoCoEmbeddingGenerator` is deprecated and calls proteingps. The package name was renamed from `autoembed_sc`
  to `proteingps`.

* Added `mean_losses` mean loses flag and argument in `ProteinGPSCoEmbeddingGenerator`. If set, uses mean of losses
  otherwise sum of losses.

* Constants updated in `ProteinGPSCoEmbeddingGenerator` (triplet_margin=0.2) and in proteingps's fit_predict
  (triplet_margin=0.2, lambda_reconstruction=5.0, lambda_triplet=5.0)

* Bug fix: add missing a `.to(device)` call to ensure tensors are correctly moved to the appropriate device.

* Update version bounds of required packages

0.4.0 (2024-12-02)
-------------------

* Added README generation.

* Refactor code.

0.3.1 (2024-09-13)
------------------

* Bug fix: raise more informative error when no embeddings overlap.

0.3.0 (2024-09-06)
------------------

* Added ``--provenance`` flag to pass a path to json file with provenance information. This removes the
  necessity of input directory to be an RO-Crate.

0.2.0 (2024-07-17)
------------------

* Added a new coembedding algorithm accessible via flag ``--algorithm auto``. This algorithm utilizes neural networks
  to generate latent embeddings, optimizing both reconstruction and triplet losses to improve embedding accuracy
  by learning intra- and inter-modality relationships.

0.1.0 (2024-02-12)
------------------

* First release on PyPI.