cofe

Cyclic Ordering with Feature Extraction

https://github.com/bharathananth/cofe

Repository

Cyclic Ordering with Feature Extraction

README.rst

=======================================
Cyclic Ordering with Feature Extraction
=======================================
.. image:: images/coffee_stain.png
   :alt: COFE Logo
   :align: right
   :width: 200px

This package (COFE - *kaa·fee*) implements nonlinear dimensionality reduction with a circular constraint on the (dependent) principal components.

* Preprint: https://doi.org/10.1101/2024.03.13.584582
* Free software: GNU General Public License v3

Features
--------

* Assigns time-labels to high-dimensional data representing an underlying rhythmic process
* Identifies features in the data that contribute to the temporal reordering
* Regularized unsupervised machine learning approach with automated choice of hyperparameters.

Installation
------------

* Prerequisites
   - Python 3.9 or better installed on your system. You can download and install Python from the `official Python website `_.
   - Git installed on your system. You can download and install Git from the `official Git website `_.
   - Conda installed on your system. You can download and install conda from `official Conda website `_.

* Install and 
   #. Open a terminal or command prom 

* Clone the COFE Repository
   #. Open a terminal or command prompt.
   #. Navigate to the directory where you want to install COFE.
   #. Clone the COFE repository from GitHub by running the following command:

   .. code-block:: bash
   
      git clone https://github.com/bharathananth/COFE.git

* Installation
   #. Navigate to the COFE directory:

      .. code-block:: bash
      
         cd COFE

   #. Install and switch to *circular_ordering-env* environment: 

      .. code-block:: bash

        conda env create -f environment.yml
        conda activate circular_ordering-env

   #. You can install COFE and its dependencies by running the following command:

      .. code-block:: bash
   
         python -m pip install .

* Verify Installation
   To verify that COFE is installed correctly, you can try importing it in a Python environment. Open a Python interpreter or create a new Python script, and then try importing COFE:

   .. code-block:: python
   
      import COFE.analyse
      import COFE.plot
      import COFE.scpca

Getting Started
---------------

You can get started with COFE by running it on synthetic data, as illustrated in the Jupyter notebook 
``synthetic_data_example.ipynb`` located in the ``docs/`` folder.

For detailed usage, refer to the docstrings of the COFE functions.


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

Owner

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Cyclic Ordering with Feature Extraction (COFE)
message: Please cite both the paper and the software.
type: software
authors:
  - given-names: Bharath
    family-names: Ananthasubramaniam
    email: bharath.ananthasubramaniam@hu-berlin.de
    affiliation: Humboldt-Universität zu Berlin
    orcid: 'https://orcid.org/0000-0003-4467-1546'
  - given-names: Ramji
    family-names: Venkataramanan
    email: rv285@cam.ac.uk
    affiliation: University of Cambridge
    orcid: 'https://orcid.org/0000-0001-7915-5432'
repository-code: 'https://github.com/bharathananth/COFE'
abstract: >-
  COFE is a novel unsupervised machine learning approach
  that can use single high-throughput omics samples (without
  time labels) from individuals to reconstruct circadian
  rhythms across cohorts. COFE can simultaneously assign
  time labels to samples and identify rhythmic data features
  used for temporal reconstruction, while also detecting
  invalid orderings. 
keywords:
  - machine learning
  - snapshot data
  - circadian medicine
  - dimensionality reduction
  - latent representation
  - manifold learning
license: GPL-3.0
commit: e19dc4f
version: 1.1.0
date-released: '2025-04-05'
preferred-citation:
  type: article
  authors:
    - family-names: Ananthasubramaniam
      given-names: Bharath
    - family-names: Venkataramanan
      given-names: Ramji
  title: "Time series-free rhythm profiling using COFE reveals multi-omic circadian rhythms in in vivo human cancers"
  year: 2024
  doi: 10.1101/2024.03.13.584582
  url: https://doi.org/10.1101/2024.03.13.584582
  journal: "bioRxiv"

GitHub Events