Metadata-Version: 2.1
Name: immuneML
Version: 1.1.2
Summary: immuneML is a software platform for machine learning analysis of immune receptor repertoires.
Home-page: https://github.com/uio-bmi/immuneML
Author: immuneML Team
Author-email: milenpa@student.matnat.uio.no
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU Affero General Public License v3
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: pytest (>=4)
Requires-Dist: pandas (>=1)
Requires-Dist: PyYAML (>=5.3)
Requires-Dist: scikit-learn (>=0.23)
Requires-Dist: gensim (>=3.8)
Requires-Dist: matplotlib (>=3.1)
Requires-Dist: editdistance (==0.5.3)
Requires-Dist: regex
Requires-Dist: tzlocal
Requires-Dist: airr (>=1)
Requires-Dist: pystache (==0.5.4)
Requires-Dist: torch (==1.5.1)
Requires-Dist: numpy (>=1.18)
Requires-Dist: h5py (>=2.9.0)
Requires-Dist: dill (>=0.3)
Requires-Dist: tqdm (>=0.24)
Requires-Dist: tensorboard (==1.14.0)
Requires-Dist: requests (>=2.21)
Requires-Dist: plotly (>=4)
Requires-Dist: logomaker (>=0.8)
Requires-Dist: fishersapi
Requires-Dist: matplotlib-venn (>=0.11)
Requires-Dist: scipy
Provides-Extra: tcrdist
Requires-Dist: parasail (==1.2) ; extra == 'tcrdist'
Requires-Dist: tcrdist3 (>=0.1.6) ; extra == 'tcrdist'

# immuneML

![Python application](https://github.com/uio-bmi/immuneML/workflows/Python%20application/badge.svg?branch=master)
![Docker](https://github.com/uio-bmi/immuneML/workflows/Docker/badge.svg?branch=master)

immuneML is a software platform for machine learning analysis of immune receptor sequences.

It supports the analyses of experimental B- and T-cell receptor data,
as well as synthetic data for benchmarking purposes.

In immuneML, users can define flexible workflows supporting different
machine learning libraries (such as scikit-learn or PyTorch), benchmarking of different approaches, numerous reports
of data characteristics, ML algorithms and their predictions, and
visualizations of results.

Additionally, users can extend the platform by defining their own data
 representations, ML models, reports and visualizations.

## Getting started

Steps to setup immuneML environment:

1. Make sure that your machine has python 3.8 installed (or install if necessary: https://www.python.org/downloads/). immuneML can also
work with python 3.7 and 3.6, but some additional packages may need to be manually installed in that case (e.g., dataclasses).
3. Create a virtual environment (as described here: https://docs.python.org/3/library/venv.html)
4. Install the package using pip:

    `pip install git+https://github.com/uio-bmi/immuneML`

To try out the platform, see the quickstart guide and the documentation.



<hr>


© Copyright 2021, Milena Pavlovic, Lonneke Scheffer, Keshav Motwani, Victor Greiff, Geir Kjetil Sandve




