asheone / propythia

Python generic modular semi-automated platform containing functions for the classification of proteins based on their physicochemical properties using ML.

"# propythia2.0" |License| |PyPI version| |RTD version|

ProPythia

ProPythia (platform for the classification of peptides/proteins using machine and deep learning) is a Python generic modular semi-automated platform containing functions for the classification of proteins based on their physicochemical properties using ML and DL. ProPythia facilitates the major tasks of ML and includes modules to read and alter sequences, calculate several types of protein descriptors, pre-process datasets, execute feature selection and dimensionality reduction, visualization of t-SNE and UMAP, perform clustering, train and optimize ML and DL models and make predictions with different algorithms. ProPythia has an adaptable modular architecture being a versatile and easy-to-use tool to apply ML/DL analysis over protein sequences.

It was tested on the classification of membrane active antimicrobial peptides and enzymes, available in folder examples.

Documentation

Documentation available at


Instalation from PyPI (stable releases)

pip install propythia

Credits and License

Developed at the Centre of Biological Engineering, University of Minho

Please refer to this work through this publication by Ana Marta Sequeira, Diana Lousa, Miguel Rocha :

- Sequeira A.M., Lousa D., Rocha M. (2021) ProPythia: A Python Automated Platform for the Classification of Proteins Using
Machine Learning. Practical Applications of Computational Biology & Bioinformatics, 14th International Conference (PACBB 2020).
PACBB 2020. Advances in Intelligent Systems and Computing, vol 1240. Springer, Cham. https://doi.org/10.1007/978-3-030-54568-0_4

Released under the GNU Public License (version 3.0).


.. |License| image:: https://img.shields.io/badge/license-GPL%20v3.0-blue.svg
   :target: https://opensource.org/licenses/GPL-3.0
.. |PyPI version| image:: https://badge.fury.io/py/propythia.svg
   :target: https://badge.fury.io/py/propythia
.. |RTD version| image:: https://readthedocs.org/projects/propythia/badge/?version=latest&style=plastic
   :target: https://propythia.readthedocs.io/