Metadata-Version: 2.1
Name: docktgrid
Version: 0.0.1
Summary: Create customized voxel representations of protein-ligand complexes using GPU.
Author-email: Matheus Müller Pereira da Silva <matheusp@posgrad.lncc.br>
License: LGPL-3.0-only
Project-URL: Homepage, https://github.com/gmmsb-lncc/docktgrid
Keywords: voxel-grid,deep-learning,molecular-docking,virtual-screening
Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Environment :: GPU
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Description-Content-Type: text/x-rst
License-File: COPYING.LESSER
Requires-Dist: torch <3.0.0,>=2.1.0
Requires-Dist: biopandas <1.0.0,>=0.4.1
Requires-Dist: scipy <2.0.0,>=1.11.3
Requires-Dist: numpy <2.0.0,>=1.26.1
Provides-Extra: dev
Requires-Dist: black ; extra == 'dev'
Requires-Dist: pytest ; extra == 'dev'

.. image:: https://img.shields.io/badge/license-LGPLv3-green
  :target: https://www.gnu.org/licenses/lgpl-3.0.en.html

.. image:: https://img.shields.io/badge/code%20style-black-black
  :target: https://github.com/psf/black

=========
DockTGrid
=========

Generate voxel representations of protein-ligand complexes for deep learning applications.

.. image:: https://i.imgur.com/VVkQg4t.png
    :align: center
    :width: 50%

    
📌 Features
===========

* GPU-accelerated voxelization of protein-ligand complexes.
* Easy customization of voxel grid channels and parameters.
* Readily usable with `PyTorch <https://pytorch.org/>`_.
* Support for multiple file formats (to be expanded).

  * ✅ PDB
  * ❌ MOL2
  * ❌ SDF



🚀 Getting Started
==================

Installation (pip)
------------------
Install DockTGrid using `pip <https://pip.pypa.io/en/stable/>`_::

    $ python -m pip install docktgrid


Development
-----------

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
Python 3.11 is recommended, other versions may work but are not tested.

Clone the repository::

    $ git clone https://github.com/gmmsb-lncc/docktgrid.git
    $ cd docktgrid


Create a new environment using `venv` and activate it::

    $ python3.11 -m venv env
    $ source env/bin/activate

Or if you prefer using `conda <https://docs.conda.io/en/latest/>`_::

    $ conda create --prefix ./venv python=3.11
    $ conda activate ./venv



.. Installation (development)
.. --------------------------

Install the required packages::

    $ python -m pip install -r requirements.txt


.. Testing
.. -------

Run the tests::

    $ python -m pytest tests/



🖥️ Usage
========

See the `documentation <https://docktgrid.readthedocs.io/>`_ for more information on how to use DockTGrid.

There are also some examples in the `notebooks` folder.


📄 License
==========

This project is licensed under the `LGPL v3.0 <https://www.gnu.org/licenses/lgpl-3.0.en.html>`_ license.


📙 Dataset
===========

We provide a dataset of voxel representations of protein-ligand complexes generated using DockTGrid.
The dataset is available for download at `Zenodo <https://zenodo.org/records/10202043>`_.
For more information, see the associated publication.


🖋️ Citing
=========

If you use DockTGrid in your research, please cite the following paper:

.. code-block:: bibtex

    @article{silva2023deep,
        title={Deep Learning-Ready Voxel Representation of Protein-Ligand Complexes from an Enhanced PBDbind v.2020 Dataset},
        author={da Silva, Matheus M. P. and Guedes, Isabella A. and Lima, Fabio C. and Dardenne, Laurent E.},
        journal={ChemRxiv},
        year={2023},
        publisher={Cambridge: Cambridge Open Engage}
    }


.. We have used DockTGrid in the following publications:

.. .. code-block:: bibtex

..     @article{,
..     title={},
..     author={},
..     journal={},
..     volume={},
..     number={},
..     pages={},
..     year={},
..     publisher={}
..     }
