Getting Started

gninatorch is a PyTorch implementation of GNINA scoring function, a CNN-based scoring function for molecular docking.

Note

gninatorch depends on libmolgrid, and therefore it is only available on Linux and requires a NVIDIA GPU.

Help

If you find an issue with gninatorch, please open a GitHub issue. If you have a question about gninatorch, please use GitHub Discussions.

Clone the repository from GitHub:

git clone https://github.com/RMeli/gnina-torch.git
cd gnina-torch

Create a conda or mamba environment with all the dependencies:

conda env create -f devtools/conda-envs/gninatorch.yaml
conda activate gninatorch

Install gninatorch from source:

python -m pip install .

python -m pip install gninatorch

Warning

Packages on PyPI are still WIP and should be considered experimental.

Run tests with pytest and report code coverage:

pytest --cov=gninatorch

.. bibliography::
   :cited: