Skip to main content

PyTorch implementation of ANI

Project description

Accurate Neural Network Potential on PyTorch


PyPI PyPI - Downloads


Actions Status Actions Status Actions Status Actions Status Actions Status Actions Status CodeFactor Total alerts


Actions Status Actions Status

TorchANI is a pytorch implementation of ANI. It is currently under alpha release, which means, the API is not stable yet. If you find a bug of TorchANI, or have some feature request, feel free to open an issue on GitHub, or send us a pull request.


TorchANI requires the latest preview version of PyTorch. You can install PyTorch by the following commands (assuming cuda10):

pip install numpy
pip install --pre torch torchvision -f

If you updated TorchANI, you may also need to update PyTorch:

pip install --upgrade --pre torch torchvision -f

After installing the correct PyTorch, you can install TorchANI by:

pip install torchani

See also PyTorch's official site for instructions of installing latest preview version of PyTorch.

Please install nightly PyTorch through pip install instead of conda install. If your PyTorch is installed through conda install, then pip would mistakenly recognize the package name as torch instead of torch-nightly, which would cause dependency issue when installing TorchANI.

To run the tests and examples, you must manually download a data package



The original ANI-1 paper is:

  • Smith JS, Isayev O, Roitberg AE. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chemical science. 2017;8(4):3192-203.

We are planning a seperate paper for TorchANI, it will be available when we are ready for beta release of TorchANI.

See also: isayev/ASE_ANI


To install TorchANI from GitHub:

git clone
cd torchani
pip install -e .

After TorchANI has been installed, you can build the documents by running sphinx-build docs build. But make sure you install dependencies:

pip install sphinx sphinx-gallery pillow matplotlib sphinx_rtd_theme

To manually run unit tests, do python nosetests

If you opened a pull request, you could see your generated documents at after you docs check succeed. Keep in mind that this repository is only for the purpose of convenience of development, and only keeps the latest push. The CI runing for other pull requests might overwrite this repository. You could rerun the docs check to overwrite this repo to your build.

Note to TorchANI developers

Never commit to the master branch directly. If you need to change something, create a new branch, submit a PR on GitHub.

You must pass all the tests on GitHub before your PR can be merged.

Code review is required before merging pull request.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for torchani, version 1.0.1
Filename, size File type Python version Upload date Hashes
Filename, size torchani-1.0.1.linux-x86_64.tar.gz (21.6 MB) File type Source Python version None Upload date Hashes View
Filename, size torchani-1.0.1-py3-none-any.whl (21.8 MB) File type Wheel Python version py3 Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page