Auto3D is a Python package for generating low-energy conformers from SMILES/SDF. Over the development process, we also added the APIs for computing single point energies, optimizing geometries, find stable tautomers. Auto3D can be imported as a Python library, or be excuted from the terminal.

Please check out the information at documentation, including installation, usage, API and citation.

• Jupyter notebook examples can be found here
• To-do list for improvement and new features can be found here. You are welcomed to share your thoughts.
• Bugs go to the issues
• AIMNet2: The default model in Auto3D is AIMNet2 since 2.2.1. If you specify optimizing_engine="AIMNET", it actually uses AIMNet2. The old AIMNet model has been deprecated since Auto3D 2.2.1, and every call to “AIMNET” refers to the AIMNet2 model.

Auto3D is published on JCIM. For citation, please use:

@article{
    liu2022auto3d,
    title={Auto3d: Automatic generation of the low-energy 3d structures with ANI neural network potentials},
    author={Liu, Zhen and Zubatiuk, Tetiana and Roitberg, Adrian and Isayev, Olexandr},
    journal={Journal of Chemical Information and Modeling},
    volume={62},
    number={22},
    pages={5373--5382},
    year={2022},
    publisher={ACS Publications}
}