.. This file is autogenerated by dev/scripts/generate_page.py

ANI-1x
======

.. grid:: 1 1 2 2
    
    .. grid-item::

        .. raw:: html
            :file: ../_static/visualisations/ANI-1x.html

    .. grid-item::
        :class: info-card

        The ANI-1x dataset is a comprehensive collection of labelled molecular structures designed for training machine learned potentials. 
        ANI-1x was generated using an active learning approach to produce a diverse and useful dataset
        covering the chemical space of organic molecules composed of C, H, N, and O atoms, 
        Accurate energy and force labels are provided for each structure using the :math:`\omega`\ B97x/6-31G(d) level of theory.
        Internall, files are downloaded from
        `FigShare <https://springernature.figshare.com/collections/The_ANI-1ccx_and_ANI-1x_data_sets_coupled-cluster_and_density_functional_theory_properties_for_molecules/4712477>`__.
        


.. code-block:: pycon

    >>> from load_atoms import load_dataset
    >>> load_dataset("ANI-1x")
    ANI-1x:
        structures: 4,956,005
        atoms: 75,700,481
        species:
            H: 47.63%
            C: 30.30%
            N: 13.32%
            O: 8.75%
        properties:
            per atom: (forces)
            per structure: (dipole, energy, is_in_ccx)
    


License
-------

This dataset is licensed under the `CC0 <https://creativecommons.org/publicdomain/zero/1.0/>`_ license.


Citation
--------

If you use this dataset in your work, please cite the following:

.. code-block:: latex
    
    @article{Smith-18-05,
        title = {
            Less Is More: Sampling Chemical Space with Active Learning
        },
        author = {
            Smith, Justin S. and Nebgen, Ben and Lubbers, Nicholas and 
            Isayev, Olexandr and Roitberg, Adrian E.
        },
        year = {2018},
        journal = {The Journal of Chemical Physics},
        volume = {148},
        number = {24},
        doi = {10.1063/1.5023802},
    }


Properties
----------

**Per-atom**:

.. list-table::
    :header-rows: 1

    * - Property
      - Units
      - Type
      - Description
    * - :code:`forces`
      - eV/Å
      - :class:`ndarray(N, 3) <numpy.ndarray>`
      - force vectors (as labelled with :math:`\omega`\ B97x/6-31G(d))


**Per-structure**:
    
.. list-table::
    :header-rows: 1

    * - Property
      - Units
      - Type
      - Description
    * - :code:`energy`
      - eV
      - :class:`~float64`
      - energy of the structure (as labelled with :math:`\omega`\ B97x/6-31G(d))

    * - :code:`dipole`
      - e Å
      - :class:`ndarray(3,) <numpy.ndarray>`
      - dipole moment of the structure (as labelled with :math:`\omega`\ B97x/6-31G(d))

    * - :code:`is_in_ccx`
      - 
      - :class:`~bool`
      - whether the structure is in the :doc:`/datasets/ANI-1ccx` subset



Miscellaneous information
-------------------------

``ANI-1x`` is imported as an 
:class:`~load_atoms.atoms_dataset.LmdbAtomsDataset`:

.. dropdown:: Importer script for :code:`ANI-1x`

    .. literalinclude:: ../../../src/load_atoms/database/importers/ani_1x.py
       :language: python



.. dropdown:: :class:`~load_atoms.database.DatabaseEntry` for :code:`ANI-1x`

    .. code-block:: yaml

        name: ANI-1x
        year: 2018
        category: Benchmarks
        license: CC0
        minimum_load_atoms_version: 0.3
        format: lmdb
        description: |
            The ANI-1x dataset is a comprehensive collection of labelled molecular structures designed for training machine learned potentials. 
            ANI-1x was generated using an active learning approach to produce a diverse and useful dataset
            covering the chemical space of organic molecules composed of C, H, N, and O atoms, 
            Accurate energy and force labels are provided for each structure using the :math:`\omega`\ B97x/6-31G(d) level of theory.
            Internall, files are downloaded from
            `FigShare <https://springernature.figshare.com/collections/The_ANI-1ccx_and_ANI-1x_data_sets_coupled-cluster_and_density_functional_theory_properties_for_molecules/4712477>`__.
        citation: |
            @article{Smith-18-05,
                title = {
                    Less Is More: Sampling Chemical Space with Active Learning
                },
                author = {
                    Smith, Justin S. and Nebgen, Ben and Lubbers, Nicholas and 
                    Isayev, Olexandr and Roitberg, Adrian E.
                },
                year = {2018},
                journal = {The Journal of Chemical Physics},
                volume = {148},
                number = {24},
                doi = {10.1063/1.5023802},
            }
        
        per_atom_properties:
            forces:
                desc: force vectors (as labelled with :math:`\omega`\ B97x/6-31G(d))
                units: eV/Å
        per_structure_properties:
            energy:
                desc: energy of the structure (as labelled with :math:`\omega`\ B97x/6-31G(d))
                units: eV
            dipole:
                desc: dipole moment of the structure (as labelled with :math:`\omega`\ B97x/6-31G(d))
                units: e Å
            is_in_ccx:
                desc: whether the structure is in the :doc:`/datasets/ANI-1ccx` subset
        representative_structure: 205_000