P-GAP-20

The complete Phosphorus dataset used to train the P-GAP-20 model from A General-Purpose Machine-Learning Force Field for Bulk and Nanostructured Phosphorus. This dataset contains structures generated by GAP-RSS, together with liquids, crystals and isolated fragments. For more information about the dataset’s construction, see the paper’s Supplementary Information.

>>> from load_atoms import load_dataset
>>> load_dataset("P-GAP-20")
P-GAP-20:
    structures: 4,798
    atoms: 140,910
    species:
        P: 100.00%
    properties:
        per atom: (forces)
        per structure: (energy)

License

This dataset is licensed under the CC BY 4.0 license.

Citation

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

@article{Deringer-20-10,
  title = {
    A General-Purpose Machine-Learning Force Field
    for Bulk and Nanostructured Phosphorus
  },
  author = {
    Deringer, Volker L. and Caro, Miguel A.
    and Cs{\'a}nyi, G{\'a}bor
  },
  year = {2020},
  journal = {Nature Communications},
  volume = {11},
  number = {1},
  pages = {5461},
  doi = {10.1038/s41467-020-19168-z},
}

Properties

Per-atom:

Property	Units	Type	Description
forces	eV/Å	ndarray(N, 3)	force vectors (DFT + MBD)

Per-structure:

Property	Units	Type	Description
energy	eV	float64	total structure energy (DFT + MBD)

Miscellaneous information

P-GAP-20 is imported as an InMemoryAtomsDataset:

Importer script for P-GAP-20

from load_atoms.database.backend import SingleFileImporter
from load_atoms.database.internet import FileDownload


class Importer(SingleFileImporter):
    @classmethod
    def file_to_download(cls) -> FileDownload:
        return FileDownload(
            url="https://zenodo.org/record/4003703/files/P_GAP_20_fitting_data.xyz",
            expected_hash="ab3059018068",
        )

DatabaseEntry for P-GAP-20

name: P-GAP-20
year: 2020
description: |
    The complete Phosphorus dataset used to train the `P-GAP-20 <https://zenodo.org/records/4003703>`_ model from
    `A General-Purpose Machine-Learning Force Field for Bulk and Nanostructured Phosphorus <https://doi.org/10.1038/s41467-020-19168-z>`_.
    This dataset contains structures generated by GAP-RSS, together with liquids, crystals and isolated fragments.
    For more information about the dataset's construction, see the paper's `Supplementary Information <https://static-content.springer.com/esm/art%3A10.1038%2Fs41467-020-19168-z/MediaObjects/41467_2020_19168_MOESM1_ESM.pdf>`__.
category: Potential Fitting
minimum_load_atoms_version: 0.2
citation: |
    @article{Deringer-20-10,
      title = {
        A General-Purpose Machine-Learning Force Field
        for Bulk and Nanostructured Phosphorus
      },
      author = {
        Deringer, Volker L. and Caro, Miguel A.
        and Cs{\'a}nyi, G{\'a}bor
      },
      year = {2020},
      journal = {Nature Communications},
      volume = {11},
      number = {1},
      pages = {5461},
      doi = {10.1038/s41467-020-19168-z},
    }
license: CC BY 4.0
representative_structure: 280
per_atom_properties:
    forces:
        desc: force vectors (DFT + MBD)
        units: eV/Å
per_structure_properties:
    energy:
        desc: total structure energy (DFT + MBD)
        units: eV


# TODO: remove after Dec 2024
# backwards compatability: unused as of 0.3.0
files:
     - url: https://zenodo.org/record/4003703/files/P_GAP_20_fitting_data.xyz
       hash: ab3059018068