{
  "_schema": "https://data.nist.gov/od/dm/nerdm-schema/v0.7#",
  "@context": [
    "https://data.nist.gov/od/dm/nerdm-pub-context.jsonld",
    {
      "@base": "ark:/88434/mds2-3463"
    }
  ],
  "@type": [
    "nrdp:DataPublication",
    "nrdp:PublicDataResource",
    "dcat:Dataset"
  ],
  "_extensionSchemas": [
    "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/PublicDataResource"
  ],
  "@id": "ark:/88434/mds2-3463",
  "ediid": "ark:/88434/mds2-3463",
  "version": "1.0.2",
  "doi": "doi:10.18434/mds2-3463",
  "title": "AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design ",
  "contactPoint": {
    "fn": "Daniel Wines",
    "hasEmail": "mailto:daniel.wines@nist.gov"
  },
  "modified": "2024-06-01 00:00:00",
  "status": "available",
  "landingPage": "https://data.nist.gov/od/id/mds2-3463",
  "description": [
    "AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design"
  ],
  "keyword": [
    "Large language models",
    "Materials design",
    "JARVIS"
  ],
  "topic": [
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Materials: Modeling and computational material science"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Information Technology: Data and informatics"
    },
    {
      "scheme": "https://data.nist.gov/od/dm/nist-themes-chipsmetrology/v2.0",
      "tag": "Metrology: Computational Technique: Simulation",
      "@type": "Concept"
    },
    {
      "scheme": "https://data.nist.gov/od/dm/nist-themes-chipsmetrology/v2.0",
      "tag": "Metrology: Computational Technique: AI/ML",
      "@type": "Concept"
    },
    {
      "scheme": "https://data.nist.gov/od/dm/nist-themes-chipsmetrology/v2.0",
      "tag": "Materials Research: Semiconductor",
      "@type": "Concept"
    },
    {
      "scheme": "https://data.nist.gov/od/dm/nist-themes-chipsmetrology/v2.0",
      "tag": "Materials Research: Dielectric and Insulator",
      "@type": "Concept"
    },
    {
      "scheme": "https://data.nist.gov/od/dm/nist-themes-chipsmetrology/v2.0",
      "tag": "Materials Research: Metal",
      "@type": "Concept"
    },
    {
      "scheme": "https://data.nist.gov/od/dm/nist-themes-chipsmetrology/v2.0",
      "tag": "Metrology: Grand Challenge: 4-Modeling and Simulating Semiconductor Materials, Designs, and Components",
      "@type": "Concept"
    }
  ],
  "accessLevel": "public",
  "license": "https://www.nist.gov/open/license",
  "publisher": {
    "name": "National Institute of Standards and Technology",
    "@type": "org:Organization"
  },
  "language": [
    "en"
  ],
  "bureauCode": [
    "006:55"
  ],
  "programCode": [
    "006:052"
  ],
  "theme": [
    "Materials: Modeling and computational material science",
    "Information Technology: Data and informatics"
  ],
  "references": [
    {
      "@type": [
        "npg:Document"
      ],
      "@id": "#ref:10.1021/acs.jpclett.4c01126",
      "refType": "IsSupplementTo",
      "location": "https://doi.org/10.1021/acs.jpclett.4c01126",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/bib/v0.7#/definitions/DCiteReference"
      ],
      "title": "AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design",
      "issued": "2024-06-27",
      "citation": "Choudhary, K. (2024). AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design. The Journal of Physical Chemistry Letters, 15(27), 6909\u00e2\u0080\u00936917. https://doi.org/10.1021/acs.jpclett.4c01126\n"
    }
  ],
  "components": [
    {
      "accessURL": "https://github.com/usnistgov/atomgpt",
      "description": "Large language models (LLMs) such as generative pretrained transformers (GPTs) have shown potential for various commercial applications, but their applicability for materials design remains underexplored. In this Letter, AtomGPT is introduced as a model specifically developed for materials design based on transformer architectures, demonstrating capabilities for both atomistic property prediction and structure generation. This study shows that a combination of chemical and structural text descriptions can efficiently predict material properties with accuracy comparable to graph neural network models, including formation energies, electronic bandgaps from two different methods, and superconducting transition temperatures. Furthermore, AtomGPT can generate atomic structures for tasks such as designing new superconductors, with the predictions validated through density functional theory calculations. This work paves the way for leveraging LLMs in forward and inverse materials design, offering an efficient approach to the discovery and optimization of materials.",
      "title": "AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#usnistgov/atomgpt",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    }
  ],
  "_editStatus": "done",
  "authors": [
    {
      "familyName": "Choudhary",
      "fn": "Kamal  Choudhary",
      "givenName": "Kamal",
      "middleName": "",
      "affiliation": [
        {
          "title": "National Institute of Standards and Technology",
          "subunits": [
            "MSED"
          ],
          "@type": "org:Organization",
          "@id": "ror:05xpvk416"
        }
      ],
      "orcid": "0000-0001-9737-8074",
      "@type": "foaf:Person"
    }
  ],
  "annotated": "2025-11-25T14:30:28.868878",
  "revised": "2024-11-22T12:22:36.441066",
  "issued": null,
  "firstIssued": "2024-11-22T12:22:36.441066",
  "releaseHistory": {
    "@id": "ark:/88434/mds2-3463/pdr:v",
    "@type": [
      "nrdr:ReleaseHistory"
    ],
    "hasRelease": [
      {
        "version": "1.0.0",
        "issued": "2024-11-22",
        "@id": "ark:/88434/mds2-3463/pdr:v/1.0.0",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-3463/pdr:v/1.0.0",
        "description": "initial release"
      },
      {
        "version": "1.0.1",
        "issued": "2025-11-04",
        "@id": "ark:/88434/mds2-3463/pdr:v/1.0.1",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-3463/pdr:v/1.0.1",
        "description": "added to CHIPS Metrology collection"
      },
      {
        "version": "1.0.2",
        "issued": "2024-06-01 00:00:00",
        "@id": "ark:/88434/mds2-3463/pdr:v/1.0.2",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-3463/pdr:v/1.0.2",
        "description": "metadata update"
      }
    ]
  },
  "isPartOf": [
    {
      "@type": [
        "nrda:ScienceTheme",
        "nrdp:PublicDataResource"
      ],
      "@id": "ark:/88434/pdr0-0002",
      "title": "CHIPS Metrology Data"
    }
  ]
}