{
  "_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/mds2-3787"
    }
  ],
  "@type": [
    "nrdp:DataPublication",
    "nrdp:PublicDataResource",
    "dcat:Dataset"
  ],
  "_extensionSchemas": [
    "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/PublicDataResource"
  ],
  "@id": "ark:/88434/mds2-3787",
  "ediid": "ark:/88434/mds2-3787",
  "version": "1.0.0",
  "doi": "doi:10.18434/mds2-3787",
  "title": "NIST test dataset for assessing baseline nucleic acid sequence screening",
  "contactPoint": {
    "fn": "Tyler Laird",
    "hasEmail": "mailto:tyler.laird@nist.gov"
  },
  "modified": "2024-08-09",
  "status": "available",
  "landingPage": "https://data.nist.gov/od/id/mds2-3787",
  "description": [
    "This repository contains the dataset used in the manuscript \"Inter-tool analysis of a NIST dataset for assessing baseline nucleic acid sequence screening\". NIST constructed the test dataset based on the current screening recommendations from HHS. The dataset is a FASTA formatted file with blinded numerical sequence headers. The dataset was sent to sequence screening tool developers for initial testing and to obtain feedback about its utility for assessing baseline sequence screening. An additional metadata file provides the NIST-assigned label for each sequence, along with a more detailed description derived from the source database."
  ],
  "keyword": [
    "Nucleic Acid Synthesis",
    "Sequence Screening",
    "DNA",
    "Biosecurity"
  ],
  "theme": [
    "Bioscience: Engineering/synthetic biology",
    "Public Safety: Chemical/Biological/Radiological/Nuclear/Explosives (CBRNE)",
    "Bioscience: Biomaterials"
  ],
  "topic": [
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Bioscience: Engineering/synthetic biology"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Public Safety: Chemical/Biological/Radiological/Nuclear/Explosives (CBRNE)"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Bioscience: Biomaterials"
    }
  ],
  "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"
  ],
  "_editStatus": "done",
  "components": [
    {
      "@id": "cmps/NIST_nucleic_acid_syntheisis_screening_test_dataset_metadata.tsv",
      "@type": [
        "nrdp:DataFile",
        "nrdp:DownloadableFile",
        "dcat:Distribution"
      ],
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/DataFile"
      ],
      "filepath": "NIST_nucleic_acid_syntheisis_screening_test_dataset_metadata.tsv",
      "downloadURL": "https://data.nist.gov/od/ds/mds2-3787/NIST_nucleic_acid_syntheisis_screening_test_dataset_metadata.tsv",
      "mediaType": "text/tab-separated-values",
      "title": "NIST_nucleic_acid_syntheisis_screening_test_dataset_metadata",
      "size": 133986,
      "checksum": {
        "hash": "0f7d96fbdc2324ecc0c4f0885c3bd21196e41afdb9d6d38fc25e827d90b23ee3",
        "algorithm": {
          "tag": "sha256",
          "@type": "Thing"
        }
      },
      "description": "A file with additional information for each sequence in the associated FASTA file"
    },
    {
      "@id": "cmps/NIST_nucleic_acid_synthesis_screening_test_dataset.fasta",
      "@type": [
        "nrdp:DataFile",
        "nrdp:DownloadableFile",
        "dcat:Distribution"
      ],
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/DataFile"
      ],
      "filepath": "NIST_nucleic_acid_synthesis_screening_test_dataset.fasta",
      "downloadURL": "https://data.nist.gov/od/ds/mds2-3787/NIST_nucleic_acid_synthesis_screening_test_dataset.fasta",
      "mediaType": "text/plain",
      "title": "NIST_nucleic_acid_synthesis_screening_test_dataset",
      "size": 209712,
      "checksum": {
        "hash": "ae5167e9e84f2bb42fc96a272a641f323dd0a94ed515a28b2af78664ce984881",
        "algorithm": {
          "tag": "sha256",
          "@type": "Thing"
        }
      },
      "description": "A FASTA file of blinded sequences used as a test for assessing baseline sequence screening capabilities of several nucleic acid synthesis screening tools.",
      "format": {
        "description": "FASTA"
      }
    },
    {
      "@id": "cmps/README.md",
      "@type": [
        "nrdp:DataFile",
        "nrdp:DownloadableFile",
        "dcat:Distribution"
      ],
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/DataFile"
      ],
      "filepath": "README.md",
      "downloadURL": "https://data.nist.gov/od/ds/mds2-3787/README.md",
      "mediaType": "text/markdown",
      "description": "A README file pertaining to the NIST test dataset for assessing baseline nucleic acid sequence screening.",
      "title": "README",
      "size": 4672,
      "checksum": {
        "hash": "b0db0a9d91541ee6cbf78999bce0c7b45f5c42db73ee16a1fb8ae888f00a3012",
        "algorithm": {
          "tag": "sha256",
          "@type": "Thing"
        }
      }
    }
  ],
  "authors": [
    {
      "familyName": "Laird",
      "fn": "Tyler S Laird",
      "givenName": "Tyler",
      "middleName": "S",
      "affiliation": [
        {
          "title": "NIST",
          "subunits": [
            "Biosystems and Biomaterials Division"
          ],
          "@type": "org:Organization",
          "@id": "ror:05xpvk416"
        }
      ],
      "orcid": "0000-0003-2317-2895",
      "@type": "foaf:Person"
    },
    {
      "familyName": "Forry",
      "fn": "Samuel P. Forry",
      "givenName": "Samuel",
      "middleName": "P.",
      "affiliation": [
        {
          "title": "National Institute of Standards and Technology",
          "subunits": [
            "Biosystems and Biomaterials Division"
          ],
          "@type": "org:Organization",
          "@id": "ror:05xpvk416"
        }
      ],
      "orcid": "0009-0000-8200-0327",
      "@type": "foaf:Person"
    }
  ],
  "annotated": "2025-05-21T18:00:21.097308",
  "revised": "2025-05-21T18:00:21.097308",
  "issued": null,
  "firstIssued": "2025-05-21T18:00:21.097308"
}