September 28, 2018 Dataset Open Access

Stupp, Gregory S; Su, Andrew I

JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/6eda3742-fb23-405b-96ec-7254bb83bf51/faers_indications.csv"
      }, 
      "checksum": "md5:4c9d12fcbd78257622a8be91504cd741", 
      "bucket": "6eda3742-fb23-405b-96ec-7254bb83bf51", 
      "key": "faers_indications.csv", 
      "type": "csv", 
      "size": 242342
    }
  ], 
  "owners": [
    52981
  ], 
  "doi": "10.5281/zenodo.1436000", 
  "stats": {
    "version_unique_downloads": 462.0, 
    "unique_views": 2466.0, 
    "views": 2621.0, 
    "version_views": 2621.0, 
    "unique_downloads": 462.0, 
    "version_unique_views": 2466.0, 
    "volume": 118505238.0, 
    "version_downloads": 489.0, 
    "downloads": 489.0, 
    "version_volume": 118505238.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.1436000", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.1435999", 
    "bucket": "https://zenodo.org/api/files/6eda3742-fb23-405b-96ec-7254bb83bf51", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.1435999.svg", 
    "html": "https://zenodo.org/record/1436000", 
    "latest_html": "https://zenodo.org/record/1436000", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.1436000.svg", 
    "latest": "https://zenodo.org/api/records/1436000"
  }, 
  "conceptdoi": "10.5281/zenodo.1435999", 
  "created": "2018-09-28T23:21:17.039235+00:00", 
  "updated": "2020-01-24T19:25:08.122588+00:00", 
  "conceptrecid": "1435999", 
  "revision": 48, 
  "id": 1436000, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.1436000", 
    "version": "2018q2", 
    "language": "eng", 
    "title": "Drug Indications Extracted from FAERS", 
    "license": {
      "id": "CC0-1.0"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.1435999", 
        "relation": "isVersionOf"
      }
    ], 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "1435999"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "1436000"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "2R01GM089820-06", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/100000002::2R01GM089820-06"
        }, 
        "title": "Gene Wiki: expanding the ecosystem of community-intelligence resources", 
        "acronym": "", 
        "program": "NATIONAL_INSTITUTE_OF_GENERAL_MEDICAL_SCIENCES", 
        "funder": {
          "doi": "10.13039/100000002", 
          "acronyms": [], 
          "name": "National Institutes of Health", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/100000002"
          }
        }
      }
    ], 
    "keywords": [
      "faers, drug indications, fda, drugs"
    ], 
    "publication_date": "2018-09-28", 
    "creators": [
      {
        "orcid": "0000-0002-0644-7212", 
        "affiliation": "The Scripps Research Institute", 
        "name": "Stupp, Gregory S"
      }, 
      {
        "orcid": "0000-0002-9859-4104", 
        "affiliation": "The Scripps Research Institute", 
        "name": "Su, Andrew I"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "description": "<p>This dataset contains drug indications extracted from the&nbsp;FDA Adverse Event Reporting System (<a href=\"https://www.fda.gov/drugs/guidancecomplianceregulatoryinformation/surveillance/adversedrugeffects/\">FAERS</a>).</p>\n\n<p>Source code here:&nbsp;<a href=\"https://github.com/stuppie/faers\">https://github.com/stuppie/faers</a></p>\n\n<p><strong>Method Outline</strong></p>\n\n<ul>\n\t<li>Data files are extracted from zip files, parsed from csvs, and imported into a MySQL database (see&nbsp;parser.py).</li>\n\t<li>Duplicate records are then de-duplicated by taking only the most recent version for each case ID (see&nbsp;dedupe.py).</li>\n\t<li>Indications are normalized by matching to UMLS terms by string matching. Cross-references to Human Phenotype Ontology are pulled from UMLS and xrefs to Monarch Disease Ontology (MONDO) are pulled from MONDO using the UMLS xrefs. (See&nbsp;normalize_indications.py)</li>\n\t<li>Drugs names are normalized first by applying a few simple string cleaning operations (strip, fix slashes and periods). Then they are attempted to be matched to rxnorm by exact string matching. Those that don&#39;t match are run against rxnorm&#39;s <a href=\"https://rxnav.nlm.nih.gov/RxNormAPIs.html#uLink=RxNorm_REST_getApproximateMatch\">approximate matching service</a>, and are accepted if the score is higher than&nbsp;67/100. The matched rxnorm CUIs are then mapped to the their Ingredient level rxnorm ID. (See&nbsp;normalize_drugs.py)</li>\n\t<li>Indications are then retrieved for each drug ingredient and filtered to require a minimum of 20 individual occurances. (See&nbsp;get_indications.py)</li>\n</ul>"
  }
}