September 28, 2018 Dataset Open Access

Stupp, Gregory S; Su, Andrew I

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.1436000</identifier>
  <creators>
    <creator>
      <creatorName>Stupp, Gregory S</creatorName>
      <givenName>Gregory S</givenName>
      <familyName>Stupp</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-0644-7212</nameIdentifier>
      <affiliation>The Scripps Research Institute</affiliation>
    </creator>
    <creator>
      <creatorName>Su, Andrew I</creatorName>
      <givenName>Andrew I</givenName>
      <familyName>Su</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-9859-4104</nameIdentifier>
      <affiliation>The Scripps Research Institute</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Drug Indications Extracted from FAERS</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <subjects>
    <subject>faers, drug indications, fda, drugs</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2018-09-28</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/1436000</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1435999</relatedIdentifier>
  </relatedIdentifiers>
  <version>2018q2</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/publicdomain/zero/1.0/legalcode">Creative Commons Zero v1.0 Universal</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This dataset contains drug indications extracted from the&amp;nbsp;FDA Adverse Event Reporting System (&lt;a href="https://www.fda.gov/drugs/guidancecomplianceregulatoryinformation/surveillance/adversedrugeffects/"&gt;FAERS&lt;/a&gt;).&lt;/p&gt;

&lt;p&gt;Source code here:&amp;nbsp;&lt;a href="https://github.com/stuppie/faers"&gt;https://github.com/stuppie/faers&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Method Outline&lt;/strong&gt;&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;Data files are extracted from zip files, parsed from csvs, and imported into a MySQL database (see&amp;nbsp;parser.py).&lt;/li&gt;
	&lt;li&gt;Duplicate records are then de-duplicated by taking only the most recent version for each case ID (see&amp;nbsp;dedupe.py).&lt;/li&gt;
	&lt;li&gt;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&amp;nbsp;normalize_indications.py)&lt;/li&gt;
	&lt;li&gt;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&amp;#39;t match are run against rxnorm&amp;#39;s &lt;a href="https://rxnav.nlm.nih.gov/RxNormAPIs.html#uLink=RxNorm_REST_getApproximateMatch"&gt;approximate matching service&lt;/a&gt;, and are accepted if the score is higher than&amp;nbsp;67/100. The matched rxnorm CUIs are then mapped to the their Ingredient level rxnorm ID. (See&amp;nbsp;normalize_drugs.py)&lt;/li&gt;
	&lt;li&gt;Indications are then retrieved for each drug ingredient and filtered to require a minimum of 20 individual occurances. (See&amp;nbsp;get_indications.py)&lt;/li&gt;
&lt;/ul&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>National Institutes of Health</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100000002</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/NIH/NATIONAL_INSTITUTE_OF_GENERAL_MEDICAL_SCIENCES/2R01GM089820-06/">2R01GM089820-06</awardNumber>
      <awardTitle>Gene Wiki: expanding the ecosystem of community-intelligence resources</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>