Drug Indications Extracted from FAERS

<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> <p>Source code here:&nbsp;<a href="https://github.com/stuppie/faers">https://github.com/stuppie/faers</a></p> <p><strong>Method Outline</strong></p> <ul> <li>Data files are extracted from zip files, parsed from csvs, and imported into a MySQL database (see&nbsp;parser.py).</li> <li>Duplicate records are then de-duplicated by taking only the most recent version for each case ID (see&nbsp;dedupe.py).</li> <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> <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> <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> </ul>