fda-database

openFDA Drug and Adverse Event Database

Overview

openFDA provides public access to FDA regulatory data through a simple REST API. Key datasets include the FDA Adverse Event Reporting System (FAERS) with 20M+ adverse event reports, drug product labeling (NDC, SPL), drug approvals (Drugs@FDA), medical device reports, and recall enforcement actions. The API supports full-text search and structured queries using Elasticsearch-style syntax.

When to Use

• Retrieving adverse event reports for a drug to assess safety signals and side effect profiles
• Querying FAERS for disproportionality analysis (comparing drug vs. drug adverse event profiles)
• Looking up official drug labeling (indications, contraindications, warnings, dosing) by drug name or NDC
• Searching for drug recalls and enforcement actions by drug name or company
• Identifying all marketed products containing a given active ingredient
• Building pharmacovigilance pipelines that monitor drug safety signals from public regulatory data
• For clinical trial efficacy data use clinicaltrials-database-search; for drug structures/targets use drugbank-database-access

Prerequisites

• Python packages: requests, pandas
• Data requirements: drug names, active ingredients, MedDRA terms, NDC codes
• Environment: internet connection; no authentication required for basic use
• Rate limits: 1000 req/day without API key; 120,000 req/day with free API key from https://open.fda.gov/apis/authentication/

pip install requests pandas

Quick Start

import requests

BASE = "https://api.fda.gov/drug"
# Optional: add api_key parameter for higher rate limits

# Find adverse events for aspirin
r = requests.get(
    f"{BASE}/event.json",
    params={
        "search": 'patient.drug.medicinalproduct:"aspirin"',
        "count": "patient.reaction.reactionmeddrapt.exact",
        "limit": 10
    }
)
r.raise_for_status()
data = r.json()
print("Top adverse reactions for aspirin:")
for item in data["results"][:5]:
    print(f"  {item['term']:40s} count={item['count']}")

Core API

Query 1: Adverse Event Report Search (FAERS)

Search the FDA Adverse Event Reporting System for drug-event associations.

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def faers_search(drug_name, limit=100):
    """Search FAERS for adverse event reports mentioning a drug."""
    r = requests.get(f"{BASE}/event.json",
                     params={"search": f'patient.drug.medicinalproduct:"{drug_name}"',
                             "limit": limit})
    r.raise_for_status()
    return r.json()

data = faers_search("warfarin", limit=5)
total = data["meta"]["results"]["total"]
print(f"Total FAERS reports for warfarin: {total:,}")

# Show first report summary
report = data["results"][0]
print(f"\nReport {report['safetyreportid']}:")
print(f"  Date     : {report.get('receivedate', 'n/a')}")
print(f"  Serious  : {report.get('serious', 'n/a')}")
drugs = [d.get("medicinalproduct", "n/a") for d in report.get("patient", {}).get("drug", [])]
print(f"  Drugs    : {drugs[:5]}")
reactions = [r.get("reactionmeddrapt", "n/a") for r in report.get("patient", {}).get("reaction", [])]
print(f"  Reactions: {reactions[:5]}")

Query 2: Count Top Adverse Events for a Drug

Use the count parameter to aggregate adverse event terms.

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def top_adverse_events(drug_name, limit=20):
    """Get the most frequently reported adverse events for a drug."""
    r = requests.get(f"{BASE}/event.json",
                     params={
                         "search": f'patient.drug.medicinalproduct:"{drug_name}"',
                         "count": "patient.reaction.reactionmeddrapt.exact",
                         "limit": limit
                     })
    r.raise_for_status()
    results = r.json()["results"]
    return pd.DataFrame(results).rename(columns={"term": "reaction", "count": "reports"})

df_atorvastatin = top_adverse_events("atorvastatin", limit=15)
print("Top adverse events for atorvastatin:")
print(df_atorvastatin.head(10).to_string(index=False))
df_atorvastatin.to_csv("atorvastatin_adverse_events.csv", index=False)

# Compare two drugs: adverse event profile overlap
df_drug1 = top_adverse_events("simvastatin", limit=20)
df_drug2 = top_adverse_events("atorvastatin", limit=20)

common = set(df_drug1["reaction"]) & set(df_drug2["reaction"])
print(f"\nCommon adverse events (simvastatin ∩ atorvastatin): {len(common)}")
print("Shared reactions:", list(common)[:10])

Query 3: Drug Labeling Search

Retrieve official drug labels (indications, warnings, dosing, contraindications).

import requests

BASE = "https://api.fda.gov/drug"

def get_label(drug_name):
    """Retrieve FDA drug label by brand or generic name."""
    r = requests.get(f"{BASE}/label.json",
                     params={"search": f'openfda.brand_name:"{drug_name}"',
                             "limit": 1})
    if r.status_code == 404:
        r = requests.get(f"{BASE}/label.json",
                         params={"search": f'openfda.generic_name:"{drug_name}"',
                                 "limit": 1})
    r.raise_for_status()
    results = r.json()["results"]
    return results[0] if results else None

label = get_label("Lipitor")
if label:
    print(f"Brand name  : {label.get('openfda', {}).get('brand_name', ['n/a'])[0]}")
    print(f"Generic name: {label.get('openfda', {}).get('generic_name', ['n/a'])[0]}")
    print(f"Manufacturer: {label.get('openfda', {}).get('manufacturer_name', ['n/a'])[0]}")
    indications = label.get("indications_and_usage", ["n/a"])[0]
    print(f"\nIndications (first 300 chars):\n{indications[:300]}...")

Query 4: Drug Product Lookup by NDC

Retrieve marketed product information by National Drug Code.

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def ndc_search(ndc_or_name, limit=10):
    """Search NDC directory for drug product information."""
    # Search by product name or NDC
    r = requests.get(f"{BASE}/ndc.json",
                     params={"search": f'generic_name:"{ndc_or_name}"',
                             "limit": limit})
    r.raise_for_status()
    return r.json()

data = ndc_search("metformin", limit=10)
total = data["meta"]["results"]["total"]
print(f"Metformin products: {total}")

rows = []
for prod in data["results"]:
    rows.append({
        "product_ndc": prod.get("product_ndc"),
        "brand_name": prod.get("brand_name"),
        "generic_name": prod.get("generic_name"),
        "dosage_form": prod.get("dosage_form"),
        "route": ", ".join(prod.get("route", [])),
        "labeler": prod.get("labeler_name"),
    })
df = pd.DataFrame(rows)
print(df.to_string(index=False))

Query 5: Drug Recall Search

Search FDA enforcement actions and drug recalls by drug name or company.

import requests, pandas as pd

BASE = "https://api.fda.gov/drug"

def drug_recalls(drug_name, limit=20):
    """Find FDA drug recalls for a given drug name."""
    r = requests.get(f"{BASE}/enforcement.json",
                     params={
                         "search": f'product_description:"{drug_name}"',
                         "limit": limit
                     })
    if r.status_code == 404:
        return pd.DataFrame()
    r.raise_for_status()
    results = r.json()["results"]
    return pd.DataFrame([{
        "recalling_firm": rec.get("recalling_firm"),
        "product": rec.get("product_description", "")[:80],
        "reason": rec.get("reason_for_recall", "")[:100],
        "classification": rec.get("classification"),
        "recall_date": rec.get("recall_initiation_date"),
        "status": rec.get("status"),
    } for rec in results])

recalls = drug_recalls("metformin", limit=5)
print(f"Metformin recalls: {len(recalls)}")
if not recalls.empty:
    print(recalls[["recalling_firm", "classificati