drugbank-database-access

DrugBank Database — Local XML Access

Overview

Query the DrugBank comprehensive drug database (14,000+ drug entries, 5,000+ protein targets, 17,000+ drug interactions) by parsing the locally downloaded XML file with Python's ElementTree. Covers drug lookups, interaction checking, target/pathway extraction, chemical property analysis, and cross-database identifier mapping.

When to Use

• Looking up drug information (description, indication, mechanism, pharmacology) by DrugBank ID, name, or CAS number
• Checking drug-drug interactions and severity classifications for polypharmacy safety
• Extracting drug targets, enzymes, transporters, and carriers with UniProt accessions
• Retrieving chemical properties (SMILES, InChI, molecular weight) for cheminformatics analysis
• Mapping DrugBank entries to external databases (PubChem, ChEMBL, UniProt, KEGG)
• Building drug similarity matrices from molecular fingerprints
• For live bioactivity data (IC50, Ki, EC50) use chembl-database-bioactivity instead
• For compound property lookups without downloading a database use pubchem-compound-search instead

Prerequisites

• DrugBank account: Register at https://go.drugbank.com/ (free academic license)
• XML download: Download drugbank_all_full_database.xml.zip after registration (~1.5 GB uncompressed)
• Python packages: lxml, rdkit (similarity), pandas (tabular analysis)
• REST API (optional): 3,000 req/month dev tier; use local XML for batch work

pip install lxml pandas
pip install rdkit-pypi          # chemical similarity
pip install drugbank-downloader  # programmatic XML download

Quick Start

import xml.etree.ElementTree as ET

NS = {'db': 'http://www.drugbank.ca'}  # Required for ALL XPath queries

tree = ET.parse('drugbank_all_full_database.xml')  # 30-60s for full XML
root = tree.getroot()

# Build lookup index (DrugBank ID + lowercase name → element)
drug_index = {}
for drug in root.findall('db:drug', NS):
    db_id = drug.find('db:drugbank-id[@primary="true"]', NS)
    name = drug.find('db:name', NS)
    if db_id is not None and name is not None:
        drug_index[db_id.text] = drug
        drug_index[name.text.lower()] = drug

def find_drug(query):
    """Find drug by DrugBank ID, name (case-insensitive), or CAS number."""
    result = drug_index.get(query) or drug_index.get(query.lower())
    if result is not None:
        return result
    for drug in root.findall('db:drug', NS):  # CAS fallback
        cas = drug.find('db:cas-number', NS)
        if cas is not None and cas.text == query:
            return drug
    return None

drug = find_drug('DB00945')  # Aspirin
name = drug.find('db:name', NS).text
print(f"{name}: {drug.find('db:description', NS).text[:100]}...")

Core API

1. Data Access and Setup

import xml.etree.ElementTree as ET

NS = {'db': 'http://www.drugbank.ca'}
tree = ET.parse('drugbank_all_full_database.xml')
root = tree.getroot()
print(f"Total drug entries: {len(root.findall('db:drug', NS))}")

For memory-constrained environments, use iterparse:

drug_names = {}
for event, elem in ET.iterparse('drugbank_all_full_database.xml', events=('end',)):
    if elem.tag == '{http://www.drugbank.ca}drug':
        db_id = elem.find('{http://www.drugbank.ca}drugbank-id[@primary="true"]')
        name = elem.find('{http://www.drugbank.ca}name')
        if db_id is not None and name is not None:
            drug_names[db_id.text] = name.text
        elem.clear()  # Free memory
print(f"Parsed {len(drug_names)} drugs via iterparse")

2. Drug Information Queries

def get_drug_info(drug_element):
    """Extract comprehensive drug information."""
    def txt(path):
        el = drug_element.find(path, NS)
        return el.text if el is not None and el.text else None

    return {
        'drugbank_id': txt('db:drugbank-id[@primary="true"]'),
        'name': txt('db:name'),
        'type': drug_element.get('type'),
        'description': txt('db:description'),
        'indication': txt('db:indication'),
        'mechanism_of_action': txt('db:mechanism-of-action'),
        'cas_number': txt('db:cas-number'),
        'groups': [g.text for g in drug_element.findall('db:groups/db:group', NS)],
    }

info = get_drug_info(find_drug('Metformin'))
print(f"{info['name']} ({info['type']}): Groups={info['groups']}")

# Search by name pattern (partial match)
def search_by_name(pattern):
    pattern_lower = pattern.lower()
    return [d for d in root.findall('db:drug', NS)
            if d.find('db:name', NS) is not None
            and pattern_lower in d.find('db:name', NS).text.lower()]

statins = search_by_name('statin')
print(f"Found {len(statins)} drugs matching 'statin'")

3. Drug-Drug Interactions

def get_interactions(drug_element):
    """Extract all drug-drug interactions."""
    return [{
        'drugbank_id': i.find('db:drugbank-id', NS).text,
        'name': i.find('db:name', NS).text,
        'description': i.find('db:description', NS).text,
    } for i in drug_element.findall('db:drug-interactions/db:drug-interaction', NS)]

def classify_severity(description):
    """Classify severity from interaction description text."""
    if not description:
        return 'unknown'
    dl = description.lower()
    if any(w in dl for w in ['contraindicated', 'avoid', 'fatal', 'life-threatening']):
        return 'major'
    if any(w in dl for w in ['increase', 'decrease', 'enhance', 'reduce', 'alter']):
        return 'moderate'
    return 'minor'

interactions = get_interactions(find_drug('Aspirin'))
print(f"Aspirin has {len(interactions)} interactions")
for i in interactions[:3]:
    print(f"  [{classify_severity(i['description'])}] {i['name']}")

# Check pairwise interaction between two drugs
def check_interaction(drug1_elem, drug2_elem):
    id2 = drug2_elem.find('db:drugbank-id[@primary="true"]', NS).text
    for inter in get_interactions(drug1_elem):
        if inter['drugbank_id'] == id2:
            inter['severity'] = classify_severity(inter['description'])
            return inter
    return None

result = check_interaction(find_drug('Warfarin'), find_drug('Aspirin'))
if result:
    print(f"[{result['severity']}] {result['description'][:150]}")

4. Drug Targets and Pathways

def get_targets(drug_element, target_type='targets'):
    """Extract targets/enzymes/transporters/carriers.
    target_type: 'targets', 'enzymes', 'transporters', or 'carriers'
    """
    results = []
    for target in drug_element.findall(f'db:{target_type}/db:{target_type[:-1]}', NS):
        t = {
            'name': (target.find('db:name', NS).text
                     if target.find('db:name', NS) is not None else None),
            'actions': [a.text for a in target.findall('db:actions/db:action', NS) if a.text],
        }
        poly = target.find('db:polypeptide', NS)
        if poly is not None:
            t['uniprot_id'] = poly.get('id')
            gene = poly.find('db:gene-name', NS)
            t['gene_name'] = gene.text if gene is not None else None
        results.append(t)
    return results

drug = find_drug('Imatinib')
targets = get_targets(drug, 'targets')
enzymes = get_targets(drug, 'enzymes')
print(f"Imatinib — Targets: {len(targets)}, Enzymes: {len(enzymes)}")
for t in targets[:3]:
    print(f"  {t['name']} (UniProt: {t.get('uniprot_id', 'N/A')}) — {t['actions']}")

def get_pathways(drug_element):
    """Extract SMPDB pathway associations."""
    pathways = []
    for pw in drug_element.findall('db:pathways/db:pathway', NS):
        name = pw.find('db:name', NS)
        smpdb = pw.find('db:smpdb-id', NS)
        pathways.append({
            'smpdb_id': smpdb.text if smpdb is not None else None,
            'name': name.text if name is not None else None,
        })
    return pathways

for pw in get_pathways(find_drug('Metformin')):
    print(f"  {pw['smpdb_id']}: