Hmdb Database

pip install lxml pandas

import xml.etree.ElementTree as ET

NS = {'hmdb': 'http://www.hmdb.ca'}

tree = ET.parse('hmdb_metabolites.xml')  # 60-120s for full XML
root = tree.getroot()

# Build lookup index (HMDB ID + lowercase name -> element)
metabolite_index = {}
for met in root.findall('hmdb:metabolite', NS):
    accession = met.find('hmdb:accession', NS)
    name = met.find('hmdb:name', NS)
    if accession is not None and accession.text:
        metabolite_index[accession.text] = met
    if name is not None and name.text:
        metabolite_index[name.text.lower()] = met

def find_metabolite(query):
    """Find metabolite by HMDB ID or name (case-insensitive)."""
    return metabolite_index.get(query) or metabolite_index.get(query.lower())

met = find_metabolite('HMDB0000122')  # Glucose
name = met.find('hmdb:name', NS).text
formula = met.find('hmdb:chemical_formula', NS).text
print(f"{name}: {formula}")
# Glucose: C6H12O6

import xml.etree.ElementTree as ET

NS = {'hmdb': 'http://www.hmdb.ca'}
tree = ET.parse('hmdb_metabolites.xml')
root = tree.getroot()
print(f"Total metabolite entries: {len(root.findall('hmdb:metabolite', NS))}")
# Total metabolite entries: ~220000+

met_names = {}
for event, elem in ET.iterparse('hmdb_metabolites.xml', events=('end',)):
    if elem.tag == '{http://www.hmdb.ca}metabolite':
        acc = elem.find('{http://www.hmdb.ca}accession')
        name = elem.find('{http://www.hmdb.ca}name')
        if acc is not None and name is not None and acc.text and name.text:
            met_names[acc.text] = name.text
        elem.clear()
print(f"Parsed {len(met_names)} metabolites via iterparse")

def get_chemical_properties(met_element):
    """Extract chemical properties from a metabolite entry."""
    def txt(path):
        el = met_element.find(path, NS)
        return el.text if el is not None and el.text else None
    # Fields: accession, name, chemical_formula, average_molecular_weight,
    # monisotopic_molecular_weight, smiles, inchi, inchikey, state, iupac_name
    return {tag: txt(f'hmdb:{tag}') for tag in [
        'accession', 'name', 'chemical_formula', 'average_molecular_weight',
        'monisotopic_molecular_weight', 'smiles', 'inchi', 'inchikey', 'state']}

props = get_chemical_properties(find_metabolite('HMDB0000158'))  # L-Tyrosine
print(f"{props['name']}: MW={props['average_molecular_weight']}, SMILES={props['smiles']}")

# Extract taxonomy / chemical classification (ClassyFire ontology)
def get_classification(met_element):
    tax = met_element.find('hmdb:taxonomy', NS)
    if tax is None:
        return {}
    def txt(tag):
        el = tax.find(f'hmdb:{tag}', NS)
        return el.text if el is not None and el.text else None
    return {'kingdom': txt('kingdom'), 'super_class': txt('super_class'),
            'class': txt('class'), 'sub_class': txt('sub_class'),
            'direct_parent': txt('direct_parent')}

print(get_classification(find_metabolite('HMDB0000122')))
# {'kingdom': 'Organic compounds', 'super_class': 'Organooxygen compounds', ...}

def get_pathways(met_element):
    """Extract metabolic pathway associations."""
    pathways = []
    for pw in met_element.findall('hmdb:pathways/hmdb:pathway', NS):
        name = pw.find('hmdb:name', NS)
        smpdb_id = pw.find('hmdb:smpdb_id', NS)
        kegg_id = pw.find('hmdb:kegg_map_id', NS)
        pathways.append({
            'name': name.text if name is not None else None,
            'smpdb_id': smpdb_id.text if smpdb_id is not None else None,
            'kegg_map_id': kegg_id.text if kegg_id is not None else None,
        })
    return pathways

for pw in get_pathways(find_metabolite('HMDB0000122'))[:5]:
    print(f"  {pw['smpdb_id']}: {pw['name']}")

def get_biolocations(met_element):
    """Extract biofluid, tissue, and cellular locations."""
    bp = 'hmdb:biological_properties/hmdb:'
    def texts(path):
        return [el.text for el in met_element.findall(path, NS) if el.text]
    return {'biofluids': texts(f'{bp}biospecimen_locations/hmdb:biospecimen'),
            'tissues': texts(f'{bp}tissue_locations/hmdb:tissue'),
            'cellular': texts(f'{bp}cellular_locations/hmdb:cellular')}

locs = get_biolocations(find_metabolite('HMDB0000122'))
print(f"Glucose biofluids: {locs['biofluids']}")

def get_enzymes(met_element):
    """Extract associated enzymes/proteins with UniProt IDs."""
    return [{'name': (p.find('hmdb:name', NS).text
                      if p.find('hmdb:name', NS) is not None else None),
             'uniprot_id': (p.find('hmdb:uniprot_id', NS).text
                            if p.find('hmdb:uniprot_id', NS) is not None else None),
             'gene_name': (p.find('hmdb:gene_name', NS).text
                           if p.find('hmdb:gene_name', NS) is not None else None)}
            for p in met_element.findall('hmdb:protein_associations/hmdb:protein', NS)]

enz = get_enzymes(find_metabolite('HMDB0000122'))
print(f"Glucose-associated proteins: {len(enz)}")
for e in enz[:3]:
    print(f"  {e['gene_name']} ({e['uniprot_id']}): {e['name']}")

def get_diseases(met_element):
    """Extract disease associations with OMIM IDs and PubMed references."""
    diseases = []
    for d in met_element.findall('hmdb:diseases/hmdb:disease', NS):
        name = d.find('hmdb:name', NS)
        omim = d.find('hmdb:omim_id', NS)
        pmids = [r.find('hmdb:pubmed_id', NS).text
                 for r in d.findall('hmdb:references/hmdb:reference', NS)
                 if r.find('hmdb:pubmed_id', NS) is not None and r.find('hmdb:pubmed_id', NS).text]
        diseases.append({'name': name.text if name is not None else None,
                         'omim_id': omim.text if omim is not None else None,
                         'pubmed_ids': pmids})
    return diseases

diseases = get_diseases(find_metabolite('HMDB0000122'))
print(f"Glucose disease associations: {len(diseases)}")
for d in diseases[:3]:
    print(f"  {d['name']} (OMIM: {d['omim_id']})")

def get_concentrations(met_element, biospecimen='Blood'):
    """Extract normal/abnormal concentration data filtered by biospecimen."""
    result = {'normal': [], 'abnormal': []}
    for ctype, key in [('normal_concentrations', 'normal'),
                       ('abnormal_concentrations', 'abnormal')]:
        for c in met_element.findall(f'hmdb:{ctype}/hmdb:concentration', NS):
            bio = c.find('hmdb:biospecimen', NS)
            if bio is None or bio.text != biospecimen:
                continue
            def txt(tag):
                el = c.find(f'hmdb:{tag}', NS)
                return el.text if el is not None else None
            result[key].append({'value': txt('concentration_value'),
                                'units': txt('concentration_units'),
                                'condition': txt('subject_condition')})
    return result

conc = get_concentrations(find_metabolite('HMDB0000122'), 'Blood')
print(f"Glucose blood: {len(conc['normal'])} normal, {len(conc['abnormal'])} abnormal")

def get_ms_spectra(met_element):
    """Extract MS/MS spectral peak lists (m/z + intensity)."""
    spectra = []
    for spec in met_element.findall('hmdb:spectra/hmdb:spectrum', NS):
        stype = spec.find('hmdb:type', NS)
        if stype is None or 'MS' not in (stype.text or ''):
            continue
        peaks = [{'mz': float(p.find('hmdb:mass_charge', NS).text),
                  'intensity': float(p.find('hmdb:intensity', NS).text or 0)}
                 for p in spec.findall('hmdb:ms_ms_peaks/hmdb:ms_ms_peak', NS)
                 if p.find('hmdb:mass_charge', NS) is not None
                 and p.find('hmdb:mass_charge', NS).text]
        spectra.append({'type': stype.text, 'num_peaks': len(peaks), 'peaks': peaks})
    return spectra

spectra = get_ms_spectra(find_metabolite('HMDB0000122'))
print(f"Glucose MS spectra: {len(spectra)}")

def get_nmr_spectra(met_element):
    """Extract NMR spectral peak lists (1H, 13C). Same pattern as MS above."""
    spectra = []
    for spec in met_element.findall('hmdb:spectra/hmdb:spectrum', NS):
        stype = spec.find('hmdb:type', NS)
        if stype is None or 'NMR' not in (stype.text or ''):
            continue
        nucleus = spec.find('hmdb:nucleus', NS)
        shifts = [float(p.find('hmdb:chemical_shift', NS).text)
                  for p in spec.findall('hmdb:nmr_one_d_peaks/hmdb:nmr_one_d_peak', NS)
                  if p.find('hmdb:chemical_shift', NS) is not None
                  and p.find('hmdb:chemical_shift', NS).text]
        spectra.append({'type': stype.text,
                        'nucleus': nucleus.text if nucleus is not None else None,
                        'num_peaks': len(shifts), 'chemical_shifts': shifts})
    return spectra

nmr = get_nmr_spectra(find_metabolite('HMDB0000122'))
print(f"Glucose NMR spectra: {len(nmr)}")

def get_external_ids(met_element):
    """Extract cross-database identifiers (KEGG, PubChem, ChEBI, DrugBank, CAS, etc.)."""
    fields = {'kegg_id': 'KEGG', 'pubchem_compound_id': 'PubChem', 'chebi_id': 'ChEBI',
              'drugbank_id': 'DrugBank', 'chemspider_id': 'ChemSpider',
              'cas_registry_number': 'CAS', 'biocyc_id': 'BioCyc', 'pdb_id': 'PDB',
              'foodb_id': 'FooDB', 'metlin_id': 'METLIN'}
    ids = {}
    for tag, label in fields.items():
        el = met_element.find(f'hmdb:{tag}', NS)
        if el is not None and el.text:
            ids[label] = el.text
    return ids

ids = get_external_ids(find_metabolite('HMDB0000122'))
print(f"Glucose cross-refs: {ids}")
# {'KEGG': 'C00031', 'PubChem': '5793', 'ChEBI': '17234', ...}

# Build cross-reference table for a metabolite list
import pandas as pd

queries = ['HMDB0000122', 'HMDB0000158', 'HMDB0000167', 'HMDB0000148']
rows = []
for q in queries:
    m = find_metabolite(q)
    if m is None: continue
    ids = get_external_ids(m)
    rows.append({'name': m.find('hmdb:name', NS).text, 'hmdb_id': q,
                 'kegg': ids.get('KEGG'), 'pubchem': ids.get('PubChem'),
                 'chebi': ids.get('ChEBI')})
print(pd.DataFrame(rows).to_string(index=False))

import pandas as pd

observed_mz = 180.063  # [M+H]+ for glucose
adduct_mass = 1.00728  # H+ adduct
target_mw = observed_mz - adduct_mass
tolerance_da = 0.01

candidates = []
for met in root.findall('hmdb:metabolite', NS):
    mw_el = met.find('hmdb:monisotopic_molecular_weight', NS)
    if mw_el is None or not mw_el.text:
        continue
    mw = float(mw_el.text)
    if abs(mw - target_mw) <= tolerance_da:
        candidates.append({
            'hmdb_id': met.find('hmdb:accession', NS).text,
            'name': met.find('hmdb:name', NS).text,
            'mw': mw, 'delta_da': abs(mw - target_mw),
            'formula': (met.find('hmdb:chemical_formula', NS).text
                        if met.find('hmdb:chemical_formula', NS) is not None else None),
        })

df = pd.DataFrame(candidates).sort_values('delta_da')
print(f"Candidates within {tolerance_da} Da of {target_mw:.3f}: {len(df)}")
print(df.head(10).to_string(index=False))

import pandas as pd

disease_query = 'diabetes'
biomarkers = []
for met in root.findall('hmdb:metabolite', NS):
    for d in met.findall('hmdb:diseases/hmdb:disease', NS):
        dname = d.find('hmdb:name', NS)
        if dname is None or not dname.text:
            continue
        if disease_query.lower() not in dname.text.lower():
            continue
        abnormal = [c for c in met.findall(
            'hmdb:abnormal_concentrations/hmdb:concentration', NS)
            if c.find('hmdb:subject_condition', NS) is not None
            and disease_query.lower() in
            (c.find('hmdb:subject_condition', NS).text or '').lower()]
        biomarkers.append({
            'hmdb_id': met.find('hmdb:accession', NS).text,
            'metabolite': met.find('hmdb:name', NS).text,
            'disease': dname.text,
            'abnormal_measurements': len(abnormal),
        })

df = pd.DataFrame(biomarkers).drop_duplicates(['hmdb_id', 'disease'])
print(f"Metabolites linked to '{disease_query}': {len(df)}")
print(df.sort_values('abnormal_measurements', ascending=False).head(15).to_string(index=False))

from collections import Counter
import pandas as pd

hit_ids = ['HMDB0000122', 'HMDB0000158', 'HMDB0000167',
           'HMDB0000148', 'HMDB0000064', 'HMDB0000161']

hit_pathways = Counter()
for hid in hit_ids:
    met = metabolite_index.get(hid)
    if met is None:
        continue
    for pw in met.findall('hmdb:pathways/hmdb:pathway', NS):
        pw_name = pw.find('hmdb:name', NS)
        if pw_name is not None and pw_name.text:
            hit_pathways[pw_name.text] += 1

enriched = [(pw, count) for pw, count in hit_pathways.most_common() if count >= 2]
df = pd.DataFrame(enriched, columns=['Pathway', 'Hit_Count'])
print(f"Pathways with 2+ hits from {len(hit_ids)} metabolites:")
print(df.to_string(index=False))