Metabolomics Workbench Database

pip install requests pandas

import requests

BASE = "https://www.metabolomicsworkbench.org/rest"

# Two-step free-text → compound (the API rejects compound/name/...)
def lookup_by_name(name):
    # 1) Normalise to RefMet name
    r = requests.get(f"{BASE}/refmet/match/{name}", timeout=30)
    r.raise_for_status()
    refmet = r.json()
    if not refmet.get("refmet_name"):
        return None
    # 2) Pull full compound record by RefMet name (or by pubchem_cid)
    r2 = requests.get(f"{BASE}/refmet/name/{refmet['refmet_name']}/all", timeout=30)
    rec = r2.json() if r2.json() else {}
    return rec if isinstance(rec, dict) else None

c = lookup_by_name("glucose")
print(f"{c['name']}: formula={c['formula']}, PubChem CID={c['pubchem_cid']}, "
      f"InChIKey={c['inchi_key']}")
# Glucose: formula=C6H12O6, PubChem CID=5793, InChIKey=WQZGKKKJIJFFOK-GASJEMHNSA-N

import requests

BASE = "https://www.metabolomicsworkbench.org/rest"

# By PubChem CID
r = requests.get(f"{BASE}/compound/pubchem_cid/5793/all/json", timeout=30)
glucose = r.json()
print(f"PubChem 5793 -> {glucose['name']}, formula={glucose['formula']}, "
      f"HMDB={glucose.get('hmdb_id')}, KEGG={glucose.get('kegg_id')}")

# By KEGG ID
r = requests.get(f"{BASE}/compound/kegg_id/C00031/all/json", timeout=30)
print("KEGG C00031 ->", r.json()["name"])

# By InChIKey
r = requests.get(f"{BASE}/compound/inchi_key/WQZGKKKJIJFFOK-GASJEMHNSA-N/all/json", timeout=30)
print("InChIKey -> regno:", r.json()["regno"])

# Compound by formula returns a paged dict (multiple matches)
import requests
BASE = "https://www.metabolomicsworkbench.org/rest"
r = requests.get(f"{BASE}/compound/formula/C6H12O6/all/json", timeout=30)
matches = r.json()
print(f"Compounds with formula C6H12O6: {len(matches)}")
for k in list(matches)[:3]:
    print(f"  regno={matches[k]['regno']}  name={matches[k]['name']}")

import requests, pandas as pd

BASE = "https://www.metabolomicsworkbench.org/rest"

# Single-study summary — `study/study_id/{id}/summary` returns a flat dict
# (keys: study_id, study_title, species, institute, analysis_type, ...)
r = requests.get(f"{BASE}/study/study_id/ST000001/summary", timeout=30)
s = r.json()
print(f"{s['study_id']}: {s['study_title'][:60]}")
print(f"  Species : {s.get('species')}  Institute: {s.get('institute')}")
print(f"  Submit  : {s.get('submission_date')}")

# Studies that detected a metabolite — `study/refmet_name/{x}/summary` returns
# a thin index of (refmet_name, kegg_id, study_id) rows. Chain study_id → full summary
# to get title and species.
import requests, pandas as pd
BASE = "https://www.metabolomicsworkbench.org/rest"
r = requests.get(f"{BASE}/study/refmet_name/Glucose/summary", timeout=60)
d = r.json()
rows = list(d.values()) if isinstance(d, dict) else d
print(f"Studies referencing 'Glucose': {len(rows)}")
print(pd.DataFrame(rows).head(5).to_string(index=False))
# refmet_name kegg_id  study_id
#     Glucose  C00031  ST000001
#     Glucose  C00031  ST000002
#     ...

import requests

BASE = "https://www.metabolomicsworkbench.org/rest"

def normalise_to_refmet(user_text):
    r = requests.get(f"{BASE}/refmet/match/{user_text}", timeout=30)
    r.raise_for_status()
    m = r.json()
    if not m or not m.get("refmet_name"):
        return None
    return m["refmet_name"]

def refmet_full(refmet_name):
    r = requests.get(f"{BASE}/refmet/name/{refmet_name}/all", timeout=30)
    r.raise_for_status()
    rec = r.json()
    return rec if isinstance(rec, dict) and rec else None

name = normalise_to_refmet("alpha-D-glucose")  # -> 'Glucose'
print(f"Normalised: {name}")
rec = refmet_full(name)
print(f"  PubChem CID : {rec['pubchem_cid']}")
print(f"  InChIKey    : {rec['inchi_key']}")
print(f"  Super class : {rec['super_class']} / {rec['main_class']} / {rec['sub_class']}")

import requests, pandas as pd

BASE = "https://www.metabolomicsworkbench.org/rest"

def study_ids_for_metabolite(refmet_name):
    """Return the study_id list that report a given RefMet name."""
    r = requests.get(f"{BASE}/study/refmet_name/{refmet_name}/summary", timeout=60)
    r.raise_for_status()
    d = r.json()
    rows = list(d.values()) if isinstance(d, dict) else d
    return sorted({row["study_id"] for row in rows if row.get("study_id")})

def study_summary(study_id):
    """Pull full summary (title, species, institute, dates) for one study_id.
    Response is a flat dict with keys study_id/study_title/species/institute/..."""
    return requests.get(f"{BASE}/study/study_id/{study_id}/summary", timeout=30).json()

# Find glucose studies, then enrich the first few
ids = study_ids_for_metabolite("Glucose")
print(f"Studies referencing 'Glucose': {len(ids)}")
rows = [study_summary(sid) for sid in ids[:5]]
df = pd.DataFrame(rows)
print(df[["study_id", "study_title", "species"]].head().to_string(index=False))

import requests, io, pandas as pd

BASE = "https://www.metabolomicsworkbench.org/rest"

def moverz_search(db, mz, ion, tolerance=0.005):
    """Search precursor m/z in REFMET / LIPIDS / MB and return a DataFrame.
    Response is TSV text — no JSON variant."""
    assert db in {"REFMET", "LIPIDS", "MB"}
    r = requests.get(f"{BASE}/moverz/{db}/{mz}/{ion}/{tolerance}/txt", timeout=30)
    r.raise_for_status()
    return pd.read_csv(io.StringIO(r.text), sep="\t")

df = moverz_search("REFMET", 180.063, "M+H", 0.005)
print(f"Candidates at m/z 180.063 [M+H]+ (REFMET): {len(df)}")
print(df.head(5).to_string(index=False))

# Same query against the LIPIDS database
import requests, io, pandas as pd
BASE = "https://www.metabolomicsworkbench.org/rest"
r = requests.get(f"{BASE}/moverz/LIPIDS/760.585/M+H/0.01/txt", timeout=30)
df_lipids = pd.read_csv(io.StringIO(r.text), sep="\t")
print(f"Lipid candidates at m/z 760.585: {len(df_lipids)}")
print(df_lipids.head(3).to_string(index=False))

import requests

BASE = "https://www.metabolomicsworkbench.org/rest"

r = requests.get(f"{BASE}/gene/gene_symbol/HMGCR/all", timeout=30)
g = r.json()
print(f"{g['gene_symbol']} -> MGP: {g.get('mgp_id')}  ({g.get('gene_name', '')[:60]})")

# Protein by UniProt accession
r2 = requests.get(f"{BASE}/protein/uniprot_id/P04035/all", timeout=30)
p = r2.json()
print(f"UniProt P04035: {p.get('protein_name', '')[:60]}  organism={p.get('organism')}")

import requests, pandas as pd

BASE = "https://www.metabolomicsworkbench.org/rest"

def resolve_to_compound(user_text):
    # 1) Normalise via refmet/match
    rm = requests.get(f"{BASE}/refmet/match/{user_text}", timeout=30).json()
    if not rm.get("refmet_name"):
        return None
    name = rm["refmet_name"]
    # 2) Fetch full RefMet record (includes pubchem_cid / inchi_key)
    full = requests.get(f"{BASE}/refmet/name/{name}/all", timeout=30).json()
    if not isinstance(full, dict) or not full:
        return None
    # 3) Optionally pull the matching compound record via PubChem CID
    cid = full.get("pubchem_cid")
    compound = None
    if cid:
        compound = requests.get(f"{BASE}/compound/pubchem_cid/{cid}/all/json",
                                timeout=30).json()
    return {
        "input": user_text,
        "refmet_name": name,
        "formula": full.get("formula"),
        "pubchem_cid": cid,
        "hmdb_id": compound.get("hmdb_id") if compound else None,
        "kegg_id": compound.get("kegg_id") if compound else None,
        "inchi_key": full.get("inchi_key"),
    }

queries = ["glucose", "alpha-D-glucose", "L-tyrosine", "cholesterol"]
df = pd.DataFrame([resolve_to_compound(q) for q in queries])
print(df.to_string(index=False))
df.to_csv("name_resolution.csv", index=False)

import requests, io, pandas as pd, time

BASE = "https://www.metabolomicsworkbench.org/rest"

def annotate_peaks(mz_values, ion="M+H", tolerance=0.005):
    out = []
    for mz in mz_values:
        r = requests.get(f"{BASE}/moverz/REFMET/{mz}/{ion}/{tolerance}/txt", timeout=30)
        if r.status_code != 200 or not r.text.strip():
            time.sleep(0.3); continue
        df = pd.read_csv(io.StringIO(r.text), sep="\t")
        for _, row in df.iterrows():
            out.append({
                "query_mz": mz,
                "matched_mz": row["Matched m/z"],
                "delta": row["Delta"],
                "name": row["Name"],
                "formula": row["Formula"],
                "ion": row["Ion"],
                "main_class": row.get("Main class"),
            })
        time.sleep(0.3)
    return pd.DataFrame(out)

peaks = [180.063, 166.086, 90.055]   # glucose, phenylalanine, alanine
df_ann = annotate_peaks(peaks)
print(df_ann.head(10).to_string(index=False))
df_ann.to_csv("ms_annotations.csv", index=False)

import requests, pandas as pd

BASE = "https://www.metabolomicsworkbench.org/rest"

def studies_with(refmet_name, enrich_n=20):
    """Return a DataFrame: study_id rows that report the metabolite, enriched with
    title + species for the first `enrich_n` IDs (via study/study_id/.../summary)."""
    r = requests.get(f"{BASE}/study/refmet_name/{refmet_name}/summary", timeout=60)
    r.raise_for_status()
    d = r.json()
    rows = list(d.values()) if isinstance(d, dict) else d
    ids = sorted({row["study_id"] for row in rows if row.get("study_id")})
    enriched = []
    for sid in ids[:enrich_n]:
        enriched.append(requests.get(
            f"{BASE}/study/study_id/{sid}/summary", timeout=30).json())
    return pd.DataFrame(enriched)

df = studies_with("Glucose", enrich_n=20)
print(f"Glucose-detecting studies (first 20 enriched): {len(df)}")
print(df.groupby("species").size().sort_values(ascending=False).head(8))