Brenda Database

pip install zeep pandas requests
# Register at https://www.brenda-enzymes.org/register.php to obtain API credentials

from zeep import Client

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = "your_sha256_hashed_password"  # Use hashlib.sha256

# Get Km values for lactate dehydrogenase (EC 1.1.1.27) and pyruvate
ec_number = "1.1.1.27"
params = (EMAIL, PASSWORD_SHA256,
          f"ecNumber*{ec_number}", "substrate*pyruvate", "", "", "", "", "")
result = client.service.getKmValue(*params)
print(f"Km values for LDH with pyruvate: {len(result)} records")
for r in result[:3]:
    print(f"  Km={r.kmValue} {r.kmValueMaximum or ''} mM | org: {r.organism} | PMID: {r.literature}")

from zeep import Client
import hashlib, pandas as pd

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD = "your_password"
PASSWORD_SHA256 = hashlib.sha256(PASSWORD.encode()).hexdigest()

def get_km_values(ec_number, substrate=""):
    """Retrieve Km values for an EC number, optionally filtered by substrate."""
    substrate_param = f"substrate*{substrate}" if substrate else ""
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", substrate_param, "", "", "", "", "")
    return client.service.getKmValue(*params)

# Km for glucokinase (EC 2.7.1.2) with glucose
results = get_km_values("2.7.1.2", substrate="glucose")
print(f"Km (glucose, glucokinase): {len(results)} measurements")

rows = []
for r in results[:10]:
    rows.append({
        "km_value": r.kmValue,
        "km_max": r.kmValueMaximum,
        "unit": "mM",
        "organism": r.organism,
        "commentary": r.commentary[:80] if r.commentary else "",
        "pmid": r.literature,
    })
df = pd.DataFrame(rows)
print(df.to_string(index=False))

# Get ALL Km values (all substrates) for an EC number
all_km = get_km_values("1.1.1.1")  # Alcohol dehydrogenase
print(f"\nAlcohol dehydrogenase - total Km records: {len(all_km)}")
substrate_counts = {}
for r in all_km:
    sub = r.substrate or "unknown"
    substrate_counts[sub] = substrate_counts.get(sub, 0) + 1
top_substrates = sorted(substrate_counts.items(), key=lambda x: -x[1])[:5]
print("Top substrates by measurement count:")
for sub, cnt in top_substrates:
    print(f"  {sub}: {cnt} measurements")

from zeep import Client
import hashlib, pandas as pd

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

def get_kcat_values(ec_number, substrate=""):
    substrate_param = f"substrate*{substrate}" if substrate else ""
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", substrate_param, "", "", "", "", "")
    return client.service.getTurnoverNumber(*params)

results = get_kcat_values("1.1.1.27")  # Lactate dehydrogenase
print(f"kcat records for LDH: {len(results)}")

rows = []
for r in results[:10]:
    rows.append({
        "kcat": r.turnoverNumber,
        "unit": "1/s",
        "substrate": r.substrate,
        "organism": r.organism,
    })
df = pd.DataFrame(rows)
print(df.head())

from zeep import Client
import hashlib, pandas as pd

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

def get_substrates_products(ec_number):
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", "", "", "", "", "", "")
    return client.service.getSubstrates(*params)

results = get_substrates_products("4.2.1.1")  # Carbonic anhydrase
print(f"Substrates for carbonic anhydrase (EC 4.2.1.1):")
substrates_seen = set()
for r in results[:10]:
    if r.substrate not in substrates_seen:
        print(f"  {r.substrate} | organism: {r.organism}")
        substrates_seen.add(r.substrate)

# Get inhibitors
def get_inhibitors(ec_number):
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", "", "", "", "", "", "")
    return client.service.getInhibitors(*params)

inhibitors = get_inhibitors("4.2.1.1")
print(f"\nInhibitors of carbonic anhydrase: {len(inhibitors)} records")
inhib_names = list(set(r.inhibitor for r in inhibitors if r.inhibitor))
print("Sample inhibitors:", inhib_names[:8])

from zeep import Client
import hashlib

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

def get_km_by_organism(ec_number, organism):
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", "", f"organism*{organism}", "", "", "", "")
    return client.service.getKmValue(*params)

# Human GAPDH Km values
human_km = get_km_by_organism("1.2.1.12", "Homo sapiens")
print(f"Human GAPDH (EC 1.2.1.12) Km values: {len(human_km)} records")
for r in human_km[:5]:
    print(f"  Substrate: {r.substrate:30s} Km={r.kmValue} mM")

from zeep import Client
import hashlib

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

def get_ph_optimum(ec_number):
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", "", "", "", "", "", "")
    return client.service.getPhOptimum(*params)

def get_temp_optimum(ec_number):
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", "", "", "", "", "", "")
    return client.service.getTemperatureOptimum(*params)

ec = "3.4.21.4"  # Trypsin
ph_data = get_ph_optimum(ec)
temp_data = get_temp_optimum(ec)

print(f"Trypsin (EC {ec}):")
ph_values = [r.phOptimum for r in ph_data[:10] if r.phOptimum]
temp_values = [r.temperatureOptimum for r in temp_data[:10] if r.temperatureOptimum]
if ph_values:
    print(f"  pH optima: {sorted(ph_values)}")
if temp_values:
    print(f"  Temperature optima (°C): {sorted(temp_values)}")

from zeep import Client
import hashlib

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

def get_uniprot_accessions(ec_number):
    params = (EMAIL, PASSWORD_SHA256,
              f"ecNumber*{ec_number}", "", "", "", "", "", "")
    return client.service.getUniprotAccession(*params)

results = get_uniprot_accessions("1.1.1.27")  # LDH
print(f"UniProt accessions for LDH (EC 1.1.1.27):")
seen = set()
for r in results[:10]:
    acc = r.uniprotAccessionNumber
    org = r.organism
    if acc and acc not in seen:
        print(f"  {acc:12s} ({org})")
        seen.add(acc)

from zeep import Client
import hashlib, pandas as pd, time

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

# Glycolysis enzymes
enzymes = {
    "Hexokinase": "2.7.1.1",
    "Phosphoglucose isomerase": "5.3.1.9",
    "Phosphofructokinase": "2.7.1.11",
    "Aldolase": "4.1.2.13",
}

rows = []
for name, ec in enzymes.items():
    params = (EMAIL, PASSWORD_SHA256, f"ecNumber*{ec}", "", "organism*Homo sapiens", "", "", "", "")
    try:
        km_results = client.service.getKmValue(*params)
        kcat_results = client.service.getTurnoverNumber(*params)
        km_vals = [r.kmValue for r in km_results if r.kmValue]
        kcat_vals = [r.turnoverNumber for r in kcat_results if r.turnoverNumber]
        rows.append({
            "enzyme": name,
            "ec": ec,
            "n_km_records": len(km_vals),
            "km_median_mM": pd.Series(km_vals).median() if km_vals else None,
            "n_kcat_records": len(kcat_vals),
            "kcat_median_1_s": pd.Series(kcat_vals).median() if kcat_vals else None,
        })
    except Exception as e:
        rows.append({"enzyme": name, "ec": ec, "error": str(e)})
    time.sleep(0.5)

df = pd.DataFrame(rows)
df.to_csv("glycolysis_kinetics.csv", index=False)
print(df.to_string(index=False))

from zeep import Client
import hashlib, pandas as pd, time
from collections import Counter

WSDL = "https://www.brenda-enzymes.org/soap/brenda_zeep.wsdl"
client = Client(WSDL)

EMAIL = "your@email.com"
PASSWORD_SHA256 = hashlib.sha256("your_password".encode()).hexdigest()

# Carbonic anhydrase isoforms
ca_ecs = ["4.2.1.1"]  # All carbonic anhydrases share this EC

rows = []
for ec in ca_ecs:
    params = (EMAIL, PASSWORD_SHA256, f"ecNumber*{ec}", "", "", "", "", "", "")
    try:
        inhib_results = client.service.getInhibitors(*params)
        for r in inhib_results[:30]:
            rows.append({
                "ec": ec,
                "inhibitor": r.inhibitor,
                "organism": r.organism,
                "ic50": r.ic50Value if hasattr(r, "ic50Value") else None,
            })
    except Exception as e:
        print(f"Error for {ec}: {e}")
    time.sleep(0.5)

df = pd.DataFrame(rows)
print(f"Total inhibitor records: {len(df)}")
top_inhib = Counter(df["inhibitor"]).most_common(10)
print("\nMost reported inhibitors:")
for inhib, count in top_inhib:
    print(f"  {inhib}: {count} records")