Monarch Database

pip install requests pandas matplotlib

import requests

MONARCH_API = "https://api.monarchinitiative.org/v3/api"

def monarch_get(endpoint: str, params: dict = None) -> dict:
    """GET request to Monarch API; raises on HTTP errors."""
    r = requests.get(f"{MONARCH_API}{endpoint}", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

# Get all genes associated with Marfan syndrome (MONDO:0007374)
result = monarch_get("/association/all", params={
    "subject": "MONDO:0007374",
    "category": "biolink:GeneToDiseaseAssociation",
    "limit": 10
})
print(f"Total gene associations: {result['total']}")
for item in result["items"][:5]:
    obj = item.get("object", {})
    print(f"  Gene: {obj.get('label', 'N/A')}  ({obj.get('id', 'N/A')})")
# Total gene associations: 3
# Gene: FBN1  (HGNC:3603)

import requests
import pandas as pd
import time

MONARCH_API = "https://api.monarchinitiative.org/v3/api"

def monarch_get(endpoint, params=None):
    r = requests.get(f"{MONARCH_API}{endpoint}", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

def get_disease_genes(mondo_id: str, limit: int = 200) -> pd.DataFrame:
    """Return DataFrame of genes associated with a disease."""
    result = monarch_get("/association/all", params={
        "subject": mondo_id,
        "category": "biolink:CausalGeneToDiseaseAssociation",
        "limit": limit
    })
    rows = []
    for item in result.get("items", []):
        obj = item.get("object", {})
        rows.append({
            "gene_id": obj.get("id"),
            "gene_symbol": obj.get("label"),
            "taxon": obj.get("taxon", {}).get("label") if obj.get("taxon") else None,
            "relation": item.get("predicate"),
            "evidence_count": len(item.get("evidence", [])),
        })
    return pd.DataFrame(rows)

# Cystic fibrosis (MONDO:0009861)
df = get_disease_genes("MONDO:0009861")
print(f"Genes for cystic fibrosis: {len(df)}")
print(df[["gene_symbol", "gene_id", "relation"]].to_string(index=False))
# Genes for cystic fibrosis: 1
# gene_symbol  gene_id    relation
#        CFTR  HGNC:1884  biolink:causes

def get_disease_phenotypes(mondo_id: str, limit: int = 200) -> pd.DataFrame:
    """Return DataFrame of phenotypes (HP terms) for a disease."""
    result = monarch_get("/association/all", params={
        "subject": mondo_id,
        "category": "biolink:DiseaseToPhenotypicFeatureAssociation",
        "limit": limit
    })
    rows = []
    for item in result.get("items", []):
        obj = item.get("object", {})
        rows.append({
            "hp_id": obj.get("id"),
            "phenotype": obj.get("label"),
            "frequency": item.get("frequency", {}).get("label") if item.get("frequency") else None,
            "onset": item.get("onset", {}).get("label") if item.get("onset") else None,
        })
    return pd.DataFrame(rows)

# Marfan syndrome (MONDO:0007374)
df = get_disease_phenotypes("MONDO:0007374", limit=50)
print(f"Phenotypes for Marfan syndrome: {len(df)}")
print(df[["phenotype", "hp_id", "frequency"]].head(8).to_string(index=False))
# Phenotypes for Marfan syndrome: 26
# phenotype                      hp_id        frequency
# Aortic root aneurysm        HP:0002616    HP:0040281  ...

def get_entity(entity_id: str) -> dict:
    """Retrieve metadata for a gene, disease, or phenotype by its ID."""
    result = monarch_get(f"/entity/{entity_id}")
    return result

# Look up HP:0001250 (Seizure)
hp = get_entity("HP:0001250")
print(f"Name: {hp.get('name')}")
print(f"ID: {hp.get('id')}")
print(f"Description: {hp.get('description', '')[:120]}")
print(f"Synonyms: {[s.get('val') for s in hp.get('synonyms', [])[:3]]}")
# Name: Seizure
# ID: HP:0001250
# Description: A seizure is an intermittent abnormality of nervous system physiology ...

# Look up a MONDO disease
disease = get_entity("MONDO:0007374")
print(f"\nDisease: {disease.get('name')}")
print(f"ID: {disease.get('id')}")

def search_entities(query: str, category: str = None, limit: int = 10) -> list:
    """Search Monarch entities by label/synonym."""
    params = {"q": query, "limit": limit}
    if category:
        params["category"] = category
    result = monarch_get("/search", params=params)
    return result.get("items", [])

# Search for "Ehlers-Danlos" diseases
hits = search_entities("Ehlers-Danlos", category="biolink:Disease", limit=8)
for hit in hits:
    print(f"  {hit.get('id'):<25}  {hit.get('name', 'N/A')}")
# MONDO:0020066              Ehlers-Danlos syndrome
# MONDO:0007522              classical Ehlers-Danlos syndrome
# MONDO:0007528              hypermobile Ehlers-Danlos syndrome
# MONDO:0007523              kyphoscoliotic Ehlers-Danlos syndrome

def get_gene_diseases(gene_id: str, limit: int = 100) -> pd.DataFrame:
    """Return DataFrame of diseases associated with a gene."""
    result = monarch_get("/association/all", params={
        "subject": gene_id,
        "category": "biolink:GeneToDiseaseAssociation",
        "limit": limit
    })
    rows = []
    for item in result.get("items", []):
        obj = item.get("object", {})
        rows.append({
            "disease_id": obj.get("id"),
            "disease_name": obj.get("label"),
            "predicate": item.get("predicate"),
        })
    return pd.DataFrame(rows)

# Diseases caused by FBN1 (HGNC:3603)
df = get_gene_diseases("HGNC:3603")
print(f"Diseases linked to FBN1: {len(df)}")
print(df[["disease_name", "disease_id"]].head(5).to_string(index=False))
# Diseases linked to FBN1: 8
# disease_name                     disease_id
# Marfan syndrome                  MONDO:0007374
# Stiff skin syndrome              MONDO:0007926

def get_gene_phenotypes(gene_id: str, limit: int = 100) -> pd.DataFrame:
    """Return gene-phenotype associations, optionally across species."""
    result = monarch_get("/association/all", params={
        "subject": gene_id,
        "category": "biolink:GeneToPhenotypicFeatureAssociation",
        "limit": limit
    })
    rows = []
    for item in result.get("items", []):
        subj = item.get("subject", {})
        obj = item.get("object", {})
        rows.append({
            "gene_id": subj.get("id"),
            "gene_symbol": subj.get("label"),
            "taxon": subj.get("taxon", {}).get("label") if subj.get("taxon") else None,
            "phenotype_id": obj.get("id"),
            "phenotype": obj.get("label"),
        })
    return pd.DataFrame(rows)

# Phenotypes for human FBN1
df = get_gene_phenotypes("HGNC:3603")
print(f"FBN1 phenotype associations: {len(df)}")
print(df[["taxon", "phenotype"]].value_counts("taxon"))
# Homo sapiens    18
# Mus musculus     6

def get_histopheno(mondo_id: str) -> dict:
    """Retrieve summarized phenotype distribution for a disease."""
    result = monarch_get(f"/histopheno/{mondo_id}")
    return result

hist = get_histopheno("MONDO:0007374")   # Marfan syndrome
items = hist.get("items", [])
print(f"Phenotype categories for Marfan syndrome ({len(items)} systems):")
for item in sorted(items, key=lambda x: x.get("count", 0), reverse=True)[:8]:
    print(f"  {item.get('label', 'N/A'):<40}  n={item.get('count', 0)}")
# Connective tissue                         n=12
# Cardiovascular system                     n=8
# Eye                                       n=6

def get_phenotype_genes(hp_id: str, limit: int = 50) -> pd.DataFrame:
    """Return genes associated with a phenotype term."""
    result = monarch_get("/association/all", params={
        "object": hp_id,
        "category": "biolink:GeneToPhenotypicFeatureAssociation",
        "limit": limit
    })
    rows = []
    for item in result.get("items", []):
        subj = item.get("subject", {})
        rows.append({
            "gene_id": subj.get("id"),
            "gene_symbol": subj.get("label"),
            "taxon": subj.get("taxon", {}).get("label") if subj.get("taxon") else None,
        })
    return pd.DataFrame(rows)

# HP:0001631 — Atrial septal defect
df = get_phenotype_genes("HP:0001631")
print(f"Genes associated with Atrial septal defect: {len(df)}")
print(df[df["taxon"] == "Homo sapiens"]["gene_symbol"].head(8).tolist())
# ['TBX5', 'GATA4', 'NKX2-5', 'MYH6', 'ACTC1', ...]

import requests
import pandas as pd
import time

MONARCH_API = "https://api.monarchinitiative.org/v3/api"

def monarch_get(endpoint, params=None):
    r = requests.get(f"{MONARCH_API}{endpoint}", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

# Patient HPO profile
patient_hp_terms = ["HP:0001250", "HP:0000252", "HP:0001263"]   # Seizure, Microcephaly, DD

gene_scores = {}
for hp_id in patient_hp_terms:
    result = monarch_get("/association/all", params={
        "object": hp_id,
        "category": "biolink:DiseaseToPhenotypicFeatureAssociation",
        "limit": 50
    })
    diseases = [item.get("subject", {}).get("id") for item in result.get("items", [])]
    # For each disease, get causal genes
    for disease_id in diseases[:5]:    # limit per phenotype for demo
        gene_result = monarch_get("/association/all", params={
            "subject": disease_id,
            "category": "biolink:CausalGeneToDiseaseAssociation",
            "limit": 20
        })
        for item in gene_result.get("items", []):
            gene_sym = item.get("object", {}).get("label", "")
            if gene_sym:
                gene_scores[gene_sym] = gene_scores.get(gene_sym, 0) + 1
        time.sleep(0.3)

# Rank genes by co-occurrence with patient phenotypes
df = pd.DataFrame(
    [(gene, score) for gene, score in gene_scores.items()],
    columns=["gene_symbol", "phenotype_overlap_score"]
).sort_values("phenotype_overlap_score", ascending=False)
print(f"Candidate genes ranked by phenotype overlap (n={len(df)})")
print(df.head(10).to_string(index=False))
df.to_csv("candidate_genes_phenotype_ranked.csv", index=False)

import requests
import pandas as pd
import matplotlib.pyplot as plt
import time

MONARCH_API = "https://api.monarchinitiative.org/v3/api"

def monarch_get(endpoint, params=None):
    r = requests.get(f"{MONARCH_API}{endpoint}", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

mondo_id = "MONDO:0009861"   # Cystic fibrosis
disease_info = monarch_get(f"/entity/{mondo_id}")
disease_name = disease_info.get("name", mondo_id)

# Step 1: Get phenotype associations
result = monarch_get("/association/all", params={
    "subject": mondo_id,
    "category": "biolink:DiseaseToPhenotypicFeatureAssociation",
    "limit": 200
})
items = result.get("items", [])
print(f"Phenotypes for {disease_name}: {len(items)}")

# Step 2: Gather HP term labels
rows = []
for item in items:
    obj = item.get("object", {})
    rows.append({
        "hp_id": obj.get("id"),
        "phenotype": obj.get("label"),
        "frequency": item.get("frequency", {}).get("label") if item.get("frequency") else "Unknown"
    })
df = pd.DataFrame(rows)

# Step 3: Histopheno summary for bar chart
hist = monarch_get(f"/histopheno/{mondo_id}")
hist_items = sorted(hist.get("items", []), key=lambda x: x.get("count", 0), reverse=True)[:12]
systems = [x.get("label", "Other")[:25] for x in hist_items]
counts = [x.get("count", 0) for x in hist_items]

fig, ax = plt.subplots(figsize=(10, 5))
bars = ax.barh(systems[::-1], counts[::-1], color="#2196F3")
ax.bar_label(bars, fmt="%d", padding=3)
ax.set_xlabel("Phenotype Count")
ax.set_title(f"Phenotype Distribution by System\n{disease_name} ({mondo_id})")
plt.tight_layout()
plt.savefig("monarch_phenotype_distribution.png", dpi=150, bbox_inches="tight")
print(f"Saved monarch_phenotype_distribution.png ({len(df)} total phenotypes)")

# Step 4: Export HPO terms
df.to_csv(f"{mondo_id.replace(':', '_')}_phenotypes.csv", index=False)
print(df[["hp_id", "phenotype", "frequency"]].head(8).to_string(index=False))

import requests
import pandas as pd
import time

MONARCH_API = "https://api.monarchinitiative.org/v3/api"

def monarch_get(endpoint, params=None):
    r = requests.get(f"{MONARCH_API}{endpoint}", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

diseases = {
    "MONDO:0007374": "Marfan syndrome",
    "MONDO:0009861": "Cystic fibrosis",
    "MONDO:0007522": "Classical EDS",
}

all_rows = []
for mondo_id, disease_name in diseases.items():
    # Human causal genes
    result = monarch_get("/association/all", params={
        "subject": mondo_id,
        "category": "biolink:CausalGeneToDiseaseAssociation",
        "limit": 50
    })
    for item in result.get("items", []):
        obj = item.get("object", {})
        all_rows.append({
            "disease_id": mondo_id,
            "disease_name": disease_name,
            "gene_id": obj.get("id"),
            "gene_symbol": obj.get("label"),
            "species": "Homo sapiens",
        })
    time.sleep(0.3)

df = pd.DataFrame(all_rows)
df.to_csv("rare_disease_gene_network.csv", index=False)
print(f"Associations collected: {len(df)}")
print(df.groupby("disease_name")["gene_symbol"].apply(list).to_string())