monarch-database

Overview

The Monarch Initiative integrates disease-phenotype-gene relationships from 30+ biomedical databases (OMIM, Orphanet, ClinVar, MGI, ZFIN, Reactome) into a unified knowledge graph. The REST API at https://api.monarchinitiative.org/v3/api provides access to associations between genes, diseases, and phenotypes using MONDO disease IDs, Human Phenotype Ontology (HPO) terms, and standard gene identifiers. No authentication is required; the service is free for academic use.

When to Use

• Mapping a disease (MONDO ID) to all associated causal genes and their evidence sources
• Retrieving phenotype profiles (HP terms) for a disease to build phenotypic similarity models
• Ranking candidate genes by phenotypic similarity to a patient's HPO symptom list
• Querying cross-species gene-phenotype associations (mouse, zebrafish, fly) for model organism comparisons
• Exploring rare disease gene-phenotype networks for diagnostic candidate generation
• Resolving entity metadata (gene symbol, disease name, phenotype label) from a MONDO/HP/HGNC ID
• Use opentargets-database instead when you need drug-target evidence scores or tractability data alongside disease associations
• Use clinvar-database when you need clinical pathogenicity classifications with submitter review status

Prerequisites

• Python packages: requests, pandas, matplotlib
• Data requirements: MONDO IDs (e.g., MONDO:0007374), HP term IDs (e.g., HP:0001250), or gene symbols/HGNC IDs
• Environment: internet connection; no API key required
• Rate limits: no published rate limit; use time.sleep(0.3) between batch requests; avoid bursts over 10 requests/second

pip install requests pandas matplotlib

Quick Start

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)

Core API

Query 1: Disease-Gene Associations

Retrieve all genes associated with a disease by MONDO ID. Returns causal gene records with evidence metadata.

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

Query 2: Disease-Phenotype Associations

Retrieve HPO phenotype terms linked to a disease. Useful for building phenotype profiles and similarity scoring.

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  ...

Query 3: Entity Lookup

Retrieve metadata for any Monarch entity (gene, disease, phenotype) by its identifier.

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')}")

Query 4: Text Search for Entities

Search for entities by free-text label, useful for resolving disease names or phenotype terms to IDs.

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

Query 5: Gene-to-Disease Associations

Retrieve diseases associated with a gene. Useful for understanding a gene's disease spectrum.

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"]].h