SkillAgentSearch skills...

monarch-database

Monarch Initiative knowledge graph REST API for disease-gene-phenotype associations and cross-species orthology. MONDO disease-to-gene/phenotype, HP phenotype profiles, cross-species comparisons. Use for rare disease gene prioritization and phenotype-based candidate ranking.

Install / Use

npx skills add jaechang-hits/SciAgent-Skills --skill monarch-database

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

91/100

Supported Platforms

Universal

Our assessment of monarch-database

monarch-database scores 91/100 on our quality scale, 256th of 599 Data & Analytics skills we index (top 43%).

Its SKILL.md is 26 KB long, well organised into 74 sections with 16 code examples: a thorough specification that gives an agent plenty to work with.

It has 367 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
11/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so monarch-database is actively maintained.
  • Our last check on 2026-11-20 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-05. Automated pattern scan on 2026-10-05. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

monarch-database compared with similar skills

All 4 of these similar skills score higher than monarch-database; compare them before choosing.

SkillScoreStarsUpdatedFormat
monarch-database (this skill)by jaechang-hits913673mo agoSKILL.md
Agent-Reachby Panniantong100113.3k12d agoCLAUDE.md
headroomby headroomlabs-ai10080.2ktodayCLAUDE.md
Scraplingby D4Vinci100104.4k2d agoMCP Server
crawl4aiby unclecode10087.6ktodayMCP Server

Frequently asked questions

How do I install monarch-database?
Run npx skills add jaechang-hits/SciAgent-Skills --skill monarch-database. The install tabs above show the steps for each supported agent.
Which AI agents does monarch-database work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is monarch-database safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is monarch-database still maintained?
The repository was last updated about 3 months ago, so monarch-database is actively maintained.

name: "monarch-database" description: "Monarch Initiative knowledge graph REST API for disease-gene-phenotype associations and cross-species orthology. MONDO disease-to-gene/phenotype, HP phenotype profiles, cross-species comparisons. Use for rare disease gene prioritization and phenotype-based candidate ranking. For GWAS use gwas-database; for clinical pathogenicity use clinvar-database." license: "BSD-3-Clause"

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"]].head(5).to_string(index=False))
# Diseases linked to FBN1: 8
# disease_name                     disease_id
# Marfan syndrome                  MONDO:0007374
# Stiff skin syndrome              MONDO:0007926

Query 6: Gene-Phenotype Associations (Cross-Species)

Query phenotypes linked to a gene across species including mouse, zebrafish, and human.

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

Query 7: Histopheno — Phenotype Distribution for a Disease

Retrieve summarized phenotype counts by anatomical system for a disease, useful for phenotype spectrum overviews.

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

Query 8: Phenotype-to-Gene Associations

Given a set of HP phenotype terms, retrieve associated genes — the basis of phenotype-matching tools.

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', ...]

Key Concepts

Monarch Identifier System

Monarch uses ontology-based compact URIs (CURIEs) as identifiers:

| Prefix | Namespace | Example | |--------|-----------|---------| | MONDO | Mondo Disease Ontology | MONDO:0007374 (Marfan syndrome) | | HP | Human Phenotype Ontology | HP:0001250 (Seizure) | |

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars367
CategoryData
Updated2mo ago
Forks36

Languages

Python

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium
monarch-database — Universal Skill: Install & Safety Check | SkillAgent