Primekg Agent Skill

PrimeKG Knowledge Graph Skill

Overview

PrimeKG is a precision medicine knowledge graph that integrates over 20 primary databases and high-quality scientific literature into a single resource. It contains over 100,000 nodes and 4 million edges across 29 relationship types, including drug-target, disease-gene, and phenotype-disease associations.

Key capabilities:

• Search for nodes (genes, proteins, drugs, diseases, phenotypes)
• Retrieve direct neighbors (associated entities and clinical evidence)
• Analyze local disease context (related genes, drugs, phenotypes)
• Identify drug-disease paths (potential repurposing opportunities)

Data access: Programmatic access via query_primekg.py. Data is stored at C:\Users\eamon\Documents\Data\PrimeKG\kg.csv.

When to Use This Skill

This skill should be used when:

• Knowledge-based drug discovery: Identifying targets and mechanisms for diseases.
• Drug repurposing: Finding existing drugs that might have evidence for new indications.
• Phenotype analysis: Understanding how symptoms/phenotypes relate to diseases and genes.
• Multiscale biology: Bridging the gap between molecular targets (genes) and clinical outcomes (diseases).
• Network pharmacology: Investigating the broader network effects of drug-target interactions.

Core Workflow

1. Search for Entities

Find identifiers for genes, drugs, or diseases.

from scripts.query_primekg import search_nodes

# Search for Alzheimer's disease nodes
results = search_nodes("Alzheimer", node_type="disease")
# Returns: [{"id": "EFO_0000249", "type": "disease", "name": "Alzheimer's disease", ...}]

2. Get Neighbors (Direct Associations)

Retrieve all connected nodes and relationship types.

from scripts.query_primekg import get_neighbors

# Get all neighbors of a specific disease ID
neighbors = get_neighbors("EFO_0000249")
# Returns: List of neighbors like {"neighbor_name": "APOE", "relation": "disease_gene", ...}

3. Analyze Disease Context

A high-level function to summarize associations for a disease.

from scripts.query_primekg import get_disease_context

# Comprehensive summary for a disease
context = get_disease_context("Alzheimer's disease")
# Access: context['associated_genes'], context['associated_drugs'], context['phenotypes']

Relationship Types in PrimeKG

The graph contains several key relationship types including:

• protein_protein: Physical PPIs
• drug_protein: Drug target/mechanism associations
• disease_gene: Genetic associations
• drug_disease: Indications and contraindications
• disease_phenotype: Clinical signs and symptoms
• gwas: Genome-wide association studies evidence

Best Practices

• Use specific IDs: When using get_neighbors, ensure you have the correct ID from search_nodes.
• Context first: Use get_disease_context for a broad overview before diving into specific genes or drugs.
• Filter relationships: Use the relation_type filter in get_neighbors to focus on specific evidence (e.g., only drug_protein).
• Multiscale integration: Combine with OpenTargets for deeper genetic evidence or Semantic Scholar for the latest literature context.

Resources

Scripts

• scripts/query_primekg.py: Core functions for searching and querying the knowledge graph.

Data Path

• Data: kg.csv, downloaded from the PrimeKG Harvard Dataverse.
• Point the scripts at it with export PRIMEKG_DATA=/path/to/kg.csv (default: data/PrimeKG/kg.csv).
• Total nodes: ~129,000
• Total edges: ~4,000,000
• Database: CSV-based, optimized for pandas querying.