primekg

Query PrimeKG knowledge graph nodes and neighbors using Python and pandas.

21|1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/OwnLabAI/ownlab --skill primekg-ownlabai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: primekg
Source: https://github.com/OwnLabAI/ownlab/tree/main/mart/skills/scientific-skills/primekg
Command: npx skills add https://github.com/OwnLabAI/ownlab --skill primekg-ownlabai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, and includes scripts (resource) components.

What problem does it solve?

PrimeKG Knowledge Graph provides researchers with a programmable interface to explore multiscale biomedical data by connecting genes, drugs, diseases, phenotypes, and more in a large integrated graph.

Core Features & Use Cases

  • Search for nodes (genes, proteins, drugs, diseases, phenotypes).
  • Retrieve direct neighbors and evidence across the knowledge graph.
  • Analyze disease context by summarizing associated genes, drugs, and phenotypes, and identify potential repurposing opportunities.
  • Use programmatic access via Python functions to perform queries and extract structured results.

Quick Start

Run a simple query against PrimeKG to fetch a disease context using the Python scripts in scripts/query_primekg.py.

Frequently Asked Questions about primekg

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query a biomedical knowledge graph for drug repurposing and disease context analysis?

Query a biomedical knowledge graph for drug repurposing by loading PrimeKG data from a local CSV file using pandas, then calling Python functions to search nodes and retrieve associated genes, drugs, and phenotypes.

What is network pharmacology data retrieval and how does it connect genes, drugs, and diseases?

Network pharmacology data retrieval connects genes, drugs, and diseases by traversing a multiscale biomedical graph of 129k nodes and 4M edges, allowing researchers to retrieve direct neighbors and evidence across biological entities.

Can I use pandas to load a local CSV file for gene-disease relationship mapping?

Yes, you can use pandas to load a local CSV file for gene-disease relationship mapping, as the workflow relies on a pandas-based Python environment to load the PrimeKG graph data and execute programmatic queries.

What's the best way to identify drug targets using a biomedical graph?

The best way to identify drug targets using a biomedical graph is to query disease contexts by summarizing associated genes and phenotypes, leveraging the integrated network to find potential repurposing opportunities.

Does PrimeKG work with Python scripts for searching disease nodes and getting graph neighbors?

Yes, PrimeKG works with Python scripts by exposing functions in the query workflow for searching disease nodes, getting direct neighbors, and building structured disease contexts from the graph data.

What are the limitations of using a local CSV file for biomedical knowledge graph queries?

Limitations of using a local CSV file for biomedical knowledge graph queries include requiring sufficient local storage and memory to load the entire 129k-node and 4M-edge graph structure into pandas before executing any search or context analysis.