primekg

Search PrimeKG knowledge graph for genes, drugs, diseases, and phenotypes.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/Hung-3008/agusta --skill primekg-hung-3008
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: primekg
Source: https://github.com/Hung-3008/agusta/tree/main/.agents/skills/primekg
Command: npx skills add https://github.com/Hung-3008/agusta --skill primekg-hung-3008

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PrimeKG is a precision medicine knowledge graph that integrates data from over 20 primary databases and high-quality literature into a single resource, enabling researchers to search for nodes, retrieve direct neighbors, and analyze disease context.

Core Features & Use Cases

  • Search for nodes (genes, drugs, diseases, phenotypes)
  • Retrieve direct neighbors with evidence
  • Analyze local disease context (related genes, drugs, phenotypes)
  • Identify drug-disease paths for potential repurposing

Quick Start

Query a disease by name to retrieve its context and related genes, drugs, and phenotypes.

Frequently Asked Questions about primekg

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

FAQPage Schema
How do I query a knowledge graph for disease context and related drugs?

You can query a knowledge graph by disease name using Python scripts to retrieve related genes, drugs, and phenotypes. This requires a local PrimeKG CSV data file to search nodes and analyze local disease context.

What is multiscale biological data retrieval from a knowledge graph?

Multiscale biological data retrieval searches an integrated knowledge graph containing genes, drugs, diseases, and phenotypes from over 20 databases. It enables searching nodes, retrieving direct neighbors with evidence, and identifying drug-disease paths for repurposing.

Can I identify drug-disease paths for drug repurposing using a biological knowledge graph?

Yes, you can identify drug-disease paths for repurposing by analyzing local disease context within the knowledge graph. The Skill retrieves direct neighbors with evidence, supporting network pharmacology workflows and target identification.

Do I need a local CSV data file to search for genes and phenotypes in PrimeKG?

Yes, a local PrimeKG CSV data file is required to search for genes and phenotypes. The Skill uses Python scripts and pandas to query this local file for node searches, neighbor retrieval, and disease-context analysis.

What are the limitations of using pandas for knowledge graph queries in drug discovery?

Using pandas limits you to searching a local CSV data file rather than a live graph database. It performs search and neighbor retrieval suitable for knowledge-based drug discovery but may face scale constraints with very large graph traversals.

How do I retrieve direct neighbors with evidence in a biological knowledge graph?

You retrieve direct neighbors with evidence by executing Python scripts against a local PrimeKG CSV file. These scripts search the knowledge graph to extract connected genes, drugs, and phenotypes, providing the evidentiary context needed for network pharmacology workflows.