primekg

Query PrimeKG to reveal relationships among genes, drugs, diseases, and phenotypes.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill primekg-scimate-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: primekg
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/primekg
Command: npx skills add https://github.com/SciMate-AI/scicli --skill primekg-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PrimeKG is a biomedical knowledge graph that enables programmatic access to reveal relationships among genes, drugs, diseases, and phenotypes, accelerating discovery and hypothesis generation.

Core Features & Use Cases

  • Search for genes, drugs, diseases, and phenotypes by name.
  • Retrieve direct neighbors and associated evidence to build contextual narratives.
  • Analyze local disease context and explore potential drug repurposing opportunities.

Quick Start

Search for Alzheimer's disease and retrieve its direct neighbors, including 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 biomedical knowledge graph for disease context and drug repurposing?

Use PrimeKG to search for genes, drugs, diseases, and phenotypes by name, retrieve direct neighbors and associated evidence to build contextual narratives, and explore potential drug repurposing opportunities.

How do I find direct neighbors of a gene or disease in a biomedical knowledge graph?

Use the get_neighbors function to retrieve direct neighbors of a gene or disease from the CSV-based PrimeKG dataset. This reveals connected drugs, diseases, and phenotypes for multiscale biological analysis.

Can I use pandas to load and analyze biomedical knowledge graph datasets?

Yes, you can use pandas to load and analyze the CSV-based PrimeKG dataset. This enables programmatic querying of relationships among genes, drugs, diseases, and phenotypes for multiscale biomedical insights.

What is multiscale biomedical analysis and how does it relate to knowledge discovery?

Multiscale biomedical analysis examines relationships among genes, drugs, diseases, and phenotypes across clinical and genomic contexts. It accelerates knowledge discovery and hypothesis generation by revealing connections in a biomedical knowledge graph.

Does PrimeKG work with pandas for searching nodes in a biomedical knowledge graph?

Yes, PrimeKG works with pandas to search nodes in a biomedical knowledge graph. It exposes the search_nodes function to operate on a CSV-based dataset, enabling programmatic access to genes, drugs, diseases, and phenotypes.

What are the limitations of using a CSV-based knowledge graph for genomic context analysis?

A limitation of using a CSV-based knowledge graph for genomic context analysis is that the dataset is loaded via pandas, which may constrain scalability for extremely large genomic datasets. It is suited for local disease context analysis and drug repurposing.