lifesciences-graph-builder

Resolve life-sciences entities and connections into validated knowledge graphs.

Updated Feb 5, 2026
One-click install
npx skills add https://github.com/donbr/lifesciences-deepagents --skill lifesciences-graph-builder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lifesciences-graph-builder
Source: https://github.com/donbr/lifesciences-deepagents/tree/main/.claude/skills/lifesciences-graph-builder
Command: npx skills add https://github.com/donbr/lifesciences-deepagents --skill lifesciences-graph-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill solves the challenge of building validated life-sciences knowledge graphs by orchestrating multi-API entity resolution and edge discovery to produce provenance-traced results.

Core Features & Use Cases

  • End-to-end graph construction across genes, proteins, pathways, drugs, and diseases using the Fuzzy-to-Fact protocol.
  • Provenance-rich results with canonical identifiers and source-trusted data from MCP tools and curl-based edge discovery.
  • Use Case: Build drug-target networks for repurposing and pathway analyses to inform experimental design.

Quick Start

Provide a query (e.g., TP53) and generate a provenance-rich knowledge graph linking genes, proteins, pathways, drugs, and diseases using MCP tools.

Frequently Asked Questions about lifesciences-graph-builder

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

FAQPage Schema
How do I build a knowledge graph from life-sciences APIs for drug target discovery?

Build a validated life-sciences knowledge graph by orchestrating multi-API entity resolution and edge discovery across genes, proteins, pathways, drugs, and diseases using a structured LOCATE-RETRIEVE-EXPAND-TRAVERSE-VALIDATE-PERSIST workflow.

What is the best way to map biological pathways with provenance tracing?

Map biological pathways with provenance tracing by using Fuzzy-to-Fact protocols that resolve canonical identifiers and source-trusted data from MCP tools and curl-based edge discovery, ensuring validated results.

Can I use MCP tools and curl to resolve life-sciences entity connections?

Yes, you can resolve life-sciences entity connections using MCP tools and curl for edge discovery, which retrieve source-trusted data to produce provenance-rich knowledge graphs linking genes, proteins, and diseases.

How do I persist a drug repurposing knowledge graph with provenance using Graphiti?

Persist a drug repurposing knowledge graph with provenance by enforcing the VALIDATE and PERSIST stages of the workflow through Graphiti, which stores the canonical identifiers and traced source data.

What life-sciences entities can I connect when building a drug repurposing network?

You can connect genes, proteins, pathways, drugs, and diseases when building a drug repurposing network, generating provenance-rich results with canonical identifiers across these biological entities.

Does building a life-sciences knowledge graph require external API dependencies?

No external dependencies are required to run the Skill itself, but it orchestrates external life-sciences APIs via MCP tools and curl to retrieve source-trusted data for entity resolution and edge discovery.