Tooluniverse Network Pharmacology

This is a systems pharmacology workflow that builds compound-target-disease networks to find drug repurposing candidates and analyze multi-target effects. It pulls data from STRING, ChEMBL, DGIdb, OpenTargets, and other databases, then runs Python to compute network proximity scores, identify hub genes, and rank repurposing opportunities on a 0-100 scale weighted toward clinical evidence and network distance. The framework explicitly distinguishes desired polypharmacology from off-target promiscuity, which is useful when you need to argue whether hitting multiple targets is therapeutic or just messy. Best for mechanistic hypotheses about existing drugs in new indications. If you just want repurposing candidates without the network math, there's a simpler skill for that.

skills.sh installs: 434
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-network-pharmacology --agent claude-code

Installs into .claude/skills of the current project.

Files

COMPUTE, DON'T DESCRIBE

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Network Pharmacology Pipeline

Construct and analyze compound-target-disease (C-T-D) networks to identify drug repurposing opportunities, understand polypharmacology, and predict drug mechanisms using systems pharmacology approaches.

LOOK UP DON'T GUESS - Retrieve actual target lists, network data, and clinical evidence from tools. Do not infer network relationships from drug class alone.

IMPORTANT: Always use English terms in tool calls, even if the user writes in another language. Respond in the user's language.