drug-discovery

Search ChEMBL for bioactive compounds and compute drug-likeness metrics.

Updated May 11, 2026
One-click install
npx skills add https://github.com/jason660519/Project-Manager --skill drug-discovery-jason660519
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/jason660519/Project-Manager/tree/main/hermes-agent/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/jason660519/Project-Manager --skill drug-discovery-jason660519

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Pharmaceutical scientists often need to rapidly identify bioactive compounds, assess drug-likeness, and interpret ADMET data from public databases. This skill consolidates ChEMBL searches, Lipinski Ro5/QED/TPSA calculations, OpenFDA interactions, and lead-optimization guidance into a cohesive workflow, reducing manual data gathering and interpretation time.

Core Features & Use Cases

  • Bioactive compound search on ChEMBL by target, activity, or molecule name.
  • Drug-likeness calculations (Ro5, QED, TPSA, synthetic accessibility) and property summaries.
  • Drug interaction lookups via OpenFDA and OpenTargets context for target-disease associations.
  • ADMET interpretation and lead-optimization suggestions for medicinal chemistry questions.
  • Open-science-friendly pipelines suitable for medicinal chemistry research and collaboration.

Quick Start

Ask me to analyze a compound or target by name, and I will fetch public data, compute drug-likeness metrics, and summarize ADMET insights.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I calculate drug-likeness properties like Ro5 and QED for a compound?

To calculate drug-likeness, provide a compound or target name to fetch public data and compute standardized metrics like Ro5, QED, TPSA, and synthetic accessibility. The workflow extracts compound information from open sources and returns actionable property summaries.

How can I search ChEMBL for bioactive compounds by target or molecule name?

You can search ChEMBL for bioactive compounds by asking the workflow to analyze a specific target, activity, or molecule name. It queries open data sources to identify and interpret bioactive compounds, returning results with citations for medicinal chemistry research.

How do I interpret ADMET data and check drug interactions for lead optimization?

Interpreting ADMET data and checking drug interactions involves querying OpenFDA for interaction lookups and OpenTargets for target-disease associations. The workflow analyzes this public data to provide ADMET interpretation and lead-optimization suggestions.

Can I use open data sources like PubChem and OpenFDA for pharmaceutical research without paid APIs?

Yes, you can use open data sources like PubChem, ChEMBL, OpenFDA, and OpenTargets for pharmaceutical research without paid APIs. The workflow integrates multiple free APIs to compute standardized metrics and return outputs with citations and safety notes.

What is the best way to find target-disease associations using open data?

Finding target-disease associations is best done by querying OpenTargets context within a consolidated workflow. This approach integrates free APIs to identify bioactive compounds and provide ADMET interpretation and lead-optimization guidance.

Are there limitations to using open data workflows for drug discovery?

Limitations of using open data workflows include reliance on public database coverage and the need for safety note interpretation. The workflow returns actionable outputs with citations, but users must manually verify lead-optimization suggestions for real-world pharmaceutical research.