drug-discovery

Analyze bioactive compounds from ChEMBL, PubChem, and OpenFDA for drug discovery.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/AlexKoncept/omnia-hub --skill drug-discovery-alexkoncept
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/AlexKoncept/omnia-hub/tree/main/HERMES/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/AlexKoncept/omnia-hub --skill drug-discovery-alexkoncept

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Pharmaceutical researchers need an integrated, open-source workflow to discover and optimize drug candidates using public data sources, compute drug-like properties, and interpret safety profiles.

Core Features & Use Cases

  • Bioactive compound search and property calculation using ChEMBL, PubChem, and OpenFDA data.
  • Lipinski Ro5, Veber, and ADMET interpretation with lead-optimization recommendations.
  • Use Case: A medicinal chemist evaluates a set of 5-10 candidates and quickly prioritizes molecules with favorable properties and minimal risk.

Quick Start

Analyze a given set of candidate compounds to compute Lipinski metrics, ADMET properties, and lead-optimization recommendations.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I calculate Lipinski Ro5 and ADMET properties for drug candidates?

You can analyze bioactive compounds by querying ChEMBL, PubChem, OpenFDA, and OpenTargets via curl. The workflow computes Lipinski Ro5, Veber rules, and ADMET properties to generate lead-optimization recommendations without requiring authentication.

Do I need API keys to retrieve bioactive compound data from ChEMBL or PubChem?

No API keys are required. The workflow retrieves public bioactive compound data from ChEMBL, PubChem, OpenFDA, and OpenTargets using curl and processes the JSON responses without authentication.

What is the best way to prioritize medicinal chemistry candidates using public data?

Evaluate 5-10 candidate molecules by computing Lipinski metrics, Veber rules, and ADMET properties. Summarize molecular properties and potential interactions to prioritize candidates with favorable drug-likeness and minimal safety risk.

Can I use this workflow for target selection and safety assessment in pharmacology?

Yes, the workflow supports target selection, lead optimization, and safety assessment by retrieving and interpreting molecular properties, drug-likeness metrics, and potential interactions from open-data pharmacology sources.

How do I interpret Veber rules and ADMET properties for lead optimization?

Interpret Veber rules and ADMET properties by analyzing computed molecular data and potential interactions. The workflow generates lead-optimization recommendations based on drug-likeness metrics and safety assessments from public databases.