drug-discovery

Query ChEMBL, PubChem, OpenFDA, and OpenTargets for pharmaceutical research workflows.

1|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/icyzh/hermes-web --skill drug-discovery-icyzh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/icyzh/hermes-web/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/icyzh/hermes-web --skill drug-discovery-icyzh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill addresses the complexity of drug discovery by automating the retrieval of bioactivity data, calculating drug-likeness, and identifying potential safety risks, which traditionally requires manual searching across disparate scientific databases.

Core Features & Use Cases

  • Bioactivity Search: Query ChEMBL for compound activity against specific biological targets.
  • Drug-Likeness Assessment: Evaluate molecules against Lipinski’s Rule of Five and Veber’s rules to predict oral bioavailability.
  • Safety & Interaction Analysis: Look up drug-drug interactions and adverse event reports via OpenFDA.
  • Use Case: A researcher can input a candidate molecule name to instantly receive a report on its molecular weight, LogP, TPSA, and potential metabolic liabilities, streamlining the lead optimization process.

Quick Start

Use the drug-discovery skill to calculate the Lipinski and Veber drug-likeness properties for the molecule aspirin.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I search bioactivity data for a compound against a specific biological target?

To search bioactivity data, you can query the ChEMBL database directly via API to retrieve compound activity measurements against specific biological targets, automating manual cross-database lookups.

How do I calculate drug-likeness and ADMET properties for a candidate molecule?

You can calculate drug-likeness by evaluating molecules against Lipinski's Rule of Five and Veber rules, while ADMET profiling and metabolic liabilities are screened via OpenFDA API queries.

Can I check drug-drug interactions and adverse event reports using OpenFDA?

Yes, you can look up drug-drug interactions and adverse event reports by querying the OpenFDA API, which automates safety analysis and identifies potential clinical pharmacology risks.

Do I need Python 3 and curl to retrieve molecular properties from PubChem?

Yes, standard Python 3 and curl are required dependencies to execute API-based queries for retrieving molecular properties like molecular weight, LogP, and TPSA from PubChem.

What is the best way to automate pharmaceutical research workflows across disparate databases?

Automating pharmaceutical research workflows is best achieved by integrating data from ChEMBL, PubChem, OpenFDA, and OpenTargets to streamline lead optimization and clinical pharmacology analysis.

Why should I not manually search multiple scientific databases for drug discovery?

Manual searching across disparate scientific databases creates complexity and delays; automating bioactivity retrieval and drug-likeness calculation streamlines the lead optimization process.