drug-discovery

Retrieve bioactivity, estimate drug-likeness, and summarize safety signals from public biomedical APIs.

Updated May 26, 2026
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill drug-discovery-ruiyangruiyi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill drug-discovery-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It streamlines early-stage pharmaceutical research by helping you quickly find bioactive compounds, estimate drug-likeness, and interpret interaction and safety signals from public biomedical databases.

Core Features & Use Cases

  • Bioactive compound search (ChEMBL): Search targets and retrieve activities to identify candidate molecules and their potency (e.g., pChEMBL filtering).
  • Drug-likeness profiling: Compute Lipinski Rule of Five and Veber oral bioavailability heuristics using PubChem properties (MW, LogP, HBD/HBA, TPSA, rotatable bonds).
  • Interaction & safety lookups (OpenFDA): Pull reported drug-drug interaction information and adverse event mentions for a given drug name.
  • Additional context (OpenTargets): Query gene/target associations with diseases via a GraphQL endpoint for target-disease hypothesis building.
  • Use Case: You’re evaluating a new lead for medicinal chemistry optimization and want a fast shortlist by potency, basic oral-liability heuristics, and a first-pass interaction/safety signal.

Quick Start

Use the drug-discovery skill to analyze a candidate by searching ChEMBL for a target, running Ro5/Veber heuristics on a molecule name, and then checking OpenFDA for interaction and adverse-event signals for a drug name.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I check drug-likeness and ADMET properties for a candidate molecule?

To check drug-likeness and ADMET properties, the skill calculates Lipinski Rule of Five and Veber oral bioavailability heuristics using PubChem data, and retrieves adverse event signals from OpenFDA for early triage.

How do I retrieve bioactivity data for a specific pharmacological target?

To retrieve bioactivity data, you can query the ChEMBL API via this skill to search targets, identify candidate molecules, and filter activity results by potency metrics like pChEMBL values.

What is the best way to find drug-drug interaction and adverse event signals?

The best way to find drug-drug interaction and adverse event signals is to query the OpenFDA API, which pulls reported interaction information and adverse event mentions for a specified drug name.

Can I explore target-disease associations for lead optimization planning?

Yes, you can explore target-disease associations for lead optimization by querying the OpenTargets GraphQL endpoint to build target-disease hypotheses and support medicinal chemistry triage.

Do I need API keys to query ChEMBL, PubChem, and OpenFDA for medicinal chemistry triage?

The skill executes API-driven workflows for ChEMBL, PubChem, OpenFDA, and OpenTargets to perform medicinal chemistry triage. It requires no local data files, relying entirely on public biomedical database queries.