drug-discovery

Integrates ChEMBL, PubChem, and OpenFDA to rank drug-like candidates and flag liabilities.

Updated May 4, 2026
One-click install
npx skills add https://github.com/Plaidmustache/hermes-nulab --skill drug-discovery-plaidmustache
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/Plaidmustache/hermes-nulab/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/Plaidmustache/hermes-nulab --skill drug-discovery-plaidmustache

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Pharmaceuticals research teams often juggle disparate data sources and manual interpretation workflows to identify bioactive compounds, assess drug-likeness, and interpret ADMET profiles. This Skill unifies ChEMBL searches, OpenFDA interactions, PubChem properties, and OpenTargets insights to streamline medicinal chemistry tasks and accelerate lead optimization.

Core Features & Use Cases

  • Bioactive compound search via ChEMBL to identify targets and activities.
  • Drug-likeness assessment using Ro5, QED, TPSA, and synthetic accessibility to prioritize candidates.
  • Drug interaction checks with OpenFDA labels and literature.
  • ADMET profiling interpretation and lead-optimization recommendations.
  • OpenTargets-backed target-disease associations for hypothesis generation and prioritization.

Quick Start

Analyze a candidate molecule against Ro5, TPSA, ADMET, and propose optimization steps.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I assess drug-likeness and ADMET profiles for candidate molecules?

You assess drug-likeness by evaluating lipophilicity, molecular weight, hydrogen-bond donors/acceptors, TPSA, and synthetic accessibility. This workflow integrates PubChem properties and OpenFDA interactions to rank compounds, flag liabilities, and provide contextual ADMET guidance for lead optimization.

What is the best way to identify bioactive compounds using ChEMBL and OpenTargets?

The best way is integrating ChEMBL target searches to find activities and OpenTargets to back target-disease associations. This unifies medicinal chemistry data sources to streamline hypothesis generation, prioritize drug-like candidates, and accelerate lead optimization.

Can I check drug interactions and adverse events using OpenFDA data?

Yes, you can check drug interactions using OpenFDA labels and literature. The workflow integrates OpenFDA interaction data with ChEMBL bioactivity and PubChem properties to provide comprehensive ADMET profiling and actionable lead-optimization recommendations.

How do I prioritize lead compounds based on Ro5 and synthetic accessibility?

Prioritize lead compounds by assessing Rule of Five compliance, QED, TPSA, and synthetic accessibility alongside ADMET profiles. The workflow ranks drug-like candidates by integrating these molecular properties with ChEMBL bioactivity and OpenTargets disease associations.

Does this drug discovery workflow require external API keys or database subscriptions?

No external dependencies are required. The workflow integrates public data sources including ChEMBL, PubChem, OpenFDA, and OpenTargets without needing API keys, allowing pharmaceutical research teams to streamline medicinal chemistry tasks immediately.

What limitations exist when integrating ChEMBL and OpenFDA for pharmacology research?

Limitations include reliance on publicly available data coverage in ChEMBL, PubChem, OpenFDA, and OpenTargets databases. Interpretation workflows depend on existing literature and labels, meaning novel compounds or targets with sparse data may yield incomplete ADMET profiles and disease associations.