drug-discovery

Retrieve and synthesize drug-discovery data from ChEMBL, PubChem, OpenFDA, and OpenTargets.

2|Updated Apr 25, 2026
One-click install
npx skills add https://github.com/AlexiosBluffMara/mercury --skill drug-discovery-alexiosbluffmara
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/AlexiosBluffMara/mercury/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/AlexiosBluffMara/mercury --skill drug-discovery-alexiosbluffmara

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Pharmaceutical and medicinal chemistry research often requires gathering diverse public data (bioactivity, drug-likeness, safety signals) from multiple sources. This skill automates data retrieval, interpretation, and cross-referencing to streamline lead optimization and literature review.

Core Features & Use Cases

  • Bioactive compound search via ChEMBL to retrieve targets, activities, and top molecules for a chosen target.
  • Drug-likeness assessment using Lipinski Ro5 and Veber rules through PubChem property data, with quick summaries and risk flags.
  • Safety and interactions lookup via OpenFDA and OpenTargets literature to inform risk assessment and decision making.
  • PubChem compound search to obtain SMILES, InChIKey, and key properties for downstream modeling.
  • Use Case: Compile a candidate set from a ChEMBL target, assess drug-likeness, and quickly surface safety considerations for lead selection.

Quick Start

Query the system to search ChEMBL for a target like EGFR, then retrieve top compounds with high pChEMBL and report key properties.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I retrieve bioactive compounds and drug-likeness data for a specific target?

To retrieve bioactive compounds and drug-likeness data, search ChEMBL for targets and activities, then use PubChem properties to assess Lipinski Ro5 and Veber rules with automated risk flags.

What is the best way to check drug safety signals and interactions from public databases?

Checking drug safety signals and interactions is done by querying OpenFDA and OpenTargets literature data to surface risk considerations and inform safety assessment decisions.

Can I get SMILES and InChIKey identifiers for compounds to use in downstream modeling?

Yes, you can get SMILES, InChIKey, and key properties for downstream molecular modeling by performing a compound search directly through the PubChem data retrieval interface.

Do I need external dependencies or specialized software to run drug discovery data retrieval?

No specialized software is needed; drug discovery data retrieval requires only minimal external dependencies like curl and python3 to fetch, compute, and summarize key metrics.

How does cross-referencing bioactivity and safety data streamline lead optimization?

Cross-referencing bioactivity and safety data streamlines lead optimization by compiling a candidate set from ChEMBL, assessing drug-likeness, and quickly surfacing safety considerations for selection.

What limitations should I expect when using public sources for pharmacology data retrieval?

Limitations of public source pharmacology data retrieval include dependency on the availability and coverage of ChEMBL, PubChem, OpenFDA, and OpenTargets for accurate target profiling and safety checks.