chembl-database

Retrieve bioactive molecule, target, and activity data from ChEMBL.

15|2|Updated Dec 17, 2025
One-click install
npx skills add https://github.com/rubensliv/k-dense-ai --skill chembl-database-rubensliv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chembl-database
Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/chembl-database
Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill chembl-database-rubensliv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chembl_webresource_client, pandas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Researchers need fast, programmatic access to ChEMBL's bioactive molecule data to perform compound discovery, target profiling, and SAR analysis without manual data wrangling.

Core Features & Use Cases

  • Molecule queries by ChEMBL ID, name, or properties to retrieve structures and properties
  • Target queries to fetch proteins, target types, and associated data
  • Bioactivity data retrieval (IC50, Ki, EC50) with units and pchembl values
  • Structure-based searches including similarity and substructure queries
  • Data export and analysis support (pandas-ready formats)
  • End-to-end workflows demonstrated by example scripts
  • Use case: identify potent EGFR inhibitors and retrieve related bioactivities

Quick Start

Run example_queries.py to perform common ChEMBL queries and view molecule, target, and bioactivity results.

Frequently Asked Questions about chembl-database

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

FAQPage Schema
How do I retrieve ChEMBL bioactivity data for drug discovery programmatically?

Retrieve ChEMBL bioactivity data by querying molecule, target, and activity endpoints for IC50, Ki, and EC50 values. The Skill returns results in JSON or pandas-ready formats, supporting compound discovery and SAR analysis without manual data wrangling.

What is the best way to search for bioactive molecules in ChEMBL by similarity or substructure?

Search bioactive molecules using structure-based queries for similarity and substructure. Retrieve molecule structures and properties by querying ChEMBL IDs, names, or specific molecular properties directly through the provided scripts.

Can I use pandas to analyze ChEMBL bioassay and target profiling results?

Yes, you can use pandas to analyze ChEMBL bioassay results because the Skill exports data in pandas-ready formats. It supports target profiling by fetching proteins, target types, and associated bioactivity data like pchembl values for downstream analysis.

Do I need chembl_webresource_client to perform molecule searches and target queries?

Yes, the chembl_webresource_client package is required to perform molecule searches and target queries. It enables programmatic access to ChEMBL endpoints for retrieving bioactive molecule data and target information.

How do I identify potent EGFR inhibitors and retrieve related bioactivities from ChEMBL?

Identify potent EGFR inhibitors by running the provided example_queries.py script to execute common ChEMBL queries. This demonstrates an end-to-end workflow to fetch molecule structures, target profiles, and related bioactivity measurements.