chembl-database

Query ChEMBL bioactive molecules and bioactivity data via Python client.

16|7|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/jackspace/ClaudeSkillz --skill chembl-database
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chembl-database
Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-db-chembl-database
Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill chembl-database

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides programmatic access to the ChEMBL database to query bioactive molecules, targets, and bioactivity data for medicinal chemistry and drug discovery.

Core Features & Use Cases

  • Molecule queries by ID, name, and property filters
  • Target queries and bioactivity data retrieval
  • Structure-based searches: similarity and substructure
  • Data export to pandas DataFrames for analysis

Quick Start

Install the Python client (chembl_webresource_client), load molecules with molecule.filter(), and explore bioactivities.

Frequently Asked Questions about chembl-database

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

FAQPage Schema
How do I query bioactive molecules from ChEMBL for drug discovery?

Query bioactive molecules using the chembl_webresource_client Python library with molecule.filter() to search by ID, name, or property filters, then retrieve bioactivity data like IC50 and Ki values for your compounds of interest.

Can I search ChEMBL by molecular structure or similarity?

Yes, ChEMBL supports structure-based searches including similarity matching and substructure searches through the webresource client, enabling you to find molecules with comparable chemical properties or scaffolds.

How do I export ChEMBL bioactivity data to pandas for analysis?

The chembl_webresource_client retrieves molecule, target, and activity data that can be exported directly to pandas DataFrames for downstream statistical analysis, SAR evaluation, and medicinal chemistry workflows.

What's the best way to discover inhibitors and perform SAR analysis?

Query inhibitor bioactivity data from ChEMBL targets using the Python client, filter by potency metrics, and export results to pandas to conduct structure-activity relationship analyses across your compound series.

Do I need to set up caching for repeated ChEMBL queries?

The chembl_webresource_client supports lazy evaluation and caching to optimize repeated queries, reducing API calls and improving performance when working with large bioactivity datasets.