chembl-database

Query ChEMBL bioactive molecules and activity data programmatically.

94|11|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/swaruplab/operon --skill chembl-database-swaruplab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chembl-database
Source: https://github.com/swaruplab/operon/tree/main/src-tauri/protocols/chembl-database
Command: npx skills add https://github.com/swaruplab/operon --skill chembl-database-swaruplab

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Retrieve and interpret bioactive molecule data from the ChEMBL database to support medicinal chemistry and drug-discovery research.

Core Features & Use Cases

  • Molecule queries: fetch compounds by ChEMBL ID, synonyms, or properties.
  • Target and mechanism data: access target information, mechanisms of action, and related drugs.
  • Bioactivity exploration: filter activities by type (IC50, Ki, EC50), value, and units to identify potent compounds.
  • Structure-based searches: perform similarity and substructure queries to discover SAR trends.
  • Data extraction and export: convert results into structured formats for downstream analysis and reporting.

Quick Start

Install the chembl_webresource_client package and run a simple lookup, for example retrieving a molecule by its CHEMBL ID.

Frequently Asked Questions about chembl-database

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

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

Retrieve ChEMBL molecule and target data programmatically to support drug discovery workflows. The Skill provides endpoints for molecule lookups, target profiling, and bioactivity filtering to extract structured data for downstream analysis.

Can I perform structure-based searches to explore SAR trends in ChEMBL?

Yes, you can perform similarity and substructure queries against the ChEMBL database. These structure-based searches help you discover structure-activity relationship (SAR) trends by fetching compounds with similar chemical scaffolds.

How do I filter bioactivity data by type and value to identify potent compounds?

Filter bioactivity data by applying Django-style filters to specify activity types such as IC50, Ki, or EC50. You can further refine results by setting exact value ranges and units to isolate the most potent compounds.

Does this approach require the chembl_webresource_client package to fetch molecule data?

Yes, fetching molecule data requires the chembl_webresource_client package. The Skill depends on this client to interface with the ChEMBL database, alongside pandas for converting the retrieved query results into structured formats.

What's the best way to extract target information and mechanisms of action from ChEMBL?

The best way to extract target information and mechanisms of action is by using the Skill's target and drug data endpoints. These endpoints provide direct access to target profiles and related drug mechanisms for applied medicinal chemistry.

How do I export extracted ChEMBL molecule and activity data for downstream analysis?

Export extracted ChEMBL molecule and activity data by converting query results into structured formats using pandas. This data extraction step ensures the retrieved bioactivity and target information is ready for downstream analysis and reporting.