ChEMBL Database

Overview

ChEMBL is a manually curated database of bioactive molecules maintained by the European Bioinformatics Institute (EBI), containing over 2 million compounds, 19 million bioactivity measurements, 13,000+ drug targets, and data on approved drugs and clinical candidates. Access and query this data programmatically using the ChEMBL Python client for drug discovery and medicinal chemistry research.

When to Use This Skill

This skill should be used when:

• Compound searches: Finding molecules by name, structure, or properties
• Target information: Retrieving data about proteins, enzymes, or biological targets
• Bioactivity data: Querying IC50, Ki, EC50, or other activity measurements
• Drug information: Looking up approved drugs, mechanisms, or indications
• Structure searches: Performing similarity or substructure searches
• Cheminformatics: Analyzing molecular properties and drug-likeness
• Target-ligand relationships: Exploring compound-target interactions
• Drug discovery: Identifying inhibitors, agonists, or bioactive molecules

Installation and Setup

Python Client

The ChEMBL Python client is required for programmatic access:

uv pip install chembl_webresource_client

Basic Usage Pattern

from chembl_webresource_client.new_client import new_client

# Access different endpoints
molecule = new_client.molecule
target = new_client.target
activity = new_client.activity
drug = new_client.drug

Core Capabilities

1. Molecule Queries

Retrieve by ChEMBL ID:

molecule = new_client.molecule
aspirin = molecule.get('CHEMBL25')

Search by name:

results = molecule.filter(pref_name__icontains='aspirin')

Filter by properties:

# Find small molecules (MW <= 500) with favorable LogP
results = molecule.filter(
    molecule_properties__mw_freebase__lte=500,
    molecule_properties__alogp__lte=5
)

2. Target Queries

Retrieve target information:

target = new_client.target
egfr = target.get('CHEMBL203')

Search for specific target types:

# Find all kinase targets
kinases = target.filter(
    target_type='SINGLE PROTEIN',
    pref_name__icontains='kinase'
)

3. Bioactivity Data

Query activities for a target:

activity = new_client.activity
# Find potent EGFR inhibitors
results = activity.filter(
    target_chembl_id='CHEMBL203',
    standard_type='IC50',
    standard_value__lte=100,
    standard_units='nM'
)

Get all activities for a compound:

compound_activities = activity.filter(
    molecule_chembl_id='CHEMBL25',
    pchembl_value__isnull=False
)

4. Structure-Based Searches

Similarity search:

similarity = new_client.similarity
# Find compounds similar to aspirin
similar = similarity.filter(
    smiles='CC(=O)Oc1ccccc1C(=O)O',
    similarity=85  # 85% similarity threshold
)

Substructure search:

substructure = new_client.substructure
# Find compounds containing benzene ring
results = substructure.filter(smiles='c1ccccc1')

5. Drug Information

Retrieve drug data:

drug = new_client.drug
drug_info = drug.get('CHEMBL25')

Get mechanisms of action:

mechanism = new_client.mechanism
mechanisms = mechanism.filter(molecule_chembl_id='CHEMBL25')

Query drug indications:

drug_indication = new_client.drug_indication
indications = drug_indication.filter(molecule_chembl_id='CHEMBL25')

Query Workflow

Workflow 1: Finding Inhibitors for a Target

1. Identify the target by searching by name:

   targets = new_client.target.filter(pref_name__icontains='EGFR')
   target_id = targets[0]['target_chembl_id']
   

2. Query bioactivity data for that target:

   activities = new_client.activity.filter(
       target_chembl_id=target_id,
       standard_type='IC50',
       standard_value__lte=100
   )
   

3. Extract compound IDs and retrieve details:

   compound_ids = [act['molecule_chembl_id'] for act in activities]
   compounds = [new_client.molecule.get(cid) for cid in compound_ids]
   

Workflow 2: Analyzing a Known Drug

1. Get drug information:

   drug_info = new_client.drug.get('CHEMBL1234')
   

2. Retrieve mechanisms:

   mechanisms = new_client.mechanism.filter(molecule_chembl_id='CHEMBL1234')
   

3. Find all bioactivities:

   activities = new_client.activity.filter(molecule_chembl_id='CHEMBL1234')
   

Workflow 3: Structure-Activity Relationship (SAR) Study

1. Find similar compounds:

   similar = new_client.similarity.filter(smiles='query_smiles', similarity=80)
   

2. Get activities for each compound:

   for compound in similar:
       activities = new_client.activity.filter(
           molecule_chembl_id=compound['molecule_chembl_id']
       )
   

3. Analyze property-activity relationships using molecular properties from results.

Filter Operators

ChEMBL supports Django-style query filters:

• __exact - Exact match
• __iexact - Case-insensitive exact match
• __contains / __icontains - Substring matching
• __startswith / __endswith - Prefix/suffix matching
• __gt, __gte, __lt, __lte - Numeric comparisons
• __range - Value in range
• __in - Value in list
• __isnull - Null/not null check

Data Export and Analysis

Convert results to pandas DataFrame for analysis:

import pandas as pd

activities = new_client.activity.filter(target_chembl_id='CHEMBL203')
df = pd.DataFrame(list(activities))

# Analyze results
print(df['standard_value'].describe())
print(df.groupby('standard_type').size())

Performance Optimization

Caching

The client automatically caches results for 24 hours. Configure caching:

from chembl_webresource_client.settings import Settings

# Disable caching
Settings.Instance().CACHING = False

# Adjust cache expiration (seconds)
Settings.Instance().CACHE_EXPIRE = 86400

Lazy Evaluation

Queries execute only when data is accessed. Convert to list to force execution:

# Query is not executed yet
results = molecule.filter(pref_name__icontains='aspirin')

# Force execution
results_list = list(results)

Pagination

Results are paginated automatically. Iterate through all results:

for activity in new_client.activity.filter(target_chembl_id='CHEMBL203'):
    # Process each activity
    print(activity['molecule_chembl_id'])

Common Use Cases

Find Kinase Inhibitors

# Identify kinase targets
kinases 
how to use chembl-database
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use chembl-database on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add chembl-database
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/davila7/claude-code-templates --skill chembl-databasecopy
The skills CLI fetches chembl-database from GitHub repository davila7/claude-code-templates and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/chembl-database
Reload or restart Cursor to activate chembl-database. Access the skill through slash commands (e.g., /chembl-database) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?