ChEMBL Bioactivity Intelligence Normalizer

Extract and normalize drug-target bioactivity data from ChEMBL, the world's largest curated database of drug-like molecules and their bioactivities.

Features

• Drug/Target Search: Search by drug name (e.g. 'aspirin', 'imatinib') or target protein (e.g. 'EGFR', 'BRD4')
• Activity Type Filtering: Filter by IC50, EC50, Ki, Kd, AC50 values
• Potency Range: Filter by activity value in nanomolar (nM) units
• Normalized Output: Clean, structured data with standardized drug names, target names, and activity types
• Rich Metadata: Includes assay type, organism, confidence scores, and literature references

Use Cases

• Pharmaceutical R&D: Identify potent compounds for specific targets
• Drug Repurposing: Find existing drugs with activity against new targets
• Competitive Intelligence: Analyze bioactivity profiles of competitor compounds
• Academic Research: Extract training data for ML models predicting drug-target interactions
• CRO Services: Screen compound libraries for client projects

Output Format

Each result includes:

• moleculeName: Normalized drug/compound name
• moleculeChEMBLId: ChEMBL identifier
• targetName: Normalized target protein name
• targetChEMBLId: ChEMBL target identifier
• targetOrganism: Source organism (e.g. 'Homo sapiens')
• activityType: IC50, EC50, Ki, Kd, etc.
• activityValue: Numeric value in nM
• activityUnits: Units (typically 'nM')
• assayType: Binding (B), Functional (F), ADMET (A), etc.
• confidenceScore: Target confidence (1-5)
• pubmedId: Literature reference (if available)
• relation: Activity relationship (=, <, >, ~)

Pricing

$2.00 per 1,000 bioactivity records returned.

Example Input

{
  "searchQuery": "EGFR",
  "searchType": "target",
  "activityType": "IC50",
  "maxActivityValue": 100,
  "maxResults": 50
}

This returns the 50 most potent IC50 values (< 100 nM) for compounds targeting EGFR.

Data Source

All data sourced from ChEMBL (EMBL-EBI), licensed under CC BY-SA 3.0.