Dataset Overview
| Property | Value |
|---|---|
| Source ID | valyu/valyu-chembl |
| Size | 2.5M+ compounds |
| Coverage | Bioactive molecules with drug-like properties |
| Updates | Monthly |
| Data Type | Structured and unstructured |
What You Get
- Compound data - Molecular structures, SMILES, InChI keys
- Bioactivity data - IC50, Ki, Kd, EC50 measurements
- Target information - Protein targets and binding data
- Drug-likeness - Lipinski properties, ADMET predictions
- Assay information - Experimental protocols and conditions
Quick Start
Data Categories
| Category | Description | Applications |
|---|---|---|
| Compounds | Small molecules with measured bioactivities | Lead identification |
| Targets | Protein targets with binding data | Target validation |
| Assays | Experimental bioactivity measurements | Activity prediction |
| Drugs | Approved and clinical-phase drugs | Drug repurposing |
Use Cases
- Lead identification - Find compounds with desired activity profiles
- Target validation - Assess druggability of biological targets
- Drug repurposing - Identify new uses for existing compounds
- SAR analysis - Structure-activity relationship studies
- AI model training - Build predictive models for drug discovery

