ChEMBL Drug and Compound Lookup
Query the ChEMBL database for drug-like molecules, drug targets, and bioactivity data. ChEMBL is EBI's open database of drug discovery and medicinal chemistry.
IMPORTANT: Query must be a specific drug or compound name
ChEMBL searches by molecule name. Always use a specific drug name or compound identifier (e.g. sotorasib, ibrutinib, CHEMBL1873475). Do NOT pass topic phrases like "kinase inhibitor resistance" — these will return garbage results. If the topic mentions multiple drugs, pick the most specific one.
When NOT to Use This Skill
Do NOT use ChEMBL when the query is any of the following — it will return large biologics, cell therapy entries, or protein records with MW=?, logP=?, phase=-1:
- Biological therapies: cell therapies, stem cells, antibodies, CAR-T, biologics (e.g. "allogeneic mesenchymal stem cells", "anti-PD1 antibody")
- Mechanism or concept phrases: "proximity-induced degradation", "PROTAC linker", "covalent warhead", "undruggable target"
- Disease names without a specific drug: "Alzheimer's disease", "pancreatic cancer", "KRAS oncogenesis"
- Pathway or process terms: "mTOR signaling", "ubiquitin-proteasome pathway", "kinase cascade"
Correct workflow for mechanism-based topics (e.g. PROTAC, degrader, proximity):
- Search PubMed first with the mechanism query
- Extract specific small-molecule compound names from the papers (e.g. "ARV-110", "dBET6", "MZ1")
- Then query ChEMBL with those specific names
Overview
- Search molecules by name or ChEMBL ID
- Retrieve molecular properties, SMILES, drug indications
- Find targets and bioactivity (IC50, Ki, etc.)
- No API key required
Usage
Search by compound or drug name
python3 {baseDir}/scripts/chembl_search.py --query "aspirin"
Get molecule by ChEMBL ID
python3 {baseDir}/scripts/chembl_search.py --chembl-id CHEMBL25
Detailed output
python3 {baseDir}/scripts/chembl_search.py --query "imatinib" --format detailed
Limit search results
python3 {baseDir}/scripts/chembl_search.py --query "kinase inhibitor" --max-results 5
Parameters
| Parameter |
Description |
Default |
--query |
Compound or drug name or search term |
- |
--chembl-id |
ChEMBL molecule ID (e.g. CHEMBL25) |
- |
--max-results |
Max results for search |
10 |
--format |
Output: summary, detailed, json |
summary |
Output
- Summary: ChEMBL ID, pref_name, molecular formula, MW, SMILES, max_phase
- Detailed: Adds drug type, first approval, indications, targets
- JSON: Full API response
Notes
- ChEMBL IDs look like CHEMBL25, CHEMBL1234567
- Use --query for name or text search
- Use --chembl-id when you know the exact molecule ID
1---2name: chembl3description: Small-molecule drug lookup by exact drug name or ChEMBL ID. Query MUST be a single drug name or ID — 1 to 3 words maximum. Valid examples: 'sotorasib', 'imatinib', 'ibrutinib', 'CHEMBL25', 'AMG 510'. If the topic is 'sotorasib KRAS G12C', the correct query is 'sotorasib'. If the topic is 'BTK inhibitors in CLL', search PubMed first to get a specific drug name, then query ChEMBL with that name. Strip protein names, mutation labels, and mechanism words — pass only the compound name.4---56# ChEMBL Drug and Compound Lookup78Query the ChEMBL database for drug-like molecules, drug targets, and bioactivity data. ChEMBL is EBI's open database of drug discovery and medicinal chemistry.910## IMPORTANT: Query must be a specific drug or compound name1112ChEMBL searches by molecule name. **Always use a specific drug name or compound identifier** (e.g. `sotorasib`, `ibrutinib`, `CHEMBL1873475`). Do NOT pass topic phrases like "kinase inhibitor resistance" — these will return garbage results. If the topic mentions multiple drugs, pick the most specific one.1314## When NOT to Use This Skill1516Do NOT use ChEMBL when the query is any of the following — it will return large biologics, cell therapy entries, or protein records with `MW=?`, `logP=?`, `phase=-1`:1718- **Biological therapies**: cell therapies, stem cells, antibodies, CAR-T, biologics (e.g. "allogeneic mesenchymal stem cells", "anti-PD1 antibody")19- **Mechanism or concept phrases**: "proximity-induced degradation", "PROTAC linker", "covalent warhead", "undruggable target"20- **Disease names without a specific drug**: "Alzheimer's disease", "pancreatic cancer", "KRAS oncogenesis"21- **Pathway or process terms**: "mTOR signaling", "ubiquitin-proteasome pathway", "kinase cascade"2223**Correct workflow for mechanism-based topics (e.g. PROTAC, degrader, proximity):**241. Search PubMed first with the mechanism query252. Extract specific small-molecule compound names from the papers (e.g. "ARV-110", "dBET6", "MZ1")263. Then query ChEMBL with those specific names2728## Overview2930- Search molecules by name or ChEMBL ID31- Retrieve molecular properties, SMILES, drug indications32- Find targets and bioactivity (IC50, Ki, etc.)33- No API key required3435## Usage3637### Search by compound or drug name38```bash39python3 {baseDir}/scripts/chembl_search.py --query "aspirin"40```4142### Get molecule by ChEMBL ID43```bash44python3 {baseDir}/scripts/chembl_search.py --chembl-id CHEMBL2545```4647### Detailed output48```bash49python3 {baseDir}/scripts/chembl_search.py --query "imatinib" --format detailed50```5152### Limit search results53```bash54python3 {baseDir}/scripts/chembl_search.py --query "kinase inhibitor" --max-results 555```5657## Parameters5859| Parameter | Description | Default |60|-----------|-------------|---------|61| `--query` | Compound or drug name or search term | - |62| `--chembl-id` | ChEMBL molecule ID (e.g. CHEMBL25) | - |63| `--max-results` | Max results for search | 10 |64| `--format` | Output: summary, detailed, json | summary |6566## Output6768- **Summary:** ChEMBL ID, pref_name, molecular formula, MW, SMILES, max_phase69- **Detailed:** Adds drug type, first approval, indications, targets70- **JSON:** Full API response7172## Notes7374- ChEMBL IDs look like CHEMBL25, CHEMBL123456775- Use --query for name or text search76- Use --chembl-id when you know the exact molecule ID
lamm-mit