pharma-db-tools

Files (2)

• SKILL.md
• pharma_db_lookup.py · templates/

SKILL.md (first lines)

# Pharma DB Tools

Use this skill when the user asks for public drug-discovery database lookups rather than local cheminformatics analysis.

Typical triggers:
- compound lookup by name, CID, SMILES, or ChEMBL id
- public bioactivity or target-association lookup from ChEMBL
- measured drug-target affinity lookup from BindingDB by UniProt, compound, or local TSV export
- FDA labeling, adverse-event, NDC, approval, recall, or shortage data
- ClinicalTrials.gov study search, status review, or NCT lookup
- OpenAlex literature retrieval for drug, target, modality, or institution queries

## Environment Check

The bundled template uses Python plus HTTP APIs. Check first.

```bash
which python3 || true
python3 - <<'PY'
mods = ["requests"]
for name in mods:
    try:
        __import__(name)
        print(f"{name}: ok")
    except Exception as exc:
        print(f"{name}: missing ({exc})")
PY
```

If outbound network access is blocked, say so explicitly before claiming the lookup ran.

## Bundled Asset

Use the reusable template instead of rewriting API snippets every time:

- `templates/pharma_db_lookup.py`

Supported sources:
- `pubchem`
- `chembl`
- `bindingdb`
- `openfda`
- `clinicaltrials`
- `openalex`

## Quick Start

```bash
python3 templates/pharma_db_lookup.py pubchem \
  --query imatinib \
  --output pharma/pubchem_imatinib.csv \
  --summary pharma/pubchem_imatinib.json
```

```bash
python3 templates/pharma_db_lookup.py chembl \
  --mode molecule \
  --chembl-id CHEMBL941 \
  --output pharma/chembl_imatinib.csv \
  --summary pharma/chembl_imatinib.json
```

```bash
python3 templates/pharma_db_lookup.py bindingdb \
  --tsv BindingDB_All.tsv \
  --uniprot-id P00519 \
  --affinity-type Ki \
  --max-nm 1000 \
  --output pharma/bindingdb_abl1.csv \
  --summary pharma/bindingdb_abl1.json
```

```bash
python3 templates/pharma_db_lookup.py openfda \
  --endpoint label \
  --query imatinib \
  --output pharma/fda_imatinib_label.csv \
  --summary pharma/fda_imatinib_label.json
```

```bash
python3 templates/pharma_db_lookup.py clinicaltrials \
  --condition "non-small cell lung cancer" \
  --intervention osimertinib \
  --status RECRUITING \
  --output pharma/osimertinib_trials.csv \
  --summary pharma/osimertinib_trials.json
```

```bash
python3 templates/pharma_db_lookup.py openalex \
  --query "KRAS G12C inhibitor resistance" \
  --limit 20 \
  --output pharma/openalex_kras_g12c.csv \
  --summary pharma/openalex_kras_g12c.json
```

## Working Rules

1. Save both a machine-readable result file and a summary JSON.
2. Report the exact database, mode, identifier, filters, and endpoint used.
3. Prefer exact identifiers when available: PubChem CID, ChEMBL id, NCT id, DOI.
4. Return direct stable links when the upstream database exposes them.
5. Distinguish clearly between compound metadata, activity measurements, regulatory evidence, clinical-study records, and literature hits.
6. If the API returns no hits, say that explicitly instead of inferring a scientific conclusion.
7. Treat these sources as evidence surfaces for prioritization and review, not as experimental proof.

## Common Patterns

### PubChem compound lookup by CID

```bash
python3 templates/pharma_db_lookup.py pubchem \
  --cid 5291 \
  --output pharma/pubchem_5291.csv \
  --summary pharma/pubchem_5291.json
```

### ChEMBL activity rows for a target

From DrugClaw/DrugClaw, Apache-2.0.

More from DrugClaw/DrugClaw