> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mareforma.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Drug Target Provenance

> MEDEA, an AI scientist, identifies drug targets from multi-omics data. Mareforma records the epistemic status of every finding.

<Card title="View on GitHub" icon="github" href="https://github.com/mareforma/mareforma/tree/main/examples/05_drug_target_provenance">
  `examples/05_drug_target_provenance/`
</Card>

[MEDEA](https://github.com/mims-harvard/Medea) is an AI scientist that identifies drug targets from multi-omics data.
Two forks run on different diseases (RA and SLE, CD4+ T cells). Mareforma
records whether MEDEA's data pipeline actually ran or whether the answer
came from LLM prior knowledge.

## Recording origin at assertion time

```python theme={"dark"}
result = run_medea_fork(disease="rheumatoid arthritis", cell_type="CD4")
classification = "ANALYTICAL" if result["generated_code"] else "INFERRED"

graph.assert_claim(
    result["final_hypothesis"],
    classification=classification,
    generated_by="medea/gpt-4o/ra_cd4",
    source_name="medeadb",
)
```

## What we found

Both forks returned `generated_code = null`. Both findings were `INFERRED`.
The classification surfaced a silent pipeline failure immediately, before
anyone acted on the results. Led to a bug report:
[mims-harvard/Medea#6](https://github.com/mims-harvard/Medea/pull/6).

## Setup

```bash theme={"dark"}
python 05_drug_target_provenance.py --install   # ~21 GB MedeaDB download
python 05_drug_target_provenance.py --data
cp Medea/env_template.txt .env                  # set OPENAI_API_KEY
python 05_drug_target_provenance.py --run
```