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

# Python SDK

> pysynthbio — the official Python client for the Synthesize Bio platform.

`pysynthbio` is a Python package that provides a convenient interface to the [Synthesize Bio](https://www.synthesize.bio/) API. It lets you generate realistic gene expression data for specified biological conditions, work with reference samples, and predict metadata from observed expression, all from Python.

If you'd prefer 1-click dataset generation and analysis, try the [web platform](https://app.synthesize.bio/datasets/).

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/pysynthbio/installation">
    Install from PyPI, source, or a GitHub release.
  </Card>

  <Card title="Getting started" icon="rocket" href="/pysynthbio/getting-started">
    Authenticate, list models, and make your first prediction.
  </Card>

  <Card title="Baseline models" icon="dna" href="/pysynthbio/models/baseline">
    Generate synthetic expression from metadata alone.
  </Card>

  <Card title="Reference conditioning" icon="microscope" href="/pysynthbio/models/reference-conditioning">
    Anchor generation to a real reference sample.
  </Card>

  <Card title="Metadata prediction" icon="magnifying-glass" href="/pysynthbio/models/metadata-prediction">
    Infer biological metadata from observed expression.
  </Card>

  <Card title="GitHub" icon="github" href="https://github.com/synthesizebio/pysynthbio">
    Source code, issues, and releases.
  </Card>
</CardGroup>

## Quickstart

```python theme={null}
import pysynthbio

pysynthbio.set_synthesize_token(use_keyring=True)

query = pysynthbio.get_example_query(model_id="gem-1-bulk")["example_query"]
result = pysynthbio.predict_query(query, model_id="gem-1-bulk")

metadata = result["metadata"]
expression = result["expression"]
```

## Support

Email [support@synthesize.bio](mailto:support@synthesize.bio) or [open an issue](https://github.com/synthesizebio/pysynthbio/issues) on GitHub.