Metadata-Version: 2.4
Name: mesengenic_hsc
Version: 0.1.1
Summary: Generative causal engine for perturbation manifold analysis and epistatic peak discovery.
Project-URL: Homepage, https://mesengenic.com
Project-URL: Documentation, https://github.com/mesengenic/mesengenic
Project-URL: Source, https://github.com/mesengenic/mesengenic
Project-URL: Bug Tracker, https://github.com/mesengenic/mesengenic/issues
Author: Mesengenic Labs
License: Proprietary
Keywords: bioinformatics,causal-inference,epistasis,perturbation,single-cell,vae
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Requires-Python: >=3.9
Requires-Dist: anndata<1,>=0.10
Requires-Dist: click<9,>=8.1
Requires-Dist: numpy<3,>=1.24
Requires-Dist: pandas<3,>=2.0
Requires-Dist: pydantic<3,>=2.0
Requires-Dist: rich<14,>=13.0
Requires-Dist: torch<3,>=2.0
Provides-Extra: dev
Requires-Dist: build>=1.0; extra == 'dev'
Requires-Dist: pytest<9,>=7.0; extra == 'dev'
Requires-Dist: ruff<1,>=0.4; extra == 'dev'
Provides-Extra: publish
Requires-Dist: build>=1.0; extra == 'publish'
Requires-Dist: twine>=4.0; extra == 'publish'
Description-Content-Type: text/markdown

# Mesengenic

Generative causal engine for perturbation manifold analysis — CLI and Python SDK for computational biologists.

## Install

### Production (PyPI)

```bash
pip install --index-url https://pypi.org/simple mesengenic_hsc
```

### Local development (`pip install -e .`)

Run from the **repository root** (where `pyproject.toml` lives):

```bash
cd mesengenic-v3
pip install -e .
```

| Component | Resolves to |
|-----------|-------------|
| Python package | `./mesengenic/` (live edits, no reinstall) |
| `mesengenic` command | `mesengenic.cli:main` via `[project.scripts]` in `pyproject.toml` |
| Checksum manifest | `assets/weights/MANIFEST.json` |

Verify:

```bash
mesengenic info          # shows install path + entry module
python -m mesengenic     # same as `mesengenic`
```

### Conda (secondary)

```bash
conda env create -f environment.yml
conda activate mesengenic
```

## Required Assets

Not bundled in the PyPI wheel. Install after `pip install mesengenic_hsc`:

```bash
# Hosted URL (set by publisher)
export MESENGENIC_WEIGHTS_URL=https://your-host/vae_epoch_50_final.pth
mesengenic weights download
mesengenic weights verify

# Or from a file you received
mesengenic weights restore --from ~/Downloads/vae_epoch_50_final.pth
```

Publishers: `./scripts/package_weights_release.sh` → share `dist/mesengenic-weights-*.tar.gz`

See **[PUBLISHING.md](PUBLISHING.md)** for PyPI build and partner handoff.

| Asset | Default path | Env var |
|-------|--------------|---------|
| VAE weights | `assets/weights/vae_epoch_50_final.pth` | `MESENGENIC_WEIGHTS_PATH` |
| AnnData | `data/norman19_processed.h5ad` | `MESENGENIC_DATA_PATH` |

## Navigation

See **[docs/NAVIGATION.md](docs/NAVIGATION.md)** for the full CLI guide, query rules, and PyPI migration notes.

## CLI (quick start)

```bash
mesengenic                          # Novaflow-style landing + command catalog
mesengenic sweep --mode 1 -o peaks.csv
mesengenic query "KLF1" --json
mesengenic trajectory "CEBPA+CEBPE"
mesengenic validate
mesengenic shell --full
```

## SDK

```python
from mesengenic import MesengenicCausalEngine

engine = MesengenicCausalEngine()
edges, deltas, peaks = engine.execute_global_sweep()
```

## Security

See [SECURITY.md](SECURITY.md) for publishing checklist, wheel contents, and supply-chain controls.
