Metadata-Version: 2.4
Name: mievformer
Version: 0.3.0
Summary: A deep learning model for microenvironment estimation based on spatial transcriptomics
Author-email: Yasuhiro Kojima <tiisaishima@gmail.com>
License: MIT License
Project-URL: Homepage, https://github.com/kojikoji/mievformer_package
Project-URL: Repository, https://github.com/kojikoji/mievformer_package
Project-URL: Bug Tracker, https://github.com/kojikoji/mievformer_package/issues
Keywords: spatial-transcriptomics,deep-learning,single-cell,microenvironment,niche,transformer
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch
Requires-Dist: pytorch-lightning
Requires-Dist: scanpy
Requires-Dist: igraph
Requires-Dist: leidenalg
Requires-Dist: anndata
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scipy
Requires-Dist: statsmodels
Requires-Dist: scikit-learn
Requires-Dist: einops
Requires-Dist: matplotlib
Requires-Dist: networkx
Requires-Dist: jax
Requires-Dist: optax
Requires-Dist: squidpy
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Dynamic: license-file

# mievformer

mievformer is a Python package for learning cellular microenvironments from
spatial transcriptomics. Its standard workflow uses reference-probability
correspondence analysis (CA) for niche clustering and UMAP, with
sample-conditional CA for joint analysis of multiple spatial slices.

## Installation

```bash
pip install mievformer
```

## Documentation

For detailed usage instructions, tutorials, and API reference, please visit the documentation:

**https://kojikoji.github.io/mievformer_package/index.html**

## Quick start

~~~python
import mievformer as mf

# Single slice: ordinary reference-probability CA.
adata = mf.optimize_nicheformer(adata, model_path="model.pth")

# Multiple slices: batch-conditioned training and sample-conditional CA.
adata = mf.optimize_nicheformer(
    adata,
    model_path="multibatch_model.pth",
    batch_key="sample",
)
~~~

## License

MIT License
