Metadata-Version: 2.1
Name: epipackpy
Version: 0.1.0.dev2
Summary: EpiPack: scATAC-seq integration, reference mapping and cell type annotation
Home-page: https://github.com/ZhangLabGT/EpiPack
Author: Yuqi Cheng
Author-email: ycheng430@gatech.edu
License: MIT
Requires-Python: >=3.8, <3.12
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: numpy >=1.17.0
Requires-Dist: pandas <2.1.2,>=1.0
Requires-Dist: scipy <2.0.0,>=1.4
Requires-Dist: scikit-learn <2.0.0,>=0.23
Requires-Dist: tqdm >=4.62
Requires-Dist: typing-extensions
Requires-Dist: torch >=2.0
Requires-Dist: scanpy >=1.9

## EpiPack
EpiPack v 0.1.0dev1

### Description
EpiPack is single-cell ATAC-seq atlas construction (integration) and cell type annotation tool. Leveraging its heterogeneous domain adaptation framework, EpiPack is able to
* Integrate multi-source scATAC-seq datasets without aligned peak set
* reference mapping of query datasets
* cell type annotation including OOR detection

<img src = "figures/overview.png" width = 600ptx>

### Dependency
```
    python >= 3.8
    pytorch >= 1.11.0
    sklearn >= 0.22.1
    numpy >= 1.21.6
    pandas >= 1.3.5
```
Note: For pytorch installation, we recommend users go to the pytorch portal to download based on their CUDA version.

### Installation
The package has been uploaded to PyPI. Users can download the package and dependent packages by:
```
    pip install epipackpy
```

## To-do-list

- [x] Publish to pypi
- [ ] Include our own preprocessing functions
- [ ] Construct a tutorial website for EpiPack
- [ ] Provide pre-trained reference model for all human tissues
