Metadata-Version: 2.4
Name: ACSCeND
Version: 1.1
Summary: A deep learning tool for bulk RNA-seq deconvolution and Stem Cells Sub-Class prediction.
Home-page: https://github.com/SML-CompBio/ACSCEND
Author: Shreyansh Priyadarshi
Author-email: shreyansh.priyadarshi02@gmail.com
License: BSD 2-clause
Description-Content-Type: text/markdown
Requires-Dist: pandas==2.3.1
Requires-Dist: numpy==2.3.1
Requires-Dist: torch==2.7.1
Requires-Dist: scikit-learn==1.7.0
Requires-Dist: joblib==1.5.1
Requires-Dist: scipy==1.16.0
Dynamic: author
Dynamic: author-email
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: summary

# AI-based Cancer Stem Cell profiler and Neoplasia Deconvoluter (ACSCeND)

**ACSCeND** is a Python package designed to analyze and process stem cell transcriptomics data. It includes two core modules for predicting stem cell subtypes and deconvoluting bulk RNA-seq data using deep learning.

## Features

1. **Stem Cell Subtypes Predictor**  
   Identify stem cell subtypes â€” Pluripotent, Multipotent, or Unipotent â€” from single-cell stem cell transcriptomics data.

2. **Deep Learning-based Deconvoluter**  
   Deconvolute bulk RNA-seq data into meaningful components using cutting-edge deep learning techniques.

---

## Installation

Install ACSCeND using pip:

```bash
pip install ACSCeND
```

---

## Documentation

Comprehensive documentation is available at:  
[ACSCeND Documentation](https://acscend.readthedocs.io/en/latest/)

---

## Usage

### Stem Cell Subtypes Predictor

```python
from ACSCeND import Predictor

# Example usage
predictor = Predictor()
subtypes = predictor(input_data)
```

### Deep Learning-based Deconvoluter

```python
from ACSCeND import Deconvoluter

# Example usage
real_freq = Deconvoluter(pseudo_data, sig_matrix, pseudo_freq, real_data, normalized=False)
```

For detailed examples and API reference, visit the [documentation](https://acscend.readthedocs.io/en/latest/).

---
