Metadata-Version: 2.4
Name: omicsmad
Version: 0.1.0
Summary: A robust Scikit-Learn style Feature Selector using Median Absolute Deviation (MAD) for high-throughput genomics data.
Project-URL: Homepage, https://github.com/rizanb
Author-email: rizanb <rijann5@gmail.com>
License-File: LICENSE
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Requires-Python: >=3.9
Requires-Dist: matplotlib>=3.5.0
Requires-Dist: numpy>=1.22.0
Requires-Dist: pandas>=1.4.0
Requires-Dist: scipy>=1.8.0
Description-Content-Type: text/markdown

# omicsmad

A clean, minimal package for filtering genomics datasets (UCSC Xena bulk expression, CNV arrays) using median absolute deviation.

## Installation

```bash
pip install omicsmad
```

## Usage

```python
import numpy as np
import pandas as pd
from omicsmad import OmicsMADSelector

# mocking data matrices
np.random.seed(42)
X_train = pd.DataFrame(np.random.randn(100, 5000), columns=[f"Gene_{i}" for i in range(5000)])

selector = OmicsMADSelector(top_n=1000)
selector.fit(X_train)

# saves to 'figures/mad_distribution.png'
selector.plot_distributions()

# saves processed matrix to 'datasets/processed/filtered_features.tsv'
selector.save_filtered_data(X_train)
```