Metadata-Version: 2.4
Name: checkdyn
Version: 0.1.0
Summary: Modeling treatment-induced immune checkpoint dynamics
License: MIT
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.0
Requires-Dist: pandas>=2.0
Requires-Dist: numpy>=1.24
Requires-Dist: scikit-learn>=1.4
Requires-Dist: scanpy>=1.10
Requires-Dist: anndata>=0.10
Requires-Dist: lifelines>=0.28
Requires-Dist: networkx>=3.0
Requires-Dist: matplotlib>=3.8
Requires-Dist: seaborn>=0.13
Requires-Dist: scipy>=1.12
Requires-Dist: statsmodels>=0.14
Requires-Dist: pycomBat>=0.3
Requires-Dist: pyyaml>=6.0
Requires-Dist: typer>=0.9
Requires-Dist: rich>=13.0
Requires-Dist: tqdm>=4.66
Requires-Dist: GEOparse>=2.0
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: pytest-cov>=5.0; extra == "dev"
Requires-Dist: ruff>=0.4; extra == "dev"

# CheckDyn

**CheckDyn** models treatment-induced immune checkpoint dynamics to predict adaptive resistance to immune checkpoint blockade (ICB) therapy.

## Overview

CheckDyn is a computational biology pipeline that:

- Collects paired pre/post-treatment RNA-seq data from GEO cohorts (≥8 datasets, ≥150 paired samples)
- Detects compensatory checkpoint upregulation patterns during ICB treatment
- Models temporal checkpoint gene dynamics via a Transformer architecture
- Predicts early adaptive resistance (target AUROC ≥ 0.75)

## Installation

```bash
pip install checkdyn
```

## Usage

```bash
# Collect datasets
checkdyn collect --output data/

# Run full analysis
checkdyn analyze --input data/ --output results/

# Predict resistance for a patient
checkdyn predict --model pretrained --input patient.csv
```

## Key Datasets

| Dataset | Cancer | Platform | GEO |
|---------|--------|----------|-----|
| Riaz2017 | Melanoma | RNA-seq | GSE91061 |
| Gide2019 | Melanoma | RNA-seq | GSE91061 |
| Chen2016 | Melanoma | RNA-seq | GSE79691 |
| Sade-Feldman2018 | Melanoma | scRNA-seq | GSE120575 |
| Yost2019 | BCC | scRNA-seq | GSE123813 |
| Caushi2021 | NSCLC | scRNA-seq | GSE176021 |
| Hanna2018 | HNSCC | NanoString | GSE112927 |

## License

MIT
