Metadata-Version: 2.1
Name: morpheus-spatial
Version: 0.2.0
Summary: 
Author: neonine2
Author-email: jerry.wang95@yahoo.ca
Requires-Python: >=3.9,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: dill (>=0.3.8,<0.4.0)
Requires-Dist: h5py (>=3.10.0,<4.0.0)
Requires-Dist: lightning (>=2.2.0.post0,<3.0.0)
Requires-Dist: pandas (>=2.2.1,<3.0.0)
Requires-Dist: scikit-learn (>=1.4.1.post1,<2.0.0)
Requires-Dist: torchvision (>=0.17.1,<0.18.0)
Description-Content-Type: text/markdown

# Morpheus: Generating Therapeutic Strategies using Spatial Omics

## Introduction

Morpheus is an integrated deep learning framework that takes large scale spatial omics profiles of patient tumors, and combines a formulation of T-cell infiltration prediction as a self-supervised machine learning problem with a counterfactual optimization strategy to generate minimal tumor perturbations predicted to boost T-cell infiltration.

![Graphical summary of the Morpheus framework](assets/summary_fig.png)

## Features

- **Self-Supervised Learning**: Utilizes unlabeled spatial omics data to learn predictive models for T-cell infiltration.
- **Counterfactual Reasoning**: Generates minimal perturbations to the tumor environment, hypothesizing potential improvements in T-cell responses.
- **Deep Learning Integration**: Employs advanced neural network architectures tailored for high-dimensional omics data.
- **Scalability**: Designed to handle large datasets typical of spatial omics studies, enabling robust analysis across numerous patient samples.

## Getting Started

### Prerequisites

- Python 3.9 or higher
- PyTorch Lightning 2.2.0 or higher
- CUDA 11.7 or higher (for GPU acceleration)
- Other dependencies listed in `requirements.txt`

### Installation

Run the following in the command line

```bash
pip install morpheus-spatial
```
