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.
Update: We are currently working on tutorial notebooks for running optimization on Slurm with fan-out across multiple CPU nodes, stay tuned!
requirements.txt
Note numpy 2.0 or above not currently supported
Run the following in the command line
pip install morpheus-spatial
To install Morpheus from source, clone the repository and install the dependencies:
git clone https://github.com/neonine2/morpheus-spatial.git
cd morpheus-spatial
pip install -r requirements.txt
pip install .
See tutorial_notebook.ipynb
for a complete, self-contained workflow on using Morpheus to generate therapeutic strategies.
Some users may encounter warnings about conflicting OpenMP libraries. If you see a warning about Intel OpenMP and LLVM OpenMP being loaded at the same time, please see https://github.com/joblib/threadpoolctl/blob/master/multiple_openmp.md for more information and possible workarounds.
assets/
: Contains images and other assets used in the documentation and the project.examples/
: Example scripts and notebooks demonstrating various use cases of the Morpheus framework.
tutorial.ipynb
: A notebook demonstrating how to reproduce the primary analyses of the paper.reproduction/
: Includes Jupyter notebooks and scripts for reproducing the main analyses presented in the associated research paper.
reproduction_notebook.ipynb
: A notebook demonstrating how to reproduce the primary analyses of the paper.src/
: The main package directory containing all core modules and functions.tests/
: Contains unit tests for the different modules of the package.requirements.txt
: A file listing all Python dependencies required to run the project.