SpatialMST

Spatially resolved metabolic and transcriptomic profiling uncovers intratumoural heterogeneity in breast cancer

Spatial Multimodal Self-supervised Transformer

• Free software: MIT License

Installation

Create environment

conda create -n SpatialMSTEnv python=3.11
conda activate SpatialMSTEnv

Install ipykernel

conda install ipykernel
python -m ipykernel install --user --name SpatialMSTEnv --display-name "Python(SpatialMSTEnv)"

Install POT: Python Optimal Transport

conda install -c conda-forge pot

Install Pytorch and pytorch-geometric

pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu129
pip install torch_geometric

Install SpatialMST

PyPI package: https://pypi.org/project/SpatialMST

pip install SpatialMST

The source files for SpatialMST can be downloaded from the Github repo.

You can either clone the public repository:

git clone https://github.com/Angione-Lab/SpatialMST.git

Once you have a copy of the source, you can install it with:

cd spatialmst
uv pip install .

Generate metabolic module flux rates and metabolite abundances for spatial transcriptomics using scFEA.

The estimated metabolic module flux rates and metabolite abundances construct the two modalities and the spatial transcriptomics data represents the third modality.

https://www.biorxiv.org/content/10.1101/2020.09.23.310656v1.full Github link

Integrating spatial transcriptomics with metabolic module fluxes and metabolite abundance:

Tutorial on multimodal integration and analysis

Download the datasets from figshare

Example dataset