scstate 0.1.0

scState: A pathway-informed graph transformer framework for decoding stem cell state transitions from scRNA-seq data

Title：scState: Decoding stem cell state transitions through pathway-informed heterogeneous graph representations

Note: This project is for internal testing purposes only. Do not use it in a production environment.

We developed scState, a pathway-informed graph transformer framework for identifying stem cells and resolving quiescent and activated stem cell states from scRNA-seq data. By integrating pathway activity with adversarial representation learning in a heterogeneous graph architecture, scState enables stem cell identification, cell state discrimination, pathway-level interpretation, and trajectory inference.

Keywords: scRNA-seq, graph transformer, adversarial learning, stem cell, state transition

Installation

System Requirements

• Python 3.8.0 or higher
• Linux system is recommended
• GPU is recommended for faster model training, but CPU installation is also supported

Installation Steps

• Create a new conda environment:

conda create --name scState python=3.8
conda activate scState

• Install PyTorch and PyTorch Geometric according to your CPU/GPU configuration.

For GPU version with CUDA 11.8:

pip install https://download.pytorch.org/whl/cu118/torch-2.4.1%2Bcu118-cp38-cp38-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-2.4.0%2Bcu118/torch_scatter-2.1.2%2Bpt24cu118-cp38-cp38-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-2.4.0%2Bcu118/torch_sparse-0.6.18%2Bpt24cu118-cp38-cp38-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-2.4.0%2Bcu118/torch_cluster-1.6.3%2Bpt24cu118-cp38-cp38-linux_x86_64.whl
pip install torch-geometric==2.6.1

For CPU version:

pip install https://download.pytorch.org/whl/cpu/torch-2.4.1%2Bcpu-cp38-cp38-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-2.4.0%2Bcpu/torch_scatter-2.1.2%2Bpt24cpu-cp38-cp38-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-2.4.0%2Bcpu/torch_sparse-0.6.18%2Bpt24cpu-cp38-cp38-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-2.4.0%2Bcpu/torch_cluster-1.6.3%2Bpt24cpu-cp38-cp38-linux_x86_64.whl
pip install torch-geometric==2.6.1

• Install MulticoreTSNE for Palantir.

palantir==1.0.0 requires MulticoreTSNE. If installing MulticoreTSNE through pip fails during compilation, we recommend installing it with conda:

conda install -c conda-forge multicore-tsne=0.1 -y

• Install the required dependencies using pip:

pip install -r requirements.txt

• Use pip to install scState:

pip install scState

• Add the environment to Jupyter Notebook:

pip install ipykernel
python -m ipykernel install --user --name scState --display-name "Python (scState)"

Dependencies

scState was tested under Python 3.8. The main dependencies are listed below:

• anndata==0.8.0
• dill==0.3.4
• matplotlib==3.5.2
• numpy==1.22.3
• pandas==1.4.2
• scipy==1.10.1
• seaborn==0.11.2
• scikit-learn==1.1.2
• torch==2.4.1+cu118
• torch-geometric==2.6.1
• torchmetrics==0.9.3
• xlwt==1.3.0
• tqdm==4.64.0
• scanpy==1.9.1
• leidenalg==0.8.10
• ipywidgets==8.0.6
• palantir==1.0.0

For PyTorch Geometric, the following extension packages are required and should match the installed PyTorch and CUDA versions:

• torch-scatter==2.1.2+pt24cu118
• torch-sparse==0.6.18+pt24cu118
• torch-cluster==1.6.3+pt24cu118

For Palantir, the following additional dependencies are required:

• PhenoGraph==1.5.7
• fcsparser==0.2.8
• MulticoreTSNE==0.1

The tested GPU environment is:

• Python==3.8.x
• PyTorch==2.4.1+cu118
• CUDA used by PyTorch==11.8
• PyTorch Geometric==2.6.1

Usage

After installation, scState can be imported as follows:

from scState.conv import *
from scState.scState_model import *
from scState.utils import *

License

This project is released under the MIT License.