Skip to content

Latest commit

 

History

History
executable file
·
72 lines (45 loc) · 1.89 KB

README.rst

File metadata and controls

executable file
·
72 lines (45 loc) · 1.89 KB

scTM: A pacakge for topic modelling in transcriptomics data

Documentation Status

scTM is a package for spatial transcriptomics for single cell that uses topic modelling, solved with stochastic variational infernce. The interesting part is with the formulation of topic models, we can get interpretable embedding which are useful for downstream analysis.

Currently available modules: STAMP

Features

  • STAMP: A spatially-aware dimensional reduction designed for spatial data.

Minimal Installation

conda create --name sctm python=3.8
conda activate sctm
pip install sctm

or

conda create --name sctm python=3.8
git clone https://github.com/JinmiaoChenLab/scTM.git
conda activate sctm
cd scTM
pip install .

Basic Usage

Check out our usage of STAMP in the documentation with a simulated data at https://jinmiaochenlab.github.io/scTM/notebooks/stamp/Simulation.

The simulated data can be found at data/simulation.h5ad.

For more advanced usage please check the examples in our detailed tutorials.

Tested with

python == 3.8

numpy == 1.24.4

numba == 0.57.1

torch == 2.0.3

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.