Python wrapper of MALLET for LDA analysis on single-cell data
Project description
scmallet
Python wrapper of MALLET for LDA analysis on single-cell data.
MALLET is the LDA backend chosen by pycistopic. The implementation in this package has several difference than pycistopic:
- Improved paralization.
- Allow train LDA model with cell subset and then inference ramaining cells. This is nicely supported by MALLET itself.
- Allow the training process to be resumable.
- Work with anndata.
Installation
You need to have Python 3.9 or newer installed on your system. If you don't have Python installed, we recommend installing Mambaforge.
There are several alternative options to install scmallet:
- Install the latest release of
scmallet
from PyPI:
pip install scmallet
- Install the latest development version:
pip install git+https://github.com/lhqing/scmallet.git@main
Usage
See example usage here: https://github.com/lhqing/scmallet/blob/main/tests/example.ipynb
Citation
-
Mallet Package: https://mimno.github.io/Mallet/
McCallum, Andrew Kachites. "MALLET: A Machine Learning for Language Toolkit." http://mallet.cs.umass.edu. 2002.
-
PyCistopic: https://github.com/aertslab/pycisTopic
Bravo Gonzalez-Blas, C. & De Winter, S. et al. (2022). SCENIC+: single-cell multiomic inference of enhancers and gene regulatory networks
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.