https://github.com/greenelab/stanmf

A python implementation of Stability NMF
https://github.com/greenelab/stanmf

analysis gene-expression machine-learning tool

Last synced: 3 months ago
JSON representation

A python implementation of Stability NMF

• Host: GitHub
• URL: https://github.com/greenelab/stanmf
• Owner: greenelab
• License: bsd-3-clause
• Created: 2016-07-29T16:44:52.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2016-11-23T18:58:18.000Z (about 8 years ago)
• Last Synced: 2024-08-09T02:17:01.331Z (6 months ago)
• Topics: analysis, gene-expression, machine-learning, tool
• Language: Python
• Homepage:
• Size: 5.1 MB
• Stars: 6
• Watchers: 6
• Forks: 3
• Open Issues: 3
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
Amy Campbell, 2016

staNMF

------

Python 2.7 implementation of `Siqi Wu et al.'s 2016 stability NMF (staNMF)

`_

Package Contents

----------------

=========

staNMF.py

=========

staNMF.py class includes the necessary methods to perform stability

NMF on a user-specified .csv datase (see sourcecode/staNMF_Example for precise

usage instructions)

=================

staNMF_Example.py

=================

Example of staNMF demonstrated on Wu et al.'s 2016

drosophila spatial expression data between K=15 and K=30; Generates

sample factorizations, calculates instability index, and plots instability

against K

================

staNMF_driver.py

================

Driver script to run staNMF in parallel; can be called from the command line

using:

python staNMF_driver.py       

(See docstring for more specific instructions) 

============================

data/WuExampleExpression.csv

============================

sample dataset (also available for download `here

`_)

Installation

-------------

$ pip install staNMF

*Please note that staNMF requires SPAMs package (version 2.5), which is

available from* `Julien Mairal et al.

`_ , or from Anaconda

using:

$ conda install -c conda-forge python-spams=2.5

Acknowledgements

----------------

This work was supported by The Gordon and Betty Moore Foundation’s Data-Driven

Discovery Initiative (GBMF 4552 to C.S.G.) and a grant from the National

Institutes of Health (R01 CA200854)