Skip to content
/ gpmeth Public

Model single-cell epigenetics in continuous processes

License

Notifications You must be signed in to change notification settings

mffrank/gpmeth

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

43 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GPmeth

GPmeth is a modeling framework based on GPflow. It detects differential DNA methylation / chromatin accessibility in single-cell multimodal datasets that study continuous biological processes. The idea is to generate temporal trajectories based on one modality (typically RNA-seq) and then model methylation/accessibility along these continuous axes with a Gaussian process model. GPmeth models methylation at base resolution and can automatically refine boundaries of differentially methylated/accessible regions.

Installation

GPmeth is built with GPflow, which dependso on TensorFlow and TensorFlow Probability. I recommend installing these first.

# Install tensorflow and tensorflow-probability
pip install gpflow tensorflow~=2.10.0 tensorflow-probability~=0.18.0

# Install gpmeth
git clone git@github.com:mffrank/gpmeth.git
cd gpmeth
pip install .

About

Model single-cell epigenetics in continuous processes

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages