Skip to content

raphael-group/Multi-GASTON

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Multi-GASTON

Multi-GASTON is an unsupervised deep learning model that learns multiple spatial gradients simoutaineously from spatially resolved data such as spatial metabolomics and spatially-resolved transcriptomics (SRT). It is an extension of GASTON (https://pmc.ncbi.nlm.nih.gov/articles/PMC10592770/), which was designed for SRT data and learns a single topographic map of a 2-D tissue slice in terms of a 1-D coordinate called isodepth, where all genes can be expressed as a function of this isodepth. Now allowing metabolites or genes to follow distinct spatial patterns, Multi-GASTON captures the metabolite abundance or gene expression topography by learning k distinct isodepths, that smoothly vary across a tissue slice and capture spatial organizations of different groups of spatially variable metabolites or genes.

Installation

TO BE CHANGED

Software dependencies

  • torch (=2.0.0)
  • matplotlib (=3.8.0)
  • pandas (=2.1.1)
  • scikit-learn (=1.3.1)
  • numpy (=1.23.4)
  • jupyterlab (=4.0.6)
  • seaborn (=0.12.2)
  • tqdm (=4.66.1)
  • scipy (=1.11.2)
  • scanpy (=1.9.5)
  • squidpy (=1.3.1)

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages