Skip to content

viktormiok/CsppaRshiny

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

96 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

version GitHub code size in bytes GitHub issues

dependencies commit GitHub

Edit with Gitpod

CsppaRshiny

Overview

The R Shiny app CsppaRshiny performs machine learning analysis and visualization of cellular spatial point patterns under hypercaloric diet shifts, and it is based on Csppa R-package.

The application visualises spatial point pattern density in both 2D and 3D, offering flexible data representation tailored to the research question. It also enables both global and local significance assessment of these densities using a range of statistical methods.

K-Nearest Neighbour and Random Forest classification algorithms are implemented to compare the grouping of the cells expressing different markers within and between the diets. Additionally, the correlation and spatial autocorrelation of cells expressing different markers can be compared using the Mantel and Moran's I tests, respectively.

Application

Here, we focus on astrocytes in the arcuate nucleus of the mouse brain, examining the expression of Gfap and Aldh1l1 and reconstructing their spatial point patterns under standard chow (SC), 5‑day, and 15‑day high‑fat high‑sugar (HFHS) diets. The R package Csppa enables the assessment of whether these astrocyte populations exhibit spatial organisation and a tendency to form locally homogeneous clusters in response to HFHS exposure over time. Spatial coherence of each astrocytic subtype, defined as similarity among neighbouring cells, is quantified across conditions (SC, 5d, and 15d HFHS) using Moran’s I, a well-established measure of spatial autocorrelation. In addition, a random forest classifier is applied to identify shared feature space partitions among astrocytes expressing Gfap and Aldh1l1 across experimental groups.

How to Run the App

To run the CsppaRshiny app locally, ensure all dependencies are installed. Open the app.R file in RStudio and click Run App. Before launching, either load the functions from the R folder into RStudio or install the R-package Csppa.

Data

Data required for cellular spatial point pattern analysis will be deposited online soon:

Data type Link to the data Code to get the data
Aldh1l1 only link link
Gfap only link link
Double positive link link

Tutorials

Please see the following notebook for detailed examples of what you can do with CsppaRshiny:

CsppaRshiny example:

License

CsppaRshiny is distributed under the MIT license. Details about the license of CsppaRshiny are provided in the LICENSE file. Please read the license before using CsppaRshiny.

References

Publications related to CsppaRshiny include:

Please cite the relevant publications if you use CsppaRshiny.

About

The R Shiny App for machine learning analysis and visualization of cellular spatial point patterns under hypercaloric diet shifts.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors