Skip to content

Machine learning analysis & visualisation of cellular spatial point patterns

License

Notifications You must be signed in to change notification settings

viktormiok/Csppa

Repository files navigation

version GitHub code size in bytes GitHub issues

dependencies commit GitHub

Edit with Gitpod

Csppa

Overview

Understanding how the anatomical location of the cells and their spatial molecular distribution determine the cellular response to a high caloric diet requires developing machine learning methods for analysis and visualization.

The R-package Csppa employ machine learning for cellular spatial point patterns analysis and visualization. Hence, Csppa allows a comprehensive understanding of spatial and temporal changes of particular cellular gene expression during different time points of adaptation to a high caloric diet.

Application

Here we focus on the astrocytes from the arcuate nucleus from the mouse brain and the expression of Gfap and Aldh1l1 genes recovering spatial point patterns under standard chow (SC), 5 and 15 days high fat high sugar (HFHS) diet. The R-package Csppa allows assessing whether these astrocyte populations are spatially organized and whether tend to form local identical clusters in response to a HFHS diet over time. To do that, the algorithm measures degree of spatial coherence (depicting the level of similarity between neighbors) of each astrocytic sub-type in different conditions (SC, 5d, or 15d HFHS diet) by applying Moran I spatial autocorrelation coefficient, previously described as an indicator of the level of spatial dispersion. On top of that, employing a random forest classifier determine the partitioning of the feature space shared by astrocytes expressing Gfap and Aldh1l1 in each experimental group.

Installation

The package Csppa depends on spatstat and on R >= 3.0.0 and is available from GitHub. This requires the package devtools:

devtools::install_github("viktormiok/Csppa", build_vignettes=TRUE)

Please restart R before loading the package and its documentation:

library(Csppa)
utils::help(Csppa)
utils::vignette("Csppa")

Data

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

Data type Data link
Aldh1l1 only link
Gfap only link
Double positive link

Tutorials

Please see the following tutorials for detailed examples of how to use Csppa:

Csppa walkthrough:

License

Csppa is distributed under the MIT license. Please read the license before using Csppa, which it is distributed in the LICENSE file.

References

Publications related to Csppa include:

Please cite the relevant publications if you use Csppa.