run_celltype_interaction: Generate cell type interaction

In SydneyBioX/scFeatures: scFeatures: Multi-view representations of single-cell and spatial data for disease outcome prediction

Generate cell type interaction

Description

This function calculates the pairwise distance between cell types for a sample by using the coordinates and cell types of the cells. We find the nearest neighbours of each cell and the cell types of these neighbours. These are considered as spatial interaction pairs. The cell type composition of the spatial interaction pairs are used as features. The function supports spatial proteomics and spatial transcriptomics.

Usage

run_celltype_interaction(data, type = "spatial_p", ncores = 1)

Arguments

data	A list object containing data matrix and celltype and sample vector.
type	The type of dataset, either "scrna", "spatial_t", or "spatial_p".
ncores	Number of cores for parallel processing.

Value

a dataframe of samples x features The features are in the form of protein 1 vs protein 2, protein 1 vs protein 3 ... etc, with the numbers representing the proportion of each interaction pairs in a give sample.

Examples

utils::data("example_scrnaseq" , package = "scFeatures")
data <- example_scrnaseq[1:50, 1:20]
celltype <- data$celltype 
data <- data@assays$RNA@data
sample <- sample( c("patient1", "patient2", "patient3"), ncol(data) , replace= TRUE )
x <- sample(1:100, ncol(data) , replace = TRUE)
y <- sample(1:100, ncol(data) , replace = TRUE)
spatialCoords <- list( x , y)
alldata <- scFeatures:::formatData(data = data, sample = sample, celltype = celltype, 
spatialCoords  = spatialCoords )

feature_celltype_interaction <- run_celltype_interaction(
    alldata, type = "spatial_p", ncores = 1
)

SydneyBioX/scFeatures documentation built on Nov. 30, 2024, 6:40 p.m.