run_nn_correlation: Generate nearest neighbour correlation

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

Generate nearest neighbour correlation

Description

This function calculates the nearest neighbour correlation for each feature (eg, proteins) in each sample. This is calculated by taking the correlation between each cell and its nearest neighbours cell for a particular feature. This function supports spatial proteomics, and spatial transcriptomics.

Usage

run_nn_correlation(data, type = "spatial_p", num_top_gene = NULL, 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".
num_top_gene	Number of top variable genes to use when genes is not provided. Defaults to 1500.
ncores	Number of cores for parallel processing.

Value

a dataframe of samples x features The features are in the form of protein 1, protein 2 ... etc, with the numbers representing Pearson's correlation.

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_nn_correlation <- run_nn_correlation(
    alldata, type = "spatial_p", ncores = 1
)

SydneyBioX/scFeatures documentation built on March 13, 2024, 12:36 a.m.