wSIR: Weighted Sliced Inverse Regression for supervised dimension reduction of spatial transcriptomics and single cell gene expression data

This is an R package for computation of the wSIR low-dimensional embedding of gene expression data, using its spatial coordinates. It includes functions to analyse the resulting low-dimensional space, as well as the mapping from high-dimensional gene expression data to low-dimensional space. There is a function to project new gene expression data (where the spatial coordinates are unknown) into a low-dimensional space which has the ability to predict each cell's spatial location.

For an overview of the method and examples, see the vignette at this website.

To install wSIR via Bioconductor: (note this won't work yet, only once wSIR is actually on Bioconductor)

library(BiocManager)
BiocManager::install("wSIR")

To install wSIR from GitHub:

library(devtools)
install_github("SydneyBioX/wSIR")

The analysis codes to recreate the results from the paper are available here.