Updates to data files.

DESCRIPTION

@@ -3,7 +3,7 @@ Type: Package
 Title: clustSIGNAL: a spatial clustering method
 Version: 0.1.0
 Author: c(
-    person(given = "Pratibha", family = "Panwar", email = "[email protected]", role = c("cre", "aut")),
+    person(given = "Pratibha", family = "Panwar", email = "[email protected]", role = c("cre", "aut", "ctb")),
     person(given = "Boyi", family = "Guo", email = "", role = "aut")),
     person(given = "Haowen", family = "Zhao", email = "", role = "aut")),
     person(given = "Stephanie", family = "Hicks", email = "", role = "aut")),
@@ -18,9 +18,30 @@ Description: clustSIGNAL: clustering of Spatially Informed Gene expression with
 License: GPL-2
 Encoding: UTF-8
 LazyData: true
+LazyDataCompression: xz
+URL: https://sydneybiox.github.io/clustSIGNAL/, https://sydneybiox.github.io/clustSIGNAL/
+BugReports: https://github.com/sydneybiox/clustSIGNAL/issues
+biocViews: Clustering, Software 
+Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.3.2
-Depends: R (>= 4.0.0), SpatialExperiment, doParallel
-Imports: BiocNeighbors, bluster, scater, aricode, distances, cluster, ggplot2, patchwork, BiocStyle
-Sugests: knitr, rmarkdown
-VignetteBuilder: knitr, rmarkdown
-URL: https://sydneybiox.github.io/clustSIGNAL/
+Depends: 
+    R (>= 4.0.0), 
+    SpatialExperiment, 
+    doParallel
+Imports: 
+    BiocNeighbors, 
+    bluster, 
+    scater, 
+    aricode, 
+    distances, 
+    cluster, 
+    ggplot2, 
+    patchwork, 
+    BiocStyle,
+    dplyr
+Suggests: 
+    knitr, 
+    rmarkdown
+VignetteBuilder: 
+    knitr, 
+    rmarkdown

R/adaptiveSmoothing.R

@@ -21,7 +21,7 @@
 #' @export
 
 #### Smoothing
-adaptiveSmoothing <- function(spe, nnCells, NN, kernel, spread) {
+adaptiveSmoothing <- function(spe, nnCells, NN = 30, kernel = "G", spread = 0.05) {
     ed = unique(spe$entropy)
     gXc = as(logcounts(spe), "sparseMatrix")
     if (kernel == "G") {

R/clustering.R

@@ -4,7 +4,9 @@
 #' A function containing two steps used at different times in the clustSIGNAL workflow. An initial non-spatial clustering and sub-clustering step (reclust = FALSE) is used to generate groups of ‘putative cell types’, whereas a later non-spatial clustering step (reclust = TRUE) is used to cluster adaptively smoothed gene expression data.
 #'
 #' @param spe SpatialExperiment object. For reclust = FALSE, the object should contain logcounts and PCA, but for reculst = TRUE, the object should contain smoothed gene expression.
+#' @param dimRed a character indicating the name of the reduced dimensions to use from the SpatialExperiment object (i.e., from reducedDimNames(spe)). Default value is 'PCA'.
 #' @param reclust a logical parameter handled within the method.
+#' @param ... additional parameters for TwoStepParam clustering methods. Include parameters like k for number of nearest neighbours and cluster.fun for selecting community detection method. Default values k = 5, cluster.fun = "louvain".
 #'
 #' @return SpatialExperiment object containing 'putative cell type' group allotted to each cell (reclust = FALSE) or clusters generated from smoothed data (reclust = TRUE).
 #'
@@ -22,7 +24,7 @@
 #' @export
 
 #### Non-spatial clustering
-nsClustering <- function(spe, dimRed, reclust, ...) {
+nsClustering <- function(spe, dimRed = "PCA", reclust, ...) {
     # number of centers = 1/5th of total cells in sample
     clustVal <- min(as.integer(ncol(spe) / 5), 50000)
     if (reclust == FALSE) {

R/data.R

@@ -0,0 +1,53 @@
+#' Mouse Embryo Data as SpatialExperiment object
+#'
+#' This dataset contains spatial transcriptomics data from 3 mouse embryos, with
+#' 351 genes and a total of 57536 cells. For running vignettes and examples, we subset
+#' the data by selecting only embryo 2 and removed all cells that were annotated
+#' as 'low quality'. After subsetting, we have 14,185 cells from embryo 2 and 351
+#' genes.
+#'
+#'
+#' @name mEmbryo2
+#' @aliases nnCells me_data me_expr regXclust
+#' @docType data
+#' @format
+#' \code{me_expr} a gene expression matrix with normalised counts, where rows indicate
+#' genes and columns indicate cells.
+#' \code{me_data} a data frame of cell metadata including cell IDs, sample IDs,
+#' cell type annotations, and x-y coordinates of cells.
+#' \code{nnCells} a matrix where each row corresponds to a cell in spe object,
+#' and the columns correspond to the nearest neighbors.
+#' \code{regXclust} a list where each element corresponds to a cell in spe object,
+#' and contains the cluster composition proportions.
+#' @usage load("mEmbryo2.RData")
+#' @source Integration of spatial and single-cell transcriptomic data elucidates mouse
+#' organogenesis, \emph{Nature Biotechnology}, 2022.
+#' Webpage: \url{https://www.nature.com/articles/s41587-021-01006-2}
+#' @keywords datasets
+NULL
+
+
+#' Mouse Hypothalamus Data as SpatialExperiment object
+#'
+#' This dataset contains spatial transcriptomics data from 181 mouse hypothalamus
+#' samples embryos, 155 genes and a total of 1,027,080 cells. For running the
+#' vignettes, we subset the data by selecting only 3 samples - Animal 1 Bregma -0.09
+#' and Animal 7 Bregmas 0.16 and -0.09, removed all cells that were annotated
+#' as 'ambiguous', and removed 20 genes that were assessed using a different technology.
+#' After subsetting, we have 15,848 cells from 3 mouse brain samples and 135 genes.
+#'
+#'
+#' @name mHypothal
+#' @aliases mh_data mh_expr
+#' @docType data
+#' @format
+#' \code{mh_expr} a gene expression matrix with normalised counts, where rows indicate
+#' genes and columns indicate cells.
+#' \code{mh_data} a data frame of cell metadata including cell IDs, sample IDs,
+#' cell type annotations, and x-y coordinates of cells.
+#' @usage load("mHypothal.RData")
+#' @source Molecular, Spatial and Functional Single-Cell Profiling of the
+#' Hypothalamic Preoptic Region, \emph{Science}, 2018.
+#' Webpage: \url{https://www.science.org/doi/10.1126/science.aau5324}
+#' @keywords datasets
+NULL

R/entropyMeasure.R

@@ -21,7 +21,7 @@
 #' @export
 
 #### Domainness measure
-entropyMeasure <- function(spe, cells, regXclust, threads) {
+entropyMeasure <- function(spe, cells, regXclust, threads = 1) {
     cellsList <- as.vector(spe[[cells]])
     cl <- parallel::makeCluster(threads)
     doParallel::registerDoParallel(cl)

R/neighborDetect.R

@@ -24,7 +24,7 @@
 #' @export
 
 #### Region description + sorting
-neighbourDetect <- function(spe, samples, NN, cells, sort) {
+neighbourDetect <- function(spe, samples, NN = 30, cells, sort = TRUE) {
     samplesList <- unique(spe[[samples]])
     nnCells <- matrix(nrow = 0, ncol = NN + 1)
     nnClusts <- matrix(nrow = 0, ncol = NN)