Merge remote-tracking branch 'compbiomed/devel' into devel

.Rbuildignore

@@ -17,3 +17,4 @@ exec/png
 ^\.github$
 ^vignettes/articles/*
 ^images
+.dockerignore

.dockerignore

@@ -0,0 +1,7 @@
+.RData
+.Rhistory
+.git
+.gitignore
+manifest.json
+rsconnect/
+.Rproj.user

DESCRIPTION

@@ -118,8 +118,9 @@ Imports:
     scuttle,
     utils,
     stats,
-    zellkonverter
-RoxygenNote: 7.3.1
+    zellkonverter,
+    tidyr
+RoxygenNote: 7.3.2
 Suggests:
     testthat,
     Rsubread,

R/computeHeatmap.R

@@ -131,6 +131,13 @@ computeHeatmap <- function(inSCE,
     features[[i]] <- .convertToHyphen(features[[i]])
   }
 
+  ## temp fix
+  # make sure the cell names are consistent
+  # UPDATE THIS IN .convertSCEToSeurat function eventually
+  rownames(object@reductions$pca@cell.embeddings) <- 
+    unlist(.convertToHyphen(rownames(object@reductions$pca@cell.embeddings)))
+  ## 
+
   object <- Seurat::ScaleData(object, features = features.all)
 
   # get assay data with only selected features (all dims) and

R/doubletFinder_doubletDetection.R

@@ -342,6 +342,7 @@
 #' @seealso \code{\link{runCellQC}}, \code{\link{plotDoubletFinderResults}}
 #' @examples
 #' data(scExample, package = "singleCellTK")
+#' options(future.globals.maxSize = 786432000)
 #' sce <- subsetSCECols(sce, colData = "type != 'EmptyDroplet'")
 #' sce <- runDoubletFinder(sce)
 #' @export

R/dropletUtils_emptyDrops.R

@@ -26,7 +26,7 @@
 
 #' @title Identify empty droplets using \link[DropletUtils]{emptyDrops}.
 #' @description Run \link[DropletUtils]{emptyDrops} on the count matrix in the
-#' provided \\linkS4class{SingleCellExperiment} object.
+#' provided \linkS4class{SingleCellExperiment} object.
 #' Distinguish between droplets containing cells and ambient RNA in a
 #' droplet-based single-cell RNA sequencing experiment.
 #' @param inSCE A \linkS4class{SingleCellExperiment} object. Must contain a raw 

R/ggPlotting.R

@@ -852,11 +852,19 @@ plotSCEScatter <- function(inSCE,
                       vcolor = "red",
                       vsize = 1,
                       vlinetype = 1) {
+
+  mult_modules <- FALSE
+
   if (is.null(groupBy)) {
-    groupBy <- rep("Sample", length(y))
+    if (length(colnames(y)) > 1){
+      mult_modules <- TRUE
+      groupBy <- rep(colnames(y), each = dim(y)[1])
+      y <- tidyr::pivot_longer(as.data.frame(y), cols = 1:dim(y)[2], cols_vary = "slowest")$value#
+    }else{
+      groupBy <- rep("Sample", length(y))
+    }
   }
 
-
   if(!is.factor(groupBy)){
     if(is.null(plotOrder)){
       plotOrder = unique(groupBy)
@@ -920,6 +928,10 @@ plotSCEScatter <- function(inSCE,
                             axis.title.x = ggplot2::element_blank())
   }
 
+  if (mult_modules){
+    p <- p + xlab("Modules")
+  }
+
   if (gridLine == TRUE){
     p <- p + ggplot2::theme(panel.grid.major.y = ggplot2::element_line("grey"))
   }
@@ -1417,9 +1429,9 @@ plotSCEViolinAssayData <- function(inSCE,
 #' @param feature Desired name of feature stored in assay of SingleCellExperiment
 #'  object. Only used when "assays" slotName is selected. Default NULL.
 #' @param sample Character vector. Indicates which sample each cell belongs to.
-#' @param dimension Desired dimension stored in the specified reducedDims.
-#'  Either an integer which indicates the column or a character vector specifies
-#'  column name. By default, the 1st dimension/column will be used.
+#' @param dimension Desired dimension(s) stored in the specified reducedDims.
+#'  Either an integer which indicates the column(s) or a character vector specifies
+#'  column name(s). By default, the 1st dimension/column will be used.
 #'  Only used when "reducedDims" slotName is selected. Default NULL.
 #' @param groupBy Groupings for each numeric value. A user may input a vector
 #' equal length to the number of the samples in the SingleCellExperiment
@@ -1568,7 +1580,11 @@ plotSCEViolin <- function(inSCE,
   samples <- unique(sample)
   plotlist <- lapply(samples, function(x) {
     sampleInd <- which(sample == x)
-    countSub <- counts[sampleInd]
+    if (length(colnames(counts)) > 1){
+      countSub <- counts[sampleInd,]
+    }else{
+      countSub <- counts[sampleInd]
+    }
     if(!is.null(groupBy)){
       groupbySub <- groupBy[sampleInd]
     }else{

R/miscFunctions.R

@@ -191,18 +191,18 @@ discreteColorPalette <- function(n, palette = c("random", "ggplot", "celda"),
 #' Adds '-1', '-2', ... '-i' to multiple duplicated rownames, and in place
 #' replace the unique rownames, store unique rownames in \code{rowData}, or
 #' return the unique rownames as character vecetor.
-#' @param x A matrix like or /linkS4class{SingleCellExperiment} object, on which
+#' @param x A matrix like or \linkS4class{SingleCellExperiment} object, on which
 #' we can apply \code{rownames()} to and has duplicated rownames.
 #' @param as.rowData Only applicable when \code{x} is a
-#' /linkS4class{SingleCellExperiment} object. When set to \code{TRUE}, will
+#' \linkS4class{SingleCellExperiment} object. When set to \code{TRUE}, will
 #' insert a new column called \code{"rownames.uniq"} to \code{rowData(x)}, with
 #' the deduplicated rownames.
 #' @param return.list When set to \code{TRUE}, will return a character vector
 #' of the deduplicated rownames.
 #' @export
-#' @return By default, a matrix or /linkS4class{SingleCellExperiment} object
+#' @return By default, a matrix or \linkS4class{SingleCellExperiment} object
 #' with rownames deduplicated.
-#' When \code{x} is a /linkS4class{SingleCellExperiment} and \code{as.rowData}
+#' When \code{x} is a \linkS4class{SingleCellExperiment} and \code{as.rowData}
 #' is set to \code{TRUE}, will return \code{x} with \code{rowData} updated.
 #' When \code{return.list} is set to \code{TRUE}, will return a character vector
 #' with the deduplicated rownames.

R/plotBubble.R

@@ -12,7 +12,7 @@
 #' @param ylab The y-axis label
 #' @param colorLow The color to be used for lowest value of mean expression
 #' @param colorHigh The color to be used for highest value of mean expression
-#' @param scale Option to scale the data. Default: /code{FALSE}. Selected assay will not be scaled. 
+#' @param scale Option to scale the data. Default: \code{FALSE}. Selected assay will not be scaled. 
 #' @return A ggplot of the bubble plot.
 #' @importFrom rlang .data
 #' @importFrom reshape2 melt

R/runBatchCorrection.R

@@ -670,7 +670,7 @@ integrated = integrated[:, orderIdx]
 #' variable genes identification. Default \code{"counts"}.
 #' @param kmeansK An integer vector. Indicating the kmeans' K-value for each
 #' batch (i.e. how many subclusters in each batch should exist), in order to
-#' construct pseudo-replicates. The length of code{kmeansK} needs to be the same
+#' construct pseudo-replicates. The length of \code{kmeansK} needs to be the same
 #' as the number of batches. Default \code{NULL}, and this value will be
 #' auto-detected by default, depending on \code{cellType}.
 #' @param cellType A single character. A string indicating a field in

R/runClusterSummaryMetrics.R

@@ -7,7 +7,7 @@
 #' @param featureNames A string or vector of strings with each gene to aggregate.
 #' @param displayName A string that is the name of the column used for genes.
 #' @param groupNames The name of a colData entry that can be used as groupNames.
-#' @param scale Option to scale the data. Default: /code{FALSE}. Selected assay will not be scaled. 
+#' @param scale Option to scale the data. Default: \code{FALSE}. Selected assay will not be scaled. 
 #' @return A dataframe with mean expression and percent of cells in cluster that 
 #' express for each cluster.
 #' @examples

R/runDimReduce.R

@@ -76,7 +76,7 @@ runDimReduce <- function(inSCE,
                        seed = seed, ...)
   } else if (method == "scaterUMAP") {
     inSCE <- runUMAP(inSCE = inSCE, useAssay = useAssay, useAltExp = useAltExp,
-                     useReducedDim = useReducedDim, initialDims = 25,
+                     useReducedDim = useReducedDim,
                      useFeatureSubset = useFeatureSubset, scale = scale,
                      reducedDimName = reducedDimName, seed = seed, ...)
   } else if (method == "scanpyPCA"){