@@ -44,6 +44,7 @@ export(importGeneSetsFromCollection)

 export(importGeneSetsFromGMT)

 export(importGeneSetsFromList)

 export(importGeneSetsFromMSigDB)

+export(importMitoGeneSet)

 export(importMultipleSources)

 export(importOptimus)

 export(importSEQC)

@@ -75,3 +75,18 @@

 #' @examples

 #' data("msigdb_table")

 "msigdb_table"

+

+#' List of mitochondrial genes of multiple reference

+#' 

+#' A list of gene set that contains mitochondrial genes of multiple reference

+#' (hg38, hg19, mm10 and mm9). It contains multiple types of gene identifier:

+#' gene symbol, entrez ID, ensemble ID and ensemble transcript ID. It's used 

+#' for the function 'importMitoGeneSet'. 

+

+#' @name MitoGenes

+#' @docType data

+#' @format A list

+#' @keywords datasets

+#' @examples

+#' data("MitoGenes")

+"MitoGenes"

\ No newline at end of file

@@ -1,6 +1,6 @@

 .importAnnDataSample <- function(sampleDir = './',

                                  sampleName = 'sample',

-                                 delayedArray = TRUE){

+                                 delayedArray = FALSE){

   anndata_file <- file.path(sampleDir, paste0(sampleName,'.h5ad',sep=''))

   if (!file.exists(anndata_file)){

@@ -83,7 +83,7 @@

 #'   with the sample name appended to each colname in colData

 #' }

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object. Default \code{TRUE}.

+#'  \link{DelayedArray} object. Default \code{FALSE}.

 #' @details

 #' \code{importAnnData} converts scRNA-seq data in the AnnData format to the

 #' \code{SingleCellExperiment} object. The .X slot in AnnData is transposed to the features x cells

@@ -107,7 +107,7 @@

 #' @export

 importAnnData <- function(sampleDirs = NULL,

                           sampleNames = NULL,

-                          delayedArray = TRUE) {

+                          delayedArray = FALSE) {

   if (length(sampleDirs)!=length(sampleNames)){

     stop("Number of sampleDirs must be equal to number of SampleNames. Please provide sample names for all input directories")

@@ -102,7 +102,7 @@

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default "Matrix".

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link[DelayedArray]{DelayedArray-class} object or not. Default \code{TRUE}.

+#'  \link[DelayedArray]{DelayedArray-class} object or not. Default \code{FALSE}.

 #' @return A \code{SingleCellExperiment} object containing the count

 #'  matrix, the gene annotation, and the cell annotation.

 #' @examples

@@ -140,7 +140,7 @@ importBUStools <- function(

     barcodesFileNames = "genes.barcodes.txt",

     gzipped = "auto",

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE) {

+    delayedArray = FALSE) {

     class <- match.arg(class)

@@ -512,7 +512,7 @@

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default \code{"Matrix"}.

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @param reference Character vector. The reference genome names. 

 #'  Default \code{NULL}. If not \code{NULL}, it must gave the length and order as 

 #'  \code{length(unlist(sampleDirs))} if \code{sampleDirs} is not \code{NULL}.

@@ -570,7 +570,7 @@ importCellRanger <- function(

     barcodesFileNames = "barcodes.tsv.gz",

     gzipped = "auto",

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE) {

+    delayedArray = FALSE) {

     class <- match.arg(class)

     dataType <- match.arg(dataType)

@@ -608,7 +608,7 @@ importCellRangerV2 <- function(

     sampleNames = NULL,

     dataTypeV2 = c("filtered", "raw"),

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE,

+    delayedArray = FALSE,

     reference = NULL,

     cellRangerOutsV2 = NULL) {

@@ -656,7 +656,7 @@ importCellRangerV2 <- function(

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default "Matrix".

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @return A \code{SingleCellExperiment} object containing the count

 #'  matrix, the feature annotations, and the cell annotation for the sample.

 #' @examples

@@ -669,7 +669,7 @@ importCellRangerV2Sample <- function(

     dataDir = NULL,

     sampleName = NULL,

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE) {

+    delayedArray = FALSE) {

     class <- match.arg(class)

@@ -701,7 +701,7 @@ importCellRangerV3 <- function(

     sampleNames = NULL,

     dataType = c("filtered", "raw"),

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE) {

+    delayedArray = FALSE) {

     class <- match.arg(class)

     dataType <- match.arg(dataType)

@@ -740,7 +740,7 @@ importCellRangerV3 <- function(

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default "Matrix".

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @return A \code{SingleCellExperiment} object containing the count

 #'  matrix, the feature annotations, and the cell annotation for the sample.

 #' @examples

@@ -753,7 +753,7 @@ importCellRangerV3Sample <- function(

     dataDir = "./",

     sampleName = "sample",

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE) {

+    delayedArray = FALSE) {

     class <- match.arg(class)

@@ -91,7 +91,7 @@

 #' @param dataType can be "filtered" or "raw". Default \code{"filtered"}.

 #' @param rdsFileName File name prefix of the DropEst RDS output. default is "cell.counts"

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @details

 #' \code{importDropEst} expects either raw counts matrix stored as "cm_raw" or filtered

 #' counts matrix stored as "cm" in the DropEst rds output.

@@ -114,7 +114,7 @@ importDropEst <- function(sampleDirs = NULL,

                           dataType = c('filtered','raw'),

                           rdsFileName = 'cell.counts',

                           sampleNames = NULL,

-                          delayedArray = TRUE) {

+                          delayedArray = FALSE) {

   dataType <- match.arg(dataType)

   if (length(sampleDirs)!=length(sampleNames)){

@@ -41,7 +41,7 @@

 #' @param featureSep Separater used for the feature annotation file. Default is "\\t".

 #' @param gzipped Whether the input file is gzipped. Default is "auto" and it will automatically detect whether the file is gzipped. Other options is TRUE or FALSE. 

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @return a SingleCellExperiment object

 #' @export

@@ -428,6 +428,75 @@ importGeneSetsFromMSigDB <- function(inSCE, categoryIDs,

 }

+

+#' @title Import mitochondrial gene sets

+#' @description Imports mitochondrial gene sets and  stores it in the metadata of the

+#' \linkS4class{SingleCellExperiment} object. These gene sets can be used in

+#' downstream quality control and analysis functions in \link{singleCellTK}. 

+#' @param inSCE Input \linkS4class{SingleCellExperiment} object.

+#' @param reference Character. Species available are "hg38", "hg19", "mm9" and "mm10." 

+#' @param by Character. Describes the location within \code{inSCE} where the gene 

+#' identifiers in the mitochondrial gene sets should be mapped. 

+#' If set to \code{"rownames"} then the features will

+#' be searched for among \code{rownames(inSCE)}. This can also be

+#' set to one of the column names of \code{rowData(inSCE)} in which case the

+#' gene identifies will be mapped to that column in the \code{rowData}

+#' of \code{inSCE}. See \link{featureIndex} for more information.

+#' Default \code{"rownames"}.

+#' @param id Types of gene id. Now it supports "symbol", "entrez", "ensemble"

+#' and "ensemble_transcriptID". 

+#' @param collectionName Character. Name of collection to add gene sets to.

+#' If this collection already exists in \code{inSCE}, then these gene sets will

+#' be added to that collection. Any gene sets within the collection with the

+#' same name will be overwritten.

+#' @return A \link[SingleCellExperiment]{SingleCellExperiment} object

+#' with gene set from \code{collectionName} output stored to the

+#' \link{metadata} slot.

+#' @details The gene identifiers of mitochondrial genes will be loaded with 

+#' "data(AllMito)". Currently, it supports hg38, hg19, mm9 and mm10 reference. 

+#' Also, it supports entrez ID, gene symbol, ensemble ID and ensemble transcript ID. 

+#' They will be mapped to the IDs in \code{inSCE} using the \code{by} parameter and

+#' stored in a \linkS4class{GeneSetCollection} object from package

+#' \link{GSEABase}. This object is stored in

+#' \code{metadata(inSCE)$sctk$genesets}, which can be accessed in downstream

+#' analysis functions such as \link[singleCellTK]{runCellQC}.

+#' @author Rui Hong

+#' @seealso \link{importGeneSetsFromList} for importing from lists,

+#' \link{importGeneSetsFromGMT} for importing from GMT files, and

+# \link{importGeneSetsFromCollection} for importing from

+#' \linkS4class{GeneSetCollection} objects.

+#' @examples

+#' data(scExample)

+#' sce <- importMitoGeneSet(inSCE = sce,

+#'                          reference = "hg38",

+#'                          id = "ensemble",

+#'                          collectionName = "hg38_mito",

+#'                          by = "rownames")

+#' @export

+importMitoGeneSet <- function(inSCE, reference, id, by, collectionName) {

+  if (!id %in% c("symbol", "entrez", "ensemble", "ensemble_transcriptID")) {

+    stop("id should be one of 'symbol', 'entrez', 'ensemble' or 'ensemble_transcriptID'")

+  }

+  

+  if (!reference %in% c("hg38", "hg19", "mm10", "mm9")) {

+    stop("Now it only supports hg38, hg19, mm10 and mm9 reference.")

+  }

+  

+  #utils::globalVariables(c("AllMito"))

+  MitoGenes <- NULL

+  utils::data(MitoGenes, envir = environment())

+  target <- paste(reference, id, sep="_")

+  if (!target %in% names(MitoGenes)) {

+    stop(target, " is not supported now. Please use function 'importGeneSetsFromGMT' or 'importGeneSetsFromList' to load mitochondrial gene sets.")

+  }

+  

+  mitogenes <- MitoGenes[[target]]

+  inSCE <- importGeneSetsFromList(inSCE = inSCE, geneSetList = mitogenes,

+                                  collectionName = collectionName, 

+                                  by = by)

+  return(inSCE)

+}

+

 #' @title Lists imported GeneSetCollections

 #' @description Returns a vector of GeneSetCollections that have been

 #' imported and stored in \code{metadata(inSCE)$sctk$genesets}.

@@ -2,7 +2,7 @@

 #' Imports samples from different sources and compiles them into a list of SCE objects

 #' @param allImportEntries object containing the sources and parameters of all the samples being imported (from the UI)

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @return A list of \link[SingleCellExperiment]{SingleCellExperiment} object containing

 #' the droplet or cell data or both,depending on the dataType that users provided.

 #' @export

@@ -246,7 +246,7 @@

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default "Matrix".

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @return A \link[SingleCellExperiment]{SingleCellExperiment} object

 #'  containing the count

 #'  matrix, the gene annotation, and the cell annotation.

@@ -267,7 +267,7 @@ importOptimus <- function(OptimusDirs,

   geneMetricsLocation = "call-MergeGeneMetrics/merged-gene-metrics.csv.gz",

   emptyDropsLocation = "call-RunEmptyDrops/empty_drops_result.csv",

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE) {

+  delayedArray = FALSE) {

   class <- match.arg(class)

@@ -110,7 +110,7 @@

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default "Matrix".

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @return A \code{SingleCellExperiment} object containing the count

 #'  matrix, the gene annotation, and the cell annotation.

 #' @examples

@@ -151,7 +151,7 @@ importSTARsolo <- function(

     barcodesFileNames = "barcodes.tsv",

     gzipped = "auto",

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE) {

+    delayedArray = FALSE) {

     class <- match.arg(class)

@@ -167,7 +167,7 @@

 #'  \link{readMM} function), or "matrix" (as returned by

 #'  \link[base]{matrix} function). Default "Matrix".

 #' @param delayedArray Boolean. Whether to read the expression matrix as

-#'  \link{DelayedArray} object or not. Default \code{TRUE}.

+#'  \link{DelayedArray} object or not. Default \code{FALSE}.

 #' @param feNotFirstCol Boolean. \code{TRUE} if first column of

 #'  sparse_counts_genes.csv

 #' is row index and it will be removed. \code{FALSE} the first column will

@@ -217,7 +217,7 @@ importSEQC <- function(

     prefix = NULL,

     gzipped = FALSE,

     class = c("Matrix", "matrix"),

-    delayedArray = TRUE,

+    delayedArray = FALSE,

     cbNotFirstCol = TRUE,

     feNotFirstCol = TRUE,

     combinedSample = TRUE) {

@@ -1,6 +1,6 @@

 #' @title Wrapper for calculating QC metrics with scater.

-#' @description A wrapper function for \link[celda]{decontX}. Identify

-#'  potential contamination from experimental factors such as ambient RNA.

+#' @description A wrapper function for \link[scater]{addPerCellQC}. Calculate

+#'  general quality control metrics for each cell in the count matrix.

 #' @param inSCE Input \link[SingleCellExperiment]{SingleCellExperiment} object.

 #' @param useAssay A string specifying which assay in the SCE to use. Default \code{"counts"}.

 #' @param collectionName Character. Name of a \code{GeneSetCollection} obtained by using one of the importGeneSet* functions. Default \code{NULL}.

new file mode 100644

Binary files /dev/null and b/data/MitoGenes.rda differ

@@ -216,7 +216,7 @@ if (numCores > 1) {

 ### checking output formats

 if (!all(formats %in% c("SCE", "AnnData", "FlatFile", "HTAN"))) {

     warning("Output format must be 'SCE', 'AnnData', 'HTAN' or 'FlatFile'. Format ", 

-         paste(formats[!format %in% c("SCE", "AnnData", "FlatFile", "HTAN")], sep = ","),

+         paste(formats[!formats %in% c("SCE", "AnnData", "FlatFile", "HTAN")], collapse = ","),

          " is not supported now. ")

 }

@@ -531,6 +531,11 @@ for(i in seq_along(process)) {

             reportDropletQC(inSCE = mergedDropletSCE, output_dir = directory, output_file = paste0("SCTK_", samplename,'_dropletQC.html'), subTitle = subTitle, studyDesign = studyDesign)

             reportCellQC(inSCE = mergedFilteredSCE, output_dir = directory, output_file = paste0("SCTK_", samplename,'_cellQC.html'), subTitle = subTitle, studyDesign = studyDesign)

+            ## generate QC metrics table for mergedFilteredSCE

+            QCsummary <- sampleSummaryStats(mergedFilteredSCE, simple=FALSE, sample = colData(mergedFilteredSCE)$sample) #colData(cellSCE)$Study_ID

+            write.csv(QCsummary, file.path(directory, 

+                                           samplename,

+                                           paste0("SCTK_", samplename,'_cellQC_summary.csv')))

         }

         if ((dataType == "Droplet") & (!isTRUE(detectCell))) {

@@ -577,6 +582,11 @@ for(i in seq_along(process)) {

             getSceParams(inSCE = mergedFilteredSCE, directory = directory, 

                          samplename = samplename, writeYAML = TRUE,

                          skip = c("scrublet", "runDecontX", "runBarcodeRanksMetaOutput"))

+

+            QCsummary <- sampleSummaryStats(mergedFilteredSCE, simple=FALSE, sample = colData(mergedFilteredSCE)$sample) #colData(cellSCE)$Study_ID

+            write.csv(QCsummary, file.path(directory, 

+                                           samplename,

+                                           paste0("SCTK_", samplename,'_cellQC_summary.csv')))

         }

     }

@@ -628,6 +638,12 @@ if (!isTRUE(split)) {

         } else {

             warning("'FlatFile' is not in output format. Skip exporting the manifest file.")

         }

+

+        ## generate QC summary

+        QCsummary <- sampleSummaryStats(cellSCE, simple=FALSE, sample = colData(cellSCE)$sample) 

+        write.csv(QCsummary, file.path(directory,

+                                       samplename, 

+                                       paste0("SCTK_", samplename,'_cellQC_summary.csv')))

     }

     if (dataType == "Cell") {

@@ -658,6 +674,11 @@ if (!isTRUE(split)) {

         reportCellQC(inSCE = cellSCE, output_dir = directory, output_file = paste0("SCTK_", samplename,'_cellQC.html'), subTitle = subTitle, studyDesign = studyDesign)

         getSceParams(inSCE = cellSCE, directory = directory, samplename = samplename, writeYAML = TRUE)

+

+        QCsummary <- sampleSummaryStats(cellSCE, simple=FALSE, sample = colData(cellSCE)$sample) 

+        write.csv(QCsummary, file.path(directory,

+                                       samplename, 

+                                       paste0("SCTK_", samplename,'_cellQC_summary.csv')))

     }

     if ((dataType == "Droplet") & (!isTRUE(detectCell))) {

new file mode 100644

@@ -0,0 +1,22 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/data.R

+\docType{data}

+\name{MitoGenes}

+\alias{MitoGenes}

+\title{List of mitochondrial genes of multiple reference}

+\format{

+A list

+}

+\usage{

+MitoGenes

+}

+\description{

+A list of gene set that contains mitochondrial genes of multiple reference

+(hg38, hg19, mm10 and mm9). It contains multiple types of gene identifier:

+gene symbol, entrez ID, ensemble ID and ensemble transcript ID. It's used 

+for the function 'importMitoGeneSet'.

+}

+\examples{

+data("MitoGenes")

+}

+\keyword{datasets}

@@ -4,7 +4,7 @@

 \alias{importAnnData}

 \title{Create a SingleCellExperiment Object from Python AnnData .h5ad files}

 \usage{

-importAnnData(sampleDirs = NULL, sampleNames = NULL, delayedArray = TRUE)

+importAnnData(sampleDirs = NULL, sampleNames = NULL, delayedArray = FALSE)

 }

 \arguments{

 \item{sampleDirs}{Folder containing the .h5ad file. Can be one of -

@@ -30,7 +30,7 @@ Can be one of -

 }}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object. Default \code{TRUE}.}

+\link{DelayedArray} object. Default \code{FALSE}.}

 }

 \value{

 A \code{SingleCellExperiment} object.

@@ -12,7 +12,7 @@ importBUStools(

   barcodesFileNames = "genes.barcodes.txt",

   gzipped = "auto",

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -46,7 +46,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link[DelayedArray]{DelayedArray-class} object or not. Default \code{TRUE}.}

+\link[DelayedArray]{DelayedArray-class} object or not. Default \code{FALSE}.}

 }

 \value{

 A \code{SingleCellExperiment} object containing the count

@@ -17,7 +17,7 @@ importCellRanger(

   barcodesFileNames = "barcodes.tsv.gz",

   gzipped = "auto",

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 importCellRangerV2(

@@ -26,7 +26,7 @@ importCellRangerV2(

   sampleNames = NULL,

   dataTypeV2 = c("filtered", "raw"),

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE,

+  delayedArray = FALSE,

   reference = NULL,

   cellRangerOutsV2 = NULL

 )

@@ -37,7 +37,7 @@ importCellRangerV3(

   sampleNames = NULL,

   dataType = c("filtered", "raw"),

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -138,7 +138,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default \code{"Matrix"}.}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 \item{dataTypeV2}{Character. The type of output to import for

 Cellranger version below 3.0.0. Whether to import the filtered or the 

@@ -8,7 +8,7 @@ importCellRangerV2Sample(

   dataDir = NULL,

   sampleName = NULL,

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -23,7 +23,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 }

 \value{

 A \code{SingleCellExperiment} object containing the count

@@ -8,7 +8,7 @@ importCellRangerV3Sample(

   dataDir = "./",

   sampleName = "sample",

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -23,7 +23,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 }

 \value{

 A \code{SingleCellExperiment} object containing the count

@@ -9,7 +9,7 @@ importDropEst(

   dataType = c("filtered", "raw"),

   rdsFileName = "cell.counts",

   sampleNames = NULL,

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -23,7 +23,7 @@ importDropEst(

 Default "sample".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 }

 \value{

 A \code{SingleCellExperiment} object containing the count matrix,

@@ -46,7 +46,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 \item{annotFileHeader}{Whether there's a header (colnames) in the cell annotation file. Default is FALSE}

new file mode 100644

@@ -0,0 +1,66 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/importGeneSets.R

+\name{importMitoGeneSet}

+\alias{importMitoGeneSet}

+\title{Import mitochondrial gene sets}

+\usage{

+importMitoGeneSet(inSCE, reference, id, by, collectionName)

+}

+\arguments{

+\item{inSCE}{Input \linkS4class{SingleCellExperiment} object.}

+

+\item{reference}{Character. Species available are "hg38", "hg19", "mm9" and "mm10."}

+

+\item{id}{Types of gene id. Now it supports "symbol", "entrez", "ensemble"

+and "ensemble_transcriptID".}

+

+\item{by}{Character. Describes the location within \code{inSCE} where the gene 

+identifiers in the mitochondrial gene sets should be mapped. 

+If set to \code{"rownames"} then the features will

+be searched for among \code{rownames(inSCE)}. This can also be

+set to one of the column names of \code{rowData(inSCE)} in which case the

+gene identifies will be mapped to that column in the \code{rowData}

+of \code{inSCE}. See \link{featureIndex} for more information.

+Default \code{"rownames"}.}

+

+\item{collectionName}{Character. Name of collection to add gene sets to.

+If this collection already exists in \code{inSCE}, then these gene sets will

+be added to that collection. Any gene sets within the collection with the

+same name will be overwritten.}

+}

+\value{

+A \link[SingleCellExperiment]{SingleCellExperiment} object

+with gene set from \code{collectionName} output stored to the

+\link{metadata} slot.

+}

+\description{

+Imports mitochondrial gene sets and  stores it in the metadata of the

+\linkS4class{SingleCellExperiment} object. These gene sets can be used in

+downstream quality control and analysis functions in \link{singleCellTK}.

+}

+\details{

+The gene identifiers of mitochondrial genes will be loaded with 

+"data(AllMito)". Currently, it supports hg38, hg19, mm9 and mm10 reference. 

+Also, it supports entrez ID, gene symbol, ensemble ID and ensemble transcript ID. 

+They will be mapped to the IDs in \code{inSCE} using the \code{by} parameter and

+stored in a \linkS4class{GeneSetCollection} object from package

+\link{GSEABase}. This object is stored in

+\code{metadata(inSCE)$sctk$genesets}, which can be accessed in downstream

+analysis functions such as \link[singleCellTK]{runCellQC}.

+}

+\examples{

+data(scExample)

+sce <- importMitoGeneSet(inSCE = sce,

+                         reference = "hg38",

+                         id = "ensemble",

+                         collectionName = "hg38_mito",

+                         by = "rownames")

+}

+\seealso{

+\link{importGeneSetsFromList} for importing from lists,

+\link{importGeneSetsFromGMT} for importing from GMT files, and

+\linkS4class{GeneSetCollection} objects.

+}

+\author{

+Rui Hong

+}

@@ -10,7 +10,7 @@ importMultipleSources(allImportEntries, delayedArray = FALSE)

 \item{allImportEntries}{object containing the sources and parameters of all the samples being imported (from the UI)}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 }

 \value{

 A list of \link[SingleCellExperiment]{SingleCellExperiment} object containing

@@ -14,7 +14,7 @@ importOptimus(

   geneMetricsLocation = "call-MergeGeneMetrics/merged-gene-metrics.csv.gz",

   emptyDropsLocation = "call-RunEmptyDrops/empty_drops_result.csv",

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -62,7 +62,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 }

 \value{

 A \link[SingleCellExperiment]{SingleCellExperiment} object

@@ -10,7 +10,7 @@ importSEQC(

   prefix = NULL,

   gzipped = FALSE,

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE,

+  delayedArray = FALSE,

   cbNotFirstCol = TRUE,

   feNotFirstCol = TRUE,

   combinedSample = TRUE

@@ -41,7 +41,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 \item{cbNotFirstCol}{Boolean. \code{TRUE} if first column of

  sparse_counts_barcode.csv

@@ -13,7 +13,7 @@ importSTARsolo(

   barcodesFileNames = "barcodes.tsv",

   gzipped = "auto",

   class = c("Matrix", "matrix"),

-  delayedArray = TRUE

+  delayedArray = FALSE

 )

 }

 \arguments{

@@ -57,7 +57,7 @@ object. Can be one of "Matrix" (as returned by

 \link[base]{matrix} function). Default "Matrix".}

 \item{delayedArray}{Boolean. Whether to read the expression matrix as

-\link{DelayedArray} object or not. Default \code{TRUE}.}

+\link{DelayedArray} object or not. Default \code{FALSE}.}

 }

 \value{

 A \code{SingleCellExperiment} object containing the count