@@ -150,7 +150,7 @@ export(sctkPythonInstallConda)

 export(sctkPythonInstallVirtualEnv)

 export(selectSCTKConda)

 export(selectSCTKVirtualEnvironment)

-export(setSCERowNames)

+export(setRowNames)

 export(setSCTKDisplayRow)

 export(seuratComputeHeatmap)

 export(seuratComputeJackStraw)

@@ -14,6 +14,8 @@

 #'  object. Can be one of "Matrix" (as returned by

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

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

 #'  matrix, the feature annotations, and the cell annotation

 #'  (which includes QC metrics stored in 'featureDump.txt').

@@ -24,7 +26,8 @@ importAlevin <- function(

   alevinDir = NULL,

   sampleName = 'sample',

   delayedArray = FALSE,

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

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

+  rowNamesDedup = TRUE) {

   class <- match.arg(class)

@@ -45,6 +48,15 @@ importAlevin <- function(

   if (delayedArray) {

     mat <- DelayedArray::DelayedArray(mat)

   }

+  

+  if (isTRUE(rowNamesDedup)) {

+    if (any(duplicated(rownames(mat)))) {

+      message("Duplicated gene names found, adding '-1', '-2', ",

+              "... suffix to them.")

+    }

+    mat <- dedupRowNames(mat)

+  }

+  

   genes <- rownames(mat)

   cb <- .readBarcodes(file.path(alevinDir, 'alevin/featureDump.txt'),

                       header = 'auto',

@@ -62,6 +74,6 @@ importAlevin <- function(

     column_name = coln,

     sample = sampleName,

     row.names = coln)

-

+  

   return(sce)

 }

@@ -120,7 +120,8 @@

 importAnnData <- function(sampleDirs = NULL,

                           sampleNames = NULL,

                           delayedArray = FALSE,

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

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

+                          rowNamesDedup = TRUE) {

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

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

@@ -138,6 +139,15 @@ importAnnData <- function(sampleDirs = NULL,

     res[[i]] <- scei

   }

   sce <- do.call(SingleCellExperiment::cbind, res)

+  

+  if (isTRUE(rowNamesDedup)) {

+    if (any(duplicated(rownames(sce)))) {

+      message("Duplicated gene names found, adding '-1', '-2', ",

+              "... suffix to them.")

+    }

+    sce <- dedupRowNames(sce)

+  }

+  

   return(sce)

 }

@@ -27,7 +27,7 @@

         column_name = coln,

         sample = sample,

         row.names = coln)

-

+    

     return(sce)

 }

@@ -41,7 +41,8 @@

     barcodesFileNames,

     gzipped,

     class,

-    delayedArray) {

+    delayedArray,

+    rowNamesDedup) {

     if (length(BUStoolsDirs) != length(samples)) {

         stop("'BUStoolsDirs' and 'samples' have unequal lengths!")

@@ -68,6 +69,15 @@

     }

     sce <- do.call(SingleCellExperiment::cbind, res)

+    

+    if (isTRUE(rowNamesDedup)) {

+        if (any(duplicated(rownames(sce)))) {

+            message("Duplicated gene names found, adding '-1', '-2', ",

+                    "... suffix to them.")

+        }

+        sce <- dedupRowNames(sce)

+    }

+    

     return(sce)

 }

@@ -103,6 +113,8 @@

 #'  \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{FALSE}.

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

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

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

 #' @examples

@@ -140,7 +152,8 @@ importBUStools <- function(

     barcodesFileNames = "genes.barcodes.txt",

     gzipped = "auto",

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

-    delayedArray = FALSE) {

+    delayedArray = FALSE,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

@@ -152,5 +165,6 @@ importBUStools <- function(

         barcodesFileNames = barcodesFileNames,

         gzipped = gzipped,

         class = class,

-        delayedArray = delayedArray)

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -347,7 +347,8 @@

     barcodesFileNames,

     gzipped,

     class,

-    delayedArray) {

+    delayedArray,

+    rowNamesDedup) {

     .checkArgsImportCellRanger(cellRangerDirs,

         sampleDirs,

@@ -400,6 +401,14 @@

     }

     sce <- do.call(SingleCellExperiment::cbind, res)

+    

+    if (isTRUE(rowNamesDedup)) {

+        if (any(duplicated(rownames(sce)))) {

+            message("Duplicated gene names found, adding '-1', '-2', ",

+                    "... suffix to them.")

+        }

+        sce <- dedupRowNames(sce)

+    }

     return(sce)

 }

@@ -531,6 +540,8 @@

 #'  \code{dataTypeV2} will be used to determine Cell Ranger output directory. If it has

 #'  length 1, it assumes that all samples use the same genome reference and

 #'  the function will load only filtered or raw data.

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

 #' @details

 #'  \code{importCellRangerV2} imports output from Cell Ranger V2.

 #'  \code{importCellRangerV2Sample} imports output from one sample from Cell

@@ -571,7 +582,8 @@ importCellRanger <- function(

     barcodesFileNames = "barcodes.tsv.gz",

     gzipped = "auto",

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

-    delayedArray = FALSE) {

+    delayedArray = FALSE,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

     dataType <- match.arg(dataType)

@@ -586,7 +598,8 @@ importCellRanger <- function(

         barcodesFileNames = barcodesFileNames,

         gzipped = gzipped,

         class = class,

-        delayedArray = delayedArray)

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -611,7 +624,8 @@ importCellRangerV2 <- function(

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

     delayedArray = FALSE,

     reference = NULL,

-    cellRangerOutsV2 = NULL) {

+    cellRangerOutsV2 = NULL,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

     dataTypeV2 <- match.arg(dataTypeV2)

@@ -628,7 +642,6 @@ importCellRangerV2 <- function(

         cellRangerOutsV2 <- .getCellRangerOutV2(dataTypeV2, reference)

     }

-

     .importCellRanger(cellRangerDirs = cellRangerDirs,

         sampleDirs = sampleDirs,

         sampleNames = sampleNames,

@@ -639,8 +652,8 @@ importCellRangerV2 <- function(

         barcodesFileNames = "barcodes.tsv",

         gzipped = FALSE,

         class = class,

-        delayedArray = delayedArray)

-

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -658,6 +671,8 @@ importCellRangerV2 <- function(

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

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

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

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

 #' @examples

@@ -670,7 +685,8 @@ importCellRangerV2Sample <- function(

     dataDir = NULL,

     sampleName = NULL,

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

-    delayedArray = FALSE) {

+    delayedArray = FALSE,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

@@ -684,7 +700,8 @@ importCellRangerV2Sample <- function(

         barcodesFileNames = "barcodes.tsv",

         gzipped = FALSE,

         class = class,

-        delayedArray = delayedArray)

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -702,7 +719,8 @@ importCellRangerV3 <- function(

     sampleNames = NULL,

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

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

-    delayedArray = FALSE) {

+    delayedArray = FALSE,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

     dataType <- match.arg(dataType)

@@ -723,7 +741,8 @@ importCellRangerV3 <- function(

         barcodesFileNames = "barcodes.tsv.gz",

         gzipped = TRUE,

         class = class,

-        delayedArray = delayedArray)

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -742,6 +761,8 @@ importCellRangerV3 <- function(

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

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

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

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

 #' @examples

@@ -754,7 +775,8 @@ importCellRangerV3Sample <- function(

     dataDir = "./",

     sampleName = "sample",

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

-    delayedArray = FALSE) {

+    delayedArray = FALSE,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

@@ -768,5 +790,6 @@ importCellRangerV3Sample <- function(

         barcodesFileNames = "barcodes.tsv.gz",

         gzipped = TRUE,

         class = class,

-        delayedArray = delayedArray)

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -102,7 +102,8 @@

 #'  object. Can be one of "Matrix" (as returned by

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

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

-

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

 #' @details

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

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

@@ -125,7 +126,8 @@ importDropEst <- function(sampleDirs = NULL,

                           rdsFileName = 'cell.counts',

                           sampleNames = NULL,

                           delayedArray = FALSE,

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

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

+                          rowNamesDedup = TRUE) {

   dataType <- match.arg(dataType)

   class <- match.arg(class)

@@ -145,6 +147,15 @@ importDropEst <- function(sampleDirs = NULL,

     res[[i]] <- scei

   }

   sce <- do.call(SingleCellExperiment::cbind, res)

+  

+  if (isTRUE(rowNamesDedup)) {

+    if (any(duplicated(rownames(sce)))) {

+      message("Duplicated gene names found, adding '-1', '-2', ",

+              "... suffix to them.")

+    }

+    sce <- dedupRowNames(sce)

+  }

+  

   return(sce)

 }

@@ -13,6 +13,8 @@

 #'   \code{"Matrix"}.

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#' \code{TRUE}.

 #' @details See the list below for the available datasets and their

 #' descriptions.

 #' \describe{

@@ -43,7 +45,7 @@

 #' @export

 #' @importFrom SummarizedExperiment colData rowData colData<- assay assays

 importExampleData <- function(dataset, class = c("Matrix", "matrix"),

-                              delayedArray = FALSE) {

+                              delayedArray = FALSE, rowNamesDedup = TRUE) {

   class <- match.arg(class)

   scRNAseqDatasets <- c("fluidigm_pollen", "allen_tasic")

@@ -62,13 +64,16 @@ importExampleData <- function(dataset, class = c("Matrix", "matrix"),

       temp <- scRNAseq::ReprocessedAllenData()

       temp$sample <- paste0(colData(temp)$driver_1_s, "_", colData(temp)$dissection_s)

     }

+    if (isTRUE(rowNamesDedup)) {

+      temp <- dedupRowNames(temp)

+    }

   } else if (dataset %in% tenxPbmcDatasets) {

     if(!("TENxPBMCData" %in% rownames(utils::installed.packages()))) {

       stop(paste0("Package 'TENxPBMCData' is not installed. Please install to load dataset '", dataset, "'."))

     }

     temp <- TENxPBMCData::TENxPBMCData(dataset = dataset)

     colnames(temp) <- paste(temp$Sample, temp$Barcode, sep="_")

-    rownames(temp) <- rowData(temp)$Symbol_TENx

+    temp <- setRowNames(temp, "Symbol_TENx", dedup = rowNamesDedup)

     colData(temp)$sample <- colData(temp)$Sample

   } else {

     stop("'dataset' must be one of: ", paste(c(scRNAseqDatasets, tenxPbmcDatasets), collapse = ","))

@@ -1,121 +1,147 @@

-.checkGzip <- function(path, gzipped){

-    if (gzipped == "auto") {

-      ext <- tools::file_ext(path)

-      if (ext == "gz") {

-            path <- gzfile(path)

-        }

-    } else if (isTRUE(gzipped)) {

-        path <- gzfile(path)

-    }

-

-    return(path)

-}

-

-#' Create a SingleCellExperiment object from files

-#'

-#' Creates a SingleCellExperiment object from a counts file in various formats.

-#' and a file of annotation information, .

-#'

-#' @param assayFile The path to a  file in .mtx, .txt, .csv, .tab, or .tsv format.

-#' @param annotFile The path to a text file that contains columns of annotation

-#' information for each sample in the assayFile. This file should have the same

-#' number of rows as there are columns in the assayFile. If multiple samples are

-#' represented in these files, this should be denoted by a column called \code{'sample'}

-#' within the \code{annotFile}.

-#' @param featureFile The path to a text file that contains columns of

-#' annotation information for each gene in the count matrix. This file should

-#' have the same genes in the same order as assayFile. This is optional.

-#' @param assayName The name of the assay that you are uploading. The default

-#' is "counts".

-#' @param inputDataFrames If TRUE, assayFile and annotFile are read as data

-#' frames instead of file paths. The default is FALSE.

-#' @param class Character. The class of the expression matrix stored in the SCE

-#'  object. Can be one of "Matrix" (as returned by

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

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

-#' @param annotFileHeader Whether there's a header (colnames) in the cell annotation file. Default is FALSE

-#' @param annotFileRowName Which column is used as the rownames for the cell annotation file. Default is 1 (first column).

-#' @param annotFileSep Separater used for the cell annotation file. Default is "\\t".

-#' @param featureHeader Whether there's a header (colnames) in the feature annotation file. Default is FALSE

-#' @param featureRowName Which column is used as the rownames for the feature annotation file. Default is 1 (first column).

-#' @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{FALSE}.

-#' @return a SingleCellExperiment object

-#' @export

-

-importFromFiles <- function(assayFile, annotFile = NULL, featureFile = NULL,

-                            assayName = "counts", inputDataFrames = FALSE,

-                            class = c("Matrix", "matrix"), delayedArray = FALSE,

-                            annotFileHeader = FALSE, annotFileRowName = 1,

-                            annotFileSep = "\t", featureHeader = FALSE,

-                            featureRowName = 1, featureSep = "\t", gzipped = "auto"

-                            ){

-

-  class <- match.arg(class)

-

-  if (inputDataFrames){

-    countsin <- assayFile

-    annotin <- annotFile

-    featurein <- featureFile

-  } else{

-    countsin <- readSingleCellMatrix(assayFile, class = class, delayedArray = delayedArray)

-    if (!is.null(annotFile)){

-      annotFile <- .checkGzip(annotFile, gzipped = gzipped)

-      annotin <- utils::read.table(annotFile, sep = annotFileSep, header = annotFileHeader,

-                                   row.names = annotFileRowName, stringsAsFactors = FALSE)

-    }

-    if (!is.null(featureFile)){

-      featureFile <- .checkGzip(featureFile, gzipped = gzipped)

-      featurein <- utils::read.table(featureFile, sep = featureSep, header = featureHeader,

-                                     row.names = featureRowName, stringsAsFactors = FALSE)

-    }

-  }

-  if (is.null(annotFile)){

-    annotin <- data.frame(row.names = colnames(countsin))

-    annotin <- S4Vectors::DataFrame(annotin)

-  }

-  if (is.null(featureFile)){

-    featurein <- data.frame(Gene = rownames(countsin))

-    rownames(featurein) <- featurein$Gene

-    featurein <- S4Vectors::DataFrame(featurein)

-  }

-

-  if (nrow(annotin) != ncol(countsin)){

-    stop("Different number of samples in input matrix and annotations: annot: ",

-         nrow(annotin), ", counts: ", ncol(countsin))

-  }

-  if (nrow(featurein) != nrow(countsin)){

-    stop("Different number of samples in input matrix and feature annotation",

-         nrow(featurein), ", counts: ", nrow(countsin))

-  }

-  if (any(rownames(annotin) != colnames(countsin))){

-    stop("Sample names in input matrix and annotation do not match!\nExample: ",

-         rownames(annotin)[rownames(annotin) != colnames(countsin)][1], " vs. ",

-         colnames(countsin)[rownames(annotin) != colnames(countsin)][1])

-  }

-  if (any(rownames(featurein) != rownames(countsin))){

-    stop("Sample names in input matrix and feature annotation do not match!")

-  }

-

-  assaylist <- list()

-  if (is.null(rownames(countsin))){

-    rownames(countsin) <- rownames(featurein)

-  }

-  if (is.null(colnames(countsin))){

-    colnames(countsin) <- rownames(annotin)

-  }

-  #assaylist[[assayName]] <- methods::as(countsin, "dgCMatrix")

-  assaylist[[assayName]] <- .convertToMatrix(countsin)

-

-  newassay <- SingleCellExperiment::SingleCellExperiment(assays = assaylist,

-                                                         colData = annotin,

-                                                         rowData = featurein)

-

-  if(is.null(newassay$sample)) {

-    newassay$sample <- "sample"

-  }

-

-  return(newassay)

-}

+.checkGzip <- function(path, gzipped){

+    if (gzipped == "auto") {

+      ext <- tools::file_ext(path)

+      if (ext == "gz") {

+            path <- gzfile(path)

+        }

+    } else if (isTRUE(gzipped)) {

+        path <- gzfile(path)

+    }

+

+    return(path)

+}

+

+#' Create a SingleCellExperiment object from files

+#'

+#' @details Creates a \linkS4class{SingleCellExperiment} object from a counts 

+#' file in various formats, and files of cell and feature annotation.

+#' @param assayFile The path to a file in .mtx, .txt, .csv, .tab, or .tsv 

+#' format.

+#' @param annotFile The path to a text file that contains columns of annotation

+#' information for each cell in the \code{assayFile}. This file should have the 

+#' same number of rows as there are columns in the \code{assayFile}. If multiple

+#' samples are represented in the dataset, this should be denoted by a column 

+#' called \code{'sample'} within the \code{annotFile}.

+#' @param featureFile The path to a text file that contains columns of

+#' annotation information for each gene in the count matrix. This file should

+#' have the same genes in the same order as \code{assayFile}. This is optional.

+#' @param assayName The name of the assay that you are uploading. The default

+#' is \code{"counts"}.

+#' @param inputDataFrames If \code{TRUE}, \code{assayFile}, \code{annotFile} and

+#' \code{featureFile} should be \code{data.frames} object (or its inheritance) 

+#' instead of file paths. The default is \code{FALSE}.

+#' @param class Character. The class of the expression matrix stored in the SCE

+#'  object. Can be one of \code{"Matrix"} (as returned by

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

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

+#' @param annotFileHeader Whether there's a header (colnames) in the cell 

+#' annotation file. Default is \code{FALSE}.

+#' @param annotFileRowName Which column is used as the rownames for the cell 

+#' annotation file. This should match to the colnames of the \code{assayFile}. 

+#' Default is \code{1} (first column).

+#' @param annotFileSep Separater used for the cell annotation file. Default is 

+#' \code{"\\t"}.

+#' @param featureHeader Whether there's a header (colnames) in the feature 

+#' annotation file. Default is \code{FALSE}.

+#' @param featureRowName Which column is used as the rownames for the feature 

+#' annotation file. This should match to the rownames of the \code{assayFile}. 

+#' Default is \code{1}. (first column).

+#' @param featureSep Separater used for the feature annotation file. Default is 

+#' \code{"\\t"}.

+#' @param gzipped Whether the input file is gzipped. Default is \code{"auto"} 

+#' and it will automatically detect whether the file is gzipped. Other options 

+#' are \code{TRUE} or \code{FALSE}.

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

+#' @return a \linkS4class{SingleCellExperiment} object

+#' @export

+

+importFromFiles <- function(assayFile, annotFile = NULL, featureFile = NULL,

+                            assayName = "counts", inputDataFrames = FALSE,

+                            class = c("Matrix", "matrix"), delayedArray = FALSE,

+                            annotFileHeader = FALSE, annotFileRowName = 1,

+                            annotFileSep = "\t", featureHeader = FALSE,

+                            featureRowName = 1, featureSep = "\t", 

+                            gzipped = "auto", rowNamesDedup = TRUE){

+

+  class <- match.arg(class)

+

+  if (inputDataFrames){

+    countsin <- assayFile

+    annotin <- annotFile

+    featurein <- featureFile

+  } else{

+    countsin <- readSingleCellMatrix(assayFile, class = class, 

+                                     delayedArray = delayedArray)

+    if (!is.null(annotFile)){

+      annotFile <- .checkGzip(annotFile, gzipped = gzipped)

+      annotin <- utils::read.table(annotFile, sep = annotFileSep, 

+                                   header = annotFileHeader,

+                                   row.names = annotFileRowName, 

+                                   stringsAsFactors = FALSE)

+    }

+    if (!is.null(featureFile)){

+      featureFile <- .checkGzip(featureFile, gzipped = gzipped)

+      featurein <- utils::read.table(featureFile, sep = featureSep, 

+                                     header = featureHeader,

+                                     row.names = featureRowName, 

+                                     stringsAsFactors = FALSE)

+    }

+  }

+  if (is.null(annotFile)){

+    annotin <- data.frame(row.names = colnames(countsin))

+    annotin <- S4Vectors::DataFrame(annotin)

+  }

+  if (is.null(featureFile)){

+    featurein <- data.frame(Gene = rownames(countsin))

+    rownames(featurein) <- featurein$Gene

+    featurein <- S4Vectors::DataFrame(featurein)

+  }

+

+  if (nrow(annotin) != ncol(countsin)){

+    stop("Different number of cells in input matrix and annotations: annot: ",

+         nrow(annotin), ", counts: ", ncol(countsin))

+  }

+  if (nrow(featurein) != nrow(countsin)){

+    stop("Different number of features in input matrix and feature annotation",

+         nrow(featurein), ", counts: ", nrow(countsin))

+  }

+  if (any(rownames(annotin) != colnames(countsin))){

+    stop("Cell names in input matrix and annotation do not match!\nExample: ",

+         rownames(annotin)[rownames(annotin) != colnames(countsin)][1], " vs. ",

+         colnames(countsin)[rownames(annotin) != colnames(countsin)][1])

+  }

+  if (any(rownames(featurein) != rownames(countsin))){

+    stop("Feature names in input matrix and feature annotation do not match!")

+  }

+

+  assaylist <- list()

+  if (is.null(rownames(countsin))){

+    rownames(countsin) <- rownames(featurein)

+  }

+  if (is.null(colnames(countsin))){

+    colnames(countsin) <- rownames(annotin)

+  }

+  #assaylist[[assayName]] <- methods::as(countsin, "dgCMatrix")

+  assaylist[[assayName]] <- .convertToMatrix(countsin)

+

+  newassay <- SingleCellExperiment::SingleCellExperiment(assays = assaylist,

+                                                         colData = annotin,

+                                                         rowData = featurein)

+

+  if(is.null(newassay$sample)) {

+    newassay$sample <- "sample"

+  }

+

+  if (isTRUE(rowNamesDedup)) {

+    if (any(duplicated(rownames(newassay)))) {

+      message("Duplicated gene names found, adding '-1', '-2', ",

+              "... suffix to them.")

+    }

+    newassay <- dedupRowNames(newassay)

+  }

+  

+  return(newassay)

+}

@@ -10,20 +10,26 @@

   #  sparse <- reticulate::import("scipy.sparse")

   #  numpy <- reticulate::import("numpy")

   if (!reticulate::py_module_available(module = "scipy.sparse")) {

-    stop("Error!", "Cannot find python module 'scipy.sparse', please install Conda and run sctkPythonInstallConda()

-         or run sctkPythonInstallVirtualEnv(). If one of these have been previously run to install the modules,

-         make sure to run selectSCTKConda() or selectSCTKVirtualEnvironment(), respectively, if R has been

-         restarted since the module installation. Alternatively, scipy can be installed on the local machine

-         with pip (e.g. pip install scipy) and then the 'use_python()' function from the 'reticulate' package

-         can be used to select the correct Python environment.")

+    stop("Error!", "Cannot find python module 'scipy.sparse', please install 

+          Conda and run sctkPythonInstallConda() or run 

+          sctkPythonInstallVirtualEnv(). If one of these have been previously 

+          run to install the modules, make sure to run selectSCTKConda() or 

+          selectSCTKVirtualEnvironment(), respectively, if R has been restarted 

+          since the module installation. Alternatively, scipy can be installed 

+          on the local machine with pip (e.g. pip install scipy) and then the 

+          'use_python()' function from the 'reticulate' package can be used to 

+         select the correct Python environment.")

   }

   if (!reticulate::py_module_available(module = "numpy")) {

-    stop("Error!", "Cannot find python module 'numpy', please install Conda and run sctkPythonInstallConda()

-         or run sctkPythonInstallVirtualEnv(). If one of these have been previously run to install the modules,

-         make sure to run selectSCTKConda() or selectSCTKVirtualEnvironment(), respectively, if R has been

-         restarted since the module installation. Alternatively, numpy can be installed on the local machine

-         with pip (e.g. pip install numpy) and then the 'use_python()' function from the 'reticulate' package

-         can be used to select the correct Python environment.")

+    stop("Error!", "Cannot find python module 'numpy', please install Conda and 

+          run sctkPythonInstallConda() or run sctkPythonInstallVirtualEnv(). If 

+          one of these have been previously run to install the modules, make 

+          sure to run selectSCTKConda() or selectSCTKVirtualEnvironment(), 

+          respectively, if R has been restarted since the module installation. 

+          Alternatively, numpy can be installed on the local machine with pip 

+          (e.g. pip install numpy) and then the 'use_python()' function from the

+          'reticulate' package can be used to select the correct Python 

+          environment.")

   }

   error <- try({

@@ -56,7 +62,9 @@

   }, silent = TRUE)

   if(inherits(error, "try-error")) {

-    stop(paste0("importOptimus did not complete successfully. SCE could not be generated. Error given during the import process: \n\n", error))

+    stop(paste0("importOptimus did not complete successfully. SCE could not be",

+                "generated. Error given during the import process: \n\n", 

+                error))

   }

   if (class == "matrix") {

@@ -180,7 +188,8 @@

   geneMetricsLocation,

   emptyDropsLocation,

   class,

-  delayedArray) {

+  delayedArray,

+  rowNamesDedup) {

   .checkArgsImportOptimus(OptimusDirs, samples)

@@ -201,6 +210,15 @@

   }

   sce <- do.call(SingleCellExperiment::cbind, res)

+  

+  if (isTRUE(rowNamesDedup)) {

+    if (any(duplicated(rownames(sce)))) {

+      message("Duplicated gene names found, adding '-1', '-2', ",

+              "... suffix to them.")

+    }

+    sce <- dedupRowNames(sce)

+  }

+  

   return(sce)

 }

@@ -247,6 +265,8 @@

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

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

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

 #'  containing the count

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

@@ -267,7 +287,8 @@ importOptimus <- function(OptimusDirs,

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

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

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

-  delayedArray = FALSE) {

+  delayedArray = FALSE,

+  rowNamesDedup = TRUE) {

   class <- match.arg(class)

@@ -280,6 +301,7 @@ importOptimus <- function(OptimusDirs,

     geneMetricsLocation = geneMetricsLocation,

     emptyDropsLocation = emptyDropsLocation,

     class = class,

-    delayedArray = delayedArray)

+    delayedArray = delayedArray,

+    rowNamesDedup = rowNamesDedup)

 }

@@ -40,7 +40,8 @@

     barcodesFileNames,

     gzipped,

     class,

-    delayedArray) {

+    delayedArray,

+    rowNamesDedup) {

     if (length(STARsoloDirs) != length(samples)) {

         stop("'STARsoloDirs' and 'samples' have unequal lengths!")

@@ -68,6 +69,14 @@

     }

     sce <- do.call(SingleCellExperiment::cbind, res)

+    

+    if (isTRUE(rowNamesDedup)) {

+        if (any(duplicated(rownames(sce)))) {

+            message("Duplicated gene names found, adding '-1', '-2', ",

+                    "... suffix to them.")

+        }

+        sce <- dedupRowNames(sce)

+    }

     return(sce)

 }

@@ -111,6 +120,8 @@

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

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

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

+#' @param rowNamesDedup Boolean. Whether to deduplicate rownames. Default 

+#'  \code{TRUE}.

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

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

 #' @examples

@@ -151,7 +162,8 @@ importSTARsolo <- function(

     barcodesFileNames = "barcodes.tsv",

     gzipped = "auto",

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

-    delayedArray = FALSE) {

+    delayedArray = FALSE,

+    rowNamesDedup = TRUE) {

     class <- match.arg(class)

@@ -164,5 +176,6 @@ importSTARsolo <- function(

         barcodesFileNames = barcodesFileNames,

         gzipped = gzipped,

         class = class,

-        delayedArray = delayedArray)

+        delayedArray = delayedArray,

+        rowNamesDedup = rowNamesDedup)

 }

@@ -74,7 +74,8 @@

     delayedArray,

     cbNotFirstCol,

     feNotFirstCol,

-    combinedSample) {

+    combinedSample,

+    rowNamesDedup) {

     if (length(seqcDirs) != length(samples)) {

         stop("'seqcDirs' and 'samples' have unequal lengths!")

@@ -121,6 +122,13 @@

         }

         sce <- do.call(SingleCellExperiment::cbind, res)

+        if (isTRUE(rowNamesDedup)) {

+            if (any(duplicated(rownames(sce)))) {

+                message("Duplicated gene names found, adding '-1', '-2', ",

+                        "... suffix to them.")

+            }

+            sce <- dedupRowNames(sce)

+        }

         return(sce)

     } else {

@@ -133,7 +141,15 @@

             res[[i]] <- scei

         }

         if (length(seqcDirs) == 1) {

-            return(res[[1]])

+            sce <- res[[1]]

+            if (isTRUE(rowNamesDedup)) {

+                if (any(duplicated(rownames(sce)))) {

+                    message("Duplicated gene names found, adding '-1', '-2', ",

+                            "... suffix to them.")

+                }

+                sce <- dedupRowNames(sce)

+            }

+            return(sce)

         } else {

             return(res)

         }

@@ -145,12 +161,11 @@

 #' @rdname importSEQC

 #' @title Construct SCE object from seqc output

 #' @description Read the filtered barcodes, features, and matrices for all

-#'  samples from (preferably a single run of) seqc output. Import and

-#'  combine them as one big \link[SingleCellExperiment]{SingleCellExperiment}

-#'  object.

+#'  samples from (preferably a single run of) seqc output. Import and combine

+#'  them as one big \link[SingleCellExperiment]{SingleCellExperiment} object.

 #' @param seqcDirs A vector of paths to seqc output files. Each sample

-#'  should have its own path. For example: \code{./pbmc_1k_50x50}.

-#'  Must have the same length as \code{samples}.

+#'  should have its own path. For example: \code{"./pbmc_1k_50x50"}. Must have 

+#'  the same length as \code{samples}.

 #' @param samples A vector of user-defined sample names for the samples to be

 #'  imported. Must have the same length as \code{seqcDirs}.

 #' @param prefix A vector containing the prefix of file names within each

@@ -158,44 +173,39 @@

 #'  length as \emph{samples}.

 #' @param gzipped Boolean. \code{TRUE} if the seqc output files

 #'  (sparse_counts_barcode.csv, sparse_counts_genes.csv, and

-#'  sparse_molecule_counts.mtx)

-#'  were gzip compressed. \code{FALSE} otherwise. Default seqc outputs are

-#'  not gzipped.

-#' Default \code{FALSE}.

+#'  sparse_molecule_counts.mtx) were gzip compressed. \code{FALSE} otherwise. 

+#'  Default seqc outputs are not gzipped. Default \code{FALSE}.

 #' @param class Character. The class of the expression matrix stored in the SCE

-#'  object. Can be one of "Matrix" (as returned by

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

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

+#'  object. Can be one of \code{"Matrix"} (as returned by \link{readMM} 

+#'  function), or \code{"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{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

-#'  be kept.

+#'  sparse_counts_genes.csv is row index and it will be removed. \code{FALSE} 

+#'  the first column will be kept.

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

-#'  sparse_counts_barcode.csv