@@ -1,7 +1,5 @@

 # Generated by roxygen2: do not edit by hand

-export(MAST)

-export(alignSingleCellData)

 export(calcEffectSizes)

 export(combineSCE)

 export(computeZScore)

@@ -50,7 +48,6 @@ export(importSEQC)

 export(importSTARsolo)

 export(iterateSimulations)

 export(mergeSCEColData)

-export(parseRsubreadLogs)

 export(plotBarcodeRankDropsResults)

 export(plotBarcodeRankScatter)

 export(plotBatchVariance)

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

   barcodes,

   metadata,

   reducedDims) {

-  

+

   sce <- SingleCellExperiment::SingleCellExperiment(assays = matrices)

   SummarizedExperiment::rowData(sce) <- S4Vectors::DataFrame(features)

   SummarizedExperiment::colData(sce) <- S4Vectors::DataFrame(barcodes)

@@ -21,9 +21,9 @@

   return(list(RowUnion, ColUnion))

 }

-.getMatUnion <- function(dimsList, x, 

-                         combineRow, combineCol, 

-                         sparse = FALSE, 

+.getMatUnion <- function(dimsList, x,

+                         combineRow, combineCol,

+                         sparse = FALSE,

                          fill = c("NA", "0")){

   row <- dimsList[[1]]

   col <- dimsList[[2]]

@@ -34,8 +34,8 @@

   } else {

     fill <- NA

   }

-  

-  ### combine row 

+

+  ### combine row

   if (isTRUE(combineRow) & (!is.null(row))) {

     missRow <- row[!row %in% rownames(x)]

     missMat <- Matrix::Matrix(fill, nrow = length(missRow), ncol = ncol(matOrigin),

@@ -43,15 +43,15 @@

     if (!isTRUE(sparse)) {

       missMat <- as.matrix(missMat)

     }

-    

+

     mat <- rbind(matOrigin, missMat)

     if (anyDuplicated(rownames(mat))) {

       mat <- mat[!duplicated(rownames(mat)), ]

     }

     matOrigin <- mat[row, ]

   }

-  

-  ### combine cols 

+

+  ### combine cols

   if (isTRUE(combineCol) & (!is.null(col))) {

     missCol <- col[!col %in% colnames(x)]

     missMat <- Matrix::Matrix(fill, nrow = nrow(matOrigin), ncol = length(missCol),

@@ -59,7 +59,7 @@

     if (!isTRUE(sparse)) {

       missMat <- as.matrix(missMat)

     }

-    

+

     mat <- cbind(matOrigin, missMat)

     if (anyDuplicated(colnames(mat))) {

       mat <- mat[, !duplicated(colnames(mat))]

@@ -76,17 +76,17 @@

     rw[['rownames']] <- rownames(rw)

     return(rw)

   })

-  

+

   ## Get merged rowData

   by.r <- unique(c('rownames', by.r))

   unionFe <- Reduce(function(r1, r2) merge(r1, r2, by=by.r, all=TRUE), feList)

   allGenes <- unique(unlist(lapply(feList, rownames)))

-  

+

   ## rowData

   newFe <- unionFe

   if (nrow(newFe) != length(allGenes)) {

     warning("Conflicts were found when merging two rowData. ",

-            "Resolved the conflicts by choosing the first entries.", 

+            "Resolved the conflicts by choosing the first entries.",

             "To avoid conflicts, please provide the 'by.r' arguments to ",

             "specify columns in rowData that does not have conflict between two singleCellExperiment object. ")

     newFe <- newFe[!duplicated(newFe$rownames), ]

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

     cD[['rownames']] <- rownames(cD)

     return(cD)

   })

-  

+

   by.c <- unique(c("rownames", by.c))

   unionCb <- Reduce(function(c1, c2) merge(c1, c2, by=by.c, all=TRUE), cbList)

   rownames(unionCb) <- unionCb[['rownames']]

@@ -118,34 +118,34 @@

   reduceList <- lapply(sceList, SingleCellExperiment::reducedDims)

   ## get every reducedDim exists in at least one SCEs

   UnionReducedDims <- unique(unlist(lapply(sceList, SingleCellExperiment::reducedDimNames)))

-  

+

   ## for each reducedDim, get union row/cols

   reducedDims <- list()

   for (reduceDim in UnionReducedDims) {

     x <- lapply(sceList, function(x) {if (reduceDim %in% SingleCellExperiment::reducedDimNames(x)) {SingleCellExperiment::reducedDim(x, reduceDim)}})

     reducedDims[[reduceDim]] <- .getDimUnion(x)

   }

-  

+

   ## Merge reducedDim for each SCE

   redList <- list()

   for (idx in seq_along(sceList)){

     redMat <- reduceList[[idx]]

-    

+

     for (DimName in UnionReducedDims) {

       if (DimName %in% names(redMat)) {

         redMat[[DimName]] <- .getMatUnion(reducedDims[[DimName]], redMat[[DimName]],

                                           combineRow = FALSE, combineCol = TRUE,

                                           sparse = FALSE, fill = "NA")

       } else {

-        redMat[[DimName]] <- base::matrix(NA, nrow = ncol(sceList[[idx]]), 

+        redMat[[DimName]] <- base::matrix(NA, nrow = ncol(sceList[[idx]]),

                                           ncol = length(reducedDims[[DimName]][[2]]),

                                           dimnames = list(colnames(sceList[[idx]]), reducedDims[[DimName]][[2]]))

       }

     }

-    

+

     redList[[idx]] <- redMat

   }

-  

+

   return(redList)

 }

@@ -154,21 +154,21 @@

                         lapply(sceList, SummarizedExperiment::assayNames))

   assayList <- lapply(sceList, assays)

   assayDims <- list(

-    unique(unlist(lapply(sceList, rownames))), 

+    unique(unlist(lapply(sceList, rownames))),

     unique(unlist(lapply(sceList, colnames)))

   )

-  

+

   asList <- list()

   for (idx in seq_along(assayList)){

     assay <- assayList[[idx]]

     for (assayName in UnionAssays) {

       if (assayName %in% names(assay)) {

         assay[[assayName]] <- .getMatUnion(assayDims, assay[[assayName]],

-                                           combineRow = TRUE, combineCol = FALSE, 

+                                           combineRow = TRUE, combineCol = FALSE,

                                            sparse = TRUE, fill = "0")

       } else{

-        assay[[assayName]] <- Matrix::Matrix(0, nrow = length(assayDims[[1]]), 

-                                             ncol = ncol(sceList[[idx]]), 

+        assay[[assayName]] <- Matrix::Matrix(0, nrow = length(assayDims[[1]]),

+                                             ncol = ncol(sceList[[idx]]),

                                              dimnames = list(assayDims[[1]], colnames(sceList[[idx]]))) #assayDims[[assayName]])

       }

     }

@@ -181,46 +181,48 @@

 # .mergeMetaSCE <- function(sceList) {

 #   metaList <- lapply(sceList, S4Vectors::metadata)

 #   metaNames <- unlist(lapply(metaList, names))

-  

+

 #   if ("runBarcodeRanksMetaOutput" %in% metaNames) {

 #     barcodeMetas <- lapply(metaList, function(x) {x[["runBarcodeRanksMetaOutput"]]})

 #     barcodeMetas <- do.call(rbind, barcodeMetas)

-    

+

 #     for (i in seq_along(metaList)) {

-#       metaList[[i]][["runBarcodeRanksMetaOutput"]] <- NULL  

+#       metaList[[i]][["runBarcodeRanksMetaOutput"]] <- NULL

 #     }

-    

+

 #     metaList[["runBarcodeRanksMetaOutput"]] <- barcodeMetas

 #   }

-  

+

 #   return(metaList)

 # }

 .mergeMetaSCE <- function(SCE_list) {

-  sampleMeta <- lapply(SCE_list, S4Vectors::metadata) 

+  sampleMeta <- lapply(SCE_list, S4Vectors::metadata)

   metaNames <- unique(unlist(lapply(sampleMeta, names)))

   NewMeta <- list()

-  

+

   for (meta in metaNames) {

     for (i in seq_along(sampleMeta)) {

       NewMeta[[meta]][[i]] <- sampleMeta[[i]][[meta]]

     }

   }

-  

+

   if ("runBarcodeRanksMetaOutput" %in% metaNames) {

     NewMeta[["runBarcodeRanksMetaOutput"]] <- unlist(NewMeta[["runBarcodeRanksMetaOutput"]])

   }

-  

+

   return(NewMeta)

 }

 #' Combine a list of SingleCellExperiment objects as one SingleCellExperiment object

-#' @param sceList A list contains \link[SingleCellExperiment]{SingleCellExperiment} objects 

+#' @param sceList A list contains \link[SingleCellExperiment]{SingleCellExperiment} objects

 #' @param by.r Specifications of the columns used for merging rowData. See 'Details'.

 #' @param by.c Specifications of the columns used for merging colData. See 'Details'.

-#' @param combined logical; if TRUE, it will combine the list of SingleCellExperiment objects. See 'Details'.  

-#' @return A \link[SingleCellExperiment]{SingleCellExperiment} object which combines all 

-#' objects in sceList. The colData is merged.  

+#' @param combined logical; if TRUE, it will combine the list of SingleCellExperiment objects. See 'Details'.

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

+#' objects in sceList. The colData is merged.

+#' @examples

+#' combinedsce <- combineSCE(list(sce,sce), by.r = NULL, by.c = NULL, combined = TRUE)

 #' @export

 combineSCE <- function(sceList, by.r, by.c, combined){

@@ -229,19 +231,19 @@ combineSCE <- function(sceList, by.r, by.c, combined){

   ## colData

   newCbList <- .mergeColDataSCE(sceList, by.c)

   ## reducedDim

-  redMatList <- .mergeRedimSCE(sceList) 

+  redMatList <- .mergeRedimSCE(sceList)

   ## assay

-  assayList <- .mergeAssaySCE(sceList) 

-  

+  assayList <- .mergeAssaySCE(sceList)

+

   New_SCE <- list()

   for (i in seq(length(sceList))) {

     ## create new sce

     New_SCE[[i]] <- .constructSCE(matrices = assayList[[i]], features = newFeList,

-                                  barcodes = newCbList[[i]], 

+                                  barcodes = newCbList[[i]],

                                   metadata = S4Vectors::metadata(sceList[[i]]),

                                   reducedDims = redMatList[[i]])

   }

-  

+

   if (isTRUE(combined)) {

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

     meta <- .mergeMetaSCE(New_SCE)

@@ -329,11 +329,9 @@

 #' @return SingleCellExperiment object containing the

 #'  'doublet_finder_doublet_score'.

 #' @examples

-#' \donttest{

 #' data(scExample, package = "singleCellTK")

 #' sce <- sce[, colData(sce)$type != 'EmptyDroplet']

 #' sce <- runDoubletFinder(sce)

-#' }

 #' @export

 #' @importFrom SummarizedExperiment colData colData<-

 #' @importFrom SingleCellExperiment reducedDim<-

@@ -1,5 +1,5 @@

-#' @title Export a \link[SingleCellExperiment]{SingleCellExperiment} R object as 

-#' Python annData object 

+#' @title Export a \link[SingleCellExperiment]{SingleCellExperiment} R object as

+#' Python annData object

 #' @description Writes all assays, colData, rowData, reducedDims, and altExps objects in a

 #' \link[SingleCellExperiment]{SingleCellExperiment} to a Python annData object in the .h5ad format

 #' All parameters of Anndata.write_h5ad function (https://icb-anndata.readthedocs-hosted.com/en/stable/anndata.AnnData.write_h5ad.html)

@@ -9,7 +9,7 @@

 #'  exported.

 #' @param useAssay Character. The name of assay of

 #' interests that will be set as the primary matrix of the output AnnData.

-#' Default \code{"counts"}. 

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

 #' @param outputDir Path to the directory where .h5ad outputs will be written. Default is the current working directory.

 #' @param prefix Prefix to use for the name of the output file. Default \code{"sample"}.

 #' @param overwrite Boolean. Default \code{TRUE}.

@@ -17,15 +17,13 @@

 #' 'gzip' or 'lzf' as inputs. Default \code{None}.

 #' @param compressionOpts Integer. Sets the compression level

 #' @param forceDense Default \code{False} Write sparse data as a dense matrix.

-#' Refer \code{anndata.write_h5ad} documentation for details. Default \code{NULL}. 

+#' Refer \code{anndata.write_h5ad} documentation for details. Default \code{NULL}.

 #' @examples

-#' \dontrun{

 #' data(sce_chcl, package = "scds")

 #' exportSCEtoAnnData(sce=sce_chcl, compression="gzip")

-#' }

-#' 

+#'

 #' @export

-exportSCEtoAnnData <- function(sce, 

+exportSCEtoAnnData <- function(sce,

                                 useAssay = 'counts',

                                 outputDir = "./",

                                 prefix = "sample",

@@ -50,7 +48,7 @@ exportSCEtoAnnData <- function(sce,

             " function from the 'reticulate' package can be used to select the",

             " correct Python environment.")

     return(sce)}

-  

+

   AssayName <- SummarizedExperiment::assayNames(sce)

   for (assay in AssayName){

     if (!methods::is(SummarizedExperiment::assay(sce, assay), 'dgCMatrix')) {

@@ -58,18 +56,18 @@ exportSCEtoAnnData <- function(sce,

     }

   }

-  

+

   dir.create(outputDir, showWarnings = FALSE, recursive = TRUE)

   annData <- .sce2adata(sce,useAssay)

   fileName <- paste0(prefix,".h5ad")

   filePath <- file.path(outputDir,fileName)

-  

+

   if (file.exists(filePath) && !isTRUE(overwrite)) {

     stop(paste0(path, " already exists. Change 'outputDir' or set 'overwrite' to TRUE."))

     }

   annData$write_h5ad(filePath,

-                     compression = compression, 

+                     compression = compression,

                      compression_opts = compressionOpts,

                      force_dense = forceDense)

 }

@@ -10,13 +10,11 @@

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

 #'  gzip compressed. \code{FALSE} otherwise. Default

 #'  \code{TRUE}.

-#' @param sample Name of the sample. It will be used as the prefix of file names. 

+#' @param sample Name of the sample. It will be used as the prefix of file names.

 #' @examples

-#' \dontrun{

 #' data(sce_chcl, package = "scds")

 #' exportSCEtoFlatFile(sce_chcl, "sce_chcl")

-#' }

-#' 

+#'

 #' @export

 #' @importFrom SummarizedExperiment colData rowData

 exportSCEtoFlatFile <- function(sce,

@@ -24,10 +22,10 @@ exportSCEtoFlatFile <- function(sce,

                                 overwrite = TRUE,

                                 gzipped = TRUE,

                                 sample = 'sample') {

-  

+

   .writeAssays(sce, outputDir, overwrite, gzipped, sample)

-  .writeColData(sce, outputDir, overwrite, gzipped, sample)  

-  .writeRowData(sce, outputDir, overwrite, gzipped, sample)  

+  .writeColData(sce, outputDir, overwrite, gzipped, sample)

+  .writeRowData(sce, outputDir, overwrite, gzipped, sample)

   .writeMetaData(sce, outputDir, overwrite, sample)

   .writeReducedDims(sce, outputDir, overwrite, gzipped, sample)

   .writeAltExps(sce, outputDir, overwrite, gzipped, sample)

@@ -42,13 +40,13 @@ exportSCEtoFlatFile <- function(sce,

 # function to write txt gz files

 .writeSCEFile <- function(data, path, overwrite, gzipped) {

-  

+

   if(is.null(rownames(data))) {

     data <- data.frame(ID = seq(nrow(data)), data)

   } else {

     data <- data.frame(ID = rownames(data), data)

   }

-  

+

   if (isTRUE(gzipped)) {

     filename <- paste0(path, ".txt.gz")

   } else {

@@ -65,7 +63,7 @@ exportSCEtoFlatFile <- function(sce,

   if (length(SummarizedExperiment::assays(sce)) > 0) {

     assaysFolder <- file.path(path, "/assays")

     dir.create(assaysFolder, showWarnings = FALSE, recursive = TRUE)

-    

+

     assayNames <- names(SummarizedExperiment::assays(sce))

     if(is.null(assayNames)) {

       assayNames <- paste0("assay", seq(SummarizedExperiment::assays(sce)))

@@ -74,16 +72,16 @@ exportSCEtoFlatFile <- function(sce,

       message(date(), " .. Writing assay '", assayNames[i], "'")

       filename <- paste(sample, paste0(assayNames[i], ".mtx"), sep="_")

       assaypath <- file.path(assaysFolder, filename)

-      

+

       .checkOverwrite(assaypath, overwrite)

       mat <- .convertToMatrix(SummarizedExperiment::assays(sce)[[i]])

       out <- Matrix::writeMM(mat, assaypath)

-      

+

       if(isTRUE(gzipped)) {

         .checkOverwrite(paste0(assaypath, ".gz"), overwrite)

         R.utils::gzip(filename = assaypath, overwrite = overwrite)

       }

-    }  

+    }

   }

 }

@@ -94,13 +92,13 @@ exportSCEtoFlatFile <- function(sce,

   if (length(SingleCellExperiment::altExpNames(sce)) > 0) {

     altExpsFolder <- file.path(path, "/altExps")

     dir.create(altExpsFolder, showWarnings = FALSE, recursive = TRUE)

-    

+

     altExpNames <- SingleCellExperiment::altExpNames(sce)

     for (i in altExpNames) {

       sceAltExp <- SingleCellExperiment::altExp(sce, i, withColData = FALSE)

       altExpPath <- file.path(path, i)

       message(date(), " .. Writing altExp '", i, "'")

-      

+

       assaysFolder <- file.path(altExpPath, "/assays")

       dir.create(assaysFolder, showWarnings = FALSE, recursive = TRUE)

       .writeAssays(sceAltExp, path = assaysFolder, overwrite = overwrite, gzipped = gzipped, sample)

@@ -117,7 +115,7 @@ exportSCEtoFlatFile <- function(sce,

     data <- SummarizedExperiment::colData(sce)

     colDataPath <- file.path(path, paste(sample, "colData", sep="_"))

     .writeSCEFile(data, colDataPath, overwrite, gzipped)

-  } 

+  }

 }

@@ -137,7 +135,7 @@ exportSCEtoFlatFile <- function(sce,

   if (length(SingleCellExperiment::reducedDimNames(sce)) > 0) {

     reducedDimsFolder <- file.path(path, "reducedDims")

     dir.create(reducedDimsFolder, showWarnings = FALSE, recursive = TRUE)

-    

+

     if (length(reducedDimNames(sce)) > 0) {

       reducedDimNames <- SingleCellExperiment::reducedDimNames(sce)

       for (i in reducedDimNames) {

@@ -155,7 +153,7 @@ exportSCEtoFlatFile <- function(sce,

   if (length(S4Vectors::metadata(sce)) > 0) {

     metadataFolder <- file.path(path, "/metadata")

     dir.create(metadataFolder, showWarnings = FALSE, recursive = TRUE)

-    

+

     filename <- file.path(metadataFolder, paste(sample, "metadata.rds", sep="_"))

     .checkOverwrite(filename, overwrite)

     saveRDS(object = S4Vectors::metadata(sce), file = filename)

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

 #' @param sampleRelWidths If there are multiple samples and combining by "all",

 #'  the relative widths for each plot.

 #' @examples

-#' \donttest{

 #' data(scExample, package="singleCellTK")

+#' \donttest{

 #' sce <- sce[, colData(sce)$type != "EmptyDroplet"]

 #' sce <- getUMAP(inSCE=sce, useAssay="counts", reducedDimName="UMAP")

 #' sce <- runPerCellQC(sce)

@@ -888,7 +888,8 @@ plotDoubletFinderResults <- function(inSCE,

         pattern="doubletFinder_doublet_score_",

         "", x=x

       ))

-    })

+    }, character(1))

+

     # merged.plots <- list(merged.plots)

     merged.plots <- list(Violin = merged.plots)

   }

@@ -926,7 +927,7 @@ plotDoubletFinderResults <- function(inSCE,

             pattern="doubletFinder_doublet_score_",

             "", x=x

         ))

-    })

+    }, character(1))

     res.list <- c(res.list, densityScore)

     scatterScore <- lapply(df.scores, function(x) {

@@ -969,7 +970,7 @@ plotDoubletFinderResults <- function(inSCE,

         pattern="doubletFinder_doublet_score_",

         "", x=x

       ))

-    })

+    }, character(1))

     res.list <- c(res.list, scatterScore)

     if(combinePlot != "all" | length(samples) == 1){

@@ -1007,7 +1008,7 @@ plotDoubletFinderResults <- function(inSCE,

         pattern="doubletFinder_doublet_score_",

         "", x=x

       ))

-    })

+    }, character(1))

     res.list <- c(res.list, violinScore)

     }

@@ -1053,7 +1054,7 @@ plotDoubletFinderResults <- function(inSCE,

         pattern="doubletFinder_doublet_label_",

         "", x=x

       ))

-    })

+    }, character(1))

     res.list <- c(res.list, scatterCall)

     return(res.list)

   })

@@ -623,13 +623,11 @@ plotSCEDimReduceFeatures <- function(inSCE,

 #'  as the labels. If set to "none", no label will be plotted.

 #' @return a ggplot of the reduced dimensions.

 #' @examples

-#' \donttest{

 #' plotSCEScatter(

 #'   inSCE = mouseBrainSubsetSCE, legendTitle = NULL,

 #'   slot = "assays", annotation = "counts", feature = "Apoe",

 #'   reducedDimName = "TSNE_counts", labelClusters = FALSE

 #' )

-#' }

 #' @export

 #' @import SingleCellExperiment

 plotSCEScatter <- function(inSCE,

@@ -8,8 +8,8 @@

 #' @param output_dir name of the output directory to save the rendered file. If NULL/default the file is stored to the current working directory

 #' @return .html file

 #' @examples

-#' \dontrun{

 #' data(scExample, package = "singleCellTK")

+#' \dontrun{

 #' sce <- runDropletQC(sce)

 #' reportDropletQC(inSCE = sce)

 #' }

@@ -46,9 +46,9 @@ reportDropletQC <- function(inSCE, output_file = NULL,

 #' @param output_dir name of the output directory to save the rendered file. If NULL/default the file is stored to the current working directory

 #' @return .html file

 #' @examples

-#' \dontrun{

 #' data(scExample, package = "singleCellTK")

 #' sce <- sce[, colData(sce)$type != 'EmptyDroplet']

+#' \dontrun{

 #' sce <- runCellQC(sce)

 #' reportCellQC(inSCE = sce)

 #' }

@@ -83,9 +83,9 @@ reportCellQC <- function(inSCE, output_file = NULL,

 #' @param output_dir name of the output directory to save the rendered file. If NULL/default the file is stored to the current working directory

 #' @return .html file

 #' @examples

-#' \donttest{

 #' data(scExample, package = "singleCellTK")

 #' sce <- sce[, colData(sce)$type != 'EmptyDroplet']

+#' \donttest{

 #' sce <- runDecontX(sce)

 #' sce <- getUMAP(sce)

 #' reportQCTool(inSCE = sce, algorithm = "DecontX")

@@ -165,6 +165,12 @@ reportQCTool <- function(inSCE, algorithm=c("BarcodeRankDrops",

 #' @param output_dir name of the output directory to save the rendered file. If

 #' \code{NULL} the file is stored to the current working directory.

 #' Default \code{NULL}.

+#' @examples

+#' data(scExample, package = "singleCellTK")

+#' sce <- sce[, colData(sce)$type != 'EmptyDroplet']

+#' sce <- runDEAnalysis(inSCE = sce, groupName1 = "Sample1", method = "DESeq2",

+#'  groupName2 = "Sample2", index1 = 1:20, index2 = 21:40, analysisName = "DESeq2")

+#' reportDiffExp(sce, study = "DESeq2", output_file = "DESeq2_res")

 #' @return .html file

 #' @export

 reportDiffExp <- function(inSCE, study,

@@ -1,25 +1,25 @@

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

                                  sampleName = 'sample',

                                  delayedArray = TRUE){

-  

+

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

   if (!file.exists(anndata_file)){

     stop("AnnData file not found at specified location. Please check path provided and/or filename.")

   }

   anndata <- ad$read_h5ad(anndata_file)

-  

+

   counts_matrix <- t((reticulate::py_to_r(anndata$X)))

   if (isTRUE(delayedArray)) {

     counts_matrix <- DelayedArray::DelayedArray(counts_matrix)

   }

-  

+

   sce_rowdata <- S4Vectors::DataFrame(reticulate::py_to_r(anndata$var))

   sce_coldata <- S4Vectors::DataFrame(reticulate::py_to_r(anndata$obs))

   sce <- SingleCellExperiment(list(counts = counts_matrix),

                               rowData = sce_rowdata,

                               colData = sce_coldata)

   colnames(sce) <- paste0(sampleName,"_",colnames(sce))

-  

+

   multidim_observations <- reticulate::py_to_r(anndata$obsm_keys())

   for(obsm_name in multidim_observations){

     tryCatch({

@@ -28,9 +28,9 @@

       error_message <- paste0("Warning: unable to add '",uns_name,"' from .obsm AnnData slot to SCE metadata. Skipping. ")

       message(error_message)

     })

-    

+

   }

-  

+

   unstructured_data <- reticulate::py_to_r(anndata$uns_keys())

   for(uns_name in unstructured_data){

     tryCatch({

@@ -39,71 +39,72 @@

       error_message <- paste0("Warning: unable to add unstructured data (.uns slot): '",uns_name,"' to SCE metadata. Skipping. ")

       message(error_message)

     })

-    

+

   }

-  

+

   return(sce)

-  

+

 }

 #' @name importAnnData

 #' @rdname importAnnData

 #' @title Create a SingleCellExperiment Object from Python AnnData .h5ad files

-#' @description This function reads in one or more Python AnnData files in the .h5ad format 

-#' and returns a single \link[SingleCellExperiment]{SingleCellExperiment} object containing all the 

+#' @description This function reads in one or more Python AnnData files in the .h5ad format

+#' and returns a single \link[SingleCellExperiment]{SingleCellExperiment} object containing all the

 #' AnnData samples by concatenating their counts matrices and related information slots.

-#' @param sampleDirs Folder containing the .h5ad file. Can be one of - 

+#' @param sampleDirs Folder containing the .h5ad file. Can be one of -

 #' \itemize{

 #'   \item Default \code{current working directory}.

-#'   \item Full path to the directory containing the .h5ad file. 

+#'   \item Full path to the directory containing the .h5ad file.

 #'   E.g \code{sampleDirs = '/path/to/sample'}

-#'   \item A vector of folder paths for the samples to import. 

+#'   \item A vector of folder paths for the samples to import.

 #'   E.g. \code{sampleDirs = c('/path/to/sample1', '/path/to/sample2','/path/to/sample3')}

-#'   importAnnData will return a single SCE object containing all the samples 

+#'   importAnnData will return a single SCE object containing all the samples

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

 #' }

-#' @param sampleNames The prefix/name of the .h5ad file without the .h5ad extension 

+#' @param sampleNames The prefix/name of the .h5ad file without the .h5ad extension

 #' e.g. if 'sample.h5ad' is the filename, pass \code{sampleNames = 'sample'}.

-#' Can be one of - 

+#' Can be one of -

 #' \itemize{

 #'   \item Default \code{sample}.

 #'   \item A vector of samples to import. Length of vector must be equal to length of sampleDirs vector

 #'   E.g. \code{sampleDirs = c('sample1', 'sample2','sample3')}

-#'   importAnnData will return a single SCE object containing all the samples 

+#'   importAnnData will return a single SCE object containing all the samples

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

 #' }

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

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

 #' @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 

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

 #' format and becomes the 'counts' matrix in the assay slot. The .vars AnnData slot becomes the SCE rowData

 #' and the .obs AnnData slot becomes the SCE colData. Multidimensional data in the .obsm AnnData slot is

-#' ported over to the SCE reducedDims slot. Additionally, unstructured data in the .uns AnnData slot is 

-#' available through the SCE metadata slot. 

-#' There are 2 currently known minor issues - 

+#' ported over to the SCE reducedDims slot. Additionally, unstructured data in the .uns AnnData slot is

+#' available through the SCE metadata slot.

+#' There are 2 currently known minor issues -

 #' Anndata python module depends on another python module h5pyto read hd5 format files.

 #' If there are errors reading the .h5ad files, such as "ValueError: invalid shape in fixed-type tuple."

-#' the user will need to do downgrade h5py by running \code{pip3 install --user h5py==2.9.0} 

+#' the user will need to do downgrade h5py by running \code{pip3 install --user h5py==2.9.0}

 #' Additionally there might be errors in converting some python objects in the unstructured data slots.

 #' There are no known R solutions at present. Refer \url{https://github.com/rstudio/reticulate/issues/209}

 #' @return A \code{SingleCellExperiment} object.

 #' @examples

+#' file.path <- system.file("extdata/annData_pbmc_3k", package = "singleCellTK")

 #' \dontrun{

-#' sce <- importAnnData(sampleDirs = system.file("extdata/annData_pbmc_3k", package = "singleCellTK"),

+#' sce <- importAnnData(sampleDirs = file.path,

 #'                      sampleNames = 'pbmc3k_20by20')

 #' }

 #' @export

 importAnnData <- function(sampleDirs = NULL,

                           sampleNames = NULL,

                           delayedArray = 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")

   }

-  

+

   res <- vector("list", length = length(sampleDirs))

-  

+

   for (i in seq_along(sampleDirs)){

     scei <- .importAnnDataSample(sampleDir = sampleDirs[[i]],

                                  sampleName = sampleNames[[i]],

@@ -6,12 +6,12 @@

 #' \link[TENxPBMCData]{TENxPBMCData} packages. See 'Details' for a

 #' list of available datasets.

 #' @param dataset Character. Name of the dataset to retrieve.

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

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

 #'   object. Can be one of \code{"Matrix"} or \code{"matrix"}. \code{"Matrix"}

 #'   will store the data as a sparse matrix from package \link{Matrix} while

 #'   \code{"matrix"} will store the data in a standard matrix. Default

 #'   \code{"Matrix"}.

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

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

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

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

 #' descriptions.

@@ -24,32 +24,30 @@

 #' \code{\link[scRNAseq]{ReprocessedAllenData}}. Returns a dataset of 379 mouse

 #' brain cells from Tasic et al. (2016).}

 #' \item{"pbmc3k"}{Retrieved with \code{\link[TENxPBMCData]{TENxPBMCData}}.

-#'  2,700 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.} 

+#'  2,700 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.}

 #' \item{"pbmc4k"}{Retrieved with \code{\link[TENxPBMCData]{TENxPBMCData}}.

-#'  4,340 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.} 

+#'  4,340 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.}

 #' \item{"pbmc6k"}{Retrieved with \code{\link[TENxPBMCData]{TENxPBMCData}}.

-#'  5,419 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.} 

+#'  5,419 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.}

 #' \item{"pbmc8k"}{Retrieved with \code{\link[TENxPBMCData]{TENxPBMCData}}.

 #'  8,381 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.}

 #' \item{"pbmc33k"}{Retrieved with \code{\link[TENxPBMCData]{TENxPBMCData}}.

-#'  33,148 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.} 

+#'  33,148 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.}

 #' \item{"pbmc68k"}{Retrieved with \code{\link[TENxPBMCData]{TENxPBMCData}}.

 #'  68,579 peripheral blood mononuclear cells (PBMCs) from 10X Genomics.}

-#' }   

+#' }

 #' @author Joshua D. Campbell, David Jenkins

-#' @examples 

-#' \dontrun{

+#' @examples

 #' sce <- importExampleData("pbmc3k")

-#' }

 #' @export

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

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

                               delayedArray = FALSE) {

   class <- match.arg(class)

-  

+

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

   tenxPbmcDatasets <- c("pbmc3k", "pbmc4k", "pbmc6k", "pbmc8k", "pbmc33k", "pbmc68k")

-  

+

   if(dataset %in% scRNAseqDatasets) {

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

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

@@ -72,15 +70,15 @@ importExampleData <- function(dataset, class = c("Matrix", "matrix"),

   } else {

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

   }

-    

+

   # Convert to sparseMatrix or regular matrix

   for(i in seq_along(names(assays(temp)))) {

     if (class == "matrix") {

       assay(temp, i) <- as.matrix(temp)

     } else if(class == "Matrix") {

-      assay(temp, i) <- .convertToMatrix(assay(temp, i))  

+      assay(temp, i) <- .convertToMatrix(assay(temp, i))

     }

-    

+

     if (isTRUE(delayedArray)) {

       assay(temp, i) <- DelayedArray::DelayedArray(assay(temp, i))

     }

@@ -10,7 +10,7 @@

   #  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() 

+    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

@@ -18,14 +18,14 @@

          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() 

+    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({

     mat <- sparse$load_npz(matrixLocation)

     colIndex <- as.vector(numpy$load(colIndexLocation, allow_pickle = TRUE))

@@ -54,11 +54,11 @@

     rownames(newM) <- rownames(mat)

     mat <- newM

   }, 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))

   }

-  

+

   if (class == "matrix") {

     mat <- as.matrix(mat)

   }

@@ -251,10 +251,10 @@

 #'  containing the count

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

 #' @examples

+#' file.path <- system.file("extdata/Optimus_20x1000",

+#'   package = "singleCellTK")

 #' \dontrun{

-#' sce <- importOptimus(OptimusDirs =

-#'   system.file("extdata/Optimus_20x1000",

-#'   package = "singleCellTK"),

+#' sce <- importOptimus(OptimusDirs = file.path,

 #'   samples = "Optimus_20x1000")

 #' }

 #' @export

@@ -236,6 +236,10 @@ featureNameDedup <- function(countmat){

 #' or to identify partial matches using \code{\link{grep}}. Default \code{TRUE}

 #' @param firstMatch A logical scalar. Whether to only identify the first

 #' matches or to return all plausible matches. Default \code{TRUE}

+#' @examples

+#' data(scExample, package = "singleCellTK")

+#' retrieveSCEIndex(inSCE = sce, IDs = "ENSG00000205542",

+#'  axis = "row")

 #' @return A unique, non-NA numeric vector of indices for the matching

 #' features/cells in \code{inSCE}.

 #' @author Yusuke Koga, Joshua Campbell

@@ -172,6 +172,9 @@ plotBatchVariance <- function(inSCE, useAssay = NULL, useReddim = NULL,

 #' @param xlab label for x-axis. Default \code{"batch"}.

 #' @param ylab label for y-axis. Default \code{"Feature Mean"}.

 #' @param ... Additional arguments passed to \code{\link{.ggViolin}}.

+#' @examples

+#' data('sceBatches', package = 'singleCellTK')

+#' plotSCEBatchFeatureMean(sceBatches, useAssay = "logcounts")