diff --git a/.gitignore b/.gitignore index 0f456112..7f20e6ac 100644 --- a/.gitignore +++ b/.gitignore @@ -8,4 +8,11 @@ work # Python related files *__pycache__* -.venv \ No newline at end of file +.venv + +# R related files +.Rproj.user +htrnaseq.Rproj + +# vscode +.vscode diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 00000000..14bce61b --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,9 @@ +# demultiplex v0.2.0 + +# New functionality + +* Make sure that the Well ID matches the required format (PR #22). + +# demultiplex v0.1.0 + +Initial release diff --git a/README.md b/README.md index 7bb25386..20d55213 100644 --- a/README.md +++ b/README.md @@ -122,3 +122,8 @@ nextflow run . -main-script target/nextflow/workflows/htrnaseq/main.nf \ ``` Or, by running `src/workflows/htrnaseq/integration_test.sh`. + + +# Special Thanks + +Developed in collaboration with Data Intuitive and Open Analytics. \ No newline at end of file diff --git a/src/base/authors/dries_schaumont.yaml b/src/base/authors/dries_schaumont.yaml new file mode 100644 index 00000000..c8eaa47d --- /dev/null +++ b/src/base/authors/dries_schaumont.yaml @@ -0,0 +1,11 @@ +name: Dries Schaumont +info: + links: + email: dries@data-intuitive.com + github: DriesSchaumont + orcid: "0000-0002-4389-0440" + linkedin: dries-schaumont + organizations: + - name: Data Intuitive + href: https://www.data-intuitive.com + role: Data Scientist \ No newline at end of file diff --git a/src/base/authors/marijke_van_moerbeke.yaml b/src/base/authors/marijke_van_moerbeke.yaml new file mode 100644 index 00000000..429bd926 --- /dev/null +++ b/src/base/authors/marijke_van_moerbeke.yaml @@ -0,0 +1,10 @@ +name: Marijke Van Moerbeke +info: + links: + github: mvanmoerbeke + orcid: 0000-0002-3097-5621 + linkedin: marijke-van-moerbeke-84303a34 + organizations: + - name: OpenAnalytics + href: https://www.openanalytics.eu + role: Statistical Consultant \ No newline at end of file diff --git a/src/base/authors/toni_verbeiren.yaml b/src/base/authors/toni_verbeiren.yaml new file mode 100644 index 00000000..aa78550d --- /dev/null +++ b/src/base/authors/toni_verbeiren.yaml @@ -0,0 +1,10 @@ +name: Toni Verbeiren +info: + role: Core Team Member + links: + github: tverbeiren + linkedin: verbeiren + organizations: + - name: Data Intuitive + href: https://www.data-intuitive.com + role: Data Scientist and CEO \ No newline at end of file diff --git a/src/config/labels.config b/src/config/labels.config index 66f5e21c..2821ec46 100644 --- a/src/config/labels.config +++ b/src/config/labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/src/eset/create_eset/config.vsh.yaml b/src/eset/create_eset/config.vsh.yaml index f6848dd3..194c2bce 100644 --- a/src/eset/create_eset/config.vsh.yaml +++ b/src/eset/create_eset/config.vsh.yaml @@ -1,5 +1,10 @@ name: create_eset namespace: "eset" +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ author ] argument_groups: - name: "Arguments" arguments: diff --git a/src/eset/create_eset/test_data/pData.tsv b/src/eset/create_eset/test_data/pData.tsv index e7fe4de3..3bfc64e0 100644 --- a/src/eset/create_eset/test_data/pData.tsv +++ b/src/eset/create_eset/test_data/pData.tsv @@ -1,3 +1,3 @@ -WellBC NumberOfMTReads pctMT NumberOfERCCReads pctERCC NumberOfChromReads pctChrom NumberOfInputReads NumberOfMappedReads PctMappedReads NumberOfReadsMappedToMultipleLoci PectOfReadsMappedToMultipleLoci NumberOfReadsMappedToTooManyLoci PectOfReadsMappedToTooManyLoci NumberOfReadsUnmappedTooManyMismatches PectOfReadsUnmappedTooManyMismatches NumberOfReadsUnmappedTooShort PectOfReadsUnmappedTooShort NumberOfReadsUnmappedOther PectOfReadsUnmappedOther ReadsWithValidBarcodes SequencingSaturation Q30BasesInCB+UMI ReadsMappedToTranscriptome:Unique+MultipeGenes EstimatedNumberOfCells FractionOfReadsInCells MeanReadsPerCell NumberOfUMIs NumberOfGenes NumberOfCountedReads -AACAAGGTAC 0 0 0 0 8542 100 141303 23749 16.81 0 0 8458 5.99 0 0 109035 77.16 61 0.04 0.999816 0.0698056 0.979965 0.0618175 1 1 8538 7942 408 9535 -ACGCCTTCGT 0 0 0 0 5863 100 96430 16869 17.49 0 0 6124 6.35 0 0 73375 76.09 62 0.06 0.999782 0.0665302 0.980077 0.0620969 1 1 5862 5472 377 6463 +WellBC WellID NumberOfMTReads pctMT NumberOfERCCReads pctERCC NumberOfChromReads pctChrom NumberOfInputReads NumberOfMappedReads PctMappedReads NumberOfReadsMappedToMultipleLoci PectOfReadsMappedToMultipleLoci NumberOfReadsMappedToTooManyLoci PectOfReadsMappedToTooManyLoci NumberOfReadsUnmappedTooManyMismatches PectOfReadsUnmappedTooManyMismatches NumberOfReadsUnmappedTooShort PectOfReadsUnmappedTooShort NumberOfReadsUnmappedOther PectOfReadsUnmappedOther ReadsWithValidBarcodes SequencingSaturation Q30BasesInCB+UMI ReadsMappedToTranscriptome:Unique+MultipeGenes EstimatedNumberOfCells FractionOfReadsInCells MeanReadsPerCell NumberOfUMIs NumberOfGenes NumberOfCountedReads +AACAAGGTAC A1 0 0 0 0 8542 100 141303 23749 16.81 0 0 8458 5.99 0 0 109035 77.16 61 0.04 0.999816 0.0698056 0.979965 0.0618175 1 1 8538 7942 408 9535 +ACGCCTTCGT B2 0 0 0 0 5863 100 96430 16869 17.49 0 0 6124 6.35 0 0 73375 76.09 62 0.06 0.999782 0.0665302 0.980077 0.0620969 1 1 5862 5472 377 6463 diff --git a/src/eset/create_fdata/config.vsh.yaml b/src/eset/create_fdata/config.vsh.yaml index f9cff04f..9a5651d4 100644 --- a/src/eset/create_fdata/config.vsh.yaml +++ b/src/eset/create_fdata/config.vsh.yaml @@ -2,6 +2,11 @@ name: create_fdata namespace: eset description: | Create a fdata file +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ contributor ] arguments: - name: "--gtf" type: file diff --git a/src/eset/create_pdata/config.vsh.yaml b/src/eset/create_pdata/config.vsh.yaml index 1dd868b6..48933e37 100644 --- a/src/eset/create_pdata/config.vsh.yaml +++ b/src/eset/create_pdata/config.vsh.yaml @@ -2,6 +2,11 @@ name: create_pdata namespace: eset description: | Create a pdata file by combining the mapping statistics +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ contributor ] arguments: - name: "--star_stats_file" type: file diff --git a/src/eset/create_pdata/create_pdata.py b/src/eset/create_pdata/create_pdata.py index 34d3cdd3..8f703648 100644 --- a/src/eset/create_pdata/create_pdata.py +++ b/src/eset/create_pdata/create_pdata.py @@ -33,7 +33,7 @@ def main(par): logger.info("Reads per gene and chromosome table contains information for the following barcodes: %s", ", ".join(reads_and_genes_per_chr_stats.index)) logger.info("Filtering mapping statistics file columns.") - cols_to_keep = ("NumberOfMTReads", "pctMT", "NumberOfERCCReads", + cols_to_keep = ("WellID", "NumberOfMTReads", "pctMT", "NumberOfERCCReads", "pctERCC", "NumberOfChromReads", "pctChrom") try: reads_and_genes_per_chr_stats = reads_and_genes_per_chr_stats.loc[:,cols_to_keep] diff --git a/src/eset/create_pdata/nrReadsNrGenesPerChromPool.txt b/src/eset/create_pdata/nrReadsNrGenesPerChromPool.txt index ee68ce33..0b678058 100644 --- a/src/eset/create_pdata/nrReadsNrGenesPerChromPool.txt +++ b/src/eset/create_pdata/nrReadsNrGenesPerChromPool.txt @@ -1,8 +1,8 @@ -WellBC 20 pctChrom pctMT pctERCC SumReads NumberOfGenes NumberOfERCCReads NumberOfChromReads NumberOfMTReads -AACAAGGTAC 8542 100 0 0 8542 408 0 8542 0 -ACGCCTTCGT 5863 100 0 0 5863 377 0 5863 0 -CCATACTGAC 7396 100 0 0 7396 391 0 7396 0 -GCAAGCGAAT 10092 100 0 0 10092 420 0 10092 0 -GTCTCGAGTG 470 100 0 0 470 150 0 470 0 -TGCGCTCATT 7650 100 0 0 7650 407 0 7650 0 -TTGTGTTCGA 9422 100 0 0 9422 420 0 9422 0 +WellBC WellID 20 pctChrom pctMT pctERCC SumReads NumberOfGenes NumberOfERCCReads NumberOfChromReads NumberOfMTReads +AACAAGGTAC A1 8542 100 0 0 8542 408 0 8542 0 +ACGCCTTCGT A2 5863 100 0 0 5863 377 0 5863 0 +CCATACTGAC A3 7396 100 0 0 7396 391 0 7396 0 +GCAAGCGAAT B1 10092 100 0 0 10092 420 0 10092 0 +GTCTCGAGTG C5 470 100 0 0 470 150 0 470 0 +TGCGCTCATT D6 7650 100 0 0 7650 407 0 7650 0 +TTGTGTTCGA E19 9422 100 0 0 9422 420 0 9422 0 diff --git a/src/eset/create_pdata/test.py b/src/eset/create_pdata/test.py index 7385df8f..5f1e3bb4 100644 --- a/src/eset/create_pdata/test.py +++ b/src/eset/create_pdata/test.py @@ -43,6 +43,7 @@ def test_create_fdata(run_component, test_reads_and_genes_per_chr_path, expected_dict = { 'WellBC': ['AACAAGGTAC', 'ACGCCTTCGT', 'CCATACTGAC', 'GCAAGCGAAT', 'GTCTCGAGTG', 'TGCGCTCATT', 'TTGTGTTCGA'], + 'WellID': ['A1', 'A2', 'A3', 'B1', 'C5', 'D6', 'E19'], 'NumberOfMTReads': ['0', '0', '0', '0', '0', '0', '0'], 'pctMT': ['0', '0', '0', '0', '0', '0', '0'], 'NumberOfERCCReads': ['0', '0', '0', '0', '0', '0', '0'], diff --git a/src/integration_test_components/htrnaseq/check_eset/config.vsh.yaml b/src/integration_test_components/htrnaseq/check_eset/config.vsh.yaml index 1b470ad4..9c5b6d94 100644 --- a/src/integration_test_components/htrnaseq/check_eset/config.vsh.yaml +++ b/src/integration_test_components/htrnaseq/check_eset/config.vsh.yaml @@ -1,6 +1,9 @@ name: "check_eset" namespace: "integration_test_components/htrnaseq" description: "This component test the ExpressionSet object as output by the main pipeline." +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ author, maintainer ] argument_groups: - name: Inputs arguments: diff --git a/src/integration_test_components/htrnaseq/check_eset/script.R b/src/integration_test_components/htrnaseq/check_eset/script.R index 179195bf..a5be5613 100644 --- a/src/integration_test_components/htrnaseq/check_eset/script.R +++ b/src/integration_test_components/htrnaseq/check_eset/script.R @@ -129,6 +129,7 @@ stopifnot(identical(sampleNames(sample_1_result), expected_sample_names)) expected_var_labels <- c( "WellBC", + "WellID", "NumberOfMTReads", "pctMT", "NumberOfERCCReads", diff --git a/src/parallel_map/config.vsh.yaml b/src/parallel_map/config.vsh.yaml index 8856f4ad..aee6457f 100644 --- a/src/parallel_map/config.vsh.yaml +++ b/src/parallel_map/config.vsh.yaml @@ -3,6 +3,11 @@ description: | Map wells in batch, using STAR Spliced Transcripts Alignment to a Reference (C) Alexander Dobin https://github.com/alexdobin/STAR +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] + - __merge__: /src/base/authors/toni_verbeiren.yaml + roles: [ author, maintainer ] requirements: commands: - STAR diff --git a/src/report/OutputSTARsolo.png b/src/report/OutputSTARsolo.png new file mode 100644 index 00000000..cb77d8e0 Binary files /dev/null and b/src/report/OutputSTARsolo.png differ diff --git a/src/report/config.vsh.yaml b/src/report/config.vsh.yaml new file mode 100644 index 00000000..cf0efbd7 --- /dev/null +++ b/src/report/config.vsh.yaml @@ -0,0 +1,73 @@ +name: create_report +namespace: "report" +description: | + Create a basic QC report in HTML format based on a number of esets. +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ author, maintainer ] +argument_groups: + - name: "Arguments" + arguments: + - type: file + name: "--eset" + required: true + multiple: true + - type: file + name: "--output_report" + required: true + direction: output + example: report.html +resources: + - type: r_script + path: script.R + - type: r_script + path: template.Rmd + - type: r_script + path: plateLayouts.R + - path: OutputSTARsolo.png + type: file +test_resources: + - type: r_script + path: test.R + - path: ./test_data +engines: + - type: docker + image: rocker/r2u:24.04 + setup: + - type: apt + packages: + - procps + - pandoc + - type: r + bioc: + - Biobase + - ComplexHeatmap + cran: + - ggplot2 + - knitr + - gridExtra + - RColorBrewer + - processx + - whisker + - rmarkdown + - bookdown + - data.table + - platetools + - htmltools + - DT + - logger + - bit64 + script: + - install.packages("oaStyle", repos = c(rdepot = "https://repos.openanalytics.eu/repo/public", getOption("repos"))) + test_setup: + - type: r + packages: + - testthat + - R.utils +runners: + - type: executable + - type: nextflow + + \ No newline at end of file diff --git a/src/report/plateLayouts.R b/src/report/plateLayouts.R new file mode 100644 index 00000000..c8b16cff --- /dev/null +++ b/src/report/plateLayouts.R @@ -0,0 +1,424 @@ + +#' Displays the annotation of the wells in a plateLayout +#' @param plateData a data.table object containing the information +#' of the plate. This must contain a "WellID". +#' @param plateName The plate name +#' @param valueVariable The name of the variable in 'plateData' to +#' be visualized in a plate layout. +#' @param textVariable The name of the variable in 'plateData' to be +#' shown in the wells of the plate layout. If NULL, the valueVariable +#' is shown. +#' @param colours A named character vector containing the colours +#' for the different levels of the valuevariable. The names should +#' correspond to the dose levels. if not specified, a scheme of blues +#' will be provided. +#' @param breaks Numeric vector indicating breaks for plot coloring. +#' @param colourWellText Colour to display the text in the wells. +#' @param layout Integer vector of length two with number of rows and +#' colums in a plate, e.g. \code{c(16,24)} +#' @param legend.title A title for the legend +#' @param plot.title A title for the plot, will be contracted +#' with the plate name +#' @param ... additional arguments for \code{plateLayout.default} function +#' @import data.table +#' @importFrom platetools fill_plate +#' @export +plateLayout.annotation <- function( + plateData, + plateName = character(), + valueVariable = "Dose", + textVariable = NULL, + breaks = NULL, colours = NULL, + colourWellText = "black", + layout = c(16, 24), + legend.title = "Dose", + plot.title = "Plate Annotation - ", + textFontSize = 9, ... +) { + WellID <- Label <- NULL + + if (!(all(c("WellID", "SampleName") %in% colnames(plateData)))) { + stop(" 'WellID' and 'SampleName' column required in plateData object") + } + + + plateData[, WellID := paste0( + sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + sprintf( + "%02d", as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ) + )] + + plateData <- platetools::fill_plate(plateData, "WellID", plate = 384) + + plateData$column <- factor( + sprintf( + "%02d", + as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ), + levels = sprintf("%02d", seq(1, layout[2])) + ) + plateData$row <- factor(sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + levels = LETTERS[seq(1, layout[1])]) + + if (!is.null(valueVariable)){ + plateData[, values := as.character(plateData[, ..valueVariable][[1]])] + valueVar <- "values" + }else{ + plateData[, values := "grey"] + valueVar <- "values" + colours <- setNames("grey", "grey") + } + + + if (is.null(colours)) { + + blues <- colorRampPalette(c("#d6e0ff", "#2171B5")) + greens <- colorRampPalette(c("light green", "dark green")) + + numLevels <- sort(as.numeric(as.character(unique(plateData[, values])[ + grepl( + "^[[:digit:]]+([.][[:digit:]]+)?$", + trimws(unique(plateData[, values])) + ) + ]))) + otherLevels <- sort(as.character(unique(plateData[, values])[ + !grepl( + "^[[:digit:]]+([.][[:digit:]]+)?$", + trimws(unique(plateData[,values])) + ) + ])) + + colours <- c(blues(length(numLevels)), greens(length(otherLevels)), "red") + names(colours) <- c(numLevels, otherLevels, "failed") + } + + if (!is.null(textVariable)) { + plateData[, + Label := do.call(paste, c(.SD, sep = "\n ")), + .SDcols = textVariable + ] + plateData[, Label := gsub("-", "-\n", Label)] + plateData[, Label := gsub("_", "_\n", Label)] + textVar <- "Label" + } else { + textVar <- NULL + } + + + if (is.null(breaks)){ + breaks <- seq_len(length(colours)) + } + + plateLayout( + plateData = plateData, valueVariable = valueVar, + textVariable = textVar, plateName = plateName, + breaks = breaks, colourWellText = colourWellText, + legend.title = legend.title, layout = layout, + colours = colours, plot.title = plot.title, + textFontSize = textFontSize, ... + ) +} + + + +#' Create a heatmap of values in a plateLayout view. The values can be +#' library sizes, number of genes, qcScore (0/1) or a factor. +#' @param plateData A data.table of the values to be visualized with +#' at least the column of interest (specified in 'varOfInterest') +#' and a 'WellID' column indicating the wells in the plate. The WellID +#' is a combination of a letter (row in the plate) and an integer +#' (column in the plate). +#' @param valueVariable The name of the variable in 'plateData' +#' to be visualized in a plate layout +#' @param textVariable The name of the variable in 'plateData' +#' to be shown in the wells of the plate layout. Defaults to the +#' valueVariable and if NULL, no text will be displayed. +#' @param breaks Numeric vector indicating breaks for plot coloring. +#' @param colours Colours to be used for levels specified by +#' the breaks. If NULL, a colour scheme of purples is shown. +#' @param colourWellText Colour to display the text in the wells. +#' @param layout Integer vector of length two with number of rows +#' and colums in a plate, e.g. \code{c(16,24)} +#' @param makeContourColours Logical, whether or not the plate +#' layout will contain a contour colours for the wells based on the +#' parameters in 'contourColours' and 'categories' +#' @param contourVariable The variable used for the contour colouring +#' @param contourColours Character vector specifying a colour for +#' each range in 'categories' +#' @param labelsCategories Character vector specifying the names +#' (labels) for each range in 'categories' +#' @param categories if contour Variable is not a factor, a numeric +#' vector specifying the categories to divide the 'varOfInterest', +#' including the lower and upper limits. +#' @param plateName The plate name +#' @param plot.title A title for the plot, will be contracted with +#' the plate name +#' @param legend.title A title for the legend +#' @param displayHeatmap Logical, whether to display the plateLayout heatmap +#' @param saveHeatmap Logical, whether to save the plateLayout heatmap +#' @param outputDir The directory where the plateLayout heatmap should be saved +#' @param prefix The prefix to the file name of the saved plateLayout heatmap +#' @param ... additional arguments for \code{ComplexHeatmap::Heatmap} function +#' @importFrom platetools fill_plate +#' @importFrom RColorBrewer brewer.pal +#' @importFrom ComplexHeatmap Heatmap +#' @importFrom circlize colorRamp2 +#' @importFrom grid grid.text grid.rect gpar legendGrob gpar +#' @importFrom grDevices dev.off png +#' @importFrom graphics title +#' @export +plateLayout <- function( + plateData, valueVariable, textVariable = valueVariable, + breaks = NULL, colours = NULL, colourWellText = "white", textFontSize = 6, + layout = c(16, 24), makeContourColours = FALSE, contourVariable = character(), + contourColours = c("red", "orange", "seagreen3"),lwdContours = c(1, 1, 1), + labelsCategories = c('1', '2', '3'), categories = NULL, plateName = character(), + plot.title = character(), legend.title = NULL, legendFontSize = 15, + row_split = rep("A", 16), col_split = rep("A", 24), legendFontSizeTitle = 15, + displayHeatmap = TRUE, saveHeatmap = FALSE, outputDir = ".", prefix = "" +) { + WellID <- NULL + if (!(all(c("WellID", "SampleName") %in% colnames(plateData)))) { + stop(" 'WellID' and 'SampleName' column required in plateData object") + } + + + plateData[, WellID := paste0( + sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + sprintf( + "%02d", + as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ) + )] + + plateData <- platetools::fill_plate(plateData, "WellID", plate = 384) + + plateData$column <- factor( + sprintf("%02d", as.numeric( + sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID) + )), + levels = sprintf("%02d", seq(1, layout[2])) + ) + plateData$row <- factor(sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + levels = LETTERS[seq(1, layout[1])]) + + + plateValues <- plateLayoutFormat( + plateData, + varOfInterest = valueVariable, + rows = layout[1], + cols = layout[2] + ) + if (!is.null(textVariable)) { + plateText <- plateLayoutFormat( + plateData, varOfInterest = textVariable, + rows = layout[1], + cols = layout[2] + ) + } + plot.title <- gsub( + "^([a-z])", "\\U\\1", + gsub("([A-Z])", " \\1", + plot.title, perl = TRUE), perl = TRUE + ) + mainTitle <- paste0(plot.title, plateName) + plateContourColours <- matrix("", nrow = layout[1], ncol = layout[2]) + + if (makeContourColours) { + contourData <- plateData[WellType %in% c("nonEmpty", "Treated Wells"), ] + + if (is.numeric(contourData[, ..contourVariable][[1]])) { + contourData$contours <- cut( + contourData[, ..contourVariable][[1]], + categories, left = TRUE, + right = TRUE, + labels = labelsCategories) + } + else { + contourData$contours <- contourData[, ..contourVariable][[1]] + } + names(contourColours) <- labelsCategories + names(lwdContours) <- labelsCategories + for (i in seq_len(layout[1])) { + for (j in seq_len(layout[2])) { + tryCatch({ + sampleHit <- which( + as.character(contourData$WellID) == paste0( + LETTERS[i], sprintf("%02d", j) + ) + ) + if (length(sampleHit) == 1) { + plateContourColours[i, j] <- as.character( + contourData[sampleHit,'contours'][[1]] + ) + } + }, + error = function(e) { + print(paste0(LETTERS[i], sprintf("%02d", j), " is missing.")) + } + ) + } + } + } + + plateValues$contours <- plateContourColours + colnames(plateValues$values) <- seq_len(ncol(plateValues$values)) + + if (is.null(breaks)) { + breakValues <- plateValues$values + breakValues[which(is.na(breakValues))] <- 0 + if (all(breakValues >= 0)) { + breaks <- computeBreaks(7, max(plateValues$values, na.rm = TRUE)) + } else { + breaks <- quantile(plateValues$values, probs = seq(0, 1, 0.125)) + } + } + + if (is.null(colours)) { + colours <- tryCatch({ + colorRamp2( + breaks = breaks, + colors = brewer.pal(length(breaks), "Purples") + ) + }, + error = function(cond) { + return(c("#9370DB", "white")) + }) + } + ht <- Heatmap( + plateValues$values, + column_title = mainTitle, column_title_side = "top", + rect_gp = gpar(lwd = 0.4), + cluster_rows = FALSE, cluster_columns = FALSE, + col = colours, row_title = NULL, + row_split = row_split, column_split = col_split, + row_names_side = "left", + cluster_row_slices = FALSE, + cluster_column_slices = FALSE, + show_heatmap_legend = TRUE, + heatmap_legend_param = list( + title = ifelse( + is.null(legend.title), + paste0(valueVariable, "\n"), + paste0(legend.title, "\n") + ), + grid_height = unit(9, "mm"), border = "black", + labels_gp = gpar(fontsize = legendFontSize), + title_gp = gpar(fontsize = legendFontSizeTitle) + ), + cell_fun = function(j, i, x, y, width, height, fill) { + if (is.na(plateValues$values[i, j])) { + grid.rect( + x, y, width, height, + gp = gpar(fill = "white", alpha = 0.7, lwd = 0.7, col = "white") + ) + } + else if (!is.null(textVariable)) { + grid.text( + plateText$values[i, j], x, y, + just = "centre", + gp = gpar(fontsize = textFontSize, col = colourWellText) + ) + } + if (makeContourColours) { + if (!is.na(plateValues$contours[i, j])) { + grid.rect( + x, y, width, height, + gp = gpar( + col = contourColours[as.character(plateValues$contours[i, j])], + fill = NA, + lwd = lwdContours[as.character(plateValues$contours[i, j])] + ) + ) + } + } + } + ) + + if (displayHeatmap) { + print(ht) + } + if (saveHeatmap) { + png( + file.path( + outputDir, + paste0(prefix,gsub(" |-", "",plot.title), "_", plateName, ".png") + ), + width = 30, height = 10, units = "cm", res = 1200 + ) + print(ht) + dev.off() + } + + return(ht) +} + + +#' Return numerical matrix with number of reads that corresponds to the +#' plate layout +#' @param data A data.frame of the values to be visualized with at least +#' the columnof interest (specified in 'varOfInterest') and a 'WellID' column +#' indicating the wells in the plate. The WellID is a combination of a +#' letter (row in the plate) and an integer (column in the plate). +#' @param varOfInterest The name of the variable in 'data' to be visualized +#' in a plate layout +#' @param rows number of rows in a plate layout +#' @param cols number of columns in a plate layout +#' @param verbose if \code{TRUE}, samples missing from the plate +#' will be reported +#' @export +plateLayoutFormat <- function( + data, varOfInterest, + rows = 16, cols = 24, + verbose = FALSE +) { + plateValues <- matrix(NA, nrow = rows, ncol = cols) + for (i in seq_len(rows)) { + for (j in seq_len(cols)) { + tryCatch({ + sampleHit <- which( + as.character(data$WellID) == paste0(LETTERS[i], sprintf("%02d", j)) + ) + if(length(sampleHit) == 1){ + plateValues[i, j] <- data[sampleHit, ..varOfInterest][[1]] + } + }, + error = function(e) { + if (verbose == TRUE) { + print(paste0(LETTERS[i], sprintf("%02d", j), " is missing.")) + } + } + ) + } + } + + row.names(plateValues) <- LETTERS[1:rows] + return(list("values" = plateValues)) +} + + + +#' Helper function to automate break selection for raw count data +#' +#' This function creates an exponentially increasing vector for given number +#' breaks between zero and some element of choice. It is particularly useful for +#' raw counts or raw counts per million. +#' +#' @param nBreaks Number of breaks to be generated +#' @param maxElement Maximum value of data entries +#' @export +computeBreaks <- function(nBreaks, variable) { + + maxElement <- max(variable, na.rm = TRUE) + if (length(unique(variable)) == 1) { + breaks <- c(0, 0.5, ifelse(maxElement < 1, 1, maxElement)) + } else { + coefSystem <- solve( + rbind(c(1, 1), c(1, (nBreaks - 1)))) %*% c(0, log(maxElement) + ) + coefExp <- c(exp(coefSystem[1]), coefSystem[2]) + breaks <- coefExp[1] * exp((1:(nBreaks - 1)) * coefExp[2]) + } + return(c(0, breaks)) +} \ No newline at end of file diff --git a/src/report/script.R b/src/report/script.R new file mode 100644 index 00000000..7ab2a467 --- /dev/null +++ b/src/report/script.R @@ -0,0 +1,33 @@ +library(whisker) +library(logger) + +log_info("Setting temporary directory to: {meta$temp_dir}") +Sys.setenv(TMP = meta$temp_dir) +temp_folder <- tempdir(check = TRUE) +log_info("Created temporary directory {temp_folder}") + +template <- file.path(meta$resources_dir, "template.Rmd") + +esets_normalized <- lapply(par$eset, function(eset_path) { + return(file.path(normalizePath(dirname(eset_path)), basename(eset_path))) +}) + +log_info(paste0( + "Rendering markdown {template} to HTML ", + "{par$output_report} with esets {paste(esets_normalized, collapse = ', ')}" +)) + +rmarkdown::render( + normalizePath(template), + output_file = basename(par$output_report), + output_dir = dirname(par$output_report), + runtime = "static", + intermediates_dir = par$report_dir, + clean = TRUE, + params = list( + esets = esets_normalized, + outputDir = par$report_dir + ) +) + +log_info("Done") diff --git a/src/report/template.Rmd b/src/report/template.Rmd new file mode 100644 index 00000000..20f8c190 --- /dev/null +++ b/src/report/template.Rmd @@ -0,0 +1,977 @@ +--- +title: "Exploratory Data Report" +date: "`r format(Sys.time(), '%d %B, %Y')`" +editor_options: + chunk_output_type: console +output: + oaStyle::html_report +# parameters which are overwritten by the script +params: + outputDir: 'output/' + esets: + - sample1.rds + - sample2.rds +--- + + + + + + + + + +```{r params, eval = TRUE, include = FALSE} +outputDir <- params$outputDir +esets <- params$esets +``` + + +```{r outputDir, echo = FALSE} +## Required: ABSOLUTE outputDir +outputDir <- file.path(outputDir) + +# When working on a windows computer it should be +# "/Users/..." instead of "C:/Users/..." +if (.Platform$OS.type == "windows") { + outputDir <- paste0( + "/", + paste( + unlist(strsplit(outputDir, split = "/"))[-1], collapse = "/" + ), + "/" + ) +} +``` + + + + +```{r optionsChunkDoNotModify, echo = FALSE, message = FALSE, warning=FALSE} + +## Chunk with options for knitr. This chunk should not be modified. +knitr::opts_chunk$set( + eval = TRUE, + echo = FALSE, + message = FALSE, + cache = FALSE, + warning = FALSE, + error = FALSE, + comment = NA, #"#", + tidy = FALSE, + collapse = TRUE, + out.width = "100%", + fig.width = 20, + fig.height = 10, + results = "asis") + +knitr::opts_knit$set(root.dir = getwd()) + +options(warn = 1, width = 200) + +``` + +```{r libraries_and_functions} +source("plateLayouts.R") +library(ComplexHeatmap) +library(data.table) +library(ggplot2) +library(knitr) +library(Biobase) +library(gridExtra) +library(RColorBrewer) +``` + + +```{r dataImport} + +# Create esetList +esetList <- sapply( + esets, simplify = FALSE, + USE.NAMES = TRUE, + function(eset_raw) { + if (!file.exists(eset_raw)) { + stop(paste0("Provided path '", eset_raw, "' is not a file.")) + } + eset <- readRDS(eset_raw) + } +) +pools <- sapply(esetList, function(eset) { + unique(eset$PoolName) +}) +names(esetList) <- unlist(pools) + +# Create qcData +pDataList <- lapply(esetList, function(eset) data.table(pData(eset))) +qcData <- rbindlist(pDataList, fill = TRUE) + +textVars <- "SampleName" +annotationVar <- "PoolName" + +if (!"SampleName" %in% names(qcData)) { + qcData[, SampleName := paste0(PoolName, "_", WellBC)] +} +qcData[, log10LibSize := round(log10(NumberOfInputReads))] +qcData[, (annotationVar) := lapply(.SD, as.factor), .SDcols = annotationVar] + + +colourList <- list() +Design_levels <- sort( + as.character(unique(qcData[, ..annotationVar][[1]])), + decreasing = TRUE +) + +if (length(Design_levels) == 1) { + colours <- c("#d6e0ff", "lightgrey") + names(colours) <- c(Design_levels, "Empty") + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +}else if (length(Design_levels) == 2) { + colours <- c("#d6e0ff", "#FF9999") + + names(colours) <- c(Design_levels) + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +} else if (length(Design_levels) <= 20) { + + if (length(Design_levels) > 12) { + colours <- c( + brewer.pal(12, "Set3"), + brewer.pal((length(Design_levels) - 12), + "Pastel2") + ) + } else { + colours <- c(brewer.pal(length(Design_levels), "Set3")) + } + + names(colours) <- c(Design_levels) + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +} else { + colours <- c("#d6e0ff") + names(colours) <- c("nonEmpty") + colourList[[annotVar]] <- list( + "colours" = colours, + "annotVar" = annotVar, + "text" = annotVar + ) +} +``` + +# Pool Description + +Per pool within this study, there are several pool layout plots shown, based on the + +* number of STAR input reads (= library size) + +* log10 transformed number of STAR input reads + +* number of detected UMIs + +* number of detected genes + +* number of chromosomal reads + +* percentage of ERCC + +* percentage of mitochondria + + +> The values for the different samples within each pool is expected to be comparable if the content of the different pools is equally diverse. + +```{r plateAnnotation, out.width = "100%",fig.width = 20, fig.height= 10} + +plateVars <- c("NumberOfInputReads", "log10LibSize", "NumberOfMappedReads", + "NumberOfChromReads", "NumberOfUMIs", "NumberOfGenes", + "pctMT", "pctERCC") + +breaksVars <- lapply( + plateVars, + function(var) { + computeBreaks(7, qcData[, ..var]) + } +) +names(breaksVars) <- plateVars + +for (pool in pools){ + cat("\n\n") + cat(paste0("## ", pool, " {.tabset} \n\n")) + poolData <- qcData[PoolName == pool] + lapply(plateVars, function(plateVar) { + cat("\n\n") + cat(sprintf("### %s {.unnumbered}", plateVar)) + cat("\n\n") + plateLayout( + poolData, valueVariable = plateVar, + textFontSize = 10, legendFontSize = 12, + plateName = pool, plot.title = "libSize - ", + legend.title = "libSize", breaks = breaksVars[[plateVar]] + ) + cat("\n\n") + }) + cat("\n\n") +} +``` + +
+ + +# Data Distributions + + +## Reads Distributions {.tabset} + +The 4 box plots below represent the distributions per pool of the different samples based on: + +* the number of STAR input reads + +* the number of STAR mapped reads + +* the percentage of STAR mapped reads + +* the number of detected genes + +> The distributions contribute to the QC metrics mentioned in Par 3. The higher these values, the better. +> The data range for the different plates is expected to be comparable if the content of the different plates is equally diverse. + + +### Number of Input Reads {.tabset .unnumbered} + +```{r settings_1} + +nColPlots = 1 +figHeight = 7 + +``` + +#### Distribution {.tabset .unnumbered} + + +```{r boxplots_input_plate, fig.height = figHeight} +ggplot( + qcData, + aes( + x = PoolName, + y = NumberOfInputReads, colour = PoolName + ) +) + geom_boxplot() + ylab("Number of Input Reads") + + ggtitle("Number of Input Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + + +### Number of Mapped Reads {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_mapped_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfMappedReads, colour = PoolName) +) + geom_boxplot() + ylab("Number of Mapped Reads") + + ggtitle("Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +#### pct Mapped Reads {.unnumbered} + +```{r boxplots_pctMapped_plate, fig.height = figHeight} +ggplot( + qcData, + aes(x = PoolName, y = PctMappedReads, colour = PoolName) +) + + geom_boxplot() + + ylab("pct Mapped Reads") + + ggtitle("pct Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### Number of Chromosomal Reads {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_chrom_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfChromReads, colour = PoolName) +) + geom_boxplot() + ylab("Number of Chromosomal Reads") + + ggtitle("Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + +#### pct Chromosomal Reads {.unnumbered} + +```{r boxplots_pctChrom_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = pctChrom, colour = PoolName) +) + geom_boxplot() + ylab("pct Chromosomal Reads") + + ggtitle("pct Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### Number of UMIs {.tabset .unnumbered} + +#### Distribution {.tabset .unnumbered} + + +```{r boxplots_umi_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfUMIs, colour = PoolName) +) + geom_boxplot() + ylab("Number of UMIs") + + ggtitle('Number of UMIs') + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + +#### Density distribution {.unnumbered} + +```{r density_numberOfUMIs} + +## Pre-filtering data exploration +dt_plot <- melt( + qcData, + id.vars = c("SampleName", "PoolName", "WellID"), + measure.vars = c("NumberOfInputReads", "NumberOfMappedReads", "NumberOfUMIs") +) + +readsDensity_plot <- ggplot(dt_plot, aes(value)) +readsDensity_plot <- readsDensity_plot + + geom_density(aes(fill = variable), alpha=0.8) + + facet_grid(~ PoolName, scales = "free_x", space = "fixed", drop = TRUE) + + geom_vline( + xintercept = 5e5, + linetype = "dashed", + color = "steelblue3", size = 2 + ) + + annotate( + "text", + x = 3.5e5, y = 2e-6, label = "500k", + angle = 90, color = "steelblue3", size = 10 + ) + + geom_vline( + xintercept = 1.5e6, linetype = "dashed", + color = "forestgreen", size = 2 + ) + + annotate( + "text", x = 1.35e6, y = 2e-6, label = "1.5M", + angle = 90, color = "forestgreen", size = 10 + ) + + labs( + title = "Density plot", + subtitle = paste0( + "# Samples with NumberOfMappedReads > 1.5M: ", + length(which(qcData$NumberOfMappedReads > 1.5e6)), + "\n# Samples with NumberOfUMIs > 500k: ", + length(which(qcData$NumberOfUMIs > 5e5)) + ), + caption = paste0("# Total samples (after removing empty): ", nrow(qcData)), + x = "Count", + fill = "Variable" + ) + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 5), + axis.text.x = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + plot.subtitle = element_text(size = 17), + plot.caption = element_text(size = 15), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.y = element_blank(), + axis.ticks.y = element_blank(), + axis.title.y = element_blank() + ) +readsDensity_plot + +``` + +### Number of Genes {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_genes_plate, fig.height = figHeight} +ggplot( + qcData, + aes(x = PoolName, y = NumberOfGenes, colour = PoolName) +) + + geom_boxplot() + ylab("Number of Genes") + + ggtitle("Number of Genes") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +## {.tabset .toc-ignore .unnumbered} + + +In addition, several plots are shown visualizing the efficiency of the reads-to-genes translation: + +* the number of input reads vs the number of mapped reads + +* the number of chromosomal reads vs the number of mapped reads + +* the number of mapped reads per UMI vs the number of mapped reads + +* the number of UNI vs the number of mapped reads + +* the number of mapped reads vs the number of genes + +* the number of chromosomal reads vs the number of genes + +* the number of mapped reads per UMI vs the number of genes + +### Mapping Efficiency {.tabset .unnumbered} + +#### Number of Input Reads {.unnumbered} + +```{r mapping_efficiency_1_plate, fig.height = 7} + +ggplot( + qcData, + aes(x = NumberOfInputReads, y = NumberOfMappedReads, colour = PoolName) +) + + geom_point() + + xlab("Number of Input Reads") + + ylab("Number of Mapped Reads") + + ggtitle("Number of Mapped Reads vs Number of Input Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + + +#### Number of Chromosomal Reads {.unnumbered} + +```{r mapping_efficiency_2_plate, fig.height = 7} + +ggplot( + qcData, + aes(x = NumberOfChromReads, y = NumberOfMappedReads, colour = PoolName) +) + geom_point() + + xlab("Number of Chromosomal Reads") + ylab("Number of Mapped Reads") + + ggtitle("Number of Chromosomal Reads vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) +) + +``` + + +#### Number of UMI {.unnumbered} + +```{r mapping_efficiency_4_plate, fig.height = 7} + +ggplot( + qcData, + aes(x =NumberOfUMIs, y = NumberOfMappedReads, colour = PoolName) +) + geom_point() + + ylab("Number of Mapped Reads") + xlab("Number of UMIs ") + + ggtitle("Number of UMIs vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + +### Counting Efficiency {.tabset .unnumbered} + +#### Number of Mapped Reads {.unnumbered} + +```{r gene_efficiency_1_plate, fig.height = 7} +ggplot( + qcData, + aes(x = NumberOfMappedReads, y = NumberOfGenes, colour = PoolName) +) + geom_point() + + ylab("Number of Genes") + xlab("Number of Mapped Reads") + + ggtitle("Number of Genes vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + +#### Number of Chromosomal Reads {.unnumbered} + +```{r gene_efficiency_2_plate, fig.height = 7} +ggplot( + qcData, + aes(x = NumberOfChromReads, y = NumberOfGenes, colour = PoolName) +) + geom_point() + + ylab("Number of Genes") + xlab("Number of Chromosomal Reads") + + ggtitle("Number of Genes vs Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + + + +## Sequencing Saturation {.tabset} + +The barplots below represent the sequencing saturation per sample as determined by STAR, split per pool. +The HT-RNAseq platform aims for shallow sequencing resulting in relatively low sequencing saturations of 10-20%. +In addition, the sequencing saturation vs the number of input reads is shown. + +### Sequencing Saturation {.unnumbered} + + + +```{r sequencingSaturation, fig.height = figHeight} + +ggplot( + qcData, + aes(x = WellID, y = SequencingSaturation, fill = PoolName) +) + geom_bar(stat = "identity", position = "dodge") + + xlab("Samples") + ggtitle("Sequencing Saturation per Sample") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(1, "lines"), + text = element_text(size = 10), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.text.y = element_text(size = 15), + axis.ticks.x = element_blank() + ) +``` + +### Sequencing Saturation - Input Reads {.unnumbered} + + +```{r sequencingSaturation_inputReads, fig.height = figHeight} + + +ggplot( + qcData, + aes(x = NumberOfInputReads, y = SequencingSaturation, colour = PoolName) +) + geom_point() + + ggtitle("Sequencing Saturation vs Number of Input Reads") + + theme(strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + +### Sequencing Saturation - Mapped Reads {.unnumbered} + +```{r sequencingSaturation_mappedReads, fig.height = figHeight} +ggplot( + qcData, + aes(x = NumberOfChromReads, y = SequencingSaturation, colour = PoolName) +) + geom_point() + + ggtitle("Sequencing Saturation vs Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size=10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size=18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) +) +``` + +
+ +## Genomic Origin {.tabset} + +The 3 boxplots below represent, per pool, the distributions of the percentage of reads mapping to: + +* chromosomal regions + +* mitochondrial regions + +* ERCC spike-ins + +The 4th plot summarises the above results across samples per pool. + +The 5th plot shows the percentage of reads mapped to the transcriptome (as counted by STAR). This measurement serves as a proxy for the percentage of reads mapped to exons. + +> The percentage ERCC contributes to the QC metrics mentioned in Par 3. This value is ideally as low as possible (but non-zero to ensure the they have been spiked in) and comparable for the different pools. + + + + +### pctChrom {.tabset .unnumbered} + + +```{r genomicOrigin_chrom_plate, fig.height = figHeight} + +ggplot( + qcData, aes(x = PoolName, y = pctChrom, colour = PoolName) +) + + geom_boxplot() + + ggtitle("pctChrom") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +### pctMT {.tabset .unnumbered} + +```{r genomicOrigin_mt_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = pctMT, colour = PoolName) +) + + geom_boxplot() + ggtitle("pctMT") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### pctERCC {.tabset .unnumbered} + + +```{r genomicOrigin_ercc_plate, fig.height = figHeight} +ggplot(qcData, aes(x = PoolName, y = pctERCC, colour = PoolName)) + + geom_boxplot() + + ggtitle("pctERCC") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +### Genomic Summary {.tabset .unnumbered} + + + +```{r genomicOrigin_summary_plate} +meanPctChromMTData <- qcData[, .( + "pctChrom" = median(pctChrom), + "pctMT" = median(pctMT), + "pctERCC" = median(pctERCC) +), by = PoolName] +meanPctChromMTDataLong <- melt( + meanPctChromMTData, + id.vars = "PoolName", + measure.vars = c("pctChrom", "pctMT", "pctERCC"), + variable.name = "Origin", value.name = "pct" +) +ggplot( + meanPctChromMTDataLong, + aes(fill = Origin, y = pct, x = PoolName)) + + geom_bar(position = "stack", stat = "identity") + + ggtitle("Genomic Origin") + + theme( + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + + + +# Depletion {.tabset} + +
+```{r depletion} + + +for (eset_name in pools) { + cat("\n\n") + cat(paste0("## ", eset_name, " {.unnumbered}")) + cat("\n\n") + + eset <- esetList[[eset_name]] + average_reads <- sort(apply(exprs(eset), 1, mean), decreasing = TRUE) + plotData <- data.table( + ENSGID = names(average_reads), + av_count = average_reads + ) + + gen_descript <- data.table( + ENSGID = eset@featureData@data$gene_id, + Description = eset@featureData@data$GENENAME + ) + order_gen_descript <- gen_descript[ + match(plotData$ENSGID, gen_descript$ENSGID), + ] + + g <- ggplot( + plotData[c(1:100)], + aes(x = reorder(ENSGID, -av_count), y = av_count) + ) + geom_bar(stat = "identity") + + theme( + axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size = 12), + axis.text.y = element_text(size = 12), + legend.text = element_text(size = 15), + legend.title = element_text(size = 15), + axis.title = element_text(size = 18), + plot.title = element_text(size = 20) + ) + ylab("Average Counts") + xlab("Genes") + + print(g) + + cat("\n\n") + cat("
") + cat("
") + + print(htmltools::tagList((DT::datatable(order_gen_descript[1:100, ])))) +} +``` +
+ + +
+
+
+
+ +# Glossary {.unnumbered} + + +## Read {.unlisted .unnumbered} + +A read is a oligonucleotide (a short RNA fragment) that has been sequenced. It consists of a fixed number of base pairs (bp) and therefore has a specific read length. + + + +## Input Read {.unlisted .unnumbered} + +Each read of the fastq file used as input to the STAR aligner is considered an input read. + + + +## Read With Valid Barcode {.unlisted .unnumbered} + +A read with a valid barcode is a read for which the barcode matches the white list of barcodes under the given restriction of the number of allowed mismatches. The number of reads with a valid barcode is lower or equal to the number of input reads. + + + +## Mapped Read {.unlisted .unnumbered} + +A read that has been aligned against the reference genome and for which one or more suitable matching locations have been found is a mapped read. Depending on the number of allowed mismatches this might or might not be be an exact match. The number of mapped reads is lower or equal to the number of reads with a valid barcode. + + + +## Uniquely Mapped Read {.unlisted .unnumbered} + +A read for which one and only one suitable matching location in the reference genome was found is an uniquely mapped read. The number of uniquely mapped reads is lower or equal to the number of mapped reads. + + + +## Counted Read {.unlisted .unnumbered} + +A mapped read will only be counted if it overlaps (1 nucleotide or more) with one and only one gene. The number of counted reads is lower or equal to the number of (uniquely) mapped reads. + + + +## UMIs {.unlisted .unnumbered} + +Unique molecular identifiers (UMI) are short sequences in order to uniquely tag each molecule in a sample library. Sequencing with UMIs allows bioinformatics software to filter out duplicate reads and PCR errors with a high level of accuracy and report unique reads. + +The reported UMIs is the number of UMIs among the set of reads that map to an unique gene, i.e the number of reads is deduplicated. + + + +## pctERCC {.unlisted .unnumbered} + +The percentage of reads mapping to the ERCC genes among the total number of **mapped** reads. + + + +## pctMT {.unlisted .unnumbered} + +The percentage of reads mapping to the MT genes among the total number of **mapped** reads. + + + +## Sequencing Saturation {.unlisted .unnumbered} + +The sequencing saturation is a measure of the fraction of library complexity. The inverse of one minus the sequencing saturation can be interpreted as the number of additional reads it would take to detect a new transcript. Consequently, a low sequencing saturation indicates a shallow sequencing in which a new transcript could be discovered with a few reads. + +
+
+
+
+ +
+![](OutputSTARsolo.png) +
+ +
+
diff --git a/src/report/test.R b/src/report/test.R new file mode 100644 index 00000000..84c15694 --- /dev/null +++ b/src/report/test.R @@ -0,0 +1,41 @@ +library(whisker) +library(testthat) +library(R.utils) + +cat(">> Creating temporary directory \n") +Sys.setenv(TMP = meta$temp_dir) +temp_folder <- tempdir(check = TRUE) + +cat(">> Running component create_report for test case \n") + +input_dir <- file.path(meta$resources_dir, "test_data") +stopifnot(file.exists(input_dir)) + + +out <- processx::run(meta$executable, c( + "--eset", file.path(meta$resources_dir, "test_data", "eset.sample_one.rds"), + "--eset", file.path(meta$resources_dir, "test_data", "eset.sample_two.rds"), + "--output_report", "report.html" +)) + +expect_equal(out$status, 0) +expect_true(file.exists("report.html")) + +cat(">> Test succesful \n") + +cat(">> Running component create_report with symbolic links \n") + +link_sample_1 <- file.path(temp_folder, "eset.sample_one.rds") +link_sample_2 <- file.path(temp_folder, "eset.sample_two.rds") +createLink(link = link_sample_1, + target = file.path(meta$resources_dir, "test_data", "eset.sample_one.rds")) +createLink(link = link_sample_2, + target = file.path(meta$resources_dir, "test_data", "eset.sample_two.rds")) + +out <- processx::run(meta$executable, c( + "--eset", link_sample_1, + "--eset", link_sample_2, + "--output_report", "report2.html" +)) + +expect_true(file.exists("report2.html")) \ No newline at end of file diff --git a/src/report/test_data/eset.sample_one.rds b/src/report/test_data/eset.sample_one.rds new file mode 100644 index 00000000..f440362e Binary files /dev/null and b/src/report/test_data/eset.sample_one.rds differ diff --git a/src/report/test_data/eset.sample_two.rds b/src/report/test_data/eset.sample_two.rds new file mode 100644 index 00000000..c622f216 Binary files /dev/null and b/src/report/test_data/eset.sample_two.rds differ diff --git a/src/stats/combine_star_logs/config.vsh.yaml b/src/stats/combine_star_logs/config.vsh.yaml index fb3fd831..61cf6c6c 100644 --- a/src/stats/combine_star_logs/config.vsh.yaml +++ b/src/stats/combine_star_logs/config.vsh.yaml @@ -1,5 +1,8 @@ name: combine_star_logs namespace: "stats" +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ author, maintainer ] argument_groups: - name: "Arguments" arguments: diff --git a/src/stats/generate_pool_statistics/config.vsh.yaml b/src/stats/generate_pool_statistics/config.vsh.yaml index 68f8fa8b..3c9263bc 100644 --- a/src/stats/generate_pool_statistics/config.vsh.yaml +++ b/src/stats/generate_pool_statistics/config.vsh.yaml @@ -1,5 +1,10 @@ name: generate_pool_statistics namespace: "stats" +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ author, maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ contributor ] argument_groups: - name: "Arguments" arguments: diff --git a/src/stats/generate_pool_statistics/script.py b/src/stats/generate_pool_statistics/script.py index 92c4a4d4..48f68845 100644 --- a/src/stats/generate_pool_statistics/script.py +++ b/src/stats/generate_pool_statistics/script.py @@ -9,6 +9,8 @@ par = { ### VIASH END +INDEX_COL = ["WellBC", "WellID"] + if __name__ == "__main__": ######### # nrReadsNrGenesPerChrom file @@ -18,17 +20,18 @@ if __name__ == "__main__": nr_reads_nr_genes_wells.append(pd.read_csv(nr_reads_nr_genes_file, header=0, delimiter="\t", dtype={"WellBC": pd.StringDtype(), + "WellID": pd.StringDtype(), "Chr": pd.StringDtype(), "NumberOfReads": pd.UInt64Dtype(), "NumberOfGenes": pd.UInt64Dtype()})) nr_reads_nr_genes_pool = pd.concat(nr_reads_nr_genes_wells, ignore_index=True,) - total_nr_reads_per_chromosome = nr_reads_nr_genes_pool.pivot_table(index="WellBC", columns="Chr", + total_nr_reads_per_chromosome = nr_reads_nr_genes_pool.pivot_table(index=INDEX_COL, columns="Chr", values=["NumberOfReads"], fill_value=0, aggfunc="sum").droplevel(0, axis=1) total_nr_reads_per_chromosome.columns.name = None ##### Total number of genes from all chromosomes - total_nr_genes = nr_reads_nr_genes_pool.loc[:,['WellBC', 'NumberOfGenes']].groupby("WellBC").sum() + total_nr_genes = nr_reads_nr_genes_pool.loc[:, INDEX_COL + ['NumberOfGenes']].groupby(["WellBC", "WellID"]).sum() ##### Total counts across (irrespective of chromosome) total_sum_of_reads = total_nr_reads_per_chromosome.sum(numeric_only=True, axis=1) @@ -77,9 +80,9 @@ if __name__ == "__main__": **cols_to_add ) - total_nr_reads_per_chromosome.reset_index(names="WellBC")\ + total_nr_reads_per_chromosome.reset_index(names=INDEX_COL)\ .to_csv(par["nrReadsNrGenesPerChromPool"], sep="\t", header=True, index=False, float_format="%g", - columns=("WellBC",) + tuple(chromosome_names) + tuple(cols_to_add.keys()) + columns=tuple(INDEX_COL) + tuple(chromosome_names) + tuple(cols_to_add.keys()) ) diff --git a/src/stats/generate_pool_statistics/test.py b/src/stats/generate_pool_statistics/test.py index aa757870..de3a2683 100644 --- a/src/stats/generate_pool_statistics/test.py +++ b/src/stats/generate_pool_statistics/test.py @@ -1,6 +1,5 @@ from uuid import uuid4 from textwrap import dedent -from io import StringIO import pandas as pd import pytest import sys @@ -35,14 +34,14 @@ def simple_input_file_one(random_tsv_path, request): contents = dedent( f"""\ - WellBC Chr NumberOfReads NumberOfGenes - AGG {prefix}1 2 1 - AGG {prefix}2 3 2 - AGG {prefix}3 4 2 - AGG {mito_name} 4 2 - AGG {prefix}X 2 3 - AGG ERCC-1 1 1 - AGG ERCC-2 1 1 + WellBC WellID Chr NumberOfReads NumberOfGenes + AGG A1 {prefix}1 2 1 + AGG A1 {prefix}2 3 2 + AGG A1 {prefix}3 4 2 + AGG A1 {mito_name} 4 2 + AGG A1 {prefix}X 2 3 + AGG A1 ERCC-1 1 1 + AGG A1 ERCC-2 1 1 """) output_file = random_tsv_path() with output_file.open("w") as open_file: @@ -55,15 +54,15 @@ def simple_input_file_two(random_tsv_path, request): prefix = request.param contents = dedent( f"""\ - WellBC Chr NumberOfReads NumberOfGenes - CCC {prefix}2 2 1 - CCC {prefix}3 3 2 - CCC {prefix}5 4 2 - CCC {prefix}1 4 2 - CCC {prefix}Y 2 3 - CCC {prefix}X 2 3 - CCC ERCC-3 1 1 - CCC ERCC-2 1 1 + WellBC WellID Chr NumberOfReads NumberOfGenes + CCC B2 {prefix}2 2 1 + CCC B2 {prefix}3 3 2 + CCC B2 {prefix}5 4 2 + CCC B2 {prefix}1 4 2 + CCC B2 {prefix}Y 2 3 + CCC B2 {prefix}X 2 3 + CCC B2 ERCC-3 1 1 + CCC B2 ERCC-2 1 1 """) output_file = random_tsv_path() with output_file.open("w") as open_file: @@ -85,6 +84,7 @@ def test_generate_pool_statistics_simple(run_component, simple_input_file_one, mito_name = f"{expected}M{'T' if not expected else ''}" expected_dict = { "WellBC": ["AGG", "CCC"], + "WellID": ["A1", "B2"], "ERCC-1": ["1", "0"], "ERCC-2": ["1", "1"], "ERCC-3": ["0", "1"], @@ -118,11 +118,11 @@ def test_only_numerical_chromosomes(run_component, random_tsv_path): output_path = random_tsv_path() contents1 = dedent( f"""\ - WellBC Chr NumberOfReads NumberOfGenes - CCC 2 2 1 - CCC 3 3 2 - CCC 5 4 2 - CCC 1 4 2 + WellBC WellID Chr NumberOfReads NumberOfGenes + CCC B2 2 2 1 + CCC B2 3 3 2 + CCC B2 5 4 2 + CCC B2 1 4 2 """) input_file_1 = random_tsv_path() with input_file_1.open("w") as open_file: @@ -130,11 +130,11 @@ def test_only_numerical_chromosomes(run_component, random_tsv_path): contents2 = dedent( f"""\ - WellBC Chr NumberOfReads NumberOfGenes - AGG 2 2 1 - AGG 3 3 2 - AGG 5 4 2 - AGG 1 4 2 + WellBC WellID Chr NumberOfReads NumberOfGenes + AGG A1 2 2 1 + AGG A1 3 3 2 + AGG A1 5 4 2 + AGG A1 1 4 2 """) input_file_2 = random_tsv_path() with input_file_2.open("w") as open_file: @@ -148,6 +148,7 @@ def test_only_numerical_chromosomes(run_component, random_tsv_path): expected_dict = { "WellBC": ["AGG", "CCC"], + "WellID": ["A1", "B2"], "1": ["4", "4"], "2": ["2", "2"], "3": ["3", "3"], diff --git a/src/stats/generate_well_statistics/config.vsh.yaml b/src/stats/generate_well_statistics/config.vsh.yaml index c49bca3f..60904be8 100644 --- a/src/stats/generate_well_statistics/config.vsh.yaml +++ b/src/stats/generate_well_statistics/config.vsh.yaml @@ -1,6 +1,11 @@ name: generate_well_statistics namespace: "stats" description: Generate summary statistics from BAM files generated by STAR solo. +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ author, maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ contributor ] argument_groups: - name: "Arguments" arguments: @@ -15,6 +20,11 @@ argument_groups: The barcode for the well that is being processed. Is only used to add a metadata column to all output files. required: true + - name: "--well_id" + type: string + description: | + ID of this well. Only used to add a metadata column to the output files. + required: true - name: "--processedBAMFile" type: file description: | diff --git a/src/stats/generate_well_statistics/script.py b/src/stats/generate_well_statistics/script.py index 95b2ac49..a1bcfff6 100644 --- a/src/stats/generate_well_statistics/script.py +++ b/src/stats/generate_well_statistics/script.py @@ -36,11 +36,11 @@ if __name__ == "__main__": columns=tags_selection) tag_dataframe_to_write = tag_dataframe.copy() logger.info("Done reading BAM file. Found %i entries", tag_dataframe.shape[0]) - tag_dataframe.assign(WellBC=par["barcode"])\ + tag_dataframe.assign(WellBC=par["barcode"], WellID=par["well_id"])\ .reset_index(names="Chr")\ .to_csv(par["processedBAMFile"], sep="\t", na_rep="", header=True, index=False, - columns=("WellBC", "Chr") + tags_selection) + columns=("WellBC", "WellID", "Chr") + tags_selection) logger.info("Constructing of dataframe done.") # Number of genes that had a read mapped to them per chromosome, # and the number of reads mapped to those genes per chromosome. @@ -50,19 +50,19 @@ if __name__ == "__main__": ) logger.info("Done calculating number of reads per gene and per chromesome. Writing to %s", par['nrReadsNrGenesPerChrom']) - nr_reads_nr_genes.reset_index(names="Chr").assign(WellBC=par["barcode"])\ + nr_reads_nr_genes.reset_index(names="Chr").assign(WellBC=par["barcode"], WellID=par["well_id"])\ .to_csv(par["nrReadsNrGenesPerChrom"], sep="\t", header=True, index=False, - columns=("WellBC", "Chr", "NumberOfReads", "NumberOfGenes")) + columns=("WellBC", "WellID", "Chr", "NumberOfReads", "NumberOfGenes")) # Number of reads mapped to the reference, grouped by UMI nr_read_per_umi = tag_dataframe.groupby('UB').size()\ .drop("", errors="ignore").sort_values(ascending=False).head(100) nr_read_per_umi_df = nr_read_per_umi.to_frame(name="N") logger.info("Done calculating number of mapped reads per UMI, writing to %s", par["umiFreqTop"]) - nr_read_per_umi_df.assign(WellBC=par["barcode"]).reset_index(names="UB")\ + nr_read_per_umi_df.assign(WellBC=par["barcode"], WellID=par["well_id"]).reset_index(names="UB")\ .to_csv(par["umiFreqTop"], header=True, sep="\t", - index=False, columns=("WellBC", "UB", "N")) + index=False, columns=("WellBC", "WellID", "UB", "N")) # Total number of mapped reads and total number of UMIs (not grouped per chromosome) nr_reads_and_umi_per_barcode = tag_dataframe.groupby(by="CB").agg( @@ -71,7 +71,7 @@ if __name__ == "__main__": ) logger.info("Done calculating number of mapped reads and number of UMIs per Cell Barcode, writing to %s", par["nrReadsNrUMIsPerCB"]) - nr_reads_and_umi_per_barcode.assign(WellBC=par["barcode"]).reset_index(names="CB")\ + nr_reads_and_umi_per_barcode.assign(WellBC=par["barcode"], WellID=par["well_id"]).reset_index(names="CB")\ .to_csv(par["nrReadsNrUMIsPerCB"], sep="\t", header=True, - index=False, columns=("WellBC", "CB", "NumberOfReads", "nrUMIs")) + index=False, columns=("WellBC", "WellID", "CB", "NumberOfReads", "nrUMIs")) logger.info("Finished!") \ No newline at end of file diff --git a/src/stats/generate_well_statistics/test.py b/src/stats/generate_well_statistics/test.py index d84a22a2..aa1ad48c 100644 --- a/src/stats/generate_well_statistics/test.py +++ b/src/stats/generate_well_statistics/test.py @@ -63,7 +63,8 @@ def test_generate_well_statistics_simple_bam(run_component, input_sam_path, sam_ "--nrReadsNrGenesPerChrom", reads_per_chromosome, "--nrReadsNrUMIsPerCB", nr_reads_nr_umis_per_cb, "--umiFreqTop", top_onehundred_umis, - "--barcode", "ACGT" + "--barcode", "ACGT", + "--well_id", "A1", ]) for file_path in (processed_bam, reads_per_chromosome, nr_reads_nr_umis_per_cb, top_onehundred_umis): @@ -71,33 +72,33 @@ def test_generate_well_statistics_simple_bam(run_component, input_sam_path, sam_ expected_processed_bam = \ dedent("""\ - WellBC Chr CB UB GX GN - ACGT 1 ACA CGG gene1 gene1 - ACGT 1 ACA CGG gene1 gene1 - ACGT 2 GGG GTT gene2 gene2 - ACGT 2 GGG GTC gene3 gene3 + WellBC WellID Chr CB UB GX GN + ACGT A1 1 ACA CGG gene1 gene1 + ACGT A1 1 ACA CGG gene1 gene1 + ACGT A1 2 GGG GTT gene2 gene2 + ACGT A1 2 GGG GTC gene3 gene3 """) expected_reads_per_chromosome = \ dedent("""\ - WellBC Chr NumberOfReads NumberOfGenes - ACGT 1 2 1 - ACGT 2 2 2 + WellBC WellID Chr NumberOfReads NumberOfGenes + ACGT A1 1 2 1 + ACGT A1 2 2 2 """) expected_nr_reads_nr_umis_per_cb = \ dedent("""\ - WellBC CB NumberOfReads nrUMIs - ACGT ACA 2 1 - ACGT GGG 2 2 + WellBC WellID CB NumberOfReads nrUMIs + ACGT A1 ACA 2 1 + ACGT A1 GGG 2 2 """) expected_top_onehundred_umis = \ dedent("""\ - WellBC UB N - ACGT CGG 2 - ACGT GTC 1 - ACGT GTT 1 + WellBC WellID UB N + ACGT A1 CGG 2 + ACGT A1 GTC 1 + ACGT A1 GTT 1 """) assert_file_content_equals(processed_bam, expected_processed_bam) diff --git a/src/workflows/htrnaseq/config.vsh.yaml b/src/workflows/htrnaseq/config.vsh.yaml index d4523c77..e92f13ba 100644 --- a/src/workflows/htrnaseq/config.vsh.yaml +++ b/src/workflows/htrnaseq/config.vsh.yaml @@ -1,5 +1,8 @@ name: htrnaseq namespace: workflows +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] argument_groups: - name: Input arguments arguments: @@ -74,6 +77,11 @@ argument_groups: direction: output required: true default: pData.$id.tsv + - name: "--html_report" + type: file + direction: output + required: true + default: report.html resources: - type: nextflow_script path: main.nf @@ -101,6 +109,8 @@ dependencies: repository: local - name: eset/create_pdata repository: local + - name: report/create_report + repository: local repositories: - name: local type: local diff --git a/src/workflows/htrnaseq/integration_test.sh b/src/workflows/htrnaseq/integration_test.sh index 57f83a39..a5f68e1b 100755 --- a/src/workflows/htrnaseq/integration_test.sh +++ b/src/workflows/htrnaseq/integration_test.sh @@ -18,4 +18,4 @@ nextflow \ -entry test_wf \ -resume \ -profile docker,local \ - --publish_dir output \ + --publish_dir output diff --git a/src/workflows/htrnaseq/main.nf b/src/workflows/htrnaseq/main.nf index 170b0f49..d6c1d64c 100644 --- a/src/workflows/htrnaseq/main.nf +++ b/src/workflows/htrnaseq/main.nf @@ -15,21 +15,6 @@ workflow run_wf { // Perform mapping of each well. The input here are events per pool, // the output channel is one event per well. mapping_ch = input_ch - | map {id, state -> - def n_barcodes = state.barcodesFasta.countFasta() as int - def newState = state + ["n_barcodes": n_barcodes] - // The header is the full header, the id is the part header up to the first whitespace character - // We do not allow whitespace in the header of the fasta file, so assert this. - def fasta_entries = state.barcodesFasta.splitFasta(record: ["id": true, "header": true, "seqString": true]) - assert fasta_entries.every{it.id == it.header}, "The barcodes FASTA headers must not contain any whitespace!" - // Check if the fasta headers are unique - def fasta_ids = fasta_entries.collect{it.id} - assert fasta_ids.clone().unique() == fasta_ids, "The barcodes FASTA entries must have a unique name!" - // Check if the sequences are unique - def fasta_sequences = fasta_entries.collect{it.seqString} - assert fasta_sequences.clone().unique() == fasta_sequences, "The barcodes FASTA sequences must be unique!" - [id, newState] - } | well_demultiplex.run( fromState: [ "input_r1": "input_r1", @@ -41,7 +26,7 @@ workflow run_wf { def filtered_results = result.findAll{!["output_r1", "output_r2"].contains(it.key)} def new_state = filtered_input + filtered_results + [ "fastq_output_r1": result.output_r1, - "fastq_output_r2": result.output_r2, + "fastq_output_r2": result.output_r2, ] return new_state } @@ -69,6 +54,7 @@ workflow run_wf { [ "input": state.star_output.resolve('Aligned.sortedByCoord.out.bam'), "barcode": state.barcode, + "well_id": state.well_id, ] }, toState: [ @@ -79,7 +65,7 @@ workflow run_wf { // Create a special groupKey, such that groupTuple // knows when all the barcodes have been grouped into 1 event. // This way the processing is as distributed as possible. - def key = groupKey(state.pool, state.n_barcodes) + def key = groupKey(state.pool, state.n_wells) def newEvent = [key, state] return newEvent } @@ -95,10 +81,14 @@ workflow run_wf { def barcodes = states.collect{it.barcode} assert barcodes.clone().unique().size() == barcodes.size(), \ "Error when gathering information for pool ${id}, barcodes are not unique!" + def well_ids = states.collect{it.well_id} + assert well_ids.clone().unique().size() == well_ids.size(), \ + "Error when gathering information for pool ${id}, well IDs are not unique!" def custom_state = [ "fastq_output_r1": states.collect{it.fastq_output_r1[0]}, "fastq_output_r2": states.collect{it.fastq_output_r2[0]}, "barcode": barcodes, + "well_id": well_ids, "star_output": states.collect{it.star_output}, "nrReadsNrGenesPerChrom": states.collect{it.nrReadsNrGenesPerChrom}, ] @@ -167,7 +157,7 @@ workflow run_wf { toState: ["p_data": "output"], ) - output_ch = p_data_ch.join(f_data_ch, remainder: true) + eset_ch = p_data_ch.join(f_data_ch, remainder: true) | map {id, p_data_state, f_data_state -> def newState = p_data_state + ["f_data": f_data_state["f_data"]] [id, newState] @@ -186,6 +176,36 @@ workflow run_wf { "eset": "output", ] ) + + report_channel = eset_ch + | toSortedList() + | map {ids_and_states -> + def states = ids_and_states.collect{it[1]} + def html_report = states[0].html_report + def ids = ids_and_states.collect{it[0]} + def esets = states.collect{it.eset} + ["report", ["esets": esets, "html_report": html_report, "original_ids": ids]] + } + | create_report.run( + fromState: [ + "eset": "esets", + "output_report": "html_report", + ], + toState: [ + "html_report": "output_report" + ] + ) + | flatMap {id, state -> + state.original_ids.collect{original_id -> + [original_id, ["html_report": state.html_report]] + } + } + + output_ch = eset_ch.join(report_channel) + | map {id, state_eset, state_report -> + def new_state = state_eset + ["html_report": state_report.html_report] + [id, new_state] + } | setState([ "star_output": "star_output", "fastq_output_r1": "fastq_output_r1", @@ -195,7 +215,8 @@ workflow run_wf { "star_qc_metrics": "star_qc_metrics", "eset": "eset", "f_data": "f_data", - "p_data": "p_data" + "p_data": "p_data", + "html_report": "html_report", ]) diff --git a/src/workflows/htrnaseq/test.nf b/src/workflows/htrnaseq/test.nf index 2f38249a..808f1bed 100644 --- a/src/workflows/htrnaseq/test.nf +++ b/src/workflows/htrnaseq/test.nf @@ -15,7 +15,7 @@ workflow test_wf { input_r1: resources_test_file.resolve("100k/SRR14730301/VH02001612_S9_R1_001.fastq"), input_r2: resources_test_file.resolve("100k/SRR14730301/VH02001612_S9_R2_001.fastq"), genomeDir: resources_test_file.resolve("genomeDir/gencode.v41.star.sparse"), - barcodesFasta: resources_test_file.resolve("360-wells.fasta"), + barcodesFasta: resources_test_file.resolve("360-wells-with-ids.fasta"), annotation: resources_test_file.resolve("genomeDir/gencode.v41.annotation.gtf.gz") ], [ @@ -23,7 +23,7 @@ workflow test_wf { input_r1: resources_test_file.resolve("100k/SRR14730302/VH02001614_S8_R1_001.fastq"), input_r2: resources_test_file.resolve("100k/SRR14730302/VH02001614_S8_R2_001.fastq"), genomeDir: resources_test_file.resolve("genomeDir/gencode.v41.star.sparse"), - barcodesFasta: resources_test_file.resolve("360-wells.fasta"), + barcodesFasta: resources_test_file.resolve("360-wells-with-ids.fasta"), annotation: resources_test_file.resolve("genomeDir/gencode.v41.annotation.gtf.gz") ] ]) diff --git a/src/workflows/parallel_map_wf/config.vsh.yaml b/src/workflows/parallel_map_wf/config.vsh.yaml index 9181020a..563ae1ce 100644 --- a/src/workflows/parallel_map_wf/config.vsh.yaml +++ b/src/workflows/parallel_map_wf/config.vsh.yaml @@ -4,7 +4,10 @@ description: | Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo. Input data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for one barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the - workflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.xx + workflow. Output is provided as mapped output per pool, i.e. one output is provided per pool. +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] argument_groups: - name: "Arguments" arguments: diff --git a/src/workflows/utils/groupWells/config.vsh.yaml b/src/workflows/utils/groupWells/config.vsh.yaml index fa05a2b8..4cb0db83 100644 --- a/src/workflows/utils/groupWells/config.vsh.yaml +++ b/src/workflows/utils/groupWells/config.vsh.yaml @@ -2,6 +2,9 @@ name: groupWells namespace: workflows/utils description: | N/A +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] argument_groups: - name: Inputs arguments: diff --git a/src/workflows/well_demultiplex/config.vsh.yaml b/src/workflows/well_demultiplex/config.vsh.yaml index 465f8e2c..2be85f86 100644 --- a/src/workflows/well_demultiplex/config.vsh.yaml +++ b/src/workflows/well_demultiplex/config.vsh.yaml @@ -1,6 +1,11 @@ name: well_demultiplex namespace: workflows description: Demultiplexing on well level +authors: + - __merge__: /src/base/authors/dries_schaumont.yaml + roles: [ maintainer ] + - __merge__: /src/base/authors/marijke_van_moerbeke.yaml + roles: [ contributor ] argument_groups: - name: Input arguments arguments: @@ -41,6 +46,9 @@ argument_groups: type: string description: The original pool / sample name direction: output + - name: "--well_id" + type: string + direction: output - name: "--barcode" type: string direction: output @@ -50,6 +58,10 @@ argument_groups: - name: "--pair_end" type: string direction: output + - name: "--n_wells" + type: integer + direction: output + description: The number of wells in the pool is well is a part of. resources: - type: nextflow_script path: main.nf @@ -60,6 +72,9 @@ test_resources: - type: nextflow_script path: test.nf entrypoint: test_wf + - type: nextflow_script + path: test.nf + entrypoint: test_wf2 dependencies: - name: cutadapt diff --git a/src/workflows/well_demultiplex/integration_test.sh b/src/workflows/well_demultiplex/integration_test.sh index 59080a53..005a3daf 100755 --- a/src/workflows/well_demultiplex/integration_test.sh +++ b/src/workflows/well_demultiplex/integration_test.sh @@ -18,4 +18,15 @@ nextflow \ -entry test_wf \ -resume \ -profile docker,local \ - --publish_dir output \ + --publish_dir output + + +nextflow \ + run . \ + -main-script src/workflows/well_demultiplex/test.nf \ + -config ./src/config/labels.config \ + -entry test_wf2 \ + -resume \ + -profile docker,local \ + --publish_dir output_2 \ + diff --git a/src/workflows/well_demultiplex/main.nf b/src/workflows/well_demultiplex/main.nf index 317535c0..619f6bb6 100644 --- a/src/workflows/well_demultiplex/main.nf +++ b/src/workflows/well_demultiplex/main.nf @@ -4,18 +4,73 @@ workflow run_wf { main: output_ch = input_ch + /* + Parse the fasta file containing the barcodes and do the following: + - The sequence headers must not contain any whitespaces + - The headers (Well IDs) must be unique + - The barcodes must be unique + - Store the number of barcodes in the state + - Add a barcode to well ID (header) mapping to the state, + in order to be able to retreive the well ID based on the FASTQ name after well demultiplexing + */ + | map {id, state -> + def n_wells = state.barcodesFasta.countFasta() as int + // The header is the full header, the id is the part header up to the first whitespace character + // We do not allow whitespace in the header of the fasta file, so assert this. + def fasta_entries = state.barcodesFasta.splitFasta( + record: ["id": true, "header": true, "seqString": true] + ) + assert fasta_entries.every{it.id == it.header}, \ + "The barcodes FASTA headers must not contain any whitespace!" + // Check if the fasta headers are unique + def fasta_ids = fasta_entries.collect{it.id} + assert fasta_ids.clone().unique() == fasta_ids, \ + "The barcodes FASTA entries must have a unique name!" + // Check if the sequences are unique + def fasta_sequences = fasta_entries.collect{it.seqString} + assert fasta_sequences.clone().unique() == fasta_sequences, \ + "The barcodes FASTA sequences must be unique!" + def well_id_matcher = /^([A-Za-z]+)0*([1-9]?[0-9]+)$/ + def entries_corrected_id = fasta_entries.collectEntries { it -> + def unformatted_id = it.header + def id_matched_to_format = unformatted_id =~ well_id_matcher + assert (id_matched_to_format && id_matched_to_format.getCount() == 1), \ + "The FASTA headers must match the coordinate system of a well plate (e.g. A01, B01, ... or AA1, AB1, ...). Found: ${unformatted_id}" + def id_letters = id_matched_to_format[0][1].toUpperCase() + def id_numbers = id_matched_to_format[0][2] + ["${id_letters}${id_numbers}", it.seqString] + } + def newState = state + [ + "n_wells": n_wells, + "well_id_barcode_mapping": entries_corrected_id, + ] + [id, newState] + } + /* + For each pool (i.e. event) in the channel, a list of R1 and R2 input + reads is provided which correspond to the lanes. If there are multiple lanes, + we can demultiplex into the wells for each lane in parallel. Therefore, cutadapt + must be started multiple times and we need an event per lane. The events are + created by taking the R1 and R2 pairs from the input lists. The index of the elements + in these lists are added to the ID in order to make them unique. + */ | flatMap {id, state -> - assert state.input_r1.size() == state.input_r2.size(), "Expected equal number of inputs for R1 and R2" + assert state.input_r1.size() == state.input_r2.size(), \ + "Expected equal number of inputs for R1 and R2" + // Store the number of lanes that were encountered here in order to + // group them together in an asynchronous manner later by providing + // the expected number of events to be grouped to groupTuple. + // see https://www.nextflow.io/docs/latest/reference/operator.html#grouptuple def n_lanes = state.input_r1.size() [state.input_r1, state.input_r2].transpose().withIndex().collect{ input_pair, index -> def single_input_r1 = input_pair[0] def single_input_r2 = input_pair[1] - def newState = state + ["input_r1": single_input_r1, - "input_r2": single_input_r2, - "pool": id, + def newState = state + ["input_r1": single_input_r1, + "input_r2": single_input_r2, + "pool": id, "lane_sorting": index, "n_lanes": n_lanes] - def newId = id + "_" + index + def newId = id + "_" + index [newId, newState] } } @@ -36,10 +91,12 @@ workflow run_wf { }, toState: { id, result, state -> def newState = [ - pool: state.pool, - n_lanes: state.n_lanes, - output: result.output, - lane_sorting: state.lane_sorting, + "pool": state.pool, + "n_lanes": state.n_lanes, + "output": result.output, + "lane_sorting": state.lane_sorting, + "n_wells": state.n_wells, + "well_id_barcode_mapping": state.well_id_barcode_mapping, ] return newState } @@ -48,58 +105,129 @@ workflow run_wf { | flatMap{ id, state -> def pool = state.pool state.output.collect{ p -> - def barcode = (p =~ /.*\\/([ACTG]*|unknown)_R?.*/)[0][1] - def pair_end = (p =~ /.*_(R[12])_.*/)[0][1] - def lane = (p =~ /.*_(L\d+).*/) ? (p =~ /.*_(L\d+).*/)[0][1] : "NA" - def new_id = pool + "__" + barcode - def group_key = groupKey(new_id, state.n_lanes * 2) + def well_id_matcher = p =~ /.*\\/([A-Za-z0-9]*|unknown)_R?.*/ + assert well_id_matcher, \ + "Could not find Well ID in the name of FASTQ file ($p) output from cutadapt." + def well_id = well_id_matcher[0][1] + // Note: set the barcode to 'null' for reads that were put into 'unknown' + def barcode = (well_id != "unknown") ? state.well_id_barcode_mapping[well_id].replaceAll("[^ACGTacgt]", "") : null + assert (well_id == "unknown") || (barcode != null), \ + "After demultiplexing, no Well ID could be retreived for barcode ${barcode}." + def pair_end_matcher = p =~ /.*_(R[12])_.*/ + assert pair_end_matcher, \ + "Could not find read orientation information in the name of the FASTQ file ($p) output from cutadapt." + def pair_end = pair_end_matcher[0][1] + def lane_matcher = p =~ /.*_(L\d+).*/ + def lane = lane_matcher ? lane_matcher[0][1] : "NA" + def new_id = pool + "__" + well_id [ - group_key, + new_id, [ - pool: pool, - barcode: barcode, - output: p, - lane: lane, - pair_end: pair_end, - lane_sorting: state.lane_sorting, - _meta: [ join_id: pool ] + "pool": pool, + "barcode": barcode, + "well_id": well_id, + "output": p, + "lane": lane, + "n_wells": state.n_wells, + "pair_end": pair_end, + "n_lanes": state.n_lanes, + "lane_sorting": state.lane_sorting, + "_meta": [ "join_id": pool ] ] ] } } - // Group the outputs from across lanes - | groupTuple(sort: "hash") + /* + At this point, the events are provided on the smallest possible level, + as each event represents the reads for a certain orientation from a + particular lane and a single well. Here, we join these events back together + on well level, gathering FASTQS across the lanes and read orientations. + In order to make this joining as efficient as possible, the number of + lanes which are expected to be gathered were stored in the state earlier. + This way, the processing of a well can continue as as soon as all of + the lanes have been gathered. The number of lanes times 2 (forward + and reverse orientation) represents the total number of FASTQS (events) + to be included for a certain well. + */ + | map {id, state -> + def group_key = groupKey(id, state.n_lanes * 2) + return [group_key, state] + } + | groupTuple(sort: {a, b -> + // Make sure that the grouped states are in order, + // meaning forward and reverse FASTQs are paired and the FASTQ + // for the forward reads comes before the reverse reads FASTQ. + if (a.lane_sorting == b.lane_sorting) { + return a.pair_end <=> b.pair_end + } + return a.lane_sorting <=> b.lane_sorting + }) | map {_, states -> - def r1_output = states.findAll{ it.pair_end == "R1" }.collect{it.output} - def r2_output = states.findAll{ it.pair_end == "R2" }.collect{it.output} - def lane_sorting_r1 = states.findAll{ it.pair_end == "R1" }.collect{it.lane_sorting} - def lane_sorting_r2 = states.findAll{ it.pair_end == "R2" }.collect{it.lane_sorting} + // The states are in one long flat list, group them into pairs + // This assumes that the FASTQ files are already in order! + // (See the 'sort' argument of groupTuple above) + def output_pairs = states.collate(2) - // At this point, the lane_sorting hold the positios the items in r1_output and r2_output - // should become in a new list. - def r1_output_sorted = new ArrayList(r1_output.size()) - def r2_output_sorted = new ArrayList(r2_output.size()) - - lane_sorting_r1.eachWithIndex { pos, index -> - r1_output_sorted[pos] = r1_output[index] - } - - lane_sorting_r2.eachWithIndex { pos, index -> - r2_output_sorted[pos] = r2_output[index] + // Sanity check the state + output_pairs.each{ pair -> + assert pair.size() == 2, \ + "State error: expected FASTQ pairs as output from cutadapt, " + + "found output state: $pair" + def (first, second) = pair + def should_be_the_same = [ + "barcode", + "well_id", + "lane", + "pool", + "lane_sorting", + ] + should_be_the_same.each { attr_to_check -> + first_attr = first.get(attr_to_check) + second_attr = second.get(attr_to_check) + assert first_attr == second_attr, \ + "State error: expected FASTQ pairs from cutadapt to have " + + "the same detected ${attr_to_check}. Found: " + + "$first_attr and $second_attr" + } + // Forward and reverse reads should be designated + // by 'R1' and 'R2', and sorted lexographically. + assert first.pair_end == "R1", \ + "State error: expected first item from FASTQ pair to have " + + "orientation 'R1', found $first.pair_end" + assert second.pair_end == "R2", \ + "State error: expected second item from FASTQ pair to have " + + "orientation 'R2', found $second.pair_end" } + def r1_output = output_pairs.collect{it[0].output} + def r2_output = output_pairs.collect{it[1].output} assert r1_output.size() == r2_output.size() + + /* The lane sorting represents the order of the FASTQ files + as provided by the input. The order of the FASTQ files should + remain the same in the well output. This is because the result of STAR + can differ based on the order of the reads in the FASTQ file. + Even when the same reads are provided, the order of them matters. + */ + def lane_sorting = output_pairs.it[0].lane_sorting + def sorting_is_monotonically_increasing = lane_sorting.withIndex().every { i, idx -> + idx == 0 || lane_sorting[idx - 1] <= i + } + assert sorting_is_monotonically_increasing, \ + "State error: expected the order of the FASTQ files after grouping " + + "the cutadapt output to be the same as the order in the input. " + + "Found sorting $lane_sorting, R1 output: $r1_output, R2 output: $r2_output." + // Here we pick the state from the first item in the list of states // and overwrite the keys which are different across states - // TODO: we can assert that these keys are the same def first_state = states[0] - def new_id = first_state.pool + "__" + first_state.barcode - def new_state = first_state + ["output_r1": r1_output_sorted, "output_r2": r2_output_sorted] + def new_id = first_state.pool + "__" + first_state.well_id + def new_state = first_state + ["output_r1": r1_output, "output_r2": r2_output] [new_id, new_state] } // TODO: Expand this into matching a whitelist/blacklist of barcodes // ... and turn into separate component - | filter{ id, state -> state.barcode != "unknown" } + | filter{ id, state -> state.well_id != "unknown" } | concat_text.run( directives: [label: ["lowmem", "lowcpu"]], key: "concat_txt_r1", @@ -132,7 +260,7 @@ workflow run_wf { return newState } ) - | setState(["pool", "barcode", "lane", "_meta", "output_r1", "output_r2"]) + | setState(["pool", "well_id", "n_wells", "barcode", "lane", "_meta", "output_r1", "output_r2"]) emit: output_ch diff --git a/src/workflows/well_demultiplex/test.nf b/src/workflows/well_demultiplex/test.nf index 03d60a45..cd2c9656 100644 --- a/src/workflows/well_demultiplex/test.nf +++ b/src/workflows/well_demultiplex/test.nf @@ -9,13 +9,13 @@ workflow test_wf { id: "SRR14730301", input_r1: resources_test_file.resolve("100k/SRR14730301/VH02001612_S9_R1_001.fastq"), input_r2: resources_test_file.resolve("100k/SRR14730301/VH02001612_S9_R2_001.fastq"), - barcodesFasta: resources_test_file.resolve("2-wells.fasta"), + barcodesFasta: resources_test_file.resolve("2-wells-with-ids.fasta"), ], [ id: "SRR14730302", input_r1: resources_test_file.resolve("100k/SRR14730302/VH02001614_S8_R1_001.fastq"), input_r2: resources_test_file.resolve("100k/SRR14730302/VH02001614_S8_R2_001.fastq"), - barcodesFasta: resources_test_file.resolve("2-wells.fasta"), + barcodesFasta: resources_test_file.resolve("2-wells-with-ids.fasta"), ], ]) | map { state -> [ state.id, state ] } @@ -40,3 +40,43 @@ workflow test_wf { } } + +workflow test_wf2 { + resources_test_file = file(params.resources_test) + output_ch = Channel.fromList([ + [ + id: "SRR14730301", + input_r1: + [ + resources_test_file.resolve("100k/SRR14730301/VH02001612_S9_R1_001.fastq"), + resources_test_file.resolve("100k/SRR14730302/VH02001614_S8_R1_001.fastq"), + ], + input_r2: + [ + resources_test_file.resolve("100k/SRR14730301/VH02001612_S9_R2_001.fastq"), + resources_test_file.resolve("100k/SRR14730302/VH02001614_S8_R2_001.fastq"), + ], + barcodesFasta: resources_test_file.resolve("2-wells-with-ids.fasta"), + ], + ]) + | map { state -> [ state.id, state ] } + | well_demultiplex.run( + fromState: { id, state -> + [ + input_r1: state.input_r1, + input_r2: state.input_r2, + barcodesFasta: state.barcodesFasta, + ] + }, + toState: { id, output, state -> + output } + ) + | view { output -> + assert output.size() == 2 : "outputs should contain two elements; [id, file]" + "Output: $output" + } + | toSortedList() + | view { output -> + assert output.size() == 2 : "1 samples, and two barcodes" + } +} diff --git a/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml index ed9ca980..7cbe26aa 100644 --- a/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/.config.vsh.yaml @@ -740,9 +740,9 @@ build_info: output: "target/nextflow/cutadapt" executable: "target/nextflow/cutadapt/main.nf" viash_version: "0.9.0" - git_commit: "06005a79b49911f1197ccfddf066fc566d5b1def" - git_remote: "https://x-access-token:ghs_s2VchCFPnGFkJ2bOWXBcoeam5dPxgi4UR0W2@github.com/viash-hub/biobox" - git_tag: "v0.2.0-22-g06005a7" + git_commit: "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b" + git_remote: "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox" + git_tag: "v0.2.0-27-g952ff08" package_config: name: "biobox" version: "main" diff --git a/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf index 1dc4d2ee..a7f02e16 100644 --- a/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/main.nf @@ -3619,9 +3619,9 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/cutadapt", "viash_version" : "0.9.0", - "git_commit" : "06005a79b49911f1197ccfddf066fc566d5b1def", - "git_remote" : "https://x-access-token:ghs_s2VchCFPnGFkJ2bOWXBcoeam5dPxgi4UR0W2@github.com/viash-hub/biobox", - "git_tag" : "v0.2.0-22-g06005a7" + "git_commit" : "952ff0843093b538cbfd6fefdecf2e7a0bc9e70b", + "git_remote" : "https://x-access-token:ghs_EwAUAMYJ0K4VBHlAEMs4ZP2OyQYqJM0PSfEO@github.com/viash-hub/biobox", + "git_tag" : "v0.2.0-27-g952ff08" }, "package_config" : { "name" : "biobox", diff --git a/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json index 09c66f90..2b7fb1b4 100644 --- a/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json +++ b/target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt/nextflow_schema.json @@ -180,7 +180,7 @@ "description": "Type: `boolean_true`, default: `false`. Treat adapters given with -a/-A etc", "help_text": "Type: `boolean_true`, default: `false`. Treat adapters given with -a/-A etc. as pairs. Either both\nor none are removed from each read pair.\n" , - "default": "False" + "default":false } @@ -203,7 +203,7 @@ "description": "Type: `boolean_true`, default: `false`. Read and/or write interleaved paired-end reads", "help_text": "Type: `boolean_true`, default: `false`. Read and/or write interleaved paired-end reads.\n" , - "default": "False" + "default":false } @@ -254,7 +254,7 @@ "description": "Type: `boolean_true`, default: `false`. Allow only mismatches in alignments", "help_text": "Type: `boolean_true`, default: `false`. Allow only mismatches in alignments.\n" , - "default": "False" + "default":false } @@ -285,7 +285,7 @@ "description": "Type: `boolean_true`, default: `false`. Interpret IUPAC wildcards in reads", "help_text": "Type: `boolean_true`, default: `false`. Interpret IUPAC wildcards in reads.\n" , - "default": "False" + "default":false } @@ -296,7 +296,7 @@ "description": "Type: `boolean_true`, default: `false`. Do not interpret IUPAC wildcards in adapters", "help_text": "Type: `boolean_true`, default: `false`. Do not interpret IUPAC wildcards in adapters.\n" , - "default": "False" + "default":false } @@ -319,7 +319,7 @@ "description": "Type: `boolean_true`, default: `false`. Check both the read and its reverse complement for adapter\nmatches", "help_text": "Type: `boolean_true`, default: `false`. Check both the read and its reverse complement for adapter\nmatches. If match is on reverse-complemented version,\noutput that one.\n" , - "default": "False" + "default":false } @@ -422,7 +422,7 @@ "description": "Type: `boolean_true`, default: `false`. Trim poly-A tails", "help_text": "Type: `boolean_true`, default: `false`. Trim poly-A tails" , - "default": "False" + "default":false } @@ -443,7 +443,7 @@ "description": "Type: `boolean_true`, default: `false`. Trim N\u0027s on ends of reads", "help_text": "Type: `boolean_true`, default: `false`. Trim N\u0027s on ends of reads." , - "default": "False" + "default":false } @@ -504,7 +504,7 @@ "description": "Type: `boolean_true`, default: `false`. Change negative quality values to zero", "help_text": "Type: `boolean_true`, default: `false`. Change negative quality values to zero." , - "default": "False" + "default":false } @@ -575,7 +575,7 @@ "description": "Type: `boolean_true`, default: `false`. Discard reads that contain an adapter", "help_text": "Type: `boolean_true`, default: `false`. Discard reads that contain an adapter. Use also -O to\navoid discarding too many randomly matching reads.\n" , - "default": "False" + "default":false } @@ -586,7 +586,7 @@ "description": "Type: `boolean_true`, default: `false`. Discard reads that do not contain an adapter", "help_text": "Type: `boolean_true`, default: `false`. Discard reads that do not contain an adapter.\n" , - "default": "False" + "default":false } @@ -597,7 +597,7 @@ "description": "Type: `boolean_true`, default: `false`. Discard reads that did not pass CASAVA filtering (header\nhas :Y:)", "help_text": "Type: `boolean_true`, default: `false`. Discard reads that did not pass CASAVA filtering (header\nhas :Y:).\n" , - "default": "False" + "default":false } @@ -630,7 +630,7 @@ "description": "Type: `boolean_true`, default: `false`. Write report in JSON format to this file", "help_text": "Type: `boolean_true`, default: `false`. Write report in JSON format to this file.\n" , - "default": "False" + "default":false } @@ -641,7 +641,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.output_*.fast[a,q]`, example: `fastq/*_001.fast[a,q]`, multiple_sep: `\";\"`. Glob pattern for matching the expected output files", "help_text": "Type: List of `file`, required, default: `$id.$key.output_*.fast[a,q]`, example: `fastq/*_001.fast[a,q]`, multiple_sep: `\";\"`. Glob pattern for matching the expected output files.\nShould include `$output_dir`.\n" , - "default": "$id.$key.output_*.fast[a,q]" + "default":"$id.$key.output_*.fast[a,q]" } @@ -652,7 +652,7 @@ "description": "Type: `boolean_true`, default: `false`. Output FASTA to standard output even on FASTQ input", "help_text": "Type: `boolean_true`, default: `false`. Output FASTA to standard output even on FASTQ input.\n" , - "default": "False" + "default":false } @@ -663,7 +663,7 @@ "description": "Type: `boolean_true`, default: `false`. Write information about each read and its adapter matches\ninto info", "help_text": "Type: `boolean_true`, default: `false`. Write information about each read and its adapter matches\ninto info.txt in the output directory.\nSee the documentation for the file format.\n" , - "default": "False" + "default":false } @@ -684,7 +684,7 @@ "description": "Type: `boolean_true`, default: `false`. Print debug information", "help_text": "Type: `boolean_true`, default: `false`. Print debug information" , - "default": "False" + "default":false } diff --git a/target/executable/eset/create_eset/.config.vsh.yaml b/target/executable/eset/create_eset/.config.vsh.yaml index 26fbe30f..68f8c186 100644 --- a/target/executable/eset/create_eset/.config.vsh.yaml +++ b/target/executable/eset/create_eset/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "create_eset" namespace: "eset" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "author" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -194,8 +220,8 @@ build_info: output: "target/executable/eset/create_eset" executable: "target/executable/eset/create_eset/create_eset" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/eset/create_eset/create_eset b/target/executable/eset/create_eset/create_eset index 6ba70c39..92cb796a 100755 --- a/target/executable/eset/create_eset/create_eset +++ b/target/executable/eset/create_eset/create_eset @@ -10,6 +10,10 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (maintainer) +# * Marijke Van Moerbeke (author) set -e @@ -482,10 +486,11 @@ RUN Rscript -e 'if (!requireNamespace("remotes", quietly = TRUE)) install.packag remotes::install_url("https://cran.r-project.org/src/contrib/Archive/Seurat/Seurat_4.4.0.tar.gz", repos=BiocManager::repositories(), dependencies=TRUE, upgrade_dependencies=FALSE)\ ' +LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component eset create_eset" -LABEL org.opencontainers.image.created="2024-11-05T15:39:43Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/eset/create_eset/nextflow_labels.config b/target/executable/eset/create_eset/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/eset/create_eset/nextflow_labels.config +++ b/target/executable/eset/create_eset/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/eset/create_fdata/.config.vsh.yaml b/target/executable/eset/create_fdata/.config.vsh.yaml index d2298f4e..a464b79a 100644 --- a/target/executable/eset/create_fdata/.config.vsh.yaml +++ b/target/executable/eset/create_fdata/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "create_fdata" namespace: "eset" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -151,8 +177,8 @@ build_info: output: "target/executable/eset/create_fdata" executable: "target/executable/eset/create_fdata/create_fdata" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/eset/create_fdata/create_fdata b/target/executable/eset/create_fdata/create_fdata index 2c076b66..2ad25aac 100755 --- a/target/executable/eset/create_fdata/create_fdata +++ b/target/executable/eset/create_fdata/create_fdata @@ -10,6 +10,10 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (maintainer) +# * Marijke Van Moerbeke (contributor) set -e @@ -472,10 +476,11 @@ RUN apt-get update && \ RUN pip install --upgrade pip && \ pip install --upgrade --no-cache-dir "pandas" +LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component eset create_fdata" -LABEL org.opencontainers.image.created="2024-11-05T15:39:42Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:24Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/eset/create_fdata/nextflow_labels.config b/target/executable/eset/create_fdata/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/eset/create_fdata/nextflow_labels.config +++ b/target/executable/eset/create_fdata/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/eset/create_pdata/.config.vsh.yaml b/target/executable/eset/create_pdata/.config.vsh.yaml index 1025c55e..b8394101 100644 --- a/target/executable/eset/create_pdata/.config.vsh.yaml +++ b/target/executable/eset/create_pdata/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "create_pdata" namespace: "eset" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -165,8 +191,8 @@ build_info: output: "target/executable/eset/create_pdata" executable: "target/executable/eset/create_pdata/create_pdata" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/eset/create_pdata/create_pdata b/target/executable/eset/create_pdata/create_pdata index a88f8505..a2192ba8 100755 --- a/target/executable/eset/create_pdata/create_pdata +++ b/target/executable/eset/create_pdata/create_pdata @@ -10,6 +10,10 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (maintainer) +# * Marijke Van Moerbeke (contributor) set -e @@ -482,10 +486,11 @@ RUN apt-get update && \ RUN pip install --upgrade pip && \ pip install --upgrade --no-cache-dir "pandas" +LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component eset create_pdata" -LABEL org.opencontainers.image.created="2024-11-05T15:39:43Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER @@ -1104,7 +1109,7 @@ def main(par): logger.info("Reads per gene and chromosome table contains information for the following barcodes: %s", ", ".join(reads_and_genes_per_chr_stats.index)) logger.info("Filtering mapping statistics file columns.") - cols_to_keep = ("NumberOfMTReads", "pctMT", "NumberOfERCCReads", + cols_to_keep = ("WellID", "NumberOfMTReads", "pctMT", "NumberOfERCCReads", "pctERCC", "NumberOfChromReads", "pctChrom") try: reads_and_genes_per_chr_stats = reads_and_genes_per_chr_stats.loc[:,cols_to_keep] diff --git a/target/executable/eset/create_pdata/nextflow_labels.config b/target/executable/eset/create_pdata/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/eset/create_pdata/nextflow_labels.config +++ b/target/executable/eset/create_pdata/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml b/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml index 8967ce4b..68fc24ad 100644 --- a/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml +++ b/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml @@ -1,6 +1,21 @@ name: "check_eset" namespace: "integration_test_components/htrnaseq" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Inputs" arguments: @@ -133,8 +148,8 @@ build_info: output: "target/executable/integration_test_components/htrnaseq/check_eset" executable: "target/executable/integration_test_components/htrnaseq/check_eset/check_eset" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/integration_test_components/htrnaseq/check_eset/check_eset b/target/executable/integration_test_components/htrnaseq/check_eset/check_eset index 185f19b8..0e483aca 100755 --- a/target/executable/integration_test_components/htrnaseq/check_eset/check_eset +++ b/target/executable/integration_test_components/htrnaseq/check_eset/check_eset @@ -10,6 +10,9 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (author, maintainer) set -e @@ -465,10 +468,11 @@ RUN Rscript -e 'if (!requireNamespace("remotes", quietly = TRUE)) install.packag Rscript -e 'if (!requireNamespace("Biobase", quietly = TRUE)) BiocManager::install("Biobase")' && \ Rscript -e 'remotes::install_cran(c("bit64"), repos = "https://cran.rstudio.com")' +LABEL org.opencontainers.image.authors="Dries Schaumont" LABEL org.opencontainers.image.description="Companion container for running component integration_test_components/htrnaseq check_eset" -LABEL org.opencontainers.image.created="2024-11-05T15:39:42Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:24Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER @@ -1197,6 +1201,7 @@ stopifnot(identical(sampleNames(sample_1_result), expected_sample_names)) expected_var_labels <- c( "WellBC", + "WellID", "NumberOfMTReads", "pctMT", "NumberOfERCCReads", diff --git a/target/executable/integration_test_components/htrnaseq/check_eset/nextflow_labels.config b/target/executable/integration_test_components/htrnaseq/check_eset/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/integration_test_components/htrnaseq/check_eset/nextflow_labels.config +++ b/target/executable/integration_test_components/htrnaseq/check_eset/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/parallel_map/.config.vsh.yaml b/target/executable/parallel_map/.config.vsh.yaml index 8652642a..137c150d 100644 --- a/target/executable/parallel_map/.config.vsh.yaml +++ b/target/executable/parallel_map/.config.vsh.yaml @@ -1,5 +1,32 @@ name: "parallel_map" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Toni Verbeiren" + roles: + - "author" + - "maintainer" + info: + role: "Core Team Member" + links: + github: "tverbeiren" + linkedin: "verbeiren" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist and CEO" argument_groups: - name: "Input arguments" arguments: @@ -237,8 +264,8 @@ build_info: output: "target/executable/parallel_map" executable: "target/executable/parallel_map/parallel_map" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/parallel_map/nextflow_labels.config b/target/executable/parallel_map/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/parallel_map/nextflow_labels.config +++ b/target/executable/parallel_map/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/parallel_map/parallel_map b/target/executable/parallel_map/parallel_map index efef30c2..468d6e29 100755 --- a/target/executable/parallel_map/parallel_map +++ b/target/executable/parallel_map/parallel_map @@ -10,6 +10,10 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (maintainer) +# * Toni Verbeiren (author, maintainer) set -e @@ -511,10 +515,11 @@ ENV STAR_TARGET="/app/star-$STAR_V.tar.gz" ENV STAR_INSTALL_DIR="/app/STAR-$STAR_V" ENV STAR_BINARY=STAR COPY STAR /usr/local/bin/$STAR_BINARY +LABEL org.opencontainers.image.authors="Dries Schaumont, Toni Verbeiren" LABEL org.opencontainers.image.description="Companion container for running component parallel_map" -LABEL org.opencontainers.image.created="2024-11-05T15:39:41Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:23Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/report/create_report/.config.vsh.yaml b/target/executable/report/create_report/.config.vsh.yaml new file mode 100644 index 00000000..089090ac --- /dev/null +++ b/target/executable/report/create_report/.config.vsh.yaml @@ -0,0 +1,235 @@ +name: "create_report" +namespace: "report" +version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "author" + - "maintainer" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" +argument_groups: +- name: "Arguments" + arguments: + - type: "file" + name: "--eset" + info: null + must_exist: true + create_parent: true + required: true + direction: "input" + multiple: true + multiple_sep: ";" + - type: "file" + name: "--output_report" + info: null + example: + - "report.html" + must_exist: true + create_parent: true + required: true + direction: "output" + multiple: false + multiple_sep: ";" +resources: +- type: "r_script" + path: "script.R" + is_executable: true +- type: "r_script" + path: "template.Rmd" + is_executable: true +- type: "r_script" + path: "plateLayouts.R" + is_executable: true +- type: "file" + path: "OutputSTARsolo.png" +- type: "file" + path: "nextflow_labels.config" + dest: "nextflow_labels.config" +description: "Create a basic QC report in HTML format based on a number of esets.\n" +test_resources: +- type: "r_script" + path: "test.R" + is_executable: true +- type: "file" + path: "test_data" +info: null +status: "enabled" +requirements: + commands: + - "ps" +license: "MIT" +links: + repository: "https://github.com/viash-hub/htrnaseq" +runners: +- type: "executable" + id: "executable" + docker_setup_strategy: "ifneedbepullelsecachedbuild" +- type: "nextflow" + id: "nextflow" + directives: + tag: "$id" + auto: + simplifyInput: true + simplifyOutput: false + transcript: false + publish: false + config: + labels: + mem1gb: "memory = 1000000000.B" + mem2gb: "memory = 2000000000.B" + mem5gb: "memory = 5000000000.B" + mem10gb: "memory = 10000000000.B" + mem20gb: "memory = 20000000000.B" + mem50gb: "memory = 50000000000.B" + mem100gb: "memory = 100000000000.B" + mem200gb: "memory = 200000000000.B" + mem500gb: "memory = 500000000000.B" + mem1tb: "memory = 1000000000000.B" + mem2tb: "memory = 2000000000000.B" + mem5tb: "memory = 5000000000000.B" + mem10tb: "memory = 10000000000000.B" + mem20tb: "memory = 20000000000000.B" + mem50tb: "memory = 50000000000000.B" + mem100tb: "memory = 100000000000000.B" + mem200tb: "memory = 200000000000000.B" + mem500tb: "memory = 500000000000000.B" + mem1gib: "memory = 1073741824.B" + mem2gib: "memory = 2147483648.B" + mem4gib: "memory = 4294967296.B" + mem8gib: "memory = 8589934592.B" + mem16gib: "memory = 17179869184.B" + mem32gib: "memory = 34359738368.B" + mem64gib: "memory = 68719476736.B" + mem128gib: "memory = 137438953472.B" + mem256gib: "memory = 274877906944.B" + mem512gib: "memory = 549755813888.B" + mem1tib: "memory = 1099511627776.B" + mem2tib: "memory = 2199023255552.B" + mem4tib: "memory = 4398046511104.B" + mem8tib: "memory = 8796093022208.B" + mem16tib: "memory = 17592186044416.B" + mem32tib: "memory = 35184372088832.B" + mem64tib: "memory = 70368744177664.B" + mem128tib: "memory = 140737488355328.B" + mem256tib: "memory = 281474976710656.B" + mem512tib: "memory = 562949953421312.B" + cpu1: "cpus = 1" + cpu2: "cpus = 2" + cpu5: "cpus = 5" + cpu10: "cpus = 10" + cpu20: "cpus = 20" + cpu50: "cpus = 50" + cpu100: "cpus = 100" + cpu200: "cpus = 200" + cpu500: "cpus = 500" + cpu1000: "cpus = 1000" + script: + - "includeConfig(\"nextflow_labels.config\")" + debug: false + container: "docker" +engines: +- type: "docker" + id: "docker" + image: "rocker/r2u:24.04" + target_registry: "images.viash-hub.com" + target_tag: "main" + namespace_separator: "/" + setup: + - type: "apt" + packages: + - "procps" + - "pandoc" + interactive: false + - type: "r" + cran: + - "ggplot2" + - "knitr" + - "gridExtra" + - "RColorBrewer" + - "processx" + - "whisker" + - "rmarkdown" + - "bookdown" + - "data.table" + - "platetools" + - "htmltools" + - "DT" + - "logger" + - "bit64" + bioc: + - "Biobase" + - "ComplexHeatmap" + script: + - "install.packages(\"oaStyle\", repos = c(rdepot = \"https://repos.openanalytics.eu/repo/public\"\ + , getOption(\"repos\")))" + bioc_force_install: false + test_setup: + - type: "r" + packages: + - "testthat" + - "R.utils" + bioc_force_install: false + entrypoint: [] + cmd: null +- type: "native" + id: "native" +build_info: + config: "src/report/config.vsh.yaml" + runner: "executable" + engine: "docker|native" + output: "target/executable/report/create_report" + executable: "target/executable/report/create_report/create_report" + viash_version: "0.9.0" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" +package_config: + name: "htrnaseq" + version: "main" + description: "High-throughput pipeline [WIP]\n" + info: + test_resources: + - path: "gs://viash-hub-test-data/htrnaseq/v1/" + dest: "resources_test" + viash_version: "0.9.0" + source: "src" + target: "target" + config_mods: + - ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].config.script\ + \ := 'includeConfig(\"nextflow_labels.config\")'\n.resources += {path: '/src/config/labels.config',\ + \ dest: 'nextflow_labels.config'}\n" + - ".engines += { type: \"native\" }" + - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" + - ".engines[.type == 'docker'].target_tag := 'main'" + keywords: + - "bioinformatics" + - "sequence" + - "high-throughput" + - "mapping" + - "counting" + - "pipeline" + license: "MIT" + organization: "vsh" + links: + repository: "https://github.com/viash-hub/htrnaseq" + issue_tracker: "https://github.com/viash-hub/htrnaseq/issues" diff --git a/target/executable/report/create_report/OutputSTARsolo.png b/target/executable/report/create_report/OutputSTARsolo.png new file mode 100644 index 00000000..cb77d8e0 Binary files /dev/null and b/target/executable/report/create_report/OutputSTARsolo.png differ diff --git a/target/executable/report/create_report/create_report b/target/executable/report/create_report/create_report new file mode 100755 index 00000000..e0835aad --- /dev/null +++ b/target/executable/report/create_report/create_report @@ -0,0 +1,1162 @@ +#!/usr/bin/env bash + +# create_report main +# +# This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +# work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +# Intuitive. +# +# The component may contain files which fall under a different license. The +# authors of this component should specify the license in the header of such +# files, or include a separate license file detailing the licenses of all included +# files. +# +# Component authors: +# * Dries Schaumont (maintainer) +# * Marijke Van Moerbeke (author, maintainer) + +set -e + +if [ -z "$VIASH_TEMP" ]; then + VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMPDIR} + VIASH_TEMP=${VIASH_TEMP:-$VIASH_TEMPDIR} + VIASH_TEMP=${VIASH_TEMP:-$VIASH_TMP} + VIASH_TEMP=${VIASH_TEMP:-$TMPDIR} + VIASH_TEMP=${VIASH_TEMP:-$TMP} + VIASH_TEMP=${VIASH_TEMP:-$TEMPDIR} + VIASH_TEMP=${VIASH_TEMP:-$TEMP} + VIASH_TEMP=${VIASH_TEMP:-/tmp} +fi + +# define helper functions +# ViashQuote: put quotes around non flag values +# $1 : unquoted string +# return : possibly quoted string +# examples: +# ViashQuote --foo # returns --foo +# ViashQuote bar # returns 'bar' +# Viashquote --foo=bar # returns --foo='bar' +function ViashQuote { + if [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+=.+$ ]]; then + echo "$1" | sed "s#=\(.*\)#='\1'#" + elif [[ "$1" =~ ^-+[a-zA-Z0-9_\-]+$ ]]; then + echo "$1" + else + echo "'$1'" + fi +} +# ViashRemoveFlags: Remove leading flag +# $1 : string with a possible leading flag +# return : string without possible leading flag +# examples: +# ViashRemoveFlags --foo=bar # returns bar +function ViashRemoveFlags { + echo "$1" | sed 's/^--*[a-zA-Z0-9_\-]*=//' +} +# ViashSourceDir: return the path of a bash file, following symlinks +# usage : ViashSourceDir ${BASH_SOURCE[0]} +# $1 : Should always be set to ${BASH_SOURCE[0]} +# returns : The absolute path of the bash file +function ViashSourceDir { + local source="$1" + while [ -h "$source" ]; do + local dir="$( cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd )" + source="$(readlink "$source")" + [[ $source != /* ]] && source="$dir/$source" + done + cd -P "$( dirname "$source" )" >/dev/null 2>&1 && pwd +} +# ViashFindTargetDir: return the path of the '.build.yaml' file, following symlinks +# usage : ViashFindTargetDir 'ScriptPath' +# $1 : The location from where to start the upward search +# returns : The absolute path of the '.build.yaml' file +function ViashFindTargetDir { + local source="$1" + while [[ "$source" != "" && ! -e "$source/.build.yaml" ]]; do + source=${source%/*} + done + echo $source +} +# see https://en.wikipedia.org/wiki/Syslog#Severity_level +VIASH_LOGCODE_EMERGENCY=0 +VIASH_LOGCODE_ALERT=1 +VIASH_LOGCODE_CRITICAL=2 +VIASH_LOGCODE_ERROR=3 +VIASH_LOGCODE_WARNING=4 +VIASH_LOGCODE_NOTICE=5 +VIASH_LOGCODE_INFO=6 +VIASH_LOGCODE_DEBUG=7 +VIASH_VERBOSITY=$VIASH_LOGCODE_NOTICE + +# ViashLog: Log events depending on the verbosity level +# usage: ViashLog 1 alert Oh no something went wrong! +# $1: required verbosity level +# $2: display tag +# $3+: messages to display +# stdout: Your input, prepended by '[$2] '. +function ViashLog { + local required_level="$1" + local display_tag="$2" + shift 2 + if [ $VIASH_VERBOSITY -ge $required_level ]; then + >&2 echo "[$display_tag]" "$@" + fi +} + +# ViashEmergency: log events when the system is unstable +# usage: ViashEmergency Oh no something went wrong. +# stdout: Your input, prepended by '[emergency] '. +function ViashEmergency { + ViashLog $VIASH_LOGCODE_EMERGENCY emergency "$@" +} + +# ViashAlert: log events when actions must be taken immediately (e.g. corrupted system database) +# usage: ViashAlert Oh no something went wrong. +# stdout: Your input, prepended by '[alert] '. +function ViashAlert { + ViashLog $VIASH_LOGCODE_ALERT alert "$@" +} + +# ViashCritical: log events when a critical condition occurs +# usage: ViashCritical Oh no something went wrong. +# stdout: Your input, prepended by '[critical] '. +function ViashCritical { + ViashLog $VIASH_LOGCODE_CRITICAL critical "$@" +} + +# ViashError: log events when an error condition occurs +# usage: ViashError Oh no something went wrong. +# stdout: Your input, prepended by '[error] '. +function ViashError { + ViashLog $VIASH_LOGCODE_ERROR error "$@" +} + +# ViashWarning: log potentially abnormal events +# usage: ViashWarning Something may have gone wrong. +# stdout: Your input, prepended by '[warning] '. +function ViashWarning { + ViashLog $VIASH_LOGCODE_WARNING warning "$@" +} + +# ViashNotice: log significant but normal events +# usage: ViashNotice This just happened. +# stdout: Your input, prepended by '[notice] '. +function ViashNotice { + ViashLog $VIASH_LOGCODE_NOTICE notice "$@" +} + +# ViashInfo: log normal events +# usage: ViashInfo This just happened. +# stdout: Your input, prepended by '[info] '. +function ViashInfo { + ViashLog $VIASH_LOGCODE_INFO info "$@" +} + +# ViashDebug: log all events, for debugging purposes +# usage: ViashDebug This just happened. +# stdout: Your input, prepended by '[debug] '. +function ViashDebug { + ViashLog $VIASH_LOGCODE_DEBUG debug "$@" +} + +# find source folder of this component +VIASH_META_RESOURCES_DIR=`ViashSourceDir ${BASH_SOURCE[0]}` + +# find the root of the built components & dependencies +VIASH_TARGET_DIR=`ViashFindTargetDir $VIASH_META_RESOURCES_DIR` + +# define meta fields +VIASH_META_NAME="create_report" +VIASH_META_FUNCTIONALITY_NAME="create_report" +VIASH_META_EXECUTABLE="$VIASH_META_RESOURCES_DIR/$VIASH_META_NAME" +VIASH_META_CONFIG="$VIASH_META_RESOURCES_DIR/.config.vsh.yaml" +VIASH_META_TEMP_DIR="$VIASH_TEMP" + + +# ViashHelp: Display helpful explanation about this executable +function ViashHelp { + echo "create_report main" + echo "" + echo "Create a basic QC report in HTML format based on a number of esets." + echo "" + echo "Arguments:" + echo " --eset" + echo " type: file, required parameter, multiple values allowed, file must exist" + echo "" + echo " --output_report" + echo " type: file, required parameter, output, file must exist" + echo " example: report.html" +} + +# initialise variables +VIASH_MODE='run' +VIASH_ENGINE_ID='docker' + +######## Helper functions for setting up Docker images for viash ######## +# expects: ViashDockerBuild + +# ViashDockerInstallationCheck: check whether Docker is installed correctly +# +# examples: +# ViashDockerInstallationCheck +function ViashDockerInstallationCheck { + ViashDebug "Checking whether Docker is installed" + if [ ! command -v docker &> /dev/null ]; then + ViashCritical "Docker doesn't seem to be installed. See 'https://docs.docker.com/get-docker/' for instructions." + exit 1 + fi + + ViashDebug "Checking whether the Docker daemon is running" + local save=$-; set +e + local docker_version=$(docker version --format '{{.Client.APIVersion}}' 2> /dev/null) + local out=$? + [[ $save =~ e ]] && set -e + if [ $out -ne 0 ]; then + ViashCritical "Docker daemon does not seem to be running. Try one of the following:" + ViashCritical "- Try running 'dockerd' in the command line" + ViashCritical "- See https://docs.docker.com/config/daemon/" + exit 1 + fi +} + +# ViashDockerRemoteTagCheck: check whether a Docker image is available +# on a remote. Assumes `docker login` has been performed, if relevant. +# +# $1 : image identifier with format `[registry/]image[:tag]` +# exit code $? : whether or not the image was found +# examples: +# ViashDockerRemoteTagCheck python:latest +# echo $? # returns '0' +# ViashDockerRemoteTagCheck sdaizudceahifu +# echo $? # returns '1' +function ViashDockerRemoteTagCheck { + docker manifest inspect $1 > /dev/null 2> /dev/null +} + +# ViashDockerLocalTagCheck: check whether a Docker image is available locally +# +# $1 : image identifier with format `[registry/]image[:tag]` +# exit code $? : whether or not the image was found +# examples: +# docker pull python:latest +# ViashDockerLocalTagCheck python:latest +# echo $? # returns '0' +# ViashDockerLocalTagCheck sdaizudceahifu +# echo $? # returns '1' +function ViashDockerLocalTagCheck { + [ -n "$(docker images -q $1)" ] +} + +# ViashDockerPull: pull a Docker image +# +# $1 : image identifier with format `[registry/]image[:tag]` +# exit code $? : whether or not the image was found +# examples: +# ViashDockerPull python:latest +# echo $? # returns '0' +# ViashDockerPull sdaizudceahifu +# echo $? # returns '1' +function ViashDockerPull { + ViashNotice "Checking if Docker image is available at '$1'" + if [ $VIASH_VERBOSITY -ge $VIASH_LOGCODE_INFO ]; then + docker pull $1 && return 0 || return 1 + else + local save=$-; set +e + docker pull $1 2> /dev/null > /dev/null + local out=$? + [[ $save =~ e ]] && set -e + if [ $out -ne 0 ]; then + ViashWarning "Could not pull from '$1'. Docker image doesn't exist or is not accessible." + fi + return $out + fi +} + +# ViashDockerPush: push a Docker image +# +# $1 : image identifier with format `[registry/]image[:tag]` +# exit code $? : whether or not the image was found +# examples: +# ViashDockerPush python:latest +# echo $? # returns '0' +# ViashDockerPush sdaizudceahifu +# echo $? # returns '1' +function ViashDockerPush { + ViashNotice "Pushing image to '$1'" + local save=$-; set +e + local out + if [ $VIASH_VERBOSITY -ge $VIASH_LOGCODE_INFO ]; then + docker push $1 + out=$? + else + docker push $1 2> /dev/null > /dev/null + out=$? + fi + [[ $save =~ e ]] && set -e + if [ $out -eq 0 ]; then + ViashNotice "Container '$1' push succeeded." + else + ViashError "Container '$1' push errored. You might not be logged in or have the necessary permissions." + fi + return $out +} + +# ViashDockerPullElseBuild: pull a Docker image, else build it +# +# $1 : image identifier with format `[registry/]image[:tag]` +# ViashDockerBuild : a Bash function which builds a docker image, takes image identifier as argument. +# examples: +# ViashDockerPullElseBuild mynewcomponent +function ViashDockerPullElseBuild { + local save=$-; set +e + ViashDockerPull $1 + local out=$? + [[ $save =~ e ]] && set -e + if [ $out -ne 0 ]; then + ViashDockerBuild $@ + fi +} + +# ViashDockerSetup: create a Docker image, according to specified docker setup strategy +# +# $1 : image identifier with format `[registry/]image[:tag]` +# $2 : docker setup strategy, see DockerSetupStrategy.scala +# examples: +# ViashDockerSetup mynewcomponent alwaysbuild +function ViashDockerSetup { + local image_id="$1" + local setup_strategy="$2" + if [ "$setup_strategy" == "alwaysbuild" -o "$setup_strategy" == "build" -o "$setup_strategy" == "b" ]; then + ViashDockerBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id") + elif [ "$setup_strategy" == "alwayspull" -o "$setup_strategy" == "pull" -o "$setup_strategy" == "p" ]; then + ViashDockerPull $image_id + elif [ "$setup_strategy" == "alwayspullelsebuild" -o "$setup_strategy" == "pullelsebuild" ]; then + ViashDockerPullElseBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id") + elif [ "$setup_strategy" == "alwayspullelsecachedbuild" -o "$setup_strategy" == "pullelsecachedbuild" ]; then + ViashDockerPullElseBuild $image_id $(ViashDockerBuildArgs "$engine_id") + elif [ "$setup_strategy" == "alwayscachedbuild" -o "$setup_strategy" == "cachedbuild" -o "$setup_strategy" == "cb" ]; then + ViashDockerBuild $image_id $(ViashDockerBuildArgs "$engine_id") + elif [[ "$setup_strategy" =~ ^ifneedbe ]]; then + local save=$-; set +e + ViashDockerLocalTagCheck $image_id + local outCheck=$? + [[ $save =~ e ]] && set -e + if [ $outCheck -eq 0 ]; then + ViashInfo "Image $image_id already exists" + elif [ "$setup_strategy" == "ifneedbebuild" ]; then + ViashDockerBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id") + elif [ "$setup_strategy" == "ifneedbecachedbuild" ]; then + ViashDockerBuild $image_id $(ViashDockerBuildArgs "$engine_id") + elif [ "$setup_strategy" == "ifneedbepull" ]; then + ViashDockerPull $image_id + elif [ "$setup_strategy" == "ifneedbepullelsebuild" ]; then + ViashDockerPullElseBuild $image_id --no-cache $(ViashDockerBuildArgs "$engine_id") + elif [ "$setup_strategy" == "ifneedbepullelsecachedbuild" ]; then + ViashDockerPullElseBuild $image_id $(ViashDockerBuildArgs "$engine_id") + else + ViashError "Unrecognised Docker strategy: $setup_strategy" + exit 1 + fi + elif [ "$setup_strategy" == "push" -o "$setup_strategy" == "forcepush" -o "$setup_strategy" == "alwayspush" ]; then + ViashDockerPush "$image_id" + elif [ "$setup_strategy" == "pushifnotpresent" -o "$setup_strategy" == "gentlepush" -o "$setup_strategy" == "maybepush" ]; then + local save=$-; set +e + ViashDockerRemoteTagCheck $image_id + local outCheck=$? + [[ $save =~ e ]] && set -e + if [ $outCheck -eq 0 ]; then + ViashNotice "Container '$image_id' exists, doing nothing." + else + ViashNotice "Container '$image_id' does not yet exist." + ViashDockerPush "$image_id" + fi + elif [ "$setup_strategy" == "donothing" -o "$setup_strategy" == "meh" ]; then + ViashNotice "Skipping setup." + else + ViashError "Unrecognised Docker strategy: $setup_strategy" + exit 1 + fi +} + +# ViashDockerCheckCommands: Check whether a docker container has the required commands +# +# $1 : image identifier with format `[registry/]image[:tag]` +# $@ : commands to verify being present +# examples: +# ViashDockerCheckCommands bash:4.0 bash ps foo +function ViashDockerCheckCommands { + local image_id="$1" + shift 1 + local commands="$@" + local save=$-; set +e + local missing # mark 'missing' as local in advance, otherwise the exit code of the command will be missing and always be '0' + missing=$(docker run --rm --entrypoint=sh "$image_id" -c "for command in $commands; do command -v \$command >/dev/null 2>&1; if [ \$? -ne 0 ]; then echo \$command; exit 1; fi; done") + local outCheck=$? + [[ $save =~ e ]] && set -e + if [ $outCheck -ne 0 ]; then + ViashError "Docker container '$image_id' does not contain command '$missing'." + exit 1 + fi +} + +# ViashDockerBuild: build a docker image +# $1 : image identifier with format `[registry/]image[:tag]` +# $... : additional arguments to pass to docker build +# $VIASH_META_TEMP_DIR : temporary directory to store dockerfile & optional resources in +# $VIASH_META_NAME : name of the component +# $VIASH_META_RESOURCES_DIR : directory containing the resources +# $VIASH_VERBOSITY : verbosity level +# exit code $? : whether or not the image was built successfully +function ViashDockerBuild { + local image_id="$1" + shift 1 + + # create temporary directory to store dockerfile & optional resources in + local tmpdir=$(mktemp -d "$VIASH_META_TEMP_DIR/dockerbuild-$VIASH_META_NAME-XXXXXX") + local dockerfile="$tmpdir/Dockerfile" + function clean_up { + rm -rf "$tmpdir" + } + trap clean_up EXIT + + # store dockerfile and resources + ViashDockerfile "$VIASH_ENGINE_ID" > "$dockerfile" + + # generate the build command + local docker_build_cmd="docker build -t '$image_id' $@ '$VIASH_META_RESOURCES_DIR' -f '$dockerfile'" + + # build the container + ViashNotice "Building container '$image_id' with Dockerfile" + ViashInfo "$docker_build_cmd" + local save=$-; set +e + if [ $VIASH_VERBOSITY -ge $VIASH_LOGCODE_INFO ]; then + eval $docker_build_cmd + else + eval $docker_build_cmd &> "$tmpdir/docker_build.log" + fi + + # check exit code + local out=$? + [[ $save =~ e ]] && set -e + if [ $out -ne 0 ]; then + ViashError "Error occurred while building container '$image_id'" + if [ $VIASH_VERBOSITY -lt $VIASH_LOGCODE_INFO ]; then + ViashError "Transcript: --------------------------------" + cat "$tmpdir/docker_build.log" + ViashError "End of transcript --------------------------" + fi + exit 1 + fi +} + +######## End of helper functions for setting up Docker images for viash ######## + +# ViashDockerFile: print the dockerfile to stdout +# $1 : engine identifier +# return : dockerfile required to run this component +# examples: +# ViashDockerFile +function ViashDockerfile { + local engine_id="$1" + + if [[ "$engine_id" == "docker" ]]; then + cat << 'VIASHDOCKER' +FROM rocker/r2u:24.04 +ENTRYPOINT [] +RUN apt-get update && \ + DEBIAN_FRONTEND=noninteractive apt-get install -y procps pandoc && \ + rm -rf /var/lib/apt/lists/* + +RUN Rscript -e 'if (!requireNamespace("remotes", quietly = TRUE)) install.packages("remotes")' && \ + Rscript -e 'if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager")' && \ + Rscript -e 'if (!requireNamespace("Biobase", quietly = TRUE)) BiocManager::install("Biobase")' && \ + Rscript -e 'if (!requireNamespace("ComplexHeatmap", quietly = TRUE)) BiocManager::install("ComplexHeatmap")' && \ + Rscript -e 'remotes::install_cran(c("ggplot2", "knitr", "gridExtra", "RColorBrewer", "processx", "whisker", "rmarkdown", "bookdown", "data.table", "platetools", "htmltools", "DT", "logger", "bit64"), repos = "https://cran.rstudio.com")' && \ + Rscript -e 'install.packages("oaStyle", repos = c(rdepot = "https://repos.openanalytics.eu/repo/public", getOption("repos")))' + +LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" +LABEL org.opencontainers.image.description="Companion container for running component report create_report" +LABEL org.opencontainers.image.created="2024-12-17T13:58:23Z" +LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" +LABEL org.opencontainers.image.version="main" + +VIASHDOCKER + fi +} + +# ViashDockerBuildArgs: return the arguments to pass to docker build +# $1 : engine identifier +# return : arguments to pass to docker build +function ViashDockerBuildArgs { + local engine_id="$1" + + if [[ "$engine_id" == "docker" ]]; then + echo "" + fi +} + +# ViashAbsolutePath: generate absolute path from relative path +# borrowed from https://stackoverflow.com/a/21951256 +# $1 : relative filename +# return : absolute path +# examples: +# ViashAbsolutePath some_file.txt # returns /path/to/some_file.txt +# ViashAbsolutePath /foo/bar/.. # returns /foo +function ViashAbsolutePath { + local thePath + local parr + local outp + local len + if [[ ! "$1" =~ ^/ ]]; then + thePath="$PWD/$1" + else + thePath="$1" + fi + echo "$thePath" | ( + IFS=/ + read -a parr + declare -a outp + for i in "${parr[@]}"; do + case "$i" in + ''|.) continue ;; + ..) + len=${#outp[@]} + if ((len==0)); then + continue + else + unset outp[$((len-1))] + fi + ;; + *) + len=${#outp[@]} + outp[$len]="$i" + ;; + esac + done + echo /"${outp[*]}" + ) +} +# ViashDockerAutodetectMount: auto configuring docker mounts from parameters +# $1 : The parameter value +# returns : New parameter +# $VIASH_DIRECTORY_MOUNTS : Added another parameter to be passed to docker +# $VIASH_DOCKER_AUTOMOUNT_PREFIX : The prefix to be used for the automounts +# examples: +# ViashDockerAutodetectMount /path/to/bar # returns '/viash_automount/path/to/bar' +# ViashDockerAutodetectMountArg /path/to/bar # returns '--volume="/path/to:/viash_automount/path/to"' +function ViashDockerAutodetectMount { + local abs_path=$(ViashAbsolutePath "$1") + local mount_source + local base_name + if [ -d "$abs_path" ]; then + mount_source="$abs_path" + base_name="" + else + mount_source=`dirname "$abs_path"` + base_name=`basename "$abs_path"` + fi + local mount_target="$VIASH_DOCKER_AUTOMOUNT_PREFIX$mount_source" + if [ -z "$base_name" ]; then + echo "$mount_target" + else + echo "$mount_target/$base_name" + fi +} +function ViashDockerAutodetectMountArg { + local abs_path=$(ViashAbsolutePath "$1") + local mount_source + local base_name + if [ -d "$abs_path" ]; then + mount_source="$abs_path" + base_name="" + else + mount_source=`dirname "$abs_path"` + base_name=`basename "$abs_path"` + fi + local mount_target="$VIASH_DOCKER_AUTOMOUNT_PREFIX$mount_source" + ViashDebug "ViashDockerAutodetectMountArg $1 -> $mount_source -> $mount_target" + echo "--volume=\"$mount_source:$mount_target\"" +} +function ViashDockerStripAutomount { + local abs_path=$(ViashAbsolutePath "$1") + echo "${abs_path#$VIASH_DOCKER_AUTOMOUNT_PREFIX}" +} +# initialise variables +VIASH_DIRECTORY_MOUNTS=() + +# configure default docker automount prefix if it is unset +if [ -z "${VIASH_DOCKER_AUTOMOUNT_PREFIX+x}" ]; then + VIASH_DOCKER_AUTOMOUNT_PREFIX="/viash_automount" +fi + +# initialise docker variables +VIASH_DOCKER_RUN_ARGS=(-i --rm) + +# initialise array +VIASH_POSITIONAL_ARGS='' + +while [[ $# -gt 0 ]]; do + case "$1" in + -h|--help) + ViashHelp + exit + ;; + ---v|---verbose) + let "VIASH_VERBOSITY=VIASH_VERBOSITY+1" + shift 1 + ;; + ---verbosity) + VIASH_VERBOSITY="$2" + shift 2 + ;; + ---verbosity=*) + VIASH_VERBOSITY="$(ViashRemoveFlags "$1")" + shift 1 + ;; + --version) + echo "create_report main" + exit + ;; + --eset) + if [ -z "$VIASH_PAR_ESET" ]; then + VIASH_PAR_ESET="$2" + else + VIASH_PAR_ESET="$VIASH_PAR_ESET;""$2" + fi + [ $# -lt 2 ] && ViashError Not enough arguments passed to --eset. Use "--help" to get more information on the parameters. && exit 1 + shift 2 + ;; + --eset=*) + if [ -z "$VIASH_PAR_ESET" ]; then + VIASH_PAR_ESET=$(ViashRemoveFlags "$1") + else + VIASH_PAR_ESET="$VIASH_PAR_ESET;"$(ViashRemoveFlags "$1") + fi + shift 1 + ;; + --output_report) + [ -n "$VIASH_PAR_OUTPUT_REPORT" ] && ViashError Bad arguments for option \'--output_report\': \'$VIASH_PAR_OUTPUT_REPORT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_PAR_OUTPUT_REPORT="$2" + [ $# -lt 2 ] && ViashError Not enough arguments passed to --output_report. Use "--help" to get more information on the parameters. && exit 1 + shift 2 + ;; + --output_report=*) + [ -n "$VIASH_PAR_OUTPUT_REPORT" ] && ViashError Bad arguments for option \'--output_report=*\': \'$VIASH_PAR_OUTPUT_REPORT\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_PAR_OUTPUT_REPORT=$(ViashRemoveFlags "$1") + shift 1 + ;; + ---engine) + VIASH_ENGINE_ID="$2" + shift 2 + ;; + ---engine=*) + VIASH_ENGINE_ID="$(ViashRemoveFlags "$1")" + shift 1 + ;; + ---setup) + VIASH_MODE='setup' + VIASH_SETUP_STRATEGY="$2" + shift 2 + ;; + ---setup=*) + VIASH_MODE='setup' + VIASH_SETUP_STRATEGY="$(ViashRemoveFlags "$1")" + shift 1 + ;; + ---dockerfile) + VIASH_MODE='dockerfile' + shift 1 + ;; + ---docker_run_args) + VIASH_DOCKER_RUN_ARGS+=("$2") + shift 2 + ;; + ---docker_run_args=*) + VIASH_DOCKER_RUN_ARGS+=("$(ViashRemoveFlags "$1")") + shift 1 + ;; + ---docker_image_id) + VIASH_MODE='docker_image_id' + shift 1 + ;; + ---debug) + VIASH_MODE='debug' + shift 1 + ;; + ---cpus) + [ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_META_CPUS="$2" + [ $# -lt 2 ] && ViashError Not enough arguments passed to ---cpus. Use "--help" to get more information on the parameters. && exit 1 + shift 2 + ;; + ---cpus=*) + [ -n "$VIASH_META_CPUS" ] && ViashError Bad arguments for option \'---cpus=*\': \'$VIASH_META_CPUS\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_META_CPUS=$(ViashRemoveFlags "$1") + shift 1 + ;; + ---memory) + [ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_META_MEMORY="$2" + [ $# -lt 2 ] && ViashError Not enough arguments passed to ---memory. Use "--help" to get more information on the parameters. && exit 1 + shift 2 + ;; + ---memory=*) + [ -n "$VIASH_META_MEMORY" ] && ViashError Bad arguments for option \'---memory=*\': \'$VIASH_META_MEMORY\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_META_MEMORY=$(ViashRemoveFlags "$1") + shift 1 + ;; + *) # positional arg or unknown option + # since the positional args will be eval'd, can we always quote, instead of using ViashQuote + VIASH_POSITIONAL_ARGS="$VIASH_POSITIONAL_ARGS '$1'" + [[ $1 == -* ]] && ViashWarning $1 looks like a parameter but is not a defined parameter and will instead be treated as a positional argument. Use "--help" to get more information on the parameters. + shift # past argument + ;; + esac +done + +# parse positional parameters +eval set -- $VIASH_POSITIONAL_ARGS + + +if [ "$VIASH_ENGINE_ID" == "native" ] ; then + VIASH_ENGINE_TYPE='native' +elif [ "$VIASH_ENGINE_ID" == "docker" ] ; then + VIASH_ENGINE_TYPE='docker' +else + ViashError "Engine '$VIASH_ENGINE_ID' is not recognized. Options are: docker, native." + exit 1 +fi + +if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then + # check if docker is installed properly + ViashDockerInstallationCheck + + # determine docker image id + if [[ "$VIASH_ENGINE_ID" == 'docker' ]]; then + VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/htrnaseq/report/create_report:main' + fi + + # print dockerfile + if [ "$VIASH_MODE" == "dockerfile" ]; then + ViashDockerfile "$VIASH_ENGINE_ID" + exit 0 + + elif [ "$VIASH_MODE" == "docker_image_id" ]; then + echo "$VIASH_DOCKER_IMAGE_ID" + exit 0 + + # enter docker container + elif [[ "$VIASH_MODE" == "debug" ]]; then + VIASH_CMD="docker run --entrypoint=bash ${VIASH_DOCKER_RUN_ARGS[@]} -v '$(pwd)':/pwd --workdir /pwd -t $VIASH_DOCKER_IMAGE_ID" + ViashNotice "+ $VIASH_CMD" + eval $VIASH_CMD + exit + + # build docker image + elif [ "$VIASH_MODE" == "setup" ]; then + ViashDockerSetup "$VIASH_DOCKER_IMAGE_ID" "$VIASH_SETUP_STRATEGY" + ViashDockerCheckCommands "$VIASH_DOCKER_IMAGE_ID" 'ps' 'bash' + exit 0 + fi + + # check if docker image exists + ViashDockerSetup "$VIASH_DOCKER_IMAGE_ID" ifneedbepullelsecachedbuild + ViashDockerCheckCommands "$VIASH_DOCKER_IMAGE_ID" 'ps' 'bash' +fi + +# setting computational defaults + +# helper function for parsing memory strings +function ViashMemoryAsBytes { + local memory=`echo "$1" | tr '[:upper:]' '[:lower:]' | tr -d '[:space:]'` + local memory_regex='^([0-9]+)([kmgtp]i?b?|b)$' + if [[ $memory =~ $memory_regex ]]; then + local number=${memory/[^0-9]*/} + local symbol=${memory/*[0-9]/} + + case $symbol in + b) memory_b=$number ;; + kb|k) memory_b=$(( $number * 1000 )) ;; + mb|m) memory_b=$(( $number * 1000 * 1000 )) ;; + gb|g) memory_b=$(( $number * 1000 * 1000 * 1000 )) ;; + tb|t) memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 )) ;; + pb|p) memory_b=$(( $number * 1000 * 1000 * 1000 * 1000 * 1000 )) ;; + kib|ki) memory_b=$(( $number * 1024 )) ;; + mib|mi) memory_b=$(( $number * 1024 * 1024 )) ;; + gib|gi) memory_b=$(( $number * 1024 * 1024 * 1024 )) ;; + tib|ti) memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 )) ;; + pib|pi) memory_b=$(( $number * 1024 * 1024 * 1024 * 1024 * 1024 )) ;; + esac + echo "$memory_b" + fi +} +# compute memory in different units +if [ ! -z ${VIASH_META_MEMORY+x} ]; then + VIASH_META_MEMORY_B=`ViashMemoryAsBytes $VIASH_META_MEMORY` + # do not define other variables if memory_b is an empty string + if [ ! -z "$VIASH_META_MEMORY_B" ]; then + VIASH_META_MEMORY_KB=$(( ($VIASH_META_MEMORY_B+999) / 1000 )) + VIASH_META_MEMORY_MB=$(( ($VIASH_META_MEMORY_KB+999) / 1000 )) + VIASH_META_MEMORY_GB=$(( ($VIASH_META_MEMORY_MB+999) / 1000 )) + VIASH_META_MEMORY_TB=$(( ($VIASH_META_MEMORY_GB+999) / 1000 )) + VIASH_META_MEMORY_PB=$(( ($VIASH_META_MEMORY_TB+999) / 1000 )) + VIASH_META_MEMORY_KIB=$(( ($VIASH_META_MEMORY_B+1023) / 1024 )) + VIASH_META_MEMORY_MIB=$(( ($VIASH_META_MEMORY_KIB+1023) / 1024 )) + VIASH_META_MEMORY_GIB=$(( ($VIASH_META_MEMORY_MIB+1023) / 1024 )) + VIASH_META_MEMORY_TIB=$(( ($VIASH_META_MEMORY_GIB+1023) / 1024 )) + VIASH_META_MEMORY_PIB=$(( ($VIASH_META_MEMORY_TIB+1023) / 1024 )) + else + # unset memory if string is empty + unset $VIASH_META_MEMORY_B + fi +fi +# unset nproc if string is empty +if [ -z "$VIASH_META_CPUS" ]; then + unset $VIASH_META_CPUS +fi + + +# check whether required parameters exist +if [ -z ${VIASH_PAR_ESET+x} ]; then + ViashError '--eset' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_PAR_OUTPUT_REPORT+x} ]; then + ViashError '--output_report' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_META_NAME+x} ]; then + ViashError 'name' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then + ViashError 'functionality_name' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_META_RESOURCES_DIR+x} ]; then + ViashError 'resources_dir' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_META_EXECUTABLE+x} ]; then + ViashError 'executable' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_META_CONFIG+x} ]; then + ViashError 'config' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi +if [ -z ${VIASH_META_TEMP_DIR+x} ]; then + ViashError 'temp_dir' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi + +# check whether required files exist +if [ ! -z "$VIASH_PAR_ESET" ]; then + IFS=';' + set -f + for file in $VIASH_PAR_ESET; do + unset IFS + if [ ! -e "$file" ]; then + ViashError "Input file '$file' does not exist." + exit 1 + fi + done + set +f +fi + +# check whether parameters values are of the right type +if [[ -n "$VIASH_META_CPUS" ]]; then + if ! [[ "$VIASH_META_CPUS" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'cpus' has to be an integer. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_B" ]]; then + if ! [[ "$VIASH_META_MEMORY_B" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_b' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_KB" ]]; then + if ! [[ "$VIASH_META_MEMORY_KB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_kb' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_MB" ]]; then + if ! [[ "$VIASH_META_MEMORY_MB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_mb' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_GB" ]]; then + if ! [[ "$VIASH_META_MEMORY_GB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_gb' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_TB" ]]; then + if ! [[ "$VIASH_META_MEMORY_TB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_tb' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_PB" ]]; then + if ! [[ "$VIASH_META_MEMORY_PB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_pb' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_KIB" ]]; then + if ! [[ "$VIASH_META_MEMORY_KIB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_kib' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_MIB" ]]; then + if ! [[ "$VIASH_META_MEMORY_MIB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_mib' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_GIB" ]]; then + if ! [[ "$VIASH_META_MEMORY_GIB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_gib' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_TIB" ]]; then + if ! [[ "$VIASH_META_MEMORY_TIB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_tib' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi +if [[ -n "$VIASH_META_MEMORY_PIB" ]]; then + if ! [[ "$VIASH_META_MEMORY_PIB" =~ ^[-+]?[0-9]+$ ]]; then + ViashError 'memory_pib' has to be a long. Use "--help" to get more information on the parameters. + exit 1 + fi +fi + +# create parent directories of output files, if so desired +if [ ! -z "$VIASH_PAR_OUTPUT_REPORT" ] && [ ! -d "$(dirname "$VIASH_PAR_OUTPUT_REPORT")" ]; then + mkdir -p "$(dirname "$VIASH_PAR_OUTPUT_REPORT")" +fi + +if [ "$VIASH_ENGINE_ID" == "native" ] ; then + if [ "$VIASH_MODE" == "run" ]; then + VIASH_CMD="bash" + else + ViashError "Engine '$VIASH_ENGINE_ID' does not support mode '$VIASH_MODE'." + exit 1 + fi +fi + +if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then + # detect volumes from file arguments + VIASH_CHOWN_VARS=() +if [ ! -z "$VIASH_PAR_ESET" ]; then + VIASH_TEST_ESET=() + IFS=';' + for var in $VIASH_PAR_ESET; do + unset IFS + VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$var")" ) + var=$(ViashDockerAutodetectMount "$var") + VIASH_TEST_ESET+=( "$var" ) + done + VIASH_PAR_ESET=$(IFS=';' ; echo "${VIASH_TEST_ESET[*]}") +fi +if [ ! -z "$VIASH_PAR_OUTPUT_REPORT" ]; then + VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_PAR_OUTPUT_REPORT")" ) + VIASH_PAR_OUTPUT_REPORT=$(ViashDockerAutodetectMount "$VIASH_PAR_OUTPUT_REPORT") + VIASH_CHOWN_VARS+=( "$VIASH_PAR_OUTPUT_REPORT" ) +fi +if [ ! -z "$VIASH_META_RESOURCES_DIR" ]; then + VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_RESOURCES_DIR")" ) + VIASH_META_RESOURCES_DIR=$(ViashDockerAutodetectMount "$VIASH_META_RESOURCES_DIR") +fi +if [ ! -z "$VIASH_META_EXECUTABLE" ]; then + VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_EXECUTABLE")" ) + VIASH_META_EXECUTABLE=$(ViashDockerAutodetectMount "$VIASH_META_EXECUTABLE") +fi +if [ ! -z "$VIASH_META_CONFIG" ]; then + VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_CONFIG")" ) + VIASH_META_CONFIG=$(ViashDockerAutodetectMount "$VIASH_META_CONFIG") +fi +if [ ! -z "$VIASH_META_TEMP_DIR" ]; then + VIASH_DIRECTORY_MOUNTS+=( "$(ViashDockerAutodetectMountArg "$VIASH_META_TEMP_DIR")" ) + VIASH_META_TEMP_DIR=$(ViashDockerAutodetectMount "$VIASH_META_TEMP_DIR") +fi + + # get unique mounts + VIASH_UNIQUE_MOUNTS=($(for val in "${VIASH_DIRECTORY_MOUNTS[@]}"; do echo "$val"; done | sort -u)) +fi + +if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then + # change file ownership + function ViashPerformChown { + if (( ${#VIASH_CHOWN_VARS[@]} )); then + set +e + VIASH_CMD="docker run --entrypoint=bash --rm ${VIASH_UNIQUE_MOUNTS[@]} $VIASH_DOCKER_IMAGE_ID -c 'chown $(id -u):$(id -g) --silent --recursive ${VIASH_CHOWN_VARS[@]}'" + ViashDebug "+ $VIASH_CMD" + eval $VIASH_CMD + set -e + fi + } + trap ViashPerformChown EXIT +fi + +if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then + # helper function for filling in extra docker args + if [ ! -z "$VIASH_META_MEMORY_B" ]; then + VIASH_DOCKER_RUN_ARGS+=("--memory=${VIASH_META_MEMORY_B}") + fi + if [ ! -z "$VIASH_META_CPUS" ]; then + VIASH_DOCKER_RUN_ARGS+=("--cpus=${VIASH_META_CPUS}") + fi +fi + +if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then + VIASH_CMD="docker run --entrypoint=bash ${VIASH_DOCKER_RUN_ARGS[@]} ${VIASH_UNIQUE_MOUNTS[@]} $VIASH_DOCKER_IMAGE_ID" +fi + + +# set dependency paths + + +ViashDebug "Running command: $(echo $VIASH_CMD)" +cat << VIASHEOF | eval $VIASH_CMD +set -e +tempscript=\$(mktemp "$VIASH_META_TEMP_DIR/viash-run-create_report-XXXXXX").R +function clean_up { + rm "\$tempscript" +} +function interrupt { + echo -e "\nCTRL-C Pressed..." + exit 1 +} +trap clean_up EXIT +trap interrupt INT SIGINT +cat > "\$tempscript" << 'VIASHMAIN' +## VIASH START +# The following code has been auto-generated by Viash. +# treat warnings as errors +.viash_orig_warn <- options(warn = 2) + +par <- list( + "eset" = $( if [ ! -z ${VIASH_PAR_ESET+x} ]; then echo -n "strsplit('"; echo -n "$VIASH_PAR_ESET" | sed "s#['\\]#\\\\&#g"; echo "', split = ';')[[1]]"; else echo NULL; fi ), + "output_report" = $( if [ ! -z ${VIASH_PAR_OUTPUT_REPORT+x} ]; then echo -n "'"; echo -n "$VIASH_PAR_OUTPUT_REPORT" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ) +) +meta <- list( + "name" = $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo -n "'"; echo -n "$VIASH_META_NAME" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ), + "functionality_name" = $( if [ ! -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then echo -n "'"; echo -n "$VIASH_META_FUNCTIONALITY_NAME" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ), + "resources_dir" = $( if [ ! -z ${VIASH_META_RESOURCES_DIR+x} ]; then echo -n "'"; echo -n "$VIASH_META_RESOURCES_DIR" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ), + "executable" = $( if [ ! -z ${VIASH_META_EXECUTABLE+x} ]; then echo -n "'"; echo -n "$VIASH_META_EXECUTABLE" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ), + "config" = $( if [ ! -z ${VIASH_META_CONFIG+x} ]; then echo -n "'"; echo -n "$VIASH_META_CONFIG" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ), + "temp_dir" = $( if [ ! -z ${VIASH_META_TEMP_DIR+x} ]; then echo -n "'"; echo -n "$VIASH_META_TEMP_DIR" | sed "s#['\\]#\\\\&#g"; echo "'"; else echo NULL; fi ), + "cpus" = $( if [ ! -z ${VIASH_META_CPUS+x} ]; then echo -n "as.integer('"; echo -n "$VIASH_META_CPUS" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_b" = $( if [ ! -z ${VIASH_META_MEMORY_B+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_B" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_kb" = $( if [ ! -z ${VIASH_META_MEMORY_KB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_KB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_mb" = $( if [ ! -z ${VIASH_META_MEMORY_MB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_MB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_gb" = $( if [ ! -z ${VIASH_META_MEMORY_GB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_GB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_tb" = $( if [ ! -z ${VIASH_META_MEMORY_TB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_TB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_pb" = $( if [ ! -z ${VIASH_META_MEMORY_PB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_PB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_kib" = $( if [ ! -z ${VIASH_META_MEMORY_KIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_KIB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_mib" = $( if [ ! -z ${VIASH_META_MEMORY_MIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_MIB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_gib" = $( if [ ! -z ${VIASH_META_MEMORY_GIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_GIB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_tib" = $( if [ ! -z ${VIASH_META_MEMORY_TIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_TIB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_pib" = $( if [ ! -z ${VIASH_META_MEMORY_PIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_PIB" | sed "s#['\\]#\\\\&#g"; echo "')"; else echo NULL; fi ) +) +dep <- list( + +) + + +# restore original warn setting +options(.viash_orig_warn) +rm(.viash_orig_warn) + +## VIASH END +library(whisker) +library(logger) + +log_info("Setting temporary directory to: {meta\$temp_dir}") +Sys.setenv(TMP = meta\$temp_dir) +temp_folder <- tempdir(check = TRUE) +log_info("Created temporary directory {temp_folder}") + +template <- file.path(meta\$resources_dir, "template.Rmd") + +esets_normalized <- lapply(par\$eset, function(eset_path) { + return(file.path(normalizePath(dirname(eset_path)), basename(eset_path))) +}) + +log_info(paste0( + "Rendering markdown {template} to HTML ", + "{par\$output_report} with esets {paste(esets_normalized, collapse = ', ')}" +)) + +rmarkdown::render( + normalizePath(template), + output_file = basename(par\$output_report), + output_dir = dirname(par\$output_report), + runtime = "static", + intermediates_dir = par\$report_dir, + clean = TRUE, + params = list( + esets = esets_normalized, + outputDir = par\$report_dir + ) +) + +log_info("Done") +VIASHMAIN +Rscript "\$tempscript" & +wait "\$!" + +VIASHEOF + + +if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then + # strip viash automount from file paths + + if [ ! -z "$VIASH_PAR_ESET" ]; then + unset VIASH_TEST_ESET + IFS=';' + for var in $VIASH_PAR_ESET; do + unset IFS + if [ -z "$VIASH_TEST_ESET" ]; then + VIASH_TEST_ESET="$(ViashDockerStripAutomount "$var")" + else + VIASH_TEST_ESET="$VIASH_TEST_ESET;""$(ViashDockerStripAutomount "$var")" + fi + done + VIASH_PAR_ESET="$VIASH_TEST_ESET" + fi + if [ ! -z "$VIASH_PAR_OUTPUT_REPORT" ]; then + VIASH_PAR_OUTPUT_REPORT=$(ViashDockerStripAutomount "$VIASH_PAR_OUTPUT_REPORT") + fi + if [ ! -z "$VIASH_META_RESOURCES_DIR" ]; then + VIASH_META_RESOURCES_DIR=$(ViashDockerStripAutomount "$VIASH_META_RESOURCES_DIR") + fi + if [ ! -z "$VIASH_META_EXECUTABLE" ]; then + VIASH_META_EXECUTABLE=$(ViashDockerStripAutomount "$VIASH_META_EXECUTABLE") + fi + if [ ! -z "$VIASH_META_CONFIG" ]; then + VIASH_META_CONFIG=$(ViashDockerStripAutomount "$VIASH_META_CONFIG") + fi + if [ ! -z "$VIASH_META_TEMP_DIR" ]; then + VIASH_META_TEMP_DIR=$(ViashDockerStripAutomount "$VIASH_META_TEMP_DIR") + fi +fi + + +# check whether required files exist +if [ ! -z "$VIASH_PAR_OUTPUT_REPORT" ] && [ ! -e "$VIASH_PAR_OUTPUT_REPORT" ]; then + ViashError "Output file '$VIASH_PAR_OUTPUT_REPORT' does not exist." + exit 1 +fi + + +exit 0 diff --git a/target/executable/report/create_report/nextflow_labels.config b/target/executable/report/create_report/nextflow_labels.config new file mode 100644 index 00000000..2821ec46 --- /dev/null +++ b/target/executable/report/create_report/nextflow_labels.config @@ -0,0 +1,108 @@ +executor { + $k8s { + submitRateLimit = '10sec' + pollInterval = '1 sec' + } +} + +process { + container = 'nextflow/bash:latest' + + // default resources + memory = { 8.Gb * task.attempt } + cpus = 8 + maxForks = 36 + + // Retry for exit codes that have something to do with memory issues + errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' } + maxRetries = 3 + maxMemory = 192.GB + + // Resource labels + withLabel: verylowcpu { cpus = 2 } + withLabel: lowcpu { cpus = 8 } + withLabel: midcpu { cpus = 16 } + withLabel: highcpu { cpus = 32 } + + withLabel: verylowmem { memory = { get_memory( 4.GB * task.attempt ) } } + withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } + withLabel: midmem { memory = { get_memory( 16.GB * task.attempt ) } } + withLabel: highmem { memory = { get_memory( 64.GB * task.attempt ) } } + +} + +profiles { + // detect tempdir + tempDir = java.nio.file.Paths.get( + System.getenv('NXF_TEMP') ?: + System.getenv('VIASH_TEMP') ?: + System.getenv('TEMPDIR') ?: + System.getenv('TMPDIR') ?: + '/tmp' + ).toAbsolutePath() + + mount_temp { + docker.temp = tempDir + podman.temp = tempDir + charliecloud.temp = tempDir + } + + no_publish { + process { + withName: '.*' { + publishDir = [ + enabled: false + ] + } + } + } + + docker { + docker.fixOwnership = true + docker.enabled = true + // docker.userEmulation = true + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + + local { + // This config is for local processing. + process { + withName: ".*parallel_map_process" { + maxForks = 1 + } + maxMemory = 25.GB + withLabel: verylowcpu { cpus = 2 } + withLabel: lowcpu { cpus = 4 } + withLabel: midcpu { cpus = 6 } + withLabel: highcpu { cpus = 8 } + + withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } + withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } + withLabel: highmem { memory = { get_memory( 20.GB * task.attempt ) } } + } + } +} + +def get_memory(to_compare) { + if (!process.containsKey("maxMemory") || !process.maxMemory) { + return to_compare + } + + try { + if (process.containsKey("maxRetries") && process.maxRetries && task.attempt == (process.maxRetries as int)) { + return process.maxMemory + } + else if (to_compare.compareTo(process.maxMemory as nextflow.util.MemoryUnit) == 1) { + return max_memory as nextflow.util.MemoryUnit + } + else { + return to_compare + } + } catch (all) { + println "Error processing memory resources. Please check that process.maxMemory '${process.maxMemory}' and process.maxRetries '${process.maxRetries}' are valid!" + System.exit(1) + } + } diff --git a/target/executable/report/create_report/plateLayouts.R b/target/executable/report/create_report/plateLayouts.R new file mode 100755 index 00000000..c8b16cff --- /dev/null +++ b/target/executable/report/create_report/plateLayouts.R @@ -0,0 +1,424 @@ + +#' Displays the annotation of the wells in a plateLayout +#' @param plateData a data.table object containing the information +#' of the plate. This must contain a "WellID". +#' @param plateName The plate name +#' @param valueVariable The name of the variable in 'plateData' to +#' be visualized in a plate layout. +#' @param textVariable The name of the variable in 'plateData' to be +#' shown in the wells of the plate layout. If NULL, the valueVariable +#' is shown. +#' @param colours A named character vector containing the colours +#' for the different levels of the valuevariable. The names should +#' correspond to the dose levels. if not specified, a scheme of blues +#' will be provided. +#' @param breaks Numeric vector indicating breaks for plot coloring. +#' @param colourWellText Colour to display the text in the wells. +#' @param layout Integer vector of length two with number of rows and +#' colums in a plate, e.g. \code{c(16,24)} +#' @param legend.title A title for the legend +#' @param plot.title A title for the plot, will be contracted +#' with the plate name +#' @param ... additional arguments for \code{plateLayout.default} function +#' @import data.table +#' @importFrom platetools fill_plate +#' @export +plateLayout.annotation <- function( + plateData, + plateName = character(), + valueVariable = "Dose", + textVariable = NULL, + breaks = NULL, colours = NULL, + colourWellText = "black", + layout = c(16, 24), + legend.title = "Dose", + plot.title = "Plate Annotation - ", + textFontSize = 9, ... +) { + WellID <- Label <- NULL + + if (!(all(c("WellID", "SampleName") %in% colnames(plateData)))) { + stop(" 'WellID' and 'SampleName' column required in plateData object") + } + + + plateData[, WellID := paste0( + sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + sprintf( + "%02d", as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ) + )] + + plateData <- platetools::fill_plate(plateData, "WellID", plate = 384) + + plateData$column <- factor( + sprintf( + "%02d", + as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ), + levels = sprintf("%02d", seq(1, layout[2])) + ) + plateData$row <- factor(sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + levels = LETTERS[seq(1, layout[1])]) + + if (!is.null(valueVariable)){ + plateData[, values := as.character(plateData[, ..valueVariable][[1]])] + valueVar <- "values" + }else{ + plateData[, values := "grey"] + valueVar <- "values" + colours <- setNames("grey", "grey") + } + + + if (is.null(colours)) { + + blues <- colorRampPalette(c("#d6e0ff", "#2171B5")) + greens <- colorRampPalette(c("light green", "dark green")) + + numLevels <- sort(as.numeric(as.character(unique(plateData[, values])[ + grepl( + "^[[:digit:]]+([.][[:digit:]]+)?$", + trimws(unique(plateData[, values])) + ) + ]))) + otherLevels <- sort(as.character(unique(plateData[, values])[ + !grepl( + "^[[:digit:]]+([.][[:digit:]]+)?$", + trimws(unique(plateData[,values])) + ) + ])) + + colours <- c(blues(length(numLevels)), greens(length(otherLevels)), "red") + names(colours) <- c(numLevels, otherLevels, "failed") + } + + if (!is.null(textVariable)) { + plateData[, + Label := do.call(paste, c(.SD, sep = "\n ")), + .SDcols = textVariable + ] + plateData[, Label := gsub("-", "-\n", Label)] + plateData[, Label := gsub("_", "_\n", Label)] + textVar <- "Label" + } else { + textVar <- NULL + } + + + if (is.null(breaks)){ + breaks <- seq_len(length(colours)) + } + + plateLayout( + plateData = plateData, valueVariable = valueVar, + textVariable = textVar, plateName = plateName, + breaks = breaks, colourWellText = colourWellText, + legend.title = legend.title, layout = layout, + colours = colours, plot.title = plot.title, + textFontSize = textFontSize, ... + ) +} + + + +#' Create a heatmap of values in a plateLayout view. The values can be +#' library sizes, number of genes, qcScore (0/1) or a factor. +#' @param plateData A data.table of the values to be visualized with +#' at least the column of interest (specified in 'varOfInterest') +#' and a 'WellID' column indicating the wells in the plate. The WellID +#' is a combination of a letter (row in the plate) and an integer +#' (column in the plate). +#' @param valueVariable The name of the variable in 'plateData' +#' to be visualized in a plate layout +#' @param textVariable The name of the variable in 'plateData' +#' to be shown in the wells of the plate layout. Defaults to the +#' valueVariable and if NULL, no text will be displayed. +#' @param breaks Numeric vector indicating breaks for plot coloring. +#' @param colours Colours to be used for levels specified by +#' the breaks. If NULL, a colour scheme of purples is shown. +#' @param colourWellText Colour to display the text in the wells. +#' @param layout Integer vector of length two with number of rows +#' and colums in a plate, e.g. \code{c(16,24)} +#' @param makeContourColours Logical, whether or not the plate +#' layout will contain a contour colours for the wells based on the +#' parameters in 'contourColours' and 'categories' +#' @param contourVariable The variable used for the contour colouring +#' @param contourColours Character vector specifying a colour for +#' each range in 'categories' +#' @param labelsCategories Character vector specifying the names +#' (labels) for each range in 'categories' +#' @param categories if contour Variable is not a factor, a numeric +#' vector specifying the categories to divide the 'varOfInterest', +#' including the lower and upper limits. +#' @param plateName The plate name +#' @param plot.title A title for the plot, will be contracted with +#' the plate name +#' @param legend.title A title for the legend +#' @param displayHeatmap Logical, whether to display the plateLayout heatmap +#' @param saveHeatmap Logical, whether to save the plateLayout heatmap +#' @param outputDir The directory where the plateLayout heatmap should be saved +#' @param prefix The prefix to the file name of the saved plateLayout heatmap +#' @param ... additional arguments for \code{ComplexHeatmap::Heatmap} function +#' @importFrom platetools fill_plate +#' @importFrom RColorBrewer brewer.pal +#' @importFrom ComplexHeatmap Heatmap +#' @importFrom circlize colorRamp2 +#' @importFrom grid grid.text grid.rect gpar legendGrob gpar +#' @importFrom grDevices dev.off png +#' @importFrom graphics title +#' @export +plateLayout <- function( + plateData, valueVariable, textVariable = valueVariable, + breaks = NULL, colours = NULL, colourWellText = "white", textFontSize = 6, + layout = c(16, 24), makeContourColours = FALSE, contourVariable = character(), + contourColours = c("red", "orange", "seagreen3"),lwdContours = c(1, 1, 1), + labelsCategories = c('1', '2', '3'), categories = NULL, plateName = character(), + plot.title = character(), legend.title = NULL, legendFontSize = 15, + row_split = rep("A", 16), col_split = rep("A", 24), legendFontSizeTitle = 15, + displayHeatmap = TRUE, saveHeatmap = FALSE, outputDir = ".", prefix = "" +) { + WellID <- NULL + if (!(all(c("WellID", "SampleName") %in% colnames(plateData)))) { + stop(" 'WellID' and 'SampleName' column required in plateData object") + } + + + plateData[, WellID := paste0( + sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + sprintf( + "%02d", + as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ) + )] + + plateData <- platetools::fill_plate(plateData, "WellID", plate = 384) + + plateData$column <- factor( + sprintf("%02d", as.numeric( + sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID) + )), + levels = sprintf("%02d", seq(1, layout[2])) + ) + plateData$row <- factor(sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + levels = LETTERS[seq(1, layout[1])]) + + + plateValues <- plateLayoutFormat( + plateData, + varOfInterest = valueVariable, + rows = layout[1], + cols = layout[2] + ) + if (!is.null(textVariable)) { + plateText <- plateLayoutFormat( + plateData, varOfInterest = textVariable, + rows = layout[1], + cols = layout[2] + ) + } + plot.title <- gsub( + "^([a-z])", "\\U\\1", + gsub("([A-Z])", " \\1", + plot.title, perl = TRUE), perl = TRUE + ) + mainTitle <- paste0(plot.title, plateName) + plateContourColours <- matrix("", nrow = layout[1], ncol = layout[2]) + + if (makeContourColours) { + contourData <- plateData[WellType %in% c("nonEmpty", "Treated Wells"), ] + + if (is.numeric(contourData[, ..contourVariable][[1]])) { + contourData$contours <- cut( + contourData[, ..contourVariable][[1]], + categories, left = TRUE, + right = TRUE, + labels = labelsCategories) + } + else { + contourData$contours <- contourData[, ..contourVariable][[1]] + } + names(contourColours) <- labelsCategories + names(lwdContours) <- labelsCategories + for (i in seq_len(layout[1])) { + for (j in seq_len(layout[2])) { + tryCatch({ + sampleHit <- which( + as.character(contourData$WellID) == paste0( + LETTERS[i], sprintf("%02d", j) + ) + ) + if (length(sampleHit) == 1) { + plateContourColours[i, j] <- as.character( + contourData[sampleHit,'contours'][[1]] + ) + } + }, + error = function(e) { + print(paste0(LETTERS[i], sprintf("%02d", j), " is missing.")) + } + ) + } + } + } + + plateValues$contours <- plateContourColours + colnames(plateValues$values) <- seq_len(ncol(plateValues$values)) + + if (is.null(breaks)) { + breakValues <- plateValues$values + breakValues[which(is.na(breakValues))] <- 0 + if (all(breakValues >= 0)) { + breaks <- computeBreaks(7, max(plateValues$values, na.rm = TRUE)) + } else { + breaks <- quantile(plateValues$values, probs = seq(0, 1, 0.125)) + } + } + + if (is.null(colours)) { + colours <- tryCatch({ + colorRamp2( + breaks = breaks, + colors = brewer.pal(length(breaks), "Purples") + ) + }, + error = function(cond) { + return(c("#9370DB", "white")) + }) + } + ht <- Heatmap( + plateValues$values, + column_title = mainTitle, column_title_side = "top", + rect_gp = gpar(lwd = 0.4), + cluster_rows = FALSE, cluster_columns = FALSE, + col = colours, row_title = NULL, + row_split = row_split, column_split = col_split, + row_names_side = "left", + cluster_row_slices = FALSE, + cluster_column_slices = FALSE, + show_heatmap_legend = TRUE, + heatmap_legend_param = list( + title = ifelse( + is.null(legend.title), + paste0(valueVariable, "\n"), + paste0(legend.title, "\n") + ), + grid_height = unit(9, "mm"), border = "black", + labels_gp = gpar(fontsize = legendFontSize), + title_gp = gpar(fontsize = legendFontSizeTitle) + ), + cell_fun = function(j, i, x, y, width, height, fill) { + if (is.na(plateValues$values[i, j])) { + grid.rect( + x, y, width, height, + gp = gpar(fill = "white", alpha = 0.7, lwd = 0.7, col = "white") + ) + } + else if (!is.null(textVariable)) { + grid.text( + plateText$values[i, j], x, y, + just = "centre", + gp = gpar(fontsize = textFontSize, col = colourWellText) + ) + } + if (makeContourColours) { + if (!is.na(plateValues$contours[i, j])) { + grid.rect( + x, y, width, height, + gp = gpar( + col = contourColours[as.character(plateValues$contours[i, j])], + fill = NA, + lwd = lwdContours[as.character(plateValues$contours[i, j])] + ) + ) + } + } + } + ) + + if (displayHeatmap) { + print(ht) + } + if (saveHeatmap) { + png( + file.path( + outputDir, + paste0(prefix,gsub(" |-", "",plot.title), "_", plateName, ".png") + ), + width = 30, height = 10, units = "cm", res = 1200 + ) + print(ht) + dev.off() + } + + return(ht) +} + + +#' Return numerical matrix with number of reads that corresponds to the +#' plate layout +#' @param data A data.frame of the values to be visualized with at least +#' the columnof interest (specified in 'varOfInterest') and a 'WellID' column +#' indicating the wells in the plate. The WellID is a combination of a +#' letter (row in the plate) and an integer (column in the plate). +#' @param varOfInterest The name of the variable in 'data' to be visualized +#' in a plate layout +#' @param rows number of rows in a plate layout +#' @param cols number of columns in a plate layout +#' @param verbose if \code{TRUE}, samples missing from the plate +#' will be reported +#' @export +plateLayoutFormat <- function( + data, varOfInterest, + rows = 16, cols = 24, + verbose = FALSE +) { + plateValues <- matrix(NA, nrow = rows, ncol = cols) + for (i in seq_len(rows)) { + for (j in seq_len(cols)) { + tryCatch({ + sampleHit <- which( + as.character(data$WellID) == paste0(LETTERS[i], sprintf("%02d", j)) + ) + if(length(sampleHit) == 1){ + plateValues[i, j] <- data[sampleHit, ..varOfInterest][[1]] + } + }, + error = function(e) { + if (verbose == TRUE) { + print(paste0(LETTERS[i], sprintf("%02d", j), " is missing.")) + } + } + ) + } + } + + row.names(plateValues) <- LETTERS[1:rows] + return(list("values" = plateValues)) +} + + + +#' Helper function to automate break selection for raw count data +#' +#' This function creates an exponentially increasing vector for given number +#' breaks between zero and some element of choice. It is particularly useful for +#' raw counts or raw counts per million. +#' +#' @param nBreaks Number of breaks to be generated +#' @param maxElement Maximum value of data entries +#' @export +computeBreaks <- function(nBreaks, variable) { + + maxElement <- max(variable, na.rm = TRUE) + if (length(unique(variable)) == 1) { + breaks <- c(0, 0.5, ifelse(maxElement < 1, 1, maxElement)) + } else { + coefSystem <- solve( + rbind(c(1, 1), c(1, (nBreaks - 1)))) %*% c(0, log(maxElement) + ) + coefExp <- c(exp(coefSystem[1]), coefSystem[2]) + breaks <- coefExp[1] * exp((1:(nBreaks - 1)) * coefExp[2]) + } + return(c(0, breaks)) +} \ No newline at end of file diff --git a/target/executable/report/create_report/template.Rmd b/target/executable/report/create_report/template.Rmd new file mode 100755 index 00000000..20f8c190 --- /dev/null +++ b/target/executable/report/create_report/template.Rmd @@ -0,0 +1,977 @@ +--- +title: "Exploratory Data Report" +date: "`r format(Sys.time(), '%d %B, %Y')`" +editor_options: + chunk_output_type: console +output: + oaStyle::html_report +# parameters which are overwritten by the script +params: + outputDir: 'output/' + esets: + - sample1.rds + - sample2.rds +--- + + + + + + + + + +```{r params, eval = TRUE, include = FALSE} +outputDir <- params$outputDir +esets <- params$esets +``` + + +```{r outputDir, echo = FALSE} +## Required: ABSOLUTE outputDir +outputDir <- file.path(outputDir) + +# When working on a windows computer it should be +# "/Users/..." instead of "C:/Users/..." +if (.Platform$OS.type == "windows") { + outputDir <- paste0( + "/", + paste( + unlist(strsplit(outputDir, split = "/"))[-1], collapse = "/" + ), + "/" + ) +} +``` + + + + +```{r optionsChunkDoNotModify, echo = FALSE, message = FALSE, warning=FALSE} + +## Chunk with options for knitr. This chunk should not be modified. +knitr::opts_chunk$set( + eval = TRUE, + echo = FALSE, + message = FALSE, + cache = FALSE, + warning = FALSE, + error = FALSE, + comment = NA, #"#", + tidy = FALSE, + collapse = TRUE, + out.width = "100%", + fig.width = 20, + fig.height = 10, + results = "asis") + +knitr::opts_knit$set(root.dir = getwd()) + +options(warn = 1, width = 200) + +``` + +```{r libraries_and_functions} +source("plateLayouts.R") +library(ComplexHeatmap) +library(data.table) +library(ggplot2) +library(knitr) +library(Biobase) +library(gridExtra) +library(RColorBrewer) +``` + + +```{r dataImport} + +# Create esetList +esetList <- sapply( + esets, simplify = FALSE, + USE.NAMES = TRUE, + function(eset_raw) { + if (!file.exists(eset_raw)) { + stop(paste0("Provided path '", eset_raw, "' is not a file.")) + } + eset <- readRDS(eset_raw) + } +) +pools <- sapply(esetList, function(eset) { + unique(eset$PoolName) +}) +names(esetList) <- unlist(pools) + +# Create qcData +pDataList <- lapply(esetList, function(eset) data.table(pData(eset))) +qcData <- rbindlist(pDataList, fill = TRUE) + +textVars <- "SampleName" +annotationVar <- "PoolName" + +if (!"SampleName" %in% names(qcData)) { + qcData[, SampleName := paste0(PoolName, "_", WellBC)] +} +qcData[, log10LibSize := round(log10(NumberOfInputReads))] +qcData[, (annotationVar) := lapply(.SD, as.factor), .SDcols = annotationVar] + + +colourList <- list() +Design_levels <- sort( + as.character(unique(qcData[, ..annotationVar][[1]])), + decreasing = TRUE +) + +if (length(Design_levels) == 1) { + colours <- c("#d6e0ff", "lightgrey") + names(colours) <- c(Design_levels, "Empty") + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +}else if (length(Design_levels) == 2) { + colours <- c("#d6e0ff", "#FF9999") + + names(colours) <- c(Design_levels) + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +} else if (length(Design_levels) <= 20) { + + if (length(Design_levels) > 12) { + colours <- c( + brewer.pal(12, "Set3"), + brewer.pal((length(Design_levels) - 12), + "Pastel2") + ) + } else { + colours <- c(brewer.pal(length(Design_levels), "Set3")) + } + + names(colours) <- c(Design_levels) + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +} else { + colours <- c("#d6e0ff") + names(colours) <- c("nonEmpty") + colourList[[annotVar]] <- list( + "colours" = colours, + "annotVar" = annotVar, + "text" = annotVar + ) +} +``` + +# Pool Description + +Per pool within this study, there are several pool layout plots shown, based on the + +* number of STAR input reads (= library size) + +* log10 transformed number of STAR input reads + +* number of detected UMIs + +* number of detected genes + +* number of chromosomal reads + +* percentage of ERCC + +* percentage of mitochondria + + +> The values for the different samples within each pool is expected to be comparable if the content of the different pools is equally diverse. + +```{r plateAnnotation, out.width = "100%",fig.width = 20, fig.height= 10} + +plateVars <- c("NumberOfInputReads", "log10LibSize", "NumberOfMappedReads", + "NumberOfChromReads", "NumberOfUMIs", "NumberOfGenes", + "pctMT", "pctERCC") + +breaksVars <- lapply( + plateVars, + function(var) { + computeBreaks(7, qcData[, ..var]) + } +) +names(breaksVars) <- plateVars + +for (pool in pools){ + cat("\n\n") + cat(paste0("## ", pool, " {.tabset} \n\n")) + poolData <- qcData[PoolName == pool] + lapply(plateVars, function(plateVar) { + cat("\n\n") + cat(sprintf("### %s {.unnumbered}", plateVar)) + cat("\n\n") + plateLayout( + poolData, valueVariable = plateVar, + textFontSize = 10, legendFontSize = 12, + plateName = pool, plot.title = "libSize - ", + legend.title = "libSize", breaks = breaksVars[[plateVar]] + ) + cat("\n\n") + }) + cat("\n\n") +} +``` + +
+ + +# Data Distributions + + +## Reads Distributions {.tabset} + +The 4 box plots below represent the distributions per pool of the different samples based on: + +* the number of STAR input reads + +* the number of STAR mapped reads + +* the percentage of STAR mapped reads + +* the number of detected genes + +> The distributions contribute to the QC metrics mentioned in Par 3. The higher these values, the better. +> The data range for the different plates is expected to be comparable if the content of the different plates is equally diverse. + + +### Number of Input Reads {.tabset .unnumbered} + +```{r settings_1} + +nColPlots = 1 +figHeight = 7 + +``` + +#### Distribution {.tabset .unnumbered} + + +```{r boxplots_input_plate, fig.height = figHeight} +ggplot( + qcData, + aes( + x = PoolName, + y = NumberOfInputReads, colour = PoolName + ) +) + geom_boxplot() + ylab("Number of Input Reads") + + ggtitle("Number of Input Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + + +### Number of Mapped Reads {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_mapped_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfMappedReads, colour = PoolName) +) + geom_boxplot() + ylab("Number of Mapped Reads") + + ggtitle("Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +#### pct Mapped Reads {.unnumbered} + +```{r boxplots_pctMapped_plate, fig.height = figHeight} +ggplot( + qcData, + aes(x = PoolName, y = PctMappedReads, colour = PoolName) +) + + geom_boxplot() + + ylab("pct Mapped Reads") + + ggtitle("pct Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### Number of Chromosomal Reads {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_chrom_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfChromReads, colour = PoolName) +) + geom_boxplot() + ylab("Number of Chromosomal Reads") + + ggtitle("Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + +#### pct Chromosomal Reads {.unnumbered} + +```{r boxplots_pctChrom_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = pctChrom, colour = PoolName) +) + geom_boxplot() + ylab("pct Chromosomal Reads") + + ggtitle("pct Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### Number of UMIs {.tabset .unnumbered} + +#### Distribution {.tabset .unnumbered} + + +```{r boxplots_umi_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfUMIs, colour = PoolName) +) + geom_boxplot() + ylab("Number of UMIs") + + ggtitle('Number of UMIs') + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + +#### Density distribution {.unnumbered} + +```{r density_numberOfUMIs} + +## Pre-filtering data exploration +dt_plot <- melt( + qcData, + id.vars = c("SampleName", "PoolName", "WellID"), + measure.vars = c("NumberOfInputReads", "NumberOfMappedReads", "NumberOfUMIs") +) + +readsDensity_plot <- ggplot(dt_plot, aes(value)) +readsDensity_plot <- readsDensity_plot + + geom_density(aes(fill = variable), alpha=0.8) + + facet_grid(~ PoolName, scales = "free_x", space = "fixed", drop = TRUE) + + geom_vline( + xintercept = 5e5, + linetype = "dashed", + color = "steelblue3", size = 2 + ) + + annotate( + "text", + x = 3.5e5, y = 2e-6, label = "500k", + angle = 90, color = "steelblue3", size = 10 + ) + + geom_vline( + xintercept = 1.5e6, linetype = "dashed", + color = "forestgreen", size = 2 + ) + + annotate( + "text", x = 1.35e6, y = 2e-6, label = "1.5M", + angle = 90, color = "forestgreen", size = 10 + ) + + labs( + title = "Density plot", + subtitle = paste0( + "# Samples with NumberOfMappedReads > 1.5M: ", + length(which(qcData$NumberOfMappedReads > 1.5e6)), + "\n# Samples with NumberOfUMIs > 500k: ", + length(which(qcData$NumberOfUMIs > 5e5)) + ), + caption = paste0("# Total samples (after removing empty): ", nrow(qcData)), + x = "Count", + fill = "Variable" + ) + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 5), + axis.text.x = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + plot.subtitle = element_text(size = 17), + plot.caption = element_text(size = 15), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.y = element_blank(), + axis.ticks.y = element_blank(), + axis.title.y = element_blank() + ) +readsDensity_plot + +``` + +### Number of Genes {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_genes_plate, fig.height = figHeight} +ggplot( + qcData, + aes(x = PoolName, y = NumberOfGenes, colour = PoolName) +) + + geom_boxplot() + ylab("Number of Genes") + + ggtitle("Number of Genes") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +## {.tabset .toc-ignore .unnumbered} + + +In addition, several plots are shown visualizing the efficiency of the reads-to-genes translation: + +* the number of input reads vs the number of mapped reads + +* the number of chromosomal reads vs the number of mapped reads + +* the number of mapped reads per UMI vs the number of mapped reads + +* the number of UNI vs the number of mapped reads + +* the number of mapped reads vs the number of genes + +* the number of chromosomal reads vs the number of genes + +* the number of mapped reads per UMI vs the number of genes + +### Mapping Efficiency {.tabset .unnumbered} + +#### Number of Input Reads {.unnumbered} + +```{r mapping_efficiency_1_plate, fig.height = 7} + +ggplot( + qcData, + aes(x = NumberOfInputReads, y = NumberOfMappedReads, colour = PoolName) +) + + geom_point() + + xlab("Number of Input Reads") + + ylab("Number of Mapped Reads") + + ggtitle("Number of Mapped Reads vs Number of Input Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + + +#### Number of Chromosomal Reads {.unnumbered} + +```{r mapping_efficiency_2_plate, fig.height = 7} + +ggplot( + qcData, + aes(x = NumberOfChromReads, y = NumberOfMappedReads, colour = PoolName) +) + geom_point() + + xlab("Number of Chromosomal Reads") + ylab("Number of Mapped Reads") + + ggtitle("Number of Chromosomal Reads vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) +) + +``` + + +#### Number of UMI {.unnumbered} + +```{r mapping_efficiency_4_plate, fig.height = 7} + +ggplot( + qcData, + aes(x =NumberOfUMIs, y = NumberOfMappedReads, colour = PoolName) +) + geom_point() + + ylab("Number of Mapped Reads") + xlab("Number of UMIs ") + + ggtitle("Number of UMIs vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + +### Counting Efficiency {.tabset .unnumbered} + +#### Number of Mapped Reads {.unnumbered} + +```{r gene_efficiency_1_plate, fig.height = 7} +ggplot( + qcData, + aes(x = NumberOfMappedReads, y = NumberOfGenes, colour = PoolName) +) + geom_point() + + ylab("Number of Genes") + xlab("Number of Mapped Reads") + + ggtitle("Number of Genes vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + +#### Number of Chromosomal Reads {.unnumbered} + +```{r gene_efficiency_2_plate, fig.height = 7} +ggplot( + qcData, + aes(x = NumberOfChromReads, y = NumberOfGenes, colour = PoolName) +) + geom_point() + + ylab("Number of Genes") + xlab("Number of Chromosomal Reads") + + ggtitle("Number of Genes vs Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + + + +## Sequencing Saturation {.tabset} + +The barplots below represent the sequencing saturation per sample as determined by STAR, split per pool. +The HT-RNAseq platform aims for shallow sequencing resulting in relatively low sequencing saturations of 10-20%. +In addition, the sequencing saturation vs the number of input reads is shown. + +### Sequencing Saturation {.unnumbered} + + + +```{r sequencingSaturation, fig.height = figHeight} + +ggplot( + qcData, + aes(x = WellID, y = SequencingSaturation, fill = PoolName) +) + geom_bar(stat = "identity", position = "dodge") + + xlab("Samples") + ggtitle("Sequencing Saturation per Sample") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(1, "lines"), + text = element_text(size = 10), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.text.y = element_text(size = 15), + axis.ticks.x = element_blank() + ) +``` + +### Sequencing Saturation - Input Reads {.unnumbered} + + +```{r sequencingSaturation_inputReads, fig.height = figHeight} + + +ggplot( + qcData, + aes(x = NumberOfInputReads, y = SequencingSaturation, colour = PoolName) +) + geom_point() + + ggtitle("Sequencing Saturation vs Number of Input Reads") + + theme(strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + +### Sequencing Saturation - Mapped Reads {.unnumbered} + +```{r sequencingSaturation_mappedReads, fig.height = figHeight} +ggplot( + qcData, + aes(x = NumberOfChromReads, y = SequencingSaturation, colour = PoolName) +) + geom_point() + + ggtitle("Sequencing Saturation vs Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size=10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size=18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) +) +``` + +
+ +## Genomic Origin {.tabset} + +The 3 boxplots below represent, per pool, the distributions of the percentage of reads mapping to: + +* chromosomal regions + +* mitochondrial regions + +* ERCC spike-ins + +The 4th plot summarises the above results across samples per pool. + +The 5th plot shows the percentage of reads mapped to the transcriptome (as counted by STAR). This measurement serves as a proxy for the percentage of reads mapped to exons. + +> The percentage ERCC contributes to the QC metrics mentioned in Par 3. This value is ideally as low as possible (but non-zero to ensure the they have been spiked in) and comparable for the different pools. + + + + +### pctChrom {.tabset .unnumbered} + + +```{r genomicOrigin_chrom_plate, fig.height = figHeight} + +ggplot( + qcData, aes(x = PoolName, y = pctChrom, colour = PoolName) +) + + geom_boxplot() + + ggtitle("pctChrom") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +### pctMT {.tabset .unnumbered} + +```{r genomicOrigin_mt_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = pctMT, colour = PoolName) +) + + geom_boxplot() + ggtitle("pctMT") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### pctERCC {.tabset .unnumbered} + + +```{r genomicOrigin_ercc_plate, fig.height = figHeight} +ggplot(qcData, aes(x = PoolName, y = pctERCC, colour = PoolName)) + + geom_boxplot() + + ggtitle("pctERCC") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +### Genomic Summary {.tabset .unnumbered} + + + +```{r genomicOrigin_summary_plate} +meanPctChromMTData <- qcData[, .( + "pctChrom" = median(pctChrom), + "pctMT" = median(pctMT), + "pctERCC" = median(pctERCC) +), by = PoolName] +meanPctChromMTDataLong <- melt( + meanPctChromMTData, + id.vars = "PoolName", + measure.vars = c("pctChrom", "pctMT", "pctERCC"), + variable.name = "Origin", value.name = "pct" +) +ggplot( + meanPctChromMTDataLong, + aes(fill = Origin, y = pct, x = PoolName)) + + geom_bar(position = "stack", stat = "identity") + + ggtitle("Genomic Origin") + + theme( + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + + + +# Depletion {.tabset} + +
+```{r depletion} + + +for (eset_name in pools) { + cat("\n\n") + cat(paste0("## ", eset_name, " {.unnumbered}")) + cat("\n\n") + + eset <- esetList[[eset_name]] + average_reads <- sort(apply(exprs(eset), 1, mean), decreasing = TRUE) + plotData <- data.table( + ENSGID = names(average_reads), + av_count = average_reads + ) + + gen_descript <- data.table( + ENSGID = eset@featureData@data$gene_id, + Description = eset@featureData@data$GENENAME + ) + order_gen_descript <- gen_descript[ + match(plotData$ENSGID, gen_descript$ENSGID), + ] + + g <- ggplot( + plotData[c(1:100)], + aes(x = reorder(ENSGID, -av_count), y = av_count) + ) + geom_bar(stat = "identity") + + theme( + axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size = 12), + axis.text.y = element_text(size = 12), + legend.text = element_text(size = 15), + legend.title = element_text(size = 15), + axis.title = element_text(size = 18), + plot.title = element_text(size = 20) + ) + ylab("Average Counts") + xlab("Genes") + + print(g) + + cat("\n\n") + cat("
") + cat("
") + + print(htmltools::tagList((DT::datatable(order_gen_descript[1:100, ])))) +} +``` +
+ + +
+
+
+
+ +# Glossary {.unnumbered} + + +## Read {.unlisted .unnumbered} + +A read is a oligonucleotide (a short RNA fragment) that has been sequenced. It consists of a fixed number of base pairs (bp) and therefore has a specific read length. + + + +## Input Read {.unlisted .unnumbered} + +Each read of the fastq file used as input to the STAR aligner is considered an input read. + + + +## Read With Valid Barcode {.unlisted .unnumbered} + +A read with a valid barcode is a read for which the barcode matches the white list of barcodes under the given restriction of the number of allowed mismatches. The number of reads with a valid barcode is lower or equal to the number of input reads. + + + +## Mapped Read {.unlisted .unnumbered} + +A read that has been aligned against the reference genome and for which one or more suitable matching locations have been found is a mapped read. Depending on the number of allowed mismatches this might or might not be be an exact match. The number of mapped reads is lower or equal to the number of reads with a valid barcode. + + + +## Uniquely Mapped Read {.unlisted .unnumbered} + +A read for which one and only one suitable matching location in the reference genome was found is an uniquely mapped read. The number of uniquely mapped reads is lower or equal to the number of mapped reads. + + + +## Counted Read {.unlisted .unnumbered} + +A mapped read will only be counted if it overlaps (1 nucleotide or more) with one and only one gene. The number of counted reads is lower or equal to the number of (uniquely) mapped reads. + + + +## UMIs {.unlisted .unnumbered} + +Unique molecular identifiers (UMI) are short sequences in order to uniquely tag each molecule in a sample library. Sequencing with UMIs allows bioinformatics software to filter out duplicate reads and PCR errors with a high level of accuracy and report unique reads. + +The reported UMIs is the number of UMIs among the set of reads that map to an unique gene, i.e the number of reads is deduplicated. + + + +## pctERCC {.unlisted .unnumbered} + +The percentage of reads mapping to the ERCC genes among the total number of **mapped** reads. + + + +## pctMT {.unlisted .unnumbered} + +The percentage of reads mapping to the MT genes among the total number of **mapped** reads. + + + +## Sequencing Saturation {.unlisted .unnumbered} + +The sequencing saturation is a measure of the fraction of library complexity. The inverse of one minus the sequencing saturation can be interpreted as the number of additional reads it would take to detect a new transcript. Consequently, a low sequencing saturation indicates a shallow sequencing in which a new transcript could be discovered with a few reads. + +
+
+
+
+ +
+![](OutputSTARsolo.png) +
+ +
+
diff --git a/target/executable/stats/combine_star_logs/.config.vsh.yaml b/target/executable/stats/combine_star_logs/.config.vsh.yaml index e87340e2..061a43f6 100644 --- a/target/executable/stats/combine_star_logs/.config.vsh.yaml +++ b/target/executable/stats/combine_star_logs/.config.vsh.yaml @@ -1,6 +1,21 @@ name: "combine_star_logs" namespace: "stats" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Arguments" arguments: @@ -183,8 +198,8 @@ build_info: output: "target/executable/stats/combine_star_logs" executable: "target/executable/stats/combine_star_logs/combine_star_logs" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/stats/combine_star_logs/combine_star_logs b/target/executable/stats/combine_star_logs/combine_star_logs index 7c36dead..84326014 100755 --- a/target/executable/stats/combine_star_logs/combine_star_logs +++ b/target/executable/stats/combine_star_logs/combine_star_logs @@ -10,6 +10,9 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (author, maintainer) set -e @@ -485,10 +488,11 @@ RUN apt-get update && \ RUN pip install --upgrade pip && \ pip install --upgrade --no-cache-dir "pandas" +LABEL org.opencontainers.image.authors="Dries Schaumont" LABEL org.opencontainers.image.description="Companion container for running component stats combine_star_logs" -LABEL org.opencontainers.image.created="2024-11-05T15:39:41Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER diff --git a/target/executable/stats/combine_star_logs/nextflow_labels.config b/target/executable/stats/combine_star_logs/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/stats/combine_star_logs/nextflow_labels.config +++ b/target/executable/stats/combine_star_logs/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/stats/generate_pool_statistics/.config.vsh.yaml b/target/executable/stats/generate_pool_statistics/.config.vsh.yaml index 09b52aef..1fb63c0c 100644 --- a/target/executable/stats/generate_pool_statistics/.config.vsh.yaml +++ b/target/executable/stats/generate_pool_statistics/.config.vsh.yaml @@ -1,6 +1,33 @@ name: "generate_pool_statistics" namespace: "stats" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -155,8 +182,8 @@ build_info: output: "target/executable/stats/generate_pool_statistics" executable: "target/executable/stats/generate_pool_statistics/generate_pool_statistics" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/stats/generate_pool_statistics/generate_pool_statistics b/target/executable/stats/generate_pool_statistics/generate_pool_statistics index 2b6b0a02..7e70eae6 100755 --- a/target/executable/stats/generate_pool_statistics/generate_pool_statistics +++ b/target/executable/stats/generate_pool_statistics/generate_pool_statistics @@ -10,6 +10,10 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (author, maintainer) +# * Marijke Van Moerbeke (contributor) set -e @@ -477,10 +481,11 @@ RUN apt-get update && \ RUN pip install --upgrade pip && \ pip install --upgrade --no-cache-dir "pandas" +LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component stats generate_pool_statistics" -LABEL org.opencontainers.image.created="2024-11-05T15:39:43Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:22Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER @@ -1073,6 +1078,8 @@ dep = { ### VIASH END +INDEX_COL = ["WellBC", "WellID"] + if __name__ == "__main__": ######### # nrReadsNrGenesPerChrom file @@ -1082,17 +1089,18 @@ if __name__ == "__main__": nr_reads_nr_genes_wells.append(pd.read_csv(nr_reads_nr_genes_file, header=0, delimiter="\\t", dtype={"WellBC": pd.StringDtype(), + "WellID": pd.StringDtype(), "Chr": pd.StringDtype(), "NumberOfReads": pd.UInt64Dtype(), "NumberOfGenes": pd.UInt64Dtype()})) nr_reads_nr_genes_pool = pd.concat(nr_reads_nr_genes_wells, ignore_index=True,) - total_nr_reads_per_chromosome = nr_reads_nr_genes_pool.pivot_table(index="WellBC", columns="Chr", + total_nr_reads_per_chromosome = nr_reads_nr_genes_pool.pivot_table(index=INDEX_COL, columns="Chr", values=["NumberOfReads"], fill_value=0, aggfunc="sum").droplevel(0, axis=1) total_nr_reads_per_chromosome.columns.name = None ##### Total number of genes from all chromosomes - total_nr_genes = nr_reads_nr_genes_pool.loc[:,['WellBC', 'NumberOfGenes']].groupby("WellBC").sum() + total_nr_genes = nr_reads_nr_genes_pool.loc[:, INDEX_COL + ['NumberOfGenes']].groupby(["WellBC", "WellID"]).sum() ##### Total counts across (irrespective of chromosome) total_sum_of_reads = total_nr_reads_per_chromosome.sum(numeric_only=True, axis=1) @@ -1141,10 +1149,10 @@ if __name__ == "__main__": **cols_to_add ) - total_nr_reads_per_chromosome.reset_index(names="WellBC")\\ + total_nr_reads_per_chromosome.reset_index(names=INDEX_COL)\\ .to_csv(par["nrReadsNrGenesPerChromPool"], sep="\\t", header=True, index=False, float_format="%g", - columns=("WellBC",) + tuple(chromosome_names) + tuple(cols_to_add.keys()) + columns=tuple(INDEX_COL) + tuple(chromosome_names) + tuple(cols_to_add.keys()) ) VIASHMAIN python -B "\$tempscript" & diff --git a/target/executable/stats/generate_pool_statistics/nextflow_labels.config b/target/executable/stats/generate_pool_statistics/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/stats/generate_pool_statistics/nextflow_labels.config +++ b/target/executable/stats/generate_pool_statistics/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/executable/stats/generate_well_statistics/.config.vsh.yaml b/target/executable/stats/generate_well_statistics/.config.vsh.yaml index 87ae083e..394cca74 100644 --- a/target/executable/stats/generate_well_statistics/.config.vsh.yaml +++ b/target/executable/stats/generate_well_statistics/.config.vsh.yaml @@ -1,6 +1,33 @@ name: "generate_well_statistics" namespace: "stats" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -25,6 +52,15 @@ argument_groups: direction: "input" multiple: false multiple_sep: ";" + - type: "string" + name: "--well_id" + description: "ID of this well. Only used to add a metadata column to the output\ + \ files.\n" + info: null + required: true + direction: "input" + multiple: false + multiple_sep: ";" - type: "file" name: "--processedBAMFile" description: "Path to a .tsv file listing, per read in the BAM file,\nthe value\ @@ -226,8 +262,8 @@ build_info: output: "target/executable/stats/generate_well_statistics" executable: "target/executable/stats/generate_well_statistics/generate_well_statistics" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/executable/stats/generate_well_statistics/generate_well_statistics b/target/executable/stats/generate_well_statistics/generate_well_statistics index d0b797e2..add70704 100755 --- a/target/executable/stats/generate_well_statistics/generate_well_statistics +++ b/target/executable/stats/generate_well_statistics/generate_well_statistics @@ -10,6 +10,10 @@ # authors of this component should specify the license in the header of such # files, or include a separate license file detailing the licenses of all included # files. +# +# Component authors: +# * Dries Schaumont (author, maintainer) +# * Marijke Van Moerbeke (contributor) set -e @@ -187,6 +191,10 @@ function ViashHelp { echo " metadata" echo " column to all output files." echo "" + echo " --well_id" + echo " type: string, required parameter" + echo " ID of this well. Only used to add a metadata column to the output files." + echo "" echo " --processedBAMFile" echo " type: file, output, file must exist" echo " default: processedBamFile.txt" @@ -510,10 +518,11 @@ RUN apt-get update && \ RUN pip install --upgrade pip && \ pip install --upgrade --no-cache-dir "pysam" "pandas" +LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke" LABEL org.opencontainers.image.description="Companion container for running component stats generate_well_statistics" -LABEL org.opencontainers.image.created="2024-11-05T15:39:43Z" +LABEL org.opencontainers.image.created="2024-12-17T13:58:23Z" LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq" -LABEL org.opencontainers.image.revision="65dd41d8b1b4a307735c72320c96c0880c75f17f" +LABEL org.opencontainers.image.revision="82647a421dae521a9563f7f02050f13a1319eb4a" LABEL org.opencontainers.image.version="main" VIASHDOCKER @@ -675,6 +684,17 @@ while [[ $# -gt 0 ]]; do VIASH_PAR_BARCODE=$(ViashRemoveFlags "$1") shift 1 ;; + --well_id) + [ -n "$VIASH_PAR_WELL_ID" ] && ViashError Bad arguments for option \'--well_id\': \'$VIASH_PAR_WELL_ID\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_PAR_WELL_ID="$2" + [ $# -lt 2 ] && ViashError Not enough arguments passed to --well_id. Use "--help" to get more information on the parameters. && exit 1 + shift 2 + ;; + --well_id=*) + [ -n "$VIASH_PAR_WELL_ID" ] && ViashError Bad arguments for option \'--well_id=*\': \'$VIASH_PAR_WELL_ID\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 + VIASH_PAR_WELL_ID=$(ViashRemoveFlags "$1") + shift 1 + ;; --processedBAMFile) [ -n "$VIASH_PAR_PROCESSEDBAMFILE" ] && ViashError Bad arguments for option \'--processedBAMFile\': \'$VIASH_PAR_PROCESSEDBAMFILE\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1 VIASH_PAR_PROCESSEDBAMFILE="$2" @@ -906,6 +926,10 @@ if [ -z ${VIASH_PAR_BARCODE+x} ]; then ViashError '--barcode' is a required argument. Use "--help" to get more information on the parameters. exit 1 fi +if [ -z ${VIASH_PAR_WELL_ID+x} ]; then + ViashError '--well_id' is a required argument. Use "--help" to get more information on the parameters. + exit 1 +fi if [ -z ${VIASH_META_NAME+x} ]; then ViashError 'name' is a required argument. Use "--help" to get more information on the parameters. exit 1 @@ -1164,6 +1188,7 @@ import logging par = { 'input': $( if [ ! -z ${VIASH_PAR_INPUT+x} ]; then echo "r'${VIASH_PAR_INPUT//\'/\'\"\'\"r\'}'"; else echo None; fi ), 'barcode': $( if [ ! -z ${VIASH_PAR_BARCODE+x} ]; then echo "r'${VIASH_PAR_BARCODE//\'/\'\"\'\"r\'}'"; else echo None; fi ), + 'well_id': $( if [ ! -z ${VIASH_PAR_WELL_ID+x} ]; then echo "r'${VIASH_PAR_WELL_ID//\'/\'\"\'\"r\'}'"; else echo None; fi ), 'processedBAMFile': $( if [ ! -z ${VIASH_PAR_PROCESSEDBAMFILE+x} ]; then echo "r'${VIASH_PAR_PROCESSEDBAMFILE//\'/\'\"\'\"r\'}'"; else echo None; fi ), 'nrReadsNrGenesPerChrom': $( if [ ! -z ${VIASH_PAR_NRREADSNRGENESPERCHROM+x} ]; then echo "r'${VIASH_PAR_NRREADSNRGENESPERCHROM//\'/\'\"\'\"r\'}'"; else echo None; fi ), 'nrReadsNrUMIsPerCB': $( if [ ! -z ${VIASH_PAR_NRREADSNRUMISPERCB+x} ]; then echo "r'${VIASH_PAR_NRREADSNRUMISPERCB//\'/\'\"\'\"r\'}'"; else echo None; fi ), @@ -1218,11 +1243,11 @@ if __name__ == "__main__": columns=tags_selection) tag_dataframe_to_write = tag_dataframe.copy() logger.info("Done reading BAM file. Found %i entries", tag_dataframe.shape[0]) - tag_dataframe.assign(WellBC=par["barcode"])\\ + tag_dataframe.assign(WellBC=par["barcode"], WellID=par["well_id"])\\ .reset_index(names="Chr")\\ .to_csv(par["processedBAMFile"], sep="\\t", na_rep="", header=True, index=False, - columns=("WellBC", "Chr") + tags_selection) + columns=("WellBC", "WellID", "Chr") + tags_selection) logger.info("Constructing of dataframe done.") # Number of genes that had a read mapped to them per chromosome, # and the number of reads mapped to those genes per chromosome. @@ -1232,19 +1257,19 @@ if __name__ == "__main__": ) logger.info("Done calculating number of reads per gene and per chromesome. Writing to %s", par['nrReadsNrGenesPerChrom']) - nr_reads_nr_genes.reset_index(names="Chr").assign(WellBC=par["barcode"])\\ + nr_reads_nr_genes.reset_index(names="Chr").assign(WellBC=par["barcode"], WellID=par["well_id"])\\ .to_csv(par["nrReadsNrGenesPerChrom"], sep="\\t", header=True, index=False, - columns=("WellBC", "Chr", "NumberOfReads", "NumberOfGenes")) + columns=("WellBC", "WellID", "Chr", "NumberOfReads", "NumberOfGenes")) # Number of reads mapped to the reference, grouped by UMI nr_read_per_umi = tag_dataframe.groupby('UB').size()\\ .drop("", errors="ignore").sort_values(ascending=False).head(100) nr_read_per_umi_df = nr_read_per_umi.to_frame(name="N") logger.info("Done calculating number of mapped reads per UMI, writing to %s", par["umiFreqTop"]) - nr_read_per_umi_df.assign(WellBC=par["barcode"]).reset_index(names="UB")\\ + nr_read_per_umi_df.assign(WellBC=par["barcode"], WellID=par["well_id"]).reset_index(names="UB")\\ .to_csv(par["umiFreqTop"], header=True, sep="\\t", - index=False, columns=("WellBC", "UB", "N")) + index=False, columns=("WellBC", "WellID", "UB", "N")) # Total number of mapped reads and total number of UMIs (not grouped per chromosome) nr_reads_and_umi_per_barcode = tag_dataframe.groupby(by="CB").agg( @@ -1253,9 +1278,9 @@ if __name__ == "__main__": ) logger.info("Done calculating number of mapped reads and number of UMIs per Cell Barcode, writing to %s", par["nrReadsNrUMIsPerCB"]) - nr_reads_and_umi_per_barcode.assign(WellBC=par["barcode"]).reset_index(names="CB")\\ + nr_reads_and_umi_per_barcode.assign(WellBC=par["barcode"], WellID=par["well_id"]).reset_index(names="CB")\\ .to_csv(par["nrReadsNrUMIsPerCB"], sep="\\t", header=True, - index=False, columns=("WellBC", "CB", "NumberOfReads", "nrUMIs")) + index=False, columns=("WellBC", "WellID", "CB", "NumberOfReads", "nrUMIs")) logger.info("Finished!") VIASHMAIN python -B "\$tempscript" & diff --git a/target/executable/stats/generate_well_statistics/nextflow_labels.config b/target/executable/stats/generate_well_statistics/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/executable/stats/generate_well_statistics/nextflow_labels.config +++ b/target/executable/stats/generate_well_statistics/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/eset/create_eset/.config.vsh.yaml b/target/nextflow/eset/create_eset/.config.vsh.yaml index a54d5449..fcc19fad 100644 --- a/target/nextflow/eset/create_eset/.config.vsh.yaml +++ b/target/nextflow/eset/create_eset/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "create_eset" namespace: "eset" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "author" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -194,8 +220,8 @@ build_info: output: "target/nextflow/eset/create_eset" executable: "target/nextflow/eset/create_eset/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/eset/create_eset/main.nf b/target/nextflow/eset/create_eset/main.nf index bebb5acc..921c8dd8 100644 --- a/target/nextflow/eset/create_eset/main.nf +++ b/target/nextflow/eset/create_eset/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) +// * Marijke Van Moerbeke (author) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2811,49 @@ meta = [ "name" : "create_eset", "namespace" : "eset", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "author" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -3043,8 +3090,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/eset/create_eset", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/eset/create_eset/nextflow.config b/target/nextflow/eset/create_eset/nextflow.config index 224ef5ea..25f89fd7 100644 --- a/target/nextflow/eset/create_eset/nextflow.config +++ b/target/nextflow/eset/create_eset/nextflow.config @@ -3,6 +3,7 @@ manifest { mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' version = 'main' + author = 'Dries Schaumont, Marijke Van Moerbeke' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/eset/create_eset/nextflow_labels.config b/target/nextflow/eset/create_eset/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/eset/create_eset/nextflow_labels.config +++ b/target/nextflow/eset/create_eset/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/eset/create_eset/nextflow_schema.json b/target/nextflow/eset/create_eset/nextflow_schema.json index 84b5f12d..1e6f217e 100644 --- a/target/nextflow/eset/create_eset/nextflow_schema.json +++ b/target/nextflow/eset/create_eset/nextflow_schema.json @@ -60,7 +60,7 @@ "description": "Type: `file`, required, default: `$id.$key.output.rds`. ", "help_text": "Type: `file`, required, default: `$id.$key.output.rds`. " , - "default": "$id.$key.output.rds" + "default":"$id.$key.output.rds" } diff --git a/target/nextflow/eset/create_fdata/.config.vsh.yaml b/target/nextflow/eset/create_fdata/.config.vsh.yaml index 99a19dcc..29aceed1 100644 --- a/target/nextflow/eset/create_fdata/.config.vsh.yaml +++ b/target/nextflow/eset/create_fdata/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "create_fdata" namespace: "eset" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -151,8 +177,8 @@ build_info: output: "target/nextflow/eset/create_fdata" executable: "target/nextflow/eset/create_fdata/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/eset/create_fdata/main.nf b/target/nextflow/eset/create_fdata/main.nf index 0948b6b0..5b08c223 100644 --- a/target/nextflow/eset/create_fdata/main.nf +++ b/target/nextflow/eset/create_fdata/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) +// * Marijke Van Moerbeke (contributor) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2811,49 @@ meta = [ "name" : "create_fdata", "namespace" : "eset", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "contributor" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -2997,8 +3044,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/eset/create_fdata", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/eset/create_fdata/nextflow.config b/target/nextflow/eset/create_fdata/nextflow.config index 9487f5c3..755e3ee5 100644 --- a/target/nextflow/eset/create_fdata/nextflow.config +++ b/target/nextflow/eset/create_fdata/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'Create a fdata file\n' + author = 'Dries Schaumont, Marijke Van Moerbeke' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/eset/create_fdata/nextflow_labels.config b/target/nextflow/eset/create_fdata/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/eset/create_fdata/nextflow_labels.config +++ b/target/nextflow/eset/create_fdata/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/eset/create_fdata/nextflow_schema.json b/target/nextflow/eset/create_fdata/nextflow_schema.json index 1917415c..cde29031 100644 --- a/target/nextflow/eset/create_fdata/nextflow_schema.json +++ b/target/nextflow/eset/create_fdata/nextflow_schema.json @@ -30,7 +30,7 @@ "description": "Type: `file`, default: `$id.$key.output.txt`. Tab-delimited text file containing information about the \u0027gene\u0027 or \u0027transcript\u0027\nentries from the input GTF file", "help_text": "Type: `file`, default: `$id.$key.output.txt`. Tab-delimited text file containing information about the \u0027gene\u0027 or \u0027transcript\u0027\nentries from the input GTF file. The \u0027transcript\u0027 entries are used in case the source\nof the GTF was \u0027refGene\u0027 or \u0027ncbiRefSeq\u0027. \n" , - "default": "$id.$key.output.txt" + "default":"$id.$key.output.txt" } diff --git a/target/nextflow/eset/create_pdata/.config.vsh.yaml b/target/nextflow/eset/create_pdata/.config.vsh.yaml index 64fab900..3e7dc011 100644 --- a/target/nextflow/eset/create_pdata/.config.vsh.yaml +++ b/target/nextflow/eset/create_pdata/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "create_pdata" namespace: "eset" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -165,8 +191,8 @@ build_info: output: "target/nextflow/eset/create_pdata" executable: "target/nextflow/eset/create_pdata/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/eset/create_pdata/main.nf b/target/nextflow/eset/create_pdata/main.nf index 6c0a3e8f..12c25cb5 100644 --- a/target/nextflow/eset/create_pdata/main.nf +++ b/target/nextflow/eset/create_pdata/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) +// * Marijke Van Moerbeke (contributor) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2811,49 @@ meta = [ "name" : "create_pdata", "namespace" : "eset", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "contributor" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -3011,8 +3058,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/eset/create_pdata", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", @@ -3117,7 +3164,7 @@ def main(par): logger.info("Reads per gene and chromosome table contains information for the following barcodes: %s", ", ".join(reads_and_genes_per_chr_stats.index)) logger.info("Filtering mapping statistics file columns.") - cols_to_keep = ("NumberOfMTReads", "pctMT", "NumberOfERCCReads", + cols_to_keep = ("WellID", "NumberOfMTReads", "pctMT", "NumberOfERCCReads", "pctERCC", "NumberOfChromReads", "pctChrom") try: reads_and_genes_per_chr_stats = reads_and_genes_per_chr_stats.loc[:,cols_to_keep] diff --git a/target/nextflow/eset/create_pdata/nextflow.config b/target/nextflow/eset/create_pdata/nextflow.config index b61caab6..1264db0a 100644 --- a/target/nextflow/eset/create_pdata/nextflow.config +++ b/target/nextflow/eset/create_pdata/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'Create a pdata file by combining the mapping statistics \n' + author = 'Dries Schaumont, Marijke Van Moerbeke' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/eset/create_pdata/nextflow_labels.config b/target/nextflow/eset/create_pdata/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/eset/create_pdata/nextflow_labels.config +++ b/target/nextflow/eset/create_pdata/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/eset/create_pdata/nextflow_schema.json b/target/nextflow/eset/create_pdata/nextflow_schema.json index fd9b1cbb..e7a40906 100644 --- a/target/nextflow/eset/create_pdata/nextflow_schema.json +++ b/target/nextflow/eset/create_pdata/nextflow_schema.json @@ -40,7 +40,7 @@ "description": "Type: `file`, default: `$id.$key.output.txt`. ", "help_text": "Type: `file`, default: `$id.$key.output.txt`. " , - "default": "$id.$key.output.txt" + "default":"$id.$key.output.txt" } diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml b/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml index 61f654fb..7e160cdc 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml @@ -1,6 +1,21 @@ name: "check_eset" namespace: "integration_test_components/htrnaseq" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Inputs" arguments: @@ -133,8 +148,8 @@ build_info: output: "target/nextflow/integration_test_components/htrnaseq/check_eset" executable: "target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf b/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf index c3f99e44..d20465e6 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf @@ -8,6 +8,9 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2810,30 @@ meta = [ "name" : "check_eset", "namespace" : "integration_test_components/htrnaseq", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Inputs", @@ -2970,8 +2997,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/integration_test_components/htrnaseq/check_eset", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", @@ -3191,6 +3218,7 @@ stopifnot(identical(sampleNames(sample_1_result), expected_sample_names)) expected_var_labels <- c( "WellBC", + "WellID", "NumberOfMTReads", "pctMT", "NumberOfERCCReads", diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow.config b/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow.config index be8d457d..be0865e9 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow.config +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'This component test the ExpressionSet object as output by the main pipeline.' + author = 'Dries Schaumont' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_labels.config b/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_labels.config +++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/parallel_map/.config.vsh.yaml b/target/nextflow/parallel_map/.config.vsh.yaml index 59270876..0b62070c 100644 --- a/target/nextflow/parallel_map/.config.vsh.yaml +++ b/target/nextflow/parallel_map/.config.vsh.yaml @@ -1,5 +1,32 @@ name: "parallel_map" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Toni Verbeiren" + roles: + - "author" + - "maintainer" + info: + role: "Core Team Member" + links: + github: "tverbeiren" + linkedin: "verbeiren" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist and CEO" argument_groups: - name: "Input arguments" arguments: @@ -237,8 +264,8 @@ build_info: output: "target/nextflow/parallel_map" executable: "target/nextflow/parallel_map/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/parallel_map/main.nf b/target/nextflow/parallel_map/main.nf index ffc031e8..d2a91168 100644 --- a/target/nextflow/parallel_map/main.nf +++ b/target/nextflow/parallel_map/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) +// * Toni Verbeiren (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -2806,6 +2810,50 @@ meta = [ "config": processConfig(readJsonBlob('''{ "name" : "parallel_map", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Toni Verbeiren", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "role" : "Core Team Member", + "links" : { + "github" : "tverbeiren", + "linkedin" : "verbeiren" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist and CEO" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Input arguments", @@ -3100,8 +3148,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/parallel_map", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/parallel_map/nextflow.config b/target/nextflow/parallel_map/nextflow.config index c54fbac9..278861d4 100644 --- a/target/nextflow/parallel_map/nextflow.config +++ b/target/nextflow/parallel_map/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n' + author = 'Dries Schaumont, Toni Verbeiren' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/parallel_map/nextflow_labels.config b/target/nextflow/parallel_map/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/parallel_map/nextflow_labels.config +++ b/target/nextflow/parallel_map/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/parallel_map/nextflow_schema.json b/target/nextflow/parallel_map/nextflow_schema.json index 1830bf16..98abd686 100644 --- a/target/nextflow/parallel_map/nextflow_schema.json +++ b/target/nextflow/parallel_map/nextflow_schema.json @@ -90,7 +90,7 @@ "description": "Type: `string`, default: `10000000000`. ", "help_text": "Type: `string`, default: `10000000000`. " , - "default": "10000000000" + "default":"10000000000" } @@ -111,7 +111,7 @@ "description": "Type: `integer`, default: `1`. Number of threads to use for a single STAR execution", "help_text": "Type: `integer`, default: `1`. Number of threads to use for a single STAR execution." , - "default": "1" + "default":1 } @@ -132,7 +132,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.output_*./*`, multiple_sep: `\";\"`. Location of the output folders, 1 folder per barcode", "help_text": "Type: List of `file`, required, default: `$id.$key.output_*./*`, multiple_sep: `\";\"`. Location of the output folders, 1 folder per barcode. The value used\nfor this argument must contain a \u0027*\u0027, which will be replaced with the\nbarcode to form the final output location for that barcode.\n" , - "default": "$id.$key.output_*./*" + "default":"$id.$key.output_*./*" } @@ -143,7 +143,7 @@ "description": "Type: `file`, default: `$id.$key.joblog.txt`. Where to store the log file listing all the jobs", "help_text": "Type: `file`, default: `$id.$key.joblog.txt`. Where to store the log file listing all the jobs." , - "default": "$id.$key.joblog.txt" + "default":"$id.$key.joblog.txt" } diff --git a/target/nextflow/report/create_report/.config.vsh.yaml b/target/nextflow/report/create_report/.config.vsh.yaml new file mode 100644 index 00000000..fff208e5 --- /dev/null +++ b/target/nextflow/report/create_report/.config.vsh.yaml @@ -0,0 +1,235 @@ +name: "create_report" +namespace: "report" +version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "author" + - "maintainer" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" +argument_groups: +- name: "Arguments" + arguments: + - type: "file" + name: "--eset" + info: null + must_exist: true + create_parent: true + required: true + direction: "input" + multiple: true + multiple_sep: ";" + - type: "file" + name: "--output_report" + info: null + example: + - "report.html" + must_exist: true + create_parent: true + required: true + direction: "output" + multiple: false + multiple_sep: ";" +resources: +- type: "r_script" + path: "script.R" + is_executable: true +- type: "r_script" + path: "template.Rmd" + is_executable: true +- type: "r_script" + path: "plateLayouts.R" + is_executable: true +- type: "file" + path: "OutputSTARsolo.png" +- type: "file" + path: "nextflow_labels.config" + dest: "nextflow_labels.config" +description: "Create a basic QC report in HTML format based on a number of esets.\n" +test_resources: +- type: "r_script" + path: "test.R" + is_executable: true +- type: "file" + path: "test_data" +info: null +status: "enabled" +requirements: + commands: + - "ps" +license: "MIT" +links: + repository: "https://github.com/viash-hub/htrnaseq" +runners: +- type: "executable" + id: "executable" + docker_setup_strategy: "ifneedbepullelsecachedbuild" +- type: "nextflow" + id: "nextflow" + directives: + tag: "$id" + auto: + simplifyInput: true + simplifyOutput: false + transcript: false + publish: false + config: + labels: + mem1gb: "memory = 1000000000.B" + mem2gb: "memory = 2000000000.B" + mem5gb: "memory = 5000000000.B" + mem10gb: "memory = 10000000000.B" + mem20gb: "memory = 20000000000.B" + mem50gb: "memory = 50000000000.B" + mem100gb: "memory = 100000000000.B" + mem200gb: "memory = 200000000000.B" + mem500gb: "memory = 500000000000.B" + mem1tb: "memory = 1000000000000.B" + mem2tb: "memory = 2000000000000.B" + mem5tb: "memory = 5000000000000.B" + mem10tb: "memory = 10000000000000.B" + mem20tb: "memory = 20000000000000.B" + mem50tb: "memory = 50000000000000.B" + mem100tb: "memory = 100000000000000.B" + mem200tb: "memory = 200000000000000.B" + mem500tb: "memory = 500000000000000.B" + mem1gib: "memory = 1073741824.B" + mem2gib: "memory = 2147483648.B" + mem4gib: "memory = 4294967296.B" + mem8gib: "memory = 8589934592.B" + mem16gib: "memory = 17179869184.B" + mem32gib: "memory = 34359738368.B" + mem64gib: "memory = 68719476736.B" + mem128gib: "memory = 137438953472.B" + mem256gib: "memory = 274877906944.B" + mem512gib: "memory = 549755813888.B" + mem1tib: "memory = 1099511627776.B" + mem2tib: "memory = 2199023255552.B" + mem4tib: "memory = 4398046511104.B" + mem8tib: "memory = 8796093022208.B" + mem16tib: "memory = 17592186044416.B" + mem32tib: "memory = 35184372088832.B" + mem64tib: "memory = 70368744177664.B" + mem128tib: "memory = 140737488355328.B" + mem256tib: "memory = 281474976710656.B" + mem512tib: "memory = 562949953421312.B" + cpu1: "cpus = 1" + cpu2: "cpus = 2" + cpu5: "cpus = 5" + cpu10: "cpus = 10" + cpu20: "cpus = 20" + cpu50: "cpus = 50" + cpu100: "cpus = 100" + cpu200: "cpus = 200" + cpu500: "cpus = 500" + cpu1000: "cpus = 1000" + script: + - "includeConfig(\"nextflow_labels.config\")" + debug: false + container: "docker" +engines: +- type: "docker" + id: "docker" + image: "rocker/r2u:24.04" + target_registry: "images.viash-hub.com" + target_tag: "main" + namespace_separator: "/" + setup: + - type: "apt" + packages: + - "procps" + - "pandoc" + interactive: false + - type: "r" + cran: + - "ggplot2" + - "knitr" + - "gridExtra" + - "RColorBrewer" + - "processx" + - "whisker" + - "rmarkdown" + - "bookdown" + - "data.table" + - "platetools" + - "htmltools" + - "DT" + - "logger" + - "bit64" + bioc: + - "Biobase" + - "ComplexHeatmap" + script: + - "install.packages(\"oaStyle\", repos = c(rdepot = \"https://repos.openanalytics.eu/repo/public\"\ + , getOption(\"repos\")))" + bioc_force_install: false + test_setup: + - type: "r" + packages: + - "testthat" + - "R.utils" + bioc_force_install: false + entrypoint: [] + cmd: null +- type: "native" + id: "native" +build_info: + config: "src/report/config.vsh.yaml" + runner: "nextflow" + engine: "docker|native" + output: "target/nextflow/report/create_report" + executable: "target/nextflow/report/create_report/main.nf" + viash_version: "0.9.0" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" +package_config: + name: "htrnaseq" + version: "main" + description: "High-throughput pipeline [WIP]\n" + info: + test_resources: + - path: "gs://viash-hub-test-data/htrnaseq/v1/" + dest: "resources_test" + viash_version: "0.9.0" + source: "src" + target: "target" + config_mods: + - ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].config.script\ + \ := 'includeConfig(\"nextflow_labels.config\")'\n.resources += {path: '/src/config/labels.config',\ + \ dest: 'nextflow_labels.config'}\n" + - ".engines += { type: \"native\" }" + - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'" + - ".engines[.type == 'docker'].target_tag := 'main'" + keywords: + - "bioinformatics" + - "sequence" + - "high-throughput" + - "mapping" + - "counting" + - "pipeline" + license: "MIT" + organization: "vsh" + links: + repository: "https://github.com/viash-hub/htrnaseq" + issue_tracker: "https://github.com/viash-hub/htrnaseq/issues" diff --git a/target/nextflow/report/create_report/OutputSTARsolo.png b/target/nextflow/report/create_report/OutputSTARsolo.png new file mode 100644 index 00000000..cb77d8e0 Binary files /dev/null and b/target/nextflow/report/create_report/OutputSTARsolo.png differ diff --git a/target/nextflow/report/create_report/main.nf b/target/nextflow/report/create_report/main.nf new file mode 100644 index 00000000..b282fcf7 --- /dev/null +++ b/target/nextflow/report/create_report/main.nf @@ -0,0 +1,3683 @@ +// create_report main +// +// This wrapper script is auto-generated by viash 0.9.0 and is thus a derivative +// work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data +// Intuitive. +// +// The component may contain files which fall under a different license. The +// authors of this component should specify the license in the header of such +// files, or include a separate license file detailing the licenses of all included +// files. +// +// Component authors: +// * Dries Schaumont (maintainer) +// * Marijke Van Moerbeke (author, maintainer) + +//////////////////////////// +// VDSL3 helper functions // +//////////////////////////// + +// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_checkArgumentType.nf' +class UnexpectedArgumentTypeException extends Exception { + String errorIdentifier + String stage + String plainName + String expectedClass + String foundClass + + // ${key ? " in module '$key'" : ""}${id ? " id '$id'" : ""} + UnexpectedArgumentTypeException(String errorIdentifier, String stage, String plainName, String expectedClass, String foundClass) { + super("Error${errorIdentifier ? " $errorIdentifier" : ""}:${stage ? " $stage" : "" } argument '${plainName}' has the wrong type. " + + "Expected type: ${expectedClass}. Found type: ${foundClass}") + this.errorIdentifier = errorIdentifier + this.stage = stage + this.plainName = plainName + this.expectedClass = expectedClass + this.foundClass = foundClass + } +} + +/** + * Checks if the given value is of the expected type. If not, an exception is thrown. + * + * @param stage The stage of the argument (input or output) + * @param par The parameter definition + * @param value The value to check + * @param errorIdentifier The identifier to use in the error message + * @return The value, if it is of the expected type + * @throws UnexpectedArgumentTypeException If the value is not of the expected type +*/ +def _checkArgumentType(String stage, Map par, Object value, String errorIdentifier) { + // expectedClass will only be != null if value is not of the expected type + def expectedClass = null + def foundClass = null + + // todo: split if need be + + if (!par.required && value == null) { + expectedClass = null + } else if (par.multiple) { + if (value !instanceof Collection) { + value = [value] + } + + // split strings + value = value.collectMany{ val -> + if (val instanceof String) { + // collect() to ensure that the result is a List and not simply an array + val.split(par.multiple_sep).collect() + } else { + [val] + } + } + + // process globs + if (par.type == "file" && par.direction == "input") { + value = value.collect{ it instanceof String ? file(it, hidden: true) : it }.flatten() + } + + // check types of elements in list + try { + value = value.collect { listVal -> + _checkArgumentType(stage, par + [multiple: false], listVal, errorIdentifier) + } + } catch (UnexpectedArgumentTypeException e) { + expectedClass = "List[${e.expectedClass}]" + foundClass = "List[${e.foundClass}]" + } + } else if (par.type == "string") { + // cast to string if need be + if (value instanceof GString) { + value = value.toString() + } + expectedClass = value instanceof String ? null : "String" + } else if (par.type == "integer") { + // cast to integer if need be + if (value instanceof String) { + try { + value = value.toInteger() + } catch (NumberFormatException e) { + // do nothing + } + } + if (value instanceof java.math.BigInteger) { + value = value.intValue() + } + expectedClass = value instanceof Integer ? null : "Integer" + } else if (par.type == "long") { + // cast to long if need be + if (value instanceof String) { + try { + value = value.toLong() + } catch (NumberFormatException e) { + // do nothing + } + } + if (value instanceof Integer) { + value = value.toLong() + } + expectedClass = value instanceof Long ? null : "Long" + } else if (par.type == "double") { + // cast to double if need be + if (value instanceof String) { + try { + value = value.toDouble() + } catch (NumberFormatException e) { + // do nothing + } + } + if (value instanceof java.math.BigDecimal) { + value = value.doubleValue() + } + if (value instanceof Float) { + value = value.toDouble() + } + expectedClass = value instanceof Double ? null : "Double" + } else if (par.type == "boolean" | par.type == "boolean_true" | par.type == "boolean_false") { + // cast to boolean if need be + if (value instanceof String) { + def valueLower = value.toLowerCase() + if (valueLower == "true") { + value = true + } else if (valueLower == "false") { + value = false + } + } + expectedClass = value instanceof Boolean ? null : "Boolean" + } else if (par.type == "file" && (par.direction == "input" || stage == "output")) { + // cast to path if need be + if (value instanceof String) { + value = file(value, hidden: true) + } + if (value instanceof File) { + value = value.toPath() + } + expectedClass = value instanceof Path ? null : "Path" + } else if (par.type == "file" && stage == "input" && par.direction == "output") { + // cast to string if need be + if (value instanceof GString) { + value = value.toString() + } + expectedClass = value instanceof String ? null : "String" + } else { + // didn't find a match for par.type + expectedClass = par.type + } + + if (expectedClass != null) { + if (foundClass == null) { + foundClass = value.getClass().getName() + } + throw new UnexpectedArgumentTypeException(errorIdentifier, stage, par.plainName, expectedClass, foundClass) + } + + return value +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processInputValues.nf' +Map _processInputValues(Map inputs, Map config, String id, String key) { + if (!workflow.stubRun) { + config.allArguments.each { arg -> + if (arg.required) { + assert inputs.containsKey(arg.plainName) && inputs.get(arg.plainName) != null : + "Error in module '${key}' id '${id}': required input argument '${arg.plainName}' is missing" + } + } + + inputs = inputs.collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } + assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid input argument" + + value = _checkArgumentType("input", par, value, "in module '$key' id '$id'") + + [ name, value ] + } + } + return inputs +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/arguments/_processOutputValues.nf' +Map _processOutputValues(Map outputs, Map config, String id, String key) { + if (!workflow.stubRun) { + config.allArguments.each { arg -> + if (arg.direction == "output" && arg.required) { + assert outputs.containsKey(arg.plainName) && outputs.get(arg.plainName) != null : + "Error in module '${key}' id '${id}': required output argument '${arg.plainName}' is missing" + } + } + + outputs = outputs.collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && it.direction == "output" } + assert par != null : "Error in module '${key}' id '${id}': '${name}' is not a valid output argument" + + value = _checkArgumentType("output", par, value, "in module '$key' id '$id'") + + [ name, value ] + } + } + return outputs +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/IDChecker.nf' +class IDChecker { + final def items = [] as Set + + @groovy.transform.WithWriteLock + boolean observe(String item) { + if (items.contains(item)) { + return false + } else { + items << item + return true + } + } + + @groovy.transform.WithReadLock + boolean contains(String item) { + return items.contains(item) + } + + @groovy.transform.WithReadLock + Set getItems() { + return items.clone() + } +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_checkUniqueIds.nf' + +/** + * Check if the ids are unique across parameter sets + * + * @param parameterSets a list of parameter sets. + */ +private void _checkUniqueIds(List>> parameterSets) { + def ppIds = parameterSets.collect{it[0]} + assert ppIds.size() == ppIds.unique().size() : "All argument sets should have unique ids. Detected ids: $ppIds" +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_getChild.nf' + +// helper functions for reading params from file // +def _getChild(parent, child) { + if (child.contains("://") || java.nio.file.Paths.get(child).isAbsolute()) { + child + } else { + def parentAbsolute = java.nio.file.Paths.get(parent).toAbsolutePath().toString() + parentAbsolute.replaceAll('/[^/]*$', "/") + child + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_parseParamList.nf' +/** + * Figure out the param list format based on the file extension + * + * @param param_list A String containing the path to the parameter list file. + * + * @return A String containing the format of the parameter list file. + */ +def _paramListGuessFormat(param_list) { + if (param_list !instanceof String) { + "asis" + } else if (param_list.endsWith(".csv")) { + "csv" + } else if (param_list.endsWith(".json") || param_list.endsWith(".jsn")) { + "json" + } else if (param_list.endsWith(".yaml") || param_list.endsWith(".yml")) { + "yaml" + } else { + "yaml_blob" + } +} + + +/** + * Read the param list + * + * @param param_list One of the following: + * - A String containing the path to the parameter list file (csv, json or yaml), + * - A yaml blob of a list of maps (yaml_blob), + * - Or a groovy list of maps (asis). + * @param config A Map of the Viash configuration. + * + * @return A List of Maps containing the parameters. + */ +def _parseParamList(param_list, Map config) { + // first determine format by extension + def paramListFormat = _paramListGuessFormat(param_list) + + def paramListPath = (paramListFormat != "asis" && paramListFormat != "yaml_blob") ? + file(param_list, hidden: true) : + null + + // get the correct parser function for the detected params_list format + def paramSets = [] + if (paramListFormat == "asis") { + paramSets = param_list + } else if (paramListFormat == "yaml_blob") { + paramSets = readYamlBlob(param_list) + } else if (paramListFormat == "yaml") { + paramSets = readYaml(paramListPath) + } else if (paramListFormat == "json") { + paramSets = readJson(paramListPath) + } else if (paramListFormat == "csv") { + paramSets = readCsv(paramListPath) + } else { + error "Format of provided --param_list not recognised.\n" + + "Found: '$paramListFormat'.\n" + + "Expected: a csv file, a json file, a yaml file,\n" + + "a yaml blob or a groovy list of maps." + } + + // data checks + assert paramSets instanceof List: "--param_list should contain a list of maps" + for (value in paramSets) { + assert value instanceof Map: "--param_list should contain a list of maps" + } + + // id is argument + def idIsArgument = config.allArguments.any{it.plainName == "id"} + + // Reformat from List to List> by adding the ID as first element of a Tuple2 + paramSets = paramSets.collect({ data -> + def id = data.id + if (!idIsArgument) { + data = data.findAll{k, v -> k != "id"} + } + [id, data] + }) + + // Split parameters with 'multiple: true' + paramSets = paramSets.collect({ id, data -> + data = _splitParams(data, config) + [id, data] + }) + + // The paths of input files inside a param_list file may have been specified relatively to the + // location of the param_list file. These paths must be made absolute. + if (paramListPath) { + paramSets = paramSets.collect({ id, data -> + def new_data = data.collectEntries{ parName, parValue -> + def par = config.allArguments.find{it.plainName == parName} + if (par && par.type == "file" && par.direction == "input") { + if (parValue instanceof Collection) { + parValue = parValue.collectMany{path -> + def x = _resolveSiblingIfNotAbsolute(path, paramListPath) + x instanceof Collection ? x : [x] + } + } else { + parValue = _resolveSiblingIfNotAbsolute(parValue, paramListPath) + } + } + [parName, parValue] + } + [id, new_data] + }) + } + + return paramSets +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/_splitParams.nf' +/** + * Split parameters for arguments that accept multiple values using their separator + * + * @param paramList A Map containing parameters to split. + * @param config A Map of the Viash configuration. This Map can be generated from the config file + * using the readConfig() function. + * + * @return A Map of parameters where the parameter values have been split into a list using + * their seperator. + */ +Map _splitParams(Map parValues, Map config){ + def parsedParamValues = parValues.collectEntries { parName, parValue -> + def parameterSettings = config.allArguments.find({it.plainName == parName}) + + if (!parameterSettings) { + // if argument is not found, do not alter + return [parName, parValue] + } + if (parameterSettings.multiple) { // Check if parameter can accept multiple values + if (parValue instanceof Collection) { + parValue = parValue.collect{it instanceof String ? it.split(parameterSettings.multiple_sep) : it } + } else if (parValue instanceof String) { + parValue = parValue.split(parameterSettings.multiple_sep) + } else if (parValue == null) { + parValue = [] + } else { + parValue = [ parValue ] + } + parValue = parValue.flatten() + } + // For all parameters check if multiple values are only passed for + // arguments that allow it. Quietly simplify lists of length 1. + if (!parameterSettings.multiple && parValue instanceof Collection) { + assert parValue.size() == 1 : + "Error: argument ${parName} has too many values.\n" + + " Expected amount: 1. Found: ${parValue.size()}" + parValue = parValue[0] + } + [parName, parValue] + } + return parsedParamValues +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/channelFromParams.nf' +/** + * Parse nextflow parameters based on settings defined in a viash config. + * Return a list of parameter sets, each parameter set corresponding to + * an event in a nextflow channel. The output from this function can be used + * with Channel.fromList to create a nextflow channel with Vdsl3 formatted + * events. + * + * This function performs: + * - A filtering of the params which can be found in the config file. + * - Process the params_list argument which allows a user to to initialise + * a Vsdl3 channel with multiple parameter sets. Possible formats are + * csv, json, yaml, or simply a yaml_blob. A csv should have column names + * which correspond to the different arguments of this pipeline. A json or a yaml + * file should be a list of maps, each of which has keys corresponding to the + * arguments of the pipeline. A yaml blob can also be passed directly as a parameter. + * When passing a csv, json or yaml, relative path names are relativized to the + * location of the parameter file. + * - Combine the parameter sets into a vdsl3 Channel. + * + * @param params Input parameters. Can optionaly contain a 'param_list' key that + * provides a list of arguments that can be split up into multiple events + * in the output channel possible formats of param_lists are: a csv file, + * json file, a yaml file or a yaml blob. Each parameters set (event) must + * have a unique ID. + * @param config A Map of the Viash configuration. This Map can be generated from the config file + * using the readConfig() function. + * + * @return A list of parameters with the first element of the event being + * the event ID and the second element containing a map of the parsed parameters. + */ + +private List>> _paramsToParamSets(Map params, Map config){ + // todo: fetch key from run args + def key_ = config.name + + /* parse regular parameters (not in param_list) */ + /*************************************************/ + def globalParams = config.allArguments + .findAll { params.containsKey(it.plainName) } + .collectEntries { [ it.plainName, params[it.plainName] ] } + def globalID = params.get("id", null) + + /* process params_list arguments */ + /*********************************/ + def paramList = params.containsKey("param_list") && params.param_list != null ? + params.param_list : [] + // if (paramList instanceof String) { + // paramList = [paramList] + // } + // def paramSets = paramList.collectMany{ _parseParamList(it, config) } + // TODO: be able to process param_list when it is a list of strings + def paramSets = _parseParamList(paramList, config) + if (paramSets.isEmpty()) { + paramSets = [[null, [:]]] + } + + /* combine arguments into channel */ + /**********************************/ + def processedParams = paramSets.indexed().collect{ index, tup -> + // Process ID + def id = tup[0] ?: globalID + + if (workflow.stubRun && !id) { + // if stub run, explicitly add an id if missing + id = "stub${index}" + } + assert id != null: "Each parameter set should have at least an 'id'" + + // Process params + def parValues = globalParams + tup[1] + // // Remove parameters which are null, if the default is also null + // parValues = parValues.collectEntries{paramName, paramValue -> + // parameterSettings = config.functionality.allArguments.find({it.plainName == paramName}) + // if ( paramValue != null || parameterSettings.get("default", null) != null ) { + // [paramName, paramValue] + // } + // } + parValues = parValues.collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } + assert par != null : "Error in module '${key_}' id '${id}': '${name}' is not a valid input argument" + + if (par == null) { + return [:] + } + value = _checkArgumentType("input", par, value, "in module '$key_' id '$id'") + + [ name, value ] + } + + [id, parValues] + } + + // Check if ids (first element of each list) is unique + _checkUniqueIds(processedParams) + return processedParams +} + +/** + * Parse nextflow parameters based on settings defined in a viash config + * and return a nextflow channel. + * + * @param params Input parameters. Can optionaly contain a 'param_list' key that + * provides a list of arguments that can be split up into multiple events + * in the output channel possible formats of param_lists are: a csv file, + * json file, a yaml file or a yaml blob. Each parameters set (event) must + * have a unique ID. + * @param config A Map of the Viash configuration. This Map can be generated from the config file + * using the readConfig() function. + * + * @return A nextflow Channel with events. Events are formatted as a tuple that contains + * first contains the ID of the event and as second element holds a parameter map. + * + * + */ +def channelFromParams(Map params, Map config) { + def processedParams = _paramsToParamSets(params, config) + return Channel.fromList(processedParams) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/checkUniqueIds.nf' +def checkUniqueIds(Map args) { + def stopOnError = args.stopOnError == null ? args.stopOnError : true + + def idChecker = new IDChecker() + + return filter { tup -> + if (!idChecker.observe(tup[0])) { + if (stopOnError) { + error "Duplicate id: ${tup[0]}" + } else { + log.warn "Duplicate id: ${tup[0]}, removing duplicate entry" + return false + } + } + return true + } +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/preprocessInputs.nf' +// This helper file will be deprecated soon +preprocessInputsDeprecationWarningPrinted = false + +def preprocessInputsDeprecationWarning() { + if (!preprocessInputsDeprecationWarningPrinted) { + preprocessInputsDeprecationWarningPrinted = true + System.err.println("Warning: preprocessInputs() is deprecated and will be removed in Viash 0.9.0.") + } +} + +/** + * Generate a nextflow Workflow that allows processing a channel of + * Vdsl3 formatted events and apply a Viash config to them: + * - Gather default parameters from the Viash config and make + * sure that they are correctly formatted (see applyConfig method). + * - Format the input parameters (also using the applyConfig method). + * - Apply the default parameter to the input parameters. + * - Do some assertions: + * ~ Check if the event IDs in the channel are unique. + * + * The events in the channel are formatted as tuples, with the + * first element of the tuples being a unique id of the parameter set, + * and the second element containg the the parameters themselves. + * Optional extra elements of the tuples will be passed to the output as is. + * + * @param args A map that must contain a 'config' key that points + * to a parsed config (see readConfig()). Optionally, a + * 'key' key can be provided which can be used to create a unique + * name for the workflow process. + * + * @return A workflow that allows processing a channel of Vdsl3 formatted events + * and apply a Viash config to them. + */ +def preprocessInputs(Map args) { + preprocessInputsDeprecationWarning() + + def config = args.config + assert config instanceof Map : + "Error in preprocessInputs: config must be a map. " + + "Expected class: Map. Found: config.getClass() is ${config.getClass()}" + def key_ = args.key ?: config.name + + // Get different parameter types (used throughout this function) + def defaultArgs = config.allArguments + .findAll { it.containsKey("default") } + .collectEntries { [ it.plainName, it.default ] } + + map { tup -> + def id = tup[0] + def data = tup[1] + def passthrough = tup.drop(2) + + def new_data = (defaultArgs + data).collectEntries { name, value -> + def par = config.allArguments.find { it.plainName == name && (it.direction == "input" || it.type == "file") } + + if (par != null) { + value = _checkArgumentType("input", par, value, "in module '$key_' id '$id'") + } + + [ name, value ] + } + + [ id, new_data ] + passthrough + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/runComponents.nf' +/** + * Run a list of components on a stream of data. + * + * @param components: list of Viash VDSL3 modules to run + * @param fromState: a closure, a map or a list of keys to extract from the input data. + * If a closure, it will be called with the id, the data and the component config. + * @param toState: a closure, a map or a list of keys to extract from the output data + * If a closure, it will be called with the id, the output data, the old state and the component config. + * @param filter: filter function to apply to the input. + * It will be called with the id, the data and the component config. + * @param id: id to use for the output data + * If a closure, it will be called with the id, the data and the component config. + * @param auto: auto options to pass to the components + * + * @return: a workflow that runs the components + **/ +def runComponents(Map args) { + log.warn("runComponents is deprecated, use runEach instead") + assert args.components: "runComponents should be passed a list of components to run" + + def components_ = args.components + if (components_ !instanceof List) { + components_ = [ components_ ] + } + assert components_.size() > 0: "pass at least one component to runComponents" + + def fromState_ = args.fromState + def toState_ = args.toState + def filter_ = args.filter + def id_ = args.id + + workflow runComponentsWf { + take: input_ch + main: + + // generate one channel per method + out_chs = components_.collect{ comp_ -> + def comp_config = comp_.config + + def filter_ch = filter_ + ? input_ch | filter{tup -> + filter_(tup[0], tup[1], comp_config) + } + : input_ch + def id_ch = id_ + ? filter_ch | map{tup -> + // def new_id = id_(tup[0], tup[1], comp_config) + def new_id = tup[0] + if (id_ instanceof String) { + new_id = id_ + } else if (id_ instanceof Closure) { + new_id = id_(new_id, tup[1], comp_config) + } + [new_id] + tup.drop(1) + } + : filter_ch + def data_ch = id_ch | map{tup -> + def new_data = tup[1] + if (fromState_ instanceof Map) { + new_data = fromState_.collectEntries{ key0, key1 -> + [key0, new_data[key1]] + } + } else if (fromState_ instanceof List) { + new_data = fromState_.collectEntries{ key -> + [key, new_data[key]] + } + } else if (fromState_ instanceof Closure) { + new_data = fromState_(tup[0], new_data, comp_config) + } + tup.take(1) + [new_data] + tup.drop(1) + } + def out_ch = data_ch + | comp_.run( + auto: (args.auto ?: [:]) + [simplifyInput: false, simplifyOutput: false] + ) + def post_ch = toState_ + ? out_ch | map{tup -> + def output = tup[1] + def old_state = tup[2] + def new_state = null + if (toState_ instanceof Map) { + new_state = old_state + toState_.collectEntries{ key0, key1 -> + [key0, output[key1]] + } + } else if (toState_ instanceof List) { + new_state = old_state + toState_.collectEntries{ key -> + [key, output[key]] + } + } else if (toState_ instanceof Closure) { + new_state = toState_(tup[0], output, old_state, comp_config) + } + [tup[0], new_state] + tup.drop(3) + } + : out_ch + + post_ch + } + + // mix all results + output_ch = + (out_chs.size == 1) + ? out_chs[0] + : out_chs[0].mix(*out_chs.drop(1)) + + emit: output_ch + } + + return runComponentsWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/runEach.nf' +/** + * Run a list of components on a stream of data. + * + * @param components: list of Viash VDSL3 modules to run + * @param fromState: a closure, a map or a list of keys to extract from the input data. + * If a closure, it will be called with the id, the data and the component itself. + * @param toState: a closure, a map or a list of keys to extract from the output data + * If a closure, it will be called with the id, the output data, the old state and the component itself. + * @param filter: filter function to apply to the input. + * It will be called with the id, the data and the component itself. + * @param id: id to use for the output data + * If a closure, it will be called with the id, the data and the component itself. + * @param auto: auto options to pass to the components + * + * @return: a workflow that runs the components + **/ +def runEach(Map args) { + assert args.components: "runEach should be passed a list of components to run" + + def components_ = args.components + if (components_ !instanceof List) { + components_ = [ components_ ] + } + assert components_.size() > 0: "pass at least one component to runEach" + + def fromState_ = args.fromState + def toState_ = args.toState + def filter_ = args.filter + def runIf_ = args.runIf + def id_ = args.id + + assert !runIf_ || runIf_ instanceof Closure: "runEach: must pass a Closure to runIf." + + workflow runEachWf { + take: input_ch + main: + + // generate one channel per method + out_chs = components_.collect{ comp_ -> + def filter_ch = filter_ + ? input_ch | filter{tup -> + filter_(tup[0], tup[1], comp_) + } + : input_ch + def id_ch = id_ + ? filter_ch | map{tup -> + def new_id = id_ + if (new_id instanceof Closure) { + new_id = new_id(tup[0], tup[1], comp_) + } + assert new_id instanceof String : "Error in runEach: id should be a String or a Closure that returns a String. Expected: id instanceof String. Found: ${new_id.getClass()}" + [new_id] + tup.drop(1) + } + : filter_ch + def chPassthrough = null + def chRun = null + if (runIf_) { + def idRunIfBranch = id_ch.branch{ tup -> + run: runIf_(tup[0], tup[1], comp_) + passthrough: true + } + chPassthrough = idRunIfBranch.passthrough + chRun = idRunIfBranch.run + } else { + chRun = id_ch + chPassthrough = Channel.empty() + } + def data_ch = chRun | map{tup -> + def new_data = tup[1] + if (fromState_ instanceof Map) { + new_data = fromState_.collectEntries{ key0, key1 -> + [key0, new_data[key1]] + } + } else if (fromState_ instanceof List) { + new_data = fromState_.collectEntries{ key -> + [key, new_data[key]] + } + } else if (fromState_ instanceof Closure) { + new_data = fromState_(tup[0], new_data, comp_) + } + tup.take(1) + [new_data] + tup.drop(1) + } + def out_ch = data_ch + | comp_.run( + auto: (args.auto ?: [:]) + [simplifyInput: false, simplifyOutput: false] + ) + def post_ch = toState_ + ? out_ch | map{tup -> + def output = tup[1] + def old_state = tup[2] + def new_state = null + if (toState_ instanceof Map) { + new_state = old_state + toState_.collectEntries{ key0, key1 -> + [key0, output[key1]] + } + } else if (toState_ instanceof List) { + new_state = old_state + toState_.collectEntries{ key -> + [key, output[key]] + } + } else if (toState_ instanceof Closure) { + new_state = toState_(tup[0], output, old_state, comp_) + } + [tup[0], new_state] + tup.drop(3) + } + : out_ch + + def return_ch = post_ch + | concat(chPassthrough) + + return_ch + } + + // mix all results + output_ch = + (out_chs.size == 1) + ? out_chs[0] + : out_chs[0].mix(*out_chs.drop(1)) + + emit: output_ch + } + + return runEachWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/channel/safeJoin.nf' +/** + * Join sourceChannel to targetChannel + * + * This function joins the sourceChannel to the targetChannel. + * However, each id in the targetChannel must be present in the + * sourceChannel. If _meta.join_id exists in the targetChannel, that is + * used as an id instead. If the id doesn't match any id in the sourceChannel, + * an error is thrown. + */ + +def safeJoin(targetChannel, sourceChannel, key) { + def sourceIDs = new IDChecker() + + def sourceCheck = sourceChannel + | map { tup -> + sourceIDs.observe(tup[0]) + tup + } + def targetCheck = targetChannel + | map { tup -> + def id = tup[0] + + if (!sourceIDs.contains(id)) { + error ( + "Error in module '${key}' when merging output with original state.\n" + + " Reason: output with id '${id}' could not be joined with source channel.\n" + + " If the IDs in the output channel differ from the input channel,\n" + + " please set `tup[1]._meta.join_id to the original ID.\n" + + " Original IDs in input channel: ['${sourceIDs.getItems().join("', '")}'].\n" + + " Unexpected ID in the output channel: '${id}'.\n" + + " Example input event: [\"id\", [input: file(...)]],\n" + + " Example output event: [\"newid\", [output: file(...), _meta: [join_id: \"id\"]]]" + ) + } + // TODO: add link to our documentation on how to fix this + + tup + } + + sourceCheck.cross(targetChannel) + | map{ left, right -> + right + left.drop(1) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/_processArgument.nf' +def _processArgument(arg) { + arg.multiple = arg.multiple != null ? arg.multiple : false + arg.required = arg.required != null ? arg.required : false + arg.direction = arg.direction != null ? arg.direction : "input" + arg.multiple_sep = arg.multiple_sep != null ? arg.multiple_sep : ";" + arg.plainName = arg.name.replaceAll("^-*", "") + + if (arg.type == "file") { + arg.must_exist = arg.must_exist != null ? arg.must_exist : true + arg.create_parent = arg.create_parent != null ? arg.create_parent : true + } + + // add default values to output files which haven't already got a default + if (arg.type == "file" && arg.direction == "output" && arg.default == null) { + def mult = arg.multiple ? "_*" : "" + def extSearch = "" + if (arg.default != null) { + extSearch = arg.default + } else if (arg.example != null) { + extSearch = arg.example + } + if (extSearch instanceof List) { + extSearch = extSearch[0] + } + def extSearchResult = extSearch.find("\\.[^\\.]+\$") + def ext = extSearchResult != null ? extSearchResult : "" + arg.default = "\$id.\$key.${arg.plainName}${mult}${ext}" + if (arg.multiple) { + arg.default = [arg.default] + } + } + + if (!arg.multiple) { + if (arg.default != null && arg.default instanceof List) { + arg.default = arg.default[0] + } + if (arg.example != null && arg.example instanceof List) { + arg.example = arg.example[0] + } + } + + if (arg.type == "boolean_true") { + arg.default = false + } + if (arg.type == "boolean_false") { + arg.default = true + } + + arg +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/addGlobalParams.nf' +def addGlobalArguments(config) { + def localConfig = [ + "argument_groups": [ + [ + "name": "Nextflow input-output arguments", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "arguments" : [ + [ + 'name': '--publish_dir', + 'required': true, + 'type': 'string', + 'description': 'Path to an output directory.', + 'example': 'output/', + 'multiple': false + ], + [ + 'name': '--param_list', + 'required': false, + 'type': 'string', + 'description': '''Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob. + | + |* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ ['id': 'foo', 'input': 'foo.txt'], ['id': 'bar', 'input': 'bar.txt'] ]`. + |* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`. + |* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {'id': 'foo', 'input': 'foo.txt'}, {'id': 'bar', 'input': 'bar.txt'} ]`. + |* A yaml blob can also be passed directly as a string. Example: `--param_list "[ {'id': 'foo', 'input': 'foo.txt'}, {'id': 'bar', 'input': 'bar.txt'} ]"`. + | + |When passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.'''.stripMargin(), + 'example': 'my_params.yaml', + 'multiple': false, + 'hidden': true + ] + // TODO: allow multiple: true in param_list? + // TODO: allow to specify a --param_list_regex to filter the param_list? + // TODO: allow to specify a --param_list_from_state to remap entries in the param_list? + ] + ] + ] + ] + + return processConfig(_mergeMap(config, localConfig)) +} + +def _mergeMap(Map lhs, Map rhs) { + return rhs.inject(lhs.clone()) { map, entry -> + if (map[entry.key] instanceof Map && entry.value instanceof Map) { + map[entry.key] = _mergeMap(map[entry.key], entry.value) + } else if (map[entry.key] instanceof Collection && entry.value instanceof Collection) { + map[entry.key] += entry.value + } else { + map[entry.key] = entry.value + } + return map + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/generateHelp.nf' +def _generateArgumentHelp(param) { + // alternatives are not supported + // def names = param.alternatives ::: List(param.name) + + def unnamedProps = [ + ["required parameter", param.required], + ["multiple values allowed", param.multiple], + ["output", param.direction.toLowerCase() == "output"], + ["file must exist", param.type == "file" && param.must_exist] + ].findAll{it[1]}.collect{it[0]} + + def dflt = null + if (param.default != null) { + if (param.default instanceof List) { + dflt = param.default.join(param.multiple_sep != null ? param.multiple_sep : ", ") + } else { + dflt = param.default.toString() + } + } + def example = null + if (param.example != null) { + if (param.example instanceof List) { + example = param.example.join(param.multiple_sep != null ? param.multiple_sep : ", ") + } else { + example = param.example.toString() + } + } + def min = param.min?.toString() + def max = param.max?.toString() + + def escapeChoice = { choice -> + def s1 = choice.replaceAll("\\n", "\\\\n") + def s2 = s1.replaceAll("\"", """\\\"""") + s2.contains(",") || s2 != choice ? "\"" + s2 + "\"" : s2 + } + def choices = param.choices == null ? + null : + "[ " + param.choices.collect{escapeChoice(it.toString())}.join(", ") + " ]" + + def namedPropsStr = [ + ["type", ([param.type] + unnamedProps).join(", ")], + ["default", dflt], + ["example", example], + ["choices", choices], + ["min", min], + ["max", max] + ] + .findAll{it[1]} + .collect{"\n " + it[0] + ": " + it[1].replaceAll("\n", "\\n")} + .join("") + + def descStr = param.description == null ? + "" : + _paragraphWrap("\n" + param.description.trim(), 80 - 8).join("\n ") + + "\n --" + param.plainName + + namedPropsStr + + descStr +} + +// Based on Helper.generateHelp() in Helper.scala +def _generateHelp(config) { + def fun = config + + // PART 1: NAME AND VERSION + def nameStr = fun.name + + (fun.version == null ? "" : " " + fun.version) + + // PART 2: DESCRIPTION + def descrStr = fun.description == null ? + "" : + "\n\n" + _paragraphWrap(fun.description.trim(), 80).join("\n") + + // PART 3: Usage + def usageStr = fun.usage == null ? + "" : + "\n\nUsage:\n" + fun.usage.trim() + + // PART 4: Options + def argGroupStrs = fun.allArgumentGroups.collect{argGroup -> + def name = argGroup.name + def descriptionStr = argGroup.description == null ? + "" : + "\n " + _paragraphWrap(argGroup.description.trim(), 80-4).join("\n ") + "\n" + def arguments = argGroup.arguments.collect{arg -> + arg instanceof String ? fun.allArguments.find{it.plainName == arg} : arg + }.findAll{it != null} + def argumentStrs = arguments.collect{param -> _generateArgumentHelp(param)} + + "\n\n$name:" + + descriptionStr + + argumentStrs.join("\n") + } + + // FINAL: combine + def out = nameStr + + descrStr + + usageStr + + argGroupStrs.join("") + + return out +} + +// based on Format._paragraphWrap +def _paragraphWrap(str, maxLength) { + def outLines = [] + str.split("\n").each{par -> + def words = par.split("\\s").toList() + + def word = null + def line = words.pop() + while(!words.isEmpty()) { + word = words.pop() + if (line.length() + word.length() + 1 <= maxLength) { + line = line + " " + word + } else { + outLines.add(line) + line = word + } + } + if (words.isEmpty()) { + outLines.add(line) + } + } + return outLines +} + +def helpMessage(config) { + if (params.containsKey("help") && params.help) { + def mergedConfig = addGlobalArguments(config) + def helpStr = _generateHelp(mergedConfig) + println(helpStr) + exit 0 + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/processConfig.nf' +def processConfig(config) { + // set defaults for arguments + config.arguments = + (config.arguments ?: []).collect{_processArgument(it)} + + // set defaults for argument_group arguments + config.argument_groups = + (config.argument_groups ?: []).collect{grp -> + grp.arguments = (grp.arguments ?: []).collect{_processArgument(it)} + grp + } + + // create combined arguments list + config.allArguments = + config.arguments + + config.argument_groups.collectMany{it.arguments} + + // add missing argument groups (based on Functionality::allArgumentGroups()) + def argGroups = config.argument_groups + if (argGroups.any{it.name.toLowerCase() == "arguments"}) { + argGroups = argGroups.collect{ grp -> + if (grp.name.toLowerCase() == "arguments") { + grp = grp + [ + arguments: grp.arguments + config.arguments + ] + } + grp + } + } else { + argGroups = argGroups + [ + name: "Arguments", + arguments: config.arguments + ] + } + config.allArgumentGroups = argGroups + + config +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/config/readConfig.nf' + +def readConfig(file) { + def config = readYaml(file ?: moduleDir.resolve("config.vsh.yaml")) + processConfig(config) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/_resolveSiblingIfNotAbsolute.nf' +/** + * Resolve a path relative to the current file. + * + * @param str The path to resolve, as a String. + * @param parentPath The path to resolve relative to, as a Path. + * + * @return The path that may have been resovled, as a Path. + */ +def _resolveSiblingIfNotAbsolute(str, parentPath) { + if (str !instanceof String) { + return str + } + if (!_stringIsAbsolutePath(str)) { + return parentPath.resolveSibling(str) + } else { + return file(str, hidden: true) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/_stringIsAbsolutePath.nf' +/** + * Check whether a path as a string is absolute. + * + * In the past, we tried using `file(., relative: true).isAbsolute()`, + * but the 'relative' option was added in 22.10.0. + * + * @param path The path to check, as a String. + * + * @return Whether the path is absolute, as a boolean. + */ +def _stringIsAbsolutePath(path) { + def _resolve_URL_PROTOCOL = ~/^([a-zA-Z][a-zA-Z0-9]*:)?\\/.+/ + + assert path instanceof String + return _resolve_URL_PROTOCOL.matcher(path).matches() +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/collectTraces.nf' +class CustomTraceObserver implements nextflow.trace.TraceObserver { + List traces + + CustomTraceObserver(List traces) { + this.traces = traces + } + + @Override + void onProcessComplete(nextflow.processor.TaskHandler handler, nextflow.trace.TraceRecord trace) { + def trace2 = trace.store.clone() + trace2.script = null + traces.add(trace2) + } + + @Override + void onProcessCached(nextflow.processor.TaskHandler handler, nextflow.trace.TraceRecord trace) { + def trace2 = trace.store.clone() + trace2.script = null + traces.add(trace2) + } +} + +def collectTraces() { + def traces = Collections.synchronizedList([]) + + // add custom trace observer which stores traces in the traces object + session.observers.add(new CustomTraceObserver(traces)) + + traces +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/deepClone.nf' +/** + * Performs a deep clone of the given object. + * @param x an object + */ +def deepClone(x) { + iterateMap(x, {it instanceof Cloneable ? it.clone() : it}) +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/getPublishDir.nf' +def getPublishDir() { + return params.containsKey("publish_dir") ? params.publish_dir : + params.containsKey("publishDir") ? params.publishDir : + null +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/getRootDir.nf' + +// Recurse upwards until we find a '.build.yaml' file +def _findBuildYamlFile(pathPossiblySymlink) { + def path = pathPossiblySymlink.toRealPath() + def child = path.resolve(".build.yaml") + if (java.nio.file.Files.isDirectory(path) && java.nio.file.Files.exists(child)) { + return child + } else { + def parent = path.getParent() + if (parent == null) { + return null + } else { + return _findBuildYamlFile(parent) + } + } +} + +// get the root of the target folder +def getRootDir() { + def dir = _findBuildYamlFile(meta.resources_dir) + assert dir != null: "Could not find .build.yaml in the folder structure" + dir.getParent() +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/iterateMap.nf' +/** + * Recursively apply a function over the leaves of an object. + * @param obj The object to iterate over. + * @param fun The function to apply to each value. + * @return The object with the function applied to each value. + */ +def iterateMap(obj, fun) { + if (obj instanceof List && obj !instanceof String) { + return obj.collect{item -> + iterateMap(item, fun) + } + } else if (obj instanceof Map) { + return obj.collectEntries{key, item -> + [key.toString(), iterateMap(item, fun)] + } + } else { + return fun(obj) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/functions/niceView.nf' +/** + * A view for printing the event of each channel as a YAML blob. + * This is useful for debugging. + */ +def niceView() { + workflow niceViewWf { + take: input + main: + output = input + | view{toYamlBlob(it)} + emit: output + } + return niceViewWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readCsv.nf' + +def readCsv(file_path) { + def output = [] + def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path + + // todo: allow escaped quotes in string + // todo: allow single quotes? + def splitRegex = java.util.regex.Pattern.compile(''',(?=(?:[^"]*"[^"]*")*[^"]*$)''') + def removeQuote = java.util.regex.Pattern.compile('''"(.*)"''') + + def br = java.nio.file.Files.newBufferedReader(inputFile) + + def row = -1 + def header = null + while (br.ready() && header == null) { + def line = br.readLine() + row++ + if (!line.startsWith("#")) { + header = splitRegex.split(line, -1).collect{field -> + m = removeQuote.matcher(field) + m.find() ? m.replaceFirst('$1') : field + } + } + } + assert header != null: "CSV file should contain a header" + + while (br.ready()) { + def line = br.readLine() + row++ + if (line == null) { + br.close() + break + } + + if (!line.startsWith("#")) { + def predata = splitRegex.split(line, -1) + def data = predata.collect{field -> + if (field == "") { + return null + } + def m = removeQuote.matcher(field) + if (m.find()) { + return m.replaceFirst('$1') + } else { + return field + } + } + assert header.size() == data.size(): "Row $row should contain the same number as fields as the header" + + def dataMap = [header, data].transpose().collectEntries().findAll{it.value != null} + output.add(dataMap) + } + } + + output +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readJson.nf' +def readJson(file_path) { + def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path + def jsonSlurper = new groovy.json.JsonSlurper() + jsonSlurper.parse(inputFile) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readJsonBlob.nf' +def readJsonBlob(str) { + def jsonSlurper = new groovy.json.JsonSlurper() + jsonSlurper.parseText(str) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readTaggedYaml.nf' +// Custom constructor to modify how certain objects are parsed from YAML +class CustomConstructor extends org.yaml.snakeyaml.constructor.Constructor { + Path root + + class ConstructPath extends org.yaml.snakeyaml.constructor.AbstractConstruct { + public Object construct(org.yaml.snakeyaml.nodes.Node node) { + String filename = (String) constructScalar(node); + if (root != null) { + return root.resolve(filename); + } + return java.nio.file.Paths.get(filename); + } + } + + CustomConstructor(org.yaml.snakeyaml.LoaderOptions options, Path root) { + super(options) + this.root = root + // Handling !file tag and parse it back to a File type + this.yamlConstructors.put(new org.yaml.snakeyaml.nodes.Tag("!file"), new ConstructPath()) + } +} + +def readTaggedYaml(Path path) { + def options = new org.yaml.snakeyaml.LoaderOptions() + def constructor = new CustomConstructor(options, path.getParent()) + def yaml = new org.yaml.snakeyaml.Yaml(constructor) + return yaml.load(path.text) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readYaml.nf' +def readYaml(file_path) { + def inputFile = file_path !instanceof Path ? file(file_path, hidden: true) : file_path + def yamlSlurper = new org.yaml.snakeyaml.Yaml() + yamlSlurper.load(inputFile) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/readYamlBlob.nf' +def readYamlBlob(str) { + def yamlSlurper = new org.yaml.snakeyaml.Yaml() + yamlSlurper.load(str) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toJsonBlob.nf' +String toJsonBlob(data) { + return groovy.json.JsonOutput.toJson(data) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toTaggedYamlBlob.nf' +// Custom representer to modify how certain objects are represented in YAML +class CustomRepresenter extends org.yaml.snakeyaml.representer.Representer { + Path relativizer + + class RepresentPath implements org.yaml.snakeyaml.representer.Represent { + public String getFileName(Object obj) { + if (obj instanceof File) { + obj = ((File) obj).toPath(); + } + if (obj !instanceof Path) { + throw new IllegalArgumentException("Object: " + obj + " is not a Path or File"); + } + def path = (Path) obj; + + if (relativizer != null) { + return relativizer.relativize(path).toString() + } else { + return path.toString() + } + } + + public org.yaml.snakeyaml.nodes.Node representData(Object data) { + String filename = getFileName(data); + def tag = new org.yaml.snakeyaml.nodes.Tag("!file"); + return representScalar(tag, filename); + } + } + CustomRepresenter(org.yaml.snakeyaml.DumperOptions options, Path relativizer) { + super(options) + this.relativizer = relativizer + this.representers.put(sun.nio.fs.UnixPath, new RepresentPath()) + this.representers.put(Path, new RepresentPath()) + this.representers.put(File, new RepresentPath()) + } +} + +String toTaggedYamlBlob(data) { + return toRelativeTaggedYamlBlob(data, null) +} +String toRelativeTaggedYamlBlob(data, Path relativizer) { + def options = new org.yaml.snakeyaml.DumperOptions() + options.setDefaultFlowStyle(org.yaml.snakeyaml.DumperOptions.FlowStyle.BLOCK) + def representer = new CustomRepresenter(options, relativizer) + def yaml = new org.yaml.snakeyaml.Yaml(representer, options) + return yaml.dump(data) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/toYamlBlob.nf' +String toYamlBlob(data) { + def options = new org.yaml.snakeyaml.DumperOptions() + options.setDefaultFlowStyle(org.yaml.snakeyaml.DumperOptions.FlowStyle.BLOCK) + options.setPrettyFlow(true) + def yaml = new org.yaml.snakeyaml.Yaml(options) + def cleanData = iterateMap(data, { it instanceof Path ? it.toString() : it }) + return yaml.dump(cleanData) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/writeJson.nf' +void writeJson(data, file) { + assert data: "writeJson: data should not be null" + assert file: "writeJson: file should not be null" + file.write(toJsonBlob(data)) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/readwrite/writeYaml.nf' +void writeYaml(data, file) { + assert data: "writeYaml: data should not be null" + assert file: "writeYaml: file should not be null" + file.write(toYamlBlob(data)) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/findStates.nf' +def findStates(Map params, Map config) { + def auto_config = deepClone(config) + def auto_params = deepClone(params) + + auto_config = auto_config.clone() + // override arguments + auto_config.argument_groups = [] + auto_config.arguments = [ + [ + type: "string", + name: "--id", + description: "A dummy identifier", + required: false + ], + [ + type: "file", + name: "--input_states", + example: "/path/to/input/directory/**/state.yaml", + description: "Path to input directory containing the datasets to be integrated.", + required: true, + multiple: true, + multiple_sep: ";" + ], + [ + type: "string", + name: "--filter", + example: "foo/.*/state.yaml", + description: "Regex to filter state files by path.", + required: false + ], + // to do: make this a yaml blob? + [ + type: "string", + name: "--rename_keys", + example: ["newKey1:oldKey1", "newKey2:oldKey2"], + description: "Rename keys in the detected input files. This is useful if the input files do not match the set of input arguments of the workflow.", + required: false, + multiple: true, + multiple_sep: ";" + ], + [ + type: "string", + name: "--settings", + example: '{"output_dataset": "dataset.h5ad", "k": 10}', + description: "Global arguments as a JSON glob to be passed to all components.", + required: false + ] + ] + if (!(auto_params.containsKey("id"))) { + auto_params["id"] = "auto" + } + + // run auto config through processConfig once more + auto_config = processConfig(auto_config) + + workflow findStatesWf { + helpMessage(auto_config) + + output_ch = + channelFromParams(auto_params, auto_config) + | flatMap { autoId, args -> + + def globalSettings = args.settings ? readYamlBlob(args.settings) : [:] + + // look for state files in input dir + def stateFiles = args.input_states + + // filter state files by regex + if (args.filter) { + stateFiles = stateFiles.findAll{ stateFile -> + def stateFileStr = stateFile.toString() + def matcher = stateFileStr =~ args.filter + matcher.matches()} + } + + // read in states + def states = stateFiles.collect { stateFile -> + def state_ = readTaggedYaml(stateFile) + [state_.id, state_] + } + + // construct renameMap + if (args.rename_keys) { + def renameMap = args.rename_keys.collectEntries{renameString -> + def split = renameString.split(":") + assert split.size() == 2: "Argument 'rename_keys' should be of the form 'newKey:oldKey', or 'newKey:oldKey;newKey:oldKey' in case of multiple values" + split + } + + // rename keys in state, only let states through which have all keys + // also add global settings + states = states.collectMany{id, state -> + def newState = [:] + + for (key in renameMap.keySet()) { + def origKey = renameMap[key] + if (!(state.containsKey(origKey))) { + return [] + } + newState[key] = state[origKey] + } + + [[id, globalSettings + newState]] + } + } + + states + } + emit: + output_ch + } + + return findStatesWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/joinStates.nf' +def joinStates(Closure apply_) { + workflow joinStatesWf { + take: input_ch + main: + output_ch = input_ch + | toSortedList + | filter{ it.size() > 0 } + | map{ tups -> + def ids = tups.collect{it[0]} + def states = tups.collect{it[1]} + apply_(ids, states) + } + + emit: output_ch + } + return joinStatesWf +} +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/publishStates.nf' +def collectFiles(obj) { + if (obj instanceof java.io.File || obj instanceof Path) { + return [obj] + } else if (obj instanceof List && obj !instanceof String) { + return obj.collectMany{item -> + collectFiles(item) + } + } else if (obj instanceof Map) { + return obj.collectMany{key, item -> + collectFiles(item) + } + } else { + return [] + } +} + +/** + * Recurse through a state and collect all input files and their target output filenames. + * @param obj The state to recurse through. + * @param prefix The prefix to prepend to the output filenames. + */ +def collectInputOutputPaths(obj, prefix) { + if (obj instanceof File || obj instanceof Path) { + def path = obj instanceof Path ? obj : obj.toPath() + def ext = path.getFileName().toString().find("\\.[^\\.]+\$") ?: "" + def newFilename = prefix + ext + return [[obj, newFilename]] + } else if (obj instanceof List && obj !instanceof String) { + return obj.withIndex().collectMany{item, ix -> + collectInputOutputPaths(item, prefix + "_" + ix) + } + } else if (obj instanceof Map) { + return obj.collectMany{key, item -> + collectInputOutputPaths(item, prefix + "." + key) + } + } else { + return [] + } +} + +def publishStates(Map args) { + def key_ = args.get("key") + def yamlTemplate_ = args.get("output_state", args.get("outputState", '$id.$key.state.yaml')) + + assert key_ != null : "publishStates: key must be specified" + + workflow publishStatesWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] + + // the input files and the target output filenames + def inputoutputFilenames_ = collectInputOutputPaths(state_, id_ + "." + key_).transpose() + def inputFiles_ = inputoutputFilenames_[0] + def outputFilenames_ = inputoutputFilenames_[1] + + def yamlFilename = yamlTemplate_ + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + + // TODO: do the pathnames in state_ match up with the outputFilenames_? + + // convert state to yaml blob + def yamlBlob_ = toRelativeTaggedYamlBlob([id: id_] + state_, java.nio.file.Paths.get(yamlFilename)) + + [id_, yamlBlob_, yamlFilename, inputFiles_, outputFilenames_] + } + | publishStatesProc + emit: input_ch + } + return publishStatesWf +} +process publishStatesProc { + // todo: check publishpath? + publishDir path: "${getPublishDir()}/", mode: "copy" + tag "$id" + input: + tuple val(id), val(yamlBlob), val(yamlFile), path(inputFiles, stageAs: "_inputfile?/*"), val(outputFiles) + output: + tuple val(id), path{[yamlFile] + outputFiles} + script: + def copyCommands = [ + inputFiles instanceof List ? inputFiles : [inputFiles], + outputFiles instanceof List ? outputFiles : [outputFiles] + ] + .transpose() + .collectMany{infile, outfile -> + if (infile.toString() != outfile.toString()) { + [ + "[ -d \"\$(dirname '${outfile.toString()}')\" ] || mkdir -p \"\$(dirname '${outfile.toString()}')\"", + "cp -r '${infile.toString()}' '${outfile.toString()}'" + ] + } else { + // no need to copy if infile is the same as outfile + [] + } + } + """ +mkdir -p "\$(dirname '${yamlFile}')" +echo "Storing state as yaml" +echo '${yamlBlob}' > '${yamlFile}' +echo "Copying output files to destination folder" +${copyCommands.join("\n ")} +""" +} + + +// this assumes that the state contains no other values other than those specified in the config +def publishStatesByConfig(Map args) { + def config = args.get("config") + assert config != null : "publishStatesByConfig: config must be specified" + + def key_ = args.get("key", config.name) + assert key_ != null : "publishStatesByConfig: key must be specified" + + workflow publishStatesSimpleWf { + take: input_ch + main: + input_ch + | map { tup -> + def id_ = tup[0] + def state_ = tup[1] // e.g. [output: new File("myoutput.h5ad"), k: 10] + def origState_ = tup[2] // e.g. [output: '$id.$key.foo.h5ad'] + + // TODO: allow overriding the state.yaml template + // TODO TODO: if auto.publish == "state", add output_state as an argument + def yamlTemplate = params.containsKey("output_state") ? params.output_state : '$id.$key.state.yaml' + def yamlFilename = yamlTemplate + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + def yamlDir = java.nio.file.Paths.get(yamlFilename).getParent() + + // the processed state is a list of [key, value, inputPath, outputFilename] tuples, where + // - key is a String + // - value is any object that can be serialized to a Yaml (so a String/Integer/Long/Double/Boolean, a List, a Map, or a Path) + // - inputPath is a List[Path] + // - outputFilename is a List[String] + // - (key, value) are the tuples that will be saved to the state.yaml file + // - (inputPath, outputFilename) are the files that will be copied from src to dest (relative to the state.yaml) + def processedState = + config.allArguments + .findAll { it.direction == "output" } + .collectMany { par -> + def plainName_ = par.plainName + // if the state does not contain the key, it's an + // optional argument for which the component did + // not generate any output + if (!state_.containsKey(plainName_)) { + return [] + } + def value = state_[plainName_] + // if the parameter is not a file, it should be stored + // in the state as-is, but is not something that needs + // to be copied from the source path to the dest path + if (par.type != "file") { + return [[key: plainName_, value: value, inputPath: [], outputFilename: []]] + } + // if the orig state does not contain this filename, + // it's an optional argument for which the user specified + // that it should not be returned as a state + if (!origState_.containsKey(plainName_)) { + return [] + } + def filenameTemplate = origState_[plainName_] + // if the pararameter is multiple: true, fetch the template + if (par.multiple && filenameTemplate instanceof List) { + filenameTemplate = filenameTemplate[0] + } + // instantiate the template + def filename = filenameTemplate + .replaceAll('\\$id', id_) + .replaceAll('\\$\\{id\\}', id_) + .replaceAll('\\$key', key_) + .replaceAll('\\$\\{key\\}', key_) + if (par.multiple) { + // if the parameter is multiple: true, the filename + // should contain a wildcard '*' that is replaced with + // the index of the file + assert filename.contains("*") : "Module '${key_}' id '${id_}': Multiple output files specified, but no wildcard '*' in the filename: ${filename}" + def outputPerFile = value.withIndex().collect{ val, ix -> + def filename_ix = filename.replace("*", ix.toString()) + def value_ = java.nio.file.Paths.get(filename_ix) + // if id contains a slash + if (yamlDir != null) { + value_ = yamlDir.relativize(value_) + } + def inputPath = val instanceof File ? val.toPath() : val + [value: value_, inputPath: inputPath, outputFilename: filename_ix] + } + def transposedOutputs = ["value", "inputPath", "outputFilename"].collectEntries{ key -> + [key, outputPerFile.collect{dic -> dic[key]}] + } + return [[key: plainName_] + transposedOutputs] + } else { + def value_ = java.nio.file.Paths.get(filename) + // if id contains a slash + if (yamlDir != null) { + value_ = yamlDir.relativize(value_) + } + def inputPath = value instanceof File ? value.toPath() : value + return [[key: plainName_, value: value_, inputPath: [inputPath], outputFilename: [filename]]] + } + } + + def updatedState_ = processedState.collectEntries{[it.key, it.value]} + def inputPaths = processedState.collectMany{it.inputPath} + def outputFilenames = processedState.collectMany{it.outputFilename} + + // convert state to yaml blob + def yamlBlob_ = toTaggedYamlBlob([id: id_] + updatedState_) + + [id_, yamlBlob_, yamlFilename, inputPaths, outputFilenames] + } + | publishStatesProc + emit: input_ch + } + return publishStatesSimpleWf +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/states/setState.nf' +def setState(fun) { + assert fun instanceof Closure || fun instanceof Map || fun instanceof List : + "Error in setState: Expected process argument to be a Closure, a Map, or a List. Found: class ${fun.getClass()}" + + // if fun is a List, convert to map + if (fun instanceof List) { + // check whether fun is a list[string] + assert fun.every{it instanceof CharSequence} : "Error in setState: argument is a List, but not all elements are Strings" + fun = fun.collectEntries{[it, it]} + } + + // if fun is a map, convert to closure + if (fun instanceof Map) { + // check whether fun is a map[string, string] + assert fun.values().every{it instanceof CharSequence} : "Error in setState: argument is a Map, but not all values are Strings" + assert fun.keySet().every{it instanceof CharSequence} : "Error in setState: argument is a Map, but not all keys are Strings" + def funMap = fun.clone() + // turn the map into a closure to be used later on + fun = { id_, state_ -> + assert state_ instanceof Map : "Error in setState: the state is not a Map" + funMap.collectMany{newkey, origkey -> + if (state_.containsKey(origkey)) { + [[newkey, state_[origkey]]] + } else { + [] + } + }.collectEntries() + } + } + + map { tup -> + def id = tup[0] + def state = tup[1] + def unfilteredState = fun(id, state) + def newState = unfilteredState.findAll{key, val -> val != null} + [id, newState] + tup.drop(2) + } +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processAuto.nf' +// TODO: unit test processAuto +def processAuto(Map auto) { + // remove null values + auto = auto.findAll{k, v -> v != null} + + // check for unexpected keys + def expectedKeys = ["simplifyInput", "simplifyOutput", "transcript", "publish"] + def unexpectedKeys = auto.keySet() - expectedKeys + assert unexpectedKeys.isEmpty(), "unexpected keys in auto: '${unexpectedKeys.join("', '")}'" + + // check auto.simplifyInput + assert auto.simplifyInput instanceof Boolean, "auto.simplifyInput must be a boolean" + + // check auto.simplifyOutput + assert auto.simplifyOutput instanceof Boolean, "auto.simplifyOutput must be a boolean" + + // check auto.transcript + assert auto.transcript instanceof Boolean, "auto.transcript must be a boolean" + + // check auto.publish + assert auto.publish instanceof Boolean || auto.publish == "state", "auto.publish must be a boolean or 'state'" + + return auto.subMap(expectedKeys) +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processDirectives.nf' +def assertMapKeys(map, expectedKeys, requiredKeys, mapName) { + assert map instanceof Map : "Expected argument '$mapName' to be a Map. Found: class ${map.getClass()}" + map.forEach { key, val -> + assert key in expectedKeys : "Unexpected key '$key' in ${mapName ? mapName + " " : ""}map" + } + requiredKeys.forEach { requiredKey -> + assert map.containsKey(requiredKey) : "Missing required key '$key' in ${mapName ? mapName + " " : ""}map" + } +} + +// TODO: unit test processDirectives +def processDirectives(Map drctv) { + // remove null values + drctv = drctv.findAll{k, v -> v != null} + + // check for unexpected keys + def expectedKeys = [ + "accelerator", "afterScript", "beforeScript", "cache", "conda", "container", "containerOptions", "cpus", "disk", "echo", "errorStrategy", "executor", "machineType", "maxErrors", "maxForks", "maxRetries", "memory", "module", "penv", "pod", "publishDir", "queue", "label", "scratch", "storeDir", "stageInMode", "stageOutMode", "tag", "time" + ] + def unexpectedKeys = drctv.keySet() - expectedKeys + assert unexpectedKeys.isEmpty() : "Unexpected keys in process directive: '${unexpectedKeys.join("', '")}'" + + /* DIRECTIVE accelerator + accepted examples: + - [ limit: 4, type: "nvidia-tesla-k80" ] + */ + if (drctv.containsKey("accelerator")) { + assertMapKeys(drctv["accelerator"], ["type", "limit", "request", "runtime"], [], "accelerator") + } + + /* DIRECTIVE afterScript + accepted examples: + - "source /cluster/bin/cleanup" + */ + if (drctv.containsKey("afterScript")) { + assert drctv["afterScript"] instanceof CharSequence + } + + /* DIRECTIVE beforeScript + accepted examples: + - "source /cluster/bin/setup" + */ + if (drctv.containsKey("beforeScript")) { + assert drctv["beforeScript"] instanceof CharSequence + } + + /* DIRECTIVE cache + accepted examples: + - true + - false + - "deep" + - "lenient" + */ + if (drctv.containsKey("cache")) { + assert drctv["cache"] instanceof CharSequence || drctv["cache"] instanceof Boolean + if (drctv["cache"] instanceof CharSequence) { + assert drctv["cache"] in ["deep", "lenient"] : "Unexpected value for cache" + } + } + + /* DIRECTIVE conda + accepted examples: + - "bwa=0.7.15" + - "bwa=0.7.15 fastqc=0.11.5" + - ["bwa=0.7.15", "fastqc=0.11.5"] + */ + if (drctv.containsKey("conda")) { + if (drctv["conda"] instanceof List) { + drctv["conda"] = drctv["conda"].join(" ") + } + assert drctv["conda"] instanceof CharSequence + } + + /* DIRECTIVE container + accepted examples: + - "foo/bar:tag" + - [ registry: "reg", image: "im", tag: "ta" ] + is transformed to "reg/im:ta" + - [ image: "im" ] + is transformed to "im:latest" + */ + if (drctv.containsKey("container")) { + assert drctv["container"] instanceof Map || drctv["container"] instanceof CharSequence + if (drctv["container"] instanceof Map) { + def m = drctv["container"] + assertMapKeys(m, [ "registry", "image", "tag" ], ["image"], "container") + def part1 = + System.getenv('OVERRIDE_CONTAINER_REGISTRY') ? System.getenv('OVERRIDE_CONTAINER_REGISTRY') + "/" : + params.containsKey("override_container_registry") ? params["override_container_registry"] + "/" : // todo: remove? + m.registry ? m.registry + "/" : + "" + def part2 = m.image + def part3 = m.tag ? ":" + m.tag : ":latest" + drctv["container"] = part1 + part2 + part3 + } + } + + /* DIRECTIVE containerOptions + accepted examples: + - "--foo bar" + - ["--foo bar", "-f b"] + */ + if (drctv.containsKey("containerOptions")) { + if (drctv["containerOptions"] instanceof List) { + drctv["containerOptions"] = drctv["containerOptions"].join(" ") + } + assert drctv["containerOptions"] instanceof CharSequence + } + + /* DIRECTIVE cpus + accepted examples: + - 1 + - 10 + */ + if (drctv.containsKey("cpus")) { + assert drctv["cpus"] instanceof Integer + } + + /* DIRECTIVE disk + accepted examples: + - "1 GB" + - "2TB" + - "3.2KB" + - "10.B" + */ + if (drctv.containsKey("disk")) { + assert drctv["disk"] instanceof CharSequence + // assert drctv["disk"].matches("[0-9]+(\\.[0-9]*)? *[KMGTPEZY]?B") + // ^ does not allow closures + } + + /* DIRECTIVE echo + accepted examples: + - true + - false + */ + if (drctv.containsKey("echo")) { + assert drctv["echo"] instanceof Boolean + } + + /* DIRECTIVE errorStrategy + accepted examples: + - "terminate" + - "finish" + */ + if (drctv.containsKey("errorStrategy")) { + assert drctv["errorStrategy"] instanceof CharSequence + assert drctv["errorStrategy"] in ["terminate", "finish", "ignore", "retry"] : "Unexpected value for errorStrategy" + } + + /* DIRECTIVE executor + accepted examples: + - "local" + - "sge" + */ + if (drctv.containsKey("executor")) { + assert drctv["executor"] instanceof CharSequence + assert drctv["executor"] in ["local", "sge", "uge", "lsf", "slurm", "pbs", "pbspro", "moab", "condor", "nqsii", "ignite", "k8s", "awsbatch", "google-pipelines"] : "Unexpected value for executor" + } + + /* DIRECTIVE machineType + accepted examples: + - "n1-highmem-8" + */ + if (drctv.containsKey("machineType")) { + assert drctv["machineType"] instanceof CharSequence + } + + /* DIRECTIVE maxErrors + accepted examples: + - 1 + - 3 + */ + if (drctv.containsKey("maxErrors")) { + assert drctv["maxErrors"] instanceof Integer + } + + /* DIRECTIVE maxForks + accepted examples: + - 1 + - 3 + */ + if (drctv.containsKey("maxForks")) { + assert drctv["maxForks"] instanceof Integer + } + + /* DIRECTIVE maxRetries + accepted examples: + - 1 + - 3 + */ + if (drctv.containsKey("maxRetries")) { + assert drctv["maxRetries"] instanceof Integer + } + + /* DIRECTIVE memory + accepted examples: + - "1 GB" + - "2TB" + - "3.2KB" + - "10.B" + */ + if (drctv.containsKey("memory")) { + assert drctv["memory"] instanceof CharSequence + // assert drctv["memory"].matches("[0-9]+(\\.[0-9]*)? *[KMGTPEZY]?B") + // ^ does not allow closures + } + + /* DIRECTIVE module + accepted examples: + - "ncbi-blast/2.2.27" + - "ncbi-blast/2.2.27:t_coffee/10.0" + - ["ncbi-blast/2.2.27", "t_coffee/10.0"] + */ + if (drctv.containsKey("module")) { + if (drctv["module"] instanceof List) { + drctv["module"] = drctv["module"].join(":") + } + assert drctv["module"] instanceof CharSequence + } + + /* DIRECTIVE penv + accepted examples: + - "smp" + */ + if (drctv.containsKey("penv")) { + assert drctv["penv"] instanceof CharSequence + } + + /* DIRECTIVE pod + accepted examples: + - [ label: "key", value: "val" ] + - [ annotation: "key", value: "val" ] + - [ env: "key", value: "val" ] + - [ [label: "l", value: "v"], [env: "e", value: "v"]] + */ + if (drctv.containsKey("pod")) { + if (drctv["pod"] instanceof Map) { + drctv["pod"] = [ drctv["pod"] ] + } + assert drctv["pod"] instanceof List + drctv["pod"].forEach { pod -> + assert pod instanceof Map + // TODO: should more checks be added? + // See https://www.nextflow.io/docs/latest/process.html?highlight=directives#pod + // e.g. does it contain 'label' and 'value', or 'annotation' and 'value', or ...? + } + } + + /* DIRECTIVE publishDir + accepted examples: + - [] + - [ [ path: "foo", enabled: true ], [ path: "bar", enabled: false ] ] + - "/path/to/dir" + is transformed to [[ path: "/path/to/dir" ]] + - [ path: "/path/to/dir", mode: "cache" ] + is transformed to [[ path: "/path/to/dir", mode: "cache" ]] + */ + // TODO: should we also look at params["publishDir"]? + if (drctv.containsKey("publishDir")) { + def pblsh = drctv["publishDir"] + + // check different options + assert pblsh instanceof List || pblsh instanceof Map || pblsh instanceof CharSequence + + // turn into list if not already so + // for some reason, 'if (!pblsh instanceof List) pblsh = [ pblsh ]' doesn't work. + pblsh = pblsh instanceof List ? pblsh : [ pblsh ] + + // check elements of publishDir + pblsh = pblsh.collect{ elem -> + // turn into map if not already so + elem = elem instanceof CharSequence ? [ path: elem ] : elem + + // check types and keys + assert elem instanceof Map : "Expected publish argument '$elem' to be a String or a Map. Found: class ${elem.getClass()}" + assertMapKeys(elem, [ "path", "mode", "overwrite", "pattern", "saveAs", "enabled" ], ["path"], "publishDir") + + // check elements in map + assert elem.containsKey("path") + assert elem["path"] instanceof CharSequence + if (elem.containsKey("mode")) { + assert elem["mode"] instanceof CharSequence + assert elem["mode"] in [ "symlink", "rellink", "link", "copy", "copyNoFollow", "move" ] + } + if (elem.containsKey("overwrite")) { + assert elem["overwrite"] instanceof Boolean + } + if (elem.containsKey("pattern")) { + assert elem["pattern"] instanceof CharSequence + } + if (elem.containsKey("saveAs")) { + assert elem["saveAs"] instanceof CharSequence //: "saveAs as a Closure is currently not supported. Surround your closure with single quotes to get the desired effect. Example: '\{ foo \}'" + } + if (elem.containsKey("enabled")) { + assert elem["enabled"] instanceof Boolean + } + + // return final result + elem + } + // store final directive + drctv["publishDir"] = pblsh + } + + /* DIRECTIVE queue + accepted examples: + - "long" + - "short,long" + - ["short", "long"] + */ + if (drctv.containsKey("queue")) { + if (drctv["queue"] instanceof List) { + drctv["queue"] = drctv["queue"].join(",") + } + assert drctv["queue"] instanceof CharSequence + } + + /* DIRECTIVE label + accepted examples: + - "big_mem" + - "big_cpu" + - ["big_mem", "big_cpu"] + */ + if (drctv.containsKey("label")) { + if (drctv["label"] instanceof CharSequence) { + drctv["label"] = [ drctv["label"] ] + } + assert drctv["label"] instanceof List + drctv["label"].forEach { label -> + assert label instanceof CharSequence + // assert label.matches("[a-zA-Z0-9]([a-zA-Z0-9_]*[a-zA-Z0-9])?") + // ^ does not allow closures + } + } + + /* DIRECTIVE scratch + accepted examples: + - true + - "/path/to/scratch" + - '$MY_PATH_TO_SCRATCH' + - "ram-disk" + */ + if (drctv.containsKey("scratch")) { + assert drctv["scratch"] == true || drctv["scratch"] instanceof CharSequence + } + + /* DIRECTIVE storeDir + accepted examples: + - "/path/to/storeDir" + */ + if (drctv.containsKey("storeDir")) { + assert drctv["storeDir"] instanceof CharSequence + } + + /* DIRECTIVE stageInMode + accepted examples: + - "copy" + - "link" + */ + if (drctv.containsKey("stageInMode")) { + assert drctv["stageInMode"] instanceof CharSequence + assert drctv["stageInMode"] in ["copy", "link", "symlink", "rellink"] + } + + /* DIRECTIVE stageOutMode + accepted examples: + - "copy" + - "link" + */ + if (drctv.containsKey("stageOutMode")) { + assert drctv["stageOutMode"] instanceof CharSequence + assert drctv["stageOutMode"] in ["copy", "move", "rsync"] + } + + /* DIRECTIVE tag + accepted examples: + - "foo" + - '$id' + */ + if (drctv.containsKey("tag")) { + assert drctv["tag"] instanceof CharSequence + } + + /* DIRECTIVE time + accepted examples: + - "1h" + - "2days" + - "1day 6hours 3minutes 30seconds" + */ + if (drctv.containsKey("time")) { + assert drctv["time"] instanceof CharSequence + // todo: validation regex? + } + + return drctv +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/processWorkflowArgs.nf' +def processWorkflowArgs(Map args, Map defaultWfArgs, Map meta) { + // override defaults with args + def workflowArgs = defaultWfArgs + args + + // check whether 'key' exists + assert workflowArgs.containsKey("key") : "Error in module '${meta.config.name}': key is a required argument" + + // if 'key' is a closure, apply it to the original key + if (workflowArgs["key"] instanceof Closure) { + workflowArgs["key"] = workflowArgs["key"](meta.config.name) + } + def key = workflowArgs["key"] + assert key instanceof CharSequence : "Expected process argument 'key' to be a String. Found: class ${key.getClass()}" + assert key ==~ /^[a-zA-Z_]\w*$/ : "Error in module '$key': Expected process argument 'key' to consist of only letters, digits or underscores. Found: ${key}" + + // check for any unexpected keys + def expectedKeys = ["key", "directives", "auto", "map", "mapId", "mapData", "mapPassthrough", "filter", "runIf", "fromState", "toState", "args", "renameKeys", "debug"] + def unexpectedKeys = workflowArgs.keySet() - expectedKeys + assert unexpectedKeys.isEmpty() : "Error in module '$key': unexpected arguments to the '.run()' function: '${unexpectedKeys.join("', '")}'" + + // check whether directives exists and apply defaults + assert workflowArgs.containsKey("directives") : "Error in module '$key': directives is a required argument" + assert workflowArgs["directives"] instanceof Map : "Error in module '$key': Expected process argument 'directives' to be a Map. Found: class ${workflowArgs['directives'].getClass()}" + workflowArgs["directives"] = processDirectives(defaultWfArgs.directives + workflowArgs["directives"]) + + // check whether directives exists and apply defaults + assert workflowArgs.containsKey("auto") : "Error in module '$key': auto is a required argument" + assert workflowArgs["auto"] instanceof Map : "Error in module '$key': Expected process argument 'auto' to be a Map. Found: class ${workflowArgs['auto'].getClass()}" + workflowArgs["auto"] = processAuto(defaultWfArgs.auto + workflowArgs["auto"]) + + // auto define publish, if so desired + if (workflowArgs.auto.publish == true && (workflowArgs.directives.publishDir != null ? workflowArgs.directives.publishDir : [:]).isEmpty()) { + // can't assert at this level thanks to the no_publish profile + // assert params.containsKey("publishDir") || params.containsKey("publish_dir") : + // "Error in module '${workflowArgs['key']}': if auto.publish is true, params.publish_dir needs to be defined.\n" + + // " Example: params.publish_dir = \"./output/\"" + def publishDir = getPublishDir() + + if (publishDir != null) { + workflowArgs.directives.publishDir = [[ + path: publishDir, + saveAs: "{ it.startsWith('.') ? null : it }", // don't publish hidden files, by default + mode: "copy" + ]] + } + } + + // auto define transcript, if so desired + if (workflowArgs.auto.transcript == true) { + // can't assert at this level thanks to the no_publish profile + // assert params.containsKey("transcriptsDir") || params.containsKey("transcripts_dir") || params.containsKey("publishDir") || params.containsKey("publish_dir") : + // "Error in module '${workflowArgs['key']}': if auto.transcript is true, either params.transcripts_dir or params.publish_dir needs to be defined.\n" + + // " Example: params.transcripts_dir = \"./transcripts/\"" + def transcriptsDir = + params.containsKey("transcripts_dir") ? params.transcripts_dir : + params.containsKey("transcriptsDir") ? params.transcriptsDir : + params.containsKey("publish_dir") ? params.publish_dir + "/_transcripts" : + params.containsKey("publishDir") ? params.publishDir + "/_transcripts" : + null + if (transcriptsDir != null) { + def timestamp = nextflow.Nextflow.getSession().getWorkflowMetadata().start.format('yyyy-MM-dd_HH-mm-ss') + def transcriptsPublishDir = [ + path: "$transcriptsDir/$timestamp/\${task.process.replaceAll(':', '-')}/\${id}/", + saveAs: "{ it.startsWith('.') ? it.replaceAll('^.', '') : null }", + mode: "copy" + ] + def publishDirs = workflowArgs.directives.publishDir != null ? workflowArgs.directives.publishDir : null ? workflowArgs.directives.publishDir : [] + workflowArgs.directives.publishDir = publishDirs + transcriptsPublishDir + } + } + + // if this is a stubrun, remove certain directives? + if (workflow.stubRun) { + workflowArgs.directives.keySet().removeAll(["publishDir", "cpus", "memory", "label"]) + } + + for (nam in ["map", "mapId", "mapData", "mapPassthrough", "filter", "runIf"]) { + if (workflowArgs.containsKey(nam) && workflowArgs[nam]) { + assert workflowArgs[nam] instanceof Closure : "Error in module '$key': Expected process argument '$nam' to be null or a Closure. Found: class ${workflowArgs[nam].getClass()}" + } + } + + // TODO: should functions like 'map', 'mapId', 'mapData', 'mapPassthrough' be deprecated as well? + for (nam in ["map", "mapData", "mapPassthrough", "renameKeys"]) { + if (workflowArgs.containsKey(nam) && workflowArgs[nam] != null) { + log.warn "module '$key': workflow argument '$nam' is deprecated and will be removed in Viash 0.9.0. Please use 'fromState' and 'toState' instead." + } + } + + // check fromState + workflowArgs["fromState"] = _processFromState(workflowArgs.get("fromState"), key, meta.config) + + // check toState + workflowArgs["toState"] = _processToState(workflowArgs.get("toState"), key, meta.config) + + // return output + return workflowArgs +} + +def _processFromState(fromState, key_, config_) { + assert fromState == null || fromState instanceof Closure || fromState instanceof Map || fromState instanceof List : + "Error in module '$key_': Expected process argument 'fromState' to be null, a Closure, a Map, or a List. Found: class ${fromState.getClass()}" + if (fromState == null) { + return null + } + + // if fromState is a List, convert to map + if (fromState instanceof List) { + // check whether fromstate is a list[string] + assert fromState.every{it instanceof CharSequence} : "Error in module '$key_': fromState is a List, but not all elements are Strings" + fromState = fromState.collectEntries{[it, it]} + } + + // if fromState is a map, convert to closure + if (fromState instanceof Map) { + // check whether fromstate is a map[string, string] + assert fromState.values().every{it instanceof CharSequence} : "Error in module '$key_': fromState is a Map, but not all values are Strings" + assert fromState.keySet().every{it instanceof CharSequence} : "Error in module '$key_': fromState is a Map, but not all keys are Strings" + def fromStateMap = fromState.clone() + def requiredInputNames = meta.config.allArguments.findAll{it.required && it.direction == "Input"}.collect{it.plainName} + // turn the map into a closure to be used later on + fromState = { it -> + def state = it[1] + assert state instanceof Map : "Error in module '$key_': the state is not a Map" + def data = fromStateMap.collectMany{newkey, origkey -> + // check whether newkey corresponds to a required argument + if (state.containsKey(origkey)) { + [[newkey, state[origkey]]] + } else if (!requiredInputNames.contains(origkey)) { + [] + } else { + throw new Exception("Error in module '$key_': fromState key '$origkey' not found in current state") + } + }.collectEntries() + data + } + } + + return fromState +} + +def _processToState(toState, key_, config_) { + if (toState == null) { + toState = { tup -> tup[1] } + } + + // toState should be a closure, map[string, string], or list[string] + assert toState instanceof Closure || toState instanceof Map || toState instanceof List : + "Error in module '$key_': Expected process argument 'toState' to be a Closure, a Map, or a List. Found: class ${toState.getClass()}" + + // if toState is a List, convert to map + if (toState instanceof List) { + // check whether toState is a list[string] + assert toState.every{it instanceof CharSequence} : "Error in module '$key_': toState is a List, but not all elements are Strings" + toState = toState.collectEntries{[it, it]} + } + + // if toState is a map, convert to closure + if (toState instanceof Map) { + // check whether toState is a map[string, string] + assert toState.values().every{it instanceof CharSequence} : "Error in module '$key_': toState is a Map, but not all values are Strings" + assert toState.keySet().every{it instanceof CharSequence} : "Error in module '$key_': toState is a Map, but not all keys are Strings" + def toStateMap = toState.clone() + def requiredOutputNames = config_.allArguments.findAll{it.required && it.direction == "Output"}.collect{it.plainName} + // turn the map into a closure to be used later on + toState = { it -> + def output = it[1] + def state = it[2] + assert output instanceof Map : "Error in module '$key_': the output is not a Map" + assert state instanceof Map : "Error in module '$key_': the state is not a Map" + def extraEntries = toStateMap.collectMany{newkey, origkey -> + // check whether newkey corresponds to a required argument + if (output.containsKey(origkey)) { + [[newkey, output[origkey]]] + } else if (!requiredOutputNames.contains(origkey)) { + [] + } else { + throw new Exception("Error in module '$key_': toState key '$origkey' not found in current output") + } + }.collectEntries() + state + extraEntries + } + } + + return toState +} + +// helper file: 'src/main/resources/io/viash/runners/nextflow/workflowFactory/workflowFactory.nf' +def _debug(workflowArgs, debugKey) { + if (workflowArgs.debug) { + view { "process '${workflowArgs.key}' $debugKey tuple: $it" } + } else { + map { it } + } +} + +// depends on: innerWorkflowFactory +def workflowFactory(Map args, Map defaultWfArgs, Map meta) { + def workflowArgs = processWorkflowArgs(args, defaultWfArgs, meta) + def key_ = workflowArgs["key"] + + workflow workflowInstance { + take: input_ + + main: + def chModified = input_ + | checkUniqueIds([:]) + | _debug(workflowArgs, "input") + | map { tuple -> + tuple = deepClone(tuple) + + if (workflowArgs.map) { + tuple = workflowArgs.map(tuple) + } + if (workflowArgs.mapId) { + tuple[0] = workflowArgs.mapId(tuple[0]) + } + if (workflowArgs.mapData) { + tuple[1] = workflowArgs.mapData(tuple[1]) + } + if (workflowArgs.mapPassthrough) { + tuple = tuple.take(2) + workflowArgs.mapPassthrough(tuple.drop(2)) + } + + // check tuple + assert tuple instanceof List : + "Error in module '${key_}': element in channel should be a tuple [id, data, ...otherargs...]\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Expected class: List. Found: tuple.getClass() is ${tuple.getClass()}" + assert tuple.size() >= 2 : + "Error in module '${key_}': expected length of tuple in input channel to be two or greater.\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Found: tuple.size() == ${tuple.size()}" + + // check id field + if (tuple[0] instanceof GString) { + tuple[0] = tuple[0].toString() + } + assert tuple[0] instanceof CharSequence : + "Error in module '${key_}': first element of tuple in channel should be a String\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Found: ${tuple[0]}" + + // match file to input file + if (workflowArgs.auto.simplifyInput && (tuple[1] instanceof Path || tuple[1] instanceof List)) { + def inputFiles = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "input" } + + assert inputFiles.size() == 1 : + "Error in module '${key_}' id '${tuple[0]}'.\n" + + " Anonymous file inputs are only allowed when the process has exactly one file input.\n" + + " Expected: inputFiles.size() == 1. Found: inputFiles.size() is ${inputFiles.size()}" + + tuple[1] = [[ inputFiles[0].plainName, tuple[1] ]].collectEntries() + } + + // check data field + assert tuple[1] instanceof Map : + "Error in module '${key_}' id '${tuple[0]}': second element of tuple in channel should be a Map\n" + + " Example: [\"id\", [input: file('foo.txt'), arg: 10]].\n" + + " Expected class: Map. Found: tuple[1].getClass() is ${tuple[1].getClass()}" + + // rename keys of data field in tuple + if (workflowArgs.renameKeys) { + assert workflowArgs.renameKeys instanceof Map : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Example: renameKeys: ['new_key': 'old_key'].\n" + + " Expected class: Map. Found: renameKeys.getClass() is ${workflowArgs.renameKeys.getClass()}" + assert tuple[1] instanceof Map : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Expected class: Map. Found: tuple[1].getClass() is ${tuple[1].getClass()}" + + // TODO: allow renameKeys to be a function? + workflowArgs.renameKeys.each { newKey, oldKey -> + assert newKey instanceof CharSequence : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Example: renameKeys: ['new_key': 'old_key'].\n" + + " Expected class of newKey: String. Found: newKey.getClass() is ${newKey.getClass()}" + assert oldKey instanceof CharSequence : + "Error renaming data keys in module '${key_}' id '${tuple[0]}'.\n" + + " Example: renameKeys: ['new_key': 'old_key'].\n" + + " Expected class of oldKey: String. Found: oldKey.getClass() is ${oldKey.getClass()}" + assert tuple[1].containsKey(oldKey) : + "Error renaming data keys in module '${key}' id '${tuple[0]}'.\n" + + " Key '$oldKey' is missing in the data map. tuple[1].keySet() is '${tuple[1].keySet()}'" + tuple[1].put(newKey, tuple[1][oldKey]) + } + tuple[1].keySet().removeAll(workflowArgs.renameKeys.collect{ newKey, oldKey -> oldKey }) + } + tuple + } + + + def chRun = null + def chPassthrough = null + if (workflowArgs.runIf) { + def runIfBranch = chModified.branch{ tup -> + run: workflowArgs.runIf(tup[0], tup[1]) + passthrough: true + } + chRun = runIfBranch.run + chPassthrough = runIfBranch.passthrough + } else { + chRun = chModified + chPassthrough = Channel.empty() + } + + def chRunFiltered = workflowArgs.filter ? + chRun | filter{workflowArgs.filter(it)} : + chRun + + def chArgs = workflowArgs.fromState ? + chRunFiltered | map{ + def new_data = workflowArgs.fromState(it.take(2)) + [it[0], new_data] + } : + chRunFiltered | map {tup -> tup.take(2)} + + // fill in defaults + def chArgsWithDefaults = chArgs + | map { tuple -> + def id_ = tuple[0] + def data_ = tuple[1] + + // TODO: could move fromState to here + + // fetch default params from functionality + def defaultArgs = meta.config.allArguments + .findAll { it.containsKey("default") } + .collectEntries { [ it.plainName, it.default ] } + + // fetch overrides in params + def paramArgs = meta.config.allArguments + .findAll { par -> + def argKey = key_ + "__" + par.plainName + params.containsKey(argKey) + } + .collectEntries { [ it.plainName, params[key_ + "__" + it.plainName] ] } + + // fetch overrides in data + def dataArgs = meta.config.allArguments + .findAll { data_.containsKey(it.plainName) } + .collectEntries { [ it.plainName, data_[it.plainName] ] } + + // combine params + def combinedArgs = defaultArgs + paramArgs + workflowArgs.args + dataArgs + + // remove arguments with explicit null values + combinedArgs + .removeAll{_, val -> val == null || val == "viash_no_value" || val == "force_null"} + + combinedArgs = _processInputValues(combinedArgs, meta.config, id_, key_) + + [id_, combinedArgs] + tuple.drop(2) + } + + // TODO: move some of the _meta.join_id wrangling to the safeJoin() function. + def chInitialOutput = chArgsWithDefaults + | _debug(workflowArgs, "processed") + // run workflow + | innerWorkflowFactory(workflowArgs) + // check output tuple + | map { id_, output_ -> + + // see if output map contains metadata + def meta_ = + output_ instanceof Map && output_.containsKey("_meta") ? + output_["_meta"] : + [:] + def join_id = meta_.join_id ?: id_ + + // remove metadata + output_ = output_.findAll{k, v -> k != "_meta"} + + // check value types + output_ = _processOutputValues(output_, meta.config, id_, key_) + + // simplify output if need be + if (workflowArgs.auto.simplifyOutput && output_.size() == 1) { + output_ = output_.values()[0] + } + + [join_id, id_, output_] + } + // | view{"chInitialOutput: ${it.take(3)}"} + + // join the output [prev_id, new_id, output] with the previous state [prev_id, state, ...] + def chNewState = safeJoin(chInitialOutput, chRunFiltered, key_) + // input tuple format: [join_id, id, output, prev_state, ...] + // output tuple format: [join_id, id, new_state, ...] + | map{ tup -> + def new_state = workflowArgs.toState(tup.drop(1).take(3)) + tup.take(2) + [new_state] + tup.drop(4) + } + + if (workflowArgs.auto.publish == "state") { + def chPublish = chNewState + // input tuple format: [join_id, id, new_state, ...] + // output tuple format: [join_id, id, new_state] + | map{ tup -> + tup.take(3) + } + + safeJoin(chPublish, chArgsWithDefaults, key_) + // input tuple format: [join_id, id, new_state, orig_state, ...] + // output tuple format: [id, new_state, orig_state] + | map { tup -> + tup.drop(1).take(3) + } + | publishStatesByConfig(key: key_, config: meta.config) + } + + // remove join_id and meta + chReturn = chNewState + | map { tup -> + // input tuple format: [join_id, id, new_state, ...] + // output tuple format: [id, new_state, ...] + tup.drop(1) + } + | _debug(workflowArgs, "output") + | concat(chPassthrough) + + emit: chReturn + } + + def wf = workflowInstance.cloneWithName(key_) + + // add factory function + wf.metaClass.run = { runArgs -> + workflowFactory(runArgs, workflowArgs, meta) + } + // add config to module for later introspection + wf.metaClass.config = meta.config + + return wf +} + +nextflow.enable.dsl=2 + +// START COMPONENT-SPECIFIC CODE + +// create meta object +meta = [ + "resources_dir": moduleDir.toRealPath().normalize(), + "config": processConfig(readJsonBlob('''{ + "name" : "create_report", + "namespace" : "report", + "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], + "argument_groups" : [ + { + "name" : "Arguments", + "arguments" : [ + { + "type" : "file", + "name" : "--eset", + "must_exist" : true, + "create_parent" : true, + "required" : true, + "direction" : "input", + "multiple" : true, + "multiple_sep" : ";" + }, + { + "type" : "file", + "name" : "--output_report", + "example" : [ + "report.html" + ], + "must_exist" : true, + "create_parent" : true, + "required" : true, + "direction" : "output", + "multiple" : false, + "multiple_sep" : ";" + } + ] + } + ], + "resources" : [ + { + "type" : "r_script", + "path" : "script.R", + "is_executable" : true + }, + { + "type" : "r_script", + "path" : "template.Rmd", + "is_executable" : true + }, + { + "type" : "r_script", + "path" : "plateLayouts.R", + "is_executable" : true + }, + { + "type" : "file", + "path" : "OutputSTARsolo.png" + }, + { + "type" : "file", + "path" : "/src/config/labels.config", + "dest" : "nextflow_labels.config" + } + ], + "description" : "Create a basic QC report in HTML format based on a number of esets.\n", + "test_resources" : [ + { + "type" : "r_script", + "path" : "test.R", + "is_executable" : true + }, + { + "type" : "file", + "path" : "./test_data" + } + ], + "status" : "enabled", + "requirements" : { + "commands" : [ + "ps" + ] + }, + "license" : "MIT", + "links" : { + "repository" : "https://github.com/viash-hub/htrnaseq" + }, + "runners" : [ + { + "type" : "executable", + "id" : "executable", + "docker_setup_strategy" : "ifneedbepullelsecachedbuild" + }, + { + "type" : "nextflow", + "id" : "nextflow", + "directives" : { + "tag" : "$id" + }, + "auto" : { + "simplifyInput" : true, + "simplifyOutput" : false, + "transcript" : false, + "publish" : false + }, + "config" : { + "labels" : { + "mem1gb" : "memory = 1000000000.B", + "mem2gb" : "memory = 2000000000.B", + "mem5gb" : "memory = 5000000000.B", + "mem10gb" : "memory = 10000000000.B", + "mem20gb" : "memory = 20000000000.B", + "mem50gb" : "memory = 50000000000.B", + "mem100gb" : "memory = 100000000000.B", + "mem200gb" : "memory = 200000000000.B", + "mem500gb" : "memory = 500000000000.B", + "mem1tb" : "memory = 1000000000000.B", + "mem2tb" : "memory = 2000000000000.B", + "mem5tb" : "memory = 5000000000000.B", + "mem10tb" : "memory = 10000000000000.B", + "mem20tb" : "memory = 20000000000000.B", + "mem50tb" : "memory = 50000000000000.B", + "mem100tb" : "memory = 100000000000000.B", + "mem200tb" : "memory = 200000000000000.B", + "mem500tb" : "memory = 500000000000000.B", + "mem1gib" : "memory = 1073741824.B", + "mem2gib" : "memory = 2147483648.B", + "mem4gib" : "memory = 4294967296.B", + "mem8gib" : "memory = 8589934592.B", + "mem16gib" : "memory = 17179869184.B", + "mem32gib" : "memory = 34359738368.B", + "mem64gib" : "memory = 68719476736.B", + "mem128gib" : "memory = 137438953472.B", + "mem256gib" : "memory = 274877906944.B", + "mem512gib" : "memory = 549755813888.B", + "mem1tib" : "memory = 1099511627776.B", + "mem2tib" : "memory = 2199023255552.B", + "mem4tib" : "memory = 4398046511104.B", + "mem8tib" : "memory = 8796093022208.B", + "mem16tib" : "memory = 17592186044416.B", + "mem32tib" : "memory = 35184372088832.B", + "mem64tib" : "memory = 70368744177664.B", + "mem128tib" : "memory = 140737488355328.B", + "mem256tib" : "memory = 281474976710656.B", + "mem512tib" : "memory = 562949953421312.B", + "cpu1" : "cpus = 1", + "cpu2" : "cpus = 2", + "cpu5" : "cpus = 5", + "cpu10" : "cpus = 10", + "cpu20" : "cpus = 20", + "cpu50" : "cpus = 50", + "cpu100" : "cpus = 100", + "cpu200" : "cpus = 200", + "cpu500" : "cpus = 500", + "cpu1000" : "cpus = 1000" + }, + "script" : [ + "includeConfig(\\"nextflow_labels.config\\")" + ] + }, + "debug" : false, + "container" : "docker" + } + ], + "engines" : [ + { + "type" : "docker", + "id" : "docker", + "image" : "rocker/r2u:24.04", + "target_registry" : "images.viash-hub.com", + "target_tag" : "main", + "namespace_separator" : "/", + "setup" : [ + { + "type" : "apt", + "packages" : [ + "procps", + "pandoc" + ], + "interactive" : false + }, + { + "type" : "r", + "cran" : [ + "ggplot2", + "knitr", + "gridExtra", + "RColorBrewer", + "processx", + "whisker", + "rmarkdown", + "bookdown", + "data.table", + "platetools", + "htmltools", + "DT", + "logger", + "bit64" + ], + "bioc" : [ + "Biobase", + "ComplexHeatmap" + ], + "script" : [ + "install.packages(\\"oaStyle\\", repos = c(rdepot = \\"https://repos.openanalytics.eu/repo/public\\", getOption(\\"repos\\")))" + ], + "bioc_force_install" : false + } + ], + "test_setup" : [ + { + "type" : "r", + "packages" : [ + "testthat", + "R.utils" + ], + "bioc_force_install" : false + } + ] + }, + { + "type" : "native", + "id" : "native" + } + ], + "build_info" : { + "config" : "/workdir/root/repo/src/report/config.vsh.yaml", + "runner" : "nextflow", + "engine" : "docker|native", + "output" : "target/nextflow/report/create_report", + "viash_version" : "0.9.0", + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" + }, + "package_config" : { + "name" : "htrnaseq", + "version" : "main", + "description" : "High-throughput pipeline [WIP]\n", + "info" : { + "test_resources" : [ + { + "path" : "gs://viash-hub-test-data/htrnaseq/v1/", + "dest" : "resources_test" + } + ] + }, + "viash_version" : "0.9.0", + "source" : "src", + "target" : "target", + "config_mods" : [ + ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'\n.resources += {path: '/src/config/labels.config', dest: 'nextflow_labels.config'}\n", + ".engines += { type: \\"native\\" }", + ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'", + ".engines[.type == 'docker'].target_tag := 'main'" + ], + "keywords" : [ + "bioinformatics", + "sequence", + "high-throughput", + "mapping", + "counting", + "pipeline" + ], + "license" : "MIT", + "organization" : "vsh", + "links" : { + "repository" : "https://github.com/viash-hub/htrnaseq", + "issue_tracker" : "https://github.com/viash-hub/htrnaseq/issues" + } + } +}''')) +] + +// resolve dependencies dependencies (if any) + + +// inner workflow +// inner workflow hook +def innerWorkflowFactory(args) { + def rawScript = '''set -e +tempscript=".viash_script.sh" +cat > "$tempscript" << VIASHMAIN +## VIASH START +# The following code has been auto-generated by Viash. +# treat warnings as errors +.viash_orig_warn <- options(warn = 2) + +par <- list( + "eset" = $( if [ ! -z ${VIASH_PAR_ESET+x} ]; then echo -n "strsplit('"; echo -n "$VIASH_PAR_ESET" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "', split = ';')[[1]]"; else echo NULL; fi ), + "output_report" = $( if [ ! -z ${VIASH_PAR_OUTPUT_REPORT+x} ]; then echo -n "'"; echo -n "$VIASH_PAR_OUTPUT_REPORT" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ) +) +meta <- list( + "name" = $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo -n "'"; echo -n "$VIASH_META_NAME" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ), + "functionality_name" = $( if [ ! -z ${VIASH_META_FUNCTIONALITY_NAME+x} ]; then echo -n "'"; echo -n "$VIASH_META_FUNCTIONALITY_NAME" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ), + "resources_dir" = $( if [ ! -z ${VIASH_META_RESOURCES_DIR+x} ]; then echo -n "'"; echo -n "$VIASH_META_RESOURCES_DIR" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ), + "executable" = $( if [ ! -z ${VIASH_META_EXECUTABLE+x} ]; then echo -n "'"; echo -n "$VIASH_META_EXECUTABLE" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ), + "config" = $( if [ ! -z ${VIASH_META_CONFIG+x} ]; then echo -n "'"; echo -n "$VIASH_META_CONFIG" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ), + "temp_dir" = $( if [ ! -z ${VIASH_META_TEMP_DIR+x} ]; then echo -n "'"; echo -n "$VIASH_META_TEMP_DIR" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "'"; else echo NULL; fi ), + "cpus" = $( if [ ! -z ${VIASH_META_CPUS+x} ]; then echo -n "as.integer('"; echo -n "$VIASH_META_CPUS" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_b" = $( if [ ! -z ${VIASH_META_MEMORY_B+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_B" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_kb" = $( if [ ! -z ${VIASH_META_MEMORY_KB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_KB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_mb" = $( if [ ! -z ${VIASH_META_MEMORY_MB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_MB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_gb" = $( if [ ! -z ${VIASH_META_MEMORY_GB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_GB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_tb" = $( if [ ! -z ${VIASH_META_MEMORY_TB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_TB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_pb" = $( if [ ! -z ${VIASH_META_MEMORY_PB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_PB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_kib" = $( if [ ! -z ${VIASH_META_MEMORY_KIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_KIB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_mib" = $( if [ ! -z ${VIASH_META_MEMORY_MIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_MIB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_gib" = $( if [ ! -z ${VIASH_META_MEMORY_GIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_GIB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_tib" = $( if [ ! -z ${VIASH_META_MEMORY_TIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_TIB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ), + "memory_pib" = $( if [ ! -z ${VIASH_META_MEMORY_PIB+x} ]; then echo -n "bit64::as.integer64('"; echo -n "$VIASH_META_MEMORY_PIB" | sed "s#['\\\\]#\\\\\\\\&#g"; echo "')"; else echo NULL; fi ) +) +dep <- list( + +) + + +# restore original warn setting +options(.viash_orig_warn) +rm(.viash_orig_warn) + +## VIASH END +library(whisker) +library(logger) + +log_info("Setting temporary directory to: {meta\\$temp_dir}") +Sys.setenv(TMP = meta\\$temp_dir) +temp_folder <- tempdir(check = TRUE) +log_info("Created temporary directory {temp_folder}") + +template <- file.path(meta\\$resources_dir, "template.Rmd") + +esets_normalized <- lapply(par\\$eset, function(eset_path) { + return(file.path(normalizePath(dirname(eset_path)), basename(eset_path))) +}) + +log_info(paste0( + "Rendering markdown {template} to HTML ", + "{par\\$output_report} with esets {paste(esets_normalized, collapse = ', ')}" +)) + +rmarkdown::render( + normalizePath(template), + output_file = basename(par\\$output_report), + output_dir = dirname(par\\$output_report), + runtime = "static", + intermediates_dir = par\\$report_dir, + clean = TRUE, + params = list( + esets = esets_normalized, + outputDir = par\\$report_dir + ) +) + +log_info("Done") +VIASHMAIN +Rscript "$tempscript" +''' + + return vdsl3WorkflowFactory(args, meta, rawScript) +} + + + +/** + * Generate a workflow for VDSL3 modules. + * + * This function is called by the workflowFactory() function. + * + * Input channel: [id, input_map] + * Output channel: [id, output_map] + * + * Internally, this workflow will convert the input channel + * to a format which the Nextflow module will be able to handle. + */ +def vdsl3WorkflowFactory(Map args, Map meta, String rawScript) { + def key = args["key"] + def processObj = null + + workflow processWf { + take: input_ + main: + + if (processObj == null) { + processObj = _vdsl3ProcessFactory(args, meta, rawScript) + } + + output_ = input_ + | map { tuple -> + def id = tuple[0] + def data_ = tuple[1] + + if (workflow.stubRun) { + // add id if missing + data_ = [id: 'stub'] + data_ + } + + // process input files separately + def inputPaths = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "input" } + .collect { par -> + def val = data_.containsKey(par.plainName) ? data_[par.plainName] : [] + def inputFiles = [] + if (val == null) { + inputFiles = [] + } else if (val instanceof List) { + inputFiles = val + } else if (val instanceof Path) { + inputFiles = [ val ] + } else { + inputFiles = [] + } + if (!workflow.stubRun) { + // throw error when an input file doesn't exist + inputFiles.each{ file -> + assert file.exists() : + "Error in module '${key}' id '${id}' argument '${par.plainName}'.\n" + + " Required input file does not exist.\n" + + " Path: '$file'.\n" + + " Expected input file to exist" + } + } + inputFiles + } + + // remove input files + def argsExclInputFiles = meta.config.allArguments + .findAll { (it.type != "file" || it.direction != "input") && data_.containsKey(it.plainName) } + .collectEntries { par -> + def parName = par.plainName + def val = data_[parName] + if (par.multiple && val instanceof Collection) { + val = val.join(par.multiple_sep) + } + if (par.direction == "output" && par.type == "file") { + val = val + .replaceAll('\\$id', id) + .replaceAll('\\$\\{id\\}', id) + .replaceAll('\\$key', key) + .replaceAll('\\$\\{key\\}', key) + } + [parName, val] + } + + [ id ] + inputPaths + [ argsExclInputFiles, meta.resources_dir ] + } + | processObj + | map { output -> + def outputFiles = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" } + .indexed() + .collectEntries{ index, par -> + def out = output[index + 1] + // strip dummy '.exitcode' file from output (see nextflow-io/nextflow#2678) + if (!out instanceof List || out.size() <= 1) { + if (par.multiple) { + out = [] + } else { + assert !par.required : + "Error in module '${key}' id '${output[0]}' argument '${par.plainName}'.\n" + + " Required output file is missing" + out = null + } + } else if (out.size() == 2 && !par.multiple) { + out = out[1] + } else { + out = out.drop(1) + } + [ par.plainName, out ] + } + + // drop null outputs + outputFiles.removeAll{it.value == null} + + [ output[0], outputFiles ] + } + emit: output_ + } + + return processWf +} + +// depends on: session? +def _vdsl3ProcessFactory(Map workflowArgs, Map meta, String rawScript) { + // autodetect process key + def wfKey = workflowArgs["key"] + def procKeyPrefix = "${wfKey}_process" + def scriptMeta = nextflow.script.ScriptMeta.current() + def existing = scriptMeta.getProcessNames().findAll{it.startsWith(procKeyPrefix)} + def numbers = existing.collect{it.replace(procKeyPrefix, "0").toInteger()} + def newNumber = (numbers + [-1]).max() + 1 + + def procKey = newNumber == 0 ? procKeyPrefix : "$procKeyPrefix$newNumber" + + if (newNumber > 0) { + log.warn "Key for module '${wfKey}' is duplicated.\n", + "If you run a component multiple times in the same workflow,\n" + + "it's recommended you set a unique key for every call,\n" + + "for example: ${wfKey}.run(key: \"foo\")." + } + + // subset directives and convert to list of tuples + def drctv = workflowArgs.directives + + // TODO: unit test the two commands below + // convert publish array into tags + def valueToStr = { val -> + // ignore closures + if (val instanceof CharSequence) { + if (!val.matches('^[{].*[}]$')) { + '"' + val + '"' + } else { + val + } + } else if (val instanceof List) { + "[" + val.collect{valueToStr(it)}.join(", ") + "]" + } else if (val instanceof Map) { + "[" + val.collect{k, v -> k + ": " + valueToStr(v)}.join(", ") + "]" + } else { + val.inspect() + } + } + + // multiple entries allowed: label, publishdir + def drctvStrs = drctv.collect { key, value -> + if (key in ["label", "publishDir"]) { + value.collect{ val -> + if (val instanceof Map) { + "\n$key " + val.collect{ k, v -> k + ": " + valueToStr(v) }.join(", ") + } else if (val == null) { + "" + } else { + "\n$key " + valueToStr(val) + } + }.join() + } else if (value instanceof Map) { + "\n$key " + value.collect{ k, v -> k + ": " + valueToStr(v) }.join(", ") + } else { + "\n$key " + valueToStr(value) + } + }.join() + + def inputPaths = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "input" } + .collect { ', path(viash_par_' + it.plainName + ', stageAs: "_viash_par/' + it.plainName + '_?/*")' } + .join() + + def outputPaths = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" } + .collect { par -> + // insert dummy into every output (see nextflow-io/nextflow#2678) + if (!par.multiple) { + ', path{[".exitcode", args.' + par.plainName + ']}' + } else { + ', path{[".exitcode"] + args.' + par.plainName + '}' + } + } + .join() + + // TODO: move this functionality somewhere else? + if (workflowArgs.auto.transcript) { + outputPaths = outputPaths + ', path{[".exitcode", ".command*"]}' + } else { + outputPaths = outputPaths + ', path{[".exitcode"]}' + } + + // create dirs for output files (based on BashWrapper.createParentFiles) + def createParentStr = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" && it.create_parent } + .collect { par -> + def contents = "args[\"${par.plainName}\"] instanceof List ? args[\"${par.plainName}\"].join('\" \"') : args[\"${par.plainName}\"]" + "\${ args.containsKey(\"${par.plainName}\") ? \"mkdir_parent '\" + escapeText(${contents}) + \"'\" : \"\" }" + } + .join("\n") + + // construct inputFileExports + def inputFileExports = meta.config.allArguments + .findAll { it.type == "file" && it.direction.toLowerCase() == "input" } + .collect { par -> + def contents = "viash_par_${par.plainName} instanceof List ? viash_par_${par.plainName}.join(\"${par.multiple_sep}\") : viash_par_${par.plainName}" + "\n\${viash_par_${par.plainName}.empty ? \"\" : \"export VIASH_PAR_${par.plainName.toUpperCase()}='\" + escapeText(${contents}) + \"'\"}" + } + + // NOTE: if using docker, use /tmp instead of tmpDir! + def tmpDir = java.nio.file.Paths.get( + System.getenv('NXF_TEMP') ?: + System.getenv('VIASH_TEMP') ?: + System.getenv('VIASH_TMPDIR') ?: + System.getenv('VIASH_TEMPDIR') ?: + System.getenv('VIASH_TMP') ?: + System.getenv('TEMP') ?: + System.getenv('TMPDIR') ?: + System.getenv('TEMPDIR') ?: + System.getenv('TMP') ?: + '/tmp' + ).toAbsolutePath() + + // construct stub + def stub = meta.config.allArguments + .findAll { it.type == "file" && it.direction == "output" } + .collect { par -> + "\${ args.containsKey(\"${par.plainName}\") ? \"touch2 \\\"\" + (args[\"${par.plainName}\"] instanceof String ? args[\"${par.plainName}\"].replace(\"_*\", \"_0\") : args[\"${par.plainName}\"].join('\" \"')) + \"\\\"\" : \"\" }" + } + .join("\n") + + // escape script + def escapedScript = rawScript.replace('\\', '\\\\').replace('$', '\\$').replace('"""', '\\"\\"\\"') + + // publishdir assert + def assertStr = (workflowArgs.auto.publish == true) || workflowArgs.auto.transcript ? + """\nassert task.publishDir.size() > 0: "if auto.publish is true, params.publish_dir needs to be defined.\\n Example: --publish_dir './output/'" """ : + "" + + // generate process string + def procStr = + """nextflow.enable.dsl=2 + | + |def escapeText = { s -> s.toString().replaceAll("'", "'\\\"'\\\"'") } + |process $procKey {$drctvStrs + |input: + | tuple val(id)$inputPaths, val(args), path(resourcesDir, stageAs: ".viash_meta_resources") + |output: + | tuple val("\$id")$outputPaths, optional: true + |stub: + |\"\"\" + |touch2() { mkdir -p "\\\$(dirname "\\\$1")" && touch "\\\$1" ; } + |$stub + |\"\"\" + |script:$assertStr + |def parInject = args + | .findAll{key, value -> value != null} + | .collect{key, value -> "export VIASH_PAR_\${key.toUpperCase()}='\${escapeText(value)}'"} + | .join("\\n") + |\"\"\" + |# meta exports + |export VIASH_META_RESOURCES_DIR="\${resourcesDir}" + |export VIASH_META_TEMP_DIR="${['docker', 'podman', 'charliecloud'].any{ it == workflow.containerEngine } ? '/tmp' : tmpDir}" + |export VIASH_META_NAME="${meta.config.name}" + |# export VIASH_META_EXECUTABLE="\\\$VIASH_META_RESOURCES_DIR/\\\$VIASH_META_NAME" + |export VIASH_META_CONFIG="\\\$VIASH_META_RESOURCES_DIR/.config.vsh.yaml" + |\${task.cpus ? "export VIASH_META_CPUS=\$task.cpus" : "" } + |\${task.memory?.bytes != null ? "export VIASH_META_MEMORY_B=\$task.memory.bytes" : "" } + |if [ ! -z \\\${VIASH_META_MEMORY_B+x} ]; then + | export VIASH_META_MEMORY_KB=\\\$(( (\\\$VIASH_META_MEMORY_B+999) / 1000 )) + | export VIASH_META_MEMORY_MB=\\\$(( (\\\$VIASH_META_MEMORY_KB+999) / 1000 )) + | export VIASH_META_MEMORY_GB=\\\$(( (\\\$VIASH_META_MEMORY_MB+999) / 1000 )) + | export VIASH_META_MEMORY_TB=\\\$(( (\\\$VIASH_META_MEMORY_GB+999) / 1000 )) + | export VIASH_META_MEMORY_PB=\\\$(( (\\\$VIASH_META_MEMORY_TB+999) / 1000 )) + | export VIASH_META_MEMORY_KIB=\\\$(( (\\\$VIASH_META_MEMORY_B+1023) / 1024 )) + | export VIASH_META_MEMORY_MIB=\\\$(( (\\\$VIASH_META_MEMORY_KIB+1023) / 1024 )) + | export VIASH_META_MEMORY_GIB=\\\$(( (\\\$VIASH_META_MEMORY_MIB+1023) / 1024 )) + | export VIASH_META_MEMORY_TIB=\\\$(( (\\\$VIASH_META_MEMORY_GIB+1023) / 1024 )) + | export VIASH_META_MEMORY_PIB=\\\$(( (\\\$VIASH_META_MEMORY_TIB+1023) / 1024 )) + |fi + | + |# meta synonyms + |export VIASH_TEMP="\\\$VIASH_META_TEMP_DIR" + |export TEMP_DIR="\\\$VIASH_META_TEMP_DIR" + | + |# create output dirs if need be + |function mkdir_parent { + | for file in "\\\$@"; do + | mkdir -p "\\\$(dirname "\\\$file")" + | done + |} + |$createParentStr + | + |# argument exports${inputFileExports.join()} + |\$parInject + | + |# process script + |${escapedScript} + |\"\"\" + |} + |""".stripMargin() + + // TODO: print on debug + // if (workflowArgs.debug == true) { + // println("######################\n$procStr\n######################") + // } + + // write process to temp file + def tempFile = java.nio.file.Files.createTempFile("viash-process-${procKey}-", ".nf") + addShutdownHook { java.nio.file.Files.deleteIfExists(tempFile) } + tempFile.text = procStr + + // create process from temp file + def binding = new nextflow.script.ScriptBinding([:]) + def session = nextflow.Nextflow.getSession() + def parser = new nextflow.script.ScriptParser(session) + .setModule(true) + .setBinding(binding) + def moduleScript = parser.runScript(tempFile) + .getScript() + + // register module in meta + def module = new nextflow.script.IncludeDef.Module(name: procKey) + scriptMeta.addModule(moduleScript, module.name, module.alias) + + // retrieve and return process from meta + return scriptMeta.getProcess(procKey) +} + +// defaults +meta["defaults"] = [ + // key to be used to trace the process and determine output names + key: null, + + // fixed arguments to be passed to script + args: [:], + + // default directives + directives: readJsonBlob('''{ + "container" : { + "registry" : "images.viash-hub.com", + "image" : "vsh/htrnaseq/report/create_report", + "tag" : "main" + }, + "tag" : "$id" +}'''), + + // auto settings + auto: readJsonBlob('''{ + "simplifyInput" : true, + "simplifyOutput" : false, + "transcript" : false, + "publish" : false +}'''), + + // Apply a map over the incoming tuple + // Example: `{ tup -> [ tup[0], [input: tup[1].output] ] + tup.drop(2) }` + map: null, + + // Apply a map over the ID element of a tuple (i.e. the first element) + // Example: `{ id -> id + "_foo" }` + mapId: null, + + // Apply a map over the data element of a tuple (i.e. the second element) + // Example: `{ data -> [ input: data.output ] }` + mapData: null, + + // Apply a map over the passthrough elements of a tuple (i.e. the tuple excl. the first two elements) + // Example: `{ pt -> pt.drop(1) }` + mapPassthrough: null, + + // Filter the channel + // Example: `{ tup -> tup[0] == "foo" }` + filter: null, + + // Choose whether or not to run the component on the tuple if the condition is true. + // Otherwise, the tuple will be passed through. + // Example: `{ tup -> tup[0] != "skip_this" }` + runIf: null, + + // Rename keys in the data field of the tuple (i.e. the second element) + // Will likely be deprecated in favour of `fromState`. + // Example: `[ "new_key": "old_key" ]` + renameKeys: null, + + // Fetch data from the state and pass it to the module without altering the current state. + // + // `fromState` should be `null`, `List[String]`, `Map[String, String]` or a function. + // + // - If it is `null`, the state will be passed to the module as is. + // - If it is a `List[String]`, the data will be the values of the state at the given keys. + // - If it is a `Map[String, String]`, the data will be the values of the state at the given keys, with the keys renamed according to the map. + // - If it is a function, the tuple (`[id, state]`) in the channel will be passed to the function, and the result will be used as the data. + // + // Example: `{ id, state -> [input: state.fastq_file] }` + // Default: `null` + fromState: null, + + // Determine how the state should be updated after the module has been run. + // + // `toState` should be `null`, `List[String]`, `Map[String, String]` or a function. + // + // - If it is `null`, the state will be replaced with the output of the module. + // - If it is a `List[String]`, the state will be updated with the values of the data at the given keys. + // - If it is a `Map[String, String]`, the state will be updated with the values of the data at the given keys, with the keys renamed according to the map. + // - If it is a function, a tuple (`[id, output, state]`) will be passed to the function, and the result will be used as the new state. + // + // Example: `{ id, output, state -> state + [counts: state.output] }` + // Default: `{ id, output, state -> output }` + toState: null, + + // Whether or not to print debug messages + // Default: `false` + debug: false +] + +// initialise default workflow +meta["workflow"] = workflowFactory([key: meta.config.name], meta.defaults, meta) + +// add workflow to environment +nextflow.script.ScriptMeta.current().addDefinition(meta.workflow) + +// anonymous workflow for running this module as a standalone +workflow { + // add id argument if it's not already in the config + // TODO: deep copy + def newConfig = deepClone(meta.config) + def newParams = deepClone(params) + + def argsContainsId = newConfig.allArguments.any{it.plainName == "id"} + if (!argsContainsId) { + def idArg = [ + 'name': '--id', + 'required': false, + 'type': 'string', + 'description': 'A unique id for every entry.', + 'multiple': false + ] + newConfig.arguments.add(0, idArg) + newConfig = processConfig(newConfig) + } + if (!newParams.containsKey("id")) { + newParams.id = "run" + } + + helpMessage(newConfig) + + channelFromParams(newParams, newConfig) + // make sure id is not in the state if id is not in the args + | map {id, state -> + if (!argsContainsId) { + [id, state.findAll{k, v -> k != "id"}] + } else { + [id, state] + } + } + | meta.workflow.run( + auto: [ publish: "state" ] + ) +} + +// END COMPONENT-SPECIFIC CODE diff --git a/target/nextflow/report/create_report/nextflow.config b/target/nextflow/report/create_report/nextflow.config new file mode 100644 index 00000000..c010710f --- /dev/null +++ b/target/nextflow/report/create_report/nextflow.config @@ -0,0 +1,126 @@ +manifest { + name = 'report/create_report' + mainScript = 'main.nf' + nextflowVersion = '!>=20.12.1-edge' + version = 'main' + description = 'Create a basic QC report in HTML format based on a number of esets.\n' + author = 'Dries Schaumont, Marijke Van Moerbeke' +} + +process.container = 'nextflow/bash:latest' + +// detect tempdir +tempDir = java.nio.file.Paths.get( + System.getenv('NXF_TEMP') ?: + System.getenv('VIASH_TEMP') ?: + System.getenv('TEMPDIR') ?: + System.getenv('TMPDIR') ?: + '/tmp' +).toAbsolutePath() + +profiles { + no_publish { + process { + withName: '.*' { + publishDir = [ + enabled: false + ] + } + } + } + mount_temp { + docker.temp = tempDir + podman.temp = tempDir + charliecloud.temp = tempDir + } + docker { + docker.enabled = true + // docker.userEmulation = true + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + singularity { + singularity.enabled = true + singularity.autoMounts = true + docker.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + podman { + podman.enabled = true + docker.enabled = false + singularity.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + shifter { + shifter.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + charliecloud.enabled = false + } + charliecloud { + charliecloud.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + } +} + +process{ + withLabel: mem1gb { memory = 1000000000.B } + withLabel: mem2gb { memory = 2000000000.B } + withLabel: mem5gb { memory = 5000000000.B } + withLabel: mem10gb { memory = 10000000000.B } + withLabel: mem20gb { memory = 20000000000.B } + withLabel: mem50gb { memory = 50000000000.B } + withLabel: mem100gb { memory = 100000000000.B } + withLabel: mem200gb { memory = 200000000000.B } + withLabel: mem500gb { memory = 500000000000.B } + withLabel: mem1tb { memory = 1000000000000.B } + withLabel: mem2tb { memory = 2000000000000.B } + withLabel: mem5tb { memory = 5000000000000.B } + withLabel: mem10tb { memory = 10000000000000.B } + withLabel: mem20tb { memory = 20000000000000.B } + withLabel: mem50tb { memory = 50000000000000.B } + withLabel: mem100tb { memory = 100000000000000.B } + withLabel: mem200tb { memory = 200000000000000.B } + withLabel: mem500tb { memory = 500000000000000.B } + withLabel: mem1gib { memory = 1073741824.B } + withLabel: mem2gib { memory = 2147483648.B } + withLabel: mem4gib { memory = 4294967296.B } + withLabel: mem8gib { memory = 8589934592.B } + withLabel: mem16gib { memory = 17179869184.B } + withLabel: mem32gib { memory = 34359738368.B } + withLabel: mem64gib { memory = 68719476736.B } + withLabel: mem128gib { memory = 137438953472.B } + withLabel: mem256gib { memory = 274877906944.B } + withLabel: mem512gib { memory = 549755813888.B } + withLabel: mem1tib { memory = 1099511627776.B } + withLabel: mem2tib { memory = 2199023255552.B } + withLabel: mem4tib { memory = 4398046511104.B } + withLabel: mem8tib { memory = 8796093022208.B } + withLabel: mem16tib { memory = 17592186044416.B } + withLabel: mem32tib { memory = 35184372088832.B } + withLabel: mem64tib { memory = 70368744177664.B } + withLabel: mem128tib { memory = 140737488355328.B } + withLabel: mem256tib { memory = 281474976710656.B } + withLabel: mem512tib { memory = 562949953421312.B } + withLabel: cpu1 { cpus = 1 } + withLabel: cpu2 { cpus = 2 } + withLabel: cpu5 { cpus = 5 } + withLabel: cpu10 { cpus = 10 } + withLabel: cpu20 { cpus = 20 } + withLabel: cpu50 { cpus = 50 } + withLabel: cpu100 { cpus = 100 } + withLabel: cpu200 { cpus = 200 } + withLabel: cpu500 { cpus = 500 } + withLabel: cpu1000 { cpus = 1000 } +} + +includeConfig("nextflow_labels.config") diff --git a/target/nextflow/report/create_report/nextflow_labels.config b/target/nextflow/report/create_report/nextflow_labels.config new file mode 100644 index 00000000..2821ec46 --- /dev/null +++ b/target/nextflow/report/create_report/nextflow_labels.config @@ -0,0 +1,108 @@ +executor { + $k8s { + submitRateLimit = '10sec' + pollInterval = '1 sec' + } +} + +process { + container = 'nextflow/bash:latest' + + // default resources + memory = { 8.Gb * task.attempt } + cpus = 8 + maxForks = 36 + + // Retry for exit codes that have something to do with memory issues + errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' } + maxRetries = 3 + maxMemory = 192.GB + + // Resource labels + withLabel: verylowcpu { cpus = 2 } + withLabel: lowcpu { cpus = 8 } + withLabel: midcpu { cpus = 16 } + withLabel: highcpu { cpus = 32 } + + withLabel: verylowmem { memory = { get_memory( 4.GB * task.attempt ) } } + withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } + withLabel: midmem { memory = { get_memory( 16.GB * task.attempt ) } } + withLabel: highmem { memory = { get_memory( 64.GB * task.attempt ) } } + +} + +profiles { + // detect tempdir + tempDir = java.nio.file.Paths.get( + System.getenv('NXF_TEMP') ?: + System.getenv('VIASH_TEMP') ?: + System.getenv('TEMPDIR') ?: + System.getenv('TMPDIR') ?: + '/tmp' + ).toAbsolutePath() + + mount_temp { + docker.temp = tempDir + podman.temp = tempDir + charliecloud.temp = tempDir + } + + no_publish { + process { + withName: '.*' { + publishDir = [ + enabled: false + ] + } + } + } + + docker { + docker.fixOwnership = true + docker.enabled = true + // docker.userEmulation = true + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + + local { + // This config is for local processing. + process { + withName: ".*parallel_map_process" { + maxForks = 1 + } + maxMemory = 25.GB + withLabel: verylowcpu { cpus = 2 } + withLabel: lowcpu { cpus = 4 } + withLabel: midcpu { cpus = 6 } + withLabel: highcpu { cpus = 8 } + + withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } + withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } + withLabel: highmem { memory = { get_memory( 20.GB * task.attempt ) } } + } + } +} + +def get_memory(to_compare) { + if (!process.containsKey("maxMemory") || !process.maxMemory) { + return to_compare + } + + try { + if (process.containsKey("maxRetries") && process.maxRetries && task.attempt == (process.maxRetries as int)) { + return process.maxMemory + } + else if (to_compare.compareTo(process.maxMemory as nextflow.util.MemoryUnit) == 1) { + return max_memory as nextflow.util.MemoryUnit + } + else { + return to_compare + } + } catch (all) { + println "Error processing memory resources. Please check that process.maxMemory '${process.maxMemory}' and process.maxRetries '${process.maxRetries}' are valid!" + System.exit(1) + } + } diff --git a/target/nextflow/report/create_report/nextflow_schema.json b/target/nextflow/report/create_report/nextflow_schema.json new file mode 100644 index 00000000..54f4d99c --- /dev/null +++ b/target/nextflow/report/create_report/nextflow_schema.json @@ -0,0 +1,81 @@ +{ +"$schema": "http://json-schema.org/draft-07/schema", +"title": "create_report", +"description": "Create a basic QC report in HTML format based on a number of esets.\n", +"type": "object", +"definitions": { + + + + "arguments" : { + "title": "Arguments", + "type": "object", + "description": "No description", + "properties": { + + + "eset": { + "type": + "string", + "description": "Type: List of `file`, required, multiple_sep: `\";\"`. ", + "help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. " + + } + + + , + "output_report": { + "type": + "string", + "description": "Type: `file`, required, default: `$id.$key.output_report.html`, example: `report.html`. ", + "help_text": "Type: `file`, required, default: `$id.$key.output_report.html`, example: `report.html`. " + , + "default":"$id.$key.output_report.html" + } + + +} +}, + + + "nextflow input-output arguments" : { + "title": "Nextflow input-output arguments", + "type": "object", + "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.", + "properties": { + + + "publish_dir": { + "type": + "string", + "description": "Type: `string`, required, example: `output/`. Path to an output directory", + "help_text": "Type: `string`, required, example: `output/`. Path to an output directory." + + } + + + , + "param_list": { + "type": + "string", + "description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel", + "help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.", + "hidden": true + + } + + +} +} +}, +"allOf": [ + + { + "$ref": "#/definitions/arguments" + }, + + { + "$ref": "#/definitions/nextflow input-output arguments" + } +] +} diff --git a/target/nextflow/report/create_report/plateLayouts.R b/target/nextflow/report/create_report/plateLayouts.R new file mode 100755 index 00000000..c8b16cff --- /dev/null +++ b/target/nextflow/report/create_report/plateLayouts.R @@ -0,0 +1,424 @@ + +#' Displays the annotation of the wells in a plateLayout +#' @param plateData a data.table object containing the information +#' of the plate. This must contain a "WellID". +#' @param plateName The plate name +#' @param valueVariable The name of the variable in 'plateData' to +#' be visualized in a plate layout. +#' @param textVariable The name of the variable in 'plateData' to be +#' shown in the wells of the plate layout. If NULL, the valueVariable +#' is shown. +#' @param colours A named character vector containing the colours +#' for the different levels of the valuevariable. The names should +#' correspond to the dose levels. if not specified, a scheme of blues +#' will be provided. +#' @param breaks Numeric vector indicating breaks for plot coloring. +#' @param colourWellText Colour to display the text in the wells. +#' @param layout Integer vector of length two with number of rows and +#' colums in a plate, e.g. \code{c(16,24)} +#' @param legend.title A title for the legend +#' @param plot.title A title for the plot, will be contracted +#' with the plate name +#' @param ... additional arguments for \code{plateLayout.default} function +#' @import data.table +#' @importFrom platetools fill_plate +#' @export +plateLayout.annotation <- function( + plateData, + plateName = character(), + valueVariable = "Dose", + textVariable = NULL, + breaks = NULL, colours = NULL, + colourWellText = "black", + layout = c(16, 24), + legend.title = "Dose", + plot.title = "Plate Annotation - ", + textFontSize = 9, ... +) { + WellID <- Label <- NULL + + if (!(all(c("WellID", "SampleName") %in% colnames(plateData)))) { + stop(" 'WellID' and 'SampleName' column required in plateData object") + } + + + plateData[, WellID := paste0( + sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + sprintf( + "%02d", as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ) + )] + + plateData <- platetools::fill_plate(plateData, "WellID", plate = 384) + + plateData$column <- factor( + sprintf( + "%02d", + as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ), + levels = sprintf("%02d", seq(1, layout[2])) + ) + plateData$row <- factor(sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + levels = LETTERS[seq(1, layout[1])]) + + if (!is.null(valueVariable)){ + plateData[, values := as.character(plateData[, ..valueVariable][[1]])] + valueVar <- "values" + }else{ + plateData[, values := "grey"] + valueVar <- "values" + colours <- setNames("grey", "grey") + } + + + if (is.null(colours)) { + + blues <- colorRampPalette(c("#d6e0ff", "#2171B5")) + greens <- colorRampPalette(c("light green", "dark green")) + + numLevels <- sort(as.numeric(as.character(unique(plateData[, values])[ + grepl( + "^[[:digit:]]+([.][[:digit:]]+)?$", + trimws(unique(plateData[, values])) + ) + ]))) + otherLevels <- sort(as.character(unique(plateData[, values])[ + !grepl( + "^[[:digit:]]+([.][[:digit:]]+)?$", + trimws(unique(plateData[,values])) + ) + ])) + + colours <- c(blues(length(numLevels)), greens(length(otherLevels)), "red") + names(colours) <- c(numLevels, otherLevels, "failed") + } + + if (!is.null(textVariable)) { + plateData[, + Label := do.call(paste, c(.SD, sep = "\n ")), + .SDcols = textVariable + ] + plateData[, Label := gsub("-", "-\n", Label)] + plateData[, Label := gsub("_", "_\n", Label)] + textVar <- "Label" + } else { + textVar <- NULL + } + + + if (is.null(breaks)){ + breaks <- seq_len(length(colours)) + } + + plateLayout( + plateData = plateData, valueVariable = valueVar, + textVariable = textVar, plateName = plateName, + breaks = breaks, colourWellText = colourWellText, + legend.title = legend.title, layout = layout, + colours = colours, plot.title = plot.title, + textFontSize = textFontSize, ... + ) +} + + + +#' Create a heatmap of values in a plateLayout view. The values can be +#' library sizes, number of genes, qcScore (0/1) or a factor. +#' @param plateData A data.table of the values to be visualized with +#' at least the column of interest (specified in 'varOfInterest') +#' and a 'WellID' column indicating the wells in the plate. The WellID +#' is a combination of a letter (row in the plate) and an integer +#' (column in the plate). +#' @param valueVariable The name of the variable in 'plateData' +#' to be visualized in a plate layout +#' @param textVariable The name of the variable in 'plateData' +#' to be shown in the wells of the plate layout. Defaults to the +#' valueVariable and if NULL, no text will be displayed. +#' @param breaks Numeric vector indicating breaks for plot coloring. +#' @param colours Colours to be used for levels specified by +#' the breaks. If NULL, a colour scheme of purples is shown. +#' @param colourWellText Colour to display the text in the wells. +#' @param layout Integer vector of length two with number of rows +#' and colums in a plate, e.g. \code{c(16,24)} +#' @param makeContourColours Logical, whether or not the plate +#' layout will contain a contour colours for the wells based on the +#' parameters in 'contourColours' and 'categories' +#' @param contourVariable The variable used for the contour colouring +#' @param contourColours Character vector specifying a colour for +#' each range in 'categories' +#' @param labelsCategories Character vector specifying the names +#' (labels) for each range in 'categories' +#' @param categories if contour Variable is not a factor, a numeric +#' vector specifying the categories to divide the 'varOfInterest', +#' including the lower and upper limits. +#' @param plateName The plate name +#' @param plot.title A title for the plot, will be contracted with +#' the plate name +#' @param legend.title A title for the legend +#' @param displayHeatmap Logical, whether to display the plateLayout heatmap +#' @param saveHeatmap Logical, whether to save the plateLayout heatmap +#' @param outputDir The directory where the plateLayout heatmap should be saved +#' @param prefix The prefix to the file name of the saved plateLayout heatmap +#' @param ... additional arguments for \code{ComplexHeatmap::Heatmap} function +#' @importFrom platetools fill_plate +#' @importFrom RColorBrewer brewer.pal +#' @importFrom ComplexHeatmap Heatmap +#' @importFrom circlize colorRamp2 +#' @importFrom grid grid.text grid.rect gpar legendGrob gpar +#' @importFrom grDevices dev.off png +#' @importFrom graphics title +#' @export +plateLayout <- function( + plateData, valueVariable, textVariable = valueVariable, + breaks = NULL, colours = NULL, colourWellText = "white", textFontSize = 6, + layout = c(16, 24), makeContourColours = FALSE, contourVariable = character(), + contourColours = c("red", "orange", "seagreen3"),lwdContours = c(1, 1, 1), + labelsCategories = c('1', '2', '3'), categories = NULL, plateName = character(), + plot.title = character(), legend.title = NULL, legendFontSize = 15, + row_split = rep("A", 16), col_split = rep("A", 24), legendFontSizeTitle = 15, + displayHeatmap = TRUE, saveHeatmap = FALSE, outputDir = ".", prefix = "" +) { + WellID <- NULL + if (!(all(c("WellID", "SampleName") %in% colnames(plateData)))) { + stop(" 'WellID' and 'SampleName' column required in plateData object") + } + + + plateData[, WellID := paste0( + sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + sprintf( + "%02d", + as.numeric(sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID)) + ) + )] + + plateData <- platetools::fill_plate(plateData, "WellID", plate = 384) + + plateData$column <- factor( + sprintf("%02d", as.numeric( + sub(".*[[:alpha:]](.+)", "\\1", plateData$WellID) + )), + levels = sprintf("%02d", seq(1, layout[2])) + ) + plateData$row <- factor(sub(".*([[:alpha:]]).+", "\\1", plateData$WellID), + levels = LETTERS[seq(1, layout[1])]) + + + plateValues <- plateLayoutFormat( + plateData, + varOfInterest = valueVariable, + rows = layout[1], + cols = layout[2] + ) + if (!is.null(textVariable)) { + plateText <- plateLayoutFormat( + plateData, varOfInterest = textVariable, + rows = layout[1], + cols = layout[2] + ) + } + plot.title <- gsub( + "^([a-z])", "\\U\\1", + gsub("([A-Z])", " \\1", + plot.title, perl = TRUE), perl = TRUE + ) + mainTitle <- paste0(plot.title, plateName) + plateContourColours <- matrix("", nrow = layout[1], ncol = layout[2]) + + if (makeContourColours) { + contourData <- plateData[WellType %in% c("nonEmpty", "Treated Wells"), ] + + if (is.numeric(contourData[, ..contourVariable][[1]])) { + contourData$contours <- cut( + contourData[, ..contourVariable][[1]], + categories, left = TRUE, + right = TRUE, + labels = labelsCategories) + } + else { + contourData$contours <- contourData[, ..contourVariable][[1]] + } + names(contourColours) <- labelsCategories + names(lwdContours) <- labelsCategories + for (i in seq_len(layout[1])) { + for (j in seq_len(layout[2])) { + tryCatch({ + sampleHit <- which( + as.character(contourData$WellID) == paste0( + LETTERS[i], sprintf("%02d", j) + ) + ) + if (length(sampleHit) == 1) { + plateContourColours[i, j] <- as.character( + contourData[sampleHit,'contours'][[1]] + ) + } + }, + error = function(e) { + print(paste0(LETTERS[i], sprintf("%02d", j), " is missing.")) + } + ) + } + } + } + + plateValues$contours <- plateContourColours + colnames(plateValues$values) <- seq_len(ncol(plateValues$values)) + + if (is.null(breaks)) { + breakValues <- plateValues$values + breakValues[which(is.na(breakValues))] <- 0 + if (all(breakValues >= 0)) { + breaks <- computeBreaks(7, max(plateValues$values, na.rm = TRUE)) + } else { + breaks <- quantile(plateValues$values, probs = seq(0, 1, 0.125)) + } + } + + if (is.null(colours)) { + colours <- tryCatch({ + colorRamp2( + breaks = breaks, + colors = brewer.pal(length(breaks), "Purples") + ) + }, + error = function(cond) { + return(c("#9370DB", "white")) + }) + } + ht <- Heatmap( + plateValues$values, + column_title = mainTitle, column_title_side = "top", + rect_gp = gpar(lwd = 0.4), + cluster_rows = FALSE, cluster_columns = FALSE, + col = colours, row_title = NULL, + row_split = row_split, column_split = col_split, + row_names_side = "left", + cluster_row_slices = FALSE, + cluster_column_slices = FALSE, + show_heatmap_legend = TRUE, + heatmap_legend_param = list( + title = ifelse( + is.null(legend.title), + paste0(valueVariable, "\n"), + paste0(legend.title, "\n") + ), + grid_height = unit(9, "mm"), border = "black", + labels_gp = gpar(fontsize = legendFontSize), + title_gp = gpar(fontsize = legendFontSizeTitle) + ), + cell_fun = function(j, i, x, y, width, height, fill) { + if (is.na(plateValues$values[i, j])) { + grid.rect( + x, y, width, height, + gp = gpar(fill = "white", alpha = 0.7, lwd = 0.7, col = "white") + ) + } + else if (!is.null(textVariable)) { + grid.text( + plateText$values[i, j], x, y, + just = "centre", + gp = gpar(fontsize = textFontSize, col = colourWellText) + ) + } + if (makeContourColours) { + if (!is.na(plateValues$contours[i, j])) { + grid.rect( + x, y, width, height, + gp = gpar( + col = contourColours[as.character(plateValues$contours[i, j])], + fill = NA, + lwd = lwdContours[as.character(plateValues$contours[i, j])] + ) + ) + } + } + } + ) + + if (displayHeatmap) { + print(ht) + } + if (saveHeatmap) { + png( + file.path( + outputDir, + paste0(prefix,gsub(" |-", "",plot.title), "_", plateName, ".png") + ), + width = 30, height = 10, units = "cm", res = 1200 + ) + print(ht) + dev.off() + } + + return(ht) +} + + +#' Return numerical matrix with number of reads that corresponds to the +#' plate layout +#' @param data A data.frame of the values to be visualized with at least +#' the columnof interest (specified in 'varOfInterest') and a 'WellID' column +#' indicating the wells in the plate. The WellID is a combination of a +#' letter (row in the plate) and an integer (column in the plate). +#' @param varOfInterest The name of the variable in 'data' to be visualized +#' in a plate layout +#' @param rows number of rows in a plate layout +#' @param cols number of columns in a plate layout +#' @param verbose if \code{TRUE}, samples missing from the plate +#' will be reported +#' @export +plateLayoutFormat <- function( + data, varOfInterest, + rows = 16, cols = 24, + verbose = FALSE +) { + plateValues <- matrix(NA, nrow = rows, ncol = cols) + for (i in seq_len(rows)) { + for (j in seq_len(cols)) { + tryCatch({ + sampleHit <- which( + as.character(data$WellID) == paste0(LETTERS[i], sprintf("%02d", j)) + ) + if(length(sampleHit) == 1){ + plateValues[i, j] <- data[sampleHit, ..varOfInterest][[1]] + } + }, + error = function(e) { + if (verbose == TRUE) { + print(paste0(LETTERS[i], sprintf("%02d", j), " is missing.")) + } + } + ) + } + } + + row.names(plateValues) <- LETTERS[1:rows] + return(list("values" = plateValues)) +} + + + +#' Helper function to automate break selection for raw count data +#' +#' This function creates an exponentially increasing vector for given number +#' breaks between zero and some element of choice. It is particularly useful for +#' raw counts or raw counts per million. +#' +#' @param nBreaks Number of breaks to be generated +#' @param maxElement Maximum value of data entries +#' @export +computeBreaks <- function(nBreaks, variable) { + + maxElement <- max(variable, na.rm = TRUE) + if (length(unique(variable)) == 1) { + breaks <- c(0, 0.5, ifelse(maxElement < 1, 1, maxElement)) + } else { + coefSystem <- solve( + rbind(c(1, 1), c(1, (nBreaks - 1)))) %*% c(0, log(maxElement) + ) + coefExp <- c(exp(coefSystem[1]), coefSystem[2]) + breaks <- coefExp[1] * exp((1:(nBreaks - 1)) * coefExp[2]) + } + return(c(0, breaks)) +} \ No newline at end of file diff --git a/target/nextflow/report/create_report/template.Rmd b/target/nextflow/report/create_report/template.Rmd new file mode 100755 index 00000000..20f8c190 --- /dev/null +++ b/target/nextflow/report/create_report/template.Rmd @@ -0,0 +1,977 @@ +--- +title: "Exploratory Data Report" +date: "`r format(Sys.time(), '%d %B, %Y')`" +editor_options: + chunk_output_type: console +output: + oaStyle::html_report +# parameters which are overwritten by the script +params: + outputDir: 'output/' + esets: + - sample1.rds + - sample2.rds +--- + + + + + + + + + +```{r params, eval = TRUE, include = FALSE} +outputDir <- params$outputDir +esets <- params$esets +``` + + +```{r outputDir, echo = FALSE} +## Required: ABSOLUTE outputDir +outputDir <- file.path(outputDir) + +# When working on a windows computer it should be +# "/Users/..." instead of "C:/Users/..." +if (.Platform$OS.type == "windows") { + outputDir <- paste0( + "/", + paste( + unlist(strsplit(outputDir, split = "/"))[-1], collapse = "/" + ), + "/" + ) +} +``` + + + + +```{r optionsChunkDoNotModify, echo = FALSE, message = FALSE, warning=FALSE} + +## Chunk with options for knitr. This chunk should not be modified. +knitr::opts_chunk$set( + eval = TRUE, + echo = FALSE, + message = FALSE, + cache = FALSE, + warning = FALSE, + error = FALSE, + comment = NA, #"#", + tidy = FALSE, + collapse = TRUE, + out.width = "100%", + fig.width = 20, + fig.height = 10, + results = "asis") + +knitr::opts_knit$set(root.dir = getwd()) + +options(warn = 1, width = 200) + +``` + +```{r libraries_and_functions} +source("plateLayouts.R") +library(ComplexHeatmap) +library(data.table) +library(ggplot2) +library(knitr) +library(Biobase) +library(gridExtra) +library(RColorBrewer) +``` + + +```{r dataImport} + +# Create esetList +esetList <- sapply( + esets, simplify = FALSE, + USE.NAMES = TRUE, + function(eset_raw) { + if (!file.exists(eset_raw)) { + stop(paste0("Provided path '", eset_raw, "' is not a file.")) + } + eset <- readRDS(eset_raw) + } +) +pools <- sapply(esetList, function(eset) { + unique(eset$PoolName) +}) +names(esetList) <- unlist(pools) + +# Create qcData +pDataList <- lapply(esetList, function(eset) data.table(pData(eset))) +qcData <- rbindlist(pDataList, fill = TRUE) + +textVars <- "SampleName" +annotationVar <- "PoolName" + +if (!"SampleName" %in% names(qcData)) { + qcData[, SampleName := paste0(PoolName, "_", WellBC)] +} +qcData[, log10LibSize := round(log10(NumberOfInputReads))] +qcData[, (annotationVar) := lapply(.SD, as.factor), .SDcols = annotationVar] + + +colourList <- list() +Design_levels <- sort( + as.character(unique(qcData[, ..annotationVar][[1]])), + decreasing = TRUE +) + +if (length(Design_levels) == 1) { + colours <- c("#d6e0ff", "lightgrey") + names(colours) <- c(Design_levels, "Empty") + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +}else if (length(Design_levels) == 2) { + colours <- c("#d6e0ff", "#FF9999") + + names(colours) <- c(Design_levels) + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +} else if (length(Design_levels) <= 20) { + + if (length(Design_levels) > 12) { + colours <- c( + brewer.pal(12, "Set3"), + brewer.pal((length(Design_levels) - 12), + "Pastel2") + ) + } else { + colours <- c(brewer.pal(length(Design_levels), "Set3")) + } + + names(colours) <- c(Design_levels) + colourList[[annotationVar]] <- list( + "colours" = colours, + "annotVar" = annotationVar, + "text" = textVars + ) +} else { + colours <- c("#d6e0ff") + names(colours) <- c("nonEmpty") + colourList[[annotVar]] <- list( + "colours" = colours, + "annotVar" = annotVar, + "text" = annotVar + ) +} +``` + +# Pool Description + +Per pool within this study, there are several pool layout plots shown, based on the + +* number of STAR input reads (= library size) + +* log10 transformed number of STAR input reads + +* number of detected UMIs + +* number of detected genes + +* number of chromosomal reads + +* percentage of ERCC + +* percentage of mitochondria + + +> The values for the different samples within each pool is expected to be comparable if the content of the different pools is equally diverse. + +```{r plateAnnotation, out.width = "100%",fig.width = 20, fig.height= 10} + +plateVars <- c("NumberOfInputReads", "log10LibSize", "NumberOfMappedReads", + "NumberOfChromReads", "NumberOfUMIs", "NumberOfGenes", + "pctMT", "pctERCC") + +breaksVars <- lapply( + plateVars, + function(var) { + computeBreaks(7, qcData[, ..var]) + } +) +names(breaksVars) <- plateVars + +for (pool in pools){ + cat("\n\n") + cat(paste0("## ", pool, " {.tabset} \n\n")) + poolData <- qcData[PoolName == pool] + lapply(plateVars, function(plateVar) { + cat("\n\n") + cat(sprintf("### %s {.unnumbered}", plateVar)) + cat("\n\n") + plateLayout( + poolData, valueVariable = plateVar, + textFontSize = 10, legendFontSize = 12, + plateName = pool, plot.title = "libSize - ", + legend.title = "libSize", breaks = breaksVars[[plateVar]] + ) + cat("\n\n") + }) + cat("\n\n") +} +``` + +
+ + +# Data Distributions + + +## Reads Distributions {.tabset} + +The 4 box plots below represent the distributions per pool of the different samples based on: + +* the number of STAR input reads + +* the number of STAR mapped reads + +* the percentage of STAR mapped reads + +* the number of detected genes + +> The distributions contribute to the QC metrics mentioned in Par 3. The higher these values, the better. +> The data range for the different plates is expected to be comparable if the content of the different plates is equally diverse. + + +### Number of Input Reads {.tabset .unnumbered} + +```{r settings_1} + +nColPlots = 1 +figHeight = 7 + +``` + +#### Distribution {.tabset .unnumbered} + + +```{r boxplots_input_plate, fig.height = figHeight} +ggplot( + qcData, + aes( + x = PoolName, + y = NumberOfInputReads, colour = PoolName + ) +) + geom_boxplot() + ylab("Number of Input Reads") + + ggtitle("Number of Input Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + + +### Number of Mapped Reads {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_mapped_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfMappedReads, colour = PoolName) +) + geom_boxplot() + ylab("Number of Mapped Reads") + + ggtitle("Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +#### pct Mapped Reads {.unnumbered} + +```{r boxplots_pctMapped_plate, fig.height = figHeight} +ggplot( + qcData, + aes(x = PoolName, y = PctMappedReads, colour = PoolName) +) + + geom_boxplot() + + ylab("pct Mapped Reads") + + ggtitle("pct Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### Number of Chromosomal Reads {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_chrom_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfChromReads, colour = PoolName) +) + geom_boxplot() + ylab("Number of Chromosomal Reads") + + ggtitle("Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + +#### pct Chromosomal Reads {.unnumbered} + +```{r boxplots_pctChrom_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = pctChrom, colour = PoolName) +) + geom_boxplot() + ylab("pct Chromosomal Reads") + + ggtitle("pct Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### Number of UMIs {.tabset .unnumbered} + +#### Distribution {.tabset .unnumbered} + + +```{r boxplots_umi_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = NumberOfUMIs, colour = PoolName) +) + geom_boxplot() + ylab("Number of UMIs") + + ggtitle('Number of UMIs') + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) + +``` + +#### Density distribution {.unnumbered} + +```{r density_numberOfUMIs} + +## Pre-filtering data exploration +dt_plot <- melt( + qcData, + id.vars = c("SampleName", "PoolName", "WellID"), + measure.vars = c("NumberOfInputReads", "NumberOfMappedReads", "NumberOfUMIs") +) + +readsDensity_plot <- ggplot(dt_plot, aes(value)) +readsDensity_plot <- readsDensity_plot + + geom_density(aes(fill = variable), alpha=0.8) + + facet_grid(~ PoolName, scales = "free_x", space = "fixed", drop = TRUE) + + geom_vline( + xintercept = 5e5, + linetype = "dashed", + color = "steelblue3", size = 2 + ) + + annotate( + "text", + x = 3.5e5, y = 2e-6, label = "500k", + angle = 90, color = "steelblue3", size = 10 + ) + + geom_vline( + xintercept = 1.5e6, linetype = "dashed", + color = "forestgreen", size = 2 + ) + + annotate( + "text", x = 1.35e6, y = 2e-6, label = "1.5M", + angle = 90, color = "forestgreen", size = 10 + ) + + labs( + title = "Density plot", + subtitle = paste0( + "# Samples with NumberOfMappedReads > 1.5M: ", + length(which(qcData$NumberOfMappedReads > 1.5e6)), + "\n# Samples with NumberOfUMIs > 500k: ", + length(which(qcData$NumberOfUMIs > 5e5)) + ), + caption = paste0("# Total samples (after removing empty): ", nrow(qcData)), + x = "Count", + fill = "Variable" + ) + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 5), + axis.text.x = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + plot.subtitle = element_text(size = 17), + plot.caption = element_text(size = 15), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.y = element_blank(), + axis.ticks.y = element_blank(), + axis.title.y = element_blank() + ) +readsDensity_plot + +``` + +### Number of Genes {.tabset .unnumbered} + +#### Distribution {.unnumbered} + +```{r boxplots_genes_plate, fig.height = figHeight} +ggplot( + qcData, + aes(x = PoolName, y = NumberOfGenes, colour = PoolName) +) + + geom_boxplot() + ylab("Number of Genes") + + ggtitle("Number of Genes") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +## {.tabset .toc-ignore .unnumbered} + + +In addition, several plots are shown visualizing the efficiency of the reads-to-genes translation: + +* the number of input reads vs the number of mapped reads + +* the number of chromosomal reads vs the number of mapped reads + +* the number of mapped reads per UMI vs the number of mapped reads + +* the number of UNI vs the number of mapped reads + +* the number of mapped reads vs the number of genes + +* the number of chromosomal reads vs the number of genes + +* the number of mapped reads per UMI vs the number of genes + +### Mapping Efficiency {.tabset .unnumbered} + +#### Number of Input Reads {.unnumbered} + +```{r mapping_efficiency_1_plate, fig.height = 7} + +ggplot( + qcData, + aes(x = NumberOfInputReads, y = NumberOfMappedReads, colour = PoolName) +) + + geom_point() + + xlab("Number of Input Reads") + + ylab("Number of Mapped Reads") + + ggtitle("Number of Mapped Reads vs Number of Input Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + + +#### Number of Chromosomal Reads {.unnumbered} + +```{r mapping_efficiency_2_plate, fig.height = 7} + +ggplot( + qcData, + aes(x = NumberOfChromReads, y = NumberOfMappedReads, colour = PoolName) +) + geom_point() + + xlab("Number of Chromosomal Reads") + ylab("Number of Mapped Reads") + + ggtitle("Number of Chromosomal Reads vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) +) + +``` + + +#### Number of UMI {.unnumbered} + +```{r mapping_efficiency_4_plate, fig.height = 7} + +ggplot( + qcData, + aes(x =NumberOfUMIs, y = NumberOfMappedReads, colour = PoolName) +) + geom_point() + + ylab("Number of Mapped Reads") + xlab("Number of UMIs ") + + ggtitle("Number of UMIs vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + +### Counting Efficiency {.tabset .unnumbered} + +#### Number of Mapped Reads {.unnumbered} + +```{r gene_efficiency_1_plate, fig.height = 7} +ggplot( + qcData, + aes(x = NumberOfMappedReads, y = NumberOfGenes, colour = PoolName) +) + geom_point() + + ylab("Number of Genes") + xlab("Number of Mapped Reads") + + ggtitle("Number of Genes vs Number of Mapped Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + +#### Number of Chromosomal Reads {.unnumbered} + +```{r gene_efficiency_2_plate, fig.height = 7} +ggplot( + qcData, + aes(x = NumberOfChromReads, y = NumberOfGenes, colour = PoolName) +) + geom_point() + + ylab("Number of Genes") + xlab("Number of Chromosomal Reads") + + ggtitle("Number of Genes vs Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + + + +## Sequencing Saturation {.tabset} + +The barplots below represent the sequencing saturation per sample as determined by STAR, split per pool. +The HT-RNAseq platform aims for shallow sequencing resulting in relatively low sequencing saturations of 10-20%. +In addition, the sequencing saturation vs the number of input reads is shown. + +### Sequencing Saturation {.unnumbered} + + + +```{r sequencingSaturation, fig.height = figHeight} + +ggplot( + qcData, + aes(x = WellID, y = SequencingSaturation, fill = PoolName) +) + geom_bar(stat = "identity", position = "dodge") + + xlab("Samples") + ggtitle("Sequencing Saturation per Sample") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(1, "lines"), + text = element_text(size = 10), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15), + axis.text.x = element_blank(), + axis.text.y = element_text(size = 15), + axis.ticks.x = element_blank() + ) +``` + +### Sequencing Saturation - Input Reads {.unnumbered} + + +```{r sequencingSaturation_inputReads, fig.height = figHeight} + + +ggplot( + qcData, + aes(x = NumberOfInputReads, y = SequencingSaturation, colour = PoolName) +) + geom_point() + + ggtitle("Sequencing Saturation vs Number of Input Reads") + + theme(strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) +``` + +### Sequencing Saturation - Mapped Reads {.unnumbered} + +```{r sequencingSaturation_mappedReads, fig.height = figHeight} +ggplot( + qcData, + aes(x = NumberOfChromReads, y = SequencingSaturation, colour = PoolName) +) + geom_point() + + ggtitle("Sequencing Saturation vs Number of Chromosomal Reads") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size=10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size=18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) +) +``` + +
+ +## Genomic Origin {.tabset} + +The 3 boxplots below represent, per pool, the distributions of the percentage of reads mapping to: + +* chromosomal regions + +* mitochondrial regions + +* ERCC spike-ins + +The 4th plot summarises the above results across samples per pool. + +The 5th plot shows the percentage of reads mapped to the transcriptome (as counted by STAR). This measurement serves as a proxy for the percentage of reads mapped to exons. + +> The percentage ERCC contributes to the QC metrics mentioned in Par 3. This value is ideally as low as possible (but non-zero to ensure the they have been spiked in) and comparable for the different pools. + + + + +### pctChrom {.tabset .unnumbered} + + +```{r genomicOrigin_chrom_plate, fig.height = figHeight} + +ggplot( + qcData, aes(x = PoolName, y = pctChrom, colour = PoolName) +) + + geom_boxplot() + + ggtitle("pctChrom") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +### pctMT {.tabset .unnumbered} + +```{r genomicOrigin_mt_plate, fig.height = figHeight} + +ggplot( + qcData, + aes(x = PoolName, y = pctMT, colour = PoolName) +) + + geom_boxplot() + ggtitle("pctMT") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + +### pctERCC {.tabset .unnumbered} + + +```{r genomicOrigin_ercc_plate, fig.height = figHeight} +ggplot(qcData, aes(x = PoolName, y = pctERCC, colour = PoolName)) + + geom_boxplot() + + ggtitle("pctERCC") + + theme( + strip.text.x = element_text(size = 20), + panel.spacing = unit(2, "lines"), + text = element_text(size = 10), + axis.text.y = element_text(angle = 90, size = 14), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title.y = element_text(size = 15), + axis.text.x = element_blank(), + axis.ticks.x = element_blank() + ) +``` + + +### Genomic Summary {.tabset .unnumbered} + + + +```{r genomicOrigin_summary_plate} +meanPctChromMTData <- qcData[, .( + "pctChrom" = median(pctChrom), + "pctMT" = median(pctMT), + "pctERCC" = median(pctERCC) +), by = PoolName] +meanPctChromMTDataLong <- melt( + meanPctChromMTData, + id.vars = "PoolName", + measure.vars = c("pctChrom", "pctMT", "pctERCC"), + variable.name = "Origin", value.name = "pct" +) +ggplot( + meanPctChromMTDataLong, + aes(fill = Origin, y = pct, x = PoolName)) + + geom_bar(position = "stack", stat = "identity") + + ggtitle("Genomic Origin") + + theme( + text = element_text(size = 10), + axis.text = element_text(angle = 90, size = 15), + plot.title = element_text(size = 18), + legend.text = element_text(size = 15), + legend.title = element_text(size = 17), + axis.title = element_text(size = 15) + ) + +``` + + + +# Depletion {.tabset} + +
+```{r depletion} + + +for (eset_name in pools) { + cat("\n\n") + cat(paste0("## ", eset_name, " {.unnumbered}")) + cat("\n\n") + + eset <- esetList[[eset_name]] + average_reads <- sort(apply(exprs(eset), 1, mean), decreasing = TRUE) + plotData <- data.table( + ENSGID = names(average_reads), + av_count = average_reads + ) + + gen_descript <- data.table( + ENSGID = eset@featureData@data$gene_id, + Description = eset@featureData@data$GENENAME + ) + order_gen_descript <- gen_descript[ + match(plotData$ENSGID, gen_descript$ENSGID), + ] + + g <- ggplot( + plotData[c(1:100)], + aes(x = reorder(ENSGID, -av_count), y = av_count) + ) + geom_bar(stat = "identity") + + theme( + axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size = 12), + axis.text.y = element_text(size = 12), + legend.text = element_text(size = 15), + legend.title = element_text(size = 15), + axis.title = element_text(size = 18), + plot.title = element_text(size = 20) + ) + ylab("Average Counts") + xlab("Genes") + + print(g) + + cat("\n\n") + cat("
") + cat("
") + + print(htmltools::tagList((DT::datatable(order_gen_descript[1:100, ])))) +} +``` +
+ + +
+
+
+
+ +# Glossary {.unnumbered} + + +## Read {.unlisted .unnumbered} + +A read is a oligonucleotide (a short RNA fragment) that has been sequenced. It consists of a fixed number of base pairs (bp) and therefore has a specific read length. + + + +## Input Read {.unlisted .unnumbered} + +Each read of the fastq file used as input to the STAR aligner is considered an input read. + + + +## Read With Valid Barcode {.unlisted .unnumbered} + +A read with a valid barcode is a read for which the barcode matches the white list of barcodes under the given restriction of the number of allowed mismatches. The number of reads with a valid barcode is lower or equal to the number of input reads. + + + +## Mapped Read {.unlisted .unnumbered} + +A read that has been aligned against the reference genome and for which one or more suitable matching locations have been found is a mapped read. Depending on the number of allowed mismatches this might or might not be be an exact match. The number of mapped reads is lower or equal to the number of reads with a valid barcode. + + + +## Uniquely Mapped Read {.unlisted .unnumbered} + +A read for which one and only one suitable matching location in the reference genome was found is an uniquely mapped read. The number of uniquely mapped reads is lower or equal to the number of mapped reads. + + + +## Counted Read {.unlisted .unnumbered} + +A mapped read will only be counted if it overlaps (1 nucleotide or more) with one and only one gene. The number of counted reads is lower or equal to the number of (uniquely) mapped reads. + + + +## UMIs {.unlisted .unnumbered} + +Unique molecular identifiers (UMI) are short sequences in order to uniquely tag each molecule in a sample library. Sequencing with UMIs allows bioinformatics software to filter out duplicate reads and PCR errors with a high level of accuracy and report unique reads. + +The reported UMIs is the number of UMIs among the set of reads that map to an unique gene, i.e the number of reads is deduplicated. + + + +## pctERCC {.unlisted .unnumbered} + +The percentage of reads mapping to the ERCC genes among the total number of **mapped** reads. + + + +## pctMT {.unlisted .unnumbered} + +The percentage of reads mapping to the MT genes among the total number of **mapped** reads. + + + +## Sequencing Saturation {.unlisted .unnumbered} + +The sequencing saturation is a measure of the fraction of library complexity. The inverse of one minus the sequencing saturation can be interpreted as the number of additional reads it would take to detect a new transcript. Consequently, a low sequencing saturation indicates a shallow sequencing in which a new transcript could be discovered with a few reads. + +
+
+
+
+ +
+![](OutputSTARsolo.png) +
+ +
+
diff --git a/target/nextflow/stats/combine_star_logs/.config.vsh.yaml b/target/nextflow/stats/combine_star_logs/.config.vsh.yaml index 408f956c..d7932abb 100644 --- a/target/nextflow/stats/combine_star_logs/.config.vsh.yaml +++ b/target/nextflow/stats/combine_star_logs/.config.vsh.yaml @@ -1,6 +1,21 @@ name: "combine_star_logs" namespace: "stats" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Arguments" arguments: @@ -183,8 +198,8 @@ build_info: output: "target/nextflow/stats/combine_star_logs" executable: "target/nextflow/stats/combine_star_logs/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/stats/combine_star_logs/main.nf b/target/nextflow/stats/combine_star_logs/main.nf index 9a2ea7e9..c5f93656 100644 --- a/target/nextflow/stats/combine_star_logs/main.nf +++ b/target/nextflow/stats/combine_star_logs/main.nf @@ -8,6 +8,9 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (author, maintainer) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2810,30 @@ meta = [ "name" : "combine_star_logs", "namespace" : "stats", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -3033,8 +3060,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/stats/combine_star_logs", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/stats/combine_star_logs/nextflow.config b/target/nextflow/stats/combine_star_logs/nextflow.config index feaea63f..ded1a2f9 100644 --- a/target/nextflow/stats/combine_star_logs/nextflow.config +++ b/target/nextflow/stats/combine_star_logs/nextflow.config @@ -3,6 +3,7 @@ manifest { mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' version = 'main' + author = 'Dries Schaumont' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/stats/combine_star_logs/nextflow_labels.config b/target/nextflow/stats/combine_star_logs/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/stats/combine_star_logs/nextflow_labels.config +++ b/target/nextflow/stats/combine_star_logs/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/stats/combine_star_logs/nextflow_schema.json b/target/nextflow/stats/combine_star_logs/nextflow_schema.json index 12de4145..72f77d8b 100644 --- a/target/nextflow/stats/combine_star_logs/nextflow_schema.json +++ b/target/nextflow/stats/combine_star_logs/nextflow_schema.json @@ -60,7 +60,7 @@ "description": "Type: `file`, default: `$id.$key.output.txt`. Tab-delimited file describing for each barcode (as the rows), the metrics (as columns)\ngathered from the different input files", "help_text": "Type: `file`, default: `$id.$key.output.txt`. Tab-delimited file describing for each barcode (as the rows), the metrics (as columns)\ngathered from the different input files. \n" , - "default": "$id.$key.output.txt" + "default":"$id.$key.output.txt" } diff --git a/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml b/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml index 0f89ee7e..300d7442 100644 --- a/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml +++ b/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml @@ -1,6 +1,33 @@ name: "generate_pool_statistics" namespace: "stats" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -155,8 +182,8 @@ build_info: output: "target/nextflow/stats/generate_pool_statistics" executable: "target/nextflow/stats/generate_pool_statistics/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/stats/generate_pool_statistics/main.nf b/target/nextflow/stats/generate_pool_statistics/main.nf index 70d8d90d..f12a283d 100644 --- a/target/nextflow/stats/generate_pool_statistics/main.nf +++ b/target/nextflow/stats/generate_pool_statistics/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (author, maintainer) +// * Marijke Van Moerbeke (contributor) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2811,50 @@ meta = [ "name" : "generate_pool_statistics", "namespace" : "stats", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "contributor" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -2996,8 +3044,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/stats/generate_pool_statistics", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", @@ -3082,6 +3130,8 @@ dep = { ### VIASH END +INDEX_COL = ["WellBC", "WellID"] + if __name__ == "__main__": ######### # nrReadsNrGenesPerChrom file @@ -3091,17 +3141,18 @@ if __name__ == "__main__": nr_reads_nr_genes_wells.append(pd.read_csv(nr_reads_nr_genes_file, header=0, delimiter="\\\\t", dtype={"WellBC": pd.StringDtype(), + "WellID": pd.StringDtype(), "Chr": pd.StringDtype(), "NumberOfReads": pd.UInt64Dtype(), "NumberOfGenes": pd.UInt64Dtype()})) nr_reads_nr_genes_pool = pd.concat(nr_reads_nr_genes_wells, ignore_index=True,) - total_nr_reads_per_chromosome = nr_reads_nr_genes_pool.pivot_table(index="WellBC", columns="Chr", + total_nr_reads_per_chromosome = nr_reads_nr_genes_pool.pivot_table(index=INDEX_COL, columns="Chr", values=["NumberOfReads"], fill_value=0, aggfunc="sum").droplevel(0, axis=1) total_nr_reads_per_chromosome.columns.name = None ##### Total number of genes from all chromosomes - total_nr_genes = nr_reads_nr_genes_pool.loc[:,['WellBC', 'NumberOfGenes']].groupby("WellBC").sum() + total_nr_genes = nr_reads_nr_genes_pool.loc[:, INDEX_COL + ['NumberOfGenes']].groupby(["WellBC", "WellID"]).sum() ##### Total counts across (irrespective of chromosome) total_sum_of_reads = total_nr_reads_per_chromosome.sum(numeric_only=True, axis=1) @@ -3150,10 +3201,10 @@ if __name__ == "__main__": **cols_to_add ) - total_nr_reads_per_chromosome.reset_index(names="WellBC")\\\\ + total_nr_reads_per_chromosome.reset_index(names=INDEX_COL)\\\\ .to_csv(par["nrReadsNrGenesPerChromPool"], sep="\\\\t", header=True, index=False, float_format="%g", - columns=("WellBC",) + tuple(chromosome_names) + tuple(cols_to_add.keys()) + columns=tuple(INDEX_COL) + tuple(chromosome_names) + tuple(cols_to_add.keys()) ) VIASHMAIN python -B "$tempscript" diff --git a/target/nextflow/stats/generate_pool_statistics/nextflow.config b/target/nextflow/stats/generate_pool_statistics/nextflow.config index 73677b23..d3fc1c28 100644 --- a/target/nextflow/stats/generate_pool_statistics/nextflow.config +++ b/target/nextflow/stats/generate_pool_statistics/nextflow.config @@ -3,6 +3,7 @@ manifest { mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' version = 'main' + author = 'Dries Schaumont, Marijke Van Moerbeke' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/stats/generate_pool_statistics/nextflow_labels.config b/target/nextflow/stats/generate_pool_statistics/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/stats/generate_pool_statistics/nextflow_labels.config +++ b/target/nextflow/stats/generate_pool_statistics/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json b/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json index 55cde03f..1f0ea034 100644 --- a/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json +++ b/target/nextflow/stats/generate_pool_statistics/nextflow_schema.json @@ -20,7 +20,7 @@ "description": "Type: List of `file`, default: `processedBamFile_well1.tsv;processedBamfile_well2.tsv`, multiple_sep: `\";\"`. Path to an output file that contains a ", "help_text": "Type: List of `file`, default: `processedBamFile_well1.tsv;processedBamfile_well2.tsv`, multiple_sep: `\";\"`. Path to an output file that contains a .tsv formatted table describing\nper chromosome the number of reads that were mapped to that chromosome (NumberOfReads\ncolumn) and the number of genes on that chromosome that had at least one\nread mapped to it (NumberOfGenes).\n" , - "default": "processedBamFile_well1.tsv;processedBamfile_well2.tsv" + "default":"processedBamFile_well1.tsv;processedBamfile_well2.tsv" } @@ -31,7 +31,7 @@ "description": "Type: `file`, default: `$id.$key.nrReadsNrGenesPerChromPool.txt`, example: `nrReadsNrGenesPerChrom.txt`. Pivot table in tsv format of the combined input nrReadsNrGenesPerChrom files", "help_text": "Type: `file`, default: `$id.$key.nrReadsNrGenesPerChromPool.txt`, example: `nrReadsNrGenesPerChrom.txt`. Pivot table in tsv format of the combined input nrReadsNrGenesPerChrom files. Describes\nper chromosome (as columns) the number of reads, as well as the total number \nof reads per cell barcode and the percentage of nuclear, ERCC and mitochondrial\nreads.\n" , - "default": "$id.$key.nrReadsNrGenesPerChromPool.txt" + "default":"$id.$key.nrReadsNrGenesPerChromPool.txt" } diff --git a/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml b/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml index 49cf1187..8e86141b 100644 --- a/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml +++ b/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml @@ -1,6 +1,33 @@ name: "generate_well_statistics" namespace: "stats" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "author" + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Arguments" arguments: @@ -25,6 +52,15 @@ argument_groups: direction: "input" multiple: false multiple_sep: ";" + - type: "string" + name: "--well_id" + description: "ID of this well. Only used to add a metadata column to the output\ + \ files.\n" + info: null + required: true + direction: "input" + multiple: false + multiple_sep: ";" - type: "file" name: "--processedBAMFile" description: "Path to a .tsv file listing, per read in the BAM file,\nthe value\ @@ -226,8 +262,8 @@ build_info: output: "target/nextflow/stats/generate_well_statistics" executable: "target/nextflow/stats/generate_well_statistics/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/stats/generate_well_statistics/main.nf b/target/nextflow/stats/generate_well_statistics/main.nf index 1cea56b8..790f9e80 100644 --- a/target/nextflow/stats/generate_well_statistics/main.nf +++ b/target/nextflow/stats/generate_well_statistics/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (author, maintainer) +// * Marijke Van Moerbeke (contributor) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2811,50 @@ meta = [ "name" : "generate_well_statistics", "namespace" : "stats", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "author", + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "contributor" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -2834,6 +2882,15 @@ meta = [ "multiple" : false, "multiple_sep" : ";" }, + { + "type" : "string", + "name" : "--well_id", + "description" : "ID of this well. Only used to add a metadata column to the output files.\n", + "required" : true, + "direction" : "input", + "multiple" : false, + "multiple_sep" : ";" + }, { "type" : "file", "name" : "--processedBAMFile", @@ -3078,8 +3135,8 @@ meta = [ "engine" : "docker|native", "output" : "target/nextflow/stats/generate_well_statistics", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", @@ -3138,6 +3195,7 @@ import logging par = { 'input': $( if [ ! -z ${VIASH_PAR_INPUT+x} ]; then echo "r'${VIASH_PAR_INPUT//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'barcode': $( if [ ! -z ${VIASH_PAR_BARCODE+x} ]; then echo "r'${VIASH_PAR_BARCODE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), + 'well_id': $( if [ ! -z ${VIASH_PAR_WELL_ID+x} ]; then echo "r'${VIASH_PAR_WELL_ID//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'processedBAMFile': $( if [ ! -z ${VIASH_PAR_PROCESSEDBAMFILE+x} ]; then echo "r'${VIASH_PAR_PROCESSEDBAMFILE//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'nrReadsNrGenesPerChrom': $( if [ ! -z ${VIASH_PAR_NRREADSNRGENESPERCHROM+x} ]; then echo "r'${VIASH_PAR_NRREADSNRGENESPERCHROM//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), 'nrReadsNrUMIsPerCB': $( if [ ! -z ${VIASH_PAR_NRREADSNRUMISPERCB+x} ]; then echo "r'${VIASH_PAR_NRREADSNRUMISPERCB//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ), @@ -3192,11 +3250,11 @@ if __name__ == "__main__": columns=tags_selection) tag_dataframe_to_write = tag_dataframe.copy() logger.info("Done reading BAM file. Found %i entries", tag_dataframe.shape[0]) - tag_dataframe.assign(WellBC=par["barcode"])\\\\ + tag_dataframe.assign(WellBC=par["barcode"], WellID=par["well_id"])\\\\ .reset_index(names="Chr")\\\\ .to_csv(par["processedBAMFile"], sep="\\\\t", na_rep="", header=True, index=False, - columns=("WellBC", "Chr") + tags_selection) + columns=("WellBC", "WellID", "Chr") + tags_selection) logger.info("Constructing of dataframe done.") # Number of genes that had a read mapped to them per chromosome, # and the number of reads mapped to those genes per chromosome. @@ -3206,19 +3264,19 @@ if __name__ == "__main__": ) logger.info("Done calculating number of reads per gene and per chromesome. Writing to %s", par['nrReadsNrGenesPerChrom']) - nr_reads_nr_genes.reset_index(names="Chr").assign(WellBC=par["barcode"])\\\\ + nr_reads_nr_genes.reset_index(names="Chr").assign(WellBC=par["barcode"], WellID=par["well_id"])\\\\ .to_csv(par["nrReadsNrGenesPerChrom"], sep="\\\\t", header=True, index=False, - columns=("WellBC", "Chr", "NumberOfReads", "NumberOfGenes")) + columns=("WellBC", "WellID", "Chr", "NumberOfReads", "NumberOfGenes")) # Number of reads mapped to the reference, grouped by UMI nr_read_per_umi = tag_dataframe.groupby('UB').size()\\\\ .drop("", errors="ignore").sort_values(ascending=False).head(100) nr_read_per_umi_df = nr_read_per_umi.to_frame(name="N") logger.info("Done calculating number of mapped reads per UMI, writing to %s", par["umiFreqTop"]) - nr_read_per_umi_df.assign(WellBC=par["barcode"]).reset_index(names="UB")\\\\ + nr_read_per_umi_df.assign(WellBC=par["barcode"], WellID=par["well_id"]).reset_index(names="UB")\\\\ .to_csv(par["umiFreqTop"], header=True, sep="\\\\t", - index=False, columns=("WellBC", "UB", "N")) + index=False, columns=("WellBC", "WellID", "UB", "N")) # Total number of mapped reads and total number of UMIs (not grouped per chromosome) nr_reads_and_umi_per_barcode = tag_dataframe.groupby(by="CB").agg( @@ -3227,9 +3285,9 @@ if __name__ == "__main__": ) logger.info("Done calculating number of mapped reads and number of UMIs per Cell Barcode, writing to %s", par["nrReadsNrUMIsPerCB"]) - nr_reads_and_umi_per_barcode.assign(WellBC=par["barcode"]).reset_index(names="CB")\\\\ + nr_reads_and_umi_per_barcode.assign(WellBC=par["barcode"], WellID=par["well_id"]).reset_index(names="CB")\\\\ .to_csv(par["nrReadsNrUMIsPerCB"], sep="\\\\t", header=True, - index=False, columns=("WellBC", "CB", "NumberOfReads", "nrUMIs")) + index=False, columns=("WellBC", "WellID", "CB", "NumberOfReads", "nrUMIs")) logger.info("Finished!") VIASHMAIN python -B "$tempscript" diff --git a/target/nextflow/stats/generate_well_statistics/nextflow.config b/target/nextflow/stats/generate_well_statistics/nextflow.config index 4fc4503e..17d752f9 100644 --- a/target/nextflow/stats/generate_well_statistics/nextflow.config +++ b/target/nextflow/stats/generate_well_statistics/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'Generate summary statistics from BAM files generated by STAR solo.' + author = 'Dries Schaumont, Marijke Van Moerbeke' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/stats/generate_well_statistics/nextflow_labels.config b/target/nextflow/stats/generate_well_statistics/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/stats/generate_well_statistics/nextflow_labels.config +++ b/target/nextflow/stats/generate_well_statistics/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/stats/generate_well_statistics/nextflow_schema.json b/target/nextflow/stats/generate_well_statistics/nextflow_schema.json index a924ff42..3e2b583d 100644 --- a/target/nextflow/stats/generate_well_statistics/nextflow_schema.json +++ b/target/nextflow/stats/generate_well_statistics/nextflow_schema.json @@ -33,6 +33,16 @@ } + , + "well_id": { + "type": + "string", + "description": "Type: `string`, required. ID of this well", + "help_text": "Type: `string`, required. ID of this well. Only used to add a metadata column to the output files.\n" + + } + + , "processedBAMFile": { "type": @@ -40,7 +50,7 @@ "description": "Type: `file`, default: `$id.$key.processedBAMFile.txt`. Path to a ", "help_text": "Type: `file`, default: `$id.$key.processedBAMFile.txt`. Path to a .tsv file listing, per read in the BAM file,\nthe value for the \"CB\", \"UX\", \"GX\" and \"GN\" tag, together with the\nchromsome to which the read was mapped to.\n" , - "default": "$id.$key.processedBAMFile.txt" + "default":"$id.$key.processedBAMFile.txt" } @@ -51,7 +61,7 @@ "description": "Type: `file`, default: `$id.$key.nrReadsNrGenesPerChrom.txt`. Path to an output file that contains a ", "help_text": "Type: `file`, default: `$id.$key.nrReadsNrGenesPerChrom.txt`. Path to an output file that contains a .tsv formatted table describing\nper chromosome the number of reads that were mapped to that chromosome (NumberOfReads\ncolumn) and the number of genes on that chromosome that had at least one\nread mapped to it (NumberOfGenes).\n" , - "default": "$id.$key.nrReadsNrGenesPerChrom.txt" + "default":"$id.$key.nrReadsNrGenesPerChrom.txt" } @@ -62,7 +72,7 @@ "description": "Type: `file`, default: `$id.$key.nrReadsNrUMIsPerCB.txt`. Path to an output file that contains a ", "help_text": "Type: `file`, default: `$id.$key.nrReadsNrUMIsPerCB.txt`. Path to an output file that contains a .tsv formatted table describing\nper barcode the number of UMI\u0027s (nrUMIs) and the total number of reads (NumberOfReads).\n" , - "default": "$id.$key.nrReadsNrUMIsPerCB.txt" + "default":"$id.$key.nrReadsNrUMIsPerCB.txt" } @@ -73,7 +83,7 @@ "description": "Type: `file`, default: `$id.$key.umiFreqTop.txt`. Path to an output file that contains a ", "help_text": "Type: `file`, default: `$id.$key.umiFreqTop.txt`. Path to an output file that contains a .tsv formatted table describing\nper UMI (column UB) the frequency at which they occur in the reads (column\nN). Only the top 100 UMIs are included.\n" , - "default": "$id.$key.umiFreqTop.txt" + "default":"$id.$key.umiFreqTop.txt" } @@ -84,7 +94,7 @@ "description": "Type: `integer`, default: `1`. Number of threads to use for decompressing BAM files", "help_text": "Type: `integer`, default: `1`. Number of threads to use for decompressing BAM files.\n" , - "default": "1" + "default":1 } diff --git a/target/nextflow/workflows/htrnaseq/.config.vsh.yaml b/target/nextflow/workflows/htrnaseq/.config.vsh.yaml index d587fcfb..637e6295 100644 --- a/target/nextflow/workflows/htrnaseq/.config.vsh.yaml +++ b/target/nextflow/workflows/htrnaseq/.config.vsh.yaml @@ -1,6 +1,20 @@ name: "htrnaseq" namespace: "workflows" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Input arguments" arguments: @@ -148,6 +162,17 @@ argument_groups: direction: "output" multiple: false multiple_sep: ";" + - type: "file" + name: "--html_report" + info: null + default: + - "report.html" + must_exist: true + create_parent: true + required: true + direction: "output" + multiple: false + multiple_sep: ";" resources: - type: "nextflow_script" path: "main.nf" @@ -194,6 +219,9 @@ dependencies: - name: "eset/create_pdata" repository: type: "local" +- name: "report/create_report" + repository: + type: "local" repositories: - type: "local" name: "local" @@ -280,8 +308,8 @@ build_info: output: "target/nextflow/workflows/htrnaseq" executable: "target/nextflow/workflows/htrnaseq/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" dependencies: - "target/nextflow/stats/combine_star_logs" - "target/nextflow/stats/generate_pool_statistics" @@ -292,6 +320,7 @@ build_info: - "target/nextflow/eset/create_eset" - "target/nextflow/eset/create_fdata" - "target/nextflow/eset/create_pdata" + - "target/nextflow/report/create_report" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/workflows/htrnaseq/main.nf b/target/nextflow/workflows/htrnaseq/main.nf index 9b060782..f2df086d 100644 --- a/target/nextflow/workflows/htrnaseq/main.nf +++ b/target/nextflow/workflows/htrnaseq/main.nf @@ -8,6 +8,9 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2810,29 @@ meta = [ "name" : "htrnaseq", "namespace" : "workflows", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Input arguments", @@ -2974,6 +3000,19 @@ meta = [ "direction" : "output", "multiple" : false, "multiple_sep" : ";" + }, + { + "type" : "file", + "name" : "--html_report", + "default" : [ + "report.html" + ], + "must_exist" : true, + "create_parent" : true, + "required" : true, + "direction" : "output", + "multiple" : false, + "multiple_sep" : ";" } ] } @@ -3059,6 +3098,12 @@ meta = [ "repository" : { "type" : "local" } + }, + { + "name" : "report/create_report", + "repository" : { + "type" : "local" + } } ], "repositories" : [ @@ -3165,8 +3210,8 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/htrnaseq", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", @@ -3218,6 +3263,7 @@ include { groupWells } from "${meta.resources_dir}/../../../nextflow/workflows/u include { create_eset } from "${meta.resources_dir}/../../../nextflow/eset/create_eset/main.nf" include { create_fdata } from "${meta.resources_dir}/../../../nextflow/eset/create_fdata/main.nf" include { create_pdata } from "${meta.resources_dir}/../../../nextflow/eset/create_pdata/main.nf" +include { create_report } from "${meta.resources_dir}/../../../nextflow/report/create_report/main.nf" // inner workflow // user-provided Nextflow code @@ -3238,21 +3284,6 @@ workflow run_wf { // Perform mapping of each well. The input here are events per pool, // the output channel is one event per well. mapping_ch = input_ch - | map {id, state -> - def n_barcodes = state.barcodesFasta.countFasta() as int - def newState = state + ["n_barcodes": n_barcodes] - // The header is the full header, the id is the part header up to the first whitespace character - // We do not allow whitespace in the header of the fasta file, so assert this. - def fasta_entries = state.barcodesFasta.splitFasta(record: ["id": true, "header": true, "seqString": true]) - assert fasta_entries.every{it.id == it.header}, "The barcodes FASTA headers must not contain any whitespace!" - // Check if the fasta headers are unique - def fasta_ids = fasta_entries.collect{it.id} - assert fasta_ids.clone().unique() == fasta_ids, "The barcodes FASTA entries must have a unique name!" - // Check if the sequences are unique - def fasta_sequences = fasta_entries.collect{it.seqString} - assert fasta_sequences.clone().unique() == fasta_sequences, "The barcodes FASTA sequences must be unique!" - [id, newState] - } | well_demultiplex.run( fromState: [ "input_r1": "input_r1", @@ -3264,7 +3295,7 @@ workflow run_wf { def filtered_results = result.findAll{!["output_r1", "output_r2"].contains(it.key)} def new_state = filtered_input + filtered_results + [ "fastq_output_r1": result.output_r1, - "fastq_output_r2": result.output_r2, + "fastq_output_r2": result.output_r2, ] return new_state } @@ -3292,6 +3323,7 @@ workflow run_wf { [ "input": state.star_output.resolve('Aligned.sortedByCoord.out.bam'), "barcode": state.barcode, + "well_id": state.well_id, ] }, toState: [ @@ -3302,7 +3334,7 @@ workflow run_wf { // Create a special groupKey, such that groupTuple // knows when all the barcodes have been grouped into 1 event. // This way the processing is as distributed as possible. - def key = groupKey(state.pool, state.n_barcodes) + def key = groupKey(state.pool, state.n_wells) def newEvent = [key, state] return newEvent } @@ -3318,10 +3350,14 @@ workflow run_wf { def barcodes = states.collect{it.barcode} assert barcodes.clone().unique().size() == barcodes.size(), \ "Error when gathering information for pool ${id}, barcodes are not unique!" + def well_ids = states.collect{it.well_id} + assert well_ids.clone().unique().size() == well_ids.size(), \ + "Error when gathering information for pool ${id}, well IDs are not unique!" def custom_state = [ "fastq_output_r1": states.collect{it.fastq_output_r1[0]}, "fastq_output_r2": states.collect{it.fastq_output_r2[0]}, "barcode": barcodes, + "well_id": well_ids, "star_output": states.collect{it.star_output}, "nrReadsNrGenesPerChrom": states.collect{it.nrReadsNrGenesPerChrom}, ] @@ -3390,7 +3426,7 @@ workflow run_wf { toState: ["p_data": "output"], ) - output_ch = p_data_ch.join(f_data_ch, remainder: true) + eset_ch = p_data_ch.join(f_data_ch, remainder: true) | map {id, p_data_state, f_data_state -> def newState = p_data_state + ["f_data": f_data_state["f_data"]] [id, newState] @@ -3409,6 +3445,36 @@ workflow run_wf { "eset": "output", ] ) + + report_channel = eset_ch + | toSortedList() + | map {ids_and_states -> + def states = ids_and_states.collect{it[1]} + def html_report = states[0].html_report + def ids = ids_and_states.collect{it[0]} + def esets = states.collect{it.eset} + ["report", ["esets": esets, "html_report": html_report, "original_ids": ids]] + } + | create_report.run( + fromState: [ + "eset": "esets", + "output_report": "html_report", + ], + toState: [ + "html_report": "output_report" + ] + ) + | flatMap {id, state -> + state.original_ids.collect{original_id -> + [original_id, ["html_report": state.html_report]] + } + } + + output_ch = eset_ch.join(report_channel) + | map {id, state_eset, state_report -> + def new_state = state_eset + ["html_report": state_report.html_report] + [id, new_state] + } | setState([ "star_output": "star_output", "fastq_output_r1": "fastq_output_r1", @@ -3418,7 +3484,8 @@ workflow run_wf { "star_qc_metrics": "star_qc_metrics", "eset": "eset", "f_data": "f_data", - "p_data": "p_data" + "p_data": "p_data", + "html_report": "html_report", ]) diff --git a/target/nextflow/workflows/htrnaseq/nextflow.config b/target/nextflow/workflows/htrnaseq/nextflow.config index 1b96d6a0..dd4f6be2 100644 --- a/target/nextflow/workflows/htrnaseq/nextflow.config +++ b/target/nextflow/workflows/htrnaseq/nextflow.config @@ -3,6 +3,7 @@ manifest { mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' version = 'main' + author = 'Dries Schaumont' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/workflows/htrnaseq/nextflow_labels.config b/target/nextflow/workflows/htrnaseq/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/workflows/htrnaseq/nextflow_labels.config +++ b/target/nextflow/workflows/htrnaseq/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/workflows/htrnaseq/nextflow_schema.json b/target/nextflow/workflows/htrnaseq/nextflow_schema.json index 89a8dc72..6ce186b6 100644 --- a/target/nextflow/workflows/htrnaseq/nextflow_schema.json +++ b/target/nextflow/workflows/htrnaseq/nextflow_schema.json @@ -80,7 +80,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.fastq_output_r1_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files", "help_text": "Type: List of `file`, required, default: `$id.$key.fastq_output_r1_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files" , - "default": "$id.$key.fastq_output_r1_*.fastq" + "default":"$id.$key.fastq_output_r1_*.fastq" } @@ -91,7 +91,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.fastq_output_r2_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files", "help_text": "Type: List of `file`, required, default: `$id.$key.fastq_output_r2_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files" , - "default": "$id.$key.fastq_output_r2_*.fastq" + "default":"$id.$key.fastq_output_r2_*.fastq" } @@ -102,7 +102,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.star_output_*.star_output_*`, multiple_sep: `\";\"`. Output from mapping with STAR", "help_text": "Type: List of `file`, required, default: `$id.$key.star_output_*.star_output_*`, multiple_sep: `\";\"`. Output from mapping with STAR" , - "default": "$id.$key.star_output_*.star_output_*" + "default":"$id.$key.star_output_*.star_output_*" } @@ -113,7 +113,7 @@ "description": "Type: `file`, required, default: `$id.$key.nrReadsNrGenesPerChrom.txt`. ", "help_text": "Type: `file`, required, default: `$id.$key.nrReadsNrGenesPerChrom.txt`. " , - "default": "$id.$key.nrReadsNrGenesPerChrom.txt" + "default":"$id.$key.nrReadsNrGenesPerChrom.txt" } @@ -124,7 +124,7 @@ "description": "Type: `file`, required, default: `$id.$key.star_qc_metrics.txt`. ", "help_text": "Type: `file`, required, default: `$id.$key.star_qc_metrics.txt`. " , - "default": "$id.$key.star_qc_metrics.txt" + "default":"$id.$key.star_qc_metrics.txt" } @@ -135,7 +135,7 @@ "description": "Type: `file`, required, default: `$id.$key.eset.rds`. ", "help_text": "Type: `file`, required, default: `$id.$key.eset.rds`. " , - "default": "$id.$key.eset.rds" + "default":"$id.$key.eset.rds" } @@ -146,7 +146,7 @@ "description": "Type: `file`, required, default: `$id.$key.f_data.tsv`. ", "help_text": "Type: `file`, required, default: `$id.$key.f_data.tsv`. " , - "default": "$id.$key.f_data.tsv" + "default":"$id.$key.f_data.tsv" } @@ -157,7 +157,18 @@ "description": "Type: `file`, required, default: `$id.$key.p_data.tsv`. ", "help_text": "Type: `file`, required, default: `$id.$key.p_data.tsv`. " , - "default": "$id.$key.p_data.tsv" + "default":"$id.$key.p_data.tsv" + } + + + , + "html_report": { + "type": + "string", + "description": "Type: `file`, required, default: `$id.$key.html_report.html`. ", + "help_text": "Type: `file`, required, default: `$id.$key.html_report.html`. " + , + "default":"$id.$key.html_report.html" } diff --git a/target/nextflow/workflows/parallel_map_wf/.config.vsh.yaml b/target/nextflow/workflows/parallel_map_wf/.config.vsh.yaml index ab2bb5cd..ba25da27 100644 --- a/target/nextflow/workflows/parallel_map_wf/.config.vsh.yaml +++ b/target/nextflow/workflows/parallel_map_wf/.config.vsh.yaml @@ -1,6 +1,20 @@ name: "parallel_map_wf" namespace: "workflows" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Arguments" arguments: @@ -66,7 +80,7 @@ description: "Map RNA sequencing data, provided as fastq files (paired-end) to a \ genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning\ \ that a single fastq pair provides data for\none barcode (one well). Multiple wells\ \ can be mapped in parallel by providing multiple events to the \nworkflow. Output\ - \ is provided as mapped output per pool, i.e. one output is provided per pool.xx\n" + \ is provided as mapped output per pool, i.e. one output is provided per pool.\n" info: null status: "enabled" requirements: @@ -161,8 +175,8 @@ build_info: output: "target/nextflow/workflows/parallel_map_wf" executable: "target/nextflow/workflows/parallel_map_wf/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" dependencies: - "target/nextflow/parallel_map" - "target/nextflow/workflows/utils/groupWells" diff --git a/target/nextflow/workflows/parallel_map_wf/main.nf b/target/nextflow/workflows/parallel_map_wf/main.nf index 10f35123..d946c1c1 100644 --- a/target/nextflow/workflows/parallel_map_wf/main.nf +++ b/target/nextflow/workflows/parallel_map_wf/main.nf @@ -8,6 +8,9 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2810,29 @@ meta = [ "name" : "parallel_map_wf", "namespace" : "workflows", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Arguments", @@ -2883,7 +2909,7 @@ meta = [ "dest" : "nextflow_labels.config" } ], - "description" : "Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for\none barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the \nworkflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.xx\n", + "description" : "Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for\none barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the \nworkflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.\n", "status" : "enabled", "requirements" : { "commands" : [ @@ -3002,8 +3028,8 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/parallel_map_wf", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/workflows/parallel_map_wf/nextflow.config b/target/nextflow/workflows/parallel_map_wf/nextflow.config index 354d26e0..3caf08ea 100644 --- a/target/nextflow/workflows/parallel_map_wf/nextflow.config +++ b/target/nextflow/workflows/parallel_map_wf/nextflow.config @@ -3,7 +3,8 @@ manifest { mainScript = 'main.nf' nextflowVersion = '!>=20.12.1-edge' version = 'main' - description = 'Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for\none barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the \nworkflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.xx\n' + description = 'Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for\none barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the \nworkflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.\n' + author = 'Dries Schaumont' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/workflows/parallel_map_wf/nextflow_labels.config b/target/nextflow/workflows/parallel_map_wf/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/workflows/parallel_map_wf/nextflow_labels.config +++ b/target/nextflow/workflows/parallel_map_wf/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/workflows/parallel_map_wf/nextflow_schema.json b/target/nextflow/workflows/parallel_map_wf/nextflow_schema.json index ebf972f6..7585ff9a 100644 --- a/target/nextflow/workflows/parallel_map_wf/nextflow_schema.json +++ b/target/nextflow/workflows/parallel_map_wf/nextflow_schema.json @@ -1,7 +1,7 @@ { "$schema": "http://json-schema.org/draft-07/schema", "title": "parallel_map_wf", -"description": "Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for\none barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the \nworkflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.xx\n", +"description": "Map RNA sequencing data, provided as fastq files (paired-end) to a reference genome using STAR Solo.\nInput data must have been demultiplexed beforehand, meaning that a single fastq pair provides data for\none barcode (one well). Multiple wells can be mapped in parallel by providing multiple events to the \nworkflow. Output is provided as mapped output per pool, i.e. one output is provided per pool.\n", "type": "object", "definitions": { @@ -70,7 +70,7 @@ "description": "Type: `file`, required, default: `$id.$key.output.output`. ", "help_text": "Type: `file`, required, default: `$id.$key.output.output`. " , - "default": "$id.$key.output.output" + "default":"$id.$key.output.output" } diff --git a/target/nextflow/workflows/utils/groupWells/.config.vsh.yaml b/target/nextflow/workflows/utils/groupWells/.config.vsh.yaml index 385e68a0..d7d26b2a 100644 --- a/target/nextflow/workflows/utils/groupWells/.config.vsh.yaml +++ b/target/nextflow/workflows/utils/groupWells/.config.vsh.yaml @@ -1,6 +1,20 @@ name: "groupWells" namespace: "workflows/utils" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" argument_groups: - name: "Inputs" arguments: @@ -171,8 +185,8 @@ build_info: output: "target/nextflow/workflows/utils/groupWells" executable: "target/nextflow/workflows/utils/groupWells/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" package_config: name: "htrnaseq" version: "main" diff --git a/target/nextflow/workflows/utils/groupWells/main.nf b/target/nextflow/workflows/utils/groupWells/main.nf index 3e277950..f92e9f4e 100644 --- a/target/nextflow/workflows/utils/groupWells/main.nf +++ b/target/nextflow/workflows/utils/groupWells/main.nf @@ -8,6 +8,9 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2810,29 @@ meta = [ "name" : "groupWells", "namespace" : "workflows/utils", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Inputs", @@ -3013,8 +3039,8 @@ meta = [ "engine" : "native", "output" : "target/nextflow/workflows/utils/groupWells", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", diff --git a/target/nextflow/workflows/utils/groupWells/nextflow.config b/target/nextflow/workflows/utils/groupWells/nextflow.config index 44bc2c5b..b120fa7f 100644 --- a/target/nextflow/workflows/utils/groupWells/nextflow.config +++ b/target/nextflow/workflows/utils/groupWells/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'N/A\n' + author = 'Dries Schaumont' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/workflows/utils/groupWells/nextflow_labels.config b/target/nextflow/workflows/utils/groupWells/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/workflows/utils/groupWells/nextflow_labels.config +++ b/target/nextflow/workflows/utils/groupWells/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/workflows/utils/groupWells/nextflow_schema.json b/target/nextflow/workflows/utils/groupWells/nextflow_schema.json index ebd0d593..c303a7e0 100644 --- a/target/nextflow/workflows/utils/groupWells/nextflow_schema.json +++ b/target/nextflow/workflows/utils/groupWells/nextflow_schema.json @@ -80,7 +80,7 @@ "description": "Type: List of `file`, default: `$id.$key.output_r1_*.output_r1_*`, multiple_sep: `\";\"`. Path to output for R2", "help_text": "Type: List of `file`, default: `$id.$key.output_r1_*.output_r1_*`, multiple_sep: `\";\"`. Path to output for R2" , - "default": "$id.$key.output_r1_*.output_r1_*" + "default":"$id.$key.output_r1_*.output_r1_*" } @@ -91,7 +91,7 @@ "description": "Type: List of `file`, default: `$id.$key.output_r2_*.output_r2_*`, multiple_sep: `\";\"`. Path to the output for R2", "help_text": "Type: List of `file`, default: `$id.$key.output_r2_*.output_r2_*`, multiple_sep: `\";\"`. Path to the output for R2" , - "default": "$id.$key.output_r2_*.output_r2_*" + "default":"$id.$key.output_r2_*.output_r2_*" } diff --git a/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml b/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml index e188ace5..02ae3eab 100644 --- a/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml +++ b/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml @@ -1,6 +1,32 @@ name: "well_demultiplex" namespace: "workflows" version: "main" +authors: +- name: "Dries Schaumont" + roles: + - "maintainer" + info: + links: + email: "dries@data-intuitive.com" + github: "DriesSchaumont" + orcid: "0000-0002-4389-0440" + linkedin: "dries-schaumont" + organizations: + - name: "Data Intuitive" + href: "https://www.data-intuitive.com" + role: "Data Scientist" +- name: "Marijke Van Moerbeke" + roles: + - "contributor" + info: + links: + github: "mvanmoerbeke" + orcid: "0000-0002-3097-5621" + linkedin: "marijke-van-moerbeke-84303a34" + organizations: + - name: "OpenAnalytics" + href: "https://www.openanalytics.eu" + role: "Statistical Consultant" argument_groups: - name: "Input arguments" arguments: @@ -71,6 +97,13 @@ argument_groups: direction: "output" multiple: false multiple_sep: ";" + - type: "string" + name: "--well_id" + info: null + required: false + direction: "output" + multiple: false + multiple_sep: ";" - type: "string" name: "--barcode" info: null @@ -92,6 +125,14 @@ argument_groups: direction: "output" multiple: false multiple_sep: ";" + - type: "integer" + name: "--n_wells" + description: "The number of wells in the pool is well is a part of." + info: null + required: false + direction: "output" + multiple: false + multiple_sep: ";" resources: - type: "nextflow_script" path: "main.nf" @@ -106,6 +147,10 @@ test_resources: path: "test.nf" is_executable: true entrypoint: "test_wf" +- type: "nextflow_script" + path: "test.nf" + is_executable: true + entrypoint: "test_wf2" info: null status: "enabled" requirements: @@ -210,8 +255,8 @@ build_info: output: "target/nextflow/workflows/well_demultiplex" executable: "target/nextflow/workflows/well_demultiplex/main.nf" viash_version: "0.9.0" - git_commit: "65dd41d8b1b4a307735c72320c96c0880c75f17f" - git_remote: "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + git_commit: "82647a421dae521a9563f7f02050f13a1319eb4a" + git_remote: "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" dependencies: - "target/dependencies/vsh/vsh/biobox/main/nextflow/cutadapt" - "target/dependencies/vsh/vsh/craftbox/v0.1.0/nextflow/concat_text" diff --git a/target/nextflow/workflows/well_demultiplex/main.nf b/target/nextflow/workflows/well_demultiplex/main.nf index a4b4e9cd..88f56303 100644 --- a/target/nextflow/workflows/well_demultiplex/main.nf +++ b/target/nextflow/workflows/well_demultiplex/main.nf @@ -8,6 +8,10 @@ // authors of this component should specify the license in the header of such // files, or include a separate license file detailing the licenses of all included // files. +// +// Component authors: +// * Dries Schaumont (maintainer) +// * Marijke Van Moerbeke (contributor) //////////////////////////// // VDSL3 helper functions // @@ -2807,6 +2811,49 @@ meta = [ "name" : "well_demultiplex", "namespace" : "workflows", "version" : "main", + "authors" : [ + { + "name" : "Dries Schaumont", + "roles" : [ + "maintainer" + ], + "info" : { + "links" : { + "email" : "dries@data-intuitive.com", + "github" : "DriesSchaumont", + "orcid" : "0000-0002-4389-0440", + "linkedin" : "dries-schaumont" + }, + "organizations" : [ + { + "name" : "Data Intuitive", + "href" : "https://www.data-intuitive.com", + "role" : "Data Scientist" + } + ] + } + }, + { + "name" : "Marijke Van Moerbeke", + "roles" : [ + "contributor" + ], + "info" : { + "links" : { + "github" : "mvanmoerbeke", + "orcid" : "0000-0002-3097-5621", + "linkedin" : "marijke-van-moerbeke-84303a34" + }, + "organizations" : [ + { + "name" : "OpenAnalytics", + "href" : "https://www.openanalytics.eu", + "role" : "Statistical Consultant" + } + ] + } + } + ], "argument_groups" : [ { "name" : "Input arguments", @@ -2885,6 +2932,14 @@ meta = [ "multiple" : false, "multiple_sep" : ";" }, + { + "type" : "string", + "name" : "--well_id", + "required" : false, + "direction" : "output", + "multiple" : false, + "multiple_sep" : ";" + }, { "type" : "string", "name" : "--barcode", @@ -2908,6 +2963,15 @@ meta = [ "direction" : "output", "multiple" : false, "multiple_sep" : ";" + }, + { + "type" : "integer", + "name" : "--n_wells", + "description" : "The number of wells in the pool is well is a part of.", + "required" : false, + "direction" : "output", + "multiple" : false, + "multiple_sep" : ";" } ] } @@ -2932,6 +2996,12 @@ meta = [ "path" : "test.nf", "is_executable" : true, "entrypoint" : "test_wf" + }, + { + "type" : "nextflow_script", + "path" : "test.nf", + "is_executable" : true, + "entrypoint" : "test_wf2" } ], "status" : "enabled", @@ -3064,8 +3134,8 @@ meta = [ "engine" : "native|native", "output" : "target/nextflow/workflows/well_demultiplex", "viash_version" : "0.9.0", - "git_commit" : "65dd41d8b1b4a307735c72320c96c0880c75f17f", - "git_remote" : "https://x-access-token:ghs_McZDF0yobnnHmOEb2Q4JaaB3pzr9mz1VbIOs@github.com/viash-hub/htrnaseq" + "git_commit" : "82647a421dae521a9563f7f02050f13a1319eb4a", + "git_remote" : "https://x-access-token:ghs_GvoC19gNBNw8DS3yDc8aa44laHZP4K2GBiY3@github.com/viash-hub/htrnaseq" }, "package_config" : { "name" : "htrnaseq", @@ -3119,18 +3189,73 @@ workflow run_wf { main: output_ch = input_ch + /* + Parse the fasta file containing the barcodes and do the following: + - The sequence headers must not contain any whitespaces + - The headers (Well IDs) must be unique + - The barcodes must be unique + - Store the number of barcodes in the state + - Add a barcode to well ID (header) mapping to the state, + in order to be able to retreive the well ID based on the FASTQ name after well demultiplexing + */ + | map {id, state -> + def n_wells = state.barcodesFasta.countFasta() as int + // The header is the full header, the id is the part header up to the first whitespace character + // We do not allow whitespace in the header of the fasta file, so assert this. + def fasta_entries = state.barcodesFasta.splitFasta( + record: ["id": true, "header": true, "seqString": true] + ) + assert fasta_entries.every{it.id == it.header}, \ + "The barcodes FASTA headers must not contain any whitespace!" + // Check if the fasta headers are unique + def fasta_ids = fasta_entries.collect{it.id} + assert fasta_ids.clone().unique() == fasta_ids, \ + "The barcodes FASTA entries must have a unique name!" + // Check if the sequences are unique + def fasta_sequences = fasta_entries.collect{it.seqString} + assert fasta_sequences.clone().unique() == fasta_sequences, \ + "The barcodes FASTA sequences must be unique!" + def well_id_matcher = /^([A-Za-z]+)0*([1-9]?[0-9]+)$/ + def entries_corrected_id = fasta_entries.collectEntries { it -> + def unformatted_id = it.header + def id_matched_to_format = unformatted_id =~ well_id_matcher + assert (id_matched_to_format && id_matched_to_format.getCount() == 1), \ + "The FASTA headers must match the coordinate system of a well plate (e.g. A01, B01, ... or AA1, AB1, ...). Found: ${unformatted_id}" + def id_letters = id_matched_to_format[0][1].toUpperCase() + def id_numbers = id_matched_to_format[0][2] + ["${id_letters}${id_numbers}", it.seqString] + } + def newState = state + [ + "n_wells": n_wells, + "well_id_barcode_mapping": entries_corrected_id, + ] + [id, newState] + } + /* + For each pool (i.e. event) in the channel, a list of R1 and R2 input + reads is provided which correspond to the lanes. If there are multiple lanes, + we can demultiplex into the wells for each lane in parallel. Therefore, cutadapt + must be started multiple times and we need an event per lane. The events are + created by taking the R1 and R2 pairs from the input lists. The index of the elements + in these lists are added to the ID in order to make them unique. + */ | flatMap {id, state -> - assert state.input_r1.size() == state.input_r2.size(), "Expected equal number of inputs for R1 and R2" + assert state.input_r1.size() == state.input_r2.size(), \ + "Expected equal number of inputs for R1 and R2" + // Store the number of lanes that were encountered here in order to + // group them together in an asynchronous manner later by providing + // the expected number of events to be grouped to groupTuple. + // see https://www.nextflow.io/docs/latest/reference/operator.html#grouptuple def n_lanes = state.input_r1.size() [state.input_r1, state.input_r2].transpose().withIndex().collect{ input_pair, index -> def single_input_r1 = input_pair[0] def single_input_r2 = input_pair[1] - def newState = state + ["input_r1": single_input_r1, - "input_r2": single_input_r2, - "pool": id, + def newState = state + ["input_r1": single_input_r1, + "input_r2": single_input_r2, + "pool": id, "lane_sorting": index, "n_lanes": n_lanes] - def newId = id + "_" + index + def newId = id + "_" + index [newId, newState] } } @@ -3151,10 +3276,12 @@ workflow run_wf { }, toState: { id, result, state -> def newState = [ - pool: state.pool, - n_lanes: state.n_lanes, - output: result.output, - lane_sorting: state.lane_sorting, + "pool": state.pool, + "n_lanes": state.n_lanes, + "output": result.output, + "lane_sorting": state.lane_sorting, + "n_wells": state.n_wells, + "well_id_barcode_mapping": state.well_id_barcode_mapping, ] return newState } @@ -3163,58 +3290,129 @@ workflow run_wf { | flatMap{ id, state -> def pool = state.pool state.output.collect{ p -> - def barcode = (p =~ /.*\\/([ACTG]*|unknown)_R?.*/)[0][1] - def pair_end = (p =~ /.*_(R[12])_.*/)[0][1] - def lane = (p =~ /.*_(L\d+).*/) ? (p =~ /.*_(L\d+).*/)[0][1] : "NA" - def new_id = pool + "__" + barcode - def group_key = groupKey(new_id, state.n_lanes * 2) + def well_id_matcher = p =~ /.*\\/([A-Za-z0-9]*|unknown)_R?.*/ + assert well_id_matcher, \ + "Could not find Well ID in the name of FASTQ file ($p) output from cutadapt." + def well_id = well_id_matcher[0][1] + // Note: set the barcode to 'null' for reads that were put into 'unknown' + def barcode = (well_id != "unknown") ? state.well_id_barcode_mapping[well_id].replaceAll("[^ACGTacgt]", "") : null + assert (well_id == "unknown") || (barcode != null), \ + "After demultiplexing, no Well ID could be retreived for barcode ${barcode}." + def pair_end_matcher = p =~ /.*_(R[12])_.*/ + assert pair_end_matcher, \ + "Could not find read orientation information in the name of the FASTQ file ($p) output from cutadapt." + def pair_end = pair_end_matcher[0][1] + def lane_matcher = p =~ /.*_(L\d+).*/ + def lane = lane_matcher ? lane_matcher[0][1] : "NA" + def new_id = pool + "__" + well_id [ - group_key, + new_id, [ - pool: pool, - barcode: barcode, - output: p, - lane: lane, - pair_end: pair_end, - lane_sorting: state.lane_sorting, - _meta: [ join_id: pool ] + "pool": pool, + "barcode": barcode, + "well_id": well_id, + "output": p, + "lane": lane, + "n_wells": state.n_wells, + "pair_end": pair_end, + "n_lanes": state.n_lanes, + "lane_sorting": state.lane_sorting, + "_meta": [ "join_id": pool ] ] ] } } - // Group the outputs from across lanes - | groupTuple(sort: "hash") + /* + At this point, the events are provided on the smallest possible level, + as each event represents the reads for a certain orientation from a + particular lane and a single well. Here, we join these events back together + on well level, gathering FASTQS across the lanes and read orientations. + In order to make this joining as efficient as possible, the number of + lanes which are expected to be gathered were stored in the state earlier. + This way, the processing of a well can continue as as soon as all of + the lanes have been gathered. The number of lanes times 2 (forward + and reverse orientation) represents the total number of FASTQS (events) + to be included for a certain well. + */ + | map {id, state -> + def group_key = groupKey(id, state.n_lanes * 2) + return [group_key, state] + } + | groupTuple(sort: {a, b -> + // Make sure that the grouped states are in order, + // meaning forward and reverse FASTQs are paired and the FASTQ + // for the forward reads comes before the reverse reads FASTQ. + if (a.lane_sorting == b.lane_sorting) { + return a.pair_end <=> b.pair_end + } + return a.lane_sorting <=> b.lane_sorting + }) | map {_, states -> - def r1_output = states.findAll{ it.pair_end == "R1" }.collect{it.output} - def r2_output = states.findAll{ it.pair_end == "R2" }.collect{it.output} - def lane_sorting_r1 = states.findAll{ it.pair_end == "R1" }.collect{it.lane_sorting} - def lane_sorting_r2 = states.findAll{ it.pair_end == "R2" }.collect{it.lane_sorting} + // The states are in one long flat list, group them into pairs + // This assumes that the FASTQ files are already in order! + // (See the 'sort' argument of groupTuple above) + def output_pairs = states.collate(2) - // At this point, the lane_sorting hold the positios the items in r1_output and r2_output - // should become in a new list. - def r1_output_sorted = new ArrayList(r1_output.size()) - def r2_output_sorted = new ArrayList(r2_output.size()) - - lane_sorting_r1.eachWithIndex { pos, index -> - r1_output_sorted[pos] = r1_output[index] - } - - lane_sorting_r2.eachWithIndex { pos, index -> - r2_output_sorted[pos] = r2_output[index] + // Sanity check the state + output_pairs.each{ pair -> + assert pair.size() == 2, \ + "State error: expected FASTQ pairs as output from cutadapt, " + + "found output state: $pair" + def (first, second) = pair + def should_be_the_same = [ + "barcode", + "well_id", + "lane", + "pool", + "lane_sorting", + ] + should_be_the_same.each { attr_to_check -> + first_attr = first.get(attr_to_check) + second_attr = second.get(attr_to_check) + assert first_attr == second_attr, \ + "State error: expected FASTQ pairs from cutadapt to have " + + "the same detected ${attr_to_check}. Found: " + + "$first_attr and $second_attr" + } + // Forward and reverse reads should be designated + // by 'R1' and 'R2', and sorted lexographically. + assert first.pair_end == "R1", \ + "State error: expected first item from FASTQ pair to have " + + "orientation 'R1', found $first.pair_end" + assert second.pair_end == "R2", \ + "State error: expected second item from FASTQ pair to have " + + "orientation 'R2', found $second.pair_end" } + def r1_output = output_pairs.collect{it[0].output} + def r2_output = output_pairs.collect{it[1].output} assert r1_output.size() == r2_output.size() + + /* The lane sorting represents the order of the FASTQ files + as provided by the input. The order of the FASTQ files should + remain the same in the well output. This is because the result of STAR + can differ based on the order of the reads in the FASTQ file. + Even when the same reads are provided, the order of them matters. + */ + def lane_sorting = output_pairs.it[0].lane_sorting + def sorting_is_monotonically_increasing = lane_sorting.withIndex().every { i, idx -> + idx == 0 || lane_sorting[idx - 1] <= i + } + assert sorting_is_monotonically_increasing, \ + "State error: expected the order of the FASTQ files after grouping " + + "the cutadapt output to be the same as the order in the input. " + + "Found sorting $lane_sorting, R1 output: $r1_output, R2 output: $r2_output." + // Here we pick the state from the first item in the list of states // and overwrite the keys which are different across states - // TODO: we can assert that these keys are the same def first_state = states[0] - def new_id = first_state.pool + "__" + first_state.barcode - def new_state = first_state + ["output_r1": r1_output_sorted, "output_r2": r2_output_sorted] + def new_id = first_state.pool + "__" + first_state.well_id + def new_state = first_state + ["output_r1": r1_output, "output_r2": r2_output] [new_id, new_state] } // TODO: Expand this into matching a whitelist/blacklist of barcodes // ... and turn into separate component - | filter{ id, state -> state.barcode != "unknown" } + | filter{ id, state -> state.well_id != "unknown" } | concat_text.run( directives: [label: ["lowmem", "lowcpu"]], key: "concat_txt_r1", @@ -3247,7 +3445,7 @@ workflow run_wf { return newState } ) - | setState(["pool", "barcode", "lane", "_meta", "output_r1", "output_r2"]) + | setState(["pool", "well_id", "n_wells", "barcode", "lane", "_meta", "output_r1", "output_r2"]) emit: output_ch diff --git a/target/nextflow/workflows/well_demultiplex/nextflow.config b/target/nextflow/workflows/well_demultiplex/nextflow.config index 892d49e4..5c4bb992 100644 --- a/target/nextflow/workflows/well_demultiplex/nextflow.config +++ b/target/nextflow/workflows/well_demultiplex/nextflow.config @@ -4,6 +4,7 @@ manifest { nextflowVersion = '!>=20.12.1-edge' version = 'main' description = 'Demultiplexing on well level' + author = 'Dries Schaumont, Marijke Van Moerbeke' } process.container = 'nextflow/bash:latest' diff --git a/target/nextflow/workflows/well_demultiplex/nextflow_labels.config b/target/nextflow/workflows/well_demultiplex/nextflow_labels.config index 66f5e21c..2821ec46 100644 --- a/target/nextflow/workflows/well_demultiplex/nextflow_labels.config +++ b/target/nextflow/workflows/well_demultiplex/nextflow_labels.config @@ -70,11 +70,14 @@ profiles { local { // This config is for local processing. process { + withName: ".*parallel_map_process" { + maxForks = 1 + } maxMemory = 25.GB withLabel: verylowcpu { cpus = 2 } withLabel: lowcpu { cpus = 4 } withLabel: midcpu { cpus = 6 } - withLabel: highcpu { cpus = 12 } + withLabel: highcpu { cpus = 8 } withLabel: lowmem { memory = { get_memory( 8.GB * task.attempt ) } } withLabel: midmem { memory = { get_memory( 12.GB * task.attempt ) } } diff --git a/target/nextflow/workflows/well_demultiplex/nextflow_schema.json b/target/nextflow/workflows/well_demultiplex/nextflow_schema.json index a6b3497a..7e818324 100644 --- a/target/nextflow/workflows/well_demultiplex/nextflow_schema.json +++ b/target/nextflow/workflows/well_demultiplex/nextflow_schema.json @@ -60,7 +60,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.output_r1_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files", "help_text": "Type: List of `file`, required, default: `$id.$key.output_r1_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files" , - "default": "$id.$key.output_r1_*.fastq" + "default":"$id.$key.output_r1_*.fastq" } @@ -71,7 +71,7 @@ "description": "Type: List of `file`, required, default: `$id.$key.output_r2_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files", "help_text": "Type: List of `file`, required, default: `$id.$key.output_r2_*.fastq`, multiple_sep: `\";\"`. List of demultiplexed fastq files" , - "default": "$id.$key.output_r2_*.fastq" + "default":"$id.$key.output_r2_*.fastq" } @@ -85,6 +85,16 @@ } + , + "well_id": { + "type": + "string", + "description": "Type: `string`. ", + "help_text": "Type: `string`. " + + } + + , "barcode": { "type": @@ -115,6 +125,16 @@ } + , + "n_wells": { + "type": + "integer", + "description": "Type: `integer`. The number of wells in the pool is well is a part of", + "help_text": "Type: `integer`. The number of wells in the pool is well is a part of." + + } + + } },