diff --git a/CHANGELOG.md b/CHANGELOG.md
index a9329bf5e8eeeca3a1705c43ad389cca68f58ca1..142622e23f2470f0d95e088a908db0bec3eec327 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,14 +11,20 @@ that users understand how the changes affect the new version.
version 5.0.0-dev
---------------------------
++ Centrifuge: Remove metrics file from classification (which causes the
+ summary report to be empty).
+ https://github.com/DaehwanKimLab/centrifuge/issues/83
++ Add NanoPlot and NanoQC tasks.
++ Centrifuge: Add `timeMinutes` to `Classify` task and remove unnecessary
+ downloading tasks (alternative is refseqtools).
+ collect-columns: updated docker image to version 1.0.0 and added the
`sumOnDuplicateId` input (defaults to false).
+ survivor: replace integer boolean type to logical true or false value.
+ vt: Add option to ignore masked reference.
-+ bcftools: add sorting and annotation
++ bcftools: add sorting and annotation.
+ Bam2fastx: Input bam and index are now arrays.
+ Lima: Remove globs from outputs.
-+ Updated task gridss.wdl: add --jvmheap parameter
++ Updated task gridss.wdl: add --jvmheap parameter.
+ A bwa-mem2 task was created with the same interface (including usePostalt)
as the bwa mem task.
+ bwa mem and bwa kit are now one task. The usePostalt boolean can be used to
diff --git a/bcftools.wdl b/bcftools.wdl
index 520bcf159282dac1b000b1e2978330026daf2c88..affa805a78e7fcd2755fc1dab1365741968ff885 100644
--- a/bcftools.wdl
+++ b/bcftools.wdl
@@ -52,6 +52,8 @@ task Annotate {
String dockerImage = "quay.io/biocontainers/bcftools:1.10.2--h4f4756c_2"
}
+ Boolean indexing = if outputType == "z" then true else false
+
command {
set -e
mkdir -p "$(dirname ~{outputPath})"
@@ -77,13 +79,14 @@ task Annotate {
~{true="--single-overlaps" false="" singleOverlaps} \
~{true="--remove" false="" length(removeAnns) > 0} ~{sep="," removeAnns} \
~{inputFile}
- bcftools index --tbi ~{outputPath}
+
+ ~{if indexing then 'bcftools index --tbi ~{outputPath}' else ''}
}
output {
File outputVcf = outputPath
- File outputVcfIndex = outputPath + ".tbi"
+ File? outputVcfIndex = outputPath + ".tbi"
}
runtime {
@@ -132,6 +135,8 @@ task Sort {
String outputType = "z"
}
+ Boolean indexing = if outputType == "z" then true else false
+
command {
set -e
mkdir -p "$(dirname ~{outputPath})"
@@ -139,12 +144,13 @@ task Sort {
-o ~{outputPath} \
-O ~{outputType} \
~{inputFile}
- bcftools index --tbi ~{outputPath}
+
+ ~{if indexing then 'bcftools index --tbi ~{outputPath}' else ''}
}
output {
File outputVcf = outputPath
- File outputVcfIndex = outputPath + ".tbi"
+ File? outputVcfIndex = outputPath + ".tbi"
}
runtime {
@@ -165,50 +171,6 @@ task Sort {
}
-task View {
- input {
- File inputFile
- String outputPath = "output.vcf.gz"
- String memory = "256M"
- Int timeMinutes = 1 + ceil(size(inputFile, "G"))
- String dockerImage = "quay.io/biocontainers/bcftools:1.10.2--h4f4756c_2"
- String outputType = "z"
- Int compressionLevel = 1
- }
-
- command {
- set -e
- mkdir -p "$(dirname ~{outputPath})"
- bcftools view \
- -o ~{outputPath} \
- -O ~{outputType} \
- -l ~{compressionLevel} \
- ~{inputFile}
- bcftools index --tbi ~{outputPath}
- }
-
- output {
- File outputVcf = outputPath
- File outputVcfIndex = outputPath + ".tbi"
- }
-
- runtime {
- memory: memory
- time_minutes: timeMinutes
- docker: dockerImage
- }
-
- parameter_meta {
- inputFile: {description: "A vcf or bcf file.", category: "required"}
- outputPath: {description: "The location the output VCF file should be written.", category: "common"}
- outputType: {description: "Output type: v=vcf, z=vcf.gz, b=bcf, u=uncompressed bcf", category: "advanced"}
- memory: {description: "The amount of memory this job will use.", category: "advanced"}
- compressionLevel: {description: "Compression level from 0 (uncompressed) to 9 (best).", category: "advanced"}
- timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
- dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
- }
-}
-
task Stats {
input {
File inputVcf
@@ -313,3 +275,49 @@ task Stats {
timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
}
}
+
+task View {
+ input {
+ File inputFile
+ String outputPath = "output.vcf"
+ Int compressionLevel = 0
+ String memory = "256M"
+ Int timeMinutes = 1 + ceil(size(inputFile, "G"))
+ String dockerImage = "quay.io/biocontainers/bcftools:1.10.2--h4f4756c_2"
+ }
+
+ String outputType = if compressionLevel > 0 then "z" else "v"
+ Boolean indexing = if compressionLevel > 0 then true else false
+ String outputFilePath = if compressionLevel > 0 then outputPath + ".gz" else outputPath
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputPath})"
+ bcftools view \
+ -o ~{outputPath} \
+ -l ~{compressionLevel} \
+ -O ~{outputType} \
+ ~{inputFile}
+
+ ~{if indexing then 'bcftools index --tbi ~{outputPath}' else ''}
+ }
+ output {
+ File outputVcf = outputPath
+ File? outputVcfIndex = outputPath + ".tbi"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ inputFile: {description: "A vcf or bcf file.", category: "required"}
+ compressionLevel: {description: "Compression level from 0 (uncompressed) to 9 (best).", category: "advanced"}
+ outputPath: {description: "The location the output VCF file should be written.", category: "common"}
+ memory: {description: "The amount of memory this job will use.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+ }
+}
diff --git a/centrifuge.wdl b/centrifuge.wdl
index ee30532570c43a3ab137d51d926ebd5cda6ece20..1e7a0b4566c1b782877ee37689a7a49045ea7fad 100644
--- a/centrifuge.wdl
+++ b/centrifuge.wdl
@@ -110,6 +110,7 @@ task Classify {
Int threads = 4
String memory = "16G"
+ Int timeMinutes = 2880
String dockerImage = "quay.io/biocontainers/centrifuge:1.0.4_beta--he513fc3_5"
}
@@ -127,7 +128,6 @@ task Classify {
~{inputFormatOptions[inputFormat]} \
~{true="--phred64" false="--phred33" phred64} \
--min-hitlen ~{minHitLength} \
- ~{"--met-file " + outputPrefix + "_alignment_metrics.tsv"} \
--threads ~{threads} \
~{"--trim5 " + trim5} \
~{"--trim3 " + trim3} \
@@ -142,7 +142,6 @@ task Classify {
>>>
output {
- File metrics = outputPrefix + "_alignment_metrics.tsv"
File classification = outputPrefix + "_classification.tsv"
File report = outputPrefix + "_output_report.tsv"
}
@@ -150,6 +149,7 @@ task Classify {
runtime {
cpu: threads
memory: memory
+ time_minutes: timeMinutes
docker: dockerImage
}
@@ -169,10 +169,10 @@ task Classify {
excludeTaxIDs: {description: "A comma-separated list of taxonomic IDs that will be excluded in classification procedure.", category: "common"}
threads: {description: "The number of threads to be used.", category: "advanced"}
memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
# outputs
- metrics: {description: "File with centrifuge metrics."}
classification: {description: "File with the classification results."}
report: {description: "File with a classification summary."}
}
@@ -233,73 +233,6 @@ task Inspect {
}
}
-task Download {
- input {
- String libraryPath
- Array[String]? domain
- String executable = "centrifuge-download"
- String? preCommand
- String? seqTaxMapPath
- String database = "refseq"
- String? assemblyLevel
- String? refseqCategory
- Array[String]? taxIds
- Boolean filterUnplaced = false
- Boolean maskLowComplexRegions = false
- Boolean downloadRnaSeqs = false
- Boolean modifyHeader = false
- Boolean downloadGiMap = false
- }
-
- # This will use centrifuge-download to download.
- # The bash statement at the beginning is to make sure
- # the directory for the SeqTaxMapPath exists.
- command {
- set -e -o pipefail
- ~{preCommand}
- ~{"mkdir -p $(dirname " + seqTaxMapPath + ")"}
- ~{executable} \
- -o ~{libraryPath} \
- ~{true='-d ' false='' defined(domain)}~{sep=',' domain} \
- ~{'-a "' + assemblyLevel + '"'} \
- ~{"-c " + refseqCategory} \
- ~{true='-t' false='' defined(taxIds)} '~{sep=',' taxIds}' \
- ~{true='-r' false='' downloadRnaSeqs} \
- ~{true='-u' false='' filterUnplaced} \
- ~{true='-m' false='' maskLowComplexRegions} \
- ~{true='-l' false='' modifyHeader} \
- ~{true='-g' false='' downloadGiMap} \
- ~{database} ~{">> " + seqTaxMapPath}
- }
-
- output {
- File seqTaxMap = "~{seqTaxMapPath}"
- File library = libraryPath
- Array[File] fastaFiles = glob(libraryPath + "/*/*.fna")
- }
- }
-
-task DownloadTaxonomy {
- input {
- String taxonomyDir
- String executable = "centrifuge-download"
- String? preCommand
- }
-
- command {
- set -e -o pipefail
- ~{preCommand}
- ~{executable} \
- -o ~{taxonomyDir} \
- taxonomy
- }
-
- output {
- File taxonomyTree = taxonomyDir + "/nodes.dmp"
- File nameTable = taxonomyDir + "/names.dmp"
- }
- }
-
task KReport {
input {
File classification
diff --git a/nanopack.wdl b/nanopack.wdl
new file mode 100644
index 0000000000000000000000000000000000000000..6860cf13828d50b0190c88d23e62601111bffb8d
--- /dev/null
+++ b/nanopack.wdl
@@ -0,0 +1,172 @@
+version 1.0
+
+# Copyright (c) 2020 Sequencing Analysis Support Core - Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task NanoPlot {
+ input {
+ File inputFile
+ String inputFileType
+ String outputDir
+ String outputPrefix
+ String outputPath = outputDir + outputPrefix
+ Boolean outputTsvStats = true
+ Boolean dropOutliers = false
+ Boolean logLengths = false
+ String format = "png"
+ Boolean showN50 = true
+ String title = basename(outputPrefix)
+
+ Int? maxLength
+ Int? minLength
+ Int? minQual
+ String? readType
+
+ Int threads = 2
+ String memory = "2G"
+ Int timeMinutes = 15
+ String dockerImage = "quay.io/biocontainers/nanoplot:1.32.0--py_0"
+ }
+
+ Map[String, String] fileTypeOptions = {"fastq": "--fastq ", "fasta": "--fasta ", "fastq_rich": "--fastq_rich ", "fastq_minimal": "--fastq_minimal ", "summary": "--summary ", "bam": "--bam ", "ubam": "--ubam ", "cram": "--cram ", "pickle": "--pickle ", "feather": "--feather "}
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputPath})"
+ NanoPlot \
+ --threads ~{threads} \
+ --outdir ~{outputDir} \
+ --prefix ~{outputPrefix} \
+ ~{true="--tsv_stats" false="" outputTsvStats} \
+ ~{true="--drop_outliers" false="" dropOutliers} \
+ ~{true="--loglength" false="" logLengths} \
+ --format ~{format} \
+ ~{true="--N50" false="--no-N50" showN50} \
+ ~{"--maxlength " + maxLength} \
+ ~{"--minlength " + minLength} \
+ ~{"--minqual " + minQual} \
+ ~{"--readtype " + readType} \
+ ~{fileTypeOptions[inputFileType] + inputFile}
+ }
+
+ output {
+ File dynamicHistogram = outputDir + outputPrefix + "Dynamic_Histogram_Read_length.html"
+ File readLengthHistogram = outputDir + outputPrefix + "HistogramReadlength.png"
+ File logScaleReadLengthHistogram = outputDir + outputPrefix + "LogTransformed_HistogramReadlength.png"
+ File report = outputDir + outputPrefix + "NanoPlot-report.html"
+ File weightedHistogram = outputDir + outputPrefix + "Weighted_HistogramReadlength.png"
+ File weightedLogScaleHistogram = outputDir + outputPrefix + "Weighted_LogTransformed_HistogramReadlength.png"
+ File yieldByLength = outputDir + outputPrefix + "Yield_By_Length.png"
+ File? lengthVsQualityScatterPlotDot = outputDir + outputPrefix + "LengthvsQualityScatterPlot_dot.png"
+ File? lengthVsQualityScatterPlotKde = outputDir + outputPrefix + "LengthvsQualityScatterPlot_kde.png"
+ File? stats = outputDir + outputPrefix + "NanoStats.txt"
+ }
+
+ runtime {
+ cpu: threads
+ memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ # inputs
+ inputFile: {description: "The input file.", category: "required"}
+ inputFileType: {description: "The format of the read file.", category: "required"}
+ outputDir: {description: "Output directory path.", category: "required"}
+ outputPrefix: {description: "Output file prefix.", category: "required"}
+ outputTsvStats: {description: "Output the stats file as a properly formatted TSV.", category: "common"}
+ dropOutliers: {description: "Drop outlier reads with extreme long length.", category: "advanced"}
+ logLengths: {description: "Additionally show logarithmic scaling of lengths in plots.", category: "advanced"}
+ format: {description: "Specify the output format of the plots.", category: "required"}
+ showN50: {description: "Show the N50 mark in the read length histogram.", category: "common"}
+ title: {description: "Add a title to all plots, requires quoting if using spaces.", category: "common"}
+ maxLength: {description: "Hide reads longer than length specified.", category: "advanced"}
+ minLength: {description: "Hide reads shorter than length specified.", category: "advanced"}
+ minQual: {description: "Drop reads with an average quality lower than specified.", category: "advanced"}
+ readType: {description: "Which read type to extract information about from summary. Options are 1D, 2D, 1D2", category: "advanced"}
+ threads: {description: "The number of threads to be used.", category: "advanced"}
+ memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+ # outputs
+ dynamicHistogram: {description: "Dynamic histogram of read length."}
+ readLengthHistogram: {description: "Histogram of read length."}
+ logScaleReadLengthHistogram: {description: "Histogram of read lengths after log transformation."}
+ report: {description: "Html summary report."}
+ weightedHistogram: {description: "Weighted histogram of read lengths."}
+ weightedLogScaleHistogram: {description: "Weighted histogram of read lengths after log transformation."}
+ yieldByLength: {description: "Cumulative yield plot."}
+ lengthVsQualityScatterPlotDot: {description: "Read lengths vs average read quality plot."}
+ lengthVsQualityScatterPlotKde: {description: "Read lengths vs average read quality plot."}
+ stats: {description: "NanoStats report."}
+ }
+}
+
+task NanoQc {
+ input {
+ File inputFile
+ String outputDir
+ Boolean directRna = false
+
+ Int? minLength
+
+ String memory = "2G"
+ Int timeMinutes = 15
+ String dockerImage = "quay.io/biocontainers/nanoqc:0.9.4--py_0"
+ }
+
+ command {
+ set -e
+ mkdir -p "$(dirname ~{outputDir})"
+ nanoQC \
+ --outdir ~{outputDir} \
+ ~{true="--rna" false="" directRna} \
+ ~{"--minlen " + minLength} \
+ ~{inputFile}
+ }
+
+ output {
+ File report = outputDir + "nanoQC.html"
+ File log = outputDir + "NanoQC.log"
+ }
+
+ runtime {
+ memory: memory
+ time_minutes: timeMinutes
+ docker: dockerImage
+ }
+
+ parameter_meta {
+ # inputs
+ inputFile: {description: "The input file.", category: "required"}
+ outputDir: {description: "Output directory path.", category: "required"}
+ directRna: {description: "Fastq is from direct RNA-seq and contains U nucleotides.", category: "common"}
+ minLength: {description: "Filters the reads on a minimal length of the given range. Also plots the given length/2 of the begin and end of the reads.", category: "advanced"}
+ memory: {description: "The amount of memory available to the job.", category: "advanced"}
+ timeMinutes: {description: "The maximum amount of time the job will run in minutes.", category: "advanced"}
+ dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+ # outputs
+ report: {description: "Html summary report."}
+ log: {description: "Progress report."}
+ }
+}