Commit 8ed8a020 authored by Cats's avatar Cats
Browse files

Merge remote-tracking branch 'origin/develop' into refOptional

parents ae1d2c02 cdbcd68d
......@@ -12,6 +12,13 @@ version 5.0.0-dev
---------------------------
+ GffCompare: Make the `referenceAnnotation` input optional.
+ Stringtie: Add the `minimumCoverage` input.
+ UMI-tools: update default dockerImage to use umitools v1.1.1 with correct samtools version (1.10)
+ UMI-tools: re-introduce samtools indexing
+ UMI-tools: update default dockerImage to use umitools v1.1.1
+ UMI-tools dedup: Add tempdir
+ Update BCFTOOLS view: add options for filtering (include, exclude, excludeUncalled).
+ Duphold: add duphold.wdl.
+ Add new wdl file prepareShiny.wdl for creating input files for shiny app.
+ mergePacBio: Rename `mergedReport` to `outputPathMergedReport`.
+ Lima: Fix copy commands.
+ Fixed the `size` call in the default for gffread's timeMinutes, to retrieve
......
......@@ -290,6 +290,10 @@ task View {
input {
File inputFile
String outputPath = "output.vcf"
Boolean excludeUncalled = false
String? exclude
String? include
String memory = "256M"
Int timeMinutes = 1 + ceil(size(inputFile, "G"))
......@@ -302,6 +306,9 @@ task View {
set -e
mkdir -p "$(dirname ~{outputPath})"
bcftools view \
~{"--exclude " + exclude} \
~{"--include " + include} \
~{true="--exclude-uncalled" false="" excludeUncalled} \
-o ~{outputPath} \
-O ~{true="z" false="v" compressed} \
~{inputFile}
......@@ -324,6 +331,9 @@ task View {
# inputs
inputFile: {description: "A vcf or bcf file.", category: "required"}
outputPath: {description: "The location the output VCF file should be written.", category: "common"}
include: {description: "Select sites for which the expression is true (see man page for details).", category: "advanced"}
exclude: {description: "Exclude sites for which the expression is true (see man page for details).", category: "advanced"}
excludeUncalled: {description: "Exclude sites without a called genotype (see man page for details).", category: "advanced"}
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"}
......
version 1.0
# Copyright (c) 2020 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 Duphold {
input {
File inputVcf
File bamFile
File bamIndex
File referenceFasta
File referenceFastaFai
String sample
String outputPath = "./duphold.vcf"
String memory = "15G"
Int timeMinutes = 1440
String dockerImage = "quay.io/biocontainers/duphold:0.2.1--h516909a_1"
}
command {
set -e
mkdir -p "$(dirname ~{outputPath})"
export DUPHOLD_SAMPLE_NAME=~{sample}
duphold \
-v ~{inputVcf} \
-b ~{bamFile} \
-f ~{referenceFasta} \
-o ~{outputPath}
}
output {
File outputVcf = outputPath
}
runtime {
memory: memory
time_minutes: timeMinutes
docker: dockerImage
}
parameter_meta {
# inputs
inputVcf: {description: "The VCF file to process.", category: "required"}
bamFile: {description: "The bam file to process.", category: "required"}
bamIndex: {description: "The index of the bam file.", category: "required"}
referenceFasta: {description: "The reference fasta file also used for mapping.", category: "required"}
referenceFastaFai: {description: "Fasta index (.fai) file of the reference.", category: "required" }
sample: {description: "The name of the sample.", category: "required"}
outputPath: {description: "The location the output VCF file should be written.", category: "common"}
memory: {description: "The memory required to run the programs.", category: "advanced"}
timeMinutes: {description: "The maximum duration (in minutes) the tool is allowed to run.", 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
outputVcf: {description: "Duphold annotated VCF file."}
}
}
version 1.0
# Copyright (c) 2017 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 CreateDesignMatrix {
input {
File countTable
String shinyDir = "."
String memory = "5G"
Int timeMinutes = 30
String dockerImage = "quay.io/biocontainers/predex:0.9.2--pyh3252c3a_0"
}
command {
set -e
mkdir -p ~{shinyDir}
predex design \
--input ~{countTable} \
--output ~{shinyDir}
}
output {
File dgeDesign = shinyDir + "/design_matrix.tsv"
}
runtime {
memory: memory
time_minutes: timeMinutes
docker: dockerImage
}
parameter_meta {
# inputs
countTable: {description: "The created count table from HTseq.", category: "required"}
shinyDir: {description: "The directory to write the output to.", category: "required"}
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"}
# outputs
dgeDesign: {description: "Design matrix template to add sample information for DGE analysis."}
}
}
task CreateAnnotation {
input {
File referenceFasta
File referenceGtfFile
String shinyDir = "."
String memory = "5G"
Int timeMinutes = 30
String dockerImage = "quay.io/biocontainers/predex:0.9.2--pyh3252c3a_0"
}
command {
set -e
mkdir -p ~{shinyDir}
predex annotation \
--fasta ~{referenceFasta} \
--gtf ~{referenceGtfFile} \
--output ~{shinyDir}
}
output {
File dgeAnnotation = shinyDir + "/annotation.tsv"
}
runtime {
memory: memory
time_minutes: timeMinutes
docker: dockerImage
}
parameter_meta {
# inputs
referenceFasta: {description: "The reference Fasta file.", category: "required"}
referenceGtfFile: {description: "The reference GTF file.", category: "required"}
shinyDir: {description: "The directory to write the output to.", category: "required"}
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"}
# outputs
dgeAnnotation: {description: "Annotation file for DGE analysis."}
}
}
......@@ -31,7 +31,7 @@ task Extract {
Boolean threePrime = false
Int timeMinutes = 1 + ceil(size([read1, read2], "G") * 2)
String dockerImage = "quay.io/biocontainers/mulled-v2-509311a44630c01d9cb7d2ac5727725f51ea43af:6089936aca6219b5bb5f54210ac5eb456c7503f2-0"
String dockerImage = "quay.io/biocontainers/mulled-v2-509311a44630c01d9cb7d2ac5727725f51ea43af:3067b520386698317fd507c413baf7f901666fd4-0"
}
command {
......@@ -78,6 +78,8 @@ task Dedup {
File inputBam
File inputBamIndex
String outputBamPath
String tmpDir = "./umiToolsDedupTmpDir"
Boolean paired = true
String? umiSeparator
......@@ -85,21 +87,21 @@ task Dedup {
String memory = "25G"
Int timeMinutes = 30 + ceil(size(inputBam, "G") * 30)
# Use a multi-package-container which includes umi_tools (0.5.5) and samtools (1.9).
String dockerImage = "quay.io/biocontainers/mulled-v2-509311a44630c01d9cb7d2ac5727725f51ea43af:6089936aca6219b5bb5f54210ac5eb456c7503f2-0"
String dockerImage = "quay.io/biocontainers/mulled-v2-509311a44630c01d9cb7d2ac5727725f51ea43af:3067b520386698317fd507c413baf7f901666fd4-0"
}
String outputBamIndex = sub(outputBamPath, "\.bam$", ".bai")
command {
set -e
mkdir -p "$(dirname ~{outputBamPath})"
mkdir -p "$(dirname ~{outputBamPath})" "~{tmpDir}"
umi_tools dedup \
--stdin ~{inputBam} \
--stdout ~{outputBamPath} \
--stdin=~{inputBam} \
--stdout=~{outputBamPath} \
~{"--output-stats " + statsPrefix} \
~{"--umi-separator=" + umiSeparator} \
~{true="--paired" false="" paired}
~{true="--paired" false="" paired} \
--temp-dir=~{tmpDir}
samtools index ~{outputBamPath} ~{outputBamIndex}
}
......@@ -122,6 +124,7 @@ task Dedup {
inputBam: {description: "The input BAM file.", categrory: "required"}
inputBamIndex: {description: "The index for the ipnut BAM file.", cateogry: "required"}
outputBamPath: {description: "The location to write the output BAM file to.", category: "required"}
tmpDir: {description: "Temporary directory.", category: "advanced"}
paired: {description: "Whether or not the data is paired.", category: "common"}
umiSeparator: {description: "Seperator used for UMIs in the read names.", category: "advanced"}
statsPrefix: {description: "The prefix for the stats files.", category: "advanced"}
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment