Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
T
tasks
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container Registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
biowdl
tasks
Commits
34bda02c
Unverified
Commit
34bda02c
authored
6 years ago
by
Peter van 't Hof
Committed by
GitHub
6 years ago
Browse files
Options
Downloads
Plain Diff
Merge branch 'master' into SASC-741
parents
8ffea620
605c278c
No related branches found
Branches containing commit
No related tags found
Tags containing commit
1 merge request
!11
Changes needed for the iterative assembly pipeline
Changes
5
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
biopet.wdl
+1
-2
1 addition, 2 deletions
biopet.wdl
centrifuge.wdl
+138
-44
138 additions, 44 deletions
centrifuge.wdl
flash.wdl
+40
-0
40 additions, 0 deletions
flash.wdl
gatk.wdl
+3
-2
3 additions, 2 deletions
gatk.wdl
star.wdl
+2
-0
2 additions, 0 deletions
star.wdl
with
184 additions
and
48 deletions
biopet.wdl
+
1
−
2
View file @
34bda02c
...
...
@@ -145,10 +145,9 @@ task SampleConfig {
}
output {
Array[String] keys = read_lines(
stdout()
)
File keysFile =
stdout()
File? jsonOutput = jsonOutputPath
File? tsvOutput = tsvOutputPath
Object values = if (defined(tsvOutput) && size(tsvOutput) > 0) then read_map(tsvOutput) else { "": "" }
}
runtime {
...
...
This diff is collapsed.
Click to expand it.
centrifuge.wdl
+
138
−
44
View file @
34bda02c
# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 201
7
# Copyright Sequencing Analysis Support Core - Leiden University Medical Center 201
8
#
# Tasks from centrifuge
task build {
File conversionTable
File taxonomyTree
File inputFasta
String centrifugeIndexBase
String? preCommand
String? centrifugeBuildExecutable = "centrifuge-build"
#Boolean? c = false
Boolean? largeIndex = false
Boolean? noAuto = false
Int? bMax
Int? bMaxDivn
Boolean? noDiffCover = false
Boolean? noRef = false
Boolean? justRef = false
Int? offRate
Int? fTabChars
File? nameTable
File? sizeTable
Int? seed
Int? threads
Int? memory
Int? kmerCount
command {
set -e -o pipefail
${preCommand}
${"mkdir -p $(dirname " + centrifugeIndexBase + ")"}
${centrifugeBuildExecutable} \
${true='--large-index' false='' largeIndex} \
${true='--noauto' false='' noAuto} \
${'--bmax ' + bMax} \
${'--bmaxdivn ' + bMaxDivn} \
${true='--nodc' false='' noDiffCover} \
${true='--noref' false='' noRef} \
${true='--justref' false='' justRef} \
${'--offrate ' + offRate} \
${'--ftabchars ' + fTabChars} \
${'--name-table ' + nameTable } \
${'--size-table ' + sizeTable} \
${'--seed ' + seed} \
${'--kmer-count' + kmerCount} \
${'--threads ' + threads} \
--conversion-table ${conversionTable} \
--taxonomy-tree ${taxonomyTree} \
${inputFasta} \
${centrifugeIndexBase}
}
runtime {
cpu: select_first([threads, 8])
memory: select_first([memory, 20])
}
}
task classify {
String outputDir
Boolean? compressOutput = true
String? preCommand
String indexPrefix
File? unpairedReads
File read1
File? read2
Boolean? fastaInput
# Variables for handling output
String outputFileName = outputDir + "/centrifuge.out"
String reportFileName = outputDir + "/centrifuge_report.tsv"
String finalOutputName = if (compressOutput == true) then outputFileName + ".gz" else outputFileName
String? metFileName # If this is specified, the report file is empty
Int? assignments
Int? minHitLen
Int? minTotalLen
Array[String]? hostTaxIds
Array[String]? excludeTaxIds
Int? threads
Int? memory
command {
set -e -o pipefail
mkdir -p ${outputDir}
${preCommand}
centrifuge \
${"-p " + threads} \
${"-x " + indexPrefix} \
${true="-f" false="" fastaInput} \
${true="-k " false="" defined(assignments)} ${assignments} \
${true="-1 " false="-U " defined(read2)} ${read1} \
${"-2 " + read2} \
${"-U " + unpairedReads} \
${"--report-file " + reportFileName} \
${"--min-hitlen " + minHitLen} \
${"--min-totallen " + minTotalLen} \
${"--met-file " + metFileName} \
${true="--host-taxids " false="" defined(hostTaxIds)} ${sep=',' hostTaxIds} \
${true="--exclude-taxids " false="" defined(excludeTaxIds)} ${sep=',' excludeTaxIds} \
${true="| gzip -c >" false="-S" compressOutput} ${finalOutputName}
}
output {
File classifiedReads = finalOutputName
File reportFile = reportFileName
}
runtime {
cpu: select_first([threads, 1])
memory: select_first([memory, 4])
}
}
task download {
String libraryPath
...
...
@@ -62,55 +170,41 @@ task downloadTaxonomy {
}
}
task build {
File conversionTable
File taxonomyTree
File inputFasta
String centrifugeIndexBase
task kreport {
String? preCommand
String? centrifugeBuildExecutable = "centrifuge-build"
#Boolean? c = false
Boolean? largeIndex = false
Boolean? noAuto = false
Int? bMax
Int? bMaxDivn
Boolean? noDiffCover = false
Boolean? noRef = false
Boolean? justRef = false
Int? offRate
Int? fTabChars
File? nameTable
File? sizeTable
Int? seed
Int? threads = 1
Int? kmerCount
File centrifugeOut
Boolean inputIsCompressed
String kreportFileName=sub(centrifugeOut, "\\.out$|\\.out\\.gz$", "\\.kreport")
String indexPrefix
Boolean? onlyUnique
Boolean? showZeros
Boolean? isCountTable
Int? minScore
Int? minLength
Int? cores
Int? memory
command {
set -e -o pipefail
${preCommand}
${"mkdir -p $(dirname " + centrifugeIndexBase + ")"}
${centrifugeBuildExecutable} \
${true='--large-index' false='' largeIndex} \
${true='--noauto' false='' noAuto} \
${'--bmax ' + bMax} \
${'--bmaxdivn ' + bMaxDivn} \
${true='--nodc' false='' noDiffCover} \
${true='--noref' false='' noRef} \
${true='--justref' false='' justRef} \
${'--offrate ' + offRate} \
${'--ftabchars ' + fTabChars} \
${'--name-table ' + nameTable } \
${'--size-table ' + sizeTable} \
${'--seed ' + seed} \
${'--kmer-count' + kmerCount} \
${'--threads ' + threads} \
--conversion-table ${conversionTable} \
--taxonomy-tree ${taxonomyTree} \
${inputFasta} \
${centrifugeIndexBase}
centrifuge-kreport \
-x ${indexPrefix} \
${true="--only-unique" false="" onlyUnique} \
${true="--show-zeros" false="" showZeros} \
${true="--is-count-table" false="" isCountTable} \
${"--min-score " + minScore} \
${"--min-length " + minLength} \
${true="<(zcat" false="" inputIsCompressed} ${centrifugeOut}\
${true=")" false="" inputIsCompressed} \
> ${kreportFileName}
}
output {
File kreport = kreportFileName
}
runtime {
cpu: select_first([threads])
cpu: select_first([cores, 1])
memory: select_first([memory, 4])
}
}
This diff is collapsed.
Click to expand it.
flash.wdl
0 → 100644
+
40
−
0
View file @
34bda02c
task flash {
String? preCommand
File inputR1
File inputR2
String outdirPath
String? outPrefix = "flash"
Int? minOverlap
Int? maxOverlap
Boolean? compress = true
Int? threads
Int? memory
command {
set -e -o pipefail
mkdir -p ${outdirPath}
${preCommand}
flash \
${"--threads=" + threads} \
${"--output-directory=" + outdirPath} \
${"--output-prefix=" + outPrefix} \
${true="--compress " false="" defined(compress)} \
${"--min-overlap=" + minOverlap} \
${"--max-overlap=" + maxOverlap} \
${inputR1} ${inputR2}
}
output {
File extendedFrags = outdirPath + "/" + outPrefix + ".extendedFrags.fastq.gz"
File notCombined1 = outdirPath + "/" + outPrefix + ".notCombined_1.fastq.gz"
File notCombined2 = outdirPath + "/" + outPrefix + ".notCombined_2.fastq.gz"
File hist = outdirPath + "/" + outPrefix + ".hist"
File histogram = outdirPath + "/" + outPrefix + ".histogram"
}
runtime {
cpu: select_first([threads, 2])
memory: select_first([memory, 2])
}
}
\ No newline at end of file
This diff is collapsed.
Click to expand it.
gatk.wdl
+
3
−
2
View file @
34bda02c
...
...
@@ -253,6 +253,7 @@ task SplitNCigarReads {
String? preCommand
File input_bam
File input_bam_index
File ref_fasta
File ref_fasta_index
File ref_dict
...
...
@@ -271,13 +272,13 @@ task SplitNCigarReads {
SplitNCigarReads \
-I ${input_bam} \
-R ${ref_fasta} \
-O ${output_bam}
# might have to be -o depending on GATK version
\
-O ${output_bam} \
-L ${sep=' -L ' intervals}
}
output {
File bam = output_bam
File bam_index = output_bam
+
".bai"
File bam_index =
sub(
output_bam
, "\\.bam$",
".bai"
)
}
runtime {
...
...
This diff is collapsed.
Click to expand it.
star.wdl
+
2
−
0
View file @
34bda02c
...
...
@@ -12,6 +12,7 @@ task Star {
String? outStd
String? twopassMode
Array[String]? outSAMattrRGline
Int? limitBAMsortRAM
Int? memory
...
...
@@ -34,6 +35,7 @@ task Star {
${"--runThreadN " + runThreadN} \
${"--outStd " + outStd} \
${"--twopassMode " + twopassMode} \
${"--limitBAMsortRAM " + limitBAMsortRAM} \
${true="--outSAMattrRGline " false="" defined(outSAMattrRGline)} ${sep=" , " outSAMattrRGline}
}
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment