Merge conflict resolved

Author: Szilveszter Juhos

.github/CONTRIBUTING.md

@@ -1,25 +1,25 @@
-# CAW Contributing Guidelines
+# Sarek Contributing Guidelines
 
-Hi there! Many thanks for taking an interest in improving CAW.
+Hi there! Many thanks for taking an interest in improving Sarek.
 
-We try to manage the required tasks for CAW using GitHub issues, you probably came to this page when creating one. Please use the prefilled template to save time.
+We try to manage the required tasks for Sarek using GitHub issues, you probably came to this page when creating one. Please use the prefilled template to save time.
 
 However, don't be put off by this template - other more general issues and suggestions are welcome! Contributions to the code are even more welcome ;)
 
-> If you need help using CAW then the best place to go is the Gitter chatroom where you can ask us questions directly: https://gitter.im/SciLifeLab/CAW
+> If you need help using Sarek then the best place to go is the Gitter chatroom where you can ask us questions directly: https://gitter.im/SciLifeLab/Sarek
 
 ## Contribution workflow
-If you'd like to write some code for CAW, the standard workflow
+If you'd like to write some code for Sarek, the standard workflow
 is as follows:
 
 1. Check that there isn't already an issue about your idea in the
-   [CAW issues](https://github.com/SciLifeLab/CAW/issues) to avoid
+   [Sarek issues](https://github.com/SciLifeLab/Sarek/issues) to avoid
    duplicating work.
     * Feel free to add a new issue here for the same reason.
-2. Fork the CAW repository to your GitHub account
+2. Fork the Sarek repository to your GitHub account
 3. Make the necessary changes / additions within your forked repository
 4. Submit a Pull Request against the master branch and wait for the code to be reviewed and merged.
 
 If you're not used to this workflow with git, you can start with some [basic docs from GitHub](https://help.github.com/articles/fork-a-repo/) or even their [excellent interactive tutorial](https://try.github.io/).
 
-For further information/help, please consult the [CAW documentation](https://github.com/SciLifeLab/CAW#documentation) and don't hesitate to get in touch on [Gitter](https://gitter.im/SciLifeLab/CAW) or contact us: maxime.garcia@scilifelab.se, szilveszter.juhos@scilifelab.se
+For further information/help, please consult the [Sarek documentation](https://github.com/SciLifeLab/Sarek#documentation) and don't hesitate to get in touch on [Gitter](https://gitter.im/SciLifeLab/Sarek) or contact us: maxime.garcia@scilifelab.se, szilveszter.juhos@scilifelab.se

.github/ISSUE_TEMPLATE.md

@@ -1,9 +1,9 @@
 <!--
 Hi there!
 
-Many thanks for creating a CAW issue.
+Many thanks for creating a Sarek issue.
 
-Most issues fall into two categories: either you're reporting a problem with CAW or you'd like a change/improvement.
+Most issues fall into two categories: either you're reporting a problem with Sarek or you'd like a change/improvement.
 
 To make sure that you include all of the information needed, please use the template below, you can delete what is not needed.
 
@@ -35,9 +35,9 @@ or ideas how to implement the addition or change
 Providing context helps us coming up with a solution
 Include as many relevant details about the environment you experienced the bug in
 -->
-- **CAW `nextflow.log`:**
+- **Sarek `nextflow.log`:**
   <!-- Re-execute the command line that resulted in a bug with --verbose and -resume and join the .nextflow.log -->
   - [please drag and drop the `.nextflow.log` file that will help understand the error here]
-- **CAW `input.TSV`:**
+- **Sarek `input.TSV`:**
   <!-- Anonymize your TSV file if necessary and join it too  -->
   - [please drag and drop the `TSV` file that will help reproduce or understand the error here]

.gitignore

@@ -1,5 +1,4 @@
 Annotation/
-data/chr17_testdata/
 Preprocessing/
 References/
 Reports/

README.md

@@ -52,7 +52,7 @@ The worflow steps and tools used are as follows:
     * Variant annotation
         * [SnpEff](http://snpeff.sourceforge.net/)
         * [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html) (Variant Effect Predictor)
-5. **Reporting**
+5. **Reporting** - `runMultiQC.nf`
     * Reporting
         * [MultiQC](http://multiqc.info)
 

annotate.nf

@@ -77,16 +77,18 @@ vcfNotToAnnotate = Channel.create()
 
 if (annotateVCF == []) {
   Channel.empty().mix(
-    Channel.fromPath("${params.outDir}/VariantCalling/HaplotypeCaller/*.vcf.gz")
+    Channel.fromPath("${directoryMap.haplotypecaller}/*.vcf.gz")
       .flatten().map{vcf -> ['haplotypecaller',vcf]},
-    Channel.fromPath("${params.outDir}/VariantCalling/Manta/*SV.vcf.gz")
+    Channel.fromPath("${directoryMap.manta}/*SV.vcf.gz")
       .flatten().map{vcf -> ['manta',vcf]},
-    Channel.fromPath("${params.outDir}/VariantCalling/MuTect1/*.vcf.gz")
+    Channel.fromPath("${directoryMap.mutect1}/*.vcf.gz")
       .flatten().map{vcf -> ['mutect1',vcf]},
-    Channel.fromPath("${params.outDir}/VariantCalling/MuTect2/*.vcf.gz")
+    Channel.fromPath("${directoryMap.mutect2}/*.vcf.gz")
       .flatten().map{vcf -> ['mutect2',vcf]},
-    Channel.fromPath("${params.outDir}/VariantCalling/Strelka/*{somatic,variants}*.vcf.gz")
-      .flatten().map{vcf -> ['strelka',vcf]}
+    Channel.fromPath("${directoryMap.strelka}/*{somatic,variants}*.vcf.gz")
+      .flatten().map{vcf -> ['strelka',vcf]},
+    Channel.fromPath("${directoryMap.strelkabp}/*{somatic,variants}*.vcf.gz")
+      .flatten().map{vcf -> ['strelkabp',vcf]}
   ).choice(vcfToAnnotate, vcfNotToAnnotate) {
     annotateTools == [] || (annotateTools != [] && it[0] in annotateTools) ? 0 : 1
   }
@@ -197,7 +199,6 @@ process RunVEP {
   --format vcf \
   --offline \
   --per_gene \
-  --nearest symbol \
   --fork ${task.cpus} \
   --total_length \
   --vcf
@@ -222,16 +223,12 @@ def checkUppmaxProject() {
 
 def defineDirectoryMap() {
   return [
-    'bcftoolsStats'    : 'Reports/BCFToolsStats',
-    'snpeff'           : 'Annotation/SnpEff',
-    'vep'              : 'Annotation/VEP',
-    'merge'            : 'Annotation/merged'
-  ]
-}
-
-def defineStepList() {
-  return [
-    'annotate'
+    'haplotypecaller'  : "${params.outDir}/VariantCalling/HaplotypeCaller",
+    'manta'            : "${params.outDir}/VariantCalling/Manta",
+    'mutect1'          : "${params.outDir}/VariantCalling/MuTect1",
+    'mutect2'          : "${params.outDir}/VariantCalling/MuTect2",
+    'strelka'          : "${params.outDir}/VariantCalling/Strelka",
+    'strelkabp'        : "${params.outDir}/VariantCalling/StrelkaBP",
     'bcftoolsStats'    : "${params.outDir}/Reports/BCFToolsStats",
     'snpeff'           : "${params.outDir}/Annotation/SnpEff",
     'vep'              : "${params.outDir}/Annotation/VEP"
@@ -255,15 +252,7 @@ def helpMessage() {
   // Display help message
   this.sarekMessage()
   log.info "    Usage:"
-  log.info "       nextflow run SciLifeLab/Sarek --sample <file.tsv> [--step STEP] [--tools TOOL[,TOOL]] --genome <Genome>"
-  log.info "       nextflow run SciLifeLab/Sarek --sampleDir <Directory> [--step STEP] [--tools TOOL[,TOOL]] --genome <Genome>"
-  log.info "       nextflow run SciLifeLab/Sarek --test [--step STEP] [--tools TOOL[,TOOL]] --genome <Genome>"
-  log.info "    --step"
-  log.info "       Option to start workflow"
-  log.info "       Possible values are:"
-  log.info "         annotate (will annotate Variant Calling output."
-  log.info "         By default it will try to annotate all available vcfs."
-  log.info "         Use with --annotateTools or --annotateVCF to specify what to annotate"
+  log.info "       nextflow run annotate.nf --test [--step STEP] [--tools TOOL[,TOOL]] --genome <Genome>"
   log.info "    --noReports"
   log.info "       Disable QC tools and MultiQC to generate a HTML report"
   log.info "    --tools"

buildContainers.nf

@@ -203,12 +203,12 @@ def helpMessage() {
   // Display help message
   this.sarekMessage()
   log.info "    Usage:"
-  log.info "       nextflow run SciLifeLab/Sarek/buildContainers.nf [--docker] [--push]"
+  log.info "       nextflow run buildContainers.nf [--docker] [--push]"
   log.info "          [--containers <container1...>] [--singularity]"
   log.info "          [--containerPath <path>]"
   log.info "          [--tag <tag>] [--repository <repository>]"
   log.info "    Example:"
-  log.info "      nextflow run SciLifeLab/Sarek/buildContainers.nf --docker --containers sarek"
+  log.info "      nextflow run buildContainers.nf --docker --containers sarek"
   log.info "    --containers: Choose which containers to build"
   log.info "       Default: all"
   log.info "       Possible values:"

buildReferences.nf

@@ -297,14 +297,12 @@ def helpMessage() {
   log.info "    Usage:"
   log.info "       nextflow run buildReferences.nf --refDir <pathToRefDir> --genome <genome>"
   log.info "       nextflow run buildReferences.nf --download --genome smallGRCh37"
-  log.info "       nextflow run SciLifeLab/Sarek --test [--step STEP] [--tools TOOL[,TOOL]] --genome <Genome>"
   log.info "    --download"
   log.info "       Download reference files. (only with --genome smallGRCh37)"
   log.info "    --refDir <Directoy>"
   log.info "       Specify a directory containing reference files."
   log.info "    --outDir <Directoy>"
   log.info "       Specify an output directory"
-  log.info "       Default: \$PWD/References/"
   log.info "    --genome <Genome>"
   log.info "       Choose which genome to build references from"
   log.info "       Possible values are:"

configuration/base.config

@@ -42,6 +42,7 @@ params {
   sampleDir = '' // samples directory (for Germline only)
   singularity = false // Don't use singularity to build buildContainers.nf
   step = 'mapping' // Default step is mapping
+  strelkaBP = false // Don't use Manta's candidate indels as input to Strelka
   tag = 'latest' // Default tag is latest, to be overwritten by --tag <version>
   test = false // Not testing by default
   tools = '' // List of tools to use

configuration/containers.config

@@ -40,5 +40,6 @@ process {
   $RunSingleStrelka.container         = "${params.repository}/sarek:${params.tag}"
   $RunSnpeff.container = {params.genome == 'GRCh38' ? "${params.repository}/snpeffgrch38:${params.tag}" : "${params.repository}/snpeffgrch37:${params.tag}"}
   $RunStrelka.container               = "${params.repository}/sarek:${params.tag}"
+  $RunStrelkaBP.container             = "${params.repository}/sarek:${params.tag}"
   $RunVEP.container = {params.genome == 'GRCh38' ? "${params.repository}/vepgrch38:${params.tag}" : "${params.repository}/vepgrch37:${params.tag}"}
 }

configuration/singularity-path.config

@@ -46,5 +46,6 @@ process {
   $RunSingleStrelka.container         = "${params.containerPath}/sarek-${params.tag}.img"
   $RunSnpeff.container                = {params.genome == 'GRCh38' ? "${params.containerPath}/snpeffgrch38-${params.tag}.img" : "${params.containerPath}/snpeffgrch37-${params.tag}.img"}
   $RunStrelka.container               = "${params.containerPath}/sarek-${params.tag}.img"
+  $RunStrelkaBP.container             = "${params.containerPath}/sarek-${params.tag}.img"
   $RunVEP.container                   = {params.genome == 'GRCh38' ? "${params.containerPath}/vepgrch38-${params.tag}.img" : "${params.containerPath}/vepgrch37-${params.tag}.img"}
 }