Merge pull request #709 from SciLifeLab/dev

Release 2.2.2

Author: maxulysse

.travis.yml

@@ -12,19 +12,23 @@ env:
     - NXF_VER=0.32.0
   matrix:
     - TEST=SOMATIC
+    - TEST=GERMLINE
     - TEST=ANNOTATEVEP
     - TEST=ANNOTATESNPEFF
-    - TEST=GERMLINE
+
+before_install:
+# PRs to master are only ok if coming from dev branch
+  - '[ $TRAVIS_PULL_REQUEST = "false" ] || [ $TRAVIS_BRANCH != "master" ] || ([ $TRAVIS_PULL_REQUEST_SLUG = $TRAVIS_REPO_SLUG ] && [ $TRAVIS_PULL_REQUEST_BRANCH = "dev" ])'
+# Donwload containers
+  - "travis_retry ./scripts/containers.sh --profile docker --test $TEST"
 
 install:
   # Install Nextflow
   - curl -fsSL get.nextflow.io | bash
   - chmod +x nextflow
   - sudo mv nextflow /usr/local/bin/
-  # Donwload big containers for ANNOTATEVEP and ANNOTATESNPEF tests)
-  - "travis_retry ./scripts/containers.sh --profile docker --test $TEST"
 
-# Build references when needed
+# Build references if needed
 before_script: "./scripts/test.sh --profile docker --test $TEST --build"
 
 # Actual tests

CHANGELOG.md

@@ -5,6 +5,41 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [2.2.2] - 2018-12-19
+
+### `Added`
+
+-   [#671](https://github.com/SciLifeLab/Sarek/pull/671) - New `publishDirMode` param and docs
+-   [#673](https://github.com/SciLifeLab/Sarek/pull/673), [#675](https://github.com/SciLifeLab/Sarek/pull/675),  [#676](https://github.com/SciLifeLab/Sarek/pull/676) - Profiles for BinAC and CFC clusters in Tübingen
+-   [#679](https://github.com/SciLifeLab/Sarek/pull/679) - Add container for `CreateIntervalBeds`
+-   [#692](https://github.com/SciLifeLab/Sarek/pull/692), [#697](https://github.com/SciLifeLab/Sarek/pull/697) - Add AWS iGenomes possibilities (within `conf/igenomes.conf`)
+-   [#694](https://github.com/SciLifeLab/Sarek/pull/694) - Add monochrome and grey logos for light or dark background
+-   [#698](https://github.com/SciLifeLab/Sarek/pull/698) - Add btb profile for munin server
+-   [#702](https://github.com/SciLifeLab/Sarek/pull/702) - Add font-ttf-dejavu-sans-mono `2.37` and fontconfig `2.12.6` to container
+
+### `Changed`
+
+-   [#678](https://github.com/SciLifeLab/Sarek/pull/678) - Changing VEP to v92 and adjusting CPUs for VEP
+-   [#663](https://github.com/SciLifeLab/Sarek/pull/663) - Update `do_release.sh` script
+-   [#671](https://github.com/SciLifeLab/Sarek/pull/671) - publishDir modes are now params
+-   [#677](https://github.com/SciLifeLab/Sarek/pull/677), [#698](https://github.com/SciLifeLab/Sarek/pull/698), [#703](https://github.com/SciLifeLab/Sarek/pull/703) - Update docs
+-   [#679](https://github.com/SciLifeLab/Sarek/pull/679) - Update old awsbatch configuration
+-   [#682](https://github.com/SciLifeLab/Sarek/pull/682) - Specifications for memory and cpus for awsbatch
+-   [#693](https://github.com/SciLifeLab/Sarek/pull/693) - Qualimap bamQC is now ran after mapping and after recalibration for better QC
+-   [#700](https://github.com/SciLifeLab/Sarek/pull/700) - Update GATK to `4.0.9.0`
+-   [#702](https://github.com/SciLifeLab/Sarek/pull/702) - Update FastQC to `0.11.8`
+-   [#705](https://github.com/SciLifeLab/Sarek/pull/705) - Change `--TMP_DIR` by `--tmp-dir` for GATK `4.0.9.0` BaseRecalibrator
+-   [#706](https://github.com/SciLifeLab/Sarek/pull/706) - Update TravisCI testing
+
+### `Fixed`
+
+-   [#665](https://github.com/SciLifeLab/Sarek/pull/665) - Input bam file now has always the same name (whether it is from a single fastq pair or multiple) in the MarkDuplicates process, so metrics too
+-   [#672](https://github.com/SciLifeLab/Sarek/pull/672) - process `PullSingularityContainers` from `buildContainers.nf` now expect a file with the correct `.simg` extension for singularity images, and no longer the `.img` one.
+-   [#679](https://github.com/SciLifeLab/Sarek/pull/679) - Add publishDirMode for `germlineVC.nf`
+-   [#700](https://github.com/SciLifeLab/Sarek/pull/700) - Fix [#699](https://github.com/SciLifeLab/Sarek/issues/699) missing DP in the FORMAT column VCFs for MuTect2
+-   [#702](https://github.com/SciLifeLab/Sarek/pull/702) - Fix [#701](https://github.com/SciLifeLab/Sarek/issues/701)
+-   [#705](https://github.com/SciLifeLab/Sarek/pull/705) - Fix [#704](https://github.com/SciLifeLab/Sarek/issues/704)
+
 ## [2.2.1] - 2018-10-04
 
 ### `Changed`

Dockerfile

@@ -7,4 +7,4 @@ LABEL \
 
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/sarek-2.2.1/bin:$PATH
+ENV PATH /opt/conda/envs/sarek-2.2.2/bin:$PATH

Sarek-data

@@ -4,10 +4,10 @@ Bootstrap:docker
 %labels
     MAINTAINER Maxime Garcia <maxime.garcia@scilifelab.se>
     DESCRIPTION Singularity image containing all requirements for the Sarek pipeline
-    VERSION 2.1.0
+    VERSION 2.2.2
 
 %environment
-    PATH=/opt/conda/envs/sarek-2.2.1/bin:$PATH
+    PATH=/opt/conda/envs/sarek-2.2.2/bin:$PATH
     export PATH
 
 %files

Singularity

@@ -42,6 +42,13 @@ if (params.help) exit 0, helpMessage()
 if (!SarekUtils.isAllowedParams(params)) exit 1, "params unknown, see --help for more information"
 if (!checkUppmaxProject()) exit 1, "No UPPMAX project ID found! Use --project <UPPMAX Project ID>"
 
+// Check for awsbatch profile configuration
+// make sure queue is defined
+if (workflow.profile == 'awsbatch') {
+    if(!params.awsqueue) exit 1, "Provide the job queue for aws batch!"
+}
+
+
 tools = params.tools ? params.tools.split(',').collect{it.trim().toLowerCase()} : []
 annotateTools = params.annotateTools ? params.annotateTools.split(',').collect{it.trim().toLowerCase()} : []
 annotateVCF = params.annotateVCF ? params.annotateVCF.split(',').collect{it.trim()} : []
@@ -103,7 +110,7 @@ vcfForVep = vcfForVep.map {
 process RunBcftoolsStats {
   tag {vcf}
 
-  publishDir directoryMap.bcftoolsStats, mode: 'link'
+  publishDir directoryMap.bcftoolsStats, mode: params.publishDirMode
 
   input:
     set variantCaller, file(vcf) from vcfForBCFtools
@@ -124,7 +131,7 @@ if (params.verbose) bcfReport = bcfReport.view {
 process RunVcftools {
   tag {vcf}
 
-  publishDir directoryMap.vcftools, mode: 'link'
+  publishDir directoryMap.vcftools, mode: params.publishDirMode
 
   input:
     set variantCaller, file(vcf) from vcfForVCFtools
@@ -145,10 +152,10 @@ if (params.verbose) vcfReport = vcfReport.view {
 process RunSnpeff {
   tag {"${variantCaller} - ${vcf}"}
 
-  publishDir params.outDir, mode: 'link', saveAs: {
-    if (it == "${vcf.simpleName}_snpEff.csv") "${directoryMap.snpeffReports}/${it}"
+  publishDir params.outDir, mode: params.publishDirMode, saveAs: {
+    if (it == "${vcf.simpleName}_snpEff.csv") "${directoryMap.snpeffReports.minus(params.outDir+'/')}/${it}"
     else if (it == "${vcf.simpleName}_snpEff.ann.vcf") null
-    else "${directoryMap.snpeff}/${it}"
+    else "${directoryMap.snpeff.minus(params.outDir+'/')}/${it}"
   }
 
   input:
@@ -198,8 +205,8 @@ if('merge' in tools) {
 process RunVEP {
   tag {"${variantCaller} - ${vcf}"}
 
-  publishDir params.outDir, mode: 'link', saveAs: {
-    if (it == "${vcf.simpleName}_VEP.summary.html") "${directoryMap.vep}/${it}"
+  publishDir params.outDir, mode: params.publishDirMode, saveAs: {
+    if (it == "${vcf.simpleName}_VEP.summary.html") "${directoryMap.vep.minus(params.outDir+'/')}/${it}"
     else null
   }
 
@@ -215,13 +222,14 @@ process RunVEP {
   script:
   finalannotator = annotator == "snpeff" ? 'merge' : 'vep'
   genome = params.genome == 'smallGRCh37' ? 'GRCh37' : params.genome
+  cache_version = params.genome == 'GRCh38' || params.genome == 'iGRCh38' ? 92 : 91
   """
   /opt/vep/src/ensembl-vep/vep --dir /opt/vep/.vep/  \
   -i ${vcf} \
   -o ${vcf.simpleName}_VEP.ann.vcf \
   --assembly ${genome} \
   --cache \
-	--cache_version 91 \
+	--cache_version ${cache_version} \
   --database \
   --everything \
   --filter_common \
@@ -245,7 +253,7 @@ vcfToCompress = snpeffVCF.mix(vepVCF)
 process CompressVCF {
   tag {"${annotator} - ${vcf}"}
 
-  publishDir "${directoryMap."$finalannotator"}", mode: 'link'
+  publishDir "${directoryMap."$finalannotator"}", mode: params.publishDirMode
 
   input:
     set annotator, variantCaller, file(vcf) from vcfToCompress
@@ -268,14 +276,14 @@ if (params.verbose) vcfCompressedoutput = vcfCompressedoutput.view {
 }
 
 process GetVersionSnpeff {
-  publishDir directoryMap.version, mode: 'link'
+  publishDir directoryMap.version, mode: params.publishDirMode
   output: file("v_*.txt")
   when: 'snpeff' in tools || 'merge' in tools
   script: QC.getVersionSnpEFF()
 }
 
 process GetVersionVEP {
-  publishDir directoryMap.version, mode: 'link'
+  publishDir directoryMap.version, mode: params.publishDirMode
   output: file("v_*.txt")
   when: 'vep' in tools || 'merge' in tools
   script: QC.getVersionVEP()

annotate.nf

@@ -38,6 +38,12 @@ if (params.help) exit 0, helpMessage()
 if (!SarekUtils.isAllowedParams(params)) exit 1, "params unknown, see --help for more information"
 if (!checkUppmaxProject()) exit 1, "No UPPMAX project ID found! Use --project <UPPMAX Project ID>"
 
+// Check for awsbatch profile configuration
+// make sure queue is defined
+if (workflow.profile == 'awsbatch') {
+    if(!params.awsqueue) exit 1, "Provide the job queue for aws batch!"
+}
+
 // Define containers to handle (build/push or pull)
 containersList = defineContainersList()
 containers = params.containers.split(',').collect {it.trim()}
@@ -86,13 +92,13 @@ if (params.verbose) containersBuilt = containersBuilt.view {
 process PullSingularityContainers {
   tag {"${params.repository}/${container}:${params.tag}"}
 
-  publishDir "${params.containerPath}", mode: 'move'
+  publishDir "${params.containerPath}", mode: params.publishDirMode
 
   input:
     val container from singularityContainers
 
   output:
-    file("${container}-${params.tag}.img") into imagePulled
+    file("${container}-${params.tag}.simg") into imagePulled
 
   when: params.singularity
 

buildContainers.nf

@@ -40,6 +40,12 @@ if (params.help) exit 0, helpMessage()
 if (!SarekUtils.isAllowedParams(params)) exit 1, "params unknown, see --help for more information"
 if (!checkUppmaxProject()) exit 1, "No UPPMAX project ID found! Use --project <UPPMAX Project ID>"
 
+// Check for awsbatch profile configuration
+// make sure queue is defined
+if (workflow.profile == 'awsbatch') {
+    if(!params.awsqueue) exit 1, "Provide the job queue for aws batch!"
+}
+
 ch_referencesFiles = Channel.fromPath("${params.refDir}/*")
 
 /*
@@ -103,7 +109,7 @@ ch_notCompressedfiles
 process BuildBWAindexes {
   tag {f_reference}
 
-  publishDir params.outDir, mode: 'link'
+  publishDir params.outDir, mode: params.publishDirMode
 
   input:
     file(f_reference) from ch_fastaForBWA
@@ -125,7 +131,7 @@ if (params.verbose) bwaIndexes.flatten().view {
 process BuildReferenceIndex {
   tag {f_reference}
 
-  publishDir params.outDir, mode: 'link'
+  publishDir params.outDir, mode: params.publishDirMode
 
   input:
     file(f_reference) from ch_fastaReference
@@ -149,7 +155,7 @@ if (params.verbose) ch_referenceIndex.view {
 process BuildSAMToolsIndex {
   tag {f_reference}
 
-  publishDir params.outDir, mode: 'link'
+  publishDir params.outDir, mode: params.publishDirMode
 
   input:
     file(f_reference) from ch_fastaForSAMTools
@@ -170,7 +176,7 @@ if (params.verbose) ch_samtoolsIndex.view {
 process BuildVCFIndex {
   tag {f_reference}
 
-  publishDir params.outDir, mode: 'link'
+  publishDir params.outDir, mode: params.publishDirMode
 
   input:
     file(f_reference) from ch_vcfFile

buildReferences.nf

@@ -8,19 +8,55 @@
  */
 
 params {
-  genome_base = params.genome == 'GRCh37' ? "s3://caw-references/grch37" : params.genome == 'GRCh38' ? "s3://caw-references/grch38" : "s3://caw-references/smallgrch37"
+  genome_base = params.genome == 'GRCh37' ? "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh37" : params.genome == 'GRCh38' ? "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38" : "s3://sarek-references/small"
+  publishDirMode = 'copy'
+  singleCPUMem  = 7.GB // To make the uppmax slurm copy paste work.
+  localReportDir = 'Reports'
 }
 
-executor.name = 'awsbatch'
-executor.awscli = '/home/ec2-user/miniconda/bin/aws'
+executor {
+  name = 'awsbatch'
+  awscli = '/home/ec2-user/miniconda/bin/aws'
+}
+
+/* Rolling files are currently not supported on s3 */
+report.file = "${params.localReportDir}/Sarek_report.html"
+timeline.file = "${params.localReportDir}/Sarek_timeline.html"
+dag.file = "${params.localReportDir}/Sarek_DAG.svg"
+trace.file = "${params.localReportDir}/Sarek_trace.txt"
 
 process {
-  executor = 'awsbatch'
-  queue = 'caw-job-queue'
+  queue = params.awsqueue
 
   errorStrategy = {task.exitStatus == 143 ? 'retry' : 'terminate'}
   maxErrors = '-1'
-  maxRetries = 2
+  maxRetries = 4
   cpus = 2
-  memory = 7.GB
+  memory = 8.GB
+
+  withName:RunBcftoolsStats {
+    cpus = 1
+    memory = {params.singleCPUMem * 2} // Memory is doubled so that it won't run two on the same instance
+    // Use a tiny queue for this one, so storage doesn't run out
+    queue = params.awsqueue_tiny
+  }
+  withName:RunVcftools {
+    cpus = 1
+    memory = {params.singleCPUMem * 2} // Memory is doubled so that it won't run two on the same instance
+    // Use a tiny queue for this one, so storage doesn't run out
+    queue = params.awsqueue_tiny
+  }
+  withName:RunHaplotypecaller {
+    cpus = 1
+    // Increase memory quadratically
+    memory = {params.singleCPUMem * 2} // Memory is doubled so that it won't run two on the same instance
+    // Use a tiny queue for this one, so storage doesn't run out
+    queue = params.awsqueue_tiny
+  }
+  withName:RunGenotypeGVCFs {
+    cpus = 1
+    memory = {params.singleCPUMem * 2} // Memory is doubled so that it won't run two on the same instance
+    // Use a tiny queue for this one, so storage doesn't run out
+    queue = params.awsqueue_tiny
+  }
 }