Merge pull request #164 from MaxUlysse/Mutect2

Final polishing

.github/markdownlint.yml

@@ -1,8 +1,6 @@
 # Markdownlint configuration file
 default: true,
 line-length: false
-no-duplicate-header:
-    siblings_only: true
 no-inline-html: 
     allowed_elements:
         - a

.github/workflows/ci.yml

@@ -41,7 +41,7 @@ jobs:
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
         env:
-          # Only check Nextflow pipeline minimum version for other C
+          # Only check Nextflow pipeline minimum version
           NXF_VER: '19.10.0'
       - name: Pull docker image
         run: |
@@ -50,7 +50,7 @@ jobs:
           docker pull nfcore/sarek${{ matrix.tools }}:dev.${{ matrix.species }}
           docker tag nfcore/sarek${{ matrix.tools }}:dev.${{ matrix.species }} nfcore/sarek${{ matrix.tools }}:dev.${{ matrix.species }}
       - name: Run annotation test
-        run: nextflow run . -profile test_annotation,docker --verbose --tools ${{ matrix.tools }}
+        run: nextflow run . -profile test_annotation,docker --tools ${{ matrix.tools }}
 
   germline:
     env:
@@ -63,7 +63,7 @@ jobs:
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
         env:
-          # Only check Nextflow pipeline minimum version for other C
+          # Only check Nextflow pipeline minimum version
           NXF_VER: '19.10.0'
       - name: Pull docker image
         run: |
@@ -93,57 +93,57 @@ jobs:
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
         env:
-          # Only check Nextflow pipeline minimum version for other C
+          # Only check Nextflow pipeline minimum version
           NXF_VER: '19.10.0'
       - name: Pull docker image
         run: |
           docker pull nfcore/sarek:dev
           docker tag nfcore/sarek:dev nfcore/sarek:dev
       - name: Run test for minimal genomes
-        run: nextflow run . -profile test,docker --skipQC all --verbose --genome ${{ matrix.genome }} ${{ matrix.intervals }} --tools Manta,mpileup,Strelka,FreeBayes
+        run: nextflow run . -profile test,docker --skipQC all --genome ${{ matrix.genome }} ${{ matrix.intervals }} --tools Manta,mpileup,Strelka,FreeBayes
 
   profile:
     env:
       NXF_ANSI_LOG: false
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        profile: [test_splitfastq, test_targeted, test_trimming]
+        profile: [test_split_fastq, test_targeted, test_trimming, test_no_gatk_spark]
     steps:
       - uses: actions/checkout@v2
       - name: Install Nextflow
         run: |
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
         env:
-          # Only check Nextflow pipeline minimum version for other C
+          # Only check Nextflow pipeline minimum version
           NXF_VER: '19.10.0'
       - name: Pull docker image
         run: |
           docker pull nfcore/sarek:dev
           docker tag nfcore/sarek:dev nfcore/sarek:dev
       - name: Run ${{ matrix.profile }} test
-        run: nextflow run . -profile ${{ matrix.profile }},docker --verbose
+        run: nextflow run . -profile ${{ matrix.profile }},docker
 
   tools:
     env:
       NXF_ANSI_LOG: false
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        tool: [Haplotypecaller, Freebayes, Manta, mpileup, Strelka, TIDDIT, msisensor]
+        tool: [Haplotypecaller, Freebayes, Manta, mpileup, Strelka, TIDDIT, MSIsensor]
     steps:
       - uses: actions/checkout@v2
       - name: Install Nextflow
         run: |
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
         env:
-          # Only check Nextflow pipeline minimum version for other C
+          # Only check Nextflow pipeline minimum version
           NXF_VER: '19.10.0'
       - name: Pull docker image
         run: |
           docker pull nfcore/sarek:dev
           docker tag nfcore/sarek:dev nfcore/sarek:dev
       - name: Run ${{ matrix.tool }} test
-        run: nextflow run . -profile test_tool,docker --verbose --tools ${{ matrix.tool }}
+        run: nextflow run . -profile test_tool,docker --tools ${{ matrix.tool }}

README.md

@@ -4,8 +4,8 @@
 [![nf-core](https://img.shields.io/badge/nf--core-pipeline-brightgreen.svg)](https://nf-co.re/)
 [![DOI](https://zenodo.org/badge/184289291.svg)](https://zenodo.org/badge/latestdoi/184289291)
 
-[![GitHub Actions CI status](https://github.com/nf-core/sarek/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/sarek/actions?query=workflow%3A%22sarek+CI%22)
-[![GitHub Actions Linting status](https://github.com/nf-core/sarek/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/sarek/actions?query=workflow%3A%22sarek+linting%22)
+[![GitHub Actions CI status](https://github.com/nf-core/sarek/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/sarek/actions?query=workflow%3A%22nf-core+CI%22)
+[![GitHub Actions Linting status](https://github.com/nf-core/sarek/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/sarek/actions?query=workflow%3A%22nf-core+linting%22)
 [![CircleCi build status](https://img.shields.io/circleci/project/github/nf-core/sarek?logo=circleci)](https://circleci.com/gh/nf-core/sarek/)
 
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg)](http://bioconda.github.io/)
@@ -85,6 +85,7 @@ Helpful contributors:
 * [Adrian Lärkeryd](https://github.com/adrlar)
 * [Alexander Peltzer](https://github.com/apeltzer)
 * [Chela James](https://github.com/chelauk)
+* [David Mas-Ponte](https://github.com/davidmasp)
 * [Francesco L](https://github.com/nibscles)
 * [FriederikeHanssen](https://github.com/FriederikeHanssen)
 * [Gisela Gabernet](https://github.com/ggabernet)
@@ -105,7 +106,6 @@ Helpful contributors:
 * [gulfshores](https://github.com/gulfshores)
 * [pallolason](https://github.com/pallolason)
 * [silviamorins](https://github.com/silviamorins)
-* [David Mas-Ponte](https://github.com/davidmasp)
 
 ## Contributions & Support
 

conf/genomes.config

@@ -55,7 +55,7 @@ params {
     'smallGRCh37' {
       dbsnp                   = "${params.genomes_base}/dbsnp_138.b37.small.vcf.gz"
       fasta                   = "${params.genomes_base}/human_g1k_v37_decoy.small.fasta"
-      germline_resource       = "${params.genomes_base}/dbsnp_138.b37.small.vcf.gz"
+      germline_resource       = "${params.genomes_base}/gnomAD.r2.1.1.GRCh37.small.PASS.AC.AF.only.vcf.gz"
       intervals               = "${params.genomes_base}/small.intervals"
       known_indels            = "${params.genomes_base}/Mills_1000G_gold_standard_and_1000G_phase1.indels.b37.small.vcf.gz"
       snpeff_db               = 'GRCh37.87'

conf/test.config

@@ -17,12 +17,12 @@ params {
   max_time = 48.h
 
   // Input data
-  input = 'https://github.com/nf-core/test-datasets/raw/sarek/testdata/tsv/tiny-manta-https.tsv'
+  input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/tsv/tiny-manta-https.tsv'
 
   // Small reference genome
   igenomes_ignore = true
   genome = 'smallGRCh37'
-  genomes_base = "https://github.com/nf-core/test-datasets/raw/sarek/reference"
+  genomes_base = "https://raw.githubusercontent.com/nf-core/test-datasets/sarek/reference"
 }
 
 process {

conf/test_annotation.config

@@ -4,12 +4,12 @@
  * -------------------------------------------------
  * Defines bundled input files and everything required
  * to run a fast and simple test. Use as follows:
- *   nextflow run nf-core/sarek -profile test
+ *   nextflow run nf-core/sarek -profile test_annotation
  */
 
 includeConfig 'test.config'
 
 params {
   genome            = 'WBcel235'
-  input             = 'https://github.com/nf-core/test-datasets/raw/sarek/testdata/vcf/Strelka_1234N_variants.vcf.gz'
+  input             = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/vcf/Strelka_1234N_variants.vcf.gz'
 }

conf/test_no_gatk_spark.config

@@ -0,0 +1,14 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow config file for running tests
+ * -------------------------------------------------
+ * Defines bundled input files and everything required
+ * to run a fast and simple test. Use as follows:
+ *   nextflow run nf-core/sarek -profile test_no_gatk_spark
+ */
+
+includeConfig 'test.config'
+
+params {
+  no_gatk_spark = true
+}

conf/test_splitfastq.config → conf/test_split_fastq.config

@@ -4,11 +4,11 @@
  * -------------------------------------------------
  * Defines bundled input files and everything required
  * to run a fast and simple test. Use as follows:
- *   nextflow run nf-core/sarek -profile test
+ *   nextflow run nf-core/sarek -profile test_split_fastq
  */
 
 includeConfig 'test.config'
 
 params {
   split_fastq = 500
-}
+}

conf/test_targeted.config

@@ -10,6 +10,6 @@
 includeConfig 'test.config'
 
 params {
-  target_bed = 'https://github.com/nf-core/test-datasets/raw/sarek/testdata/target.bed'
+  target_bed = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/target.bed'
   tools = 'manta,strelka'
-}
+}

conf/test_tool.config

@@ -4,13 +4,13 @@
  * -------------------------------------------------
  * Defines bundled input files and everything required
  * to run a fast and simple test. Use as follows:
- *   nextflow run nf-core/sarek -profile test
+ *   nextflow run nf-core/sarek -profile test_tool
  */
 
 includeConfig 'test.config'
 
 params {
   // Input data
-  input = 'https://github.com/nf-core/test-datasets/raw/sarek/testdata/tsv/tiny-recal-pair-https.tsv'
+  input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/tsv/tiny-recal-pair-https.tsv'
   step = 'variantcalling'
 }

conf/test_trimming.config

@@ -4,7 +4,7 @@
  * -------------------------------------------------
  * Defines bundled input files and everything required
  * to run a fast and simple test. Use as follows:
- *   nextflow run nf-core/sarek -profile test
+ *   nextflow run nf-core/sarek -profile test_trimming
  */
 
 includeConfig 'test.config'

docs/containers.md

@@ -21,7 +21,7 @@ For annotation, the main container can be used, but the cache has to be download
 - Contain **[Control-FREEC](https://github.com/BoevaLab/FREEC)** 11.5
 - Contain **[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/)** 0.11.9
 - Contain **[FreeBayes](https://github.com/ekg/freebayes)** 1.3.2
-- Contain **[GATK4-spark](https://github.com/broadinstitute/gatk)** 4.1.4.1
+- Contain **[GATK4-spark](https://github.com/broadinstitute/gatk)** 4.1.6.0
 - Contain **[GeneSplicer](https://ccb.jhu.edu/software/genesplicer/)** 1.0
 - Contain **[ggplot2](https://github.com/tidyverse/ggplot2)** 3.3.0
 - Contain **[HTSlib](https://github.com/samtools/htslib)** 1.9

docs/usage.md

@@ -20,6 +20,7 @@
   - [--annotateVCF](#--annotatevcf)
   - [--no_gvcf](#--no_gvcf)
   - [--noGVCF](#--nogvcf)
+  - [--no_gatk_spark](#--no_gatk_spark)
   - [--skip_qc](#--skip_qc)
   - [--skipQC](#--skipqc)
   - [--noReports](#--noreports)
@@ -78,7 +79,7 @@
 - [Job resources](#job-resources)
   - [Automatic resubmission](#automatic-resubmission)
   - [Custom resource requests](#custom-resource-requests)
-- [AWS Batch specific parameters](#aws-batch-specific-parameters)
+- [AWSBatch specific parameters](#awsbatch-specific-parameters)
   - [--awsqueue](#--awsqueue)
   - [--awsregion](#--awsregion)
   - [--awscli](#--awscli)
@@ -289,6 +290,10 @@ Use this to disable g.vcf from `HaplotypeCaller`.
 > :warning: This params is deprecated -- it will be removed in a future release.
 > Please check: [`--no_gvcf`](#--no_gvcf)
 
+### --no_gatk_spark
+
+Use this to disable usage of GATK Spark implementation of their tools in local mode.
+
 ### --skip_qc
 
 Use this to disable specific QC and Reporting tools.
@@ -323,7 +328,7 @@ Available: `mapping`, `recalibrate`, `variantcalling` and `annotate`
 ### --tools
 
 Use this to specify the tools to run:
-Available: `ASCAT`, `ControlFREEC`, `FreeBayes`, `HaplotypeCaller`, `Manta`, `mpileup`, `Mutect2`, `Strelka`, `TIDDIT`
+Available: `ASCAT`, `ControlFREEC`, `FreeBayes`, `HaplotypeCaller`, `Manta`, `mpileup`, `MSIsensor`, `Mutect2`, `Strelka`, `TIDDIT`
 
 ### --sentieon
 
@@ -772,14 +777,14 @@ You can then create a pull request to the `nf-core/configs` repository with the
 
 If you have any questions or issues please send us a message on [Slack](https://nf-co.re/join/slack).
 
-## AWS Batch specific parameters
+## AWSBatch specific parameters
 
-Running the pipeline on AWS Batch requires a couple of specific parameters to be set according to your AWS Batch configuration.
+Running the pipeline on AWSBatch requires a couple of specific parameters to be set according to your AWSBatch configuration.
 Please use [`-profile awsbatch`](https://github.com/nf-core/configs/blob/master/conf/awsbatch.config) and then specify all of the following parameters.
 
 ### --awsqueue
 
-The JobQueue that you intend to use on AWS Batch.
+The JobQueue that you intend to use on AWSBatch.
 
 ### --awsregion
 
@@ -788,7 +793,8 @@ Default is set to `eu-west-1` but can be adjusted to your needs.
 
 ### --awscli
 
-The [AWS CLI](https://www.nextflow.io/docs/latest/awscloud.html#aws-cli-installation) path in your custom AMI. Default: `/home/ec2-user/miniconda/bin/aws`.
+The [AWS CLI](https://www.nextflow.io/docs/latest/awscloud.html#aws-cli-installation) path in your custom AMI.
+Default: `/home/ec2-user/miniconda/bin/aws`.
 
 Please make sure to also set the `-w/--work-dir` and `--outdir` parameters to a S3 storage bucket of your choice - you'll get an error message notifying you if you didn't.
 

environment.yml

@@ -17,7 +17,7 @@ dependencies:
   - bioconda::ensembl-vep=99.2
   - bioconda::fastqc=0.11.9
   - bioconda::freebayes=1.3.2
-  - bioconda::gatk4-spark=4.1.4.1
+  - bioconda::gatk4-spark=4.1.6.0
   - bioconda::genesplicer=1.0
   - bioconda::htslib=1.9
   - bioconda::manta=1.6.0