Merge pull request #13 from apeltzer/travis

Travis Tests for ExoSeq

Author: apeltzer

.travis.yml

@@ -0,0 +1,35 @@
+sudo: required
+language: java
+jdk: openjdk8
+services:
+  - docker
+python:
+  - "2.7"
+
+cache: pip
+
+matrix:
+  fast_finish: true
+
+install:
+  - "./scripts/install.sh --tool $TOOL_INSTALL"
+  # Install nf-core/tools
+  - git clone https://github.com/nf-core/tools.git /tmp/nf-core-tools
+  - cd /tmp/nf-core-tools
+  - pip install --user -e .
+  # Get Kit Files
+  - wget -O kits.tar.bz2 https://qbic-intranet.am10.uni-tuebingen.de/owncloud/index.php/s/Qvku3etEqb3PW58/download
+  # Get tiny Reference Files
+  # Reset
+  - cd ${TRAVIS_BUILD_DIR}/tests
+
+env:
+  global:
+    - NXF_VER=0.27.6 SGT_VER=2.4.2
+  matrix:
+    - PROFILE=docker TEST=TOOLS TOOL_INSTALL=ALL
+    - PROFILE=singularity TEST=TOOLS TOOL_INSTALL=ALL
+
+script:
+  - "nf-core lint ${TRAVIS_BUILD_DIR}"
+  - "./scripts/test.sh --profile $PROFILE --test $TEST"

CHANGELOG.md

@@ -1,2 +1,2 @@
-## [nf-core/ExoSeq v0.9dev]
+## [nf-core/ExoSeq v1.0dev]
 The release marks the point where the pipeline was moved from SciLifeLab/NGI-ExoSeq over to the new nf-core community, at nf-core/ExoSeq.

PairedSingleSampleWF.nf

@@ -43,22 +43,9 @@ Output:
 --outdir                       Path where the results to be saved [Default: './results']
 
 Kit files:
+--kitfiles                     Path to kitfiles defined in metafiles.config
+--metafiles                    Path to metafiles defined in metafiles.config
 --kit                          Kit used to prep samples [Default: 'agilent_v5']
---bait                         Absolute path to bait file
---target                       Absolute path to target file
---target_bed                   Absolute path to target bed file (snpEff compatible format)
-
-Genome/Variation files:
---dbsnp                        Absolute path to dbsnp file
---thousandg                    Absolute path to 1000G file
---mills                        Absolute path to Mills file
---omni                         Absolute path to Omni file
---gfasta                       Absolute path to genome fasta file
---bwa_index                    Absolute path to bwa genome index
-
-Other options:
---exome                        Exome data, if this is not set, run as genome data
---project                      Uppnex project to user for SLURM executor
 
 For more detailed information regarding the parameters and usage refer to package
 documentation at https://github.com/nf-core/ExoSeq
@@ -69,9 +56,7 @@ params.name = false
 params.help = false
 params.reads = false
 params.singleEnd = false
-params.genome = false
 params.run_id = false
-params.exome = false //default genome, set to true to run restricting to exome positions
 params.aligner = 'bwa' //Default, but stay tuned for later ;-) 
 params.saveReference = true
 
@@ -91,24 +76,14 @@ params.three_prime_clip_r2 = 0
 
 // Kit options
 params.kit = 'agilent_v5'
-params.bait = params.kitFiles[ params.kit ] ? params.kitFiles[ params.kit ].bait ?: false : false
-params.target = params.kitFiles[ params.kit ] ? params.kitFiles[ params.kit ].target ?: false : false
-params.target_bed = params.kitFiles[ params.kit ] ? params.kitFiles[ params.kit ].target_bed ?: false : false
-params.dbsnp = params.metaFiles[ params.genome ] ? params.metaFiles[ params.genome ].dbsnp ?: false : false
-params.thousandg = params.metaFiles[ params.genome ] ? params.metaFiles[ params.genome ].thousandg ?: false : false
-params.mills = params.metaFiles[ params.genome ] ? params.metaFiles[ params.genome ].mills ?: false : false
-params.omni = params.metaFiles[ params.genome ] ? params.metaFiles[ params.genome ].omni ?: false : false
-params.gfasta = params.metaFiles[ params.genome ] ? params.metaFiles[ params.genome ].gfasta ?: false : false
-params.bwa_index = params.metaFiles[ params.genome ] ? params.metaFiles[ params.genome ].bwa_index ?: false : false
 
 // Has the run name been specified by the user?
-//  this has the bonus effect of catching both -name and --name
+// this has the bonus effect of catching both -name and --name
 custom_runName = params.name
 if( !(workflow.runName ==~ /[a-z]+_[a-z]+/) ){
   custom_runName = workflow.runName
 }
 
-
 // Show help when needed
 if (params.help){
     log.info helpMessage
@@ -119,14 +94,12 @@ if (params.help){
 if (!params.reads || !params.genome){
     exit 1, "Parameters '--reads' and '--genome' are required to run the pipeline"
 }
-if (!params.kitFiles[ params.kit ] && ['bait', 'target'].count{ params[it] } != 2){
-    exit 1, "Kit '${params.kit}' is not available in pre-defined config, so " +
-            "provide all kit specific files with option '--bait' and '--target'"
+if (!params.kitfiles){
+    exit 1, "No Exome Capturing Kit specified!"
+}
+if (!params.metafiles){
+    exit 1, "No Exome Metafiles specified!"
 }
- if (!params.metaFiles[ params.genome ] && ['gfasta', 'bwa_index', 'dbsnp', 'thousandg', 'mills', 'omni'].count{ params[it] } != 6){
-     exit 1, "Genome '${params.genome}' is not available in pre-defined config, so you need to provide all genome specific " +
-             "files with options '--gfasta', '--bwa_index', '--dbsnp', '--thousandg', '--mills' and '--omni'"
- }
 
 // Create a channel for input files
 
@@ -137,7 +110,6 @@ Channel
 
 
 // Validate Input indices for BWA Mem and GATK
-
 if(params.aligner == 'bwa' ){
     bwaId = Channel
         .fromPath("${params.gfasta}.bwt")
@@ -150,8 +122,7 @@ def summary = [:]
 summary['Run Name']     = custom_runName ?: workflow.runName
 summary['Reads']        = params.reads
 summary['Data Type']    = params.singleEnd ? 'Single-End' : 'Paired-End'
-summary['Genome']       = params.genome
-summary['WES/WGS']      = params.exome ? 'WES' : 'WGS'
+summary['Genome Assembly']       = params.genome
 summary['Trim R1'] = params.clip_r1
 summary['Trim R2'] = params.clip_r2
 summary["Trim 3' R1"] = params.three_prime_clip_r1
@@ -178,7 +149,6 @@ summary['Config Profile'] = workflow.profile
 log.info summary.collect { k,v -> "${k.padRight(15)}: $v" }.join("\n")
 log.info "========================================="
 
-
 try {
     if( ! workflow.nextflow.version.matches(">= $params.nf_required_version") ){
         throw GroovyException('Nextflow version too old')

README.md

@@ -1,5 +1,5 @@
 # ![nf-core/ExoSeq](https://raw.githubusercontent.com/nf-core/Exoseq/master/docs/images/ExoSeq_logo.png)
-
+[![Build Status](https://travis-ci.org/nf-core/ExoSeq.svg?branch=master)](https://travis-ci.org/nf-core/ExoSeq)
 [![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A50.27.6-brightgreen.svg)](https://www.nextflow.io/)
 [![Gitter](https://img.shields.io/badge/gitter-%20join%20chat%20%E2%86%92-4fb99a.svg)](https://gitter.im/nf-core/exoseq)
 [![Docker Container available](https://img.shields.io/docker/automated/nfcore/exoseq.svg)](https://hub.docker.com/r/nfcore/exoseq/)

conf/metafiles.config

@@ -0,0 +1,18 @@
+
+genomes {
+        'GRCh37' {
+            gfasta = '${params.metafiles}/b37/human_g1k_v37.fasta'
+            bwa_index = '${params.metafiles}/b37/human_g1k_v37.fasta.bwt'
+            dbsnp = '${params.metafiles}/b37/dbsnp_138.b37.vcf'
+            mills = '${params.metafiles}/b37/Mills_and_1000G_gold_standard.indels.b37.vcf'
+            omni = '${params.metafiles}/b37/1000G_omni2.5.b37.vcf'
+            thousandg = '${params.metafiles}/b37/1000G_phase1.snps.high_confidence.b37.vcf'
+            kits {
+      			'agilent_v5' {
+         		    bait = '${params.kitfiles}/agilent_v5/S04380110_Regions.interval_list'
+                    target = '${params.kitfiles}/agilent_v5/S04380110_Covered.interval_list'
+                    target_bed = '${params.kitfiles}/agilent_v5/S04380110_Covered.bed'
+      			}
+   		    }
+        }
+    }

conf/test.config

@@ -0,0 +1,23 @@
+/*
+ * -------------------------------------------------
+ *  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/rnaseq -profile test
+ */
+
+params {
+  max_cpus = 2
+  max_memory = 6.GB
+  max_time = 48.h
+  // Input data
+  singleEnd = false
+  kitfiles = './kits'
+  readPaths = [
+    ['Testdata_R1', ['https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R1.tiny.fastq.gz']],
+    ['Testdata_R2', ['https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R2.tiny.fastq.gz']],
+    ]
+  // Genome references
+  fasta = 'https://github.com/nf-core/test-datasets/raw/exoseq/reference/human_g1k_v37_decoy.small.fasta'
+}

environment.yml

@@ -1,6 +1,6 @@
 # You can use this file to create a conda environment for this pipeline:
 #   conda env create -f environment.yml
-name: nfcore-exoseq-0.9dev
+name: nfcore-exoseq-1.0dev
 channels:
   - bioconda
   - conda-forge
@@ -11,7 +11,7 @@ dependencies:
   - bwa=0.7.17
   - fastqc=0.11.7
   - trim-galore=0.4.5
-  - samtools=1.8
-  - gatk4=4.0.3.0
+  - samtools=1.9
+  - gatk4=4.0.4.0
   - qualimap=2.2.2a
-  - multiqc=1.5
+  - multiqc=1.6

nextflow.config

@@ -11,9 +11,12 @@
 
 params {
 	outdir = './results'
-	version = '0.9dev'
-	nf_required_version = '0.27.6'
+	version = '1.0dev'
+	nf_required_version = '0.30.2'
 	container = 'nfcore/exoseq'
+  metafiles = './references'
+  kitfiles = './kitfiles'
+  tracedir = "${params.outdir}/pipeline_info"
 }
 
 
@@ -35,21 +38,34 @@ profiles {
     uppmax {
         includeConfig 'conf/uppmax.config'
     }
+    test {
+        includeConfig 'conf/base.config'
+        includeConfig 'conf/test.config'
+        includeConfig 'conf/metafiles.config'
+    }
 }
 
 // Capture exit codes from upstream processes when piping
-process.shell = ['/bin/bash','-euo', 'pipefail']
+process.shell = ['/bin/bash', '-euo', 'pipefail']
 
 timeline {
   enabled = true
-  file = "${params.outdir}/NGI-ExoSeq_timeline.html"
+  file = "${params.tracedir}/pipeline_info/nfcore-exoseq_timeline.html"
+}
+report {
+  enabled = true
+  file = "${params.tracedir}/pipeline_info/nfcore-exoseq_report.html"
 }
-
 trace {
   enabled = true
-  file = "${params.outdir}/NGI-ExoSeq_trace.txt"
+  file = "${params.tracedir}/pipeline_info/nfcore-exoseq_trace.txt"
+}
+dag {
+  enabled = true
+  file = "${params.tracedir}/pipeline_info/nfcore-exoseq_DAG.svg"
 }
 
+
 manifest {
     homePage = 'https://github.com/SciLifeLab/NGI-ExoSeq'
     description = 'Nextflow Exome Sequencing Best Practice analysis pipeline.'

scripts/install.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+#Credit to the Sarek devs at https://github.com/SciLifeLab/Sarek
+TOOL="all"
+
+while [[ $# -gt 0 ]]
+do
+  key="$1"
+  case $key in
+    -t|--tool)
+    TOOL="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    *) # unknown option
+    shift # past argument
+    ;;
+  esac
+done
+
+# Install Nextflow
+if [[ "$TOOL" = nextflow ]] || [[ "$TOOL" = all ]]
+then
+  cd $HOME
+  curl -fsSL get.nextflow.io | bash
+  chmod +x nextflow
+  sudo mv nextflow /usr/local/bin/
+fi
+
+# Install Singularity
+if [[ "$TOOL" = singularity ]] || [[ "$TOOL" = all ]]
+then
+  sudo apt-get install squashfs-tools
+  cd $HOME
+  wget https://github.com/singularityware/singularity/releases/download/$SGT_VER/singularity-$SGT_VER.tar.gz
+  tar xvf singularity-$SGT_VER.tar.gz
+  cd singularity-$SGT_VER
+  ./configure --prefix=/usr/local
+  make
+  sudo make install
+  cd ..
+  rm -rf singularity-$SGT_VER*
+fi