Merge branch 'master' into ivar-consensus

.github/filters.yml

@@ -34,6 +34,10 @@ bedtools_genomecov:
   - software/bedtools/genomecov/**
   - tests/software/bedtools/genomecov/**
 
+bedtools_getfasta:
+  - software/bedtools/getfasta/**
+  - tests/software/bedtools/getfasta/**
+
 bedtools_intersect:
   - software/bedtools/intersect/**
   - tests/software/bedtools/intersect/**
@@ -88,6 +92,10 @@ bwa_mem:
   - software/bwa/mem/**
   - tests/software/bwa/mem/**
 
+cat_fastq:
+  - software/cat/fastq/**
+  - tests/software/cat/fastq/**
+
 cutadapt:
   - software/cutadapt/**
   - tests/software/cutadapt/**

software/bandage/image/main.nf

@@ -11,7 +11,7 @@ process BANDAGE_IMAGE {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? 'bioconda::bandage=0.8.1' : null)
+    conda (params.enable_conda ? 'bioconda::bandage=0.8.1=hc9558a2_2' : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bandage:0.8.1--hc9558a2_2"
     } else {

software/bcftools/bgzip/main.nf

@@ -10,7 +10,7 @@ process BCFTOOLS_BGZIP {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bcftools=1.11" : null)
+    conda (params.enable_conda ? "bioconda::bcftools=1.11=h7c999a4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bcftools:1.11--h7c999a4_0"
     } else {

software/bcftools/consensus/main.nf

@@ -10,7 +10,7 @@ process BCFTOOLS_CONSENSUS {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bcftools=1.11" : null)
+    conda (params.enable_conda ? "bioconda::bcftools=1.11=h7c999a4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bcftools:1.11--h7c999a4_0"
     } else {

software/bcftools/filter/main.nf

@@ -10,7 +10,7 @@ process BCFTOOLS_FILTER {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bcftools=1.11" : null)
+    conda (params.enable_conda ? "bioconda::bcftools=1.11=h7c999a4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bcftools:1.11--h7c999a4_0"
     } else {

software/bcftools/isec/main.nf

@@ -10,7 +10,7 @@ process BCFTOOLS_ISEC {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bcftools=1.11" : null)
+    conda (params.enable_conda ? "bioconda::bcftools=1.11=h7c999a4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bcftools:1.11--h7c999a4_0"
     } else {

software/bcftools/stats/main.nf

@@ -10,7 +10,7 @@ process BCFTOOLS_STATS {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bcftools=1.11" : null)
+    conda (params.enable_conda ? "bioconda::bcftools=1.11=h7c999a4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bcftools:1.11--h7c999a4_0"
     } else {
@@ -21,8 +21,8 @@ process BCFTOOLS_STATS {
     tuple val(meta), path(vcf)
 
     output:
-    tuple val(meta), path("*.txt"), emit: stats
-    path  "*.version.txt"         , emit: version
+    tuple val(meta), path("*stats.txt"), emit: stats
+    path  "*.version.txt"              , emit: version
 
     script:
     def software = getSoftwareName(task.process)

software/bcftools/stats/meta.yml

@@ -52,7 +52,7 @@ output:
     - stats:
         type: file
         description: Text output file containing stats
-        pattern: "*.{txt}"
+        pattern: "*_{stats.txt}"
     - version:
         type: file
         description: File containing software version

software/bcftools/tabix/main.nf

@@ -10,7 +10,7 @@ process BCFTOOLS_TABIX {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bcftools=1.11" : null)
+    conda (params.enable_conda ? "bioconda::bcftools=1.11=h7c999a4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bcftools:1.11--h7c999a4_0"
     } else {

software/bedtools/getfasta/functions.nf

@@ -0,0 +1,59 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/bedtools/getfasta/main.nf

@@ -0,0 +1,42 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process BEDTOOLS_GETFASTA {
+    tag "$bed"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
+
+    conda (params.enable_conda ? "bioconda::bedtools=2.30.0=hc088bd4_0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bedtools:2.30.0--hc088bd4_0"
+    } else {
+        container "quay.io/biocontainers/bedtools:2.30.0--hc088bd4_0"
+    }
+
+    input:
+    path bed
+    path fasta
+
+    output:
+    path "*.fa"         , emit: fasta
+    path "*.version.txt", emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${bed.baseName}${options.suffix}" : "${bed.baseName}"
+    """
+    bedtools \\
+        getfasta \\
+        $options.args \\
+        -fi $fasta \\
+        -bed $bed \\
+        -fo ${prefix}.fa
+
+    bedtools --version | sed -e "s/bedtools v//g" > ${software}.version.txt
+    """
+}

software/bedtools/getfasta/meta.yml

@@ -0,0 +1,54 @@
+name: bedtools_getfasta
+description: extract sequences in a FASTA file based on intervals defined in a feature file.
+keywords:
+    - bed
+    - fasta
+    - getfasta
+tools:
+    - bedtools:
+        description: |
+            A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+        documentation: https://bedtools.readthedocs.io/en/latest/content/tools/intersect.html
+params:
+    - outdir:
+          type: string
+          description: |
+              The pipeline's output directory. By default, the module will
+              output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+          type: string
+          description: |
+              Value for the Nextflow `publishDir` mode parameter.
+              Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - enable_conda:
+          type: boolean
+          description: |
+              Run the module with Conda using the software specified
+              via the `conda` directive
+    - singularity_pull_docker_container:
+          type: boolean
+          description: |
+              Instead of directly downloading Singularity images for use with Singularity,
+              force the workflow to pull and convert Docker containers instead.
+input:
+    - bed:
+        type: file
+        description: Bed feature file
+        pattern: "*.{bed}"
+    - fasta:
+        type: file
+        description: Input fasta file
+        pattern: "*.{fa,fasta}"
+
+output:
+    - fasta:
+        type: file
+        description: Output fasta file with extracted sequences
+        pattern: "*.{fa}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
+authors:
+    - "@joseespinosa"
+    - "@drpatelh"

software/bedtools/maskfasta/main.nf

@@ -11,7 +11,7 @@ process BEDTOOLS_MASKFASTA {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? "bioconda::bedtools=2.30.0" : null)
+    conda (params.enable_conda ? "bioconda::bedtools=2.30.0=hc088bd4_0" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://depot.galaxyproject.org/singularity/bedtools:2.30.0--hc088bd4_0"
     } else {

software/blast/blastn/main.nf

@@ -11,7 +11,7 @@ process BLAST_BLASTN {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? 'bioconda::blast=2.10.1' : null)
+    conda (params.enable_conda ? 'bioconda::blast=2.10.1=pl526he19e7b1_3' : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container 'https://depot.galaxyproject.org/singularity/blast:2.10.1--pl526he19e7b1_3'
     } else {

software/blast/makeblastdb/main.nf

@@ -11,7 +11,7 @@ process BLAST_MAKEBLASTDB {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
 
-    conda (params.enable_conda ? 'bioconda::blast=2.10.1' : null)
+    conda (params.enable_conda ? 'bioconda::blast=2.10.1=pl526he19e7b1_3' : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container 'https://depot.galaxyproject.org/singularity/blast:2.10.1--pl526he19e7b1_3'
     } else {

software/bwa/index/main.nf

@@ -22,13 +22,14 @@ process BWA_INDEX {
     path fasta
 
     output:
-    path "${fasta}.*"   , emit: index
+    path "bwa"          , emit: index
     path "*.version.txt", emit: version
 
     script:
     def software = getSoftwareName(task.process)
     """
-    bwa index $options.args $fasta
+    mkdir bwa
+    bwa index $options.args $fasta -p bwa/${fasta.baseName}
     echo \$(bwa 2>&1) | sed 's/^.*Version: //; s/Contact:.*\$//' > ${software}.version.txt
     """
 }

software/bwa/mem/main.nf

@@ -21,7 +21,6 @@ process BWA_MEM {
     input:
     tuple val(meta), path(reads)
     path  index
-    path  fasta
 
     output:
     tuple val(meta), path("*.bam"), emit: bam
@@ -32,13 +31,15 @@ process BWA_MEM {
     def prefix     = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
     def read_group = meta.read_group ? "-R ${meta.read_group}" : ""
     """
+    INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'`
+
     bwa mem \\
         $options.args \\
         $read_group \\
         -t $task.cpus \\
-        $fasta \\
+        \$INDEX \\
         $reads \\
-        | samtools view $options.args2 -@ $task.cpus -bS -o ${prefix}.bam -
+        | samtools view $options.args2 -@ $task.cpus -bhS -o ${prefix}.bam -
 
     echo \$(bwa 2>&1) | sed 's/^.*Version: //; s/Contact:.*\$//' > ${software}.version.txt
     """

software/bwa/mem/meta.yml

@@ -51,10 +51,7 @@ input:
     - index:
         type: file
         description: BWA genome index files
-        pattern: "*.{amb,ann,bwt,pac,sa}"
-    - fasta:
-        type: file
-        description: Input genome fasta file
+        pattern: "Directory containing BWA index *.{amb,ann,bwt,pac,sa}"
 output:
     - bam:
         type: file

software/cat/fastq/functions.nf

@@ -0,0 +1,59 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/cat/fastq/main.nf

@@ -0,0 +1,46 @@
+// Import generic module functions
+include { initOptions; saveFiles } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process CAT_FASTQ {
+    tag "$meta.id"
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'merged_fastq', publish_id:meta.id) }
+
+    conda (params.enable_conda ? "conda-forge::sed=4.7=h1bed415_1000" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img"
+    } else {
+        container "biocontainers/biocontainers:v1.2.0_cv1"
+    }
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.merged.fastq.gz"), emit: reads
+
+    script:
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def readList = reads.collect{ it.toString() }
+    if (meta.single_end) {
+        if (readList.size > 1) {
+            """
+            cat ${readList.sort().join(' ')} > ${prefix}.merged.fastq.gz
+            """
+        }
+    } else {
+        if (readList.size > 2) {
+            def read1 = []
+            def read2 = []
+            readList.eachWithIndex{ v, ix -> ( ix & 1 ? read2 : read1 ) << v }
+            """
+            cat ${read1.sort().join(' ')} > ${prefix}_1.merged.fastq.gz
+            cat ${read2.sort().join(' ')} > ${prefix}_2.merged.fastq.gz
+            """
+        }
+    }
+}

software/cat/fastq/meta.yml

@@ -0,0 +1,55 @@
+name: cat_fastq
+description: Concatenates fastq files
+keywords:
+    - fastq
+    - concatenate
+tools:
+    - cat:
+        description: |
+            The cat utility reads files sequentially, writing them to the standard output.
+        documentation: https://www.gnu.org/software/coreutils/manual/html_node/cat-invocation.html
+params:
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - enable_conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+    - singularity_pull_docker_container:
+        type: boolean
+        description: |
+            Instead of directly downloading Singularity images for use with Singularity,
+            force the workflow to pull and convert Docker containers instead.
+input:
+    input:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: list
+        description: |
+            List of input FastQ files to be concatenated.
+output:
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+    - reads:
+        type: file
+        description: Merged fastq file
+        pattern: "*.{merged.fastq.gz}"
+authors:
+    - "@joseespinosa"
+    - "@drpatelh"

software/gunzip/main.nf

@@ -10,7 +10,7 @@ process GUNZIP {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
 
-    conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
+    conda (params.enable_conda ? "conda-forge::sed=4.7=h1bed415_1000" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img"
     } else {

software/pangolin/main.nf

@@ -11,19 +11,19 @@ process PANGOLIN {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
 
-    conda (params.enable_conda ? 'bioconda::pangolin=2.1.7=py_0' : null)
+    conda (params.enable_conda ? 'bioconda::pangolin=2.2.1=py_0 bioconda::pangolearn=2021.02.05=pyh3252c3a_0' : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container 'https://depot.galaxyproject.org/singularity/pangolin:2.1.7--py_0'
+        container 'https://depot.galaxyproject.org/singularity/pangolin:2.2.1--py_0'
     } else {
-        container 'quay.io/biocontainers/pangolin:2.1.7--py_0'
+        container 'quay.io/biocontainers/pangolin:2.2.1--py_0'
     }
 
     input:
     tuple val(meta), path(fasta)
 
     output:
-    tuple val(meta), path('*.lineage_report.csv'), emit: report
-    path  '*.version.txt'                        , emit: version
+    tuple val(meta), path('*.csv'), emit: report
+    path  '*.version.txt'         , emit: version
 
     script:
     def software = getSoftwareName(task.process)
@@ -31,7 +31,7 @@ process PANGOLIN {
     """
     pangolin \\
         $fasta\\
-        --outfile ${prefix}.lineage_report.csv \\
+        --outfile ${prefix}.pangolin.csv \\
         $options.args
 
     pangolin --version | sed "s/pangolin //g" > ${software}.version.txt

software/pangolin/meta.yml

@@ -1,57 +1,54 @@
 name: pangolin
 description: Phylogenetic Assignment of Named Global Outbreak LINeages
 keywords:
-  - covid
-  - pangolin
-  - lineage
+    - covid
+    - pangolin
+    - lineage
 tools:
-  - star:
-      description: |
-        Phylogenetic Assignment of Named Global Outbreak LINeages
-      homepage: https://github.com/cov-lineages/pangolin#pangolearn-description
-      manual: https://github.com/cov-lineages/pangolin#pangolearn-description
+    - star:
+        description: |
+            Phylogenetic Assignment of Named Global Outbreak LINeages
+        homepage: https://github.com/cov-lineages/pangolin#pangolearn-description
+        manual: https://github.com/cov-lineages/pangolin#pangolearn-description
 params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - enable_conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
-  - singularity_pull_docker_container:
-      type: boolean
-      description: |
-        Instead of directly downloading Singularity images for use with Singularity,
-        force the workflow to pull and convert Docker containers instead.
-
+    - outdir:
+        type: string
+        description: |
+            The pipeline's output directory. By default, the module will
+            output files into `$params.outdir/<SOFTWARE>`
+    - publish_dir_mode:
+        type: string
+        description: |
+            Value for the Nextflow `publishDir` mode parameter.
+            Available: symlink, rellink, link, copy, copyNoFollow, move.
+    - enable_conda:
+        type: boolean
+        description: |
+            Run the module with Conda using the software specified
+            via the `conda` directive
+    - singularity_pull_docker_container:
+        type: boolean
+        description: |
+            Instead of directly downloading Singularity images for use with Singularity,
+            force the workflow to pull and convert Docker containers instead.
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-  - fasta:
-      type: file
-      description: |
-        The genome assembly to be evaluated
-
+    - meta:
+        type: map
+        description: |
+            Groovy Map containing sample information
+    - fasta:
+        type: file
+        description: |
+            The genome assembly to be evaluated
 output:
-  - report:
-      type: file
-      description: The lineage report
-      pattern: "{prefix}.lineage_report.csv"
-
-  - version:
-      type: file
-      description: File containing software version
-      pattern: "*.{version.txt}"
-
+    - report:
+        type: file
+        description: Pangolin lineage report
+        pattern: "*.{csv}"
+    - version:
+        type: file
+        description: File containing software version
+        pattern: "*.{version.txt}"
 authors:
-  - "@kevinmenden"
+    - "@kevinmenden"
+    - "@drpatelh"

software/stringtie/main.nf

@@ -25,7 +25,7 @@ process STRINGTIE {
     output:
     tuple val(meta), path("*.coverage.gtf")   , emit: coverage_gtf
     tuple val(meta), path("*.transcripts.gtf"), emit: transcript_gtf
-    tuple val(meta), path("*.txt")            , emit: abundance
+    tuple val(meta), path("*.abundance.txt")  , emit: abundance
     tuple val(meta), path("*.ballgown")       , emit: ballgown
     path  "*.version.txt"                     , emit: version
 
@@ -45,7 +45,7 @@ process STRINGTIE {
         $strandedness \\
         -G $gtf \\
         -o ${prefix}.transcripts.gtf \\
-        -A ${prefix}.gene_abundance.txt \\
+        -A ${prefix}.gene.abundance.txt \\
         -C ${prefix}.coverage.gtf \\
         -b ${prefix}.ballgown \\
         $options.args

software/untar/main.nf

@@ -10,7 +10,7 @@ process UNTAR {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
 
-    conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
+    conda (params.enable_conda ? "conda-forge::sed=4.7=h1bed415_1000" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
         container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img"
     } else {

tests/software/bedtools/getfasta/main.nf

@@ -0,0 +1,12 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_GETFASTA } from '../../../../software/bedtools/getfasta/main.nf' addParams( options: [:] )
+
+workflow test_bedtools_getfasta {
+    def bed   = [ file("${launchDir}/tests/data/bed/C.bed", checkIfExists: true) ]
+    def fasta = [ file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true) ]
+
+    BEDTOOLS_GETFASTA ( bed, fasta )
+}

tests/software/bedtools/getfasta/test.yml

@@ -0,0 +1,8 @@
+- name: bedtools getfasta
+  command: nextflow run ./tests/software/bedtools/getfasta -entry test_bedtools_getfasta -c tests/config/nextflow.config
+  tags:
+    - bedtools
+    - bedtools_getfasta
+  files:
+    - path: output/bedtools/C.fa
+      md5sum: 2257190c8d9fc6f177a518440cf1f3f3

tests/software/bedtools/maskfasta/main.nf

@@ -5,10 +5,9 @@ nextflow.enable.dsl = 2
 include { BEDTOOLS_MASKFASTA } from '../../../../software/bedtools/maskfasta/main.nf' addParams( options: [:] )
 
 workflow test_bedtools_maskfasta {
-    def input,fasta = []
-    bed = [ [ id:'test'],
-              file("${launchDir}/tests/data/bed/C.bed", checkIfExists: true) ]
-    fasta =  [ file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true) ]
+    def bed  =  [ [ id:'test'],
+                  file("${launchDir}/tests/data/bed/C.bed", checkIfExists: true) ]
+    def fasta = [ file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true) ]
 
     BEDTOOLS_MASKFASTA( bed, fasta )
 }

tests/software/bwa/index/test.yml

@@ -4,11 +4,11 @@
     - bwa
     - bwa_index
   files:
-    - path: output/bwa/NC_010473.fa.amb
+    - path: output/bwa/bwa/NC_010473.amb
       md5sum: 942a990ae872f1c0b8d72dda2db405d5
-    - path: output/bwa/NC_010473.fa.bwt
+    - path: output/bwa/bwa/NC_010473.bwt
       md5sum: 7301b52e2ecb893d429a49fa692447ae
-    - path: output/bwa/NC_010473.fa.pac
+    - path: output/bwa/bwa/NC_010473.pac
       md5sum: 4d5e6fc45bbc968f7f859e9ca2cc89ad
-    - path: output/bwa/NC_010473.fa.sa
-      md5sum: a47dcc92e750e2f16fbd979b8ff9538e
+    - path: output/bwa/bwa/NC_010473.sa
+      md5sum: a47dcc92e750e2f16fbd979b8ff9538e

tests/software/bwa/mem/main.nf

@@ -15,8 +15,7 @@ workflow test_bwa_mem_single_end {
 
     BWA_MEM (
         input,
-        file("${launchDir}/tests/data/index/E_coli/bwa/NC_010473.fa.{amb,ann,bwt,pac,sa}", checkIfExists: true),
-        file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true)
+        file("${launchDir}/tests/data/index/E_coli/bwa/", checkIfExists: true)
     )
 }
 
@@ -32,7 +31,6 @@ workflow test_bwa_mem_paired_end {
 
     BWA_MEM (
         input,
-        file("${launchDir}/tests/data/index/E_coli/bwa/NC_010473.fa.{amb,ann,bwt,pac,sa}", checkIfExists: true),
-        file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true)
+        file("${launchDir}/tests/data/index/E_coli/bwa/", checkIfExists: true)
     )
 }

tests/software/bwa/mem/test.yml

@@ -6,7 +6,7 @@
     - bwa_mem_single_end
   files:
     - path: output/bwa/test.bam
-      md5sum: 3ee21210bac387e0335008146e4728bc
+      md5sum: 52e81e5bd523d0b27fe533b21a0d80f5
 
 - name: bwa mem paired-end
   command: nextflow run ./tests/software/bwa/mem -entry test_bwa_mem_paired_end -c tests/config/nextflow.config
@@ -16,4 +16,4 @@
     - bwa_mem_paired_end
   files:
     - path: output/bwa/test.bam
-      md5sum: 510d8acc6448c07cdacce8e64ec0904c
+      md5sum: 86d82fdb68ed384c656cfc62a253052f

tests/software/cat/fastq/main.nf

@@ -0,0 +1,27 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_FASTQ } from '../../../../software/cat/fastq/main.nf' addParams( options: [:] )
+
+workflow test_cat_fastq_single_end {
+
+    def input = []
+    input = [ [ id:'test', single_end:true ], // meta map
+                [ file("${launchDir}/tests/data/fastq/rna/test_R1_val_1.fq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true) ]]
+
+    CAT_FASTQ ( input )
+}
+
+workflow test_cat_fastq_paired_end {
+
+    def input = []
+    input = [ [ id:'test', single_end:false ], // meta map
+                [ file("${launchDir}/tests/data/fastq/rna/test_R1_val_1.fq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R2_val_2.fq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
+                  file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true) ]]
+
+    CAT_FASTQ ( input )
+}

tests/software/cat/fastq/test.yml

@@ -0,0 +1,21 @@
+- name: cat fastq single-end
+  command: nextflow run ./tests/software/cat/fastq -entry test_cat_fastq_single_end -c tests/config/nextflow.config
+  tags:
+    - cat
+    - cat_fastq
+    - cat_fastqc_single_end
+  files:
+    - path: output/merged_fastq/test.merged.fastq.gz
+      md5sum: 7f753b793e5b0872758b1574db84d767
+
+- name: cat fastq fastqc_paired_end
+  command: nextflow run ./tests/software/cat/fastq -entry test_cat_fastq_paired_end -c tests/config/nextflow.config
+  tags:
+    - cat
+    - cat_fastq
+    - cat_fastqc_paired_end
+  files:
+    - path: output/merged_fastq/test_1.merged.fastq.gz
+      md5sum: 7f753b793e5b0872758b1574db84d767
+    - path: output/merged_fastq/test_2.merged.fastq.gz
+      md5sum: c71ff917e002b1e852916a021d52921d

tests/software/pangolin/main.nf

@@ -2,11 +2,11 @@
 
 nextflow.enable.dsl = 2
 
-include { PANGOLIN } from '../../../software/pangolin/main.nf' addParams(options: [:])
+include { PANGOLIN } from '../../../software/pangolin/main.nf' addParams( options: [:] )
 
 workflow test_pangolin {
     input = [ [ id:'test' ], // meta map
               [ file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.fna", checkIfExists: true) ] ]
 
-    PANGOLIN( input )
+    PANGOLIN ( input )
 }

tests/software/pangolin/test.yml

@@ -3,5 +3,5 @@
   tags:
     - pangolin
   files:
-    - path: ./output/pangolin/test.lineage_report.csv
-      md5sum: a7423586a536a58f14fb4553f92b225e
+    - path: ./output/pangolin/test.pangolin.csv
+      md5sum: 097669de1843e27f4529d6db8bbed97b