Merge branch 'nf-core:master' into antismashlite

modules/cat/fastq/main.nf

@@ -4,8 +4,8 @@ process CAT_FASTQ {
 
     conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' :
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'biocontainers/biocontainers:v1.2.0_cv1' }"
+        'ubuntu:20.04' }"
 
     input:
     tuple val(meta), path(reads, stageAs: "input*/*")

modules/elprep/filter/main.nf

@@ -0,0 +1,89 @@
+process ELPREP_FILTER {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0':
+        'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }"
+
+    input:
+    tuple val(meta), path(bam)
+    val(run_haplotypecaller)
+    val(run_bqsr)
+    path(reference_sequences)
+    path(filter_regions_bed)
+    path(reference_elfasta)
+    path(known_sites_elsites)
+    path(target_regions_bed)
+    path(intermediate_bqsr_tables)
+    val(bqsr_tables_only)
+    val(get_activity_profile)
+    val(get_assembly_regions)
+
+
+    output:
+    tuple val(meta), path("output/**.{bam,sam}")    ,emit: bam
+    tuple val(meta), path("*.metrics.txt")          ,optional: true, emit: metrics
+    tuple val(meta), path("*.recall")               ,optional: true, emit: recall
+    tuple val(meta), path("*.vcf.gz")               ,optional: true, emit: gvcf
+    tuple val(meta), path("*.table")                ,optional: true, emit: table
+    tuple val(meta), path("*.activity_profile.igv") ,optional: true, emit: activity_profile
+    tuple val(meta), path("*.assembly_regions.igv") ,optional: true, emit: assembly_regions
+    path "versions.yml"                             ,emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def suffix = args.contains("--output-type sam") ? "sam" : "bam"
+
+    // filter args
+    def reference_sequences_cmd = reference_sequences ? " --replace-reference-sequences ${reference_sequences}" : ""
+    def filter_regions_cmd      = filter_regions_bed  ? " --filter-non-overlapping-reads ${filter_regions_bed}" : ""
+
+    // markdup args
+    def markdup_cmd = args.contains("--mark-duplicates") ? " --mark-optical-duplicates ${prefix}.metrics.txt": ""
+
+    // variant calling args
+    def haplotyper_cmd = run_haplotypecaller ? " --haplotypecaller ${prefix}.g.vcf.gz": ""
+
+    def fasta_cmd           = reference_elfasta   ? " --reference ${reference_elfasta}": ""
+    def known_sites_cmd     = known_sites_elsites ? " --known-sites ${known_sites_elsites}": ""
+    def target_regions_cmd  = target_regions_bed  ? " --target-regions ${target_regions_bed}": ""
+
+    // bqsr args
+    def bqsr_cmd = run_bqsr ? " --bqsr ${prefix}.recall": ""
+    def bqsr_tables_only_cmd = bqsr_tables_only ? " --bqsr-tables-only ${prefix}.table": ""
+
+    def intermediate_bqsr_cmd = intermediate_bqsr_tables ? " --bqsr-apply .": ""
+
+    // misc
+    def activity_profile_cmd = get_activity_profile ? " --activity-profile ${prefix}.activity_profile.igv": ""
+    def assembly_regions_cmd = get_assembly_regions ? " --assembly-regions ${prefix}.assembly_regions.igv": ""
+
+    """
+    elprep filter ${bam} output/${prefix}.${suffix} \\
+        ${reference_sequences_cmd} \\
+        ${filter_regions_cmd} \\
+        ${markdup_cmd} \\
+        ${haplotyper_cmd} \\
+        ${fasta_cmd} \\
+        ${known_sites_cmd} \\
+        ${target_regions_cmd} \\
+        ${bqsr_cmd} \\
+        ${bqsr_tables_only_cmd} \\
+        ${intermediate_bqsr_cmd} \\
+        ${activity_profile_cmd} \\
+        ${assembly_regions_cmd} \\
+        --nr-of-threads ${task.cpus} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//')
+    END_VERSIONS
+    """
+}

modules/elprep/filter/meta.yml

@@ -0,0 +1,106 @@
+name: "elprep_filter"
+description: "Filter, sort and markdup sam/bam files, with optional BQSR and variant calling."
+keywords:
+  - sort
+  - bam
+  - sam
+  - filter
+  - variant calling
+tools:
+  - "elprep":
+      description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4."
+      homepage: "https://github.com/ExaScience/elprep"
+      documentation: "https://github.com/ExaScience/elprep"
+      tool_dev_url: "https://github.com/ExaScience/elprep"
+      doi: "10.1371/journal.pone.0244471"
+      licence: "['AGPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Input SAM/BAM file
+      pattern: "*.{bam,sam}"
+  - run_haplotypecaller:
+      type: boolean
+      description: Run variant calling on the input files. Needed to generate gvcf output.
+  - run_bqsr:
+      type: boolean
+      description: Run BQSR on the input files. Needed to generate recall metrics.
+  - reference_sequences:
+      type: file
+      description: Optional SAM header to replace existing header.
+      pattern: "*.sam"
+  - filter_regions_bed:
+      type: file
+      description: Optional BED file containing regions to filter.
+      pattern: "*.bed"
+  - reference_elfasta:
+      type: file
+      description: Elfasta file, required for BQSR and variant calling.
+      pattern: "*.elfasta"
+  - known_sites:
+      type: file
+      description: Optional elsites file containing known SNPs for BQSR.
+      pattern: "*.elsites"
+  - target_regions_bed:
+      type: file
+      description: Optional BED file containing target regions for BQSR and variant calling.
+      pattern: "*.bed"
+  - intermediate_bqsr_tables:
+      type: file
+      description: Optional list of BQSR tables, used when parsing files created by `elprep split`
+      pattern: "*.table"
+  - bqsr_tables_only:
+      type: boolean
+      description: Write intermediate BQSR tables, used when parsing files created by `elprep split`.
+  - get_activity_profile:
+      type: boolean
+      description: Get the activity profile calculated by the haplotypecaller to the given file in IGV format.
+  - get_assembly_regions:
+      type: boolean
+      description: Get the assembly regions calculated by haplotypecaller to the speficied file in IGV format.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: Sorted, markdup, optionally BQSR BAM/SAM file
+      pattern: "*.{bam,sam}"
+  - metrics:
+      type: file
+      description: Optional duplicate metrics file generated by elprep
+      pattern: "*.{metrics.txt}"
+  - recall:
+      type: file
+      description: Optional recall metrics file generated by elprep
+      pattern: "*.{recall}"
+  - gvcf:
+      type: file
+      description: Optional GVCF output file
+      pattern: "*.{vcf.gz}"
+  - table:
+      type: file
+      description: Optional intermediate BQSR table output file
+      pattern: "*.{table}"
+  - activity_profile:
+      type: file
+      description: Optional activity profile output file
+      pattern: "*.{activity_profile.igv}"
+  - assembly_regions:
+      type: file
+      description: Optional activity regions output file
+      pattern: "*.{assembly_regions.igv}"
+authors:
+  - "@matthdsm"

modules/elprep/split/main.nf

@@ -11,7 +11,7 @@ process ELPREP_SPLIT {
     tuple val(meta), path(bam)
 
     output:
-    tuple val(meta), path("**.{bam,sam}"), emit: bam
+    tuple val(meta), path("output/**.{bam,sam}"), emit: bam
     path "versions.yml"           , emit: versions
 
     when:
@@ -20,7 +20,7 @@ process ELPREP_SPLIT {
     script:
     def args        = task.ext.args ?: ''
     def prefix      = task.ext.prefix ?: "${meta.id}"
-    meta.single_end ? args += " --single-end": ""
+    def single_end  = meta.single_end ? " --single-end": ""
 
     """
     # create directory and move all input so elprep can find and merge them before splitting
@@ -31,8 +31,9 @@ process ELPREP_SPLIT {
 
     elprep split \\
         input \\
-        . \\
+        output/ \\
         $args \\
+        $single_end \\
         --nr-of-threads $task.cpus \\
         --output-prefix $prefix
 

modules/gamma/main.nf

@@ -0,0 +1,41 @@
+def VERSION = '2.1' // Version information not provided by tool on CLI
+
+process GAMMA {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gamma=2.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gamma%3A2.1--hdfd78af_0':
+        'quay.io/biocontainers/gamma:2.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    path(db)
+
+    output:
+    tuple val(meta), path("*.gamma")                , emit: gamma
+    tuple val(meta), path("*.psl")                  , emit: psl
+    tuple val(meta), path("*.gff")  , optional:true , emit: gff
+    tuple val(meta), path("*.fasta"), optional:true , emit: fasta
+    path "versions.yml"                             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    GAMMA.py \\
+        $args \\
+        $fasta \\
+        $db \\
+        $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gamma: $VERSION
+    END_VERSIONS
+    """
+}

modules/gamma/meta.yml

@@ -0,0 +1,63 @@
+name: "gamma"
+description: Gene Allele Mutation Microbial Assessment
+keywords:
+  - gamma
+  - gene-calling
+tools:
+  - "gamma":
+      description: "Tool for Gene Allele Mutation Microbial Assessment"
+      homepage: "https://github.com/rastanton/GAMMA"
+      documentation: "https://github.com/rastanton/GAMMA"
+      tool_dev_url: "https://github.com/rastanton/GAMMA"
+      doi: "10.1093/bioinformatics/btab607"
+      licence: "['Apache License 2.0']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: FASTA file
+      pattern: "*.{fa,fasta}"
+  - db:
+      type: file
+      description: Database in FASTA format
+      pattern: "*.{fa,fasta}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - gamma:
+      type: file
+      description: GAMMA file with annotated gene matches
+      pattern: "*.{gamma}"
+
+  - psl:
+      type: file
+      description: PSL file with all gene matches found
+      pattern: "*.{psl}"
+
+  - gff:
+      type: file
+      description: GFF file
+      pattern: "*.{gff}"
+
+  - fasta:
+      type: file
+      description: multifasta file of the gene matches
+      pattern: "*.{fasta}"
+
+authors:
+  - "@sateeshperi"
+  - "@rastanton"

modules/gunzip/main.nf

@@ -4,8 +4,8 @@ process GUNZIP {
 
     conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' :
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'biocontainers/biocontainers:v1.2.0_cv1' }"
+        'ubuntu:20.04' }"
 
     input:
     tuple val(meta), path(archive)

modules/kaiju/kaiju2table/main.nf

@@ -0,0 +1,40 @@
+process KAIJU_KAIJU2TABLE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::kaiju=1.8.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kaiju:1.8.2--h5b5514e_1':
+        'quay.io/biocontainers/kaiju:1.8.2--h2e03b76_0' }"
+
+    input:
+    tuple val(meta), path(results)
+    path db
+    val taxon_rank
+
+    output:
+    tuple val(meta), path('*.txt'), emit: summary
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    dbnodes=`find -L ${db} -name "*nodes.dmp"`
+    dbname=`find -L ${db} -name "*.fmi" -not -name "._*"`
+    kaiju2table   $args \\
+        -t \$dbnodes \\
+        -n \$dbname \\
+        -r ${taxon_rank} \\
+        -o ${prefix}.txt \\
+        ${results}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' ))
+    END_VERSIONS
+    """
+}

modules/kaiju/kaiju2table/meta.yml

@@ -0,0 +1,50 @@
+name: "kaiju_kaiju2table"
+description: write your description here
+keywords:
+  - classify
+  - metagenomics
+tools:
+  - kaiju:
+      description: Fast and sensitive taxonomic classification for metagenomics
+      homepage: https://kaiju.binf.ku.dk/
+      documentation: https://github.com/bioinformatics-centre/kaiju/blob/master/README.md
+      tool_dev_url: https://github.com/bioinformatics-centre/kaiju
+      doi: "10.1038/ncomms11257"
+      licence: ["GNU GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - results:
+      type: file
+      description: File containing the kaiju classification results
+      pattern: "*.{txt}"
+  - taxon_rank:
+      type: string
+      description: |
+        Taxonomic rank to display in report
+        pattern: "phylum|class|order|family|genus|species"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - results:
+      type: file
+      description: |
+        Summary table for a given taxonomic rank
+      pattern: "*.{tsv}"
+
+authors:
+  - "@sofstam"
+  - "@talnor"
+  - "@jfy133"

modules/phantompeakqualtools/main.nf

@@ -26,7 +26,7 @@ process PHANTOMPEAKQUALTOOLS {
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
     RUN_SPP=`which run_spp.R`
-    Rscript $args -e "library(caTools); source(\\"\$RUN_SPP\\")" -c="$bam" -savp="${prefix}.spp.pdf" -savd="${prefix}.spp.Rdata" -out="${prefix}.spp.out" -p=$task.cpus
+    Rscript $args -e "library(caTools); source(\\"\$RUN_SPP\\")" -c="$bam" -savp="${prefix}.spp.pdf" -savd="${prefix}.spp.Rdata" -out="${prefix}.spp.out"
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/stringtie/merge/main.nf

@@ -2,10 +2,10 @@ process STRINGTIE_MERGE {
     label 'process_medium'
 
     // Note: 2.7X indices incompatible with AWS iGenomes.
-    conda     (params.enable_conda ? "bioconda::stringtie=2.1.7" : null)
+    conda     (params.enable_conda ? "bioconda::stringtie=2.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/stringtie:2.1.7--h978d192_0' :
+        'https://depot.galaxyproject.org/singularity/stringtie:2.2.1--hecb563c_2' :
-        'quay.io/biocontainers/stringtie:2.1.7--h978d192_0' }"
+        'quay.io/biocontainers/stringtie:2.2.1--hecb563c_2' }"
 
     input:
     path stringtie_gtf

modules/stringtie/stringtie/main.nf

@@ -1,11 +1,11 @@
-process STRINGTIE {
+process STRINGTIE_STRINGTIE {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::stringtie=2.1.7" : null)
+    conda (params.enable_conda ? "bioconda::stringtie=2.2.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/stringtie:2.1.7--h978d192_0' :
+        'https://depot.galaxyproject.org/singularity/stringtie:2.2.1--hecb563c_2' :
-        'quay.io/biocontainers/stringtie:2.1.7--h978d192_0' }"
+        'quay.io/biocontainers/stringtie:2.2.1--hecb563c_2' }"
 
     input:
     tuple val(meta), path(bam)

modules/stringtie/stringtie/meta.yml

@@ -1,4 +1,4 @@
-name: stringtie
+name: stringtie_stringtie
 description: Transcript assembly and quantification for RNA-Se
 keywords:
   - transcript

modules/untar/main.nf

@@ -2,10 +2,10 @@ process UNTAR {
     tag "$archive"
     label 'process_low'
 
-    conda (params.enable_conda ? "conda-forge::tar=1.34" : null)
+    conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv2/biocontainers_v1.2.0_cv2.img' :
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'biocontainers/biocontainers:v1.2.0_cv2' }"
+        'ubuntu:20.04' }"
 
     input:
     tuple val(meta), path(archive)

tests/config/pytest_modules.yml

@@ -603,6 +603,10 @@ ectyper:
   - modules/ectyper/**
   - tests/modules/ectyper/**
 
+elprep/filter:
+  - modules/elprep/filter/**
+  - tests/modules/elprep/filter/**
+
 elprep/split:
   - modules/elprep/split/**
   - tests/modules/elprep/split/**
@@ -675,6 +679,10 @@ freebayes:
   - modules/freebayes/**
   - tests/modules/freebayes/**
 
+gamma:
+  - modules/gamma/**
+  - tests/modules/gamma/**
+
 gatk4/applybqsr:
   - modules/gatk4/applybqsr/**
   - tests/modules/gatk4/applybqsr/**
@@ -1009,6 +1017,10 @@ kaiju/kaiju:
   - modules/kaiju/kaiju/**
   - tests/modules/kaiju/kaiju/**
 
+kaiju/kaiju2table:
+  - modules/kaiju/kaiju2table/**
+  - tests/modules/kaiju/kaiju2table/**
+
 kallisto/index:
   - modules/kallisto/index/**
   - tests/modules/kallisto/index/**

tests/config/test_data.config

@@ -112,6 +112,7 @@ params {
         }
         'homo_sapiens' {
             'genome' {
+                genome_elfasta                                 = "${test_data_dir}/genomics/homo_sapiens/genome/genome.elfasta"
                 genome_fasta                                   = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta"
                 genome_fasta_fai                               = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta.fai"
                 genome_dict                                    = "${test_data_dir}/genomics/homo_sapiens/genome/genome.dict"
@@ -123,6 +124,7 @@ params {
                 genome_header                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome.header"
                 genome_bed_gz                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed.gz"
                 genome_bed_gz_tbi                              = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed.gz.tbi"
+                genome_elsites                                 = "${test_data_dir}/genomics/homo_sapiens/genome/genome.elsites"
                 transcriptome_fasta                            = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta"
                 genome2_fasta                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta"
                 genome_chain_gz                                = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz"
@@ -136,6 +138,7 @@ params {
                 genome_21_multi_interval_bed_gz_tbi            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz.tbi"
                 genome_21_chromosomes_dir                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"
 
+                dbsnp_146_hg38_elsites                         = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.elsites"
                 dbsnp_146_hg38_vcf_gz                          = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
                 dbsnp_146_hg38_vcf_gz_tbi                      = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
                 gnomad_r2_1_1_vcf_gz                           = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
@@ -332,6 +335,7 @@ params {
         'bacteroides_fragilis' {
             'genome' {
                 genome_fna_gz                   = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz"
+                genome_gbff_gz                  = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.gbff.gz"
                 genome_paf                      = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.paf"
                 genome_mapping_potential_arg    = "${test_data_dir}/genomics/prokaryotes/bacteroides_fragilis/genome/genome.mapping.potential.ARG"
 

tests/modules/elprep/filter/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ELPREP_FILTER } from '../../../../modules/elprep/filter/main.nf'
+
+workflow test_elprep_filter {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+    ]
+    reference_elfasta = file(params.test_data['homo_sapiens']['genome']['genome_elfasta'], checkIfExists: true)
+    known_sites_elsites = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_elsites'], checkIfExists: true)
+    target_regions_bed = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
+
+    ELPREP_FILTER ( input, true, true, [],  [], reference_elfasta, known_sites_elsites, target_regions_bed, [], [], true, true)
+}

tests/modules/elprep/filter/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: ELPREP_FILTER {
+        ext.args = "--mark-duplicates "
+    }
+}

tests/modules/elprep/filter/test.yml

@@ -0,0 +1,13 @@
+- name: elprep filter test_elprep_filter
+  command: nextflow run tests/modules/elprep/filter -entry test_elprep_filter -c tests/config/nextflow.config
+  tags:
+    - elprep
+    - elprep/filter
+  files:
+    - path: output/elprep/test.activity_profile.igv
+    - path: output/elprep/test.assembly_regions.igv
+    - path: output/elprep/output/test.bam
+    - path: output/elprep/test.g.vcf.gz
+    - path: output/elprep/test.metrics.txt
+    - path: output/elprep/test.recall
+    - path: output/elprep/versions.yml

tests/modules/elprep/split/test.yml

@@ -4,7 +4,7 @@
     - elprep
     - elprep/split
   files:
-    - path: output/elprep/splits/test-group00001.bam
+    - path: output/elprep/output/splits/test-group00001.bam
-    - path: output/elprep/splits/test-unmapped.bam
+    - path: output/elprep/output/splits/test-unmapped.bam
-    - path: output/elprep/test-spread.bam
+    - path: output/elprep/output/test-spread.bam
     - path: output/elprep/versions.yml

tests/modules/gamma/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GAMMA } from '../../../modules/gamma/main.nf'
+
+workflow test_gamma {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    db = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
+
+    GAMMA ( input, db )
+}

tests/modules/gamma/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    ext.args = '--fasta'
+
+}

tests/modules/gamma/test.yml

@@ -0,0 +1,13 @@
+- name: gamma test_gamma
+  command: nextflow run tests/modules/gamma -entry test_gamma -c tests/config/nextflow.config
+  tags:
+    - gamma
+  files:
+    - path: output/gamma/test.fasta
+      md5sum: df37b48466181311e0a679f3c5878484
+    - path: output/gamma/test.gamma
+      md5sum: 3256708fa517a65ed01d99e0e3c762ae
+    - path: output/gamma/test.psl
+      md5sum: 162a2757ed3b167ae1e0cdb24213f940
+    - path: output/gamma/versions.yml
+      md5sum: 3fefb5b46c94993362243c5f9a472057

tests/modules/kaiju/kaiju2table/main.nf

@@ -0,0 +1,21 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { UNTAR             } from '../../../../modules/untar/main.nf'
+include { KAIJU_KAIJU       } from '../../../../modules/kaiju/kaiju/main.nf'
+include { KAIJU_KAIJU2TABLE } from '../../../../modules/kaiju/kaiju2table/main.nf'
+
+workflow test_kaiju_kaiju_single_end {
+
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
+    db    = [ [], file(params.test_data['sarscov2']['genome']['kaiju_tar_gz'], checkIfExists: true) ]
+    taxon_rank = "species"
+
+    ch_db = UNTAR ( db )
+    KAIJU_KAIJU ( input, ch_db.untar.map{ it[1] } )
+    KAIJU_KAIJU2TABLE ( KAIJU_KAIJU.out.results, ch_db.untar.map{ it[1] }, taxon_rank )
+}

tests/modules/kaiju/kaiju2table/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/kaiju/kaiju2table/test.yml

@@ -0,0 +1,9 @@
+- name: kaiju kaiju2table test_kaiju_kaiju_single_end
+  command: nextflow run tests/modules/kaiju/kaiju2table -entry test_kaiju_kaiju_single_end -c tests/config/nextflow.config
+  tags:
+    - kaiju
+    - kaiju/kaiju2table
+  files:
+    - path: output/kaiju/test.txt
+      md5sum: 0d9f8fd36fcf2888296ae12632c5f0a8
+    - path: output/kaiju/versions.yml

tests/modules/stringtie/merge/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { STRINGTIE       } from '../../../../modules/stringtie/stringtie/main.nf'
+include { STRINGTIE_STRINGTIE } from '../../../../modules/stringtie/stringtie/main.nf'
 include { STRINGTIE_MERGE     } from '../../../../modules/stringtie/merge/main.nf'
 
 /*
@@ -15,8 +15,8 @@ workflow test_stringtie_forward_merge {
     ]
     annotation_gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
 
-    STRINGTIE ( input, annotation_gtf )
+    STRINGTIE_STRINGTIE ( input, annotation_gtf )
-    STRINGTIE
+    STRINGTIE_STRINGTIE
         .out
         .transcript_gtf
         .map { it -> it[1] }
@@ -35,8 +35,8 @@ workflow test_stringtie_reverse_merge {
     ]
     annotation_gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
 
-    STRINGTIE ( input, annotation_gtf )
+    STRINGTIE_STRINGTIE ( input, annotation_gtf )
-    STRINGTIE
+    STRINGTIE_STRINGTIE
         .out
         .transcript_gtf
         .map { it -> it[1] }

tests/modules/stringtie/merge/test.yml

@@ -5,7 +5,7 @@
     - stringtie/merge
   files:
     - path: output/stringtie/stringtie.merged.gtf
-      md5sum: 9fab7049ef2eafdea246fc787d1def40
+      md5sum: d959eb2fab0db48ded7275e0a2e83c05
     - path: output/stringtie/test.ballgown/e2t.ctab
       md5sum: 9ae42e056c955a88a883e5e917840d77
     - path: output/stringtie/test.ballgown/e_data.ctab
@@ -17,11 +17,10 @@
     - path: output/stringtie/test.ballgown/t_data.ctab
       md5sum: 92a98902784e7406ffe054d2adbabc7c
     - path: output/stringtie/test.coverage.gtf
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/stringtie/test.gene.abundance.txt
-      md5sum: 9708811bcefe0f6384293d6f419f3250
+      md5sum: 8bcd8e2730ed3337e2730186dbc184f3
     - path: output/stringtie/test.transcripts.gtf
-      md5sum: 0e42709bfe30c2c7f2574ba664f5fa9f
+      md5sum: a914bd55b68a4b5f607738b17861e362
 
 - name: stringtie merge test_stringtie_reverse_merge
   command: nextflow run ./tests/modules/stringtie/merge -entry test_stringtie_reverse_merge -c ./tests/config/nextflow.config -c ./tests/modules/stringtie/merge/nextflow.config
@@ -30,7 +29,7 @@
     - stringtie/merge
   files:
     - path: output/stringtie/stringtie.merged.gtf
-      md5sum: afc461bb3cbc368f268a7a45c1b54497
+      md5sum: 6da479298d73d5b3216d4e1576a2bdf4
     - path: output/stringtie/test.ballgown/e2t.ctab
       md5sum: 9ae42e056c955a88a883e5e917840d77
     - path: output/stringtie/test.ballgown/e_data.ctab
@@ -42,8 +41,7 @@
     - path: output/stringtie/test.ballgown/t_data.ctab
       md5sum: 92a98902784e7406ffe054d2adbabc7c
     - path: output/stringtie/test.coverage.gtf
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/stringtie/test.gene.abundance.txt
-      md5sum: 94b85145d60ab1b80a7f0f6cf08418b0
+      md5sum: f289f41b3ba1b9f0aa05d14408f1a5da
     - path: output/stringtie/test.transcripts.gtf
-      md5sum: 3196e3d50fd461aae6408e0a70acae68
+      md5sum: 9dcdc9577c0fdbb25089eda210267546

tests/modules/stringtie/stringtie/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { STRINGTIE } from '../../../../modules/stringtie/stringtie/main.nf'
+include { STRINGTIE_STRINGTIE } from '../../../../modules/stringtie/stringtie/main.nf'
 //
 // Test with forward strandedness
 //
@@ -13,7 +13,7 @@ workflow test_stringtie_forward {
     ]
     annotation_gtf = file(params.test_data['sarscov2']['genome']['genome_gtf'], checkIfExists: true)
 
-    STRINGTIE ( input, annotation_gtf )
+    STRINGTIE_STRINGTIE ( input, annotation_gtf )
 }
 
 //
@@ -26,5 +26,5 @@ workflow test_stringtie_reverse {
     ]
     annotation_gtf = file(params.test_data['sarscov2']['genome']['genome_gtf'], checkIfExists: true)
 
-    STRINGTIE ( input, annotation_gtf )
+    STRINGTIE_STRINGTIE ( input, annotation_gtf )
 }

tests/modules/stringtie/stringtie/test.yml

@@ -8,7 +8,6 @@
     - path: ./output/stringtie/test.gene.abundance.txt
       md5sum: 7d8bce7f2a922e367cedccae7267c22e
     - path: ./output/stringtie/test.coverage.gtf
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: ./output/stringtie/test.ballgown/e_data.ctab
       md5sum: 6b4cf69bc03f3f69890f972a0e8b7471
     - path: ./output/stringtie/test.ballgown/i_data.ctab
@@ -30,7 +29,6 @@
     - path: ./output/stringtie/test.gene.abundance.txt
       md5sum: 7385b870b955dae2c2ab78a70cf05cce
     - path: ./output/stringtie/test.coverage.gtf
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: ./output/stringtie/test.ballgown/e_data.ctab
       md5sum: 879b6696029d19c4737b562e9d149218
     - path: ./output/stringtie/test.ballgown/i_data.ctab