Merge branch 'master' into feat/update_cnvpytor

modules/ensemblvep/Dockerfile

@@ -8,13 +8,14 @@ LABEL \
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
-# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-vep-104.3/bin:$PATH
-
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=99
+ARG VEP_VERSION=104
+ARG VEP_TAG=104.3
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH
 
 # Download Genome
 RUN vep_install \
@@ -27,4 +28,4 @@ RUN vep_install \
     --NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-vep-104.3 > nf-core-vep-104.3.yml
+RUN conda env export --name nf-core-vep-${VEP_TAG} > nf-core-vep-${VEP_TAG}.yml

modules/ensemblvep/build.sh

@@ -10,11 +10,12 @@ build_push() {
     VEP_TAG=$4
 
     docker build \
+        . \
         -t nfcore/vep:${VEP_TAG}.${GENOME} \
-        software/vep/. \
         --build-arg GENOME=${GENOME} \
         --build-arg SPECIES=${SPECIES} \
-        --build-arg VEP_VERSION=${VEP_VERSION}
+        --build-arg VEP_VERSION=${VEP_VERSION} \
+        --build-arg VEP_TAG=${VEP_TAG}
 
     docker push nfcore/vep:${VEP_TAG}.${GENOME}
 }

modules/ensemblvep/main.nf

@@ -13,6 +13,7 @@ process ENSEMBLVEP {
     val   species
     val   cache_version
     path  cache
+    path  extra_files
 
     output:
     tuple val(meta), path("*.ann.vcf"), emit: vcf

modules/ensemblvep/meta.yml

@@ -10,17 +10,6 @@ tools:
       homepage: https://www.ensembl.org/info/docs/tools/vep/index.html
       documentation: https://www.ensembl.org/info/docs/tools/vep/script/index.html
       licence: ["Apache-2.0"]
-params:
-  - use_cache:
-      type: boolean
-      description: |
-        Enable the usage of containers with cache
-        Does not work with conda
-  - vep_tag:
-      type: value
-      description: |
-        Specify the tag for the container
-        https://hub.docker.com/r/nfcore/vep/tags
 input:
   - meta:
       type: map
@@ -47,6 +36,10 @@ input:
       type: file
       description: |
         path to VEP cache (optional)
+  - extra_files:
+      type: tuple
+      description: |
+        path to file(s) needed for plugins  (optional)
 output:
   - vcf:
       type: file

modules/happy/happy/main.nf

@@ -0,0 +1,42 @@
+def VERSION = '0.3.14'
+
+process HAPPY_HAPPY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::hap.py=0.3.14" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hap.py:0.3.14--py27h5c5a3ab_0':
+        'quay.io/biocontainers/hap.py:0.3.14--py27h5c5a3ab_0' }"
+
+    input:
+    tuple val(meta), path(truth_vcf), path(query_vcf), path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    output:
+    tuple val(meta), path('*.csv'), path('*.json')  , emit: metrics
+    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}"
+
+    """
+    hap.py \\
+        $truth_vcf \\
+        $query_vcf \\
+        $args \\
+        --reference $fasta \\
+        --threads $task.cpus \\
+        -R $bed \\
+        -o $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hap.py: $VERSION
+    END_VERSIONS
+    """
+}

modules/happy/happy/meta.yml

@@ -0,0 +1,67 @@
+name: "happy_happy"
+description: Hap.py is a tool to compare diploid genotypes at haplotype level. Rather than comparing VCF records row by row, hap.py will generate and match alternate sequences in a superlocus. A superlocus is a small region of the genome (sized between 1 and around 1000 bp) that contains one or more variants.
+keywords:
+  - happy
+  - benchmark
+  - haplotype
+tools:
+  - "happy":
+      description: "Haplotype VCF comparison tools"
+      homepage: "https://www.illumina.com/products/by-type/informatics-products/basespace-sequence-hub/apps/hap-py-benchmarking.html"
+      documentation: "https://github.com/Illumina/hap.py"
+      tool_dev_url: "https://github.com/Illumina/hap.py"
+      doi: ""
+      licence: "['BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - truth_vcf:
+      type: file
+      description: gold standard VCF file
+      pattern: "*.{vcf,vcf.gz}"
+  - query_vcf:
+      type: file
+      description: VCF/GVCF file to query
+      pattern: "*.{vcf,vcf.gz}"
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: FASTA file of the reference genome
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA
+      pattern: "*.fai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - summary:
+      type: file
+      description: A CSV file containing the summary of the benchmarking
+      pattern: "*.summary.csv"
+  - extended:
+      type: file
+      description: A CSV file containing extended info of the benchmarking
+      pattern: "*.extended.csv"
+  - runinfo:
+      type: file
+      description: A JSON file containing the run info
+      pattern: "*.runinfo.json"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

modules/happy/prepy/main.nf

@@ -0,0 +1,41 @@
+def VERSION = '0.3.14'
+
+process HAPPY_PREPY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::hap.py=0.3.14" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hap.py:0.3.14--py27h5c5a3ab_0':
+        'quay.io/biocontainers/hap.py:0.3.14--py27h5c5a3ab_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path(bed)
+    tuple path(fasta), path(fasta_fai)
+
+    output:
+    tuple val(meta), path('*.vcf.gz')  , emit: preprocessed_vcf
+    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}"
+
+    """
+    pre.py \\
+        $args \\
+        -R $bed \\
+        --reference $fasta \\
+        --threads $task.cpus \\
+        $vcf \\
+        ${prefix}.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pre.py: $VERSION
+    END_VERSIONS
+    """
+}

modules/happy/prepy/meta.yml

@@ -0,0 +1,55 @@
+name: "happy_prepy"
+description: Pre.py is a preprocessing tool made to preprocess VCF files for Hap.py
+keywords:
+  - happy
+  - benchmark
+  - haplotype
+tools:
+  - "happy":
+      description: "Haplotype VCF comparison tools"
+      homepage: "https://www.illumina.com/products/by-type/informatics-products/basespace-sequence-hub/apps/hap-py-benchmarking.html"
+      documentation: "https://github.com/Illumina/hap.py"
+      tool_dev_url: "https://github.com/Illumina/hap.py"
+      doi: ""
+      licence: "['BSD-2-clause']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF file to preprocess
+      pattern: "*.{vcf,vcf.gz}"
+  - bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - fasta:
+      type: file
+      description: FASTA file of the reference genome
+      pattern: "*.{fa,fasta}"
+  - fasta_fai:
+      type: file
+      description: The index of the reference FASTA
+      pattern: "*.fai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: A preprocessed VCF file
+      pattern: "*.vcf.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nvnieuwk"

modules/krona/kronadb/main.nf

@@ -18,7 +18,9 @@ process KRONA_KRONADB {
     script:
     def args = task.ext.args ?: ''
     """
-    ktUpdateTaxonomy.sh taxonomy
+    ktUpdateTaxonomy.sh \\
+        $args \\
+        taxonomy/
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/krona/ktimporttaxonomy/main.nf

@@ -23,7 +23,10 @@ process KRONA_KTIMPORTTAXONOMY {
     script:
     def args = task.ext.args ?: ''
     """
-    ktImportTaxonomy "$report" -tax taxonomy
+    ktImportTaxonomy \\
+        $args \\
+        -tax taxonomy/ \\
+        "$report"
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/krona/ktimporttaxonomy/meta.yml

@@ -23,8 +23,11 @@ input:
         Groovy Map containing sample information
         e.g. [ id:'test']
   - database:
-      type: path
+      type: file
-      description: "Path to the taxonomy database downloaded by krona/kronadb"
+      description: |
+        Path to the taxonomy database .tab file downloaded by krona/ktUpdateTaxonomy
+        The file will be saved under a folder named "taxonomy" as "taxonomy/taxonomy.tab".
+        The parent folder will be passed as argument to ktImportTaxonomy.
   - report:
       type: file
       description: "A tab-delimited file with taxonomy IDs and (optionally) query IDs, magnitudes, and scores.  Query IDs are taken from column 1, taxonomy IDs from column 2, and scores from column 3.  Lines beginning with # will be ignored."

modules/krona/ktupdatetaxonomy/main.nf

@@ -0,0 +1,30 @@
+def VERSION='2.7.1' // Version information not provided by tool on CLI
+
+process KRONA_KTUPDATETAXONOMY {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::krona=2.7.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/krona:2.7.1--pl526_5' :
+        'quay.io/biocontainers/krona:2.7.1--pl526_5' }"
+
+    output:
+    path 'taxonomy/taxonomy.tab', emit: db
+    path "versions.yml"         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    ktUpdateTaxonomy.sh \\
+        $args \\
+        taxonomy/
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        krona: $VERSION
+    END_VERSIONS
+    """
+}

modules/krona/ktupdatetaxonomy/meta.yml

@@ -0,0 +1,31 @@
+name: krona_ktupdatetaxonomy
+description: KronaTools Update Taxonomy downloads a taxonomy database
+keywords:
+  - database
+  - taxonomy
+  - krona
+  - visualisation
+tools:
+  - krona:
+      description: Krona Tools is a set of scripts to create Krona charts from several Bioinformatics tools as well as from text and XML files.
+      homepage: https://github.com/marbl/Krona/wiki/KronaTools
+      documentation: https://github.com/marbl/Krona/wiki/Installing
+      tool_dev_url:
+      doi: https://doi.org/10.1186/1471-2105-12-385
+      licence:
+
+input:
+  - none: There is no input. This module downloads a pre-built taxonomy database for use with Krona Tools.
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: file
+      description: A TAB separated file that contains a taxonomy database.
+      pattern: "*.{tab}"
+
+authors:
+  - "@mjakobs"

modules/motus/downloaddb/main.nf

@@ -0,0 +1,39 @@
+process MOTUS_DOWNLOADDB {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::motus=3.0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/motus:3.0.1--pyhdfd78af_0':
+        'quay.io/biocontainers/motus:3.0.1--pyhdfd78af_0' }"
+
+    input:
+    path motus_downloaddb_script
+
+    output:
+    path "db_mOTU/"                , emit: db
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args     = task.ext.args ?: ''
+    def software = "${motus_downloaddb_script.simpleName}_copy.py"
+    """
+    ## must copy script file to working directory,
+    ## otherwise the reference_db will be download to bin folder
+    ## other than current directory
+    cp $motus_downloaddb_script ${software}
+    python ${software} \\
+        $args \\
+        -t $task.cpus
+
+    ## mOTUs version number is not available from command line.
+    ## mOTUs save the version number in index database folder.
+    ## mOTUs will check the database version is same version as exec version.
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mOTUs: \$(grep motus db_mOTU/db_mOTU_versions | sed 's/motus\\t//g')
+    END_VERSIONS
+    """
+}

modules/motus/downloaddb/meta.yml

@@ -0,0 +1,39 @@
+name: "motus_downloaddb"
+description: Download the mOTUs database
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - taxonomic profiling
+  - database
+  - download
+tools:
+  - "motus":
+      description: "The mOTU profiler is a computational tool that estimates relative taxonomic abundance of known and currently unknown microbial community members using metagenomic shotgun sequencing data."
+      homepage: "None"
+      documentation: "https://github.com/motu-tool/mOTUs/wiki"
+      tool_dev_url: "https://github.com/motu-tool/mOTUs"
+      doi: "10.1038/s41467-019-08844-4"
+      licence: "['GPL v3']"
+
+input:
+  - motus_downloaddb:
+      type: directory
+      description: |
+        The mOTUs downloadDB script source file.
+        It is the source file installed or
+        remote source in github such as https://raw.githubusercontent.com/motu-tool/mOTUs/master/motus/downloadDB.py
+      pattern: "downloadDB.py"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: directory
+      description: The mOTUs database directory
+      pattern: "db_mOTU"
+
+authors:
+  - "@jianhong"

modules/samtools/bam2fq/main.nf

@@ -45,7 +45,7 @@ process SAMTOOLS_BAM2FQ {
             bam2fq \\
             $args \\
             -@ $task.cpus \\
-            $inputbam >${prefix}_interleaved.fq.gz
+            $inputbam | gzip --no-name > ${prefix}_interleaved.fq.gz
 
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":

modules/snpeff/Dockerfile

@@ -8,15 +8,16 @@ LABEL \
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
-# Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-snpeff-5.0/bin:$PATH
-
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SNPEFF_CACHE_VERSION=99
+ARG SNPEFF_TAG=99
+
+# Add conda installation dir to PATH (instead of doing 'conda activate')
+ENV PATH /opt/conda/envs/nf-core-snpeff-${SNPEFF_TAG}/bin:$PATH
 
 # Download Genome
 RUN snpEff download -v ${GENOME}.${SNPEFF_CACHE_VERSION}
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-snpeff-5.0 > nf-core-snpeff-5.0.yml
+RUN conda env export --name nf-core-snpeff-${SNPEFF_TAG} > nf-core-snpeff-${SNPEFF_TAG}.yml

modules/snpeff/build.sh

@@ -9,10 +9,11 @@ build_push() {
     SNPEFF_TAG=$3
 
     docker build \
+        . \
         -t nfcore/snpeff:${SNPEFF_TAG}.${GENOME} \
-        software/snpeff/. \
         --build-arg GENOME=${GENOME} \
-        --build-arg SNPEFF_CACHE_VERSION=${SNPEFF_CACHE_VERSION}
+        --build-arg SNPEFF_CACHE_VERSION=${SNPEFF_CACHE_VERSION} \
+        --build-arg SNPEFF_TAG=${SNPEFF_TAG}
 
     docker push nfcore/snpeff:${SNPEFF_TAG}.${GENOME}
 }

modules/snpeff/meta.yml

@@ -10,18 +10,6 @@ tools:
       homepage: https://pcingola.github.io/SnpEff/
       documentation: https://pcingola.github.io/SnpEff/se_introduction/
       licence: ["MIT"]
-params:
-  - use_cache:
-      type: boolean
-      description: |
-        boolean to enable the usage of containers with cache
-        Enable the usage of containers with cache
-        Does not work with conda
-  - snpeff_tag:
-      type: value
-      description: |
-        Specify the tag for the container
-        https://hub.docker.com/r/nfcore/snpeff/tags
 input:
   - meta:
       type: map

subworkflows/nf-core/annotation/ensemblvep/main.nf

@@ -0,0 +1,31 @@
+//
+// Run VEP to annotate VCF files
+//
+
+include { ENSEMBLVEP       } from '../../../../modules/ensemblvep/main'
+include { TABIX_BGZIPTABIX } from '../../../../modules/tabix/bgziptabix/main'
+
+workflow ANNOTATION_ENSEMBLVEP {
+    take:
+    vcf               // channel: [ val(meta), vcf ]
+    vep_genome        //   value: genome to use
+    vep_species       //   value: species to use
+    vep_cache_version //   value: cache version to use
+    vep_cache         //    path: /path/to/vep/cache (optionnal)
+    vep_extra_files   // channel: [ file1, file2...] (optionnal)
+
+    main:
+    ch_versions = Channel.empty()
+
+    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+    TABIX_BGZIPTABIX(ENSEMBLVEP.out.vcf)
+
+    // Gather versions of all tools used
+    ch_versions = ch_versions.mix(ENSEMBLVEP.out.versions.first())
+    ch_versions = ch_versions.mix(TABIX_BGZIPTABIX.out.versions.first())
+
+    emit:
+    vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    reports  = ENSEMBLVEP.out.report       //    path: *.html
+    versions = ch_versions                 //    path: versions.yml
+}

subworkflows/nf-core/annotation/ensemblvep/meta.yml

@@ -0,0 +1,49 @@
+name: annotation_ensemblvep
+description: |
+  Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
+keywords:
+  - ensemblvep
+modules:
+  - ensemblvep
+  - tabix/bgziptabix
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: |
+        vcf to annotate
+  - genome:
+      type: value
+      description: |
+        which genome to annotate with
+  - species:
+      type: value
+      description: |
+        which species to annotate with
+  - cache_version:
+      type: value
+      description: |
+        which version of the cache to annotate with
+  - cache:
+      type: file
+      description: |
+        path to VEP cache (optional)
+  - extra_files:
+      type: tuple
+      description: |
+        path to file(s) needed for plugins  (optional)
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf_tbi:
+      type: file
+      description: Compressed vcf file + tabix index
+      pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
+authors:
+  - "@maxulysse"

subworkflows/nf-core/annotation/snpeff/main.nf

@@ -0,0 +1,28 @@
+//
+// Run SNPEFF to annotate VCF files
+//
+
+include { SNPEFF           } from '../../../../modules/snpeff/main'
+include { TABIX_BGZIPTABIX } from '../../../../modules/tabix/bgziptabix/main'
+
+workflow ANNOTATION_SNPEFF {
+    take:
+    vcf          // channel: [ val(meta), vcf ]
+    snpeff_db    //   value: db version to use
+    snpeff_cache //    path: /path/to/snpeff/cache (optionnal)
+
+    main:
+    ch_versions = Channel.empty()
+
+    SNPEFF(vcf, snpeff_db, snpeff_cache)
+    TABIX_BGZIPTABIX(SNPEFF.out.vcf)
+
+    // Gather versions of all tools used
+    ch_versions = ch_versions.mix(SNPEFF.out.versions.first())
+    ch_versions = ch_versions.mix(TABIX_BGZIPTABIX.out.versions.first())
+
+    emit:
+    vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    reports  = SNPEFF.out.report           //    path: *.html
+    versions = ch_versions                 //    path: versions.yml
+}

subworkflows/nf-core/annotation/snpeff/meta.yml

@@ -11,11 +11,19 @@ input:
       type: map
       description: |
         Groovy Map containing sample information
-        e.g. [ id:'test' ]
+        e.g. [ id:'test', single_end:false ]
-  - input:
+  - vcf:
-      type: vcf
+      type: file
-      description: list containing one vcf file
+      description: |
-      pattern: "[ *.{vcf,vcf.gz} ]"
+        vcf to annotate
+  - db:
+      type: value
+      description: |
+        which db to annotate with
+  - cache:
+      type: file
+      description: |
+        path to snpEff cache (optional)
 output:
   - versions:
       type: file

subworkflows/nf-core/annotation_ensemblvep/main.nf

@@ -1,26 +0,0 @@
-//
-// Run VEP to annotate VCF files
-//
-
-include { ENSEMBLVEP                                } from '../../../modules/ensemblvep/main'
-include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
-
-workflow ANNOTATION_ENSEMBLVEP {
-    take:
-    vcf               // channel: [ val(meta), vcf ]
-    vep_genome        //   value: which genome
-    vep_species       //   value: which species
-    vep_cache_version //   value: which cache version
-    vep_cache         //    path: path_to_vep_cache (optionnal)
-
-    main:
-    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache)
-    ANNOTATION_BGZIPTABIX(ENSEMBLVEP.out.vcf)
-
-    ch_versions = ENSEMBLVEP.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
-
-    emit:
-    vcf_tbi  = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = ENSEMBLVEP.out.report            //    path: *.html
-    versions = ch_versions                      //    path: versions.yml
-}

subworkflows/nf-core/annotation_ensemblvep/meta.yml

@@ -1,29 +0,0 @@
-name: annotation_ensemblvep
-description: |
-  Perform annotation with ensemblvep and bgzip + tabix index the resulting VCF file
-keywords:
-  - ensemblvep
-modules:
-  - ensemblvep
-  - tabix/bgziptabix
-input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test' ]
-  - input:
-      type: vcf
-      description: list containing one vcf file
-      pattern: "[ *.{vcf,vcf.gz} ]"
-output:
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-  - vcf_tbi:
-      type: file
-      description: Compressed vcf file + tabix index
-      pattern: "[ *{.vcf.gz,vcf.gz.tbi} ]"
-authors:
-  - "@maxulysse"

subworkflows/nf-core/annotation_snpeff/main.nf

@@ -1,23 +0,0 @@
-//
-// Run SNPEFF to annotate VCF files
-//
-
-include { SNPEFF                                    } from '../../../modules/snpeff/main'
-include { TABIX_BGZIPTABIX as ANNOTATION_BGZIPTABIX } from '../../../modules/tabix/bgziptabix/main'
-
-workflow ANNOTATION_SNPEFF {
-    take:
-    vcf            // channel: [ val(meta), vcf ]
-    snpeff_db      //   value: version of db to use
-    snpeff_cache   //    path: path_to_snpeff_cache (optionnal)
-
-    main:
-    SNPEFF(vcf, snpeff_db, snpeff_cache)
-    ANNOTATION_BGZIPTABIX(SNPEFF.out.vcf)
-    ch_versions = SNPEFF.out.versions.first().mix(ANNOTATION_BGZIPTABIX.out.versions.first())
-
-    emit:
-    vcf_tbi  = ANNOTATION_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = SNPEFF.out.report                //    path: *.html
-    versions = ch_versions                      //    path: versions.yml
-}

tests/config/pytest_modules.yml

@@ -891,6 +891,14 @@ hamronization/summarize:
   - modules/hamronization/summarize/**
   - tests/modules/hamronization/summarize/**
 
+happy/happy:
+  - modules/happy/happy/**
+  - tests/modules/happy/happy/**
+
+happy/prepy:
+  - modules/happy/prepy/**
+  - tests/modules/happy/prepy/**
+
 hicap:
   - modules/hicap/**
   - tests/modules/hicap/**
@@ -1050,6 +1058,10 @@ krona/kronadb:
   - modules/krona/kronadb/**
   - tests/modules/krona/kronadb/**
 
+krona/ktupdatetaxonomy:
+  - modules/krona/ktupdatetaxonomy/**
+  - tests/modules/krona/ktupdatetaxonomy/**
+
 krona/ktimporttaxonomy:
   - modules/krona/ktimporttaxonomy/**
   - tests/modules/krona/ktimporttaxonomy/**
@@ -1242,6 +1254,10 @@ mosdepth:
   - modules/mosdepth/**
   - tests/modules/mosdepth/**
 
+motus/downloaddb:
+  - modules/motus/downloaddb/**
+  - tests/modules/motus/downloaddb/**
+
 msisensor/msi:
   - modules/msisensor/msi/**
   - tests/modules/msisensor/msi/**

tests/config/test_data.config

@@ -111,7 +111,9 @@ params {
                 test_sequencing_summary                        = "${test_data_dir}/genomics/sarscov2/nanopore/sequencing_summary/test.sequencing_summary.txt"
             }
             'metagenome' {
+                classified_reads_assignment                    = "${test_data_dir}/genomics/sarscov2/metagenome/test_1.kraken2.reads.txt"
                 kraken_report                                  = "${test_data_dir}/genomics/sarscov2/metagenome/test_1.kraken2.report.txt"
+                krona_taxonomy                                 = "${test_data_dir}/genomics/sarscov2/metagenome/krona_taxonomy.tab"
             }
         }
         'homo_sapiens' {

tests/modules/ensemblvep/main.nf

@@ -10,5 +10,5 @@ workflow test_ensemblvep {
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
+    ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [] )
 }

tests/modules/happy/happy/main.nf

@@ -0,0 +1,39 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HAPPY_HAPPY } from '../../../../modules/happy/happy/main.nf'
+
+workflow test_happy_vcf {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_vcf'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_genome21_indels_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)        
+    ]
+
+    fasta = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    HAPPY_HAPPY ( input, fasta )
+}
+
+workflow test_happy_gvcf {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_rnaseq_vcf'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)        
+    ]
+
+    fasta = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    HAPPY_HAPPY ( input, fasta )
+}

tests/modules/happy/happy/nextflow.config

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

tests/modules/happy/happy/test.yml

@@ -0,0 +1,27 @@
+- name: happy happy test_happy_vcf
+  command: nextflow run tests/modules/happy/happy -entry test_happy_vcf -c tests/config/nextflow.config
+  tags:
+    - happy
+    - happy/happy
+  files:
+    - path: output/happy/test.extended.csv
+      md5sum: ef79c7c789ef4f146ca2e50dafaf22b3
+    - path: output/happy/test.runinfo.json
+    - path: output/happy/test.summary.csv
+      md5sum: f8aa5d36d3c48dede2f607fd565894ad
+    - path: output/happy/versions.yml
+      md5sum: 82243bf6dbdc71aa63211ee2a89f47f2
+
+- name: happy happy test_happy_gvcf
+  command: nextflow run tests/modules/happy/happy -entry test_happy_gvcf -c tests/config/nextflow.config
+  tags:
+    - happy
+    - happy/happy
+  files:
+    - path: output/happy/test.extended.csv
+      md5sum: 3d5c21b67a259a3f6dcb088d55b86cd3
+    - path: output/happy/test.runinfo.json
+    - path: output/happy/test.summary.csv
+      md5sum: 03044e9bb5a0c6f0947b7e910fc8a558
+    - path: output/happy/versions.yml
+      md5sum: 551fa216952d6f5de78e6e453b92aaab

tests/modules/happy/prepy/main.nf

@@ -0,0 +1,37 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HAPPY_PREPY } from '../../../../modules/happy/prepy/main.nf'
+
+workflow test_happy_prepy_vcf {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_genome21_indels_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)        
+    ]
+
+    fasta = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    HAPPY_PREPY ( input, fasta )
+}
+
+workflow test_happy_prepy_gvcf {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)        
+    ]
+
+    fasta = Channel.value([
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    ])
+
+    HAPPY_PREPY ( input, fasta )
+}

tests/modules/happy/prepy/nextflow.config

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

tests/modules/happy/prepy/test.yml

@@ -0,0 +1,19 @@
+- name: happy prepy test_happy_prepy_vcf
+  command: nextflow run tests/modules/happy/prepy -entry test_happy_prepy_vcf -c tests/config/nextflow.config
+  tags:
+    - happy/prepy
+    - happy
+  files:
+    - path: output/happy/test.vcf.gz
+    - path: output/happy/versions.yml
+      md5sum: 814d20f1f29f23a3d21012748a5d6393
+
+- name: happy prepy test_happy_prepy_gvcf
+  command: nextflow run tests/modules/happy/prepy -entry test_happy_prepy_gvcf -c tests/config/nextflow.config
+  tags:
+    - happy/prepy
+    - happy
+  files:
+    - path: output/happy/test.vcf.gz
+    - path: output/happy/versions.yml
+      md5sum: 970a54de46e68ef6d5228a26eaa4c8e7

tests/modules/krona/ktimporttaxonomy/main.nf

@@ -2,15 +2,27 @@
 
 nextflow.enable.dsl = 2
 
-include { KRONA_KTIMPORTTAXONOMY } from '../../../../modules/krona/ktimporttaxonomy/main.nf'
+include { KRONA_KTIMPORTTAXONOMY as KRONA_KTIMPORTTAXONOMY_READS  } from '../../../../modules/krona/ktimporttaxonomy/main.nf'
+include { KRONA_KTIMPORTTAXONOMY as KRONA_KTIMPORTTAXONOMY_REPORT } from '../../../../modules/krona/ktimporttaxonomy/main.nf'
 
-workflow test_krona_ktimporttaxonomy {
+workflow test_krona_ktimporttaxonomy_reads {
 
     input = [
         [ id:'test', single_end:false ], // meta map
-        file(params.test_data['generic']['txt']['hello'], checkIfExists: true)
+        file(params.test_data['sarscov2']['metagenome']['classified_reads_assignment'], checkIfExists: true)
     ]
-    taxonomy = file(params.test_data['generic']['txt']['hello'], checkIfExists: true)
+    taxonomy = file(params.test_data['sarscov2']['metagenome']['krona_taxonomy'], checkIfExists: true)
 
-    KRONA_KTIMPORTTAXONOMY ( input, taxonomy )
+    KRONA_KTIMPORTTAXONOMY_READS ( input, taxonomy )
+}
+
+workflow test_krona_ktimporttaxonomy_report {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['metagenome']['kraken_report'], checkIfExists: true)
+    ]
+    taxonomy = file(params.test_data['sarscov2']['metagenome']['krona_taxonomy'], checkIfExists: true)
+
+    KRONA_KTIMPORTTAXONOMY_REPORT ( input, taxonomy )
 }

tests/modules/krona/ktimporttaxonomy/nextflow.config

@@ -2,4 +2,12 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: KRONA_KTIMPORTTAXONOMY_READS {
+        ext.args = '-t 3'
+    }
+
+    withName: KRONA_KTIMPORTTAXONOMY_REPORT {
+        ext.args = '-m 3 -t 5'
+    }
+
 }

tests/modules/krona/ktimporttaxonomy/test.yml

@@ -1,9 +1,23 @@
-- name: krona ktimporttaxonomy test_krona_ktimporttaxonomy
+- name: krona ktimporttaxonomy test_krona_ktimporttaxonomy_reads
-  command: nextflow run ./tests/modules/krona/ktimporttaxonomy -entry test_krona_ktimporttaxonomy -c ./tests/config/nextflow.config -c ./tests/modules/krona/ktimporttaxonomy/nextflow.config
+  command: nextflow run tests/modules/krona/ktimporttaxonomy -entry test_krona_ktimporttaxonomy_reads -c tests/config/nextflow.config
   tags:
-    - krona/ktimporttaxonomy
     - krona
+    - krona/ktimporttaxonomy
   files:
     - path: output/krona/taxonomy.krona.html
       contains:
         - "DOCTYPE html PUBLIC"
+    - path: output/krona/versions.yml
+      md5sum: 660a8c151191bf4c63bd96db2c7fe503
+
+- name: krona ktimporttaxonomy test_krona_ktimporttaxonomy_report
+  command: nextflow run tests/modules/krona/ktimporttaxonomy -entry test_krona_ktimporttaxonomy_report -c tests/config/nextflow.config
+  tags:
+    - krona
+    - krona/ktimporttaxonomy
+  files:
+    - path: output/krona/taxonomy.krona.html
+      contains:
+        - "DOCTYPE html PUBLIC"
+    - path: output/krona/versions.yml
+      md5sum: 8a593c16bb2d4132638fb0fc342fe2b7

tests/modules/krona/ktupdatetaxonomy/main.nf

@@ -0,0 +1,9 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { KRONA_KTUPDATETAXONOMY } from '../../../../modules/krona/ktupdatetaxonomy/main.nf'
+
+workflow test_krona_ktupdatetaxonomy {
+    KRONA_KTUPDATETAXONOMY ( )
+}

tests/modules/krona/ktupdatetaxonomy/nextflow.config

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

tests/modules/krona/ktupdatetaxonomy/test.yml

@@ -0,0 +1,7 @@
+- name: krona ktupdatetaxonomy test_krona_ktupdatetaxonomy
+  command: nextflow run ./tests/modules/krona/ktupdatetaxonomy -entry test_krona_ktupdatetaxonomy -c ./tests/config/nextflow.config -c ./tests/modules/krona/ktupdatetaxonomy/nextflow.config
+  tags:
+    - krona
+    - krona/ktupdatetaxonomy
+  files:
+    - path: output/krona/taxonomy/taxonomy.tab

tests/modules/motus/downloaddb/main.nf

@@ -0,0 +1,12 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MOTUS_DOWNLOADDB } from '../../../../modules/motus/downloaddb/main.nf'
+
+workflow test_motus_downloaddb {
+
+    input = file('https://raw.githubusercontent.com/motu-tool/mOTUs/master/motus/downloadDB.py')
+
+    MOTUS_DOWNLOADDB ( input )
+}

tests/modules/motus/downloaddb/nextflow.config

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

tests/modules/motus/downloaddb/test.yml

@@ -0,0 +1,7 @@
+- name: motus downloaddb test_motus_downloaddb
+  command: nextflow run tests/modules/motus/downloaddb -entry test_motus_downloaddb -c tests/config/nextflow.config
+  tags:
+    - motus
+    - motus/downloaddb
+  files:
+    - path: output/motus/db_mOTU/db_mOTU_versions

tests/modules/samtools/bam2fq/test.yml

@@ -1,14 +1,15 @@
 - name: samtools bam2fq test_samtools_bam2fq_nosplit
-  command: nextflow run ./tests/modules/samtools/bam2fq -entry test_samtools_bam2fq_nosplit -c ./tests/config/nextflow.config -c ./tests/modules/samtools/bam2fq/nextflow.config
+  command: nextflow run tests/modules/samtools/bam2fq -entry test_samtools_bam2fq_nosplit -c tests/config/nextflow.config
   tags:
     - samtools/bam2fq
     - samtools
   files:
     - path: output/samtools/test_interleaved.fq.gz
-      md5sum: d733e66d29a4b366bf9df8c42f845256
+    - path: output/samtools/versions.yml
+      md5sum: 4973eac1b6a8f090d5fcd4456d65a894
 
 - name: samtools bam2fq test_samtools_bam2fq_withsplit
-  command: nextflow run ./tests/modules/samtools/bam2fq -entry test_samtools_bam2fq_withsplit -c ./tests/config/nextflow.config -c ./tests/modules/samtools/bam2fq/nextflow.config
+  command: nextflow run tests/modules/samtools/bam2fq -entry test_samtools_bam2fq_withsplit -c tests/config/nextflow.config
   tags:
     - samtools/bam2fq
     - samtools
@@ -21,3 +22,5 @@
       md5sum: 709872fc2910431b1e8b7074bfe38c67
     - path: output/samtools/test_singleton.fq.gz
       md5sum: 709872fc2910431b1e8b7074bfe38c67
+    - path: output/samtools/versions.yml
+      md5sum: e92d21bbcda2fed7cb438d95c51edff0

tests/subworkflows/nf-core/annotation/ensemblvep/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { ANNOTATION_ENSEMBLVEP } from '../../../../subworkflows/nf-core/annotation_ensemblvep/main'
+include { ANNOTATION_ENSEMBLVEP } from '../../../../../subworkflows/nf-core/annotation/ensemblvep/main'
 
 workflow annotation_ensemblvep {
     input = [
@@ -10,5 +10,5 @@ workflow annotation_ensemblvep {
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
-    ANNOTATION_ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
+    ANNOTATION_ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [], [] )
 }

tests/subworkflows/nf-core/annotation/ensemblvep/nextflow.config

@@ -7,7 +7,7 @@ process {
         publishDir = [ enabled: false ]
     }
 
-    withName: ANNOTATION_BGZIPTABIX {
+    withName: TABIX_BGZIPTABIX {
         ext.prefix = { "${meta.id}_VEP.ann.vcf" }
     }
 

tests/subworkflows/nf-core/annotation/snpeff/main.nf

@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { ANNOTATION_SNPEFF } from '../../../../subworkflows/nf-core/annotation_snpeff/main'
+include { ANNOTATION_SNPEFF } from '../../../../../subworkflows/nf-core/annotation_snpeff/main'
 
 workflow annotation_snpeff {
     input = [

tests/subworkflows/nf-core/annotation/snpeff/nextflow.config

@@ -7,7 +7,7 @@ process {
         publishDir = [ enabled: false ]
     }
 
-    withName: ANNOTATION_BGZIPTABIX {
+    withName: TABIX_BGZIPTABIX {
         ext.prefix = { "${meta.id}_snpEff.ann.vcf" }
     }