Merge branch 'master' into tool/elprep-merge

modules/antismash/antismashlitedownloaddatabases/main.nf

@@ -7,8 +7,9 @@ process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES {
         'quay.io/biocontainers/antismash-lite:6.0.1--pyhdfd78af_1' }"
 
     /*
-    These files are normally downloaded by download-antismash-databases itself, and must be retrieved for input by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines. This is solely for use for CI tests of the nf-core/module version of antiSMASH.
+    These files are normally downloaded/created by download-antismash-databases itself, and must be retrieved for input by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines. This is solely for use for CI tests of the nf-core/module version of antiSMASH.
     Reason: Upon execution, the tool checks if certain database files are present within the container and if not, it tries to create them in /usr/local/bin, for which only root user has write permissions. Mounting those database files with this module prevents the tool from trying to create them.
+    These files are also emitted as output channels in this module to enable the antismash-lite module to use them as mount volumes to the docker/singularity containers.
     */
 
     containerOptions {
@@ -26,6 +27,9 @@ process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES {
 
     output:
     path("antismash_db") , emit: database
+    path("css"), emit: css_dir
+    path("detection"), emit: detection_dir
+    path("modules"), emit: modules_dir
     path "versions.yml", emit: versions
 
     when:
@@ -40,7 +44,7 @@ process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        antismash: \$(antismash --version | sed 's/antiSMASH //')
+        antismash-lite: \$(antismash --version | sed 's/antiSMASH //')
     END_VERSIONS
     """
 }

modules/antismash/antismashlitedownloaddatabases/meta.yml

@@ -27,17 +27,17 @@ input:
   - database_css:
       type: directory
       description: |
-        antismash/outputs/html/css folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the use by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
+        antismash/outputs/html/css folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
       pattern: "css"
   - database_detection:
       type: directory
       description: |
-        antismash/detection folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the use by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
+        antismash/detection folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
       pattern: "detection"
   - database_modules:
       type: directory
       description: |
-        antismash/modules folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the use by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
+        antismash/modules folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
       pattern: "modules"
 
 output:
@@ -50,6 +50,21 @@ output:
       type: directory
       description: Download directory for antiSMASH databases
       pattern: "antismash_db"
+  - css_dir:
+      type: directory
+      description: |
+        antismash/outputs/html/css folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
+      pattern: "css"
+  - detection_dir:
+      type: directory
+      description: |
+        antismash/detection folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
+      pattern: "detection"
+  - modules_dir:
+      type: directory
+      description: |
+        antismash/modules folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
+      pattern: "modules"
 
 authors:
   - "@jasmezz"

modules/custom/getchromsizes/main.nf

@@ -2,10 +2,10 @@ process CUSTOM_GETCHROMSIZES {
     tag "$fasta"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::samtools=1.15" : null)
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/samtools:1.15--h1170115_1' :
-        'quay.io/biocontainers/samtools:1.15--h1170115_1' }"
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
 
     input:
     path fasta

modules/gatk4/haplotypecaller/main.nf

@@ -17,7 +17,7 @@ process GATK4_HAPLOTYPECALLER {
 
     output:
     tuple val(meta), path("*.vcf.gz"), emit: vcf
-    tuple val(meta), path("*.tbi")   , emit: tbi
+    tuple val(meta), path("*.tbi")   , optional:true, emit: tbi
     path "versions.yml"              , emit: versions
 
     when:

modules/gatk4/splitncigarreads/main.nf

@@ -8,7 +8,7 @@ process GATK4_SPLITNCIGARREADS {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(bam)
+    tuple val(meta), path(bam), path(bai), path(intervals)
     path  fasta
     path  fai
     path  dict
@@ -23,6 +23,7 @@ process GATK4_SPLITNCIGARREADS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def interval_command = intervals ? "--intervals $intervals" : ""
 
     def avail_mem = 3
     if (!task.memory) {
@@ -35,6 +36,7 @@ process GATK4_SPLITNCIGARREADS {
         --input $bam \\
         --output ${prefix}.bam \\
         --reference $fasta \\
+        $interval_command \\
         --tmp-dir . \\
         $args
 

modules/gatk4/splitncigarreads/meta.yml

@@ -23,6 +23,13 @@ input:
       type: list
       description: BAM/SAM/CRAM file containing reads
       pattern: "*.{bam,sam,cram}"
+  - bai:
+      type: list
+      description: BAI/SAI/CRAI index file (optional)
+      pattern: "*.{bai,sai,crai}"
+  - intervals:
+      type: file
+      description: Bed file with the genomic regions included in the library (optional)
   - fasta:
       type: file
       description: The reference fasta file

modules/krona/ktimporttext/main.nf

@@ -0,0 +1,34 @@
+process KRONA_KTIMPORTTEXT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::krona=2.8.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/krona:2.8.1--pl5321hdfd78af_1':
+        'quay.io/biocontainers/krona:2.8.1--pl5321hdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(report)
+
+    output:
+    tuple val(meta), path ('*.html'), emit: html
+    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}"
+    """
+    ktImportText  \\
+        $args \\
+        -o ${prefix}.html \\
+        $report
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        krona: \$( echo \$(ktImportText 2>&1) | sed 's/^.*KronaTools //g; s/- ktImportText.*\$//g')
+    END_VERSIONS
+    """
+}

modules/krona/ktimporttext/meta.yml

@@ -0,0 +1,47 @@
+name: "krona_ktimporttext"
+description: Creates a Krona chart from text files listing quantities and lineages.
+keywords:
+  - plot
+  - taxonomy
+  - interactive
+  - html
+  - visualisation
+  - krona chart
+  - metagenomics
+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: http://manpages.ubuntu.com/manpages/impish/man1/ktImportTaxonomy.1.html
+      tool_dev_url: https://github.com/marbl/Krona
+      doi: 10.1186/1471-2105-12-385
+      licence: https://raw.githubusercontent.com/marbl/Krona/master/KronaTools/LICENSE.txt
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+  - report:
+      type: file
+      description: "Tab-delimited text file. Each line should be a number followed by a list of wedges to contribute to (starting from the highest level). If no wedges are listed (and just a quantity is given), it will contribute to the top level. If the same lineage is listed more than once, the values will be added. Quantities can be omitted if -q is specified. Lines beginning with '#' will be ignored."
+      pattern: "*.{txt}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - html:
+      type: file
+      description: A html file containing an interactive krona plot.
+      pattern: "*.{html}"
+
+authors:
+  - "@jianhong"

modules/minimap2/align/main.nf

@@ -2,18 +2,22 @@ process MINIMAP2_ALIGN {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? 'bioconda::minimap2=2.21' : null)
+    conda (params.enable_conda ? 'bioconda::minimap2=2.21 bioconda::samtools=1.12' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/minimap2:2.21--h5bf99c6_0' :
-        'quay.io/biocontainers/minimap2:2.21--h5bf99c6_0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' :
+        'quay.io/biocontainers/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' }"
 
     input:
     tuple val(meta), path(reads)
     path reference
+    val bam_format
+    val cigar_paf_format
+    val cigar_bam
 
     output:
-    tuple val(meta), path("*.paf"), emit: paf
-    path "versions.yml" , emit: versions
+    tuple val(meta), path("*.paf"), optional: true, emit: paf
+    tuple val(meta), path("*.bam"), optional: true, emit: bam
+    path "versions.yml"           , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -22,13 +26,19 @@ process MINIMAP2_ALIGN {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def input_reads = meta.single_end ? "$reads" : "${reads[0]} ${reads[1]}"
+    def bam_output = bam_format ? "-a | samtools sort | samtools view -@ ${task.cpus} -b -h -o ${prefix}.bam" : "-o ${prefix}.paf"
+    def cigar_paf = cigar_paf_format && !sam_format ? "-c" : ''
+    def set_cigar_bam = cigar_bam && sam_format ? "-L" : ''
     """
     minimap2 \\
         $args \\
         -t $task.cpus \\
         $reference \\
         $input_reads \\
-        > ${prefix}.paf
+        $cigar_paf \\
+        $set_cigar_bam \\
+        $bam_output
+
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/minimap2/align/meta.yml

@@ -29,6 +29,17 @@ input:
       type: file
       description: |
         Reference database in FASTA format.
+  - bam_format:
+      type: boolean
+      description: Specify that output should be in BAM format
+  - cigar_paf_format:
+      type: boolean
+      description: Specify that output CIGAR should be in PAF format
+  - cigar_bam:
+      type: boolean
+      description: |
+        Write CIGAR with >65535 ops at the CG tag. This is recommended when
+        doing XYZ (https://github.com/lh3/minimap2#working-with-65535-cigar-operations)
 output:
   - meta:
       type: map
@@ -39,9 +50,16 @@ output:
       type: file
       description: Alignment in PAF format
       pattern: "*.paf"
+  - bam:
+      type: file
+      description: Alignment in BAM format
+      pattern: "*.bam"
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
 authors:
   - "@heuermh"
+  - "@sofstam"
+  - "@sateeshperi"
+  - "@jfy133"

modules/phantompeakqualtools/main.nf

@@ -22,11 +22,12 @@ process PHANTOMPEAKQUALTOOLS {
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
+    def args   = task.ext.args ?: ''
+    def args2  = task.ext.args2 ?: ''
     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"
+    Rscript $args -e "library(caTools); source(\\"\$RUN_SPP\\")" -c="$bam" -savp="${prefix}.spp.pdf" -savd="${prefix}.spp.Rdata" -out="${prefix}.spp.out" $args2
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/rsem/calculateexpression/main.nf

@@ -2,10 +2,10 @@ process RSEM_CALCULATEEXPRESSION {
     tag "$meta.id"
     label 'process_high'
 
-    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null)
+    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' :
-        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' :
+        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }"
 
     input:
     tuple val(meta), path(reads)

modules/rsem/preparereference/main.nf

@@ -2,10 +2,10 @@ process RSEM_PREPAREREFERENCE {
     tag "$fasta"
     label 'process_high'
 
-    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null)
+    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' :
-        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' :
+        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }"
 
     input:
     path fasta, stageAs: "rsem/*"

modules/samtools/bamtocram/main.nf

@@ -0,0 +1,35 @@
+//There is a -L option to only output alignments in interval, might be an option for exons/panel data?
+process SAMTOOLS_BAMTOCRAM {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(input), path(index)
+    path  fasta
+    path  fai
+
+    output:
+    tuple val(meta), path("*.cram"), path("*.crai"), emit: cram_crai
+    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}"
+    """
+    samtools view --threads ${task.cpus} --reference ${fasta} -C $args $input > ${prefix}.cram
+    samtools index -@${task.cpus} ${prefix}.cram
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/samtools/bamtocram/meta.yml

@@ -0,0 +1,52 @@
+name: samtools_bamtocram
+description: filter/convert and then index CRAM file
+keywords:
+  - view
+  - index
+  - bam
+  - cram
+tools:
+  - samtools:
+      description: |
+        SAMtools is a set of utilities for interacting with and post-processing
+        short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+        These files are generated as output by short read aligners like BWA.
+      homepage: http://www.htslib.org/
+      documentation: hhttp://www.htslib.org/doc/samtools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/SAM file
+      pattern: "*.{bam,sam}"
+  - index:
+      type: file
+      description: BAM/SAM index file
+      pattern: "*.{bai,sai}"
+  - fasta:
+      type: file
+      description: Reference file to create the CRAM file
+      pattern: "*.{fasta,fa}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - cram_crai:
+      type: file
+      description: filtered/converted CRAM file + index
+      pattern: "*{.cram,.crai}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+authors:
+  - "@FriederikeHanssen"
+  - "@maxulysse"

modules/tabix/tabix/main.nf

@@ -11,7 +11,8 @@ process TABIX_TABIX {
     tuple val(meta), path(tab)
 
     output:
-    tuple val(meta), path("*.tbi"), emit: tbi
+    tuple val(meta), path("*.tbi"), optional:true, emit: tbi
+    tuple val(meta), path("*.csi"), optional:true, emit: csi
     path  "versions.yml"          , emit: versions
 
     when:

modules/tabix/tabix/meta.yml

@@ -31,6 +31,10 @@ output:
       type: file
       description: tabix index file
       pattern: "*.{tbi}"
+  - csi:
+      type: file
+      description: coordinate sorted index file
+      pattern: "*.{csi}"
   - versions:
       type: file
       description: File containing software versions

modules/tiddit/sv/main.nf

@@ -24,7 +24,7 @@ process TIDDIT_SV {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def reference = fasta == "dummy_file.txt" ? "--ref $fasta" : ""
+    def reference = fasta ? "--ref $fasta" : ""
     """
     tiddit \\
         --sv \\

modules/trimgalore/main.nf

@@ -11,12 +11,13 @@ process TRIMGALORE {
     tuple val(meta), path(reads)
 
     output:
-    tuple val(meta), path("*.fq.gz")    , emit: reads
-    tuple val(meta), path("*report.txt"), emit: log
-    path "versions.yml"                 , emit: versions
+    tuple val(meta), path("*{trimmed,val}*.fq.gz"), emit: reads
+    tuple val(meta), path("*report.txt")          , emit: log
+    path "versions.yml"                           , emit: versions
 
-    tuple val(meta), path("*.html"), emit: html optional true
-    tuple val(meta), path("*.zip") , emit: zip optional true
+    tuple val(meta), path("*unpaired*.fq.gz")     , emit: unpaired, optional: true
+    tuple val(meta), path("*.html")               , emit: html    , optional: true
+    tuple val(meta), path("*.zip")                , emit: zip     , optional: true
 
     when:
     task.ext.when == null || task.ext.when
@@ -52,6 +53,7 @@ process TRIMGALORE {
             $c_r1 \\
             $tpc_r1 \\
             ${prefix}.fastq.gz
+
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":
             trimgalore: \$(echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//')
@@ -73,6 +75,7 @@ process TRIMGALORE {
             $tpc_r2 \\
             ${prefix}_1.fastq.gz \\
             ${prefix}_2.fastq.gz
+
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":
             trimgalore: \$(echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//')

modules/trimgalore/meta.yml

@@ -37,6 +37,11 @@ output:
         List of input adapter trimmed FastQ files of size 1 and 2 for
         single-end and paired-end data, respectively.
       pattern: "*.{fq.gz}"
+  - unpaired:
+      type: file
+      description: |
+        FastQ files containing unpaired reads from read 1 or read 2
+      pattern: "*unpaired*.fq.gz"
   - html:
       type: file
       description: FastQC report (optional)

tests/config/pytest_modules.yml

@@ -1054,6 +1054,10 @@ krona/ktimporttaxonomy:
   - modules/krona/ktimporttaxonomy/**
   - tests/modules/krona/ktimporttaxonomy/**
 
+krona/ktimporttext:
+  - modules/krona/ktimporttext/**
+  - tests/modules/krona/ktimporttext/**
+
 last/dotplot:
   - modules/last/dotplot/**
   - tests/modules/last/dotplot/**
@@ -1599,6 +1603,10 @@ samtools/bam2fq:
   - modules/samtools/bam2fq/**
   - tests/modules/samtools/bam2fq/**
 
+samtools/bamtocram:
+  - modules/samtools/bamtocram/**
+  - tests/modules/samtools/bamtocram/**
+
 samtools/collatefastq:
   - modules/samtools/collatefastq/**
   - tests/modules/samtools/collatefastq/**

tests/config/test_data.config

@@ -109,6 +109,9 @@ params {
 
                 test_sequencing_summary                        = "${test_data_dir}/genomics/sarscov2/nanopore/sequencing_summary/test.sequencing_summary.txt"
             }
+            'metagenome' {
+                kraken_report                                  = "${test_data_dir}/genomics/sarscov2/metagenome/test_1.kraken2.report.txt"
+            }
         }
         'homo_sapiens' {
             'genome' {
@@ -245,8 +248,8 @@ params {
                 test2_2_fastq_gz                               = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
                 test2_umi_1_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
                 test2_umi_2_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
-                test_rnaseq_1_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.rnaseq_1.fastq.gz"
-                test_rnaseq_2_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.rnaseq_2.fastq.gz"
+                test_rnaseq_1_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz"
+                test_rnaseq_2_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz"
 
                 test_baserecalibrator_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
                 test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"

tests/modules/antismash/antismashlitedownloaddatabases/test.yml

@@ -1,14 +1,17 @@
 - name: antismash antismashlitedownloaddatabases test_antismash_antismashlitedownloaddatabases
   command: nextflow run tests/modules/antismash/antismashlitedownloaddatabases -entry test_antismash_antismashlitedownloaddatabases -c tests/config/nextflow.config
   tags:
-    - antismash/antismashlitedownloaddatabases
     - antismash
+    - antismash/antismashlitedownloaddatabases
   files:
     - path: output/antismash/versions.yml
-      md5sum: e2656c8d2bcc7469eba40eb1ee5c91b3
+      md5sum: 24859c67023abab99de295d3675a24b6
     - path: output/antismash/antismash_db
     - path: output/antismash/antismash_db/clusterblast
     - path: output/antismash/antismash_db/clustercompare
     - path: output/antismash/antismash_db/pfam
     - path: output/antismash/antismash_db/resfam
     - path: output/antismash/antismash_db/tigrfam
+    - path: output/antismash/css
+    - path: output/antismash/detection
+    - path: output/antismash/modules

tests/modules/gatk4/splitncigarreads/main.nf

@@ -6,7 +6,23 @@ include { GATK4_SPLITNCIGARREADS } from '../../../../modules/gatk4/splitncigarre
 
 workflow test_gatk4_splitncigarreads {
     input = [ [ id:'test' ], // meta map
-              [ file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ] 
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true),
+                [],
+                []
+            ]
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_SPLITNCIGARREADS ( input, fasta, fai, dict )
+}
+
+workflow test_gatk4_splitncigarreads_intervals {
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
             ]
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)

tests/modules/gatk4/splitncigarreads/test.yml

@@ -5,5 +5,14 @@
     - gatk4/splitncigarreads
   files:
     - path: output/gatk4/test.bam
-      md5sum: ceed15c0bd64ff5c38d3816905933b0b
+      md5sum: 436d8e31285c6b588bdd1c7f1d07f6f2
+    - path: output/gatk4/versions.yml
+- name: gatk4 splitncigarreads test_gatk4_splitncigarreads_intervals
+  command: nextflow run tests/modules/gatk4/splitncigarreads -entry test_gatk4_splitncigarreads_intervals -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/splitncigarreads
+  files:
+    - path: output/gatk4/test.bam
+      md5sum: cd56e3225950f519fd47164cca60a0bb
     - path: output/gatk4/versions.yml

tests/modules/krona/ktimporttext/main.nf

@@ -0,0 +1,31 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { KRONA_KTIMPORTTEXT } from '../../../../modules/krona/ktimporttext/main.nf'
+
+workflow test_krona_ktimporttext_multi {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/krona/ktimporttext.txt', checkIfExists: true), // krona default test file
+            file(params.test_data['sarscov2']['metagenome']['kraken_report'], checkIfExists: true), //Kraken2 report file
+            file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/krona/kaiju_out4krona.txt', checkIfExists: true) // Kaiju output 4 krona
+        ]
+    ]
+
+    KRONA_KTIMPORTTEXT ( input )
+}
+
+workflow test_krona_ktimporttext_single {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file('http://krona.sourceforge.net/examples/text.txt', checkIfExists: true) // krona default test file
+        ]
+    ]
+
+    KRONA_KTIMPORTTEXT ( input )
+}

tests/modules/krona/ktimporttext/nextflow.config

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

tests/modules/krona/ktimporttext/test.yml

@@ -0,0 +1,19 @@
+- name: krona ktimporttext test_krona_ktimporttext_multi
+  command: nextflow run tests/modules/krona/ktimporttext -entry test_krona_ktimporttext_multi -c tests/config/nextflow.config
+  tags:
+    - krona
+    - krona/ktimporttext
+  files:
+    - path: output/krona/test.html
+      contains:
+        - "DOCTYPE html PUBLIC"
+
+- name: krona ktimporttext test_krona_ktimporttext_single
+  command: nextflow run tests/modules/krona/ktimporttext -entry test_krona_ktimporttext_single -c tests/config/nextflow.config
+  tags:
+    - krona
+    - krona/ktimporttext
+  files:
+    - path: output/krona/test.html
+      contains:
+        - "DOCTYPE html PUBLIC"

tests/modules/minimap2/align/main.nf

@@ -9,8 +9,11 @@ workflow test_minimap2_align_single_end {
               [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
             ]
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    bam_format = true
+    cigar_paf_format = false
+    cigar_bam = false
 
-    MINIMAP2_ALIGN ( input, fasta )
+    MINIMAP2_ALIGN ( input, fasta, bam_format, cigar_paf_format, cigar_bam)
 }
 
 workflow test_minimap2_align_paired_end {
@@ -19,6 +22,9 @@ workflow test_minimap2_align_paired_end {
                 file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
             ]
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    bam_format  = true
+    cigar_paf_format = false
+    cigar_bam = false
 
-    MINIMAP2_ALIGN ( input, fasta )
+    MINIMAP2_ALIGN ( input, fasta, bam_format, cigar_paf_format, cigar_bam )
 }

tests/modules/minimap2/align/test.yml

@@ -1,17 +1,17 @@
-- name: minimap2 align single-end
-  command: nextflow run ./tests/modules/minimap2/align -entry test_minimap2_align_single_end -c ./tests/config/nextflow.config -c ./tests/modules/minimap2/align/nextflow.config
+- name: minimap2 align test_minimap2_align_single_end
+  command: nextflow run tests/modules/minimap2/align -entry test_minimap2_align_single_end -c tests/config/nextflow.config
   tags:
     - minimap2
     - minimap2/align
   files:
-    - path: ./output/minimap2/test.paf
-      md5sum: 70e8cf299ee3ecd33e629d10c1f588ce
+    - path: output/minimap2/test.bam
+    - path: output/minimap2/versions.yml
 
-- name: minimap2 align paired-end
-  command: nextflow run ./tests/modules/minimap2/align -entry test_minimap2_align_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/minimap2/align/nextflow.config
+- name: minimap2 align test_minimap2_align_paired_end
+  command: nextflow run tests/modules/minimap2/align -entry test_minimap2_align_paired_end -c tests/config/nextflow.config
   tags:
     - minimap2
     - minimap2/align
   files:
-    - path: ./output/minimap2/test.paf
-      md5sum: 5e7b55a26bf0ea3a2843423d3e0b9a28
+    - path: output/minimap2/test.bam
+    - path: output/minimap2/versions.yml

tests/modules/rsem/calculateexpression/test.yml

@@ -42,7 +42,7 @@
     - path: output/rsem/rsem/genome.transcripts.fa
       md5sum: 050c521a2719c2ae48267c1e65218f29
     - path: output/rsem/rsem/genomeParameters.txt
-      md5sum: 2fe3a030e1706c3e8cd4df3818e6dd2f
+      md5sum: df5a456e3242520cc36e0083a6a7d9dd
     - path: output/rsem/rsem/sjdbInfo.txt
       md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
     - path: output/rsem/rsem/sjdbList.fromGTF.out.tab
@@ -63,4 +63,4 @@
     - path: output/rsem/test.stat/test.theta
       md5sum: de2e4490c98cc5383a86ae8225fd0a28
     - path: output/rsem/test.transcript.bam
-      md5sum: 7846491086c478858419667d60f18edd
+      md5sum: ed681d39f5700ffc74d6321525330d93

tests/modules/samtools/bamtocram/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_BAMTOCRAM } from '../../../../modules/samtools/bamtocram/main.nf'
+
+workflow test_samtools_bamtocram {
+
+    input = [ [ id:'test', single_end:false ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)]
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai   = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    SAMTOOLS_BAMTOCRAM ( input, fasta, fai )
+}

tests/modules/samtools/bamtocram/nextflow.config

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

tests/modules/samtools/bamtocram/test.yml

@@ -0,0 +1,9 @@
+- name: samtools bamtocram test_samtools_bamtocram
+  command: nextflow run ./tests/modules/samtools/bamtocram -entry test_samtools_bamtocram -c ./tests/config/nextflow.config -c ./tests/modules/samtools/bamtocram/nextflow.config
+  tags:
+    - samtools/bamtocram
+    - samtools
+  files:
+    - path: output/samtools/test.cram
+    - path: output/samtools/test.cram.crai
+    - path: output/samtools/versions.yml

tests/modules/tabix/tabix/main.nf

@@ -2,9 +2,10 @@
 
 nextflow.enable.dsl = 2
 
-include { TABIX_TABIX as TABIX_BED } from '../../../../modules/tabix/tabix/main.nf'
-include { TABIX_TABIX as TABIX_GFF } from '../../../../modules/tabix/tabix/main.nf'
-include { TABIX_TABIX as TABIX_VCF } from '../../../../modules/tabix/tabix/main.nf'
+include { TABIX_TABIX as TABIX_BED     } from '../../../../modules/tabix/tabix/main.nf'
+include { TABIX_TABIX as TABIX_GFF     } from '../../../../modules/tabix/tabix/main.nf'
+include { TABIX_TABIX as TABIX_VCF_TBI } from '../../../../modules/tabix/tabix/main.nf'
+include { TABIX_TABIX as TABIX_VCF_CSI } from '../../../../modules/tabix/tabix/main.nf'
 
 workflow test_tabix_tabix_bed {
     input = [ [ id:'B.bed' ], // meta map
@@ -22,10 +23,18 @@ workflow test_tabix_tabix_gff {
     TABIX_GFF ( input )
 }
 
-workflow test_tabix_tabix_vcf {
+workflow test_tabix_tabix_vcf_tbi {
     input = [ [ id:'test.vcf' ], // meta map
               [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true) ] 
             ]
 
-    TABIX_VCF ( input )
+    TABIX_VCF_TBI ( input )
+}
+
+workflow test_tabix_tabix_vcf_csi {
+    input = [ [ id:'test.vcf' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true) ]
+            ]
+
+    TABIX_VCF_CSI ( input )
 }

tests/modules/tabix/tabix/nextflow.config

@@ -10,8 +10,12 @@ process {
         ext.args = '-p gff'
     }
 
-    withName: TABIX_VCF {
+    withName: TABIX_VCF_TBI {
         ext.args = '-p vcf'
     }
 
+   withName: TABIX_VCF_CSI {
+        ext.args = '-p vcf --csi'
+    }
+
 }

tests/modules/tabix/tabix/test.yml

@@ -15,10 +15,18 @@
     - path: ./output/tabix/genome.gff3.gz.tbi
       md5sum: f79a67d95a98076e04fbe0455d825926
 - name: tabix tabix vcf
-  command: nextflow run ./tests/modules/tabix/tabix -entry test_tabix_tabix_vcf -c ./tests/config/nextflow.config -c ./tests/modules/tabix/tabix/nextflow.config
+  command: nextflow run ./tests/modules/tabix/tabix -entry test_tabix_tabix_vcf_tbi -c ./tests/config/nextflow.config -c ./tests/modules/tabix/tabix/nextflow.config
   tags:
     - tabix
     - tabix/tabix
   files:
     - path: output/tabix/test.vcf.gz.tbi
       md5sum: 36e11bf96ed0af4a92caa91a68612d64
+- name: tabix tabix vcf csi
+  command: nextflow run ./tests/modules/tabix/tabix -entry test_tabix_tabix_vcf_csi -c ./tests/config/nextflow.config -c ./tests/modules/tabix/tabix/nextflow.config
+  tags:
+    - tabix
+    - tabix/tabix
+  files:
+    - path: output/tabix/test.vcf.gz.csi
+      md5sum: 5f930522d2b9dcdba2807b7da4dfa3fd

tests/modules/tiddit/sv/test.yml

@@ -9,6 +9,7 @@
     - path: output/tiddit/test.signals.tab
       md5sum: dab4b2fec4ddf8eb1c23005b0770150e
     - path: output/tiddit/test.vcf
+      md5sum: bdce14ae8292bf3deb81f6f255baf859
 
 - name: tiddit sv no ref
   command: nextflow run ./tests/modules/tiddit/sv -entry test_tiddit_sv_no_ref -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/sv/nextflow.config
@@ -21,3 +22,4 @@
     - path: output/tiddit/test.signals.tab
       md5sum: dab4b2fec4ddf8eb1c23005b0770150e
     - path: output/tiddit/test.vcf
+      md5sum: 3d0e83a8199b2bdb81cfe3e6b12bf64b