Merge branch 'nf-core:master' into master

.github/PULL_REQUEST_TEMPLATE.md

@@ -27,6 +27,6 @@ Closes #XXX <!-- If this PR fixes an issue, please link it here! -->
 - [ ] Add a resource `label`
 - [ ] Use BioConda and BioContainers if possible to fulfil software requirements.
 - Ensure that the test works with either Docker / Singularity. Conda CI tests can be quite flaky:
-    - [ ] `PROFILE=docker pytest --tag <MODULE> --symlink --keep-workflow-wd`
-    - [ ] `PROFILE=singularity pytest --tag <MODULE> --symlink --keep-workflow-wd`
-    - [ ] `PROFILE=conda pytest --tag <MODULE> --symlink --keep-workflow-wd`
+    - [ ] `PROFILE=docker pytest --tag <MODULE> --symlink --keep-workflow-wd --git-aware`
+    - [ ] `PROFILE=singularity pytest --tag <MODULE> --symlink --keep-workflow-wd --git-aware`
+    - [ ] `PROFILE=conda pytest --tag <MODULE> --symlink --keep-workflow-wd --git-aware`

.github/workflows/pytest-workflow.yml

@@ -86,7 +86,7 @@ jobs:
       # Test the module
       - name: Run pytest-workflow
         # only use one thread for pytest-workflow to avoid race condition on conda cache.
-        run: TMPDIR=~ PROFILE=${{ matrix.profile }} pytest --tag ${{ matrix.tags }} --symlink --kwdof
+        run: TMPDIR=~ PROFILE=${{ matrix.profile }} pytest --tag ${{ matrix.tags }} --symlink --kwdof --git-aware
 
       - name: Output log on failure
         if: failure()

modules/chromap/chromap/main.nf

@@ -2,10 +2,10 @@ process CHROMAP_CHROMAP {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::chromap=0.1.5 bioconda::samtools=1.14" : null)
+    conda (params.enable_conda ? "bioconda::chromap=0.2.0 bioconda::samtools=1.14" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:724a1037d59f6a19c9d4e7bdba77b52b37de0dc3-0' :
-        'quay.io/biocontainers/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:724a1037d59f6a19c9d4e7bdba77b52b37de0dc3-0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:ed3529ef5253d7ccbc688b6a4c5c447152685757-0' :
+        'quay.io/biocontainers/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:ed3529ef5253d7ccbc688b6a4c5c447152685757-0' }"
 
     input:
     tuple val(meta), path(reads)

modules/chromap/index/main.nf

@@ -2,11 +2,10 @@ process CHROMAP_INDEX {
     tag '$fasta'
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::chromap=0.1.5" : null)
+    conda (params.enable_conda ? "bioconda::chromap=0.2.0" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/chromap:0.1.5--h9a82719_0' :
-        'quay.io/biocontainers/chromap:0.1.5--h9a82719_0' }"
-
+        'https://depot.galaxyproject.org/singularity/chromap:0.2.0--hd03093a_1' :
+        'quay.io/biocontainers/chromap:0.2.0--hd03093a_1' }"
 
     input:
     path fasta

modules/malt/run/main.nf

@@ -23,6 +23,7 @@ process MALT_RUN {
 
     script:
     def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
     def avail_mem = 6
     if (!task.memory) {
         log.info '[MALT_RUN] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
@@ -39,7 +40,7 @@ process MALT_RUN {
         $args \\
         --inFile ${fastqs.join(' ')} \\
         -m $mode \\
-        --index $index/ |&tee malt-run.log
+        --index $index/ |&tee ${prefix}-malt-run.log
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/malt/run/meta.yml

@@ -52,7 +52,7 @@ output:
   - log:
       type: file
       description: Log of verbose MALT stdout
-      pattern: "malt-run.log"
+      pattern: "*-malt-run.log"
 
 authors:
   - "@jfy133"

modules/maxbin2/main.nf

@@ -29,8 +29,9 @@ process MAXBIN2 {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def associate_files = reads ? "-reads $reads" : "-abund $abund"
     """
+    mkdir input/ && mv $contigs input/
     run_MaxBin.pl \\
-        -contig $contigs \\
+        -contig input/$contigs \\
         $associate_files \\
         -thread $task.cpus \\
         $args \\

modules/picard/sortvcf/main.nf

@@ -0,0 +1,49 @@
+process PICARD_SORTVCF {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::picard=2.26.10" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' :
+        'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+    path reference
+    path sequence_dict
+
+    output:
+    tuple val(meta), path("*_sorted.vcf.gz"), emit: 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}"
+    def seq_dict = sequence_dict ? "-SEQUENCE_DICTIONARY $sequence_dict" : ""
+    def reference = reference ? "-REFERENCE_SEQUENCE $reference" : ""
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[Picard SortVcf] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    picard \\
+        SortVcf \\
+        -Xmx${avail_mem}g \\
+        --INPUT $vcf \\
+        $args \\
+        $seq_dict \\
+        $reference \\
+        --OUTPUT ${prefix}_sorted.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        picard: \$(picard SortVcf --version 2>&1 | grep -o 'Version:.*' | cut -f2- -d:)
+    END_VERSIONS
+    """
+}

modules/picard/sortvcf/meta.yml

@@ -0,0 +1,40 @@
+name: picard_sortvcf
+description: Sorts vcf files
+keywords:
+  - sort
+  - vcf
+tools:
+  - picard:
+      description: Java tools for working with NGS data in the BAM/CRAM/SAM and VCF format
+      homepage: https://broadinstitute.github.io/picard/
+      documentation: https://broadinstitute.github.io/picard/command-line-overview.html#SortVcf
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF file
+      pattern: "*.{vcf,vcf.gz}"
+
+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"
+  - vcf:
+      type: file
+      description: Sorted VCF file
+      pattern: "*.{vcf}"
+
+authors:
+  - "@ramprasadn"

modules/plink2/score/main.nf

@@ -0,0 +1,39 @@
+process PLINK2_SCORE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::plink2=2.00a2.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/plink2:2.00a2.3--h712d239_1' :
+        'quay.io/biocontainers/plink2:2.00a2.3--h712d239_1' }"
+
+    input:
+    tuple val(meta), path(pgen), path(psam), path(pvar)
+    path(scorefile)
+
+    output:
+    tuple val(meta), path("*.sscore"), emit: score
+    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 mem_mb = task.memory.toMega() // plink is greedy
+    """
+    plink2 \\
+        --threads $task.cpus \\
+        --memory $mem_mb \\
+        --pfile ${pgen.baseName} vzs \\
+        --score ${scorefile} \\
+        $args \\
+        --out ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink2: \$(plink2 --version 2>&1 | sed 's/^PLINK v//; s/ 64.*\$//' )
+    END_VERSIONS
+    """
+}

modules/plink2/score/meta.yml

@@ -0,0 +1,56 @@
+name: plink2_score
+description: Apply a scoring system to each sample in a plink 2 fileset
+keywords:
+  - plink2
+  - score
+tools:
+  - plink2:
+      description: |
+          Whole genome association analysis toolset, designed to perform a range
+          of basic, large-scale analyses in a computationally efficient manner
+      homepage: http://www.cog-genomics.org/plink/2.0/
+      documentation: http://www.cog-genomics.org/plink/2.0/general_usage
+      tool_dev_url: None
+      doi: "10.1186/s13742-015-0047-8"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - pgen:
+      type: file
+      description: PLINK 2 binary genotype table
+      pattern: "*.{pgen}"
+  - psam:
+      type: file
+      description: PLINK 2 sample information file
+      pattern: "*.{psam}"
+  - pvar:
+      type: file
+      description: PLINK 2 variant information file
+      pattern: "*.{pvar}"
+  - scorefile:
+      type: file
+      description: A text file containing variant identifiers and weights
+      pattern: "*.{scores,txt,scorefile}"
+
+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"
+  - score:
+      type: file
+      description: A text file containing sample scores, in plink 2 .sscore format
+      pattern: "*.{sscore}"
+
+authors:
+  - "@nebfield"

modules/seqkit/replace/main.nf

@@ -0,0 +1,41 @@
+process SEQKIT_REPLACE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::seqkit=2.1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/seqkit:2.1.0--h9ee0642_0':
+        'quay.io/biocontainers/seqkit:2.1.0--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(fastx)
+
+    output:
+    tuple val(meta), path("*.fast*"), emit: fastx
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def extension = "fastq"
+    if ("$fastx" ==~ /.+\.fasta|.+\.fasta.gz|.+\.fa|.+\.fa.gz|.+\.fas|.+\.fas.gz|.+\.fna|.+\.fna.gz/) {
+        extension = "fasta"
+    }
+    def endswith = task.ext.suffix ?: "${extension}.gz"
+    """
+    seqkit \\
+        replace \\
+        ${args} \\
+        --threads ${task.cpus} \\
+        -i ${fastx} \\
+        -o ${prefix}.${endswith}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqkit: \$( seqkit | sed '3!d; s/Version: //' )
+    END_VERSIONS
+    """
+}

modules/seqkit/replace/meta.yml

@@ -0,0 +1,41 @@
+name: seqkit_replace
+description: Use seqkit to find/replace strings within sequences and sequence headers
+keywords:
+  - seqkit
+  - replace
+tools:
+  - seqkit:
+      description: Cross-platform and ultrafast toolkit for FASTA/Q file manipulation, written by Wei Shen.
+      homepage: https://bioinf.shenwei.me/seqkit/usage/
+      documentation: https://bioinf.shenwei.me/seqkit/usage/
+      tool_dev_url: https://github.com/shenwei356/seqkit/
+      doi: "10.1371/journal.pone.016396"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fastx:
+      type: file
+      description: fasta/q file
+      pattern: "*.{fasta,fastq,fa,fq,fas,fna,faa}*"
+
+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"
+  - fastx:
+      type: file
+      description: fasta/q file with replaced values
+      pattern: "*.{fasta,fastq,fa,fq,fas,fna,faa}*"
+
+authors:
+  - "@mjcipriano"

modules/seqtk/seq/main.nf

@@ -33,8 +33,8 @@ process SEQTK_SEQ {
         gzip -c > ${prefix}.seqtk-seq.${extension}.gz
 
     cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            seqtk: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
+    "${task.process}":
+        seqtk: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//')
     END_VERSIONS
     """
 }

modules/yara/mapper/main.nf

@@ -13,6 +13,7 @@ process YARA_MAPPER {
 
     output:
     tuple val(meta), path("*.mapped.bam"), emit: bam
+    tuple val(meta), path("*.mapped.bam.bai"), emit: bai
     path "versions.yml"                  , emit: versions
 
     when:
@@ -28,7 +29,9 @@ process YARA_MAPPER {
             -t $task.cpus \\
             -f bam \\
             ${index}/yara \\
-            $reads | samtools view -@ $task.cpus -hb -F4 > ${prefix}.mapped.bam
+            $reads | samtools view -@ $task.cpus -hb -F4 | samtools sort -@ $task.cpus > ${prefix}.mapped.bam
+
+        samtools index -@ $task.cpus ${prefix}.mapped.bam
 
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":
@@ -46,8 +49,11 @@ process YARA_MAPPER {
             ${reads[0]} \\
             ${reads[1]} > output.bam
 
-        samtools view -@ $task.cpus -hF 4 -f 0x40 -b output.bam > ${prefix}_1.mapped.bam
-        samtools view -@ $task.cpus -hF 4 -f 0x80 -b output.bam > ${prefix}_2.mapped.bam
+        samtools view -@ $task.cpus -hF 4 -f 0x40 -b output.bam | samtools sort -@ $task.cpus > ${prefix}_1.mapped.bam
+        samtools view -@ $task.cpus -hF 4 -f 0x80 -b output.bam | samtools sort -@ $task.cpus > ${prefix}_2.mapped.bam
+
+        samtools index -@ $task.cpus ${prefix}_1.mapped.bam
+        samtools index -@ $task.cpus ${prefix}_2.mapped.bam
 
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":

modules/yara/mapper/meta.yml

@@ -45,6 +45,10 @@ output:
       type: file
       description: Sorted BAM file
       pattern: "*.{bam}"
+  - bai:
+      type: file
+      description: Sorted BAM file index
+      pattern: "*.{bai}"
 
 authors:
   - "@apeltzer"

tests/config/pytest_modules.yml

@@ -1249,6 +1249,10 @@ picard/sortsam:
   - modules/picard/sortsam/**
   - tests/modules/picard/sortsam/**
 
+picard/sortvcf:
+  - modules/picard/sortvcf/**
+  - tests/modules/picard/sortvcf/**
+
 pirate:
   - modules/pirate/**
   - tests/modules/pirate/**
@@ -1269,6 +1273,10 @@ plink2/extract:
   - modules/plink2/extract/**
   - tests/modules/plink2/extract/**
 
+plink2/score:
+  - modules/plink2/score/**
+  - tests/modules/plink2/score/**
+
 plink2/vcf:
   - modules/plink2/vcf/**
   - tests/modules/plink2/vcf/**
@@ -1473,6 +1481,10 @@ seqkit/pair:
   - modules/seqkit/pair/**
   - tests/modules/seqkit/pair/**
 
+seqkit/replace:
+  - modules/seqkit/replace/**
+  - tests/modules/seqkit/replace/**
+
 seqkit/split2:
   - modules/seqkit/split2/**
   - tests/modules/seqkit/split2/**

tests/config/test_data.config

@@ -119,7 +119,7 @@ params {
                 genome_bed_gz_tbi                              = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed.gz.tbi"
                 transcriptome_fasta                            = "${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"
+                genome_chain_gz                                = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz"
                 genome_21_fasta                                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
                 genome_21_fasta_fai                            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
                 genome_21_dict                                 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
@@ -138,6 +138,7 @@ params {
                 mills_and_1000g_indels_vcf_gz_tbi              = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
                 syntheticvcf_short_vcf_gz                      = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.vcf.gz"
                 syntheticvcf_short_vcf_gz_tbi                  = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.vcf.gz.tbi"
+                syntheticvcf_short_score                       = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.score"
                 gnomad_r2_1_1_sv_vcf_gz                        = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1-sv.vcf.gz"
 
                 hapmap_3_3_hg38_21_vcf_gz                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz"

tests/modules/chromap/chromap/test.yml

@@ -7,6 +7,8 @@
     - path: output/chromap/genome.index
     - path: output/chromap/test.bed.gz
       md5sum: 25e40bde24c7b447292cd68573728694
+    - path: output/chromap/versions.yml
+      md5sum: 2d3d2959ac20d98036807964896829e7
 
 - name: chromap chromap test_chromap_chromap_paired_end
   command: nextflow run ./tests/modules/chromap/chromap -entry test_chromap_chromap_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/chromap/chromap/nextflow.config
@@ -17,6 +19,8 @@
     - path: output/chromap/genome.index
     - path: output/chromap/test.bed.gz
       md5sum: 7cdc8448882b75811e0c784f5f20aef2
+    - path: output/chromap/versions.yml
+      md5sum: 51cff66779161d8a602cce5989017395
 
 - name: chromap chromap test_chromap_chromap_paired_bam
   command: nextflow run ./tests/modules/chromap/chromap -entry test_chromap_chromap_paired_bam -c ./tests/config/nextflow.config -c ./tests/modules/chromap/chromap/nextflow.config
@@ -26,4 +30,6 @@
   files:
     - path: output/chromap/genome.index
     - path: output/chromap/test.bam
-      md5sum: 73e2c76007e3c61df625668e01b3f42f
+      md5sum: f255c7441d5a1f307fc642d2aa19647e
+    - path: output/chromap/versions.yml
+      md5sum: f91910c44169549c3923931de5c3afcb

tests/modules/chromap/index/test.yml

@@ -5,3 +5,5 @@
     - chromap
   files:
     - path: output/chromap/genome.index
+    - path: output/chromap/versions.yml
+      md5sum: b75dec647f9dc5f4887f36d1db7a9ccd

tests/modules/malt/run/test.yml

@@ -5,4 +5,4 @@
     - malt/run
   files:
     - path: output/malt/test_1.rma6
-    - path: output/malt/malt-run.log
+    - path: output/malt/test-malt-run.log

tests/modules/picard/sortvcf/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PICARD_SORTVCF } from '../../../../modules/picard/sortvcf/main.nf'
+
+workflow test_picard_sortvcf {
+
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+            ]
+
+    fasta  = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    dict  = [ file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true) ]
+
+    PICARD_SORTVCF ( input, fasta, dict )
+}

tests/modules/picard/sortvcf/nextflow.config

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

tests/modules/picard/sortvcf/test.yml

@@ -0,0 +1,7 @@
+- name: picard sortvcf
+  command: nextflow run ./tests/modules/picard/sortvcf -entry test_picard_sortvcf -c ./tests/config/nextflow.config -c ./tests/modules/picard/sortvcf/nextflow.config
+  tags:
+    - picard
+    - picard/sortvcf
+  files:
+    - path: output/picard/test_sorted.vcf.gz

tests/modules/plink2/score/main.nf

@@ -0,0 +1,24 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PLINK2_VCF } from '../../../../modules/plink2/vcf/main.nf'
+include { PLINK2_SCORE } from '../../../../modules/plink2/score/main.nf'
+
+workflow test_plink2_score {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['syntheticvcf_short_vcf_gz'], checkIfExists: true)
+    ]
+    PLINK2_VCF ( input )
+
+    scorefile = file(params.test_data['homo_sapiens']['genome']['syntheticvcf_short_score'], checkIfExists: true)
+
+    PLINK2_VCF.out.pgen
+        .concat(PLINK2_VCF.out.psam, PLINK2_VCF.out.pvar)
+        .groupTuple()
+        .map { it.flatten() }
+        .set { ch_target_genome }
+
+    PLINK2_SCORE ( ch_target_genome, scorefile )
+}

tests/modules/plink2/score/nextflow.config

@@ -0,0 +1,15 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    // relabel input variants to a common scheme chr:pos:alt:ref
+    withName: PLINK2_VCF {
+        ext.args = '--set-missing-var-ids @:#:\\$1:\\$2'
+    }
+
+    // scoring really needs an adjustment for small test dataset (n > 50
+    // normally)
+    withName: PLINK2_SCORE {
+        ext.args = 'no-mean-imputation'
+    }
+}

tests/modules/plink2/score/test.yml

@@ -0,0 +1,16 @@
+- name: plink2 score test_plink2_score
+  command: nextflow run tests/modules/plink2/score -entry test_plink2_score -c tests/config/nextflow.config
+  tags:
+    - plink2
+    - plink2/score
+  files:
+    - path: output/plink2/test.pgen
+      md5sum: fac12ca9041d6950f6b7d60ac2120721
+    - path: output/plink2/test.psam
+      md5sum: e6c714488754cb8448c3dfda08c4c0ea
+    - path: output/plink2/test.pvar.zst
+      md5sum: 98d59e9779a8b62d5032cd98b642a63b
+    - path: output/plink2/test.sscore
+      md5sum: 97bde840f69febd65f2c00e9243126e9
+    - path: output/plink2/versions.yml
+      md5sum: 71499ab14e1583c88ced3a7a4f05bfa7

tests/modules/seqkit/replace/main.nf

@@ -0,0 +1,24 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQKIT_REPLACE } from '../../../../modules/seqkit/replace/main.nf'
+include { SEQKIT_REPLACE as SEQKIT_REPLACEUNCOMP } from '../../../../modules/seqkit/replace/main.nf'
+
+workflow test_seqkit_replace {
+
+    input = [ [ id:'test' ],   // meta map
+              [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+            ]
+
+    SEQKIT_REPLACE ( input )
+}
+
+workflow test_seqkit_replace_uncomp {
+
+    input = [ [ id:'test' ],   // meta map
+              [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+            ]
+
+    SEQKIT_REPLACEUNCOMP ( input )
+}

tests/modules/seqkit/replace/nextflow.config

@@ -0,0 +1,14 @@
+process {
+
+    withName: 'SEQKIT_REPLACE' {
+        ext.args   = "-s -p 'A' -r 'N'"
+        publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    }
+
+    withName: 'SEQKIT_REPLACEUNCOMP' {
+        ext.args          = "-s -p 'T' -r 'N'"
+        ext.suffix        = ".fasta"
+        publishDir        = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    }
+
+}

tests/modules/seqkit/replace/test.yml

@@ -0,0 +1,21 @@
+- name: seqkit replace test_seqkit_replace
+  command: nextflow run tests/modules/seqkit/replace -entry test_seqkit_replace -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit/replace
+  files:
+    - path: output/seqkit/test.fasta.gz
+      md5sum: 053847219695c0a923d02352442d7abf
+    - path: output/seqkit/versions.yml
+      md5sum: dc9d18b7836c9db00a3032fd191bd831
+
+- name: seqkit replace test_seqkit_replace_uncomp
+  command: nextflow run tests/modules/seqkit/replace -entry test_seqkit_replace_uncomp -c tests/config/nextflow.config
+  tags:
+    - seqkit
+    - seqkit/replace
+  files:
+    - path: output/seqkit/test..fasta
+      md5sum: 05d3294a62c72f5489f067c1da3c2f6c
+    - path: output/seqkit/versions.yml
+      md5sum: 3b88128487ec949f0bdeecebc375c407

tests/modules/seqtk/seq/test.yml

@@ -7,7 +7,7 @@
     - path: output/seqtk/test.seqtk-seq.fasta.gz
       md5sum: 50d73992c8c7e56dc095ef47ec52a754
     - path: output/seqtk/versions.yml
-      md5sum: 2b89cd4a6e28f35fcfbbd2188384f944
+      md5sum: 6555e1061080c44f828de0b40b299e41
 
 - name: seqtk seq test_seqtk_seq_fq
   command: nextflow run tests/modules/seqtk/seq -entry test_seqtk_seq_fq -c tests/config/nextflow.config
@@ -18,4 +18,4 @@
     - path: output/seqtk/test.seqtk-seq.fasta.gz
       md5sum: 2f009f1647971a97b4edec726a99dc1a
     - path: output/seqtk/versions.yml
-      md5sum: 3467a76d3540bee8f58de050512bddaa
+      md5sum: feb70feb3165d5c19fa50c16e46e6772

tests/modules/yara/mapper/test.yml

@@ -5,6 +5,7 @@
     - yara
   files:
     - path: output/yara/test.mapped.bam
+    - path: output/yara/test.mapped.bam.bai
     - path: output/yara/yara/yara.txt.size
       md5sum: 063987b3c3f747be7d2b8043c9d91000
     - path: output/yara/yara/yara.lf.drs
@@ -39,7 +40,9 @@
     - yara
   files:
     - path: output/yara/test_2.mapped.bam
+    - path: output/yara/test_2.mapped.bam.bai
     - path: output/yara/test_1.mapped.bam
+    - path: output/yara/test_1.mapped.bam.bai
     - path: output/yara/yara/yara.txt.size
       md5sum: 063987b3c3f747be7d2b8043c9d91000
     - path: output/yara/yara/yara.lf.drs