Merge branch 'master' into master

modules/nf-core/annotsv/annotsv/main.nf

@@ -2,10 +2,10 @@ process ANNOTSV_ANNOTSV {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::annotsv=3.3.4"
+    conda "bioconda::annotsv=3.3.6"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/annotsv:3.3.4--py311hdfd78af_1' :
-        'biocontainers/annotsv:3.3.4--py311hdfd78af_1' }"
+        'https://depot.galaxyproject.org/singularity/annotsv:3.3.6--py311hdfd78af_0' :
+        'biocontainers/annotsv:3.3.6--py311hdfd78af_0' }"
 
     input:
     tuple val(meta), path(sv_vcf), path(sv_vcf_index), path(candidate_small_variants)

modules/nf-core/annotsv/installannotations/main.nf

@@ -2,10 +2,10 @@ process ANNOTSV_INSTALLANNOTATIONS {
     tag 'AnnotSV annotations'
     label 'process_single'
 
-    conda "bioconda::annotsv=3.3.4"
+    conda "bioconda::annotsv=3.3.6"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/annotsv:3.3.4--py311hdfd78af_1':
-        'biocontainers/annotsv:3.3.4--py311hdfd78af_1' }"
+        'https://depot.galaxyproject.org/singularity/annotsv:3.3.6--py311hdfd78af_0' :
+        'biocontainers/annotsv:3.3.6--py311hdfd78af_0' }"
 
     output:
     path "AnnotSV_annotations", emit: annotations

modules/nf-core/bacphlip/main.nf

@@ -0,0 +1,49 @@
+process BACPHLIP {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "bioconda::bacphlip=0.9.6 conda-forge::numpy=1.23.5 bioconda::hmmer=3.3.2"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-e16bfb0f667f2f3c236b32087aaf8c76a0cd2864:c64689d7d5c51670ff5841ec4af982edbe7aa406-0':
+        'biocontainers/mulled-v2-e16bfb0f667f2f3c236b32087aaf8c76a0cd2864:c64689d7d5c51670ff5841ec4af982edbe7aa406-0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("*.bacphlip")         , emit: bacphlip_results
+    tuple val(meta), path("*.hmmsearch.tsv")    , emit: hmmsearch_results
+    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 VERSION = '0.9.6' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    bacphlip \\
+        -i $fasta \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bacphlip: $VERSION
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '0.9.6' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    touch ${fasta}.bacphlip
+    touch ${fasta}.hmmsearch.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bacphlip: $VERSION
+    END_VERSIONS
+    """
+}

modules/nf-core/bacphlip/meta.yml

@@ -0,0 +1,50 @@
+name: "bacphlip"
+description: A bacteriophage lifestyle prediction tool
+keywords:
+  - phage
+  - lifestyle
+  - temperate
+  - virulent
+  - bacphlip
+  - hmmsearch
+tools:
+  - "bacphlip":
+      description: "A Random Forest classifier to predict bacteriophage lifestyle"
+      homepage: https://github.com/adamhockenberry/bacphlip
+      documentation: https://github.com/adamhockenberry/bacphlip
+      tool_dev_url: https://github.com/adamhockenberry/bacphlip
+      doi: 10.7717/peerj.11396
+      licence: "['MIT']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: FASTA file containing phage contigs/scaffolds/chromosomes (if it is a multi-FASTA file be sure to add the `--multi_fasta` argument)
+      pattern: "*.{fasta,fna,fa}"
+
+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"
+  - bacphlip_results:
+      type: file
+      description: TSV file containing Temperate and Virulent scores for each phage sequence
+      pattern: "*.bacphlip"
+  - hmmsearch_results:
+      type: file
+      description: TSV file containing binary output indicating gene presence/absence based on hmmsearch results
+      pattern: "*.hmmsearch.tsv"
+
+authors:
+  - "@CarsonJM"

modules/nf-core/bowtie2/align/main.nf

@@ -14,10 +14,10 @@ process BOWTIE2_ALIGN {
     val   sort_bam
 
     output:
-    tuple val(meta), path("*.bam")    , emit: bam
-    tuple val(meta), path("*.log")    , emit: log
-    tuple val(meta), path("*fastq.gz"), emit: fastq, optional:true
-    path  "versions.yml"              , emit: versions
+    tuple val(meta), path("*.{bam,sam}"), emit: aligned
+    tuple val(meta), path("*.log")      , emit: log
+    tuple val(meta), path("*fastq.gz")  , emit: fastq, optional:true
+    path  "versions.yml"                , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -38,6 +38,8 @@ process BOWTIE2_ALIGN {
     }
 
     def samtools_command = sort_bam ? 'sort' : 'view'
+    def extension_pattern = /(--output-fmt|-O)+\s+(\S+)/
+    def extension = (args2 ==~ extension_pattern) ? (args2 =~ extension_pattern)[0][2].toLowerCase() : "bam"
 
     """
     INDEX=`find -L ./ -name "*.rev.1.bt2" | sed "s/\\.rev.1.bt2\$//"`
@@ -51,7 +53,7 @@ process BOWTIE2_ALIGN {
         $unaligned \\
         $args \\
         2> ${prefix}.bowtie2.log \\
-        | samtools $samtools_command $args2 --threads $task.cpus -o ${prefix}.bam -
+        | samtools $samtools_command $args2 --threads $task.cpus -o ${prefix}.${extension} -
 
     if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
         mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
@@ -68,4 +70,25 @@ process BOWTIE2_ALIGN {
         pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
     END_VERSIONS
     """
+
+    stub:
+    def args2 = task.ext.args2 ?: ""
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def extension_pattern = /(--output-fmt|-O)+\s+(\S+)/
+    def extension = (args2 ==~ extension_pattern) ? (args2 =~ extension_pattern)[0][2].toLowerCase() : "bam"
+
+    """
+    touch ${prefix}.${extension}
+    touch ${prefix}.bowtie2.log
+    touch ${prefix}.unmapped_1.fastq.gz
+    touch ${prefix}.unmapped_2.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    END_VERSIONS
+    """
+
 }

modules/nf-core/bowtie2/align/meta.yml

@@ -46,10 +46,10 @@ input:
       description: use samtools sort (true) or samtools view (false)
       pattern: "true or false"
 output:
-  - bam:
+  - aligned:
       type: file
-      description: Output BAM file containing read alignments
-      pattern: "*.{bam}"
+      description: Output BAM/SAM file containing read alignments
+      pattern: "*.{bam,sam}"
   - versions:
       type: file
       description: File containing software versions

modules/nf-core/cutadapt/main.nf

@@ -34,4 +34,17 @@ process CUTADAPT {
         cutadapt: \$(cutadapt --version)
     END_VERSIONS
     """
+
+    stub:
+    def prefix  = task.ext.prefix ?: "${meta.id}"
+    def trimmed = meta.single_end ? "${prefix}.trim.fastq.gz" : "${prefix}_1.trim.fastq.gz ${prefix}_2.trim.fastq.gz"
+    """
+    touch ${prefix}.cutadapt.log
+    touch ${trimmed}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cutadapt: \$(cutadapt --version)
+    END_VERSIONS
+    """
 }

modules/nf-core/semibin/singleeasybin/meta.yml

@@ -2,6 +2,8 @@ name: semibin_singleeasybin
 description: metagenomic binning with self-supervised learning
 keywords:
   - binning
+  - assembly-binning
+  - metagenomics
 tools:
   - "semibin":
       description: "Metagenomic binning with semi-supervised siamese neural network"

subworkflows/nf-core/fastq_align_bowtie2/main.nf

@@ -21,18 +21,18 @@ workflow FASTQ_ALIGN_BOWTIE2 {
     // Map reads with Bowtie2
     //
     BOWTIE2_ALIGN ( ch_reads, ch_index, save_unaligned, sort_bam )
-    ch_versions = ch_versions.mix(BOWTIE2_ALIGN.out.versions.first())
+    ch_versions = ch_versions.mix(BOWTIE2_ALIGN.out.versions)
 
     //
     // Sort, index BAM file and run samtools stats, flagstat and idxstats
     //
-    BAM_SORT_STATS_SAMTOOLS ( BOWTIE2_ALIGN.out.bam, ch_fasta )
+    BAM_SORT_STATS_SAMTOOLS ( BOWTIE2_ALIGN.out.aligned, ch_fasta )
     ch_versions = ch_versions.mix(BAM_SORT_STATS_SAMTOOLS.out.versions)
 
     emit:
-    bam_orig         = BOWTIE2_ALIGN.out.bam          // channel: [ val(meta), bam   ]
-    log_out          = BOWTIE2_ALIGN.out.log          // channel: [ val(meta), log   ]
-    fastq            = BOWTIE2_ALIGN.out.fastq        // channel: [ val(meta), fastq ]
+    bam_orig         = BOWTIE2_ALIGN.out.aligned      // channel: [ val(meta), aligned ]
+    log_out          = BOWTIE2_ALIGN.out.log          // channel: [ val(meta), log     ]
+    fastq            = BOWTIE2_ALIGN.out.fastq        // channel: [ val(meta), fastq   ]
 
     bam              = BAM_SORT_STATS_SAMTOOLS.out.bam      // channel: [ val(meta), [ bam ] ]
     bai              = BAM_SORT_STATS_SAMTOOLS.out.bai      // channel: [ val(meta), [ bai ] ]

subworkflows/nf-core/fastq_align_dna/main.nf

@@ -31,7 +31,7 @@ workflow FASTQ_ALIGN_DNA {
         switch (aligner) {
             case 'bowtie2':
                 BOWTIE2_ALIGN(ch_reads, ch_aligner_index, false, sort) // if aligner is bowtie2
-                ch_bam = ch_bam.mix(BOWTIE2_ALIGN.out.bam)
+                ch_bam = ch_bam.mix(BOWTIE2_ALIGN.out.aligned)
                 ch_versions = ch_versions.mix(BOWTIE2_ALIGN.out.versions)
                 break
             case 'bwamem':

tests/config/pytest_modules.yml

@@ -174,6 +174,10 @@ backsub:
   - modules/nf-core/backsub/**
   - tests/modules/nf-core/backsub/**
 
+bacphlip:
+  - modules/nf-core/bacphlip/**
+  - tests/modules/nf-core/bacphlip/**
+
 bakta/bakta:
   - modules/nf-core/bakta/bakta/**
   - tests/modules/nf-core/bakta/bakta/**

tests/modules/nf-core/bacphlip/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BACPHLIP } from '../../../../modules/nf-core/bacphlip/main.nf'
+
+workflow test_bacphlip {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['candidatus_portiera_aleyrodidarum']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    BACPHLIP ( input )
+}

tests/modules/nf-core/bacphlip/nextflow.config

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

tests/modules/nf-core/bacphlip/test.yml

@@ -0,0 +1,19 @@
+- name: bacphlip test_bacphlip
+  command: nextflow run ./tests/modules/nf-core/bacphlip -entry test_bacphlip -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bacphlip/nextflow.config
+  tags:
+    - bacphlip
+  files:
+    - path: output/bacphlip/genome.fasta.bacphlip
+      md5sum: 3d07000f244d3a44b45c37adb2bcac4a
+    - path: output/bacphlip/genome.fasta.hmmsearch.tsv
+      md5sum: e4f0f3d4a75300ab4ee1d760cbded532
+    - path: output/bacphlip/versions.yml
+
+- name: bacphlip test_bacphlip_stub
+  command: nextflow run ./tests/modules/nf-core/bacphlip -entry test_bacphlip -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bacphlip/nextflow.config -stub-run
+  tags:
+    - bacphlip
+  files:
+    - path: output/bacphlip/genome.fasta.bacphlip
+    - path: output/bacphlip/genome.fasta.hmmsearch.tsv
+    - path: output/bacphlip/versions.yml

tests/modules/nf-core/bowtie2/align/main.nf

@@ -23,6 +23,42 @@ workflow test_bowtie2_align_single_end {
     BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
 }
 
+workflow test_bowtie2_align_single_end_sam {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = [
+        [ id:'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    save_unaligned = false
+    sort = false
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}
+
+workflow test_bowtie2_align_single_end_sam2 {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    fasta = [
+        [ id:'test'],
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+    save_unaligned = false
+    sort = false
+
+    BOWTIE2_BUILD ( fasta )
+    BOWTIE2_ALIGN ( input, BOWTIE2_BUILD.out.index, save_unaligned, sort )
+}
+
 workflow test_bowtie2_align_single_end_sorted {
     input = [
         [ id:'test', single_end:true ], // meta map

tests/modules/nf-core/bowtie2/align/nextflow.config

@@ -8,6 +8,14 @@ process {
     withName: BOWTIE2_BUILD {
     publishDir = [ enabled: false ]
     }
+
+    withName: "test_bowtie2_align_single_end_sam:BOWTIE2_ALIGN" {
+        ext.args2 = '--output-fmt SAM'
+    }
+
+    withName: "test_bowtie2_align_single_end_sam2:BOWTIE2_ALIGN" {
+        ext.args2 = '-O SAM'
+    }
 }
 
 if (params.force_large_index) {