Merge pull request #274 from sofstam/samtools_fastq

Subsitute samtools/bam2fq with samtools/fastq

CHANGELOG.md

@@ -12,6 +12,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#271](https://github.com/nf-core/taxprofiler/pull/271/files) Improved standardised table generation documentation nd mOTUs manual database download tutorial (♥ to @prototaxites for reporting, fix by @jfy133)
 - [#269](https://github.com/nf-core/taxprofiler/pull/269/files) Reduced output files in AWS full test output due to very large files
 - [#270](https://github.com/nf-core/taxprofiler/pull/270/files) Fixed warning for host removal index parameter, and improved index checks (♥ to @prototaxites for reporting, fix by @jfy133)
+- [#274](https://github.com/nf-core/taxprofiler/pull/274/files) Substituted the samtools/bam2fq module with samtools/fastq module (fix by @sofstam)
 
 ### `Dependencies`
 

conf/modules.config

@@ -250,12 +250,12 @@ process {
         ext.prefix = { "${meta.id}_${meta.run_accession}.unmapped" }
     }
 
-    withName: SAMTOOLS_BAM2FQ {
+    withName: SAMTOOLS_FASTQ {
         ext.prefix = { "${meta.id}_${meta.run_accession}.unmapped" }
         publishDir = [
-            path: { "${params.outdir}/samtools/bam2fq" },
+            path: { "${params.outdir}/samtools/fastq" },
             mode: params.publish_dir_mode,
-            pattern: '*.fq.gz',
+            pattern: '*.fastq.gz',
             enabled: params.save_hostremoval_unmapped
         ]
     }

docs/output.md

@@ -21,7 +21,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [Bowtie2](#bowtie2) - Host removal for Illumina reads
 - [minimap2](#minimap2) - Host removal for Nanopore reads
 - [SAMtools stats](#samtools-stats) - Statistics from host removal
-- [SAMtools bam2fq](#samtools-bam2fq) - Converts unmapped BAM file to fastq format (minimap2 only)
+- [SAMtools fastq](#samtools-fastq) - Converts unmapped BAM file to fastq format (minimap2 only)
 - [Bracken](#bracken) - Taxonomic classifier using k-mers and abundance estimations
 - [Kraken2](#kraken2) - Taxonomic classifier using exact k-mer matches
 - [KrakenUniq](#krakenuniq) - Taxonomic classifier that combines the k-mer-based classification and the number of unique k-mers found in each species
@@ -201,7 +201,7 @@ It is used with nf-core/taxprofiler to allow removal of 'host' (e.g. human) and/
 
 By default nf-core/taxprofiler will only provide the `.log` file if host removal is turned on. You will only have a `.bam` file if you specify `--save_hostremoval_bam`. This will contain _both_ mapped and unmapped reads. You will only get FASTQ files if you specify to save `--save_hostremoval_unmapped` - these contain only unmapped reads.
 
-> ℹ️ Unmapped reads in FASTQ are only found in this directory for short-reads, for long-reads see [`samtools/bam2fq/`](#samtools-bam2fq)
+> ℹ️ Unmapped reads in FASTQ are only found in this directory for short-reads, for long-reads see [`samtools/fastq/`](#samtools-fastq)
 
 > ⚠️ The resulting `.fastq` files may _not_ always be the 'final' reads that go into taxprofiling, if you also run other steps such as run merging etc..
 
@@ -228,11 +228,11 @@ By default, nf-core/taxprofiler will only provide the `.bam` file containing map
 
 > ℹ️ minimap2 is not yet supported as a module in MultiQC and therefore there is no dedicated section in the MultiQC HTML. Rather, alignment statistics to host genome is reported via samtools stats module in MultiQC report.
 
-> ℹ️ Unlike Bowtie2, minimap2 does not produce an unmapped FASTQ file by itself. See [`samtools/bam2fq`](#samtools-bam2fq)
+> ℹ️ Unlike Bowtie2, minimap2 does not produce an unmapped FASTQ file by itself. See [`samtools/fastq`](#samtools-fastq)
 
-### SAMtools bam2fq
+### SAMtools fastq
 
-[SAMtools bam2fq](http://www.htslib.org/doc/1.1/samtools.html) converts a `.sam`, `.bam`, or `.cram` alignment file to FASTQ format
+[SAMtools fastq](http://www.htslib.org/doc/1.1/samtools.html) converts a `.sam`, `.bam`, or `.cram` alignment file to FASTQ format
 
 <details markdown="1">
 <summary>Output files</summary>

modules.json

@@ -187,9 +187,9 @@
                         "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
                         "installed_by": ["modules"]
                     },
-                    "samtools/bam2fq": {
+                    "samtools/fastq": {
                         "branch": "master",
-                        "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
+                        "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b",
                         "installed_by": ["modules"]
                     },
                     "samtools/index": {

modules/nf-core/samtools/bam2fq/main.nf

@@ -1,56 +0,0 @@
-process SAMTOOLS_BAM2FQ {
-    tag "$meta.id"
-    label 'process_low'
-
-    conda "bioconda::samtools=1.16.1"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' :
-        'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }"
-
-    input:
-    tuple val(meta), path(inputbam)
-    val split
-
-    output:
-    tuple val(meta), path("*.fq.gz"), emit: reads
-    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}"
-
-    if (split){
-        """
-        samtools \\
-            bam2fq \\
-            $args \\
-            -@ $task.cpus \\
-            -1 ${prefix}_1.fq.gz \\
-            -2 ${prefix}_2.fq.gz \\
-            -0 ${prefix}_other.fq.gz \\
-            -s ${prefix}_singleton.fq.gz \\
-            $inputbam
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
-        END_VERSIONS
-        """
-    } else {
-        """
-        samtools \\
-            bam2fq \\
-            $args \\
-            -@ $task.cpus \\
-            $inputbam | gzip --no-name > ${prefix}_interleaved.fq.gz
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
-        END_VERSIONS
-        """
-    }
-}

modules/nf-core/samtools/bam2fq/meta.yml

@@ -1,55 +0,0 @@
-name: samtools_bam2fq
-description: |
-  The module uses bam2fq method from samtools to
-  convert a SAM, BAM or CRAM file to FASTQ format
-keywords:
-  - bam2fq
-  - samtools
-  - fastq
-tools:
-  - samtools:
-      description: Tools for dealing with SAM, BAM and CRAM files
-      homepage: None
-      documentation: http://www.htslib.org/doc/1.1/samtools.html
-      tool_dev_url: None
-      doi: ""
-      licence: ["MIT"]
-
-input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - inputbam:
-      type: file
-      description: BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
-  - split:
-      type: boolean
-      description: |
-        TRUE/FALSE value to indicate if reads should be separated into
-        /1, /2 and if present other, or singleton.
-        Note: choosing TRUE will generate 4 different files.
-        Choosing FALSE will produce a single file, which will be interleaved in case
-        the input contains paired reads.
-
-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"
-  - reads:
-      type: file
-      description: |
-        FASTQ files, which will be either a group of 4 files (read_1, read_2, other and singleton)
-        or a single interleaved .fq.gz file if the user chooses not to split the reads.
-      pattern: "*.fq.gz"
-
-authors:
-  - "@lescai"

modules/nf-core/samtools/fastq/main.nf

@@ -0,0 +1,44 @@
+process SAMTOOLS_FASTQ {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "bioconda::samtools=1.16.1"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' :
+        'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }"
+
+    input:
+    tuple val(meta), path(input)
+    val(interleave)
+
+    output:
+    tuple val(meta), path("*_{1,2}.fastq.gz")      , optional:true, emit: fastq
+    tuple val(meta), path("*_interleaved.fastq.gz"), optional:true, emit: interleaved
+    tuple val(meta), path("*_singleton.fastq.gz")  , optional:true, emit: singleton
+    tuple val(meta), path("*_other.fastq.gz")      , optional:true, emit: other
+    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 output = ( interleave && ! meta.single_end ) ? "> ${prefix}_interleaved.fastq.gz" :
+        meta.single_end ? "-1 ${prefix}_1.fastq.gz -s ${prefix}_singleton.fastq.gz" :
+        "-1 ${prefix}_1.fastq.gz -2 ${prefix}_2.fastq.gz -s ${prefix}_singleton.fastq.gz"
+    """
+    samtools \\
+        fastq \\
+        $args \\
+        --threads ${task.cpus-1} \\
+        -0 ${prefix}_other.fastq.gz \\
+        $input \\
+        $output
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/samtools/fastq/meta.yml

@@ -0,0 +1,62 @@
+name: samtools_fastq
+description: Converts a SAM/BAM/CRAM file to FASTQ
+keywords:
+  - bam
+  - sam
+  - cram
+  - fastq
+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: http://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/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - interleave:
+      type: boolean
+      description: Set true for interleaved fastq file
+
+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"
+  - fastq:
+      type: file
+      description: Compressed FASTQ file(s) with reads with either the READ1 or READ2 flag set in separate files.
+      pattern: "*_{1,2}.fastq.gz"
+  - interleaved:
+      type: file
+      description: Compressed FASTQ file with reads with either the READ1 or READ2 flag set in a combined file. Needs collated input file.
+      pattern: "*_interleaved.fastq.gz"
+  - singleton:
+      type: file
+      description: Compressed FASTQ file with singleton reads
+      pattern: "*_singleton.fastq.gz"
+  - other:
+      type: file
+      description: Compressed FASTQ file with reads with either both READ1 and READ2 flags set or unset
+      pattern: "*_other.fastq.gz"
+
+authors:
+  - "@priyanka-surana"
+  - "@suzannejin"

nextflow_schema.json

@@ -304,7 +304,7 @@
                     "type": "boolean",
                     "fa_icon": "fas fa-save",
                     "description": "Save reads from samples that went through the host-removal step",
-                    "help_text": "Save only the reads NOT mapped to the reference genome in FASTQ format (as exported from `samtools view` and `bam2fq`).\n\nThis can be useful if you wish to perform other analyses on the off-target reads from the host mapping, such as manual profiling or _de novo_ assembly."
+                    "help_text": "Save only the reads NOT mapped to the reference genome in FASTQ format (as exported from `samtools view` and `fastq`).\n\nThis can be useful if you wish to perform other analyses on the off-target reads from the host mapping, such as manual profiling or _de novo_ assembly."
                 }
             },
             "fa_icon": "fas fa-user-times"

subworkflows/local/longread_hostremoval.nf

@@ -5,7 +5,7 @@
 include { MINIMAP2_INDEX             } from '../../modules/nf-core/minimap2/index/main'
 include { MINIMAP2_ALIGN             } from '../../modules/nf-core/minimap2/align/main'
 include { SAMTOOLS_VIEW              } from '../../modules/nf-core/samtools/view/main'
-include { SAMTOOLS_BAM2FQ            } from '../../modules/nf-core/samtools/bam2fq/main'
+include { SAMTOOLS_FASTQ             } from '../../modules/nf-core/samtools/fastq/main'
 include { SAMTOOLS_INDEX             } from '../../modules/nf-core/samtools/index/main'
 include { SAMTOOLS_STATS             } from '../../modules/nf-core/samtools/stats/main'
 
@@ -38,8 +38,8 @@ workflow LONGREAD_HOSTREMOVAL {
     SAMTOOLS_VIEW ( ch_minimap2_mapped , [], [] )
     ch_versions      = ch_versions.mix( SAMTOOLS_VIEW.out.versions.first() )
 
-    SAMTOOLS_BAM2FQ ( SAMTOOLS_VIEW.out.bam, false )
-    ch_versions      = ch_versions.mix( SAMTOOLS_BAM2FQ.out.versions.first() )
+    SAMTOOLS_FASTQ ( SAMTOOLS_VIEW.out.bam, false )
+    ch_versions      = ch_versions.mix( SAMTOOLS_FASTQ.out.versions.first() )
 
     // Indexing whole BAM for host removal statistics
     SAMTOOLS_INDEX ( MINIMAP2_ALIGN.out.bam )
@@ -54,7 +54,7 @@ workflow LONGREAD_HOSTREMOVAL {
 
     emit:
     stats    = SAMTOOLS_STATS.out.stats     //channel: [val(meta), [reads  ] ]
-    reads    = SAMTOOLS_BAM2FQ.out.reads   // channel: [ val(meta), [ reads ] ]
+    reads    = SAMTOOLS_FASTQ.out.fastq.mix( SAMTOOLS_FASTQ.out.other)   // channel: [ val(meta), [ reads ] ]
     versions = ch_versions                 // channel: [ versions.yml ]
     mqc      = ch_multiqc_files
 }