Merge branch 'dev' into hostremoval

2024-11-22 06:09:55 +00:00 · 2022-04-13 13:59:51 +02:00 · 2022-04-13 13:59:51 +02:00 · 70f94603b0
commit 70f94603b0
parent 78182c2a8c 67d94a9a8d
10 changed files with 111 additions and 171 deletions
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@ -29,8 +29,8 @@ jobs:
          - NXF_VER: ""
            NXF_EDGE: "1"
        parameters:
-          - "--longread_clip false"
-          - "--shortread_clip false"
+          - "--perform_longread_clip false"
+          - "--perform_shortread_clipmerge false"
          - "--shortread_clipmerge_tool fastp"
          - "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
          - "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs"
@ -39,6 +39,8 @@ jobs:
          - "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
          - "--shortread_complexityfilter_tool bbduk"
          - "--shortread_complexityfilter_tool prinseq"
+          - "--perform_runmerging"
+          - "--perform_runmerging --shortread_clipmerge_mergepairs"
          - "--shortread_complexityfilter false --shortread_hostremoval"

    steps:
--- a/conf/modules.config
+++ b/conf/modules.config
@ -179,9 +179,19 @@ process {
        ]
    }

+    withName: CAT_FASTQ {
+        ext.prefix = { "${meta.id}" }
+        publishDir = [
+            path: { "${params.outdir}/run_merging/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_runmerged_reads
+        ]
+    }
+
    withName: MALT_RUN {
        ext.args = { "${meta.db_params}" }
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
        publishDir = [
            path: { "${params.outdir}/malt/${meta.db_name}" },
            mode: params.publish_dir_mode,
@ -191,7 +201,7 @@ process {

    withName: KRAKEN2_KRAKEN2 {
        ext.args = { "${meta.db_params}" }
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
        publishDir = [
            path: { "${params.outdir}/kraken2/${meta.db_name}" },
            mode: params.publish_dir_mode,
@ -200,12 +210,13 @@ process {
    }

    withName: METAPHLAN3 {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
        publishDir = [
            path: { "${params.outdir}/metaphlan3/${meta.db_name}" },
            mode: params.publish_dir_mode,
            pattern: '*.{biom,txt}'
        ]
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
    }

    withName: CENTRIFUGE_CENTRIFUGE {
--- a/conf/test.config
+++ b/conf/test.config
@ -22,16 +22,15 @@ params {
    // Input data
    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
    // TODO nf-core: Give any required params for the test so that command line flags are not needed
-
    input                         = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
    databases                     = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv'
    run_kraken2                   = true
    run_malt                      = true
    run_metaphlan3                = true
    run_centrifuge                = true
-    shortread_clipmerge             = true
-    longread_clip                   = false
-    shortread_complexityfilter      = true
+    perform_shortread_clipmerge           = true
+    perform_longread_clip                 = false
+    perform_shortread_complexityfilter    = true
    shortread_hostremoval           = true
    shortread_hostremoval_reference = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
 }
--- a/nextflow.config
+++ b/nextflow.config
@ -55,7 +55,7 @@ params {
    databases = null

    // FASTQ preprocessing
-    shortread_clipmerge                     = false
+    perform_shortread_clipmerge             = false
    shortread_clipmerge_tool                = 'fastp'
    shortread_clipmerge_skipadaptertrim     = false
    shortread_clipmerge_mergepairs          = false
@ -63,11 +63,11 @@ params {
    shortread_clipmerge_adapter1            = null
    shortread_clipmerge_adapter2            = null
    shortread_clipmerge_minlength           = 15
-    longread_clip                           = false
+    perform_longread_clip                   = false
    save_preprocessed_reads                 = false

    // Complexity filtering
-    shortread_complexityfilter                           = false
+    perform_shortread_complexityfilter                   = false
    shortread_complexityfilter_tool                      = 'bbduk'
    shortread_complexityfilter_entropy                   = 0.3
    shortread_complexityfilter_bbduk_windowsize          = 50
@ -76,6 +76,9 @@ params {
    shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
    save_complexityfiltered_reads                        = false

+    // run merging
+    perform_runmerging          = false
+    save_runmerged_reads        = false

    // Host Removal
    shortread_hostremoval           = false
@ -94,6 +97,7 @@ params {
    centrifuge_save_unaligned  = false
    centrifuge_save_aligned    = false
    centrifuge_sam_format      = false
+
    // metaphlan3
    run_metaphlan3             = false
 }
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@ -262,15 +262,9 @@
            "type": "string",
            "default": "None"
        },
-        "shortread_clipmerge": {
-            "type": "boolean"
-        },
        "shortread_clipmerge_excludeunmerged": {
            "type": "boolean"
        },
-        "longread_clip": {
-            "type": "boolean"
-        },
        "run_malt": {
            "type": "boolean"
        },
@ -321,8 +315,7 @@
            "default": 15
        },
        "save_preprocessed_reads": {
-            "type": "boolean",
-            "default": false
+            "type": "boolean"
        },
        "shortread_complexityfilter_tool": {
            "type": "string",
@ -335,9 +328,6 @@
        "shortread_complexityfilter_bbduk_mask": {
            "type": "boolean"
        },
-        "shortread_complexityfilter": {
-            "type": "boolean"
-        },
        "shortread_complexityfilter_entropy": {
            "type": "number",
            "default": 0.3
@ -352,8 +342,22 @@
            "default": 0.5
        },
        "save_complexityfiltered_reads": {
-            "type": "boolean",
-            "default": false
+            "type": "boolean"
+        },
+        "save_runmerged_reads": {
+            "type": "boolean"
+        },
+        "perform_shortread_clipmerge": {
+            "type": "boolean"
+        },
+        "perform_longread_clip": {
+            "type": "boolean"
+        },
+        "perform_shortread_complexityfilter": {
+            "type": "boolean"
+        },
+        "perform_runmerging": {
+            "type": "boolean"
        },
        "shortread_hostremoval": {
            "type": "boolean"
--- a/nf-core/modules/centrifuge/centrifuge/main.nf
+++ b/nf-core/modules/centrifuge/centrifuge/main.nf
@ -1,61 +0,0 @@
-process CENTRIFUGE_CENTRIFUGE {
-    tag "$meta.id"
-    label 'process_high'
-
-    conda (params.enable_conda ? "bioconda::centrifuge=1.0.4_beta" : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/centrifuge:1.0.4_beta--h9a82719_6' :
-        'quay.io/biocontainers/centrifuge:1.0.4_beta--h9a82719_6' }"
-
-    input:
-    tuple val(meta), path(reads)
-    path db
-    val save_unaligned
-    val save_aligned
-    val sam_format
-
-    output:
-    tuple val(meta), path('*report.txt')                 , emit: report
-    tuple val(meta), path('*results.txt')                , emit: results
-    tuple val(meta), path('*.sam')                       , optional: true, emit: sam
-    tuple val(meta), path('*.mapped.fastq{,.1,.2}.gz')   , optional: true, emit: fastq_mapped
-    tuple val(meta), path('*.unmapped.fastq{,.1,.2}.gz') , optional: true, emit: fastq_unmapped
-    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 paired = meta.single_end ? "-U ${reads}" :  "-1 ${reads[0]} -2 ${reads[1]}"
-    def unaligned = ''
-    def aligned = ''
-    if (meta.single_end) {
-        unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ''
-        aligned = save_aligned ? "--al-gz ${prefix}.mapped.fastq.gz" : ''
-    } else {
-        unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ''
-        aligned = save_aligned ? "--al-conc-gz ${prefix}.mapped.fastq.gz" : ''
-    }
-    def sam_output = sam_format ? "--out-fmt 'sam'" : ''
-    """
-    ## we add "-no-name ._" to ensure silly Mac OSX metafiles files aren't included
-    db_name=`find -L ${db} -name "*.1.cf" -not -name "._*"  | sed 's/.1.cf//'`
-    centrifuge \\
-        -x \$db_name \\
-        -p $task.cpus \\
-        $paired \\
-        --report-file ${prefix}.report.txt \\
-        -S ${prefix}.results.txt \\
-        $unaligned \\
-        $aligned \\
-        $sam_output \\
-        $args
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        centrifuge: \$( centrifuge --version  | sed -n 1p | sed 's/^.*centrifuge-class version //')
-    END_VERSIONS
-    """
-}
--- a/nf-core/modules/centrifuge/centrifuge/meta.yml
+++ b/nf-core/modules/centrifuge/centrifuge/meta.yml
@ -1,66 +0,0 @@
-name: centrifuge_centrifuge
-description: Classifies metagenomic sequence data
-keywords:
-  - classify
-  - metagenomics
-  - fastq
-  - db
-tools:
-  - centrifuge:
-      description: Centrifuge is a classifier for metagenomic sequences.
-      homepage: https://ccb.jhu.edu/software/centrifuge/
-      documentation: https://ccb.jhu.edu/software/centrifuge/manual.shtml
-      doi: 10.1101/gr.210641.116
-      licence: ["GPL v3"]
-input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - reads:
-      type: file
-      description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
-  - db:
-      type: directory
-      description: Path to directory containing centrifuge database files
-  - save_unaligned:
-      type: value
-      description: If true unmapped fastq files are saved
-  - save_aligned:
-      type: value
-      description: If true mapped fastq files are saved
-output:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
-  - report:
-      type: file
-      description: |
-        File containing a classification summary
-      pattern: "*.{report.txt}"
-  - results:
-      type: file
-      description: |
-        File containing classification results
-      pattern: "*.{results.txt}"
-  - fastq_unmapped:
-      type: file
-      description: Unmapped fastq files
-      pattern: "*.unmapped.fastq.gz"
-  - fastq_mapped:
-      type: file
-      description: Mapped fastq files
-      pattern: "*.mapped.fastq.gz"
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-authors:
-  - "@sofstam"
-  - "@jfy133"
-  - "@sateeshperi"
--- a/subworkflows/local/profiling.nf
+++ b/subworkflows/local/profiling.nf
@ -9,8 +9,7 @@ include { METAPHLAN3                  } from '../../modules/nf-core/modules/meta

 workflow PROFILING {
    take:
-    shortreads // [ [ meta ], [ reads ] ]
-    longreads // [ [ meta ], [ reads ] ]
+    reads // [ [ meta ], [ reads ] ]
    databases // [ [ meta ], path ]

    main:
@ -22,8 +21,14 @@ workflow PROFILING {
    */

    // e.g. output [DUMP: reads_plus_db] [['id':'2612', 'run_accession':'combined', 'instrument_platform':'ILLUMINA', 'single_end':1], <reads_path>/2612.merged.fastq.gz, ['tool':'malt', 'db_name':'mal95', 'db_params':'"-id 90"'], <db_path>/malt90]
-    ch_input_for_profiling = shortreads
-            .mix( longreads )
+    ch_input_for_profiling = reads
+            .map {
+                meta, reads ->
+                    def meta_new = meta.clone()
+                        pairtype = meta_new['single_end'] ? '_se' : '_pe'
+                        meta_new['id'] =  meta_new['id'] + pairtype
+                    [meta_new, reads]
+            }
            .combine(databases)
            .branch {
                malt:    it[2]['tool'] == 'malt'
--- a/subworkflows/local/shortread_fastp.nf
+++ b/subworkflows/local/shortread_fastp.nf
@ -28,8 +28,8 @@ workflow SHORTREAD_FASTP {
                                        .map {
                                            meta, reads ->
                                                def meta_new = meta.clone()
-                                                meta_new['single_end'] = 1
-                                                [ meta_new, reads ]
+                                                meta_new['single_end'] = true
+                                                [ meta_new, [ reads ].flatten() ]
                                        }

        ch_fastp_reads_prepped = ch_fastp_reads_prepped_pe.mix( FASTP_SINGLE.out.reads )
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@ -111,14 +111,14 @@ workflow TAXPROFILER {
    /*
        SUBWORKFLOW: PERFORM PREPROCESSING
    */
-    if ( params.shortread_clipmerge ) {
+    if ( params.perform_shortread_clipmerge ) {

        ch_shortreads_preprocessed = SHORTREAD_PREPROCESSING ( INPUT_CHECK.out.fastq ).reads
    } else {
        ch_shortreads_preprocessed = INPUT_CHECK.out.fastq
    }

-    if ( params.longread_clip ) {
+    if ( params.perform_longread_clip ) {
        ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads
                                        .map { it -> [ it[0], [it[1]] ] }
        ch_versions = ch_versions.mix(LONGREAD_PREPROCESSING.out.versions.first())
@ -130,7 +130,7 @@ workflow TAXPROFILER {
        SUBWORKFLOW: COMPLEXITY FILTERING
    */

-    if ( params.shortread_complexityfilter ) {
+    if ( params.perform_shortread_complexityfilter ) {
        ch_shortreads_filtered = SHORTREAD_COMPLEXITYFILTERING ( ch_shortreads_preprocessed ).reads
    } else {
        ch_shortreads_filtered = ch_shortreads_preprocessed
@ -147,11 +147,48 @@ workflow TAXPROFILER {
        ch_shortreads_hostremoved = ch_shortreads_filtered
    }

+    */
+
+    if ( params.perform_runmerging ) {
+
+        ch_reads_for_cat_branch = ch_shortreads_hostremoved
+            .mix( ch_longreads_preprocessed )
+            .map {
+                meta, reads ->
+                    def meta_new = meta.clone()
+                    meta_new.remove('run_accession')
+                    [ meta_new, reads ]
+            }
+            .groupTuple()
+            .map {
+                meta, reads ->
+                    [ meta, reads.flatten() ]
+            }
+            .branch {
+                meta, reads ->
+                // we can't concatenate files if there is not a second run, we branch
+                // here to separate them out, and mix back in after for efficiency
+                cat: ( meta.single_end && reads.size() > 1 ) || ( !meta.single_end && reads.size() > 2 )
+                skip: true
+            }
+
+        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads
+            .mix( ch_reads_for_cat_branch.skip )
+            .map {
+                meta, reads ->
+                [ meta, [ reads ].flatten() ]
+            }
+
+    } else {
+        ch_reads_runmerged = ch_shortreads_hostremoved
+            .mix( ch_longreads_preprocessed )
+    }
+
    /*
        SUBWORKFLOW: PROFILING
    */

-    PROFILING ( ch_shortreads_hostremoved, ch_longreads_preprocessed, DB_CHECK.out.dbs )
+    PROFILING ( ch_reads_runmerged, DB_CHECK.out.dbs )
    ch_versions = ch_versions.mix( PROFILING.out.versions )

    /*
@ -173,23 +210,28 @@ workflow TAXPROFILER {
    ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))

-    if (params.shortread_clipmerge) {
+    if (params.perform_shortread_clipmerge) {
        ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
        ch_versions = ch_versions.mix( SHORTREAD_PREPROCESSING.out.versions )
    }

-    if (params.longread_clip) {
+    if (params.perform_longread_clip) {
        ch_multiqc_files = ch_multiqc_files.mix( LONGREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
        ch_versions = ch_versions.mix( LONGREAD_PREPROCESSING.out.versions )
    }

-    if (params.shortread_complexityfilter){
+    if (params.perform_shortread_complexityfilter){
        ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_COMPLEXITYFILTERING.out.mqc.collect{it[1]}.ifEmpty([]) )
        ch_versions = ch_versions.mix( SHORTREAD_COMPLEXITYFILTERING.out.versions )
    }

    if (params.shortread_hostremoval) {
        ch_multiqc_files = ch_multiqc_files.mix(SHORTREAD_HOSTREMOVAL.out.mqc.collect{it[1]}.ifEmpty([]))
+        ch_versions = ch_versions.mix(SHORTREAD_HOSTREMOVAL.out.versions)
+    }
+    
+    if (params.perform_runmerging){
+        ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
    }

    ch_multiqc_files = ch_multiqc_files.mix( PROFILING.out.mqc )