Merge branch 'nf-core:dev' into update_usage

2024-09-21 08:42:03 +00:00 · 2022-12-20 14:11:05 +01:00 · 2022-12-20 14:11:05 +01:00 · 502a4a81cd
commit 502a4a81cd
parent 644c4ab831 b5c72894fd
16 changed files with 497 additions and 121 deletions
--- a/assets/multiqc_config.yml
+++ b/assets/multiqc_config.yml
@ -19,11 +19,20 @@ custom_logo_title: "nf-core/taxprofiler"
 run_modules:
  - fastqc
  - adapterRemoval
+  - bbduk
+  - prinseqplusplus
  - fastp
+  - filtlong
  - bowtie2
+  - minimap2
  - samtools
  - kraken
+  - kaiju
+  - metaphlan
+  - diamond
  - malt
+  - motus
+  - porechop
  - custom_content

 #extra_fn_clean_exts:
@ -36,16 +45,41 @@ top_modules:
      name: "FastQC (pre-Trimming)"
      path_filters:
        - "*raw_*fastqc.zip"
+  - "fastqc":
+      name: "Falco (pre-Trimming)"
+      path_filters:
+        - "*_raw_falco_*_report.html"
  - "fastp"
  - "adapterRemoval"
+  - "porechop"
  - "fastqc":
      name: "FastQC (post-Trimming)"
      path_filters:
-        - "*raw_*processed.zip"
+        - "*_processed_*fastqc.zip"
+  - "fastqc":
+      name: "Falco (post-Trimming)"
+      path_filters:
+        - "*_processed_falco_*_report.html"
+  - "bbduk"
+  - "prinseqplusplus"
+  - "filtlong"
+  - "bowtie2":
+      name: "bowtie2"
+  - "samtools":
+      name: "Samtools Stats"
  - "kraken":
      name: "Kraken"
      path_filters:
-        - "*.kraken2.report.txt"
+        - "*.kraken2.kraken2.report.txt"
+  - "kraken":
+      name: "Bracken"
+      anchor: "bracken"
+      target: "Bracken"
+      doi: "10.7717/peerj-cs.104"
+      info: "Estimates species abundances in metagenomics samples by probabilistically re-distributing reads in the taxonomic tree."
+      extra: "Note: plot title will say Kraken2 due to the first step of bracken producing the same output format as Kraken. Abundance information is currently not supported in MultiQC."
+      path_filters:
+        - "*.bracken.kraken2.report.txt"
  - "kraken":
      name: "Centrifuge"
      anchor: "centrifuge"
@ -55,3 +89,171 @@ top_modules:
      extra: "Note: plot title will say Kraken2 due to Centrifuge producing the same output format as Kraken. If activated, see the actual Kraken2 results in the section above."
      path_filters:
        - "*.centrifuge.txt"
+  - "malt":
+      name: "MALT"
+  - "diamond"
+  - "kaiju":
+      name: "Kaiju"
+  - "motus"
+
+#It is not possible to set placement for custom kraken and centrifuge columns.
+
+table_columns_placement:
+  FastQC (pre-Trimming):
+    total_sequences: 100
+    avg_sequence_length: 110
+    percent_duplicates: 120
+    percent_gc: 130
+    percent_fails: 140
+  Falco (pre-Trimming):
+    total_sequences: 200
+    avg_sequence_length: 210
+    percent_duplicates: 220
+    percent_gc: 230
+    percent_fails: 240
+  fastp:
+    pct_adapter: 300
+    pct_surviving: 310
+    pct_duplication: 320
+    after_filtering_gc_content: 330
+    after_filtering_q30_rate: 340
+    after_filtering_q30_bases: 350
+  Adapter Removal:
+    aligned_total: 360
+    percent_aligned: 370
+    percent_collapsed: 380
+    percent_discarded: 390
+  FastQC (post-Trimming):
+    total_sequences: 400
+    avg_sequence_length: 410
+    percent_duplicates: 420
+    percent_gc: 430
+    percent_fails: 440
+  Falco (post-Trimming):
+    total_sequences: 500
+    avg_sequence_length: 510
+    percent_duplicates: 520
+    percent_gc: 530
+    percent_fails: 540
+  bowtie2:
+    overall_alignment_rate: 600
+  Samtools Stats:
+    raw_total_sequences: 700
+    reads_mapped: 710
+    reads_mapped_percent: 720
+    reads_properly_paired_percent: 730
+    non-primary_alignments: 740
+    reads_MQ0_percent: 750
+    error_rate: 760
+  MALT:
+    Num. of queries: 1000
+    Total reads: 1100
+    Mappability: 1200
+    Assig. Taxonomy: 1300
+    Taxonomic assignment success: 1400
+  Kaiju:
+    assigned: 2000
+    "% Assigned": 2100
+    "% Unclassified": 2200
+
+table_columns_visible:
+  FastQC (pre-Trimming):
+    total_sequences: True
+    avg_sequence_length: True
+    percent_duplicates: True
+    percent_gc: True
+    percent_fails: False
+  Falco (pre-Trimming):
+    total_sequences: True
+    avg_sequence_length: True
+    percent_duplicates: True
+    percent_gc: True
+    percent_fails: False
+  fastp:
+    pct_adapter: True
+    pct_surviving: True
+    pct_duplication: False
+    after_filtering_gc_content: False
+    after_filtering_q30_rate: False
+    after_filtering_q30_bases: False
+  Adapter Removal:
+    aligned_total: True
+    percent_aligned: True
+    percent_collapsed: True
+    percent_discarded: False
+  FastQC (post-Trimming):
+    total_sequences: True
+    avg_sequence_length: True
+    percent_duplicates: False
+    percent_gc: False
+    percent_fails: False
+  Falco (post-Trimming):
+    total_sequences: True
+    avg_sequence_length: True
+    percent_duplicates: False
+    percent_gc: False
+    percent_fails: False
+  bowtie2:
+    overall_alignment_rate: True
+  Samtools Stats:
+    raw_total_sequences: True
+    reads_mapped: True
+    reads_mapped_percent: True
+    reads_properly_paired_percent: False
+    non-primary_alignments: False
+    reads_MQ0_percent: False
+    error_rate: False
+  Kraken:
+    "% Unclassified": True
+    "% Top 5": False
+  Bracken:
+    "% Unclassified": True
+    "% Top 5": False
+  Centrifuge:
+    "% Unclassified": True
+    "% Top 5": False
+  MALT:
+    Num. of queries: True
+    Total reads: True
+    Mappability: True
+    Assig. Taxonomy: False
+    Taxonomic assignment success: True
+  Kaiju:
+    assigned: False
+    "% Assigned": False
+    "% Unclassified": True
+table_columns_name:
+  FastQC (pre-Trimming):
+    total_sequences: "Nr. Input Reads"
+    avg_sequence_length: "Length Input Reads"
+    percent_gc: "% GC Input Reads"
+    percent_duplicates: "% Dups Input Reads"
+    percent_fails: "% Failed Input Reads"
+  Falco (pre-Trimming):
+    total_sequences: "Nr. Input Reads"
+    avg_sequence_length: "Length Input Reads"
+    percent_gc: "% GC Input Reads"
+    percent_duplicates: "% Dups Input Reads"
+    percent_fails: "% Failed Input Reads"
+  FastQC (post-Trimming):
+    total_sequences: "Nr. Processed Reads"
+    avg_sequence_length: "Length Processed Reads"
+    percent_gc: "% GC Processed Reads"
+    percent_duplicates: "% Dups Processed Reads"
+    percent_fails: "% Failed Processed Reads"
+  Falco (post-Trimming):
+    total_sequences: "Nr. Processed Reads"
+    avg_sequence_length: "Length Processed Reads"
+    percent_gc: "% GC Processed Reads"
+    percent_duplicates: "% Dups Processed Reads"
+    percent_fails: "% Failed Processed Reads"
+  Samtools Stats:
+    raw_total_sequences: "Nr. Reads Into Mapping"
+    reads_mapped: "Nr. Mapped Reads"
+    reads_mapped_percent: "% Mapped Reads"
+
+extra_fn_clean_exts:
+  - ".kraken2.kraken2.report.txt"
+  - ".centrifuge.txt"
+  - ".bracken.kraken2.report.txt"
+  - ".settings"
--- a/conf/modules.config
+++ b/conf/modules.config
@ -12,14 +12,6 @@

 process {

-    withName: DATABASE_CHECK {
-        publishDir = [
-            path: { "${params.outdir}/pipeline_info" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
    withName: FASTQC {
        ext.args = '--quiet'
        ext.prefix = { "${meta.id}_${meta.run_accession}_raw" }
@ -41,7 +33,7 @@ process {
    }

    withName: FALCO {
-        ext.prefix = { "${meta.id}_${meta.run_accession}_raw" }
+        ext.prefix = { "${meta.id}_${meta.run_accession}_raw_falco" }
        publishDir = [
            path: { "${params.outdir}/falco/raw" },
            mode: params.publish_dir_mode,
@ -50,7 +42,7 @@ process {
    }

    withName: FALCO_PROCESSED {
-        ext.prefix = { "${meta.id}_${meta.run_accession}_processed" }
+        ext.prefix = { "${meta.id}_${meta.run_accession}_processed_falco" }
        publishDir = [
            path: { "${params.outdir}/falco/processed" },
            mode: params.publish_dir_mode,
@ -69,10 +61,17 @@ process {
        ].join(' ').trim()
        ext.prefix = { "${meta.id}_${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/fastp" },
                mode: params.publish_dir_mode,
                pattern: '*.fastq.gz',
                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/fastp" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{log,html,json}'
+            ]
        ]
    }

@ -90,10 +89,17 @@ process {
        ].join(' ').trim()
        ext.prefix = { "${meta.id}_${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/fastp" },
                mode: params.publish_dir_mode,
                pattern: '*.fastq.gz',
                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/fastp" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{log,html,json}'
+            ]
        ]
    }

@ -106,10 +112,17 @@ process {
        ].join(' ').trim()
        ext.prefix = { "${meta.id}_${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/adapterremoval" },
                mode: params.publish_dir_mode,
                pattern: '*.fastq.gz',
                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/adapterremoval" },
+                mode: params.publish_dir_mode,
+                pattern: '*.settings'
+            ]
        ]
    }

@ -125,20 +138,34 @@ process {
        ].join(' ').trim()
        ext.prefix = { "${meta.id}_${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/adapterremoval" },
                mode: params.publish_dir_mode,
                pattern: '*.fastq.gz',
                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/adapterremoval" },
+                mode: params.publish_dir_mode,
+                pattern: '*.settings'
+            ]
        ]
    }

    withName: PORECHOP_PORECHOP {
        ext.prefix = { "${meta.id}_${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/porechop" },
                mode: params.publish_dir_mode,
                pattern: '*.fastq.gz',
                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/porechop" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
        ]
    }

@ -151,10 +178,17 @@ process {
        .join(' ').trim()
        ext.prefix = { "${meta.id}_${meta.run_accession}_filtered" }
        publishDir = [
+            [
                path: { "${params.outdir}/filtlong" },
                mode: params.publish_dir_mode,
-            pattern: '*.{fastq.gz,log}',
+                pattern: '*.fastq.gz',
                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/filtlong" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
        ]
    }

@ -248,10 +282,17 @@ process {
            ].join(' ').trim()
        ext.prefix = { "${meta.id}-${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/bbduk/" },
                mode: params.publish_dir_mode,
                pattern: '*.{fastq.gz,log}',
                enabled: params.save_complexityfiltered_reads
+            ],
+            [
+                path: { "${params.outdir}/bbduk/" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
        ]
    }

@ -263,10 +304,17 @@ process {
            ].join(' ').trim()
        ext.prefix = { "${meta.id}-${meta.run_accession}" }
        publishDir = [
+            [
                path: { "${params.outdir}/prinseqplusplus/" },
                mode: params.publish_dir_mode,
-            pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz,log}',
+                pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz}',
                enabled: params.save_complexityfiltered_reads
+            ],
+            [
+                path: { "${params.outdir}/prinseqplusplus/" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
        ]
    }

@ -303,7 +351,7 @@ process {

    withName: KRAKEN2_KRAKEN2 {
        ext.args = params.kraken2_save_minimizers ? { "${meta.db_params} --report-minimizer-data" } : { "${meta.db_params}" }
-        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = params.perform_runmerging ? { meta.tool == "bracken" ? "${meta.id}-${meta.db_name}.bracken" : "${meta.id}-${meta.db_name}" } : { meta.tool == "bracken" ? "${meta.id}-${meta.run_accession}-${meta.db_name}.bracken" : "${meta.id}-${meta.run_accession}-${meta.db_name}" }
        publishDir = [
            path: { "${params.outdir}/kraken2/${meta.db_name}/" },
            mode: params.publish_dir_mode,
@ -313,7 +361,7 @@ process {

    withName: BRACKEN_BRACKEN {
        errorStrategy = 'ignore'
-        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}.bracken" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}.bracken" }
        publishDir = [
            path: { "${params.outdir}/bracken/${meta.db_name}/" },
            mode: params.publish_dir_mode,
@ -321,12 +369,21 @@ process {
        ]
    }

-    withName: KRAKENTOOLS_COMBINEKREPORTS {
+    withName: BRACKEN_COMBINEBRACKENOUTPUTS {
+        ext.prefix = { "bracken_${meta.id}_combined_reports" }
+        publishDir = [
+            path: { "${params.outdir}/bracken/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.txt'
+        ]
+    }
+
+    withName: KRAKENTOOLS_COMBINEKREPORTS_KRAKEN {
        ext.prefix = { "kraken2_${meta.id}_combined_reports" }
        publishDir = [
            path: { "${params.outdir}/kraken2/" },
            mode: params.publish_dir_mode,
-            pattern: '*.{txt}'
+            pattern: '*.txt'
        ]
    }

--- a/modules.json
+++ b/modules.json
@ -30,6 +30,11 @@
                        "git_sha": "8cab56516076b23c6f8eb1ac20ba4ce9692c85e1",
                        "installed_by": ["modules"]
                    },
+                    "bracken/combinebrackenoutputs": {
+                        "branch": "master",
+                        "git_sha": "9c87d5fdad182590a370ea43a4ecebd200a6f6fb",
+                        "installed_by": ["modules"]
+                    },
                    "cat/fastq": {
                        "branch": "master",
                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",
@ -68,7 +73,8 @@
                    "falco": {
                        "branch": "master",
                        "git_sha": "fc959214036403ad83efe7a41d43d0606c445cda",
-                        "installed_by": ["modules"]
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/falco/falco.diff"
                    },
                    "fastp": {
                        "branch": "master",
@ -167,12 +173,12 @@
                    },
                    "motus/merge": {
                        "branch": "master",
-                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",
+                        "git_sha": "3fce766123e71e82fb384db7d07b59180baa9ee9",
                        "installed_by": ["modules"]
                    },
                    "motus/profile": {
                        "branch": "master",
-                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",
+                        "git_sha": "3fce766123e71e82fb384db7d07b59180baa9ee9",
                        "installed_by": ["modules"]
                    },
                    "multiqc": {
--- a/modules/local/database_check.nf
+++ b/modules/local/database_check.nf
@ -1,29 +0,0 @@
-process DATABASE_CHECK {
-    tag "$databasesheet"
-    label 'process_single'
-
-    conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/python:3.8.3' :
-        'quay.io/biocontainers/python:3.8.3' }"
-
-    input:
-    path databasesheet
-
-    output:
-    path '*.csv'       , emit: csv
-    path "versions.yml", emit: versions
-
-    when:
-    task.ext.when == null || task.ext.when
-
-    script: // This script is bundled with the pipeline, in nf-core/taxprofiler/bin/
-    """
-    cat $databasesheet >> database_sheet.valid.csv
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        python: \$(python --version | sed 's/Python //g')
-    END_VERSIONS
-    """
-}
--- a/modules/nf-core/bracken/combinebrackenoutputs/main.nf
+++ b/modules/nf-core/bracken/combinebrackenoutputs/main.nf
@ -0,0 +1,37 @@
+process BRACKEN_COMBINEBRACKENOUTPUTS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bracken=2.7" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bracken:2.7--py39hc16433a_0':
+        'quay.io/biocontainers/bracken:2.7--py39hc16433a_0' }"
+
+    input:
+    tuple val(meta), path(input)
+
+    output:
+    tuple val(meta), path("*.txt"), emit: txt
+    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}"
+    // WARN: Version information not provided by tool on CLI.
+    // Please update version string below when bumping container versions.
+    def VERSION = '2.7'
+    """
+    combine_bracken_outputs.py \\
+        $args \\
+        --files ${input} \\
+        -o ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        combine_bracken_output: ${VERSION}
+    END_VERSIONS
+    """
+}
--- a/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
+++ b/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
@ -0,0 +1,41 @@
+name: "bracken_combinebrackenoutputs"
+description: Combine output of metagenomic samples analyzed by bracken.
+keywords:
+  - sort
+tools:
+  - "bracken":
+      description: Bracken (Bayesian Reestimation of Abundance with KrakEN) is a highly accurate statistical method that computes the abundance of species in DNA sequences from a metagenomics sample.
+      homepage: https://ccb.jhu.edu/software/bracken/
+      documentation: https://ccb.jhu.edu/software/bracken/index.shtml?t=manual
+      tool_dev_url: https://github.com/jenniferlu717/Bracken
+      doi: "10.7717/peerj-cs.104"
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: List of output files from bracken
+      pattern: "*"
+
+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"
+  - txt:
+      type: file
+      description: Combined output in table format
+      pattern: "*.txt"
+
+authors:
+  - "@jfy133"
--- a/modules/nf-core/falco/falco.diff
+++ b/modules/nf-core/falco/falco.diff
@ -0,0 +1,16 @@
+Changes in module 'nf-core/falco'
+--- modules/nf-core/falco/main.nf
+++ modules/nf-core/falco/main.nf
+@@ -33,7 +33,9 @@
+         """
+     } else {
+         """
+-        falco $args --threads $task.cpus ${reads}
+        [ ! -f  ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
+        [ ! -f  ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
+        falco $args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz
+ 
+         cat <<-END_VERSIONS > versions.yml
+         "${task.process}":
+
+************************************************************
--- a/modules/nf-core/falco/main.nf
+++ b/modules/nf-core/falco/main.nf
@ -33,7 +33,9 @@ process FALCO {
        """
    } else {
        """
-        falco $args --threads $task.cpus ${reads}
+        [ ! -f  ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
+        [ ! -f  ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
+        falco $args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz

        cat <<-END_VERSIONS > versions.yml
        "${task.process}":
--- a/modules/nf-core/motus/merge/main.nf
+++ b/modules/nf-core/motus/merge/main.nf
@ -1,13 +1,11 @@
-VERSION = '3.0.1'
-
 process MOTUS_MERGE {
    tag "$meta.id"
    label 'process_single'

-    conda (params.enable_conda ? "bioconda::motus=3.0.1" : null)
+    conda (params.enable_conda ? "bioconda::motus=3.0.3" : null)
    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/motus:3.0.1--pyhdfd78af_0':
-        'quay.io/biocontainers/motus:3.0.1--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/motus:3.0.3--pyhdfd78af_0':
+        'quay.io/biocontainers/motus:3.0.3--pyhdfd78af_0' }"

    input:
    tuple val(meta), path(input)
--- a/modules/nf-core/motus/merge/meta.yml
+++ b/modules/nf-core/motus/merge/meta.yml
@ -14,7 +14,7 @@ tools:
      homepage: "https://motu-tool.org/"
      documentation: "https://github.com/motu-tool/mOTUs/wiki"
      tool_dev_url: "https://github.com/motu-tool/mOTUs"
-      doi: "10.1038/s41467-019-08844-4"
+      doi: "10.1186/s40168-022-01410-z"
      licence: "['GPL v3']"

 input:
--- a/modules/nf-core/motus/profile/main.nf
+++ b/modules/nf-core/motus/profile/main.nf
@ -2,10 +2,10 @@ process MOTUS_PROFILE {
    tag "$meta.id"
    label 'process_medium'

-    conda (params.enable_conda ? "bioconda::motus=3.0.1" : null)
+    conda (params.enable_conda ? "bioconda::motus=3.0.3" : null)
    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/motus:3.0.1--pyhdfd78af_0':
-        'quay.io/biocontainers/motus:3.0.1--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/motus:3.0.3--pyhdfd78af_0':
+        'quay.io/biocontainers/motus:3.0.3--pyhdfd78af_0' }"

    input:
    tuple val(meta), path(reads)
--- a/modules/nf-core/motus/profile/meta.yml
+++ b/modules/nf-core/motus/profile/meta.yml
@ -11,7 +11,7 @@ tools:
      homepage: "https://motu-tool.org/"
      documentation: "https://github.com/motu-tool/mOTUs/wiki"
      tool_dev_url: "https://github.com/motu-tool/mOTUs"
-      doi: "10.1038/s41467-019-08844-4"
+      doi: "10.1186/s40168-022-01410-z"
      licence: "['GPL v3']"

 input:
--- a/subworkflows/local/db_check.nf
+++ b/subworkflows/local/db_check.nf
@ -2,7 +2,6 @@
 // Check input samplesheet and get read channels
 //

-include { DATABASE_CHECK   } from '../../modules/local/database_check'
 include { UNTAR            } from '../../modules/nf-core/untar/main'

 workflow DB_CHECK {
@ -10,15 +9,27 @@ workflow DB_CHECK {
    dbsheet // file: /path/to/dbsheet.csv

    main:
+    ch_versions = Channel.empty()

-    // TODO: make database sheet check
-    // Checks:
-    // 1) no duplicates,
-    // 2) args do not have quotes, e.g. just `,,` and NOT `,"",`
-    parsed_samplesheet = DATABASE_CHECK ( dbsheet )
-        .csv
+    // special check to check _between_ rows, for which we must group rows together
+    // note: this will run in parallel to within-row validity, but we can assume this will run faster thus will fail first
+    Channel.fromPath(dbsheet)
            .splitCsv ( header:true, sep:',' )
-        .map { create_db_channels(it) }
+            .map {[it.tool, it.db_name] }
+            .groupTuple()
+            .map {
+                tool, db_name ->
+                    def unique_names = db_name.unique(false)
+                    if ( unique_names.size() < db_name.size() ) exit 1, "[nf-core/taxprofiler] ERROR: Each database for a tool must have a unique name, duplicated detected. Tool: ${tool}, Database name: ${unique_names}"
+            }
+
+    // normal checks for within-row validity, so can be moved to separate functions
+    parsed_samplesheet = Channel.fromPath(dbsheet)
+        .splitCsv ( header:true, sep:',' )
+        .map {
+            validate_db_rows(it)
+            create_db_channels(it)
+        }

    ch_dbs_for_untar = parsed_samplesheet
        .branch {
@ -29,12 +40,32 @@ workflow DB_CHECK {
    // TODO Filter to only run UNTAR on DBs of tools actually using?
    // TODO make optional whether to save
    UNTAR ( ch_dbs_for_untar.untar )
+    ch_versions = ch_versions.mix(UNTAR.out.versions.first())

    ch_final_dbs = ch_dbs_for_untar.skip.mix( UNTAR.out.untar )

    emit:
    dbs = ch_final_dbs                        // channel: [ val(meta), [ db ] ]
-    versions = DATABASE_CHECK.out.versions.mix(UNTAR.out.versions.first()) // channel: [ versions.yml ]
+    versions = ch_versions                   // channel: [ versions.yml ]
+}
+
+def validate_db_rows(LinkedHashMap row){
+
+        // check minimum number of columns
+        if (row.size() < 4) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database input sheet - malformed row (e.g. missing column). See documentation for more information. Error in: ${row}"
+
+        // all columns there
+        def expected_headers = ['tool', 'db_name', 'db_params', 'db_path']
+        if ( !row.keySet().containsAll(expected_headers) ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database input sheet - malformed column names. Please check input TSV. Column names should be: ${expected_keys.join(", ")}"
+
+        // valid tools specified// TIFNISIH LIST
+        def expected_tools = [ "bracken", "centrifuge", "diamond", "kaiju",  "kraken2", "krakenuniq", "malt", "metaphlan3", "motus" ]
+        if ( !expected_tools.contains(row.tool) ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid tool name. Please see documentation for all supported profilers. Error in: ${row}"
+
+        // detect quotes in params
+        if ( row.db_params.contains('"') ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database db_params entry. No quotes allowed. Error in: ${row}"
+        if ( row.db_params.contains("'") ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database db_params entry. No quotes allowed. Error in: ${row}"
+
 }

 def create_db_channels(LinkedHashMap row) {
@ -45,9 +76,11 @@ def create_db_channels(LinkedHashMap row) {

    def array = []
    if (!file(row.db_path, type: 'dir').exists()) {
-        exit 1, "ERROR: Please check input samplesheet -> database could not be found!\n${row.db_path}"
+        exit 1, "ERROR: Please check input samplesheet -> database path could not be found!\n${row.db_path}"
    }
    array = [ meta, file(row.db_path) ]

    return array
 }
+
+
--- a/subworkflows/local/profiling.nf
+++ b/subworkflows/local/profiling.nf
@ -41,14 +41,14 @@ workflow PROFILING {
            }
            .combine(databases)
            .branch {
-                malt:    it[2]['tool'] == 'malt'
-                kraken2: it[2]['tool'] == 'kraken2' || it[2]['tool'] == 'bracken' // to reuse the kraken module to produce the input data for bracken
-                metaphlan3: it[2]['tool'] == 'metaphlan3'
                centrifuge: it[2]['tool'] == 'centrifuge'
-                kaiju: it[2]['tool'] == 'kaiju'
                diamond: it[2]['tool'] == 'diamond'
-                motus: it[2]['tool'] == 'motus'
+                kaiju: it[2]['tool'] == 'kaiju'
+                kraken2: it[2]['tool'] == 'kraken2' || it[2]['tool'] == 'bracken' // to reuse the kraken module to produce the input data for bracken
                krakenuniq: it[2]['tool'] == 'krakenuniq'
+                malt:    it[2]['tool'] == 'malt'
+                metaphlan3: it[2]['tool'] == 'metaphlan3'
+                motus: it[2]['tool'] == 'motus'
                unknown: true
            }

--- a/subworkflows/local/standardisation_profiles.nf
+++ b/subworkflows/local/standardisation_profiles.nf
@ -2,6 +2,7 @@
 // Standardise output files e.g. aggregation
 //

+include { BRACKEN_COMBINEBRACKENOUTPUTS                                         } from '../../modules/nf-core/bracken/combinebrackenoutputs/main'
 include { KAIJU_KAIJU2TABLE                                                     } from '../../modules/nf-core/kaiju/kaiju2table/main'
 include { KRAKENTOOLS_COMBINEKREPORTS as KRAKENTOOLS_COMBINEKREPORTS_KRAKEN     } from '../../modules/nf-core/krakentools/combinekreports/main'
 include { KRAKENTOOLS_COMBINEKREPORTS as KRAKENTOOLS_COMBINEKREPORTS_CENTRIFUGE } from '../../modules/nf-core/krakentools/combinekreports/main'
@ -25,10 +26,11 @@ workflow STANDARDISATION_PROFILES {
    */
    ch_input_profiles = profiles
        .branch {
-            motus: it[0]['tool'] == 'motus'
-            kraken2: it[0]['tool'] == 'kraken2'
+            bracken: it[0]['tool'] == 'bracken'
            centrifuge: it[0]['tool'] == 'centrifuge'
+            kraken2: it[0]['tool'] == 'kraken2'
            metaphlan3: it[0]['tool'] == 'metaphlan3'
+            motus: it[0]['tool'] == 'motus'
            unknown: true
        }

@ -49,6 +51,17 @@ workflow STANDARDISATION_PROFILES {
        Standardise and aggregate
    */

+    // Bracken
+
+    ch_profiles_for_bracken = ch_input_profiles.bracken
+                            .map { [it[0]['db_name'], it[1]] }
+                            .groupTuple()
+                            .map {
+                                [[id:it[0]], it[1]]
+                            }
+
+    BRACKEN_COMBINEBRACKENOUTPUTS ( ch_profiles_for_bracken )
+
    // CENTRIFUGE

    // Collect and replace id for db_name for prefix
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@ -25,7 +25,7 @@ if ( params.input ) {
    exit 1, "Input samplesheet, or PEP config and base directory not specified"
 }

-if (params.databases) { ch_databases = file(params.databases) } else { exit 1, 'Input database sheet not specified!' }
+if (params.databases) { ch_databases = file(params.databases, checkIfExists: true) } else { exit 1, 'Input database sheet not specified!' }

 if (params.shortread_qc_mergepairs && params.run_malt ) log.warn "[nf-core/taxprofiler] MALT does not accept uncollapsed paired-reads. Pairs will be profiled as separate files."
 if (params.shortread_qc_includeunmerged && !params.shortread_qc_mergepairs) exit 1, "ERROR: [nf-core/taxprofiler] cannot include unmerged reads when merging is not turned on. Please specify --shortread_qc_mergepairs"