From 8939ce3e2088a7ba89c0fdbf29901e98df4e231f Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Sun, 11 Dec 2022 16:52:34 +0100
Subject: [PATCH 01/14] Start adding bracken/combinebrackenreports (need
 smodule update)

---
 conf/modules.config                           |  9 +++++
 modules.json                                  |  5 +++
 .../bracken/combinebrackenoutputs/main.nf     | 36 +++++++++++++++++++
 .../bracken/combinebrackenoutputs/meta.yml    | 31 ++++++++++++++++
 .../local/standardisation_profiles.nf         | 19 ++++++++--
 5 files changed, 97 insertions(+), 3 deletions(-)
 create mode 100644 modules/nf-core/bracken/combinebrackenoutputs/main.nf
 create mode 100644 modules/nf-core/bracken/combinebrackenoutputs/meta.yml

diff --git a/conf/modules.config b/conf/modules.config
index dd85c0c..a8bf3e8 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -321,6 +321,15 @@ process {
         ]
     }
 
+    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 {
         ext.prefix = { "kraken2_${meta.id}_combined_reports" }
         publishDir = [
diff --git a/modules.json b/modules.json
index 377e902..7815f5d 100644
--- a/modules.json
+++ b/modules.json
@@ -30,6 +30,11 @@
                         "git_sha": "8cab56516076b23c6f8eb1ac20ba4ce9692c85e1",
                         "installed_by": ["modules"]
                     },
+                    "bracken/combinebrackenoutputs": {
+                        "branch": "master",
+                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",
+                        "installed_by": ["modules"]
+                    },
                     "cat/fastq": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",
diff --git a/modules/nf-core/bracken/combinebrackenoutputs/main.nf b/modules/nf-core/bracken/combinebrackenoutputs/main.nf
new file mode 100644
index 0000000..73b7148
--- /dev/null
+++ b/modules/nf-core/bracken/combinebrackenoutputs/main.nf
@@ -0,0 +1,36 @@
+process BRACKEN_COMBINEBRACKENOUTPUTS {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::bracken=2.7" : null)
+    container "${ 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:
+    path input
+
+    output:
+    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 ?: "bracken_combined.txt"
+    // 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 ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        combine_bracken_output: ${VERSION}
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/bracken/combinebrackenoutputs/meta.yml b/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
new file mode 100644
index 0000000..c4a9712
--- /dev/null
+++ b/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
@@ -0,0 +1,31 @@
+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:
+  - input:
+      type: file
+      description: List of output files from bracken
+      pattern: "*"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - txt:
+      type: file
+      description: Combined output in table format
+      pattern: "*.txt"
+
+authors:
+  - "@jfy133"
diff --git a/subworkflows/local/standardisation_profiles.nf b/subworkflows/local/standardisation_profiles.nf
index 8c73472..582aaed 100644
--- 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
         }
 
@@ -49,7 +51,18 @@ workflow STANDARDISATION_PROFILES {
         Standardise and aggregate
     */
 
-        // CENTRIFUGE
+    // 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
     // Have to sort by size to ensure first file actually has hits otherwise

From 07bd989bc6f8e663c9e10b998101d8ed86dc5d5f Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Mon, 12 Dec 2022 10:02:22 +0100
Subject: [PATCH 02/14] Start work on groovy native datbase checks

---
 conf/modules.config             |  8 --------
 modules/local/database_check.nf | 29 ---------------------------
 subworkflows/local/db_check.nf  | 35 +++++++++++++++++++++++++++------
 workflows/taxprofiler.nf        |  2 +-
 4 files changed, 30 insertions(+), 44 deletions(-)
 delete mode 100644 modules/local/database_check.nf

diff --git a/conf/modules.config b/conf/modules.config
index dd85c0c..017e0c9 100644
--- 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}_${meta.run_accession}_raw" }
diff --git a/modules/local/database_check.nf b/modules/local/database_check.nf
deleted file mode 100644
index ccf611c..0000000
--- a/modules/local/database_check.nf
+++ /dev/null
@@ -1,29 +0,0 @@
-process DATABASE_CHECK {
-    tag "$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
-    """
-}
diff --git a/subworkflows/local/db_check.nf b/subworkflows/local/db_check.nf
index 5d0c4eb..ce26905 100644
--- 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 +9,18 @@ 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
+
+    parsed_samplesheet = Channel.fromPath(dbsheet)
         .splitCsv ( header:true, sep:',' )
-        .map { create_db_channels(it) }
+        .map {
+            validate_db_sheet(it)
+            create_db_channels(it)
+        }
 
     ch_dbs_for_untar = parsed_samplesheet
         .branch {
@@ -29,12 +31,31 @@ 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_sheet(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", "malt", "metaphlan3"  ]
+
+        // 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) {
@@ -51,3 +72,5 @@ def create_db_channels(LinkedHashMap row) {
 
     return array
 }
+
+
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index c9f002c..7bcfc3a 100644
--- 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"

From 3df0a383da88107a0cd34d6b8b3573a0a9a0fed4 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Mon, 12 Dec 2022 10:10:24 +0100
Subject: [PATCH 03/14] Update combine bracken outputs to include meta for
 publishing purposes

---
 conf/modules.config                                   |  4 ++--
 modules.json                                          |  2 +-
 modules/nf-core/bracken/combinebrackenoutputs/main.nf | 11 ++++++-----
 .../nf-core/bracken/combinebrackenoutputs/meta.yml    | 10 ++++++++++
 4 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index a8bf3e8..742992d 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -330,12 +330,12 @@ process {
         ]
     }
 
-    withName: KRAKENTOOLS_COMBINEKREPORTS {
+    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'
         ]
     }
 
diff --git a/modules.json b/modules.json
index 7815f5d..b46e88d 100644
--- a/modules.json
+++ b/modules.json
@@ -32,7 +32,7 @@
                     },
                     "bracken/combinebrackenoutputs": {
                         "branch": "master",
-                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905",
+                        "git_sha": "9c87d5fdad182590a370ea43a4ecebd200a6f6fb",
                         "installed_by": ["modules"]
                     },
                     "cat/fastq": {
diff --git a/modules/nf-core/bracken/combinebrackenoutputs/main.nf b/modules/nf-core/bracken/combinebrackenoutputs/main.nf
index 73b7148..977030c 100644
--- a/modules/nf-core/bracken/combinebrackenoutputs/main.nf
+++ b/modules/nf-core/bracken/combinebrackenoutputs/main.nf
@@ -1,4 +1,5 @@
 process BRACKEN_COMBINEBRACKENOUTPUTS {
+    tag "$meta.id"
     label 'process_low'
 
     conda (params.enable_conda ? "bioconda::bracken=2.7" : null)
@@ -7,18 +8,18 @@ process BRACKEN_COMBINEBRACKENOUTPUTS {
         'quay.io/biocontainers/bracken:2.7--py39hc16433a_0' }"
 
     input:
-    path input
+    tuple val(meta), path(input)
 
     output:
-    path "*.txt"       , emit: txt
-    path "versions.yml", emit: versions
+    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 ?: "bracken_combined.txt"
+    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'
@@ -26,7 +27,7 @@ process BRACKEN_COMBINEBRACKENOUTPUTS {
     combine_bracken_outputs.py \\
         $args \\
         --files ${input} \\
-        -o ${prefix}
+        -o ${prefix}.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/nf-core/bracken/combinebrackenoutputs/meta.yml b/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
index c4a9712..9ad5385 100644
--- a/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
+++ b/modules/nf-core/bracken/combinebrackenoutputs/meta.yml
@@ -12,12 +12,22 @@ tools:
       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

From 460f3ca157bd618dde7dbc20f5c99bdd2bda731b Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Mon, 12 Dec 2022 11:03:40 +0100
Subject: [PATCH 04/14] Add database sheet validation

---
 subworkflows/local/db_check.nf  | 31 ++++++++++++++++++++-----------
 subworkflows/local/profiling.nf | 10 +++++-----
 2 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/subworkflows/local/db_check.nf b/subworkflows/local/db_check.nf
index ce26905..4ed786d 100644
--- a/subworkflows/local/db_check.nf
+++ b/subworkflows/local/db_check.nf
@@ -11,14 +11,22 @@ workflow DB_CHECK {
     main:
     ch_versions = Channel.empty()
 
-    // TODO: make database sheet check
-    // Checks:
-    // 1) no duplicates,
+    // special check to check _between_ rows, for which we must group rows together
+    Channel.fromPath(dbsheet)
+            .splitCsv ( header:true, sep:',' )
+            .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_sheet(it)
+            validate_db_rows(it)
             create_db_channels(it)
         }
 
@@ -40,21 +48,22 @@ workflow DB_CHECK {
     versions = ch_versions                   // channel: [ versions.yml ]
 }
 
-def validate_db_sheet(LinkedHashMap row){
+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}, "
+        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(", ")}"
+        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", "malt", "metaphlan3"  ]
+        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}"
+        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}"
 
 }
 
@@ -66,7 +75,7 @@ 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) ]
 
diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf
index f5c970c..6613648 100644
--- 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
             }
 

From 7c66968fef7ec7bd2ca44e5cb1571814817acf16 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Mon, 12 Dec 2022 11:04:21 +0100
Subject: [PATCH 05/14] More comments

---
 subworkflows/local/db_check.nf | 1 +
 1 file changed, 1 insertion(+)

diff --git a/subworkflows/local/db_check.nf b/subworkflows/local/db_check.nf
index 4ed786d..14078d9 100644
--- a/subworkflows/local/db_check.nf
+++ b/subworkflows/local/db_check.nf
@@ -12,6 +12,7 @@ workflow DB_CHECK {
     ch_versions = Channel.empty()
 
     // 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 {[it.tool, it.db_name] }

From e31e7d31725cf035a51f3e796c0e52ff62b32704 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Mon, 12 Dec 2022 15:42:01 +0100
Subject: [PATCH 06/14] Update mOTUs to 3.0.3

---
 modules.json                           | 4 ++--
 modules/nf-core/motus/merge/main.nf    | 8 +++-----
 modules/nf-core/motus/merge/meta.yml   | 2 +-
 modules/nf-core/motus/profile/main.nf  | 6 +++---
 modules/nf-core/motus/profile/meta.yml | 2 +-
 5 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/modules.json b/modules.json
index b46e88d..a3017f7 100644
--- a/modules.json
+++ b/modules.json
@@ -172,12 +172,12 @@
                     },
                     "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": {
diff --git a/modules/nf-core/motus/merge/main.nf b/modules/nf-core/motus/merge/main.nf
index d9f091e..5041cf0 100644
--- 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)
diff --git a/modules/nf-core/motus/merge/meta.yml b/modules/nf-core/motus/merge/meta.yml
index 02d11d0..24ae939 100644
--- 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:
diff --git a/modules/nf-core/motus/profile/main.nf b/modules/nf-core/motus/profile/main.nf
index bd7a127..8a76250 100644
--- 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)
diff --git a/modules/nf-core/motus/profile/meta.yml b/modules/nf-core/motus/profile/meta.yml
index 3c3b660..1202042 100644
--- 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:

From 88589fbc53fa861a76509351bb032474e6ef3161 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Thu, 15 Dec 2022 10:35:06 +0100
Subject: [PATCH 07/14] Fix publishing of log files of rpreprocessing steps

---
 conf/modules.config | 144 ++++++++++++++++++++++++++++++--------------
 1 file changed, 100 insertions(+), 44 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 747a03a..5127ff5 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -61,10 +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: '*.fastq.gz',
+                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/fastp" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{log,html,json}'
+            ]
         ]
     }
 
@@ -82,10 +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: '*.fastq.gz',
+                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/fastp" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{log,html,json}'
+            ]
         ]
     }
 
@@ -98,10 +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: '*.fastq.gz',
+                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/adapterremoval" },
+                mode: params.publish_dir_mode,
+                pattern: '*.settings'
+            ]
         ]
     }
 
@@ -117,20 +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: '*.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: '*.fastq.gz',
+                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/porechop" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
         ]
     }
 
@@ -143,10 +178,17 @@ process {
         .join(' ').trim()
         ext.prefix = { "${meta.id}_${meta.run_accession}_filtered" }
         publishDir = [
-            path: { "${params.outdir}/filtlong" },
-            mode: params.publish_dir_mode,
-            pattern: '*.{fastq.gz,log}',
-            enabled: params.save_preprocessed_reads
+            [
+                path: { "${params.outdir}/filtlong" },
+                mode: params.publish_dir_mode,
+                pattern: '*.fastq.gz',
+                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/filtlong" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
         ]
     }
 
@@ -163,21 +205,21 @@ process {
         ext.prefix = { "${meta.id}_${meta.run_accession}" }
         publishDir = [
             [
-            path: { "${params.outdir}/bowtie2/align" },
-            mode: params.publish_dir_mode,
-            pattern: '*.log'
+                path: { "${params.outdir}/bowtie2/align" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
             ],
             [
-            path: { "${params.outdir}/bowtie2/align" },
-            mode: params.publish_dir_mode,
-            enabled: params.save_hostremoval_mapped,
-            pattern: '*.bam'
+                path: { "${params.outdir}/bowtie2/align" },
+                mode: params.publish_dir_mode,
+                enabled: params.save_hostremoval_mapped,
+                pattern: '*.bam'
             ],
             [
-            path: { "${params.outdir}/bowtie2/align" },
-            mode: params.publish_dir_mode,
-            enabled: params.save_hostremoval_unmapped,
-            pattern: '*.fastq.gz'
+                path: { "${params.outdir}/bowtie2/align" },
+                mode: params.publish_dir_mode,
+                enabled: params.save_hostremoval_unmapped,
+                pattern: '*.fastq.gz'
             ]
         ]
     }
@@ -240,10 +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: '*.{fastq.gz,log}',
+                enabled: params.save_complexityfiltered_reads
+            ],
+            [
+                path: { "${params.outdir}/bbduk/" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ]
         ]
     }
 
@@ -255,10 +304,17 @@ process {
             ].join(' ').trim()
         ext.prefix = { "${meta.id}-${meta.run_accession}" }
         publishDir = [
-            path: { "${params.outdir}/prinseqplusplus/" },
-            mode: params.publish_dir_mode,
-            pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz,log}',
-            enabled: params.save_complexityfiltered_reads
+            [
+                path: { "${params.outdir}/prinseqplusplus/" },
+                mode: params.publish_dir_mode,
+                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'
+            ]
         ]
     }
 
@@ -318,7 +374,7 @@ process {
         publishDir = [
             path: { "${params.outdir}/bracken/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt}'
+            pattern: '*.txt'
         ]
     }
 

From 3b86a22556825e3aa7e15cd5fa4d415343d3ac13 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Thu, 15 Dec 2022 12:57:49 +0100
Subject: [PATCH 08/14] Fix falco publication names

---
 conf/modules.config           | 4 ++--
 modules/nf-core/falco/main.nf | 4 +++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 5127ff5..f50b20c 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -33,7 +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,
@@ -42,7 +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,
diff --git a/modules/nf-core/falco/main.nf b/modules/nf-core/falco/main.nf
index 1688162..b279c57 100644
--- 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}":

From 9e6a91aff929ddd12170278565771571c18f0dda Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Thu, 15 Dec 2022 13:25:01 +0100
Subject: [PATCH 09/14] Distinguish  Kraken2 from Bracken

---
 conf/modules.config | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index f50b20c..60ebaa4 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -351,7 +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,
@@ -361,7 +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,

From 0bdc119f9cee402257816ef4362b42a2b92b4866 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Thu, 15 Dec 2022 13:27:41 +0100
Subject: [PATCH 10/14] Include falco patch

---
 modules.json                     |  3 ++-
 modules/nf-core/falco/falco.diff | 16 ++++++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)
 create mode 100644 modules/nf-core/falco/falco.diff

diff --git a/modules.json b/modules.json
index a3017f7..7eb15e3 100644
--- a/modules.json
+++ b/modules.json
@@ -73,7 +73,8 @@
                     "falco": {
                         "branch": "master",
                         "git_sha": "fc959214036403ad83efe7a41d43d0606c445cda",
-                        "installed_by": ["modules"]
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/falco/falco.diff"
                     },
                     "fastp": {
                         "branch": "master",
diff --git a/modules/nf-core/falco/falco.diff b/modules/nf-core/falco/falco.diff
new file mode 100644
index 0000000..4c726b9
--- /dev/null
+++ 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}":
+
+************************************************************

From d6db04503e0fe2d643a7f34cb915a708f490de1e Mon Sep 17 00:00:00 2001
From: Sofia Stamouli <91951607+sofstam@users.noreply.github.com>
Date: Thu, 15 Dec 2022 17:04:45 +0100
Subject: [PATCH 11/14] Configuration of multiqc report

---
 assets/multiqc_config.yml | 207 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 205 insertions(+), 2 deletions(-)

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
index e4a04a9..865879b 100644
--- 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 +89,172 @@ 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"

From a2c81e33fd6496e1cfa81d091d870cdda1030687 Mon Sep 17 00:00:00 2001
From: Sofia Stamouli <sofia.stamouli@scilifelab.se>
Date: Fri, 16 Dec 2022 08:38:58 +0100
Subject: [PATCH 12/14] Prettier

---
 assets/multiqc_config.yml | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
index 865879b..1deb8f8 100644
--- a/assets/multiqc_config.yml
+++ b/assets/multiqc_config.yml
@@ -251,10 +251,9 @@ table_columns_name:
     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"
+  - ".kraken2.kraken2.report.txt"
+  - ".centrifuge.txt"
+  - ".bracken.kraken2.report.txt"
+  - ".settings"

From 5a592f086e9e7c7cd448f9e1f0c276f218885080 Mon Sep 17 00:00:00 2001
From: Sofia Stamouli <91951607+sofstam@users.noreply.github.com>
Date: Fri, 16 Dec 2022 11:46:35 +0100
Subject: [PATCH 13/14] Update assets/multiqc_config.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
---
 assets/multiqc_config.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
index 1deb8f8..014d9f7 100644
--- a/assets/multiqc_config.yml
+++ b/assets/multiqc_config.yml
@@ -246,7 +246,7 @@ table_columns_name:
     avg_sequence_length: "Length Processed Reads"
     percent_gc: "% GC Processed Reads"
     percent_duplicates: "% Dups Processed Reads"
-    percent_fails: "%Failed Processed Reads"
+    percent_fails: "% Failed Processed Reads"
   Samtools Stats:
     raw_total_sequences: "Nr. Reads Into Mapping"
     reads_mapped: "Nr. Mapped Reads"

From 07a1cfae62ceb98b074615868550d1f933a021b4 Mon Sep 17 00:00:00 2001
From: Sofia Stamouli <91951607+sofstam@users.noreply.github.com>
Date: Fri, 16 Dec 2022 11:46:42 +0100
Subject: [PATCH 14/14] Update assets/multiqc_config.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
---
 assets/multiqc_config.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
index 014d9f7..6bc13c2 100644
--- a/assets/multiqc_config.yml
+++ b/assets/multiqc_config.yml
@@ -240,7 +240,7 @@ table_columns_name:
     avg_sequence_length: "Length Processed Reads"
     percent_gc: "% GC Processed Reads"
     percent_duplicates: "% Dups Processed Reads"
-    percent_fails: "%Failed Processed Reads"
+    percent_fails: "% Failed Processed Reads"
   Falco (post-Trimming):
     total_sequences: "Nr. Processed Reads"
     avg_sequence_length: "Length Processed Reads"