From 7b08c49cd6cb6471384a26c1202733cad0fe58ae Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 11:54:54 +0200
Subject: [PATCH 01/19] Re-add run merging and gonna let GHA see if it works
 >.>

---
 .github/workflows/ci.yml |  1 +
 nextflow.config          |  2 ++
 workflows/taxprofiler.nf | 25 +++++++++++++++++++++++--
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 79148f0..7678645 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -39,6 +39,7 @@ jobs:
           - "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
           - "--shortread_complexityfilter_tool bbduk"
           - "--shortread_complexityfilter_tool prinseq"
+          - "--run_merging"
 
     steps:
       - name: Check out pipeline code
diff --git a/nextflow.config b/nextflow.config
index 19cc823..1c69d36 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -76,6 +76,8 @@ params {
     shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
     save_complexityfiltered_reads                        = false
 
+    // run merging
+    run_merging                = false
 
     // MALT
     run_malt                   = false
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 3b08402..61eda6e 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -125,13 +125,34 @@ workflow TAXPROFILER {
         ch_shortreads_filtered = ch_shortreads_preprocessed
     }
 
+    /*
+        STEP: Run merging
+    */
+
+    if ( params.run_merging ) {
+        ch_reads_for_cat = ch_shortreads_filtered
+            .mix( ch_longreads_preprocessed )
+            .map {
+                meta, reads ->
+                    def meta_new = meta.clone()
+                    meta_new['run_accession'].remove()
+                    [ meta_new, reads ]
+            }
+            .groupTuple()
+
+        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat )
+
+    } else {
+        ch_reads_runmerged = ch_shortreads_filtered
+            .mix( ch_longreads_preprocessed )
+    }
+
     /*
         COMBINE READS WITH POSSIBLE DATABASES
     */
 
     // 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 = ch_shortreads_filtered
-            .mix( ch_longreads_preprocessed )
+    ch_input_for_profiling = ch_reads_runmerged
             .combine(DB_CHECK.out.dbs)
             .branch {
                 malt:    it[2]['tool'] == 'malt'

From 74c496f6af04e15e1625d7311791004a645b3a21 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 11:58:16 +0200
Subject: [PATCH 02/19] Fix CAT_FASTQ output

---
 workflows/taxprofiler.nf | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 61eda6e..2d0c17d 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -140,8 +140,7 @@ workflow TAXPROFILER {
             }
             .groupTuple()
 
-        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat )
-
+        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat ).reads
     } else {
         ch_reads_runmerged = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )
@@ -247,6 +246,10 @@ workflow TAXPROFILER {
         ch_versions = ch_versions.mix( SHORTREAD_COMPLEXITYFILTERING.out.versions )
     }
 
+    if (params.run_merging){
+        ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
+    }
+
     if (params.run_kraken2) {
         ch_multiqc_files = ch_multiqc_files.mix( KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([])  )
         ch_versions = ch_versions.mix( KRAKEN2_KRAKEN2.out.versions.first() )

From 4d726a87e98f56bf1a4e0d52259d9e83f89539ce Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 12:01:07 +0200
Subject: [PATCH 03/19] Fix metadata removal

---
 workflows/taxprofiler.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 2d0c17d..33d9725 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -135,7 +135,7 @@ workflow TAXPROFILER {
             .map {
                 meta, reads ->
                     def meta_new = meta.clone()
-                    meta_new['run_accession'].remove()
+                    meta_new.remove('run_accession')
                     [ meta_new, reads ]
             }
             .groupTuple()

From d130a72d74899c3fd85db3c1c751b7b6848fd031 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 13:09:23 +0200
Subject: [PATCH 04/19] Get this working

---
 .github/workflows/ci.yml              |  1 +
 conf/modules.config                   |  6 +++---
 subworkflows/local/shortread_fastp.nf |  4 ++--
 workflows/taxprofiler.nf              | 18 ++++++++++++++++--
 4 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 7678645..53423cb 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -40,6 +40,7 @@ jobs:
           - "--shortread_complexityfilter_tool bbduk"
           - "--shortread_complexityfilter_tool prinseq"
           - "--run_merging"
+          - "--run_merging --shortread_clipmerge_mergepairs"
 
     steps:
       - name: Check out pipeline code
diff --git a/conf/modules.config b/conf/modules.config
index b59850f..7602e3f 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -163,7 +163,7 @@ process {
 
     withName: MALT_RUN {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/malt/${meta.db_name}" },
             mode: params.publish_dir_mode,
@@ -173,7 +173,7 @@ process {
 
     withName: KRAKEN2_KRAKEN2 {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/kraken2/${meta.db_name}" },
             mode: params.publish_dir_mode,
@@ -183,7 +183,7 @@ process {
 
     withName: METAPHLAN3 {
         publishDir = [
-            path: { "${params.outdir}/metaphlan3/${meta.db_name}" },
+        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
             mode: params.publish_dir_mode,
             pattern: '*.{biom,txt}'
         ]
diff --git a/subworkflows/local/shortread_fastp.nf b/subworkflows/local/shortread_fastp.nf
index 18baf17..04057b1 100644
--- 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 )
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 33d9725..e04d4d6 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -130,7 +130,8 @@ workflow TAXPROFILER {
     */
 
     if ( params.run_merging ) {
-        ch_reads_for_cat = ch_shortreads_filtered
+
+        ch_reads_for_cat_branch = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )
             .map {
                 meta, reads ->
@@ -139,8 +140,21 @@ workflow TAXPROFILER {
                     [ meta_new, reads ]
             }
             .groupTuple()
+            .map {
+                meta, reads ->
+                    [ meta, reads.flatten() ]
+            }
+            .branch {
+                // we can't concate files if there is not a second run, we branch
+                // here to separate them out, and mix after
+                cat: ( it[0]['single_end'] && it[1].size() > 1 ) || ( !it[0]['single_end'] && it[1].size() > 2 )
+                skip: true
+            }
+
+        ch_reads_for_cat_branch.cat.dump(tag: "for_catting")
+
+        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads.mix( ch_reads_for_cat_branch.skip )
 
-        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat ).reads
     } else {
         ch_reads_runmerged = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )

From ca011ccc5b363ea9d6c1eaf44713a9c09e471f39 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 13:28:37 +0200
Subject: [PATCH 05/19] Fix cat_fastq naming logic?

---
 conf/modules.config      | 19 +++++++++++++++----
 nextflow.config          |  1 +
 nextflow_schema.json     | 38 +++++++++++++++++++++++++++++---------
 workflows/taxprofiler.nf |  4 ----
 4 files changed, 45 insertions(+), 17 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 7602e3f..97e9510 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -161,9 +161,19 @@ process {
         ]
     }
 
+    withName: CAT_FASTQ {
+        ext.prefix = { "${meta.id}-${meta.run_accession}" }
+        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 = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = params.run_merging ? { "${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,
@@ -173,7 +183,7 @@ process {
 
     withName: KRAKEN2_KRAKEN2 {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        ext.prefix = params.run_merging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
         publishDir = [
             path: { "${params.outdir}/kraken2/${meta.db_name}" },
             mode: params.publish_dir_mode,
@@ -182,12 +192,13 @@ process {
     }
 
     withName: METAPHLAN3 {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.run_merging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
         publishDir = [
-        ext.prefix = if params.run_merging : { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+            path: { "${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: CUSTOM_DUMPSOFTWAREVERSIONS {
diff --git a/nextflow.config b/nextflow.config
index 1c69d36..d969ed9 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -78,6 +78,7 @@ params {
 
     // run merging
     run_merging                = false
+    save_runmerged_reads       = false
 
     // MALT
     run_malt                   = false
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 6858409..0b4b4fb 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -10,7 +10,10 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": ["input", "outdir"],
+            "required": [
+                "input",
+                "outdir"
+            ],
             "properties": {
                 "input": {
                     "type": "string",
@@ -173,7 +176,14 @@
                     "description": "Method used to save pipeline results to output directory.",
                     "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                     "fa_icon": "fas fa-copy",
-                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
+                    "enum": [
+                        "symlink",
+                        "rellink",
+                        "link",
+                        "copy",
+                        "copyNoFollow",
+                        "move"
+                    ],
                     "hidden": true
                 },
                 "email_on_fail": {
@@ -288,7 +298,10 @@
         "shortread_clipmerge_tool": {
             "type": "string",
             "default": "fastp",
-            "enum": ["fastp", "adapterremoval"]
+            "enum": [
+                "fastp",
+                "adapterremoval"
+            ]
         },
         "shortread_clipmerge_skipadaptertrim": {
             "type": "boolean"
@@ -309,8 +322,7 @@
             "default": 15
         },
         "save_preprocessed_reads": {
-            "type": "boolean",
-            "default": false
+            "type": "boolean"
         },
         "shortread_complexityfilter_tool": {
             "type": "string",
@@ -333,15 +345,23 @@
         "shortread_complexityfilter_prinseqplusplus_mode": {
             "type": "string",
             "default": "entropy",
-            "enum": ["entropy", "dust"]
+            "enum": [
+                "entropy",
+                "dust"
+            ]
         },
         "shortread_complexityfilter_prinseqplusplus_dustscore": {
             "type": "number",
             "default": 0.5
         },
         "save_complexityfiltered_reads": {
-            "type": "boolean",
-            "default": false
+            "type": "boolean"
+        },
+        "run_merging": {
+            "type": "boolean"
+        },
+        "save_runmerged_reads": {
+            "type": "boolean"
         }
     }
-}
+}
\ No newline at end of file
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index e04d4d6..bdb93ab 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -140,10 +140,6 @@ workflow TAXPROFILER {
                     [ meta_new, reads ]
             }
             .groupTuple()
-            .map {
-                meta, reads ->
-                    [ meta, reads.flatten() ]
-            }
             .branch {
                 // we can't concate files if there is not a second run, we branch
                 // here to separate them out, and mix after

From a634814d848a68252d81b231e34942f5fa616c83 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 13:34:00 +0200
Subject: [PATCH 06/19] Formatting and fix fastp output

---
 nextflow_schema.json                          | 26 ++++---------------
 .../local/shortread_adapterremoval.nf         |  2 +-
 2 files changed, 6 insertions(+), 22 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 0b4b4fb..64836df 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -10,10 +10,7 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": [
-                "input",
-                "outdir"
-            ],
+            "required": ["input", "outdir"],
             "properties": {
                 "input": {
                     "type": "string",
@@ -176,14 +173,7 @@
                     "description": "Method used to save pipeline results to output directory.",
                     "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                     "fa_icon": "fas fa-copy",
-                    "enum": [
-                        "symlink",
-                        "rellink",
-                        "link",
-                        "copy",
-                        "copyNoFollow",
-                        "move"
-                    ],
+                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                     "hidden": true
                 },
                 "email_on_fail": {
@@ -298,10 +288,7 @@
         "shortread_clipmerge_tool": {
             "type": "string",
             "default": "fastp",
-            "enum": [
-                "fastp",
-                "adapterremoval"
-            ]
+            "enum": ["fastp", "adapterremoval"]
         },
         "shortread_clipmerge_skipadaptertrim": {
             "type": "boolean"
@@ -345,10 +332,7 @@
         "shortread_complexityfilter_prinseqplusplus_mode": {
             "type": "string",
             "default": "entropy",
-            "enum": [
-                "entropy",
-                "dust"
-            ]
+            "enum": ["entropy", "dust"]
         },
         "shortread_complexityfilter_prinseqplusplus_dustscore": {
             "type": "number",
@@ -364,4 +348,4 @@
             "type": "boolean"
         }
     }
-}
\ No newline at end of file
+}
diff --git a/subworkflows/local/shortread_adapterremoval.nf b/subworkflows/local/shortread_adapterremoval.nf
index b573be9..a7948e7 100644
--- a/subworkflows/local/shortread_adapterremoval.nf
+++ b/subworkflows/local/shortread_adapterremoval.nf
@@ -67,7 +67,7 @@ workflow SHORTREAD_ADAPTERREMOVAL {
                 [meta_new, reads]
             }
             .groupTuple()
-            .map { meta, fastq -> [meta, fastq.flatten()] }
+            .map { meta, fastq -> [meta, [ fastq ].flatten()] }
 
 
         CAT_FASTQ(ch_concat_fastq)

From 6c14f2b230a6c6df99e89c44ed8904cb0a5a7b59 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 13:44:52 +0200
Subject: [PATCH 07/19] Remove the flattening?

---
 subworkflows/local/shortread_adapterremoval.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/local/shortread_adapterremoval.nf b/subworkflows/local/shortread_adapterremoval.nf
index a7948e7..735d3b8 100644
--- a/subworkflows/local/shortread_adapterremoval.nf
+++ b/subworkflows/local/shortread_adapterremoval.nf
@@ -67,7 +67,7 @@ workflow SHORTREAD_ADAPTERREMOVAL {
                 [meta_new, reads]
             }
             .groupTuple()
-            .map { meta, fastq -> [meta, [ fastq ].flatten()] }
+            .map { meta, fastq -> [meta, fastq] }
 
 
         CAT_FASTQ(ch_concat_fastq)

From 35cb6e042acf3fbe34c9664bebb9c27ef0d96179 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 13:46:12 +0200
Subject: [PATCH 08/19] Flatten the right thing

---
 subworkflows/local/shortread_adapterremoval.nf | 2 +-
 subworkflows/local/shortread_fastp.nf          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/subworkflows/local/shortread_adapterremoval.nf b/subworkflows/local/shortread_adapterremoval.nf
index 735d3b8..b573be9 100644
--- a/subworkflows/local/shortread_adapterremoval.nf
+++ b/subworkflows/local/shortread_adapterremoval.nf
@@ -67,7 +67,7 @@ workflow SHORTREAD_ADAPTERREMOVAL {
                 [meta_new, reads]
             }
             .groupTuple()
-            .map { meta, fastq -> [meta, fastq] }
+            .map { meta, fastq -> [meta, fastq.flatten()] }
 
 
         CAT_FASTQ(ch_concat_fastq)
diff --git a/subworkflows/local/shortread_fastp.nf b/subworkflows/local/shortread_fastp.nf
index 04057b1..4626691 100644
--- a/subworkflows/local/shortread_fastp.nf
+++ b/subworkflows/local/shortread_fastp.nf
@@ -29,7 +29,7 @@ workflow SHORTREAD_FASTP {
                                             meta, reads ->
                                                 def meta_new = meta.clone()
                                                 meta_new['single_end'] = true
-                                                [ meta_new, reads.flatten() ]
+                                                [ meta_new, [ reads ].flatten() ]
                                         }
 
         ch_fastp_reads_prepped = ch_fastp_reads_prepped_pe.mix( FASTP_SINGLE.out.reads )

From 8839fe22b8856fb1d69e11e2e1e0a4367cb97dc3 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 20:02:22 +0200
Subject: [PATCH 09/19] Fix output tuple for reads

---
 workflows/taxprofiler.nf | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index bdb93ab..7d5f60f 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -149,7 +149,15 @@ workflow TAXPROFILER {
 
         ch_reads_for_cat_branch.cat.dump(tag: "for_catting")
 
-        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads.mix( ch_reads_for_cat_branch.skip )
+        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() ]
+            }
+
+        ch_reads_runmerged.dump(tag: "ch_reads_runmerged" )
 
     } else {
         ch_reads_runmerged = ch_shortreads_filtered

From afb66e445fcb2f9c60f4152e1184f5f8600a843c Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Fri, 8 Apr 2022 21:36:59 +0200
Subject: [PATCH 10/19] Append pairment to ID at profiling to prevent
 multiqc-level filename crash

---
 workflows/taxprofiler.nf | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 7d5f60f..1da812d 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -147,8 +147,6 @@ workflow TAXPROFILER {
                 skip: true
             }
 
-        ch_reads_for_cat_branch.cat.dump(tag: "for_catting")
-
         ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads
             .mix( ch_reads_for_cat_branch.skip )
             .map {
@@ -157,8 +155,6 @@ workflow TAXPROFILER {
                 [ meta, [ reads ].flatten() ]
             }
 
-        ch_reads_runmerged.dump(tag: "ch_reads_runmerged" )
-
     } else {
         ch_reads_runmerged = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )
@@ -168,8 +164,15 @@ workflow TAXPROFILER {
         COMBINE READS WITH POSSIBLE DATABASES
     */
 
-    // 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]
+    // 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 = ch_reads_runmerged
+            .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(DB_CHECK.out.dbs)
             .branch {
                 malt:    it[2]['tool'] == 'malt'

From 989dc55ce107ae01331727eb9678a0d41e22de03 Mon Sep 17 00:00:00 2001
From: sofstam <sofia.stamouli@scilifelab.se>
Date: Mon, 11 Apr 2022 17:42:38 +0200
Subject: [PATCH 11/19] Delete extra nf-core directory

---
 nf-core/modules/centrifuge/centrifuge/main.nf | 61 -----------------
 .../modules/centrifuge/centrifuge/meta.yml    | 66 -------------------
 2 files changed, 127 deletions(-)
 delete mode 100644 nf-core/modules/centrifuge/centrifuge/main.nf
 delete mode 100644 nf-core/modules/centrifuge/centrifuge/meta.yml

diff --git a/nf-core/modules/centrifuge/centrifuge/main.nf b/nf-core/modules/centrifuge/centrifuge/main.nf
deleted file mode 100644
index 3d23fc9..0000000
--- a/nf-core/modules/centrifuge/centrifuge/main.nf
+++ /dev/null
@@ -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
-    """
-}
diff --git a/nf-core/modules/centrifuge/centrifuge/meta.yml b/nf-core/modules/centrifuge/centrifuge/meta.yml
deleted file mode 100644
index a252c00..0000000
--- a/nf-core/modules/centrifuge/centrifuge/meta.yml
+++ /dev/null
@@ -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"

From a5f4fc42d53fce99863a3d135b017b9e468722be Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Tue, 12 Apr 2022 09:25:27 +0200
Subject: [PATCH 12/19] Fix run merging for unmerged PE data

---
 conf/modules.config      | 2 +-
 workflows/taxprofiler.nf | 7 +++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 97e9510..eb448bb 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -162,7 +162,7 @@ process {
     }
 
     withName: CAT_FASTQ {
-        ext.prefix = { "${meta.id}-${meta.run_accession}" }
+        ext.prefix = { "${meta.id}" }
         publishDir = [
             path: { "${params.outdir}/run_merging/" },
             mode: params.publish_dir_mode,
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 1da812d..2eb7e8c 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -139,7 +139,11 @@ workflow TAXPROFILER {
                     meta_new.remove('run_accession')
                     [ meta_new, reads ]
             }
-            .groupTuple()
+            .groupTuple(by: 0)
+            .map {
+                meta, reads ->
+                    [ meta, reads.flatten() ]
+            }
             .branch {
                 // we can't concate files if there is not a second run, we branch
                 // here to separate them out, and mix after
@@ -151,7 +155,6 @@ workflow TAXPROFILER {
             .mix( ch_reads_for_cat_branch.skip )
             .map {
                 meta, reads ->
-
                 [ meta, [ reads ].flatten() ]
             }
 

From 9f221f84cc66ca121a46d8f68db8f727dec523c9 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Tue, 12 Apr 2022 10:12:17 +0200
Subject: [PATCH 13/19] Only supply single input channel to profiling, as these
 are merged into single input channel at run_merging

---
 subworkflows/local/profiling.nf | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf
index c74c583..07b6b72 100644
--- 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:
@@ -22,9 +21,9 @@ 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
             .combine(databases)
+            .dump(tag: "combined_withdbs")
             .branch {
                 malt:    it[2]['tool'] == 'malt'
                 kraken2: it[2]['tool'] == 'kraken2'

From 2ef21c6ef3e46ae824ad5c99970b8a5250ef8e38 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Tue, 12 Apr 2022 10:14:05 +0200
Subject: [PATCH 14/19] Fix input to profiling

---
 subworkflows/local/profiling.nf | 1 -
 workflows/taxprofiler.nf        | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf
index 07b6b72..ac744aa 100644
--- a/subworkflows/local/profiling.nf
+++ b/subworkflows/local/profiling.nf
@@ -23,7 +23,6 @@ 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 = reads
             .combine(databases)
-            .dump(tag: "combined_withdbs")
             .branch {
                 malt:    it[2]['tool'] == 'malt'
                 kraken2: it[2]['tool'] == 'kraken2'
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 0916cac..7c02f4c 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -167,7 +167,7 @@ workflow TAXPROFILER {
         SUBWORKFLOW: PROFILING
     */
 
-    PROFILING ( ch_reads_runmerged, ch_longreads_preprocessed, DB_CHECK.out.dbs )
+    PROFILING ( ch_reads_runmerged, DB_CHECK.out.dbs )
     ch_versions = ch_versions.mix( PROFILING.out.versions )
 
     /*

From 26399718b2440499f294ebc59d669dd78dd7cdb6 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Tue, 12 Apr 2022 10:46:03 +0200
Subject: [PATCH 15/19] Re-add pairment attachment

---
 subworkflows/local/profiling.nf | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf
index ac744aa..b03b83e 100644
--- a/subworkflows/local/profiling.nf
+++ b/subworkflows/local/profiling.nf
@@ -23,6 +23,12 @@ 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 = reads
             .combine(databases)
+                meta, reads ->
+                    def meta_new = meta.clone()
+                        pairtype = meta_new['single_end'] ? '_se' : '_pe'
+                        meta_new['id'] =  meta_new['id'] + pairtype
+                    [meta_new, reads]
+            }
             .branch {
                 malt:    it[2]['tool'] == 'malt'
                 kraken2: it[2]['tool'] == 'kraken2'

From 8d689141924a52cf72e666e76db1b575d541a341 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Tue, 12 Apr 2022 10:47:44 +0200
Subject: [PATCH 16/19] Re-add operator name

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

diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf
index b03b83e..8a156c2 100644
--- a/subworkflows/local/profiling.nf
+++ b/subworkflows/local/profiling.nf
@@ -23,6 +23,7 @@ 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 = reads
             .combine(databases)
+            .map {
                 meta, reads ->
                     def meta_new = meta.clone()
                         pairtype = meta_new['single_end'] ? '_se' : '_pe'

From a15c45b00cd18e2148baf7112f15c340261acdef Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Tue, 12 Apr 2022 10:51:27 +0200
Subject: [PATCH 17/19] Put map in the rigt place

---
 subworkflows/local/profiling.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf
index 8a156c2..18de739 100644
--- a/subworkflows/local/profiling.nf
+++ b/subworkflows/local/profiling.nf
@@ -22,7 +22,6 @@ 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 = reads
-            .combine(databases)
             .map {
                 meta, reads ->
                     def meta_new = meta.clone()
@@ -30,6 +29,7 @@ workflow PROFILING {
                         meta_new['id'] =  meta_new['id'] + pairtype
                     [meta_new, reads]
             }
+            .combine(databases)
             .branch {
                 malt:    it[2]['tool'] == 'malt'
                 kraken2: it[2]['tool'] == 'kraken2'

From 16a3556bfcfddf8195bbcd486653325aaa1de4ee Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Wed, 13 Apr 2022 08:26:08 +0200
Subject: [PATCH 18/19] Changes after code review

---
 workflows/taxprofiler.nf | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 7c02f4c..58671b3 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -139,15 +139,16 @@ workflow TAXPROFILER {
                     meta_new.remove('run_accession')
                     [ meta_new, reads ]
             }
-            .groupTuple(by: 0)
+            .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: ( it[0]['single_end'] && it[1].size() > 1 ) || ( !it[0]['single_end'] && it[1].size() > 2 )
+                cat: ( meta.single_end && reads.size() > 1 ) || ( !meta.single_end && reads.size() > 2 )
                 skip: true
             }
 

From dfeaa0d1fe79a6f59c27bdb481904b3bbb620234 Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Wed, 13 Apr 2022 12:00:28 +0200
Subject: [PATCH 19/19] Rename subworkflow parameters for consistency

---
 .github/workflows/ci.yml |  8 ++++----
 conf/modules.config      |  6 +++---
 conf/test.config         |  6 +++---
 nextflow.config          | 11 ++++++-----
 nextflow_schema.json     | 22 +++++++++++-----------
 workflows/taxprofiler.nf | 16 ++++++++--------
 6 files changed, 35 insertions(+), 34 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 53423cb..c373bc8 100644
--- 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"
@@ -39,8 +39,8 @@ jobs:
           - "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
           - "--shortread_complexityfilter_tool bbduk"
           - "--shortread_complexityfilter_tool prinseq"
-          - "--run_merging"
-          - "--run_merging --shortread_clipmerge_mergepairs"
+          - "--perform_runmerging"
+          - "--perform_runmerging --shortread_clipmerge_mergepairs"
 
     steps:
       - name: Check out pipeline code
diff --git a/conf/modules.config b/conf/modules.config
index d93486f..42528de 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -173,7 +173,7 @@ process {
 
     withName: MALT_RUN {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = params.run_merging ? { "${meta.id}-${meta.db_name}" } : { "${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,
@@ -183,7 +183,7 @@ process {
 
     withName: KRAKEN2_KRAKEN2 {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = params.run_merging ? { "${meta.id}-${meta.db_name}" } : { "${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,
@@ -193,7 +193,7 @@ process {
 
     withName: METAPHLAN3 {
         ext.args = { "${meta.db_params}" }
-        ext.prefix = params.run_merging ? { "${meta.id}-${meta.db_name}" } : { "${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}/metaphlan3/${meta.db_name}" },
             mode: params.publish_dir_mode,
diff --git a/conf/test.config b/conf/test.config
index 6e82300..923dda7 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -28,7 +28,7 @@ params {
     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
 }
diff --git a/nextflow.config b/nextflow.config
index da8bbdb..b72b4f9 100644
--- 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
@@ -77,8 +77,8 @@ params {
     save_complexityfiltered_reads                        = false
 
     // run merging
-    run_merging                = false
-    save_runmerged_reads       = false
+    perform_runmerging          = false
+    save_runmerged_reads        = false
 
     // MALT
     run_malt                   = false
@@ -92,6 +92,7 @@ params {
     centrifuge_save_unaligned  = false
     centrifuge_save_aligned    = false
     centrifuge_sam_format      = false
+
     // metaphlan3
     run_metaphlan3             = false
 }
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 4db7fa0..06bd94b 100644
--- 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"
         },
@@ -334,9 +328,6 @@
         "shortread_complexityfilter_bbduk_mask": {
             "type": "boolean"
         },
-        "shortread_complexityfilter": {
-            "type": "boolean"
-        },
         "shortread_complexityfilter_entropy": {
             "type": "number",
             "default": 0.3
@@ -353,10 +344,19 @@
         "save_complexityfiltered_reads": {
             "type": "boolean"
         },
-        "run_merging": {
+        "save_runmerged_reads": {
             "type": "boolean"
         },
-        "save_runmerged_reads": {
+        "perform_shortread_clipmerge": {
+            "type": "boolean"
+        },
+        "perform_longread_clip": {
+            "type": "boolean"
+        },
+        "perform_shortread_complexityfilter": {
+            "type": "boolean"
+        },
+        "perform_runmerging": {
             "type": "boolean"
         }
     }
diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
index 58671b3..f086557 100644
--- a/workflows/taxprofiler.nf
+++ b/workflows/taxprofiler.nf
@@ -101,14 +101,14 @@ 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]] ] }
     } else {
@@ -119,7 +119,7 @@ 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
@@ -129,7 +129,7 @@ workflow TAXPROFILER {
         STEP: Run merging
     */
 
-    if ( params.run_merging ) {
+    if ( params.perform_runmerging ) {
 
         ch_reads_for_cat_branch = ch_shortreads_filtered
             .mix( ch_longreads_preprocessed )
@@ -190,22 +190,22 @@ 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.run_merging){
+    if (params.perform_runmerging){
         ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
     }