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] 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