Adding shortread deduplication feature with fastp

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#439](https://github.com/nf-core/taxprofiler/pull/439) Read deduplication with fastp (added by @maxibor)
 - [#440](https://github.com/nf-core/taxprofiler/pull/440) Include pre-built kaiju databases in tutorial.md (added by @Joon-Klaps)
 
 ### `Fixed`

conf/modules.config

@@ -57,7 +57,8 @@ process {
             params.shortread_qc_adapterlist ? "" : params.shortread_qc_adapter1 ? "--adapter_sequence ${params.shortread_qc_adapter1}" : "",
             // filtering options
             "--length_required ${params.shortread_qc_minlength}",
-            (params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == 'fastp') ? "--low_complexity_filter --complexity_threshold ${params.shortread_complexityfilter_fastp_threshold}" : ''
+            (params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == 'fastp') ? "--low_complexity_filter --complexity_threshold ${params.shortread_complexityfilter_fastp_threshold}" : '',
+            params.shortread_qc_dedup ? "--dedup" : ""
         ].join(' ').trim()
         ext.prefix = { "${meta.id}_${meta.run_accession}" }
         publishDir = [
@@ -93,7 +94,8 @@ process {
             params.shortread_qc_adapterlist ? "" : params.shortread_qc_adapter2 ? "--adapter_sequence_r2 ${params.shortread_qc_adapter2}" : "--detect_adapter_for_pe",
             // filtering options
             "--length_required ${params.shortread_qc_minlength}",
-            params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == 'fastp' ? "--low_complexity_filter --complexity_threshold ${params.shortread_complexityfilter_fastp_threshold}" : ''
+            params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == 'fastp' ? "--low_complexity_filter --complexity_threshold ${params.shortread_complexityfilter_fastp_threshold}" : '',
+            params.shortread_qc_dedup ? "--dedup" : ""
         ].join(' ').trim()
         ext.prefix = { "${meta.id}_${meta.run_accession}" }
         publishDir = [

nextflow.config

@@ -71,6 +71,7 @@ params {
     shortread_qc_adapter2            = null
     shortread_qc_adapterlist         = null
     shortread_qc_minlength           = 15
+    shortread_qc_dedup               = false
 
     perform_longread_qc                   = false
     longread_qc_skipadaptertrim           = false

nextflow_schema.json

@@ -147,6 +147,12 @@
                     "description": "Specify the minimum length of reads to be retained",
                     "help_text": "Specifying a mimum read length filtering can speed up profiling by reducing the number of short unspecific reads that need to be match/aligned to the database.\n\n> Modifies tool parameter(s):\n> - removed from reads `--length_required`\n> - AdapterRemoval: `--minlength`"
                 },
+                "shortread_qc_dedup": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-toggle-on",
+                    "description": "Perform deduplication of the input reads (fastp only)",
+                    "help_text": "This enables the deduplication of processed reads during fastp adapter removal and/or merging. It removes identical reads that are likely artefacts from laboratory protocols (e.g. amplification), and provide no additional sequence information to the library.\n\nRemoving duplicates can increase runtime and increase accuracy of abundance calculations.\n\n> Modifies tool parameter(s):\n> fastp: ` --dedup`\n"
+                },
                 "perform_shortread_complexityfilter": {
                     "type": "boolean",
                     "fa_icon": "fas fa-toggle-on",