Add compressed flag as ext.args to mmseqs modules

Author: jasmezz

conf/modules.config

@@ -41,7 +41,8 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
         ext.args   = [
-            params.taxa_classification_mmseqs_db_savetmp ? "" : "--remove-tmp-files"
+            params.taxa_classification_mmseqs_db_savetmp ? "" : "--remove-tmp-files",
+            "--compressed ${params.taxa_classification_mmseqs_compressed}"
         ].join(' ').trim()
     }
 
@@ -52,6 +53,9 @@ process {
             enabled: params.save_db,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
+        ext.args   = [
+            "--compressed ${params.taxa_classification_mmseqs_compressed}"
+        ].join(' ').trim()
     }
 
     withName: MMSEQS_TAXONOMY {
@@ -70,6 +74,7 @@ process {
             "--orf-filter-s ${params.taxa_classification_mmseqs_taxonomy_orffilters}",
             "--lca-mode ${params.taxa_classification_mmseqs_taxonomy_lcamode}",
             "--vote-mode ${params.taxa_classification_mmseqs_taxonomy_votemode}",
+            "--compressed ${params.taxa_classification_mmseqs_compressed}"
         ].join(' ').trim()
     }
 
@@ -81,6 +86,9 @@ process {
             pattern: "*.tsv",
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
+        ext.args   = [
+            "--compressed ${params.taxa_classification_mmseqs_compressed}"
+        ].join(' ').trim()
     }
 
     withName: SEQKIT_SEQ {

nextflow.config

@@ -38,6 +38,7 @@ params {
     // Taxonomy classification options
     run_taxa_classification                         = false
     taxa_classification_tool                        = 'mmseqs2'
+    taxa_classification_mmseqs_compressed           = 0
 
     taxa_classification_mmseqs_db                   = null
     taxa_classification_mmseqs_db_id                = 'Kalamari'
@@ -174,12 +175,11 @@ params {
 
     arg_skip_deeparg                                = false
     arg_deeparg_db                                  = null
-    arg_deeparg_db_version                          = 2
-    // Make sure to update on module version bump!
+    arg_deeparg_db_version                          = 2     // Make sure to update on module version bump!
     arg_deeparg_model                               = 'LS'
     arg_deeparg_minprob                             = 0.8
     arg_deeparg_alignmentidentity                   = 50
-    arg_deeparg_alignmentevalue                     = 1E-10
+    arg_deeparg_alignmentevalue                     = 1e-10
     arg_deeparg_alignmentoverlap                    = 0.8
     arg_deeparg_numalignmentsperentry               = 1000
 
@@ -229,7 +229,7 @@ params {
     bgc_skip_gecco                                  = false
     bgc_gecco_cds                                   = 3
     bgc_gecco_threshold                             = 0.8
-    bgc_gecco_pfilter                               = 1E-9
+    bgc_gecco_pfilter                               = 0.000000001
     bgc_gecco_edgedistance                          = 0
     bgc_gecco_mask                                  = false
 

nextflow_schema.json

@@ -86,6 +86,14 @@
                     "help_text": "This flag specifies which tool for taxonomic classification should be activated. At the moment only 'MMseqs2' is incorporated in the pipeline.",
                     "description": "Specifies the tool used for taxonomic classification.",
                     "fa_icon": "fas fa-tools"
+                },
+                "taxa_classification_mmseqs_compressed": {
+                    "type": "integer",
+                    "default": 0,
+                    "enum": [0, 1],
+                    "help_text": "To compress MMseqs2 output files, choose 1, otherwise leave to 0. Compressing output files can lead to errors when the output is actually empty. In that case, just leave this parameter to default. More details can be found in the [documentation (GitHub)](https://github.com/soedinglab/MMseqs2?tab=readme-ov-file#memory-requirements).\n\n>  Modifies tool parameter(s):\n> - mmseqs createdb --compressed <0|1>\n> - mmseqs createtsv --compressed <0|1>\n> - mmseqs databases --compressed <0|1>\n> - mmseqs taxonomy --compressed <0|1>",
+                    "description": "If MMseqs2 is chosen as taxonomic classification tool: Specifies if the output of all MMseqs2 subcommands shall be compressed.",
+                    "fa_icon": "fas fa-file-archive"
                 }
             },
             "fa_icon": "fas fa-tag"
@@ -1531,12 +1539,6 @@
                     "description": "Base URL or local path to location of pipeline test dataset files",
                     "default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
                     "hidden": true
-                },
-                "trace_report_suffix": {
-                    "type": "string",
-                    "fa_icon": "far calendar",
-                    "description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
-                    "hidden": true
                 }
             }
         }