Add support for RGI --clean flag

CHANGELOG.md

@@ -12,6 +12,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#506](https://github.com/nf-core/funcscan/pull/506) Added support GECCO convert for generation of additional files useful for downstream analysis (by @SkyLexS)
 - [#507](https://github.com/nf-core/funcscan/pull/507) Updated to nf-core template v3.5.1 (by @jfy133)
 - [#510](https://github.com/nf-core funcscan/pull/510) Fixed code to make Nextflow strict-syntax compliant (by @jfy133)
+- [#521](https://github.com/nf-core funcscan/pull/521) Added option to turn on RGI's own cleanup of intermediate files (❤️ to @SamD28 for requesting, added by @jfy133)
 
 ### `Fixed`
 

conf/modules.config

@@ -404,6 +404,7 @@ process {
             params.arg_rgi_includenudge ? '--include_nudge' : '',
             params.arg_rgi_lowquality ? '--low_quality' : '',
             params.arg_rgi_split_prodigal_jobs ? '--split_prodigal_jobs' : '',
+            params.arg_rgi_removetemporaryfiles ? '--clean' : '',
         ].join(' ').trim()
     }
 

nextflow.config

@@ -182,6 +182,7 @@ params {
     arg_rgi_lowquality                              = false
     arg_rgi_data                                    = 'NA'
     arg_rgi_split_prodigal_jobs                     = true
+    arg_rgi_removetemporaryfiles                    = false
 
     arg_skip_amrfinderplus                          = false
     arg_amrfinderplus_db                            = null

nextflow_schema.json

@@ -383,7 +383,7 @@
                     "default": "Bacteria",
                     "fa_icon": "fas fa-crown",
                     "description": "Specify the kingdom that the input represents.",
-                    "help_text": "Specifies the kingdom that the input sample is derived from and/or you wish to screen for\n\n> ⚠️ Prokka cannot annotate Eukaryotes.\n\nFor more information please check the Prokka [documentation](https://github.com/tseemann/prokka).\n\n> Modifies tool parameter(s):\n> - Prokka: `--kingdom`",
+                    "help_text": "Specifies the kingdom that the input sample is derived from and/or you wish to screen for\n\n>⚠️ Prokka cannot annotate Eukaryotes.\n\nFor more information please check the Prokka [documentation](https://github.com/tseemann/prokka).\n\n> Modifies tool parameter(s):\n> - Prokka: `--kingdom`",
                     "enum": ["Archaea", "Bacteria", "Mitochondria", "Viruses"]
                 },
                 "annotation_prokka_gcode": {
@@ -399,7 +399,7 @@
                     "type": "integer",
                     "default": 1,
                     "description": "Minimum contig size required for annotation (bp).",
-                    "help_text": "Specify the minimum contig lengths to carry out annotations on. The Prokka developers recommend that this should be ≥ 200 bp, if you plan to submit such annotations to NCBI.\n\nFor more information please check the Prokka [documentation](https://github.com/tseemann/prokka).\n\n> Modifies tool parameter(s):\n> - Prokka: `--mincontiglen`",
+                    "help_text": "Specify the minimum contig lengths to carry out annotations on. The Prokka developers recommend that this should be ⚠️ 200 bp, if you plan to submit such annotations to NCBI.\n\nFor more information please check the Prokka [documentation](https://github.com/tseemann/prokka).\n\n> Modifies tool parameter(s):\n> - Prokka: `--mincontiglen`",
                     "fa_icon": "fas fa-ruler-horizontal"
                 },
                 "annotation_prokka_evalue": {
@@ -705,7 +705,7 @@
                 "amp_ampcombi_db": {
                     "type": "string",
                     "description": "The path to the folder containing the reference database files.",
-                    "help_text": "The path to the folder containing the reference database files (`*.fasta` and `*.tsv`); a fasta file and the corresponding table with structural, functional and if reported taxonomic classifications. AMPcombi will then generate the corresponding `mmseqs2` directory, in which all binary files are prepared for the downstream alignment of the recovered AMPs with [MMseqs2](https://github.com/soedinglab/MMseqs2). These can also be provided by the user by setting up an mmseqs2 compatible database using `mmseqs createdb *.fasta` in a directory called `mmseqs2`.\n\nExample file structure for the reference database supplied by the user:\n\n```bash\namp_DRAMP_database/\n├── general_amps_2024_11_13.fasta\n├── general_amps_2024_11_13.txt\n└── mmseqs2\n    ├── ref_DB\n    ├── ref_DB.dbtype\n    ├── ref_DB_h\n    ├── ref_DB_h.dbtype\n    ├── ref_DB_h.index\n    ├── ref_DB.index\n    ├── ref_DB.lookup\n    └── ref_DB.source```\n\nFor more information check the AMPcombi [documentation](https://ampcombi.readthedocs.io/en/main/usage.html#parse-tables)."
+                    "help_text": "The path to the folder containing the reference database files (`*.fasta` and `*.tsv`); a fasta file and the corresponding table with structural, functional and if reported taxonomic classifications. AMPcombi will then generate the corresponding `mmseqs2` directory, in which all binary files are prepared for the downstream alignment of the recovered AMPs with [MMseqs2](https://github.com/soedinglab/MMseqs2). These can also be provided by the user by setting up an mmseqs2 compatible database using `mmseqs createdb *.fasta` in a directory called `mmseqs2`.\n\nExample file structure for the reference database supplied by the user:\n\n
                 },
                 "amp_ampcombi_parsetables_cutoff": {
                     "type": "number",
@@ -1065,14 +1065,14 @@
                 },
                 "arg_rgi_includeloose": {
                     "type": "boolean",
-                    "description": "Include all of loose, strict and perfect hits (i.e. ≥ 95% identity) found by RGI.",
+                    "description": "Include all of loose, strict and perfect hits (i.e. more than 95% identity) found by RGI.",
                     "help_text": "When activated RGI output will include 'Loose' hits in addition to 'Strict' and 'Perfect' hits. The 'Loose' algorithm works outside of the detection model cut-offs to provide detection of new, emergent threats and more distant homologs of AMR genes, but will also catalog homologous sequences and spurious partial matches that may not have a role in AMR.\n\nFor more information check the RGI [documentation](https://github.com/arpcard/rgi).\n\n> Modifies tool parameter(s):\n> - RGI_MAIN: `--include_loose`",
                     "fa_icon": "far fa-hand-scissors"
                 },
                 "arg_rgi_includenudge": {
                     "type": "boolean",
                     "description": "Suppresses the default behaviour of RGI with `--arg_rgi_includeloose`.",
-                    "help_text": "This flag suppresses the default behaviour of RGI, by listing all 'Loose' matches of ≥ 95% identity as 'Strict' or 'Perfect', regardless of alignment length.\n\nFor more information check the RGI [documentation](https://github.com/arpcard/rgi).\n\n> Modifies tool parameter(s):\n> - RGI_MAIN: `--include_nudge`",
+                    "help_text": "This flag suppresses the default behaviour of RGI, by listing all 'Loose' matches of more than 95% identity as 'Strict' or 'Perfect', regardless of alignment length.\n\nFor more information check the RGI [documentation](https://github.com/arpcard/rgi).\n\n> Modifies tool parameter(s):\n> - RGI_MAIN: `--include_nudge`",
                     "fa_icon": "fas fa-hand-scissors"
                 },
                 "arg_rgi_lowquality": {
@@ -1095,6 +1095,11 @@
                     "help_text": "For more information check the RGI [documentation](https://github.com/arpcard/rgi).\n\nModifies tool parameter:\n> - RGI_MAIN: `--split_prodigal_jobs`",
                     "fa_icon": "fas fa-angle-double-down",
                     "default": true
+                },
+                "arg_rgi_removetemporaryfiles": {
+                    "type": "boolean",
+                    "description": "Specify to trigger RGI's internal cleanup of intermediate files",
+                    "help_text": "When running on fragmented (meta)genomes (i.e., has many contigs), RGI can produce a very large number of intermediate files (~4 files per contig).\nThis can sometimes fill up filesystems blocking downstream processes.\nActivate this option to allow RGI to clean up the files on completion of the process.\n\n> Modifies tool parameter(s):\n>   - RGI_MAIN: `--cllean`"
                 }
             },
             "fa_icon": "fas fa-bacteria"