Add support for additional antismash options

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - [#500](https://github.com/nf-core/funcscan/pull/500) Updated pipeline template to nf-core/tools version 3.4.1 (by @jfy133)
+- [#508](https://github.com/nf-core/funcscan/pull/508) Added support for antiSMASH's --clusterhmmer, --fullhmmer, and --tigrfam options (❤️ to @yusukepockyby for requesting, @jfy133)
 
 ### `Fixed`
 

conf/modules.config

@@ -140,7 +140,7 @@ process {
             '--disable-residue-annot',
             '--enable-tsv-residue-annot',
             "--formats tsv",
-        ].join(' ').trim() // Warning: Do not disable the flags "--enable-tsv-residue-annot" and "--formats tsv"! This would cause a run failure because the format of the resulting files would no longer be adequate for parsing by AMPcombi2.
+        ].join(' ').trim()
     }
 
     withName: PROKKA {
@@ -470,6 +470,9 @@ process {
             params.bgc_antismash_pfam2go ? '--pfam2go' : '',
             params.bgc_antismash_rre ? '--rre' : '',
             params.bgc_antismash_tfbs ? '--tfbs' : '',
+            params.bgc_antismash_clusterhmmer ? '--clusterhmmer' : '',
+            params.bgc_antismash_fullhmmer ? '--fullhmmer' : '',
+            params.bgc_antismash_tigrfam ? '--tigrfam' : '',
             "--allow-long-headers",
             "--minlength ${params.bgc_antismash_contigminlength}",
             "--hmmdetection-strictness ${params.bgc_antismash_hmmdetectionstrictness}",

nextflow.config

@@ -20,28 +20,28 @@ params {
     multiqc_methods_description                     = null
 
     // Boilerplate options
-    outdir                       = null
-    publish_dir_mode             = 'copy'
-    email                        = null
-    email_on_fail                = null
-    plaintext_email              = false
-    monochrome_logs              = false
-    hook_url                     = System.getenv('HOOK_URL')
-    help                         = false
-    help_full                    = false
-    show_hidden                  = false
-    version                      = false
-    pipelines_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
-    trace_report_suffix          = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
+    outdir                                          = null
+    publish_dir_mode                                = 'copy'
+    email                                           = null
+    email_on_fail                                   = null
+    plaintext_email                                 = false
+    monochrome_logs                                 = false
+    hook_url                                        = System.getenv('HOOK_URL')
+    help                                            = false
+    help_full                                       = false
+    show_hidden                                     = false
+    version                                         = false
+    pipelines_testdata_base_path                    = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
+    trace_report_suffix                             = new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')
 
     // Config options
-    config_profile_name        = null
-    config_profile_description = null
+    config_profile_name                             = null
+    config_profile_description                      = null
 
-    custom_config_version      = 'master'
-    custom_config_base         = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
-    config_profile_contact     = null
-    config_profile_url         = null
+    custom_config_version                           = 'master'
+    custom_config_base                              = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
+    config_profile_contact                          = null
+    config_profile_url                              = null
 
     // Taxonomy classification options
     run_taxa_classification                         = false
@@ -231,6 +231,9 @@ params {
     bgc_antismash_rre                               = false
     bgc_antismash_taxon                             = 'bacteria'
     bgc_antismash_tfbs                              = false
+    bgc_antismash_clusterhmmer                      = false
+    bgc_antismash_fullhmmer                         = false
+    bgc_antismash_tigrfam                           = false
 
     bgc_skip_deepbgc                                = false
     bgc_deepbgc_db                                  = null
@@ -313,7 +316,7 @@ profiles {
         wave.strategy           = 'conda,container'
     }
     emulate_amd64 {
-        docker.runOptions       = '-u $(id -u):$(id -g) --platform=linux/amd64'
+        docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64'
     }
     singularity {
         singularity.enabled    = true
@@ -540,12 +543,12 @@ manifest {
 
 // Nextflow plugins
 plugins {
-    id 'nf-schema@2.5.1' // Validation of pipeline parameters and creation of an input channel from a sample sheet
+    id 'nf-schema@2.5.1'
 }
 
 validation {
     defaultIgnoreParams = ["genomes"]
-    monochromeLogs = params.monochrome_logs
+    monochromeLogs      = params.monochrome_logs
 }
 
 // Load modules.config for DSL2 module specific options

nextflow_schema.json

@@ -159,14 +159,14 @@
                 },
                 "taxa_classification_mmseqs_taxonomy_sensitivity": {
                     "type": "number",
-                    "default": 5.0,
+                    "default": 5,
                     "help_text": "This flag specifies the speed and sensitivity of the taxonomic search. It stands for how many kmers should be produced during the preliminary seeding stage. A very fast search requires a low value e.g. '1.0' and a a very sensitive search requires e.g. '7.0'. More details can be found in the [documentation](https://mmseqs.com/latest/userguide.pdf).\n\n>  Modifies tool parameter(s):\n> - mmseqs taxonomy: `-s`",
                     "description": "Specify the speed and sensitivity for taxonomy assignment.",
                     "fa_icon": "fas fa-history"
                 },
                 "taxa_classification_mmseqs_taxonomy_orffilters": {
                     "type": "number",
-                    "default": 2.0,
+                    "default": 2,
                     "help_text": "This flag specifies the sensitivity used for prefiltering the query ORF. Before the taxonomy-assigning step, MMseqs2 searches the predicted ORFs against the provided database. This value influences the speed with which the search is carried out. More details can be found in the [documentation](https://mmseqs.com/latest/userguide.pdf).\n\n>  Modifies tool parameter(s):\n> - mmseqs taxonomy: `--orf-filter-s`",
                     "description": "Specify the ORF search sensitivity in the prefilter step.",
                     "fa_icon": "fas fa-history"
@@ -723,7 +723,7 @@
                 },
                 "amp_ampcombi_parsetables_dbevalue": {
                     "type": "number",
-                    "default": 5.0,
+                    "default": 5,
                     "description": "Remove all DRAMP annotations that have an e-value greater than this value.",
                     "help_text": "This e-value is used as a cut-off for the annotations from the internal Diamond alignment step (against the DRAMP database by default). Any e-value below this value will only remove the DRAMP classification and not the entire hit.\n\n> Modifies tool parameter(s):\n> - AMPCOMBI: `--db_evalue`",
                     "fa_icon": "fas fa-sort-numeric-down"
@@ -794,14 +794,14 @@
             "properties": {
                 "amp_ampcombi_cluster_covmode": {
                     "type": "number",
-                    "default": 0.0,
+                    "default": 0,
                     "description": "MMseqs2 coverage mode.",
                     "help_text": "This assigns the coverage mode to the MMseqs2 cluster module. This determines how AMPs are grouped into clusters. More details can be found in the [MMseqs2 documentation](https://mmseqs.com/latest/userguide.pdf).\n\n> Modifies tool parameter(s):\n> - AMPCOMBI: `--cluster_cov_mode`",
                     "fa_icon": "far fa-circle"
                 },
                 "amp_ampcombi_cluster_sensitivity": {
                     "type": "number",
-                    "default": 4.0,
+                    "default": 4,
                     "description": "Remove hits that have no stop codon upstream and downstream of the AMP.",
                     "help_text": "This assigns the sensitivity of alignment to the MMseqs2 cluster module. This determines how AMPs are grouped into clusters. More information can be obtained in the [MMseqs2 documentation](https://mmseqs.com/latest/userguide.pdf).\n\n> Modifies tool parameter(s):\n> - AMPCOMBI: `--cluster_sensitivity`",
                     "fa_icon": "fas fa-arrows-alt-h"
@@ -815,7 +815,7 @@
                 },
                 "amp_ampcombi_cluster_mode": {
                     "type": "number",
-                    "default": 1.0,
+                    "default": 1,
                     "description": "MMseqs2 clustering mode.",
                     "help_text": "This assigns the cluster mode to the MMseqs2 cluster module. This determines how AMPs are grouped into clusters. More information can be obtained in the [MMseqs2 documentation](https://mmseqs.com/latest/userguide.pdf).\n\n> Modifies tool parameter(s):\n> - AMPCOMBI: `--cluster_mode`",
                     "fa_icon": "fas fa-circle"
@@ -863,7 +863,7 @@
                 },
                 "arg_amrfinderplus_identmin": {
                     "type": "number",
-                    "default": -1.0,
+                    "default": -1,
                     "help_text": "Specify the minimum percentage amino-acid identity to reference protein or nucleotide identity for nucleotide reference must have if a BLAST alignment (based on methods: BLAST or PARTIAL) was detected, otherwise NA.\n\n If you specify `-1`, this means use a curated threshold if it exists and `0.9` otherwise.\n\nSetting this value to something other than `-1` will override any curated similarity cutoffs. For BLAST: alignment is > 90% of length and > 90% identity to a protein in the AMRFinderPlus database. For PARTIAL: alignment is > 50% of length, but < 90% of length and > 90% identity to the reference, and does not end at a contig boundary.\n\nFor more information check the AMRFinderPlus [documentation](https://github.com/ncbi/amr/wiki/Running-AMRFinderPlus#--organism-option).\n\n> Modifies tool parameter(s):\n> - AMRFinderPlus: `--ident_min`",
                     "description": "Minimum percent identity to reference sequence.",
                     "fa_icon": "fas fa-angle-left"
@@ -1284,6 +1284,24 @@
                     "description": "Run TFBS finder on all gene clusters.",
                     "help_text": "This enables the prediction of transcription factor binding sites which control the gene expression. For more information see the antiSMASH [documentation](https://docs.antismash.secondarymetabolites.org/).\n\n> Modifies tool parameter(s):\n> - antiSMASH: `--tfbs`",
                     "fa_icon": "fas fa-search"
+                },
+                "bgc_antismash_clusterhmmer": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-glass-martini-alt",
+                    "description": "Run antiSMASH with --clusterhmmer mode with Pfam profiles",
+                    "help_text": "For more information see the antiSMASH [documentation](https://docs.antismash.secondarymetabolites.org/).\n\n> Modifies tool parameter(s):\n> - antiSMASH: `--clusterhmmer`"
+                },
+                "bgc_antismash_fullhmmer": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-glass-martini",
+                    "description": "Run antiSMASH with --fullhmmer mode with Pfam profiles",
+                    "help_text": "For more information see the antiSMASH [documentation](https://docs.antismash.secondarymetabolites.org/).\n\n> Modifies tool parameter(s):\n> - antiSMASH: `--fullhmmer`"
+                },
+                "bgc_antismash_tigrfam": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-cat",
+                    "description": "Run antiSMASH with --tigrfam annotation activated",
+                    "help_text": "For more information see the antiSMASH [documentation](https://docs.antismash.secondarymetabolites.org/).\n\n> Modifies tool parameter(s):\n> - antiSMASH: `--tigrfam`"
                 }
             },
             "fa_icon": "fas fa-angle-double-right"