Add min boot param

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#913](https://github.com/nf-core/ampliseq/pull/913) - Parameter `--dada_min_boot` allows the user to specify a minimum bootstrap confidence (out of 100 trials) for assigning a taxonomic level with DADA2's [assignTaxonomy](https://rdrr.io/bioc/dada2/man/assignTaxonomy.html) method.
 - [#909](https://github.com/nf-core/ampliseq/pull/909) - Parameter `--truncq` allows read truncation by quality score, where each read is truncated at the first instance of a quality score less than or equal to `truncq` (default value is 2). This quality score-based truncation occurs before read length truncation. If `--trunc_qmin` and `--trunc_rmin` are used to automatically calculate the values for `trunclenf` and `trunclenr` used for read length truncation, those calculations are based on the read metrics before quality score-based truncation (using `truncq`) is performed. `truncq` is passed directly as `truncQ` into DADA2's [filterAndTrim](https://rdrr.io/bioc/dada2/man/filterAndTrim.html) method.
 
 ### `Changed`

assets/report_template.Rmd

@@ -42,6 +42,7 @@ params:
     filter_ssu: FALSE
     min_len_asv: ""
     max_len_asv: ""
+    dada_min_boot: ""
     cut_its: FALSE
     dada2_ref_tax_title: FALSE
     qiime2_ref_tax_title: FALSE
@@ -905,11 +906,16 @@ cat("## DADA2\n")
 if ( !isFALSE(params$dada2_ref_tax_title) ) {
     cat("The taxonomic classification was performed by [DADA2](https://pubmed.ncbi.nlm.nih.gov/27214047/)
         using the database: `", params$dada2_ref_tax_title, "`.
-        More details about the reference taxonomy database can be found in the ['Methods section'](#methods).\n\n", sep = "")
+        More details about the reference taxonomy database can be found in the ['Methods section'](#methods).", sep = "")
 } else {
     cat("The taxonomic classification was performed by DADA2 using a custom database ",
-            "provided by the user.\n\n", sep = "")
+            "provided by the user.", sep = "")
+}
+if (params$dada_min_boot) {
+    cat(" A minimum bootstrap confidence of ", params$dada_min_boot, " (out of 100 trials) ",
+        "was used for assigning a taxonomic level.", sep="")
 }
+cat ("\n\n")
 
 # mention if taxonomy was cut by cutadapt
 if ( !isFALSE(params$cut_dada_ref_taxonomy) ) {
@@ -1783,10 +1789,15 @@ cat(filter_codons_fasta_passed,"ASVs had no stop codons (",params$stop_codons,")
 ```{r, eval = any_taxonomy, results='asis'}
 methods_taxonomic_classification <- c("Taxonomic classification was performed by ")
 if ( !isFALSE(params$dada2_taxonomy) ) {
+    if (params$dada_min_boot) {
+        dada_min_boot_part <- paste("(with a minimum bootstrap confidence of ",params$dada_min_boot," out of 100 trials for assigning a taxonomic level) " )
+    } else {
+        dada_min_boot_part <- ""
+    }
     if ( !isFALSE(params$dada2_ref_tax_title) ) {
-        methods_taxonomic_classification_dada <- paste("DADA2 and the database '",params$dada2_ref_tax_title,"' (`", params$dada2_ref_tax_citation,"`)", sep="")
+        methods_taxonomic_classification_dada <- paste("DADA2 ",dada_min_boot_part,"and the database '",params$dada2_ref_tax_title,"' (`", params$dada2_ref_tax_citation,"`)", sep="")
     } else {
-        methods_taxonomic_classification_dada <- paste("DADA2 with a user provided database", sep="")
+        methods_taxonomic_classification_dada <- paste("DADA2 ",dada_min_boot_part,"with a user provided database", sep="")
     }
     if ( !isFALSE(params$cut_dada_ref_taxonomy) ) {
         methods_taxonomic_classification_dada <- paste(methods_taxonomic_classification_dada,

conf/modules.config

@@ -518,7 +518,7 @@ process {
     withName: DADA2_TAXONOMY {
         ext.seed = "${params.seed}"
         ext.args = [
-            'minBoot = 50',
+            "minBoot = ${params.dada_min_boot}",
             params.dada_taxonomy_rc || params.pacbio || params.iontorrent ? "tryRC = TRUE" : "tryRC = FALSE"
         ].join(',').replaceAll('(,)*$', "")
         publishDir = [

docs/usage.md

@@ -250,7 +250,7 @@ Special features of taxonomic classification tools:
 - QIIME2's reference taxonomy databases will have regions matching the amplicon extracted with primer sequences.
 - DADA2, Kraken2, and QIIME2 have specific parameters to accept custom databases (but theoretically possible with all classifiers)
 
-Parameter guidance is given in [nf-core/ampliseq website parameter documentation](https://nf-co.re/ampliseq/parameters/#taxonomic-database). Citations are listed in [`CITATIONS.md`](CITATIONS.md).
+Parameter guidance is given in [nf-core/ampliseq website parameter documentation](https://nf-co.re/ampliseq/parameters/#taxonomic-assignment). Citations are listed in [`CITATIONS.md`](CITATIONS.md).
 
 ### Multiple region analysis with Sidle
 

modules/local/summary_report.nf

@@ -113,6 +113,7 @@ process SUMMARY_REPORT  {
         params.max_len_asv ? "max_len_asv=$params.max_len_asv" : "max_len_asv=0",
         filter_codons_fasta ? "filter_codons_fasta='$filter_codons_fasta',stop_codons='$params.stop_codons'" : "",
         filter_codons_stats ? "filter_codons_stats='$filter_codons_stats'" : "",
+        "dada_min_boot=$params.dada_min_boot",
         itsx_cutasv_summary ? "itsx_cutasv_summary='$itsx_cutasv_summary',cut_its='$params.cut_its'" : "",
         dada2_tax ? "dada2_taxonomy='$dada2_tax'" : "",
         dada2_tax && !params.dada_ref_tax_custom ? "dada2_ref_tax_title='${params.dada_ref_databases[params.dada_ref_taxonomy]["title"]}',dada2_ref_tax_file='${params.dada_ref_databases[params.dada_ref_taxonomy]["file"]}',dada2_ref_tax_citation='${params.dada_ref_databases[params.dada_ref_taxonomy]["citation"]}'" : "",

nextflow.config

@@ -25,11 +25,11 @@ params {
 
     // Other options
     save_intermediates                        = false
-    trunc_qmin                                = 25
-    trunc_rmin                                = 0.75
+    truncq                                    = 2
     trunclenf                                 = null
     trunclenr                                 = null
-    truncq                                    = 2
+    trunc_qmin                                = 25
+    trunc_rmin                                = 0.75
     max_ee                                    = 2
     max_len                                   = null
     ignore_failed_filtering                   = false
@@ -119,7 +119,8 @@ params {
     skip_multiqc           = false
     skip_report            = false
 
-    // Database options
+    // Taxonomic assignment options
+    dada_min_boot = 50
     dada_ref_taxonomy        = "silva=138.2"
     dada_assign_taxlevels    = null
     dada_ref_tax_custom      = null

nextflow_schema.json

@@ -405,12 +405,20 @@
             },
             "fa_icon": "fas fa-filter"
         },
-        "taxonomic_database": {
-            "title": "Taxonomic database",
+        "taxonomic_assignment": {
+            "title": "Taxonomic assignment",
             "type": "object",
             "fa_icon": "fas fa-database",
             "description": "Choose a method and database for taxonomic assignments to single-region amplicons",
             "properties": {
+                "dada_min_boot": {
+                    "type": "integer",
+                    "default": 50,
+                    "fa_icon": "fas fa-greater-than-equal",
+                    "description": "The minimum bootstrap confidence (out of 100 trials) for assigning a taxonomic level with DADA2. Matches `minBoot` in DADA2's assignTaxonomy method.",
+                    "minimum": 0,
+                    "maximum": 100
+                },
                 "dada_ref_taxonomy": {
                     "type": "string",
                     "help_text": "Choose any of the supported databases, and optionally also specify the version. Database and version are separated by an equal sign (`=`, e.g. `silva=138`) . This will download the desired database, format it to produce a file that is compatible with DADA2's assignTaxonomy and another file that is compatible with DADA2's addSpecies.\n\nThe following databases are supported:\n- GTDB - Genome Taxonomy Database - 16S rRNA\n- SBDI-GTDB, a Sativa-vetted version of the GTDB 16S rRNA\n- PR2 - Protist Reference Ribosomal Database - 18S rRNA\n- RDP - Ribosomal Database Project - 16S rRNA\n- SILVA ribosomal RNA gene database project - 16S rRNA\n- UNITE - eukaryotic nuclear ribosomal ITS region - ITS\n- COIDB - eukaryotic Cytochrome Oxidase I (COI) from The Barcode of Life Data System (BOLD) - COI\n\nGenerally, using `gtdb`, `pr2`, `rdp`, `sbdi-gtdb`, `silva`, `coidb`, `unite-fungi`, or `unite-alleuk` will select the most recent supported version.\n\nPlease note that commercial/non-academic entities [require licensing](https://www.arb-silva.de/silva-license-information) for SILVA v132 database (non-default) but not from v138 on (default).",
@@ -1092,7 +1100,7 @@
             "$ref": "#/$defs/asv_post_processing"
         },
         {
-            "$ref": "#/$defs/taxonomic_database"
+            "$ref": "#/$defs/taxonomic_assignment"
         },
         {
             "$ref": "#/$defs/multiregion_taxonomic_database"