Merge pull request #914 from d4straub/reviewer-2-15-0

d4straub · web-flow · commit c59b36632ba7 · 2025-09-29T11:32:12.000+02:00
Better explain --truncq / truncQ
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,20 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#909](https://github.com/nf-core/ampliseq/pull/909),[#914](https://github.com/nf-core/ampliseq/pull/914) - 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.
 - [#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`
 
 - [#903](https://github.com/nf-core/ampliseq/pull/903) - Corrects a broken link for _midori2-co1_ database.
 
 ### `Fixed`
 
-- [#906](https://github.com/nf-core/ampliseq/pull/906) - Fix `--mergepairs_strategy "consensus"` causing an error in dada2_stats when analysing a run composed by only one sample
 - [#893](https://github.com/nf-core/ampliseq/pull/893),[#896](https://github.com/nf-core/ampliseq/pull/896),[#905](https://github.com/nf-core/ampliseq/pull/905),[#912](https://github.com/nf-core/ampliseq/pull/912) - Template update for nf-core/tools version 3.3.2 and reorganization of nf-test
-- [#897](https://github.com/nf-core/ampliseq/pull/897) - Allow multiple region analysis with one sample
+- [#897](https://github.com/nf-core/ampliseq/pull/897) - Allow multiple region analysis with one sample.
 - [#899](https://github.com/nf-core/ampliseq/pull/899) - With `--dada_ref_tax_custom` all chunks defined by `--dada_assign_chunksize` are now taxonomically annotated.
 - [#904](https://github.com/nf-core/ampliseq/pull/904) - Update `untar` module.
+- [#906](https://github.com/nf-core/ampliseq/pull/906) - Fix `--mergepairs_strategy "consensus"` causing an error in dada2_stats when analysing a run composed by only one sample.
 
 ### `Dependencies`
 
diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -208,7 +208,8 @@
                     "default": 2,
                     "fa_icon": "fas fa-greater-than-equal",
                     "minimum": 0,
-                    "description": "Truncate each read at the first instance of a quality score less than or equal to truncq. Applied before read length truncation."
+                    "description": "Truncate each read at the first instance of a quality score less than or equal to `--truncq`.",
+                    "help_text": "Applied before read length truncation, but in the same step as read length truncation. The parameter is equivalent to `truncQ` in DADA2's filterAndTrim method. `--truncq` defaults to 2, which was already the default previously. If `--trunc_qmin` and `--trunc_rmin` are used to automatically calculate `--trunclenf` and `--trunclenr`, these values are determined using the read metrics calculated on the read input before DADA2 filterAndTrim is called, and so before `--truncq` is applied."
                 },
                 "trunclenf": {
                     "type": "integer",
@@ -411,14 +412,6 @@
             "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).",
@@ -481,6 +474,14 @@
                     "help_text": "Requires `--dada_ref_tax_custom`. Must be compatible to DADA2's addSpecies function: 'Can be compressed. This reference fasta file should be formatted so that the id lines correspond to the genus-species binomial of the associated sequence.' See also https://rdrr.io/bioc/dada2/man/addSpecies.html",
                     "description": "Path to a custom DADA2 reference taxonomy database for species assignment"
                 },
+                "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_assign_taxlevels": {
                     "type": "string",
                     "help_text": "Typically useful when providing a custom DADA2 reference taxonomy database with `--dada_ref_tax_custom`. If DADA2's addSpecies is used (default), the last element(s) of the comma separated string must be 'Genus' or 'Genus,Species'.",
diff --git a/subworkflows/local/qiime2_preptax.nf b/subworkflows/local/qiime2_preptax.nf
@@ -66,13 +66,13 @@ workflow QIIME2_PREPTAX {
             ch_qiime_db_dir = ch_qiime_db_dir.mix(ch_qiime_ref_tax_branched.dir)
 
             ch_ref_database_fna = ch_qiime_db_dir.map{ dir ->
-                files = file(dir.resolve("*.fna"), checkIfExists: true)
+                def files = file(dir.resolve("*.fna"), checkIfExists: true)
             } | filter { it ->
                 if (it.size() > 1) log.warn "Found multiple fasta files for QIIME2 reference database."
                 it.size() == 1
             }
             ch_ref_database_tax = ch_qiime_db_dir.map{ dir ->
-                files = file(dir.resolve("*.tax"), checkIfExists: true)
+                def files = file(dir.resolve("*.tax"), checkIfExists: true)
             } | filter { it ->
                 if (it.size() > 1) log.warn "Found multiple tax files for QIIME2 reference database."
                 it.size() == 1
