Merge pull request #277 from erikrikarddaniel/fix-empty-eukulele-channel

Fix empty eukulele channel & unzipped user provided assembly

CHANGELOG.md

@@ -3,6 +3,11 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.0.1 - [2024-04-02]
+
+- [#277](https://github.com/nf-core/metatdenovo/pull/277) - Fix mistake in how `--eukulele_db` parameter is handled. Remove possibility to use a list of dbs in the same run.
+- [#277](https://github.com/nf-core/metatdenovo/pull/277) - Gzip user provided assembly files to avoid overwriting by assuming they're already zipped.
+
 ## v1.0.0 - [date]
 
 Initial release of nf-core/metatdenovo, created with the [nf-core](https://nf-co.re/) template.

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/metatdenovo/releases/tag/1.0.0" target="_blank">nf-core/metatdenovo</a>
+  This report has been generated by the <a href="https://github.com/nf-core/metatdenovo/releases/tag/1.0.1" target="_blank">nf-core/metatdenovo</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/metatdenovo/1.0.0/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/metatdenovo/1.0.1/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-metatdenovo-methods-description":
     order: -1000

modules.json

@@ -55,6 +55,11 @@
                         "git_sha": "9e71d8519dfbfc328c078bba14d4bd4c99e39a94",
                         "installed_by": ["modules"]
                     },
+                    "pigz/compress": {
+                        "branch": "master",
+                        "git_sha": "0eab94fc1e48703c1b0a8704bd665f554905c39d",
+                        "installed_by": ["modules"]
+                    },
                     "prodigal": {
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",

nextflow.config

@@ -288,7 +288,7 @@ manifest {
     description     = """Assembly and annotation of metatranscriptomic data, both prokaryotic and eukaryotic"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '1.0.0'
+    version         = '1.0.1'
     doi             = ''
 }
 

nextflow_schema.json

@@ -326,7 +326,7 @@
                     "type": "string",
                     "enum": ["gtdb", "phylodb", "marmmetsp", "mmetsp", "eukprot"],
                     "description": "EUKulele database.",
-                    "help_text": "This option allows the user to specify which database (or set of databases, separated by comma) to use with EUKulele. Databases that are provided with EUKulele will be downloaded if not already present inside the database directory (see --eukulele_dbpath). Possible alternatives: phylodb, mmetsp, marmmetsp, eukprot. NB: you can't use this option with a custom database as eukulele will not recognize the name and it will start to download phylodb by default. If you want to use a custom database, please skip this option and specify only --eukulele_dbpath.",
+                    "help_text": "This option allows the user to specify which database to use with EUKulele. Databases that are provided with EUKulele will be downloaded if not already present inside the database directory (see --eukulele_dbpath). Possible alternatives: phylodb, mmetsp, marmmetsp, eukprot. NB: you can't use this option with a custom database as eukulele will not recognize the name and it will start to download phylodb by default. If you want to use a custom database, please skip this option and specify only --eukulele_dbpath.",
                     "fa_icon": "far fa-file-code"
                 },
                 "eukulele_dbpath": {

workflows/metatdenovo.nf

@@ -121,6 +121,7 @@ include { CAT_FASTQ            	                     } from '../modules/nf-core/
 include { FASTQC                                     } from '../modules/nf-core/fastqc/main'
 include { MULTIQC                                    } from '../modules/nf-core/multiqc/main'
 include { CUSTOM_DUMPSOFTWAREVERSIONS                } from '../modules/nf-core/custom/dumpsoftwareversions/main'
+include { PIGZ_COMPRESS as PIGZ_ASSEMBLY             } from '../modules/nf-core/pigz/compress/main'
 
 //
 // SUBWORKFLOWS: Installed directly from nf-core/modules
@@ -267,9 +268,15 @@ workflow METATDENOVO {
     // MODULE: Run Megahit or RNAspades on all interleaved fastq files
     //
     if ( params.assembly ) {
-        Channel
-            .value ( [ [ id: 'user_assembly' ], file(params.assembly) ] )
-            .set { ch_assembly_contigs }
+        // If the input assembly is not gzipped, do that since all downstream calls assume this
+        if ( ! params.assembly.endsWith('.gz') ) {
+            PIGZ_ASSEMBLY(Channel.fromPath(params.assembly).map { [ [ id:params.assembly ], it ] } )
+            PIGZ_ASSEMBLY.out.archive.first().set { ch_assembly_contigs }
+        } else {
+            Channel
+                .value ( [ [ id: 'user_assembly' ], file(params.assembly) ] )
+                .set { ch_assembly_contigs }
+        }
     } else if ( assembler == 'rnaspades' ) {
         // 1. Write a yaml file for Spades
         WRITESPADESYAML (
@@ -303,7 +310,9 @@ workflow METATDENOVO {
             .map { [ [ id: 'megahit' ], it ] }
             .set { ch_assembly_contigs }
         ch_versions = ch_versions.mix(MEGAHIT_INTERLEAVED.out.versions)
-    } else { error 'Assembler not specified!' }
+    } else { 
+        error 'Assembler not specified!' 
+    }
 
     // If the user asked for length filtering, perform that with SEQTK_SEQ (the actual length parameter is used in modules.config)
     if ( params.min_contig_length > 0 ) {
@@ -469,11 +478,11 @@ workflow METATDENOVO {
     // SUBWORKFLOW: Eukulele
     //
     ch_eukulele_db = Channel.empty()
-    if( !params.skip_eukulele){
+    if( ! params.skip_eukulele ) {
         // Create a channel for EUKulele either with a named database or not. The latter means a user-provided database in a directory.
         if ( params.eukulele_db ) {
             Channel
-                .fromList ( params.eukulele_db.split(',') )
+                .of ( params.eukulele_db )
                 .map { [ it, file(params.eukulele_dbpath) ] }
                 .set { ch_eukulele_db }
         } else {