Merge pull request #782 from nf-core/dev

Release PR for 3.4.0

Author: jfy133

.nf-core.yml

@@ -16,4 +16,4 @@ template:
   name: mag
   org: nf-core
   outdir: .
-  version: 3.3.1
+  version: 3.4.0

CHANGELOG.md

@@ -3,7 +3,35 @@
 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).
 
-## v3.3.1 - [2025-03-13]
+## 3.4.0 [2025-04-04]
+
+### `Added`
+
+- [#745](https://github.com/nf-core/mag/pull/745) - Added pipeline parameter `spades_downstreaminput` to use contigs instead of scaffolds (by @Pranjal-Bioinfo, @jfy133, @GallVp & @sateeshperi).
+- [#745](https://github.com/nf-core/mag/pull/745) - Added `trimmomatic` as an additional pre-processing tool (by @Pranjal-Bioinfo, @jfy133, @GallVp & @sateeshperi).
+- [#745](https://github.com/nf-core/mag/pull/745) - Added parameters for `concoct/cut_up_fasta.py` including `bin_concoct_chunksize`, `bin_concoct_overlap` and `bin_concoct_donotconcatlast` (by @Pranjal-Bioinfo, @jfy133, @GallVp & @sateeshperi).
+- [#777](https://github.com/nf-core/mag/pull/777) - Improved input validation through additional JSON keywords and error messages (by @agusinac)
+
+### `Changed`
+
+- [#774](https://github.com/nf-core/mag/pull/774) - Update CheckM2 to v1.1.0 and default database (by @dialvarezs).
+
+### `Fixed`
+
+- [#726](https://github.com/nf-core/mag/pull/726) - Fix formatting errors to follow Nextflow best practice (by @dialvarezs).
+- [#769](https://github.com/nf-core/mag/pull/769) - Fix megahit not emitting correct filenames due to suboptimal arguments ordering (reported and fix by @IceGreb)
+- [#771](https://github.com/nf-core/mag/pull/771) - Fix misspecified checkm2 database parameter check (reported by @dpelegri and fix by @jfy133)
+
+### `Dependencies`
+
+| Tool    | Previous version | New version |
+| ------- | ---------------- | ----------- |
+| CheckM2 | 1.0.2            | 1.1.0       |
+| SPAdes  | 4.0.0            | 4.1.0       |
+
+### `Deprecated`
+
+## v3.3.1 - [2025-02-13]
 
 ### `Added`
 

README.md

@@ -33,7 +33,7 @@
 > [!NOTE]
 > If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
 
-By default, the pipeline currently performs the following: it supports both short and long reads, quality trims the reads and adapters with [fastp](https://github.com/OpenGene/fastp) and [Porechop](https://github.com/rrwick/Porechop), and performs basic QC with [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/), and merge multiple sequencing runs.
+By default, the pipeline currently performs the following: it supports both short and long reads, quality trims the reads and adapters with [fastp](https://github.com/OpenGene/fastp), [AdapterRemoval](https://github.com/MikkelSchubert/adapterremoval), or [trimmomatic](https://github.com/usadellab/Trimmomatic) and [Porechop](https://github.com/rrwick/Porechop), and performs basic QC with [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/), and merges multiple sequencing runs.
 
 The pipeline then:
 
@@ -97,6 +97,7 @@ Other code contributors include:
 - [@willros](https://github.com/willros)
 - [Adam Rosenbaum](https://github.com/muabnezor)
 - [Diego Alvarez](https://github.com/dialvarezs)
+- [Nikolaos Vergoulidis](https://github.com/IceGreb)
 
 Long read processing was inspired by [caspargross/HybridAssembly](https://github.com/caspargross/HybridAssembly) written by Caspar Gross [@caspargross](https://github.com/caspargross)
 

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/3.3.1"
+  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/3.4.0"
   target="_blank">nf-core/mag</a> analysis pipeline. For information about how to
-  interpret these results, please see the <a href="https://nf-co.re/mag/3.3.1/docs/output"
+  interpret these results, please see the <a href="https://nf-co.re/mag/3.4.0/docs/output"
   target="_blank">documentation</a>.
 report_section_order:
   "nf-core-mag-methods-description":
@@ -28,6 +28,7 @@ run_modules:
   - prokka
   - porechop
   - filtlong
+  - trimmomatic
 
 ## Module order
 top_modules:
@@ -37,6 +38,7 @@ top_modules:
         - "*trimmed*"
   - "fastp"
   - "adapterremoval"
+  - "trimmomatic"
   - "porechop"
   - "filtlong"
   - "fastqc":
@@ -137,6 +139,8 @@ extra_fn_clean_exts:
   - "phix_removed"
   - "centrifuge_kreport"
   - "_fastp"
+  - "_trimmomatic_trim.log"
+  - "_trimmomatic_trim"
 
 ## Prettification
 custom_logo: "mag_logo_mascot_light.png"

assets/schema_input.json

@@ -10,36 +10,42 @@
             "sample": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "meta": ["id"]
+                "meta": ["id"],
+                "errorMessage": "Sample needs to be string or integer with no spaces!"
             },
             "run": {
                 "type": ["string", "integer"],
                 "pattern": "^\\S+$",
                 "meta": ["run"],
-                "unique": ["sample"]
+                "unique": ["sample"],
+                "errorMessage": "Run needs to be string or integer with no spaces!"
             },
             "group": {
                 "type": ["string", "integer"],
                 "pattern": "^\\S+$",
-                "meta": ["group"]
+                "meta": ["group"],
+                "errorMessage": "Group needs to be string or integer with no spaces!"
             },
             "short_reads_1": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$"
+                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
+                "errorMessage": "short_reads_1 needs to be a file path with no spaces.\n\nFile needs to exist!"
             },
             "short_reads_2": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$"
+                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
+                "errorMessage": "short_reads_2 needs to be a file path with no spaces.\n\nFile needs to exist!"
             },
             "long_reads": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$"
+                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
+                "errorMessage": "long_reads needs to be a file path with no spaces.\n\nFile needs to exist!"
             }
         },
         "required": ["sample", "group", "short_reads_1"]

conf/modules.config

@@ -47,6 +47,25 @@ process {
         tag        = { "${meta.id}_run${meta.run}" }
     }
 
+    withName: TRIMMOMATIC {
+        ext.args   = "LEADING:30 TRAILING:30 SLIDINGWINDOW:4:20 MINLEN:35"
+        publishDir = [
+            [
+                path: { "${params.outdir}/QC_shortreads/trimmomatic/${meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "*_trim.log",
+            ],
+            [
+                path: { "${params.outdir}/QC_shortreads/trimmomatic/${meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "*.fastq.gz",
+                enabled: params.save_clipped_reads,
+            ],
+        ]
+        ext.prefix = { "${meta.id}_run${meta.run}_trimmomatic" }
+        tag        = { "${meta.id}_run${meta.run}" }
+    }
+
     withName: ADAPTERREMOVAL_PE {
         ext.args   = [
             "--minlength ${params.reads_minlength}",
@@ -620,6 +639,14 @@ process {
         ]
     }
 
+    withName: CONCOCT_CUTUPFASTA {
+        ext.args = [
+            "-c ${params.bin_concoct_chunksize}",
+            "-o ${params.bin_concoct_overlap}",
+            params.bin_concoct_donotconcatlast ? "" : "--merge_last",
+        ].join(' ').trim()
+    }
+
     withName: 'CONCOCT_.*' {
         publishDir = [
             [

conf/test_ancient_dna.config

@@ -15,7 +15,7 @@ process {
     resourceLimits = [
         cpus: 4,
         memory: '15.GB',
-        time: '1.h'
+        time: '1.h',
     ]
 }
 
@@ -28,6 +28,8 @@ params {
     input                                = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
     centrifuge_db                        = params.pipelines_testdata_base_path + 'mag/test_data/minigut_cf.tar.gz'
     kraken2_db                           = params.pipelines_testdata_base_path + 'mag/test_data/minigut_kraken.tgz'
+    clip_tool                            = 'trimmomatic'
+    spades_downstreaminput               = 'contigs'
     skip_krona                           = true
     min_length_unbinned_contigs          = 1
     max_unbinned_contigs                 = 2