Release: v5.3.0 Rainbow Rattlesnake

.github/workflows/awsfulltest.yml

@@ -37,7 +37,7 @@ jobs:
             }
           profiles: test_full
 
-      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
+      - uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: Seqera Platform debug log file
           path: |

.github/workflows/awstest.yml

@@ -25,7 +25,7 @@ jobs:
             }
           profiles: test
 
-      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
+      - uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: Seqera Platform debug log file
           path: |

.github/workflows/download_pipeline.yml

@@ -127,7 +127,7 @@ jobs:
           fi
 
       - name: Upload Nextflow logfile for debugging purposes
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: nextflow_logfile.txt
           path: .nextflow.log*

.github/workflows/fix_linting.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # Use the @nf-core-bot token to check out so we can push later
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
+      - uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           token: ${{ secrets.nf_core_bot_auth_token }}
 

.github/workflows/linting.yml

@@ -11,7 +11,7 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
+      - uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
 
       - name: Set up Python 3.14
         uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # v6
@@ -28,7 +28,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v2
@@ -71,7 +71,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: linting-logs
           path: |

.github/workflows/nf-test.yml

@@ -40,7 +40,7 @@ jobs:
           rm -rf ./* || true
           rm -rf ./.??* || true
           ls -la ./
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
+      - uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
 
@@ -86,7 +86,7 @@ jobs:
       TOTAL_SHARDS: ${{ needs.nf-test-changes.outputs.total_shards }}
 
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
+      - uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
 

.github/workflows/template-version-comment.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           ref: ${{ github.event.pull_request.head.sha }}
 

.nf-core.yml

@@ -6,7 +6,7 @@ lint:
     - config_defaults:
         - params.phix_reference
         - params.lambda_reference
-nf_core_version: 3.4.1
+nf_core_version: 3.5.1
 repository_type: pipeline
 template:
   author: "Hadrien Gourlé, Daniel Straub, Sabrina Krakau, James A. Fellows Yates, Maxime Borry"
@@ -16,4 +16,4 @@ template:
   name: mag
   org: nf-core
   outdir: .
-  version: 5.2.0
+  version: 5.3.0

.prettierignore

@@ -12,3 +12,5 @@ testing*
 bin/
 .nf-test/
 ro-crate-metadata.json
+modules/nf-core/
+subworkflows/nf-core/

CHANGELOG.md

@@ -3,6 +3,50 @@
 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).
 
+## v5.3.0 - Rainbow Rattlesnake [2025-12-05]
+
+### `Added`
+
+- [#905](https://github.com/nf-core/mag/pull/905) - Add nf-test snapshot for `test_assembly_input` profile (by @dialvarezs)
+- [#930](https://github.com/nf-core/mag/pull/930) - Add binner SemiBin2 (by @d4straub)
+- [#861](https://github.com/nf-core/mag/pull/861) - Added `--generate_bigmag_file` to execute the bigmag workflow that generates the file to be used as input for [BIgMAG](https://github.com/jeffe107/BIgMAG) (added by @jeffe107)
+
+### `Changed`
+
+- [#932](https://github.com/nf-core/mag/pull/932) - Replaced usages of deprecated `Channel()` with `channel()` and fix other LSP warnings (by @dialvarezs)
+- [#937](https://github.com/nf-core/mag/pull/937) - Updated to nf-core 3.5.1 `TEMPLATE` (by @dialvarezs)
+- [#938](https://github.com/nf-core/mag/pull/938) - Update nf-core modules (by @dialvarezs)
+
+### `Fixed`
+
+- [#894](https://github.com/nf-core/mag/pull/894) - Fix read order in metaSPAdes to allow co-assembly of paired-end data of multiple samples (reported by @maartenciers, fix by @jfy133 with contributions from @prototaxites, @d4straub and @dialvarezs)
+- [#927](https://github.com/nf-core/mag/pull/927) - MetaBinner now succeeds when no contigs are too short or all are binned (reported by @MicroSeq, fix by @d4straub)
+- [#929](https://github.com/nf-core/mag/pull/929) - Allow the domain_classification.R script to run with any assembler, not just Megahit or Spades (reported by @MicroSeq, fix by @prototaxites)
+- [#943](https://github.com/nf-core/mag/pull/943) - Fixed concatenation of BUSCO summaries with uneven columns by changing from `csvtk` to `qsv` (reported by @jfy133 and @julianu, fix by @dialvarezs)
+- [#943](https://github.com/nf-core/mag/pull/943) - Fixed creation of the Tiara report channel used for concatenation (by @dialvarezs)
+- [#945](https://github.com/nf-core/mag/pull/945) - Skip mixing of GTDB-Tk MultiQC files when binning is skipped (reported by @amizeranschi, fix by @dialvarezs)
+- [#953](https://github.com/nf-core/mag/pull/953) - metaSPAdes retries upon error 250 (out of memory), rather than finishing the pipeline.
+- [#945](https://github.com/nf-core/mag/pull/954) - Skip GTDB-Tk when no bin QC tool is enabled and add warning messages (fix by @dialvarezs)
+
+### `Dependencies`
+
+| Tool     | Previous version | New version |
+| -------- | ---------------- | ----------- |
+| bcftools | 1.21             | 1.22        |
+| csvtk    | 0.31.0           | 5.1.0       |
+| fastp    | 0.24.0           | 1.0.1       |
+| geNomad  | 1.11.1           | 1.11.2      |
+| metamdbg | 1.1              | 1.2         |
+| mmseqs   | 17.b804f         | 18.8cc5c    |
+| nf-core  |                  | 3.5.1       |
+| qsv      |                  | 5.1.0       |
+| samtools | 1.21             | 1.22.1      |
+| SemiBin2 |                  | 2.2.0       |
+
+### `Deprecated`
+
+- [#943](https://github.com/nf-core/mag/pull/943) - Remove `csvtk/concat` module (by @dialvarezs).
+
 ## v5.2.0 - Puce Pangolin [2025-11-07]
 
 ### `Added`

CITATIONS.md

@@ -56,6 +56,10 @@
 
   > Wang Z, Huang P, You R, Sun F, Zhu S. MetaBinner: a high-performance and stand-alone ensemble binning method to recover individual genomes from complex microbial communities. Genome Biol. 2023 Jan 6;24(1):1. doi: 10.1186/s13059-022-02832-6. PMID: 36609515; PMCID: PMC9817263.
 
+- [SemiBin2](https://doi.org/10.1038/s41467-022-29843-y)
+
+  > Pan S, Zhu C, Zhao XM, Coelho LP. A deep siamese neural network improves metagenome-assembled genomes in microbiome datasets across different environments. Nat Commun. 2022 Apr 28;13(1):2326. doi: 10.1038/s41467-022-29843-y. PMID: 35484115; PMCID: PMC9051138.
+
 - [DAS Tool](https://doi.org/10.1038/s41564-018-0171-1)
 
   > Sieber, C. M. K., et al. 2018. "Recovery of Genomes from Metagenomes via a Dereplication, Aggregation and Scoring Strategy." Nature Microbiology 3 (7): 836-43. doi: 10.1038/s41564-018-0171-1
@@ -90,6 +94,10 @@
 
   > Orakov, A., Fullam, A., Coelho, A. P., Khedkar, S., Szklarczyk, D., Mende, D. R., Schmidt, T. S. B., and Bork, P.. 2021. “GUNC: Detection of Chimerism and Contamination in Prokaryotic Genomes.” Genome Biology 22 (1): 178. doi: 10.1186/s13059-021-02393-0.
 
+- [BIgMAG](https://doi.org/10.12688/f1000research.152290.2)
+
+  > Yepes-García, J., Falquet, L. (2024). Metagenome quality metrics and taxonomical annotation visualization through the integration of MAGFlow and BIgMAG. F1000Research 13:640. doi.org/10.12688/f1000research.152290.2
+
 - [MaxBin2](https://doi.org/10.1093/bioinformatics/btv638)
 
   > Yu-Wei, W., Simmons, B. A. & Singer, S. W. (2015) MaxBin 2.0: An Automated Binning Algorithm to Recover Genomes from Multiple Metagenomic Datasets. Bioinformatics 32 (4): 605–7. doi: 10.1093/bioinformatics/btv638.

README.md

@@ -5,23 +5,26 @@
   </picture>
 </h1>
 
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://github.com/codespaces/new/nf-core/mag)
+[![Open in GitHub Codespaces](https://img.shields.io/badge/Open_In_GitHub_Codespaces-black?labelColor=grey&logo=github)](https://github.com/codespaces/new/nf-core/mag)
 [![GitHub Actions CI Status](https://github.com/nf-core/mag/actions/workflows/nf-test.yml/badge.svg)](https://github.com/nf-core/mag/actions/workflows/nf-test.yml)
 [![GitHub Actions Linting Status](https://github.com/nf-core/mag/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/mag/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/mag/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.3589527-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.3589527)
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 [![Cite Publication](https://img.shields.io/badge/Cite%20Us!-Cite%20Publication-orange)](https://doi.org/10.1093/nargab/lqac007)
 
 [![Nextflow](https://img.shields.io/badge/version-%E2%89%A525.04.2-green?style=flat&logo=nextflow&logoColor=white&color=%230DC09D&link=https%3A%2F%2Fnextflow.io)](https://www.nextflow.io/)
-[![nf-core template version](https://img.shields.io/badge/nf--core_template-3.4.1-green?style=flat&logo=nfcore&logoColor=white&color=%2324B064&link=https%3A%2F%2Fnf-co.re)](https://github.com/nf-core/tools/releases/tag/3.4.1)
+[![nf-core template version](https://img.shields.io/badge/nf--core_template-3.5.1-green?style=flat&logo=nfcore&logoColor=white&color=%2324B064&link=https%3A%2F%2Fnf-co.re)](https://github.com/nf-core/tools/releases/tag/3.5.1)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)
+
 [![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/mag)
 
 [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23mag-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/mag)[![Follow on Bluesky](https://img.shields.io/badge/bluesky-%40nf__core-1185fe?labelColor=000000&logo=bluesky)](https://bsky.app/profile/nf-co.re)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
 
 ![HiRSE Code Promo Badge](https://img.shields.io/badge/Promo-8db427?label=HiRSE&labelColor=005aa0&link=https%3A%2F%2Fgo.fzj.de%2FCodePromo)
 
+[![Static Badge](https://img.shields.io/badge/%F0%9F%8D%94%20%20BIgMAG-compatible-%2324B064)](https://github.com/jeffe107/BIgMAG)
+
 ## Introduction
 
 **nf-core/mag** is a bioinformatics best-practise analysis pipeline for assembly, binning and annotation of metagenomes.
@@ -35,19 +38,14 @@
 
 ## Pipeline summary
 
-## Usage
-
-> [!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), [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:
 
 - performs assembly using [MEGAHIT](https://github.com/voutcn/megahit) and [SPAdes](http://cab.spbu.ru/software/spades/), and checks their quality using [Quast](http://quast.sourceforge.net/quast)
 - (optionally) performs ancient DNA assembly validation using [PyDamage](https://github.com/maxibor/pydamage) and contig consensus sequence recalling with [Freebayes](https://github.com/freebayes/freebayes) and [BCFtools](http://samtools.github.io/bcftools/bcftools.html)
 - predicts protein-coding genes for the assemblies using [Prodigal](https://github.com/hyattpd/Prodigal), and bins with [Prokka](https://github.com/tseemann/prokka) and optionally [MetaEuk](https://www.google.com/search?channel=fs&client=ubuntu-sn&q=MetaEuk)
-- performs metagenome binning using [MetaBAT2](https://bitbucket.org/berkeleylab/metabat/src/master/), [MaxBin2](https://sourceforge.net/projects/maxbin2/), [CONCOCT](https://github.com/BinPro/CONCOCT), [COMEBin](https://github.com/ziyewang/COMEBin), and/or [MetaBinner](https://github.com/ziyewang/MetaBinner)
+- performs metagenome binning using [MetaBAT2](https://bitbucket.org/berkeleylab/metabat/src/master/), [MaxBin2](https://sourceforge.net/projects/maxbin2/), [CONCOCT](https://github.com/BinPro/CONCOCT), [COMEBin](https://github.com/ziyewang/COMEBin), [MetaBinner](https://github.com/ziyewang/MetaBinner), and/or [SemiBin2](https://github.com/BigDataBiology/SemiBin)
 - checks the quality of the genome bins using [Busco](https://busco.ezlab.org/), [CheckM](https://ecogenomics.github.io/CheckM/), or [CheckM2](https://github.com/chklovski/CheckM2) and optionally [GUNC](https://grp-bork.embl-community.io/gunc/)
 - Performs ancient DNA validation and repair with [pyDamage](https://github.com/maxibor/pydamage) and [freebayes](https://github.com/freebayes/freebayes)
 - optionally refines bins with [DAS Tool](https://github.com/cmks/DAS_Tool)
@@ -102,6 +100,7 @@ Other code contributors include:
 - [Greg Fedewa](https://github.com/harper357)
 - [Vini Salazar](https://github.com/vinisalazar)
 - [Alex Caswell](https://github.com/AlexHoratio)
+- [Jeferyd Yepes](https://github.com/jeffe107)
 
 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

@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/5.2.0" 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/5.2.0/docs/output" target="_blank">documentation</a>.
+  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/5.3.0" 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/5.3.0/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-mag-methods-description":
     order: -1000

bin/combine_tables.py

@@ -202,6 +202,7 @@ def main(args=None):
             "Coding_Density",
             "Translation_Table_Used",
             "Total_Coding_Sequences",
+            "Genome_Size"
         ]
         checkm2_results = pd.read_csv(
             args.checkm2_summary, usecols=use_columns, sep="\t"

bin/domain_classification.R

@@ -23,11 +23,6 @@ parser <- add_option(parser, c("-j", "--join_prokaryotes"),
                     default = TRUE,
                     metavar = "logical",
                     help = "Use an general prokaryote classification instead of separating Archaea and Bacteria.")
-parser <- add_option(parser, c("-a", "--assembler"),
-                    action = "store",
-                    type = "character",
-                    metavar = "character",
-                    help = "Assembler used to assemble the contigs. 'MEGAHIT' or 'SPAdes' only.")
 parser <- add_option(parser, c("-o", "--output_prefix"),
                     action = "store",
                     type = "character",
@@ -42,12 +37,6 @@ if(is.null(args$classification_file)) {
 if(is.null(args$contig_to_bin)) {
     stop("Contig to bin file not provided.")
 }
-if(is.null(args$assembler)) {
-    stop("Assembler not provided.")
-}
-if(!(args$assembler %in% c("MEGAHIT", "SPAdes"))) {
-    stop("Invalid assembler provided.")
-}
 
 find_classification <- function(probabilities, join_prokaryotes = TRUE) {
     if(join_prokaryotes) {
@@ -58,14 +47,13 @@ find_classification <- function(probabilities, join_prokaryotes = TRUE) {
     return(classifications[which.max(probabilities)])
 }
 
-classify_bins <- function(tiara, contig2bin, join_prokaryotes, assembler){
-    ## MEGAHIT produces contigs with spaces in the name
+classify_bins <- function(tiara, contig2bin, join_prokaryotes){
+    ## Some assemblers produce contigs with spaces in the name
     ## Depending on the binner, everything after the first space is sometimes dropped
     ## Make sure that we drop everything after a possible space before doing anything else to allow merging
-    if(assembler == "MEGAHIT"){
-        tiara$sequence_id <- word(tiara$sequence_id)
-        contig2bin$sequence_id <- word(contig2bin$sequence_id)
-    }
+    tiara$sequence_id <- word(tiara$sequence_id)
+    contig2bin$sequence_id <- word(contig2bin$sequence_id)
+
     if(join_prokaryotes) {
         n_classifications <- 4
     } else {
@@ -140,10 +128,11 @@ classify_bins <- function(tiara, contig2bin, join_prokaryotes, assembler){
 classifications <- read_tsv(args$classification_file, na = c("NA", "n/a"))
 contig_to_bin <- read_tsv(args$contig_to_bin, col_names = c("sequence_id", "BinID"))
 
-results <- classify_bins(tiara = classifications,
-                        contig2bin = contig_to_bin,
-                        join_prokaryotes = args$join_prokaryotes,
-                        assembler = args$assembler)
+results <- classify_bins(
+  tiara = classifications,
+  contig2bin = contig_to_bin,
+  join_prokaryotes = args$join_prokaryotes
+)
 
 ## Keep just the classifications so we can loop over more easily
 results_basic <- select(results, BinID, classification)