[PSEUDO-PR - DO NOT MERGE] core team release review

.github/actions/nf-test/action.yml

@@ -43,6 +43,9 @@ runs:
       if: contains(inputs.profile, 'singularity')
       shell: bash
       run: |
+        # The runner image restricts unprivileged user namespaces, which non-suid
+        # apptainer needs to start a container at all.
+        sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
         mkdir -p $NXF_SINGULARITY_CACHEDIR
         mkdir -p $NXF_SINGULARITY_LIBRARYDIR
 
@@ -53,7 +56,7 @@ runs:
         auto-update-conda: true
         conda-solver: libmamba
         channels: conda-forge
-        channel-priority: strict
+        channel-priority: flexible
         conda-remove-defaults: true
 
     - name: Run nf-test

.github/workflows/awsfulltest.yml

@@ -24,7 +24,6 @@ jobs:
 
       - name: Launch workflow via Seqera Platform
         uses: seqeralabs/action-tower-launch@51565b514bff1827cf34620de25d0055759f1fc9 # v2
-        # TODO nf-core: You can customise AWS full pipeline tests as required
         # Add full size test data (but still relatively small datasets for few samples)
         # on the `test_full.config` test runs with only one set of parameters
         with:

.github/workflows/linting.yml

@@ -67,7 +67,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: linting-logs
           path: |

.github/workflows/nf-test.yml

@@ -18,7 +18,7 @@ concurrency:
 
 env:
   GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-  NFT_VER: "0.9.4"
+  NFT_VER: "0.9.5"
   NFT_WORKDIR: "~"
   NXF_ANSI_LOG: false
   NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity
@@ -50,7 +50,7 @@ jobs:
         env:
           NFT_VER: ${{ env.NFT_VER }}
         with:
-          max_shards: 7
+          max_shards: 19
 
       - name: debug
         run: |
@@ -68,13 +68,11 @@ jobs:
       fail-fast: false
       matrix:
         shard: ${{ fromJson(needs.nf-test-changes.outputs.shard) }}
-        profile: [conda, docker, singularity]
+        profile: [docker, singularity, conda]
         isMain:
           - ${{ github.base_ref == 'master' || github.base_ref == 'main' }}
         # Exclude conda and singularity on dev
         exclude:
-          - isMain: false
-            profile: "conda"
           - isMain: false
             profile: "singularity"
         NXF_VER:
@@ -100,7 +98,19 @@ jobs:
           profile: ${{ matrix.profile }}
           shard: ${{ matrix.shard }}
           total_shards: ${{ env.TOTAL_SHARDS }}
-
+      - name: list contents
+        run: ls -R "${{ env.NFT_WORKDIR }}"
+      - name: list funcprofilercontents
+        run: ls -R /home/runner/_work/funcprofiler/funcprofiler/
+      - name: Upload artifact
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v7
+        with:
+          name: my-artifact-${{ matrix.profile }}-${{ matrix.NXF_VER }}-${{ matrix.shard }}
+          path: |
+            /home/runner/_work/funcprofiler/funcprofiler/
+            !/home/runner/_work/funcprofiler/funcprofiler/**/work/conda/
+          retention-days: 2
       - name: Report test status
         if: ${{ always() }}
         run: |

.gitignore

@@ -7,4 +7,12 @@ testing/
 testing*
 *.pyc
 null/
+*~
+.nf-test/
+.nf-test.log
+dontcommit
+tmp/
+.data/
+*.code-workspace
 .lineage/
+conf/tmp.config

.nf-core.yml

@@ -7,6 +7,7 @@ lint:
     - .gitignore
 nf_core_version: 4.1.0
 repository_type: pipeline
+
 template:
   author: Nick Waters, Vini Salazar, Yixuan Yang, Mirae Baichoo
   description: Read-based functional profiling of microbiome sequencing data

CHANGELOG.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 Initial release of nf-core/funcprofiler, created with the [nf-core](https://nf-co.re/) template.
 
+Read-based functional profiling of short-read microbiome sequencing data with the following profilers, all off by default and each enabled with its own `--run_<tool>` flag:
+
+- [HUMAnN](https://huttenhower.sph.harvard.edu/humann/) v3 and v4, each preceded by a [MetaPhlAn](https://github.com/biobakery/MetaPhlAn) taxonomic prescreen and followed by `humann_regroup_table`
+- [FMH FunProfiler](https://github.com/KoslickiLab/fmh-funprofiler)
+- [mi-faser](https://bromberglab.org/project/mifaser/)
+- [RGI](https://github.com/arpcard/rgi) `bwt`, against CARD
+- [DIAMOND](https://github.com/bbuchfink/diamond) `blastx` (beta)
+- [eggNOG-mapper](https://github.com/eggnogdb/eggnog-mapper) (beta)
+
+This release performs no read QC or preprocessing; reads are expected to arrive already trimmed, quality filtered and host decontaminated.
+Long-read platforms are not supported.
+
 ### `Added`
 
 ### `Fixed`

CITATIONS.md

@@ -10,14 +10,56 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+<!-- updating tools? citations here https://www.ncbi.nlm.nih.gov/sites/myncbi/1pWMw-vIfxi56/collections/67373574/public/ -->
 
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+- [DIAMOND](https://github.com/bbuchfink/diamond/)
+
+> Buchfink B, Reuter K, Drost HG. Sensitive protein alignments at tree-of-life scale using DIAMOND. Nat Methods. 2021 Apr;18(4):366-368. doi: 10.1038/s41592-021-01101-x. PubMed PMID: 33828273.
+
+> Buchfink B, Xie C, Huson DH. Fast and sensitive protein alignment using DIAMOND. Nat Methods. 2015 Jan;12(1):59-60. doi: 10.1038/nmeth.3176. Epub 2014 Nov 17. PMID: 25402007.
+
+- [eggNOG-mapper](https://github.com/eggnogdb/eggnog-mapper)
+
+> Cantalapiedra CP, Hernández-Plaza A, Letunic I, Bork P, Huerta-Cepas J. eggNOG-mapper v2: Functional Annotation, Orthology Assignments, and Domain Prediction at the Metagenomic Scale. Mol Biol Evol. 2021 Dec 9;38(12):5825-5829. doi: 10.1093/molbev/msab293. PubMed PMID: 34597405.
+
+- [fmh-funprofiler](https://pubmed.ncbi.nlm.nih.gov/39230701/)
+
+> Hera MR, Liu S, Wei W, Rodriguez JS, Ma C, Koslicki D. Metagenomic functional profiling: to sketch or not to sketch? Bioinformatics. 2024 Sep 1;40(Suppl 2):ii165-ii173. doi: 10.1093/bioinformatics/btae397. PMID: 39230701; PMCID: PMC11373326.
+
+- [HUMAnN](http://huttenhower.sph.harvard.edu/humann)
+
+> Beghini F, McIver L, Blanco-Mìguez A, Dubois L, Asnicar F, Maharjan S ,Mailyan A, Thomas AM, Manghi P, Valles-Colomer M, Weingart G ,Zhang Y, Zolfo M,Huttenhower C, Franzosa EA, Segata N. Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3. eLife 2021;10:e65088
+
+- [mi-faser](https://academic.oup.com/nar/advance-article/doi/10.1093/nar/gkx1209/4670955)
+
+> Zhu C, Miller M, Marpaka S, Vaysberg P, Rühlemann M, Wu G, Heinsen FA, Tempel M, Zhao L, Leib W, Franke A, Bromberg Y. Functional sequencing read annotation for high precision microbiome analysis. Nucleic Acids Research. Volume 46, Issue 4. 2017. doi: 10.1093/nar/gkx1209.
+
+> Mahlich Y, Zhu C, Chung H, Velaga PK, De Paolis Kaluza MC, Radivojac P, Friedberg I, Bromberg Y. Learning from the unknown: exploring the range of bacterial functionality. Nucleic Acids Res. 2023 Oct 27;51(19):10162-10175. doi: 10.1093/nar/gkad757. PubMed PMID: 37739408.
+
+> Zhu C, Delmont TO, Vogel TM, Bromberg Y. Functional Basis of Microorganism Classification. PLoS Comput Biol. 2015 Aug 28;11(8):e1004472. doi: 10.1371/journal.pcbi.1004472. PubMed PMID: 26317871.
+
+- [MetaPhlAn3](http://segatalab.cibio.unitn.it/tools/metaphlan/index.html)
+
+> Beghini F, McIver LJ, Blanco-Míguez A, Dubois L, Asnicar F, Maharjan S, Mailyan A, Manghi P, Scholz M, Thomas AM, Valles-Colomer M, Weingart G, Zhang Y, Zolfo M, Huttenhower C, Franzosa EA, Segata N. Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3. Elife. 2021 May 4;10:e65088. doi: 10.7554/eLife.65088. PMID: 33944776; PMCID: PMC8096432.
+
+- [MetaPhlAn4](http://segatalab.cibio.unitn.it/tools/metaphlan/index.html)
+
+> Blanco-Míguez A, Beghini F, Cumbo F, McIver LJ, Thompson KN, Zolfo M, Manghi P, Dubois L, Huang KD, Thomas AM, Nickols WA, Piccinno G, Piperni E, Punčochář M, Valles-Colomer M, Tett A, Giordano F, Davies R, Wolf J, Berry SE, Spector TD, Franzosa EA, Pasolli E, Asnicar F, Huttenhower C, Segata N. Extending and improving metagenomic taxonomic profiling with uncharacterized species using MetaPhlAn 4. Nat Biotechnol. 2023 Nov;41(11):1633-1644. doi: 10.1038/s41587-023-01688-w. Epub 2023 Feb 23. PMID: 36823356; PMCID: PMC10635831.
 
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
 > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+- [RGI/CARD](https://pubmed.ncbi.nlm.nih.gov/36263822/)
+
+> Alcock BP, Huynh W, Chalil R, Smith KW, Raphenya AR, Wlodarski MA, Edalatmand A, Petkau A, Syed SA, Tsang KK, Baker SJC, Dave M, McCarthy MC, Mukiri KM, Nasir JA, Golbon B, Imtiaz H, Jiang X, Kaur K, Kwong M, Liang ZC, Niu KC, Shan P, Yang JYJ, Gray KL, Hoad GR, Jia B, Bhando T, Carfrae LA, Farha MA, French S, Gordzevich R, Rachwalski K, Tu MM, Bordeleau E, Dooley D, Griffiths E, Zubyk HL, Brown ED, Maguire F, Beiko RG, Hsiao WWL, Brinkman FSL, Van Domselaar G, McArthur AG. CARD 2023: expanded curation, support for machine learning, and resistome prediction at the Comprehensive Antibiotic Resistance Database. Nucleic Acids Res. 2023 Jan 6;51(D1):D690-D699. doi: 10.1093/nar/gkac920. PMID: 36263822; PMCID: PMC9825576.
+
+> McArthur AG, Waglechner N, Nizam F, Yan A, Azad MA, Baylay AJ, Bhullar K, Canova MJ, De Pascale G, Ejim L, Kalan L, King AM, Koteva K, Morar M, Mulvey MR, O'Brien JS, Pawlowski AC, Piddock LJ, Spanogiannopoulos P, Sutherland AD, Tang I, Taylor PL, Thaker M, Wang W, Yan M, Yu T, Wright GD. The comprehensive antibiotic resistance database. Antimicrob Agents Chemother. 2013 Jul;57(7):3348-57. doi: 10.1128/AAC.00419-13. Epub 2013 May 6. PMID: 23650175; PMCID: PMC3697360.
+
+- [seqkit](https://pubmed.ncbi.nlm.nih.gov/27706213/)
+
+> Shen W, Le S, Li Y, Hu F. SeqKit: A Cross-Platform and Ultrafast Toolkit for FASTA/Q File Manipulation. PLoS One. 2016 Oct 5;11(10):e0163962. doi: 10.1371/journal.pone.0163962. PMID: 27706213; PMCID: PMC5051824.
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -21,48 +21,63 @@
 
 ## Introduction
 
-**nf-core/funcprofiler** is a bioinformatics pipeline that ...
+**nf-core/funcprofiler** is a bioinformatics pipeline for read-based functional profiling of microbiome sequencing data. It accepts already preprocessed short-read FASTQ files and runs one or more functional profilers against user-supplied databases, producing gene family abundances, pathway abundances, pathway coverages, and antimicrobial resistance profiles. Long-read platforms are not supported in this release.
 
-<!-- TODO nf-core:
-   Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the
-   major pipeline sections and the types of output it produces. You're giving an overview to someone new
-   to nf-core here, in 15-20 seconds. For an example, see https://github.com/nf-core/rnaseq/blob/master/README.md#introduction
--->
+### Pipeline Summary
 
-<!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
-     workflows use the "tube map" design for that. See https://nf-co.re/docs/community/brand/workflow-schematics#examples for examples.   -->
-<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+![](./assets/pipeline_light.svg)
+
+Supported profilers and current status:
+
+1. [**HUMANn v3**](https://huttenhower.sph.harvard.edu/humann/) — functional profiling via MetaPhlAn + HUMANn 3 (`--run_humann_v3`)
+2. [**HUMANn v4**](https://docs.google.com/document/d/1rCx5JkuO7wCKWrL8_-UJx_FkopJAfcDFtZktgPspak0/edit?tab=t.0#heading=h.i5hn0zprhwld) — functional profiling via MetaPhlAn + HUMANn 4 (`--run_humann_v4`)
+3. [**FMH FunProfiler**](https://github.com/KoslickiLab/fmh-funprofiler) — sketch-based functional profiling (`--run_fmhfunprofiler`)
+4. [**RGI**](https://github.com/arpcard/rgi) — antimicrobial resistance gene identification (`--run_rgi`, available)
+5. [**mifaser**](https://bromberglab.org/project/mifaser/) — functional profiling via mifaser (`--run_mifaser`, available)
+6. [**DIAMOND**](https://github.com/bbuchfink/diamond) — alignment with DIAMOND blastx (`--run_diamond`, work in progress / beta)
+7. [**eggNOG-mapper**](https://github.com/eggnogdb/eggnog-mapper) — functional annotation, orthology assignments and domain prediction (`--run_eggnogmapper`, work in progress / beta)
+
+> [!WARNING]
+> DIAMOND and eggNOG-mapper support is currently in beta and should be treated as work in progress. These modules are still being validated in the full pipeline, including database handling, output behavior, and downstream reporting. Use them with caution, expect potential issues, and independently review results before using them for production analyses or interpretation.
 
 ## Usage
 
 > [!NOTE]
 > If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/get_started/environment_setup/overview) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/get_started/run-your-first-pipeline) with `-profile test` before running the workflow on actual data.
 
-<!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.
-     Explain what rows and columns represent. For instance (please edit as appropriate):
-
-First, prepare a samplesheet with your input data that looks as follows:
+First, prepare a samplesheet with your input data:
 
 `samplesheet.csv`:
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
+SAMPLE1,RUN1,ILLUMINA,/path/to/sample1_R1.fastq.gz,/path/to/sample1_R2.fastq.gz,
+SAMPLE2,RUN1,ILLUMINA,/path/to/sample2.fastq.gz,,
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
+Each row represents a sequencing run. Multiple rows with the same `sample` and different `run_accession` values will be merged before profiling. Reads are expected to arrive already preprocessed: the pipeline performs no read QC, trimming or host decontamination.
 
--->
+Then prepare a databases sheet — see [docs/usage.md](docs/usage.md) for the full format. Here is an abbreviated example for running HUMANn (which requires 4 databases):
 
-Now, you can run the pipeline using:
+`databases.csv`
 
-<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->
+```csv
+tool,db_name,db_entity,db_params,db_path
+humann_v3,uniref90_v3,humann_metaphlan,,/data/databases/metaphlan_db
+humann_v3,uniref90_v3,humann_nucleotide,,/data/databases/chocophlan
+humann_v3,uniref90_v3,humann_protein,,/data/databases/uniref90_diamond
+humann_v3,uniref90_v3,humann_utility,,/data/databases/utility_mapping
+```
+
+Now, you can run the pipeline using:
 
 ```bash
 nextflow run nf-core/funcprofiler \
    -profile <docker/singularity/.../institute> \
    --input samplesheet.csv \
-   --outdir <OUTDIR>
+   --outdir <OUTDIR> \
+   --databases databases.csv \
+   --run_humann_v3
 ```
 
 > [!WARNING]
@@ -82,7 +97,9 @@ nf-core/funcprofiler was originally written by Nick Waters, Vini Salazar, Yixuan
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+- Matthias Hörtenhuber
+- James Fellows Yates
+- Jonas Scheid
 
 ## Contributions and Support
 
@@ -92,11 +109,8 @@ For further information or help, don't hesitate to get in touch on the [Slack `#
 
 ## Citations
 
-<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
 <!-- If you use nf-core/funcprofiler for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
 
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
-
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 
 You can cite the `nf-core` publication as follows:

assets/methods_description_template.yml

@@ -3,7 +3,6 @@ description: "Suggested text and references to use when describing pipeline usag
 section_name: "nf-core/funcprofiler Methods Description"
 section_href: "https://github.com/nf-core/funcprofiler"
 plot_type: "html"
-## TODO nf-core: Update the HTML below to your preferred methods description, e.g. add publication citation for this pipeline
 ## You inject any metadata in the Nextflow '${workflow}' object
 data: |
   <h4>Methods</h4>

assets/nf-metro_command.sh

@@ -0,0 +1,8 @@
+# --x-spacing 110 is load-bearing: the layout was tuned at that spacing.
+# The committed SVGs also carry manual geometry corrections that nf-metro has no
+# directive for (the 'Short reads' caption re-anchored clear of the exit port,
+# the database bundle and report lane routed below the reads trunk, the two file
+# icons centred in their section boxes), so a plain re-render will not reproduce
+# them byte-for-byte.
+nf-metro render pipeline.mmd -o pipeline_light.svg --logo nf-core-funcprofiler_logo_light.png --theme light --animate --x-spacing 110
+nf-metro render pipeline.mmd -o pipeline_nf-core.svg --logo nf-core-funcprofiler_logo_light.png --theme nfcore --animate --x-spacing 110