Code review for #52

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

@@ -38,11 +38,16 @@ runs:
     - name: Setup apptainer
       if: contains(inputs.profile, 'singularity')
       uses: eWaterCycle/setup-apptainer@4bb22c52d4f63406c49e94c804632975787312b3 # v2.0.0
+      with:
+        apptainer-version: 1.5.3
 
     - name: Set up Singularity
       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
 

.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:

.nf-core.yml

@@ -3,7 +3,9 @@ lint:
     - assets/nf-core-funcprofiler_logo_light.png
     - .github/PULL_REQUEST_TEMPLATE.md
     - .github/workflows/linting.yml
-    - .github/workflows/linting_comment.yml
+    # The 4.0.3 template renders `HEAD_REPO:` with two spaces, which the prettier
+    # pin used by prek collapses to one, so this file can never match the template.
+    - .github/workflows/branch.yml
     - .gitignore
 nf_core_version: 4.0.3
 repository_type: pipeline

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>

conf/base.config

@@ -10,7 +10,6 @@
 
 process {
 
-    // TODO nf-core: Check the defaults for all processes
     cpus   = { 1      * task.attempt }
     memory = { 6.GB   * task.attempt }
     time   = { 4.h    * task.attempt }
@@ -24,7 +23,6 @@ process {
     //        These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
     //        If possible, it would be nice to keep the same label naming convention when
     //        adding in your local modules too.
-    // TODO nf-core: Customise requirements for specific processes.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
     withLabel:process_single {
         cpus   = { 1                   }

conf/test.config

@@ -21,11 +21,8 @@ process {
 params {
     config_profile_name                    = 'Test profile'
     config_profile_description             = 'Minimal test dataset to check pipeline function'
-    //input                                  = params.pipelines_testdata_base_path + 'samplesheets/test.csv'
-    input                                  = 'https://github.com/nickp60/test-datasets/raw/refs/heads/funcprofiler/samplesheets/test.csv'
+    input                                  = params.pipelines_testdata_base_path + 'samplesheets/test.csv'
     databases                              = params.pipelines_testdata_base_path + 'database.csv'
-    outdir                                 = "tmp"
-    cleanup                                = false
     run_fmhfunprofiler                     = true
     run_humann_v3                          = true
     run_mifaser                            = true

conf/test_full.config

@@ -13,12 +13,8 @@
 params {
     config_profile_name                    = 'Full test profile'
     config_profile_description             = 'Full test dataset to check pipeline function'
-//    input                                  = params.pipelines_testdata_base_path + 'samplesheets/test.csv'
-//    databases                              = params.pipelines_testdata_base_path + 'database_full.csv'
     input                                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/taxprofiler/samplesheet_shortreadsonly.csv'
-    databases                              = 'https://raw.githubusercontent.com/nickp60/test-datasets/refs/heads/funcprofiler/database_full.csv'
-    outdir                                 = "fulltest_results"
-    cleanup                                = false
+    databases                              = params.pipelines_testdata_base_path + 'database_full.csv'
     run_fmhfunprofiler                     = true
     run_humann_v3                          = true
     run_mifaser                            = true

docs/CONTRIBUTING.md

@@ -182,4 +182,9 @@ If you update images or graphics, follow the nf-core [style guidelines](https://
 
 ## Pipeline specific contribution guidelines
 
-<!-- TODO nf-core: Add any pipeline specific contribution guidelines here, such as coding styles, procedures, checklists etc. -->
+When adding a new profiler:
+
+- Add it to [nf-core/modules](https://github.com/nf-core/modules) rather than to `modules/local`. A local module is only a stopgap for tools that are not yet packaged on Bioconda.
+- Gate it behind a `run_<tool>` parameter, and take its database from the database sheet so it is grouped by `dbprep` like every other tool.
+- Add it to the `profile` subworkflow, to `docs/output.md`, and to `CITATIONS.md`.
+- Cover it with an nf-test, and regenerate snapshots with `nf-test test --update-snapshot`.

main.nf

@@ -38,7 +38,7 @@ workflow NFCORE_FUNCPROFILER {
     //
     // WORKFLOW: Run pipeline
     //
-    FUNCPROFILER (
+    FUNCPROFILER(
         samplesheet,
         databases,
         params.multiqc_config,

modules.json

@@ -12,7 +12,7 @@
                     },
                     "diamond/blastx": {
                         "branch": "master",
-                        "git_sha": "1b534ad2336876dbe82e9fea2773334cb624b426",
+                        "git_sha": "83ce9b314157a24d9a92f17a07ed5d55f30b78f9",
                         "installed_by": ["modules"]
                     },
                     "eggnogmapper": {
@@ -32,7 +32,7 @@
                     },
                     "gunzip": {
                         "branch": "master",
-                        "git_sha": "96c57dfd98a0641886a67bd449fe33ee2ec0e374",
+                        "git_sha": "0902eac3012baaf4f9ab6513c8c55acc9353c96c",
                         "installed_by": ["modules"]
                     },
                     "humann3/humann": {
@@ -57,7 +57,7 @@
                     },
                     "mifaser": {
                         "branch": "master",
-                        "git_sha": "6b43745037429413ca11e0e4a1029d90493c3135",
+                        "git_sha": "522d0a5709833aaa28c58d4464b4348d03316a62",
                         "installed_by": ["modules"]
                     },
                     "multiqc": {
@@ -77,12 +77,12 @@
                     },
                     "seqkit/fq2fa": {
                         "branch": "master",
-                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "git_sha": "d07a945f421a4a91ce4e5a22db63e0e7f8741607",
                         "installed_by": ["modules"]
                     },
                     "untar": {
                         "branch": "master",
-                        "git_sha": "447f7bc0fa41dfc2400c8cad4c0291880dc060cf",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
                         "installed_by": ["modules"]
                     }
                 }
@@ -101,7 +101,7 @@
                     },
                     "utils_nfschema_plugin": {
                         "branch": "master",
-                        "git_sha": "ce3424257de288c0ca25f097a68d3a289da23f12",
+                        "git_sha": "a7b27fd25bfa8dcc07d299e88bd790585901a436",
                         "installed_by": ["subworkflows"]
                     }
                 }

modules/local/humann4/humann/main.nf

@@ -1,6 +1,6 @@
 // Taken 98% from https://github.com/nf-core/modules/pull/1089/files
 process HUMANN4 {
-    tag "$meta.id"
+    tag "${meta.id}"
     label 'process_high'
 
     conda "${moduleDir}/environment.yml"
@@ -14,10 +14,10 @@ process HUMANN4 {
     path utility_db
 
     output:
-    tuple val(meta), path("*_genefamilies.tsv.gz") , emit: genefamilies
+    tuple val(meta), path("*_genefamilies.tsv.gz"), emit: genefamilies
     tuple val(meta), path("*_pathabundance.tsv.gz"), emit: pathabundance
-    tuple val(meta), path("*_reactions.tsv.gz")    , emit: reactions
-    tuple val(meta), path("*.log")                 , emit: log
+    tuple val(meta), path("*_reactions.tsv.gz"), emit: reactions
+    tuple val(meta), path("*.log"), emit: log
     tuple val("${task.process}"), val('HUMAnN'), eval("humann --version 2>&1 | sed 's/humann v//'"), emit: versions_humann, topic: versions
     tuple val("${task.process}"), val('MetaPHLan'), eval("metaphlan --version 2>&1 | sed 's/metaphlan v//'"), emit: versions_metaphlan, topic: versions
 
@@ -39,13 +39,13 @@ process HUMANN4 {
 
     find \${NUCS_DB}
     humann \\
-        $args \\
+        ${args} \\
         --threads ${task.cpus} \\
-        --input $input \\
+        --input ${input} \\
         --protein-database \${PROTS_DB} \\
         --nucleotide-database \${NUCS_DB} \\
-        --output-basename $prefix \\
-        $pangenome_string \\
+        --output-basename ${prefix} \\
+        ${pangenome_string} \\
 	${args} \\
         --o-log ${prefix}.log \\
         --output .
@@ -54,11 +54,12 @@ process HUMANN4 {
     gzip -n *.tsv
 
     """
+
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    echo $args
+    echo ${args}
 
     for suf in genefamilies.tsv.gz pathabundance.tsv.gz  reactions.tsv.gz
     do