nf-core · subwaystation · Jan 23, 2025 · Jan 20, 2025
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -46,6 +46,8 @@ jobs:
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+        with:
+          fetch-depth: 0
 
       - name: Set up Nextflow
         uses: nf-core/setup-nextflow@v2

diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml
@@ -34,6 +34,17 @@ jobs:
       REPO_LOWERCASE: ${{ steps.get_repo_properties.outputs.REPO_LOWERCASE }}
       REPOTITLE_LOWERCASE: ${{ steps.get_repo_properties.outputs.REPOTITLE_LOWERCASE }}
       REPO_BRANCH: ${{ steps.get_repo_properties.outputs.REPO_BRANCH }}
+    steps:
+      - name: Get the repository name and current branch
+        id: get_repo_properties
+        run: |
+          echo "REPO_LOWERCASE=${GITHUB_REPOSITORY,,}" >> "$GITHUB_OUTPUT"
+          echo "REPOTITLE_LOWERCASE=$(basename ${GITHUB_REPOSITORY,,})" >> "$GITHUB_OUTPUT"
+          echo "REPO_BRANCH=${{ github.event.inputs.testbranch || 'dev' }}" >> "$GITHUB_OUTPUT"
+
+  download:
+    runs-on: ubuntu-latest
+    needs: configure
     steps:
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v2
@@ -56,21 +67,10 @@ jobs:
           python -m pip install --upgrade pip
           pip install git+https://github.com/nf-core/tools.git@dev
 
-      - name: Get the repository name and current branch set as environment variable
-        id: get_repo_properties
-        run: |
-          echo "REPO_LOWERCASE=${GITHUB_REPOSITORY,,}" >> "$GITHUB_OUTPUT"
-          echo "REPOTITLE_LOWERCASE=$(basename ${GITHUB_REPOSITORY,,})" >> "$GITHUB_OUTPUT"
-          echo "REPO_BRANCH=${{ github.event.inputs.testbranch || 'dev' }}" >> "$GITHUB_OUTPUT"
-
       - name: Make a cache directory for the container images
         run: |
           mkdir -p ./singularity_container_images
 
-  download:
-    runs-on: ubuntu-latest
-    needs: configure
-    steps:
       - name: Download the pipeline
         env:
           NXF_SINGULARITY_CACHEDIR: ./singularity_container_images
@@ -87,6 +87,9 @@ jobs:
       - name: Inspect download
         run: tree ./${{ needs.configure.outputs.REPOTITLE_LOWERCASE }}
 
+      - name: Inspect container images
+        run: tree ./singularity_container_images | tee ./container_initial
+
       - name: Count the downloaded number of container images
         id: count_initial
         run: |
@@ -123,7 +126,8 @@ jobs:
             final_count=${{ steps.count_afterwards.outputs.IMAGE_COUNT_AFTER }}
             difference=$((final_count - initial_count))
             echo "$difference additional container images were \n downloaded at runtime . The pipeline has no support for offline runs!"
-            tree ./singularity_container_images
+            tree ./singularity_container_images > ./container_afterwards
+            diff ./container_initial ./container_afterwards
             exit 1
           else
             echo "The pipeline can be downloaded successfully!"

diff --git a/.nf-core.yml b/.nf-core.yml
@@ -1,7 +1,7 @@
 lint:
   files_unchanged:
     - assets/nf-core-pangenome_logo_light.png
-nf_core_version: 3.1.1
+nf_core_version: 3.1.2
 repository_type: pipeline
 template:
   author: Simon Heumos, Michael L Heuer
@@ -15,4 +15,7 @@ template:
   name: pangenome
   org: nf-core
   outdir: .
+  skip_features:
+    - fastqc
+    - igenomes
   version: 1.2.0dev
diff --git a/CITATIONS.md b/CITATIONS.md
@@ -10,9 +10,7 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
-
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+- [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.
 

diff --git a/README.md b/README.md
@@ -3,7 +3,9 @@
     <source media="(prefers-color-scheme: dark)" srcset="docs/images/nf-core-pangenome_logo_dark.png">
     <img alt="nf-core/pangenome" src="docs/images/nf-core-pangenome_logo_light.png">
   </picture>
-</h1>[![GitHub Actions CI Status](https://github.com/nf-core/pangenome/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/pangenome/actions/workflows/ci.yml)
+</h1>
+
+[![GitHub Actions CI Status](https://github.com/nf-core/pangenome/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/pangenome/actions/workflows/ci.yml)
 [![GitHub Actions Linting Status](https://github.com/nf-core/pangenome/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/pangenome/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/pangenome/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 
@@ -27,12 +29,12 @@
 
 <!-- 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/contributing/design_guidelines#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/))
+<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## 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.
+> 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.
 
 <!-- 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):
@@ -89,7 +91,9 @@ 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/pangenome 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 -->
+<!-- If you use nf-core/pangenome 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.
 

diff --git a/conf/igenomes.config b/conf/igenomes.config
diff --git a/conf/igenomes_ignored.config b/conf/igenomes_ignored.config
diff --git a/conf/modules.config b/conf/modules.config
@@ -18,10 +18,6 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
-    withName: FASTQC {
-        ext.args = '--quiet'
-    }
-
     withName: 'MULTIQC' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [

diff --git a/conf/test.config b/conf/test.config
@@ -26,7 +26,4 @@ params {
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input  = params.pipelines_testdata_base_path + 'viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
-
-    // Genome references
-    genome = 'R64-1-1'
 }
diff --git a/conf/test_full.config b/conf/test_full.config
@@ -19,6 +19,6 @@ params {
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input = params.pipelines_testdata_base_path + 'viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv'
 
-    // Genome references
-    genome = 'R64-1-1'
+    // Fasta references
+    fasta = params.pipelines_testdata_base_path + 'viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz'
 }
diff --git a/docs/output.md b/docs/output.md
@@ -12,21 +12,10 @@ The directories listed below will be created in the results directory after the
 
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
 
-- [FastQC](#fastqc) - Raw read QC- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
+- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
-### FastQC
-
-<details markdown="1">
-<summary>Output files</summary>
-
-- `fastqc/`
-  - `*_fastqc.html`: FastQC report containing quality metrics.
-  - `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images.
-
-</details>
-
-[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).### MultiQC
+### MultiQC
 
 <details markdown="1">
 <summary>Output files</summary>

diff --git a/docs/usage.md b/docs/usage.md
@@ -57,7 +57,7 @@ An [example samplesheet](../assets/samplesheet.csv) has been provided with the p
 The typical command for running the pipeline is as follows:
 
 ```bash
-nextflow run nf-core/pangenome --input ./samplesheet.csv --outdir ./results --genome GRCh37 -profile docker
+nextflow run nf-core/pangenome --input ./samplesheet.csv --outdir ./results  -profile docker
 ```
 
 This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles.
@@ -89,7 +89,6 @@ with:
 ```yaml title="params.yaml"
 input: './samplesheet.csv'
 outdir: './results/'
-genome: 'GRCh37'
 <...>
 ```
 

diff --git a/main.nf b/main.nf
@@ -18,19 +18,6 @@
 include { PANGENOME  } from './workflows/pangenome'
 include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_pangenome_pipeline'
 include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_pangenome_pipeline'
-include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_pangenome_pipeline'
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    GENOME PARAMETER VALUES
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-// TODO nf-core: Remove this line if you don't need a FASTA file
-//   This is an example of how to use getGenomeAttribute() to fetch parameters
-//   from igenomes.config using `--genome`
-params.fasta = getGenomeAttribute('fasta')
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     NAMED WORKFLOWS FOR PIPELINE

diff --git a/modules.json b/modules.json
@@ -5,11 +5,6 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
-                    "fastqc": {
-                        "branch": "master",
-                        "git_sha": "dc94b6ee04a05ddb9f7ae050712ff30a13149164",
-                        "installed_by": ["modules"]
-                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",

diff --git a/modules/nf-core/fastqc/environment.yml b/modules/nf-core/fastqc/environment.yml
diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf
diff --git a/modules/nf-core/fastqc/meta.yml b/modules/nf-core/fastqc/meta.yml
diff --git a/modules/nf-core/fastqc/tests/main.nf.test b/modules/nf-core/fastqc/tests/main.nf.test
diff --git a/modules/nf-core/fastqc/tests/main.nf.test.snap b/modules/nf-core/fastqc/tests/main.nf.test.snap
diff --git a/modules/nf-core/fastqc/tests/tags.yml b/modules/nf-core/fastqc/tests/tags.yml
diff --git a/nextflow.config b/nextflow.config
@@ -13,11 +13,6 @@ params {
     // Input options
     input                      = null
 
-    // References
-    genome                     = null
-    igenomes_base              = 's3://ngi-igenomes/igenomes/'
-    igenomes_ignore            = false
-
     // MultiQC options
     multiqc_config             = null
     multiqc_title              = null
@@ -180,8 +175,7 @@ podman.registry       = 'quay.io'
 singularity.registry  = 'quay.io'
 charliecloud.registry = 'quay.io'
 
-// Load igenomes.config if required
-includeConfig !params.igenomes_ignore ? 'conf/igenomes.config' : 'conf/igenomes_ignored.config'
+
 
 // Export these variables to prevent local Python/R libraries from conflicting with those in the container
 // The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
@@ -257,7 +251,7 @@ manifest {
 
 // Nextflow plugins
 plugins {
-    id 'nf-schema@2.1.1' // Validation of pipeline parameters and creation of an input channel from a sample sheet
+    id 'nf-schema@2.3.0' // Validation of pipeline parameters and creation of an input channel from a sample sheet
 }
 
 validation {

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -43,45 +43,6 @@
                 }
             }
         },
-        "reference_genome_options": {
-            "title": "Reference genome options",
-            "type": "object",
-            "fa_icon": "fas fa-dna",
-            "description": "Reference genome related files and options required for the workflow.",
-            "properties": {
-                "genome": {
-                    "type": "string",
-                    "description": "Name of iGenomes reference.",
-                    "fa_icon": "fas fa-book",
-                    "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
-                },
-                "fasta": {
-                    "type": "string",
-                    "format": "file-path",
-                    "exists": true,
-                    "mimetype": "text/plain",
-                    "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
-                    "description": "Path to FASTA genome file.",
-                    "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
-                    "fa_icon": "far fa-file-code"
-                },
-                "igenomes_ignore": {
-                    "type": "boolean",
-                    "description": "Do not load the iGenomes reference config.",
-                    "fa_icon": "fas fa-ban",
-                    "hidden": true,
-                    "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
-                },
-                "igenomes_base": {
-                    "type": "string",
-                    "format": "directory-path",
-                    "description": "The base path to the igenomes reference files",
-                    "fa_icon": "fas fa-ban",
-                    "hidden": true,
-                    "default": "s3://ngi-igenomes/igenomes/"
-                }
-            }
-        },
         "institutional_config_options": {
             "title": "Institutional config options",
             "type": "object",
@@ -232,9 +193,6 @@
         {
             "$ref": "#/$defs/input_output_options"
         },
-        {
-            "$ref": "#/$defs/reference_genome_options"
-        },
         {
             "$ref": "#/$defs/institutional_config_options"
         },

diff --git a/ro-crate-metadata.json b/ro-crate-metadata.json
diff --git a/subworkflows/local/utils_nfcore_pangenome_pipeline/main.nf b/subworkflows/local/utils_nfcore_pangenome_pipeline/main.nf
@@ -63,11 +63,6 @@ workflow PIPELINE_INITIALISATION {
         nextflow_cli_args
     )
 
-    //
-    // Custom validation for pipeline parameters
-    //
-    validateInputParameters()
-
     //
     // Create channel from input file provided through params.input
     //
@@ -150,12 +145,6 @@ workflow PIPELINE_COMPLETION {
     FUNCTIONS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
-//
-// Check and validate pipeline parameters
-//
-def validateInputParameters() {
-    genomeExistsError()
-}
 
 //
 // Validate channels from input samplesheet
@@ -172,31 +161,6 @@ def validateInputSamplesheet(input) {
     return [ metas[0], fastqs ]
 }
 //
-// Get attribute from genome config file e.g. fasta
-//
-def getGenomeAttribute(attribute) {
-    if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) {
-        if (params.genomes[ params.genome ].containsKey(attribute)) {
-            return params.genomes[ params.genome ][ attribute ]
-        }
-    }
-    return null
-}
-
-//
-// Exit pipeline if incorrect --genome key provided
-//
-def genomeExistsError() {
-    if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
-        def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
-            "  Genome '${params.genome}' not found in any config files provided to the pipeline.\n" +
-            "  Currently, the available genome keys are:\n" +
-            "  ${params.genomes.keySet().join(", ")}\n" +
-            "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
-        error(error_string)
-    }
-}
-//
 // Generate methods description for MultiQC
 //
 def toolCitationText() {
@@ -205,7 +169,6 @@ def toolCitationText() {
     // Uncomment function in methodsDescriptionText to render in MultiQC report
     def citation_text = [
             "Tools used in the workflow included:",
-            "FastQC (Andrews 2010),",
             "MultiQC (Ewels et al. 2016)",
             "."
         ].join(' ').trim()
@@ -218,7 +181,6 @@ def toolBibliographyText() {
     // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "<li>Author (2023) Pub name, Journal, DOI</li>" : "",
     // Uncomment function in methodsDescriptionText to render in MultiQC report
     def reference_text = [
-            "<li>Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).</li>",
             "<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>"
         ].join(' ').trim()
 

diff --git a/workflows/pangenome.nf b/workflows/pangenome.nf
@@ -3,7 +3,6 @@
     IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
-include { FASTQC                 } from '../modules/nf-core/fastqc/main'
 include { MULTIQC                } from '../modules/nf-core/multiqc/main'
 include { paramsSummaryMap       } from 'plugin/nf-schema'
 include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pipeline'
@@ -24,14 +23,6 @@ workflow PANGENOME {
 
     ch_versions = Channel.empty()
     ch_multiqc_files = Channel.empty()
-    //
-    // MODULE: Run FastQC
-    //
-    FASTQC (
-        ch_samplesheet
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
     //
     // Collate and save software versions