Add parameter typing

.github/workflows/nf-test.yml

@@ -18,7 +18,7 @@ concurrency:
 
 env:
   GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-  NFT_VER: "0.9.3"
+  NFT_VER: "0.9.5"
   NFT_WORKDIR: "~"
   NXF_ANSI_LOG: false
   NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity
@@ -76,7 +76,7 @@ jobs:
           - isMain: false
             profile: "singularity"
         NXF_VER:
-          - 25.10.0
+          - 26.04.0
           - latest-everything
     env:
       NXF_ANSI_LOG: false

.gitignore

@@ -9,3 +9,6 @@ testing*
 null/
 .nf-test*
 test_fc
+# pixi environments
+.pixi/*
+!.pixi/config.toml

.nf-core.yml

@@ -21,6 +21,7 @@ lint:
     - bin/cmgg_genelists
   multiqc_config: false
   nextflow_config: false
+  schema_params: false # TMP
   template_strings:
     - bin/cmgg_genelists
   nf_test_content: false

.vscode/settings.json

@@ -1,3 +1,4 @@
 {
-    "markdown.styles": ["public/vscode_markdown.css"]
+    "markdown.styles": ["public/vscode_markdown.css"],
+    "nextflow.telemetry.enabled": false
 }

CHANGELOG.md

@@ -5,6 +5,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## 3.0.1dev
 
+- Add parameter typing to make strict syntax runs work more properly
+- Bumped minimal Nextflow version to 26.04.0 to allow for strict syntax and other improvements
 - Fix an issue with `mosdepth` environment variables not being correctly set on GCP
 - Bump `mosdepth` module to 0.3.14
 

README.md

@@ -5,7 +5,7 @@
 [![GitHub Actions Linting Status](https://github.com/nf-cmgg/preprocessing/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-cmgg/preprocessing/actions/workflows/linting.yml)[![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)
 
-[![Nextflow](https://img.shields.io/badge/version-%E2%89%A525.10.0-green?style=flat&logo=nextflow&logoColor=white&color=%230DC09D&link=https%3A%2F%2Fnextflow.io)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/version-%E2%89%A526.04.0-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-3.5.1-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 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/)
@@ -59,6 +59,16 @@ nextflow run nf-cmgg/preprocessing \
 > Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_;
 > see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
 
+## Development environment
+
+A [pixi](https://pixi.prefix.dev/latest/) development environment is available for this pipeline. Run the following command to install the environment:
+
+```
+pixi install
+```
+
+Then run `pixi shell` to enter the environment and start developing.
+
 ## Credits
 
 nf-cmgg/preprocessing was originally written by the CMGG ICT team.

conf/igenomes.config

@@ -8,98 +8,96 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    genomes {
-        GRCh38 {
-            // Genome reference
-            fai       = "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_plus_hs38d1_analysis_set.fna.fai"
-            fasta     = "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_plus_hs38d1_analysis_set.fna"
-            dict      = "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_plus_hs38d1_analysis_set.dict"
-            gtf       = "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_analysis_set.refseq_annotation.gtf"
+params.genomes = [
+    GRCh38: [
+        // Genome reference
+        fai       : "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_plus_hs38d1_analysis_set.fna.fai",
+        fasta     : "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_plus_hs38d1_analysis_set.fna",
+        dict      : "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_plus_hs38d1_analysis_set.dict",
+        gtf       : "${params.igenomes_base}/Hsapiens/GRCh38/seq/GCA_000001405.15_GRCh38_full_analysis_set.refseq_annotation.gtf",
 
-            // Aligner reference
-            bowtie2   = "${params.igenomes_base}/Hsapiens/GRCh38/bowtie2"
-            bwamem    = "${params.igenomes_base}/Hsapiens/GRCh38/bwa"
-            bwamem2   = "${params.igenomes_base}/Hsapiens/GRCh38/bwamem2"
-            dragmap   = "${params.igenomes_base}/Hsapiens/GRCh38/dragmap"
-            snap      = "${params.igenomes_base}/Hsapiens/GRCh38/snapaligner"
-            star      = "${params.igenomes_base}/Hsapiens/GRCh38/star"
+        // Aligner reference
+        bowtie2   : "${params.igenomes_base}/Hsapiens/GRCh38/bowtie2",
+        bwamem    : "${params.igenomes_base}/Hsapiens/GRCh38/bwa",
+        bwamem2   : "${params.igenomes_base}/Hsapiens/GRCh38/bwamem2",
+        dragmap   : "${params.igenomes_base}/Hsapiens/GRCh38/dragmap",
+        snap      : "${params.igenomes_base}/Hsapiens/GRCh38/snapaligner",
+        star      : "${params.igenomes_base}/Hsapiens/GRCh38/star",
 
-            // ROI's
-            roi_copgt = "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_coPGT-M_analyses_ROI_v1.bed"
-            roi_wes   = "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_WES_analysis_ROI_v7.bed"
-        }
-        GRCm39 {
-            // Genome reference
-            fai     = "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.fna.fai"
-            fasta   = "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.fna"
-            dict    = "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.dict"
-            gtf     = "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.gtf"
+        // ROI's
+        roi_copgt : "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_coPGT-M_analyses_ROI_v1.bed",
+        roi_wes   : "${params.igenomes_base}/Hsapiens/GRCh38/regions/CMGG_WES_analysis_ROI_v7.bed",
+    ],
+    GRCm39: [
+        // Genome reference
+        fai     : "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.fna.fai",
+        fasta   : "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.fna",
+        dict    : "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.dict",
+        gtf     : "${params.igenomes_base}/Mmusculus/GRCm39/seq/GCF_000001635.27_GRCm39_genomic.gtf",
 
-            // Aligner reference
-            bowtie2 = "${params.igenomes_base}/Mmusculus/GRCm39/bowtie2"
-            bwamem  = "${params.igenomes_base}/Mmusculus/GRCm39/bwa"
-            bwamem2 = "${params.igenomes_base}/Mmusculus/GRCm39/bwamem2"
-            dragmap = "${params.igenomes_base}/Mmusculus/GRCm39/dragmap"
-            snap    = "${params.igenomes_base}/Mmusculus/GRCm39/snapaligner"
-            star    = "${params.igenomes_base}/Mmusculus/GRCm39/star"
-        }
-        mm10 {
-            // Genome reference
-            fai     = "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.fa.fai"
-            fasta   = "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.fa"
-            dict    = "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.dict"
-            gtf     = "${params.igenomes_base}/Mmusculus/mm10/seq/Mus_musculus.GRCm38.102.chr.gtf"
+        // Aligner reference
+        bowtie2 : "${params.igenomes_base}/Mmusculus/GRCm39/bowtie2",
+        bwamem  : "${params.igenomes_base}/Mmusculus/GRCm39/bwa",
+        bwamem2 : "${params.igenomes_base}/Mmusculus/GRCm39/bwamem2",
+        dragmap : "${params.igenomes_base}/Mmusculus/GRCm39/dragmap",
+        snap    : "${params.igenomes_base}/Mmusculus/GRCm39/snapaligner",
+        star    : "${params.igenomes_base}/Mmusculus/GRCm39/star",
+    ],
+    mm10: [
+        // Genome reference
+        fai     : "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.fa.fai",
+        fasta   : "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.fa",
+        dict    : "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.dict",
+        gtf     : "${params.igenomes_base}/Mmusculus/mm10/seq/Mus_musculus.GRCm38.102.chr.gtf",
 
-            // Aligner reference
-            bowtie2 = "${params.igenomes_base}/Mmusculus/mm10/bowtie2"
-            bwamem  = "${params.igenomes_base}/Mmusculus/mm10/bwa"
-            bwamem2 = "${params.igenomes_base}/Mmusculus/mm10/bwamem2"
-            dragmap = "${params.igenomes_base}/Mmusculus/mm10/dragmap"
-            snap    = "${params.igenomes_base}/Mmusculus/mm10/snapaligner"
-            star    = "${params.igenomes_base}/Mmusculus/mm10/star"
-        }
-        GRCz11 {
-            // Genome reference
-            fai     = "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.fna.fai"
-            fasta   = "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.fna"
-            dict    = "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.dict"
-            gtf     = "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.gtf"
+        // Aligner reference
+        bowtie2 : "${params.igenomes_base}/Mmusculus/mm10/bowtie2",
+        bwamem  : "${params.igenomes_base}/Mmusculus/mm10/bwa",
+        bwamem2 : "${params.igenomes_base}/Mmusculus/mm10/bwamem2",
+        dragmap : "${params.igenomes_base}/Mmusculus/mm10/dragmap",
+        snap    : "${params.igenomes_base}/Mmusculus/mm10/snapaligner",
+        star    : "${params.igenomes_base}/Mmusculus/mm10/star",
+    ],
+    GRCz11: [
+        // Genome reference
+        fai     : "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.fna.fai",
+        fasta   : "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.fna",
+        dict    : "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.dict",
+        gtf     : "${params.igenomes_base}/Drerio/GRCz11/seq/GCF_000002035.6_GRCz11_genomic.gtf",
 
-            // Aligner reference
-            bowtie2 = "${params.igenomes_base}/Drerio/GRCz11/bowtie2"
-            bwamem  = "${params.igenomes_base}/Drerio/GRCz11/bwa"
-            bwamem2 = "${params.igenomes_base}/Drerio/GRCz11/bwamem2"
-            dragmap = "${params.igenomes_base}/Drerio/GRCz11/dragmap"
-            snap    = "${params.igenomes_base}/Drerio/GRCz11/snapaligner"
-            star    = "${params.igenomes_base}/Drerio/GRCz11/star"
-        }
-        // Legacy bcbio references
-        hg38 {
-            fai     = "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.fa.fai"
-            fasta   = "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.fa"
-            dict    = "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.dict"
-            gtf     = "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.gtf"
+        // Aligner reference
+        bowtie2 : "${params.igenomes_base}/Drerio/GRCz11/bowtie2",
+        bwamem  : "${params.igenomes_base}/Drerio/GRCz11/bwa",
+        bwamem2 : "${params.igenomes_base}/Drerio/GRCz11/bwamem2",
+        dragmap : "${params.igenomes_base}/Drerio/GRCz11/dragmap",
+        snap    : "${params.igenomes_base}/Drerio/GRCz11/snapaligner",
+        star    : "${params.igenomes_base}/Drerio/GRCz11/star",
+    ],
+    // Legacy bcbio references
+    hg38: [
+        fai     : "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.fa.fai",
+        fasta   : "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.fa",
+        dict    : "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.dict",
+        gtf     : "${params.igenomes_base}/Hsapiens/hg38/seq/hg38.gtf",
 
-            bowtie2 = "${params.igenomes_base}/Hsapiens/hg38/bowtie2"
-            bwamem  = "${params.igenomes_base}/Hsapiens/hg38/bwa"
-            bwamem2 = "${params.igenomes_base}/Hsapiens/hg38/bwamem2"
-            dragmap = "${params.igenomes_base}/Hsapiens/hg38/dragmap"
-            snap    = "${params.igenomes_base}/Hsapiens/hg38/snapaligner"
-            star    = "${params.igenomes_base}/Hsapiens/hg38/star"
-        }
-        'hg38-noalt' {
-            fai     = "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.fa.fai"
-            fasta   = "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.fa"
-            dict    = "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.dict"
-            gtf     = "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.gtf"
+        bowtie2 : "${params.igenomes_base}/Hsapiens/hg38/bowtie2",
+        bwamem  : "${params.igenomes_base}/Hsapiens/hg38/bwa",
+        bwamem2 : "${params.igenomes_base}/Hsapiens/hg38/bwamem2",
+        dragmap : "${params.igenomes_base}/Hsapiens/hg38/dragmap",
+        snap    : "${params.igenomes_base}/Hsapiens/hg38/snapaligner",
+        star    : "${params.igenomes_base}/Hsapiens/hg38/star",
+    ],
+    'hg38-noalt': [
+        fai     : "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.fa.fai",
+        fasta   : "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.fa",
+        dict    : "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.dict",
+        gtf     : "${params.igenomes_base}/Hsapiens/hg38-noalt/seq/hg38-noalt.gtf",
 
-            bowtie2 = "${params.igenomes_base}/Hsapiens/hg38-noalt/bowtie2"
-            bwamem  = "${params.igenomes_base}/Hsapiens/hg38-noalt/bwa"
-            bwamem2 = "${params.igenomes_base}/Hsapiens/hg38-noalt/bwamem2"
-            dragmap = "${params.igenomes_base}/Hsapiens/hg38-noalt/dragmap"
-            snap    = "${params.igenomes_base}/Hsapiens/hg38-noalt/snapaligner"
-            star    = "${params.igenomes_base}/Hsapiens/hg38-noalt/star"
-        }
-    }
-}
+        bowtie2 : "${params.igenomes_base}/Hsapiens/hg38-noalt/bowtie2",
+        bwamem  : "${params.igenomes_base}/Hsapiens/hg38-noalt/bwa",
+        bwamem2 : "${params.igenomes_base}/Hsapiens/hg38-noalt/bwamem2",
+        dragmap : "${params.igenomes_base}/Hsapiens/hg38-noalt/dragmap",
+        snap    : "${params.igenomes_base}/Hsapiens/hg38-noalt/snapaligner",
+        star    : "${params.igenomes_base}/Hsapiens/hg38-noalt/star",
+    ],
+]

main.nf

@@ -22,6 +22,104 @@ include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_prep
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
+params {
+
+    // Path to comma-separated or yaml file containing information about the samples in the experiment.
+    input: Path
+
+    // The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.
+    outdir: Path
+
+    // Email address for completion summary.
+    email: String?
+
+    // MultiQC report title. Printed as page header, used for filename if not otherwise specified.
+    multiqc_title: String?
+
+    genomes: Map = [:]
+
+    // Specify how many reads each split of a FastQ file contains. Set 0 to turn off splitting at all.
+    split_fastq: Integer = 100000000
+
+    // Directory containing gene list bed files for granular coverage analysis
+    genelists: Path?
+
+    // Git commit id for Institutional configs.
+    custom_config_version: String = 'main'
+
+    // Base directory for custom configs.
+    custom_config_base: String = 'https://raw.githubusercontent.com/nf-cmgg/configs/main'
+
+    // Institutional config name.
+    config_profile_name: String?
+
+    // Institutional config description.
+    config_profile_description: String?
+
+    // Institutional config contact information.
+    config_profile_contact: String?
+
+    // Institutional config URL link.
+    config_profile_url: String?
+
+    // Display version and exit.
+    version: Boolean = false
+
+    // Method used to save pipeline results to output directory.
+    publish_dir_mode: String = 'copy'
+
+    // Email address for completion summary, only when pipeline fails.
+    email_on_fail: String?
+
+    // Send plain-text email instead of HTML.
+    plaintext_email: Boolean = false
+
+    // File size limit when attaching MultiQC reports to summary emails.
+    max_multiqc_email_size: String = '25.MB'
+
+    // Do not use coloured log outputs.
+    monochrome_logs: Boolean = false
+
+    // Incoming hook URL for messaging service
+    hook_url: String?
+
+    // Custom config file to supply to MultiQC.
+    multiqc_config: Path?
+
+    // Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file
+    multiqc_logo: Path?
+
+    // Custom MultiQC yaml file containing HTML including a methods description.
+    multiqc_methods_description: Path?
+
+    // Boolean whether to validate parameters against the schema at runtime
+    validate_params: Boolean = true
+
+    // Base URL or local path to location of pipeline test dataset files
+    pipelines_testdata_base_path: String = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
+
+    // Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.
+    trace_report_suffix: String
+
+    // Display the help message.
+    help = false
+
+    // Display the full detailed help message.
+    help_full: Boolean = false
+
+    // Display hidden parameters in the help message (only works when --help or --help_full are provided).
+    show_hidden: Boolean = false
+
+    // Directory / URL base for iGenomes references.
+    igenomes_base: String = '/references/'
+
+    // Do not load the iGenomes reference config.
+    igenomes_ignore: Boolean = false
+
+    // Name of iGenomes reference.
+    genome: String?
+}
+
 workflow {
 
     main:
@@ -47,10 +145,11 @@ workflow {
         params.genomes,
         params.genelists,
         params.multiqc_config
-            ? [file("${projectDir}/assets/multiqc_config.yml", checkIfExists: true), file(params.multiqc_config, checkIfExists: true)]
+            ? [file("${projectDir}/assets/multiqc_config.yml", checkIfExists: true), params.multiqc_config]
             : [file("${projectDir}/assets/multiqc_config.yml", checkIfExists: true)],
-        params.multiqc_logo ? file(params.multiqc_logo, checkIfExists: true) : [],
-        params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("${projectDir}/assets/methods_description_template.yml", checkIfExists: true),
+        params.multiqc_logo ? params.multiqc_logo : [],
+        params.multiqc_methods_description ? params.multiqc_methods_description : file("${projectDir}/assets/methods_description_template.yml", checkIfExists: true),
+        params.outdir
     )
 
     //
@@ -70,8 +169,8 @@ workflow {
     demultiplex_logs           = PREPROCESSING.out.demultiplex_logs.transpose()
     demultiplex_fastq          = PREPROCESSING.out.demultiplex_fastq.transpose()
     demultiplex_interop        = PREPROCESSING.out.demultiplex_interop.transpose(by: 1)
-    falco_html                 = PREPROCESSING.out.falco_html
-    falco_txt                  = PREPROCESSING.out.falco_txt
+    falco_html                 = PREPROCESSING.out.falco_html.transpose()
+    falco_txt                  = PREPROCESSING.out.falco_txt.transpose()
     fastp_json                 = PREPROCESSING.out.fastp_json
     fastp_html                 = PREPROCESSING.out.fastp_html
     crams                      = PREPROCESSING.out.crams