Default registry to quay.io (#3344)

* Add default registry for Docker and Podman to quay.io Will break any non quay.io containers that were not specified with a full URI * Use full URI for all modules * More docker.io added to container specs * More docker.io * Correct docker container for VEP * Artifacts named after specific run Changes: - Name the upload after the specific tool that was analysed using the tag value - Reduces download size of artifacts when investigating failures * Update universc image name to use nfcore/universc instead of biocontainers/universc * Revert snpeff docker container to nfcore/snpeff * Update cellranger/count md5sum tests * Remove eido md5sum because it doesn't work on conda * Fix eido version string * correct md5sums * Omit gatk4 conda tools that don't work * Remove slashes from tags for uploading artifacts * bb22faef28dfb0b3b106bd5cc320bf09 * Correct string parsing for artifact upload * Remove singularity gatk4/determinegermlinecontigploidy test because it just breaks the VM after too long * fix-meta-liniting --------- Co-authored-by: Sateesh Peri <perisateesh@gmail.com>
nf-core · May 2, 2023 · b9829e1 · b9829e1
1 parent c7ddd48
commit b9829e1
Show file tree

Hide file tree

Showing 73 changed files with 120 additions and 80 deletions.
diff --git a/.github/workflows/pytest-workflow.yml b/.github/workflows/pytest-workflow.yml
@@ -86,10 +86,18 @@ jobs:
             tags: fcs/fcsadaptor
           - profile: "conda"
             tags: fcs/fcsgx
+          - profile: "conda"
+            tags: gatk4/baserecalibratorspark
           - profile: "conda"
             tags: gatk4/cnnscorevariants
           - profile: "conda"
             tags: gatk4/determinegermlinecontigploidy
+          - profile: "conda"
+            tags: gatk4/germlinecnvcaller
+          - profile: "conda"
+            tags: gatk4/markduplicatesspark
+          - profile: "conda"
+            tags: gatk4/postprocessgermlinecnvcalls
           - profile: "conda"
             tags: genescopefk
           - profile: "conda"
@@ -122,6 +130,8 @@ jobs:
             tags: universc
           - profile: "singularity"
             tags: universc
+          - profile: "singularity"
+            tags: gatk4/determinegermlinecontigploidy
           - profile: "conda"
             tags: subworkflows/bcl_demultiplex
           - profile: "conda"
@@ -207,11 +217,19 @@ jobs:
           sudo apt-get install bat > /dev/null
           batcat --decorations=always --color=always /home/runner/pytest_workflow_*/*/log.{out,err}
 
+      - name: Setting global variables
+        uses: actions/github-script@v6
+        id: parsed
+        with:
+          script: |
+            return '${{ matrix.tags }}'.toLowerCase().replaceAll(/\//g, '-').trim('-').trim('"')
+          result-encoding: string
+
       - name: Upload logs on failure
         if: failure()
         uses: actions/upload-artifact@v2
         with:
-          name: logs-${{ matrix.profile }}
+          name: logs-${{ matrix.profile }}-${{ steps.parsed.outputs.result }}
           path: |
             /home/runner/pytest_workflow_*/*/.nextflow.log
             /home/runner/pytest_workflow_*/*/log.out

diff --git a/modules/nf-core/bases2fastq/main.nf b/modules/nf-core/bases2fastq/main.nf
@@ -2,7 +2,7 @@ process BASES2FASTQ {
     tag "$meta.id"
     label 'process_high'
 
-    container "elembio/bases2fastq:1.1.0"
+    container "docker.io/elembio/bases2fastq:1.1.0"
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

diff --git a/modules/nf-core/basicpy/main.nf b/modules/nf-core/basicpy/main.nf
@@ -7,7 +7,7 @@ process BASICPY {
         exit 1, "Basicpy module does not support Conda. Please use Docker / Singularity instead."
     }
 
-    container "yfukai/basicpy-docker-mcmicro:0.2.1"
+    container "docker.io/yfukai/basicpy-docker-mcmicro:0.2.1"
 
     input:
     tuple val(meta), path(image)

diff --git a/modules/nf-core/basicpy/meta.yml b/modules/nf-core/basicpy/meta.yml
@@ -11,7 +11,7 @@ tools:
       homepage: "https://github.com/peng-lab/BaSiCPy"
       documentation: "https://basicpy.readthedocs.io/en/latest/index.html"
       tool_dev_url: "https://github.com/peng-lab/BaSiCPy"
-      doi: "doi: 10.1038/ncomms14836."
+      doi: 10.1038/ncomms14836
       licence: "MIT License"
 
 input:

diff --git a/modules/nf-core/bcl2fastq/main.nf b/modules/nf-core/bcl2fastq/main.nf
@@ -2,7 +2,7 @@ process BCL2FASTQ {
     tag {"$meta.lane" ? "$meta.id"+"."+"$meta.lane" : "$meta.id" }
     label 'process_high'
 
-    container "nfcore/bcl2fastq:2.20.0.422"
+    container "docker.io/nfcore/bcl2fastq:2.20.0.422"
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

diff --git a/modules/nf-core/bclconvert/main.nf b/modules/nf-core/bclconvert/main.nf
@@ -2,7 +2,7 @@ process BCLCONVERT {
     tag {"$meta.lane" ? "$meta.id"+"."+"$meta.lane" : "$meta.id" }
     label 'process_high'
 
-    container "nfcore/bclconvert:4.0.3"
+    container "docker.io/nfcore/bclconvert:4.0.3"
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

diff --git a/modules/nf-core/cat/fastq/main.nf b/modules/nf-core/cat/fastq/main.nf
@@ -5,7 +5,7 @@ process CAT_FASTQ {
     conda "conda-forge::sed=4.7"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'ubuntu:20.04' }"
+        'docker.io/ubuntu:20.04' }"
 
     input:
     tuple val(meta), path(reads, stageAs: "input*/*")

diff --git a/modules/nf-core/cat/fastq/meta.yml b/modules/nf-core/cat/fastq/meta.yml
@@ -1,6 +1,7 @@
 name: cat_fastq
 description: Concatenates fastq files
 keywords:
+  - cat
   - fastq
   - concatenate
 tools:
@@ -16,7 +17,7 @@ input:
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
   - reads:
-      type: list
+      type: file
       description: |
         List of input FastQ files to be concatenated.
 output:

diff --git a/modules/nf-core/cellpose/main.nf b/modules/nf-core/cellpose/main.nf
@@ -6,7 +6,7 @@ process CELLPOSE {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         exit 1, "I did not manage to create a cellpose module in Conda that works in all OSes. Please use Docker / Singularity / Podman instead."}
 
-    container "biocontainers/cellpose:2.1.1_cv2"
+    container "docker.io/biocontainers/cellpose:2.1.1_cv2"
 
     input:
     tuple val(meta), path(image)

diff --git a/modules/nf-core/cellpose/meta.yml b/modules/nf-core/cellpose/meta.yml
@@ -2,13 +2,15 @@ name: "cellpose"
 description: cellpose segments cells in images
 keywords:
   - segmentation
+  - image
+  - cellpose
 tools:
   - "cellpose":
       description: "cellpose is an anatomical segmentation algorithm written in Python 3 by Carsen Stringer and Marius Pachitariu"
       homepage: "https://github.com/MouseLand/cellpose"
       documentation: "https://cellpose.readthedocs.io/en/latest/command.html"
       tool_dev_url: "https://github.com/MouseLand/cellpose"
-      doi: "https://doi.org/10.1038/s41592-022-01663-4"
+      doi: 10.1038/s41592-022-01663-4
       licence: "BSD 3-Clause"
 
 input:
@@ -18,7 +20,7 @@ input:
         Groovy Map containing sample information
         (sample id)
   - image:
-      type: image stack
+      type: file
       description: tif file for ready for segmentation
       pattern: "*.{tif,tiff}"
   - model:
@@ -36,7 +38,7 @@ output:
       description: File containing software versions
       pattern: "versions.yml"
   - mask:
-      type: tif_file
+      type: file
       description: labelled mask output from cellpose in tif format
       pattern: "*.{tif, tiff}"
 

diff --git a/modules/nf-core/coreograph/main.nf b/modules/nf-core/coreograph/main.nf
@@ -2,7 +2,7 @@ process COREOGRAPH {
     tag "$meta.id"
     label 'process_single'
 
-    container "labsyspharm/unetcoreograph:2.2.9"
+    container "docker.io/labsyspharm/unetcoreograph:2.2.9"
 
     input:
     tuple val(meta), path(image)

diff --git a/modules/nf-core/coreograph/meta.yml b/modules/nf-core/coreograph/meta.yml
@@ -11,7 +11,7 @@ tools:
       homepage: "https://mcmicro.org/parameters/core.html#coreograph"
       documentation: "https://mcmicro.org/troubleshooting/tuning/coreograph.html"
       tool_dev_url: "https://github.com/HMS-IDAC/UNetCoreograph"
-      doi: "https://doi.org/10.1038/s41592-021-01308-y"
+      doi: 10.1038/s41592-021-01308-y
       licence: "MIT License"
 
 input:
@@ -38,7 +38,7 @@ output:
       pattern: "*.{tif}"
 
   - masks:
-      type: files
+      type: file
       description: Binary masks for the Complete/Incomplete tissue cores
       pattern: "./masks/*.{tif}"
 

diff --git a/modules/nf-core/custom/tabulartogseacls/main.nf b/modules/nf-core/custom/tabulartogseacls/main.nf
@@ -5,7 +5,7 @@ process CUSTOM_TABULARTOGSEACLS {
     conda "conda-forge::coreutils=9.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'ubuntu:20.04' }"
+        'docker.io/ubuntu:20.04' }"
 
     input:
     tuple val(meta), path(samples)

diff --git a/modules/nf-core/custom/tabulartogseagct/main.nf b/modules/nf-core/custom/tabulartogseagct/main.nf
@@ -5,7 +5,7 @@ process CUSTOM_TABULARTOGSEAGCT {
     conda "conda-forge::coreutils=9.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
-        'ubuntu:20.04' }"
+        'docker.io/ubuntu:20.04' }"
 
     input:
     tuple val(meta), path(tabular)

diff --git a/modules/nf-core/custom/tabulartogseagct/meta.yml b/modules/nf-core/custom/tabulartogseagct/meta.yml
@@ -3,6 +3,7 @@ description: Convert a TSV or CSV with features by row and observations by colum
 keywords:
   - gsea
   - gct
+  - tabular
 tools:
   - tabulartogseagct:
       description: "Convert a TSV or CSV with features by row and observations by column to a GCT format file as consumed by GSEA"

diff --git a/modules/nf-core/deepcell/mesmer/main.nf b/modules/nf-core/deepcell/mesmer/main.nf
@@ -2,7 +2,7 @@ process DEEPCELL_MESMER {
     tag "$meta.id"
     label 'process_single'
 
-    container "vanvalenlab/deepcell-applications:0.4.1"
+    container "docker.io/vanvalenlab/deepcell-applications:0.4.1"
 
     input:
     tuple val(meta) , path(img)

diff --git a/modules/nf-core/deepcell/mesmer/meta.yml b/modules/nf-core/deepcell/mesmer/meta.yml
@@ -10,7 +10,7 @@ tools:
       homepage: "https://github.com/vanvalenlab/deepcell-tf"
       documentation: "https://github.com/vanvalenlab/intro-to-deepcell/tree/master/pretrained_models"
       tool_dev_url: "https://githu/b.com/vanvalenlab/deepcell-tf"
-      doi: "https://doi.org/10.1038/s41587-021-01094-0"
+      doi: 10.1038/s41587-021-01094-0
       licence: "APACHE2"
 
 input:

diff --git a/modules/nf-core/deepvariant/main.nf b/modules/nf-core/deepvariant/main.nf
@@ -2,7 +2,7 @@ process DEEPVARIANT {
     tag "$meta.id"
     label 'process_medium'
 
-    container "google/deepvariant:1.4.0"
+    container "docker.io/google/deepvariant:1.4.0"
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

diff --git a/modules/nf-core/deepvariant/meta.yml b/modules/nf-core/deepvariant/meta.yml
@@ -3,6 +3,7 @@ description: DeepVariant is an analysis pipeline that uses a deep neural network
 keywords:
   - variant calling
   - machine learning
+  - neural network
 tools:
   - deepvariant:
       description: DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data

diff --git a/modules/nf-core/eido/convert/main.nf b/modules/nf-core/eido/convert/main.nf
@@ -5,7 +5,7 @@ process EIDO_CONVERT {
     conda "conda-forge::eido=0.1.9"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://containers.biocontainers.pro/s3/SingImgsRepo/eido/0.1.9_cv1/eido_0.1.9_cv1.sif' :
-        'biocontainers/eido:0.1.9_cv1' }"
+        'docker.io/biocontainers/eido:0.1.9_cv1' }"
 
     input:
     path samplesheet
@@ -32,7 +32,7 @@ process EIDO_CONVERT {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        eido: \$(echo \$(eido --version 2>&1) | sed 's/^.*eido //;s/ .*//' ))
+        eido: \$(echo \$(eido --version 2>&1) | sed 's/^.*eido //;s/ .*//' )
     END_VERSIONS
     """
 }
diff --git a/modules/nf-core/eido/convert/meta.yml b/modules/nf-core/eido/convert/meta.yml
@@ -20,7 +20,7 @@ input:
       description: Nextflow samplesheet or PEP project
       pattern: "*.{yaml,yml,csv}"
   - format:
-      type: value
+      type: string
       description: Extension of an output file
   - pep_input_base_dir:
       type: file

diff --git a/modules/nf-core/eido/validate/main.nf b/modules/nf-core/eido/validate/main.nf
@@ -5,7 +5,7 @@ process EIDO_VALIDATE {
     conda "conda-forge::eido=0.1.9"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://containers.biocontainers.pro/s3/SingImgsRepo/eido/0.1.9_cv2/eido_0.1.9_cv2.sif' :
-        'biocontainers/eido:0.1.9_cv2' }"
+        'docker.io/biocontainers/eido:0.1.9_cv2' }"
 
     input:
     path samplesheet
@@ -27,7 +27,7 @@ process EIDO_VALIDATE {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        eido: \$(echo \$(eido --version 2>&1) | sed 's/^.*eido //;s/ .*//' ))
+        eido: \$(echo \$(eido --version 2>&1) | sed 's/^.*eido //;s/ .*//' )
     END_VERSIONS
     """
 }
diff --git a/modules/nf-core/fqtk/meta.yml b/modules/nf-core/fqtk/meta.yml
@@ -3,12 +3,12 @@ description: Demultiplex fastq files
 keywords:
   - demultiplex
   - fastq
+  - rust
 tools:
   - "fqtk":
       description: "A toolkit for working with FASTQ files, written in Rust."
       homepage: "https://github.com/fulcrumgenomics/fqtk"
       documentation: "https://github.com/fulcrumgenomics/fqtk"
-      tool_dev_url: "None"
       licence: "['MIT']"
 
 input:
@@ -22,7 +22,7 @@ input:
       description: Tsv file, with two columns sample_id and barcode
       pattern: "*.{tsv}"
   - fastq_readstructure_pairs:
-      type: list
+      type: map
       description: List of lists i.e. [[<fastq file name>, <read structure>, <absolute path to fastq directory>],...]
 
 output:

diff --git a/modules/nf-core/gatk4/applybqsrspark/main.nf b/modules/nf-core/gatk4/applybqsrspark/main.nf
@@ -3,7 +3,7 @@ process GATK4_APPLYBQSR_SPARK {
     label 'process_low'
 
     conda "bioconda::gatk4=4.3.0.0 conda-forge::openjdk=8.0.312"
-    container 'broadinstitute/gatk:4.4.0.0'
+    container 'docker.io/broadinstitute/gatk:4.4.0.0'
 
     input:
     tuple val(meta), path(input), path(input_index), path(bqsr_table), path(intervals)

diff --git a/modules/nf-core/gatk4/applybqsrspark/meta.yml b/modules/nf-core/gatk4/applybqsrspark/meta.yml
@@ -3,6 +3,7 @@ description: Apply base quality score recalibration (BQSR) to a bam file
 keywords:
   - bqsr
   - bam
+  - gatk
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/baserecalibratorspark/main.nf b/modules/nf-core/gatk4/baserecalibratorspark/main.nf
@@ -3,7 +3,7 @@ process GATK4_BASERECALIBRATOR_SPARK {
     label 'process_low'
 
     conda "bioconda::gatk4=4.4.0.0 conda-forge::openjdk=8.0.312"
-    container 'broadinstitute/gatk:4.4.0.0'
+    container 'docker.io/broadinstitute/gatk:4.4.0.0'
 
     input:
     tuple val(meta), path(input), path(input_index), path(intervals)

diff --git a/modules/nf-core/gatk4/baserecalibratorspark/meta.yml b/modules/nf-core/gatk4/baserecalibratorspark/meta.yml
@@ -2,6 +2,8 @@ name: gatk4_baserecalibrator_spark
 description: Generate recalibration table for Base Quality Score Recalibration (BQSR)
 keywords:
   - sort
+  - bqsr
+  - gatk
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/cnnscorevariants/main.nf b/modules/nf-core/gatk4/cnnscorevariants/main.nf
@@ -3,7 +3,7 @@ process GATK4_CNNSCOREVARIANTS {
     label 'process_low'
 
     //Conda is not supported at the moment: https://github.com/broadinstitute/gatk/issues/7811
-    container "broadinstitute/gatk:4.4.0.0" //Biocontainers is missing a package
+    container "docker.io/broadinstitute/gatk:4.4.0.0" //Biocontainers is missing a package
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

diff --git a/modules/nf-core/gatk4/determinegermlinecontigploidy/main.nf b/modules/nf-core/gatk4/determinegermlinecontigploidy/main.nf
@@ -3,7 +3,7 @@ process GATK4_DETERMINEGERMLINECONTIGPLOIDY {
     label 'process_single'
 
     //Conda is not supported at the moment: https://github.com/broadinstitute/gatk/issues/7811
-    container "broadinstitute/gatk:4.4.0.0" //Biocontainers is missing a package
+    container "docker.io/broadinstitute/gatk:4.4.0.0" //Biocontainers is missing a package
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {

diff --git a/modules/nf-core/gatk4/determinegermlinecontigploidy/meta.yml b/modules/nf-core/gatk4/determinegermlinecontigploidy/meta.yml
@@ -23,15 +23,15 @@ input:
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
   - counts:
-      type: file(s)
+      type: file
       description: One or more count TSV files created with gatk/collectreadcounts
       pattern: "*.tsv"
   - bed:
       type: file
       description: Optional - A bed file containing the intervals to include in the process
       pattern: "*.bed"
   - exclude_beds:
-      type: file(s)
+      type: file
       description: Optional - One or more bed files containing intervals to exclude from the process
       pattern: "*.bed"
   - contig_ploidy_table:

diff --git a/modules/nf-core/gatk4/germlinecnvcaller/main.nf b/modules/nf-core/gatk4/germlinecnvcaller/main.nf
@@ -3,7 +3,7 @@ process GATK4_GERMLINECNVCALLER {
     label 'process_single'
 
     //Conda is not supported at the moment: https://github.com/broadinstitute/gatk/issues/7811
-    container "broadinstitute/gatk:4.4.0.0" //Biocontainers is missing a package
+    container "docker.io/broadinstitute/gatk:4.4.0.0" //Biocontainers is missing a package
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-Original file line number
+Diff line change
@@ Expand Up @@
     keywords:
       - gsea
       - gct
+      - tabular
     tools:
       - tabulartogseagct:
           description: "Convert a TSV or CSV with features by row and observations by column to a GCT format file as consumed by GSEA"
@@ Expand Down @@