Merge branch 'master' of https://github.com/nf-core/modules

WackerO · Sep 25, 2023 · 5af05e3 · 5af05e3
2 parents ecf482f + 23ca653
commit 5af05e3
Show file tree

Hide file tree

Showing 181 changed files with 1,786 additions and 208 deletions.
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -100,10 +100,17 @@ jobs:
       - name: Setup Nextflow
         uses: nf-core/setup-nextflow@v1
 
-      - name: Lint ${{ matrix.tags }}
+      - name: Lint module ${{ matrix.tags }}
         run: nf-core modules lint ${{ matrix.tags }}
-        # HACK
-        if: startsWith( matrix.tags, 'subworkflow' ) != true
+        if: ${{ !startsWith(matrix.tags, 'subworkflow') }}
+
+      - name: Remove substring from matrix.tags
+        id: remove-substring
+        run: subworkflow_names=$(echo "${{ matrix.tags }}" | sed 's/subworkflows\///g')
+
+      - name: Lint subworkflow ${{ matrix.tags }}
+        run: nf-core subworkflows lint steps.set_tags.outputs.subworkflow_names
+        if: ${{ startsWith(matrix.tags, 'subworkflow') }}
 
   pytest:
     runs-on: ubuntu-20.04

diff --git a/modules/nf-core/bcl2fastq/main.nf b/modules/nf-core/bcl2fastq/main.nf
@@ -8,8 +8,8 @@ process BCL2FASTQ {
     tuple val(meta), path(samplesheet), path(run_dir)
 
     output:
-    tuple val(meta), path("**[!Undetermined]_S*_R?_00?.fastq.gz"), emit: fastq
-    tuple val(meta), path("**[!Undetermined]_S*_I?_00?.fastq.gz"), optional:true, emit: fastq_idx
+    tuple val(meta), path("**_S[1-9]*_R?_00?.fastq.gz")          , emit: fastq
+    tuple val(meta), path("**_S[1-9]*_I?_00?.fastq.gz")          , optional:true, emit: fastq_idx
     tuple val(meta), path("**Undetermined_S0*_R?_00?.fastq.gz")  , optional:true, emit: undetermined
     tuple val(meta), path("**Undetermined_S0*_I?_00?.fastq.gz")  , optional:true, emit: undetermined_idx
     tuple val(meta), path("Reports")                             , emit: reports

diff --git a/modules/nf-core/bclconvert/main.nf b/modules/nf-core/bclconvert/main.nf
@@ -8,8 +8,8 @@ process BCLCONVERT {
     tuple val(meta), path(samplesheet), path(run_dir)
 
     output:
-    tuple val(meta), path("**[!Undetermined]_S*_R?_00?.fastq.gz"), emit: fastq
-    tuple val(meta), path("**[!Undetermined]_S*_I?_00?.fastq.gz"), optional:true, emit: fastq_idx
+    tuple val(meta), path("**_S[1-9]*_R?_00?.fastq.gz")          , emit: fastq
+    tuple val(meta), path("**_S[1-9]*_I?_00?.fastq.gz")          , optional:true, emit: fastq_idx
     tuple val(meta), path("**Undetermined_S0*_R?_00?.fastq.gz")  , optional:true, emit: undetermined
     tuple val(meta), path("**Undetermined_S0*_I?_00?.fastq.gz")  , optional:true, emit: undetermined_idx
     tuple val(meta), path("Reports")                             , emit: reports

diff --git a/modules/nf-core/bracken/bracken/main.nf b/modules/nf-core/bracken/bracken/main.nf
@@ -14,7 +14,8 @@ process BRACKEN_BRACKEN {
     path database
 
     output:
-    tuple val(meta), path(bracken_report), emit: reports
+    tuple val(meta), path(bracken_report)        , emit: reports
+    tuple val(meta), path("*bracken_species.txt"), emit: txt
     path "versions.yml"          , emit: versions
 
     when:

diff --git a/modules/nf-core/bracken/bracken/meta.yml b/modules/nf-core/bracken/bracken/meta.yml
@@ -43,6 +43,10 @@ output:
       type: file
       description: TSV output report of the re-estimated abundances
       pattern: "*.{tsv}"
+  - txt:
+      type: file
+      description: TXT file of bracken corrected results of Kraken2 report output
+      pattern: "*.txt"
 
 authors:
   - "@Midnighter"
diff --git a/modules/nf-core/cellranger/count/templates/cellranger_count.py b/modules/nf-core/cellranger/count/templates/cellranger_count.py
@@ -1,4 +1,9 @@
 #!/usr/bin/env python3
+"""
+Automatically rename staged files for input into cellranger count.
+
+Copyright (c) Gregor Sturm 2023 - MIT License
+"""
 from subprocess import run
 from pathlib import Path
 from textwrap import dedent

diff --git a/modules/nf-core/controlfreec/assesssignificance/main.nf b/modules/nf-core/controlfreec/assesssignificance/main.nf
@@ -2,10 +2,10 @@ process CONTROLFREEC_ASSESSSIGNIFICANCE {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::control-freec=11.6"
+    conda "bioconda::control-freec=11.6b"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/control-freec:11.6--h1b792b2_1':
-        'biocontainers/control-freec:11.6--h1b792b2_1' }"
+        'https://depot.galaxyproject.org/singularity/control-freec:11.6b--hdbdd923_0 ':
+        'biocontainers/control-freec:11.6b--hdbdd923_0 ' }"
 
     input:
     tuple val(meta), path(cnvs), path(ratio)

diff --git a/modules/nf-core/controlfreec/freec/main.nf b/modules/nf-core/controlfreec/freec/main.nf
@@ -2,10 +2,10 @@ process CONTROLFREEC_FREEC {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::control-freec=11.6"
+    conda "bioconda::control-freec=11.6b"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/control-freec:11.6--h1b792b2_1':
-        'biocontainers/control-freec:11.6--h1b792b2_1' }"
+        'https://depot.galaxyproject.org/singularity/control-freec:11.6b--hdbdd923_0 ':
+        'biocontainers/control-freec:11.6b--hdbdd923_0 ' }"
 
     input:
     tuple val(meta), path(mpileup_normal), path(mpileup_tumor), path(cpn_normal), path(cpn_tumor), path(minipileup_normal), path(minipileup_tumor)

diff --git a/modules/nf-core/controlfreec/freec2bed/main.nf b/modules/nf-core/controlfreec/freec2bed/main.nf
@@ -2,10 +2,10 @@ process CONTROLFREEC_FREEC2BED {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::control-freec=11.6"
+    conda "bioconda::control-freec=11.6b"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/control-freec:11.6--h1b792b2_1':
-        'biocontainers/control-freec:11.6--h1b792b2_1' }"
+        'https://depot.galaxyproject.org/singularity/control-freec:11.6b--hdbdd923_0 ':
+        'biocontainers/control-freec:11.6b--hdbdd923_0 ' }"
 
     input:
     tuple val(meta), path(ratio)

diff --git a/modules/nf-core/controlfreec/freec2circos/main.nf b/modules/nf-core/controlfreec/freec2circos/main.nf
@@ -2,10 +2,10 @@ process CONTROLFREEC_FREEC2CIRCOS {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::control-freec=11.6"
+    conda "bioconda::control-freec=11.6b"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/control-freec:11.6--h1b792b2_1':
-        'biocontainers/control-freec:11.6--h1b792b2_1' }"
+        'https://depot.galaxyproject.org/singularity/control-freec:11.6b--hdbdd923_0 ':
+        'biocontainers/control-freec:11.6b--hdbdd923_0 ' }"
 
     input:
     tuple val(meta), path(ratio)

diff --git a/modules/nf-core/controlfreec/makegraph/main.nf b/modules/nf-core/controlfreec/makegraph/main.nf
@@ -2,11 +2,10 @@ process CONTROLFREEC_MAKEGRAPH {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::control-freec=11.6"
+    conda "bioconda::control-freec=11.6b"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/control-freec:11.6--h1b792b2_1':
-        'biocontainers/control-freec:11.6--h1b792b2_1' }"
-
+        'https://depot.galaxyproject.org/singularity/control-freec:11.6b--hdbdd923_0 ':
+        'biocontainers/control-freec:11.6b--hdbdd923_0 ' }"
     input:
     tuple val(meta), path(ratio), path(baf), val(ploidy)
 

diff --git a/modules/nf-core/expansionhunter/main.nf b/modules/nf-core/expansionhunter/main.nf
@@ -2,10 +2,10 @@ process EXPANSIONHUNTER {
     tag "$meta.id"
     label 'process_low'
 
-    conda "bioconda::expansionhunter=4.0.2"
+    conda "bioconda::expansionhunter=5.0.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/expansionhunter:4.0.2--he785bd8_0' :
-        'biocontainers/expansionhunter:4.0.2--he785bd8_0' }"
+        'https://depot.galaxyproject.org/singularity/expansionhunter:5.0.0--hf366f20_0' :
+        'biocontainers/expansionhunter:5.0.0--hf366f20_0' }"
 
     input:
     tuple val(meta), path(bam), path(bai)

diff --git a/modules/nf-core/gatk4/annotateintervals/main.nf b/modules/nf-core/gatk4/annotateintervals/main.nf
@@ -40,7 +40,8 @@ process GATK4_ANNOTATEINTERVALS {
     }
 
     """
-    gatk --java-options "-Xmx${avail_mem}M" AnnotateIntervals \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        AnnotateIntervals \\
         ${inputs} \\
         --reference ${fasta} \\
         --output ${prefix}.tsv \\

diff --git a/modules/nf-core/gatk4/annotateintervals/meta.yml b/modules/nf-core/gatk4/annotateintervals/meta.yml
@@ -1,11 +1,11 @@
 name: "gatk4_annotateintervals"
 description: Annotates intervals with GC content, mappability, and segmental-duplication content
 keywords:
-  - gatk
   - annotateintervals
-  - intervals
-  - bed
   - annotation
+  - bed
+  - gatk4
+  - intervals
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/applybqsr/main.nf b/modules/nf-core/gatk4/applybqsr/main.nf
@@ -33,7 +33,8 @@ process GATK4_APPLYBQSR {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" ApplyBQSR \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        ApplyBQSR \\
         --input $input \\
         --output ${prefix}.${input.getExtension()} \\
         --reference $fasta \\

diff --git a/modules/nf-core/gatk4/applybqsr/meta.yml b/modules/nf-core/gatk4/applybqsr/meta.yml
@@ -1,9 +1,11 @@
 name: gatk4_applybqsr
 description: Apply base quality score recalibration (BQSR) to a bam file
 keywords:
-  - bqsr
   - bam
   - base quality score recalibration
+  - bqsr
+  - cram
+  - gatk4
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/applybqsrspark/main.nf b/modules/nf-core/gatk4/applybqsrspark/main.nf
@@ -32,7 +32,7 @@ process GATK4_APPLYBQSR_SPARK {
     }
     """
     gatk \\
-        --java-options "-Xmx${avail_mem}M" \\
+        --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
         ApplyBQSRSpark \\
         --input $input \\
         --output ${prefix}.${input.getExtension()} \\

diff --git a/modules/nf-core/gatk4/applybqsrspark/meta.yml b/modules/nf-core/gatk4/applybqsrspark/meta.yml
@@ -1,9 +1,12 @@
 name: gatk4_applybqsr_spark
 description: Apply base quality score recalibration (BQSR) to a bam file
 keywords:
-  - bqsr
   - bam
-  - gatk
+  - base quality score recalibration
+  - bqsr
+  - cram
+  - gatk4
+  - spark
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/applyvqsr/main.nf b/modules/nf-core/gatk4/applyvqsr/main.nf
@@ -33,7 +33,8 @@ process GATK4_APPLYVQSR {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" ApplyVQSR \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        ApplyVQSR \\
         --variant ${vcf} \\
         --output ${prefix}.vcf.gz \\
         $reference_command \\

diff --git a/modules/nf-core/gatk4/applyvqsr/meta.yml b/modules/nf-core/gatk4/applyvqsr/meta.yml
@@ -6,8 +6,9 @@ description: |
   in the first step by VariantRecalibrator and a target sensitivity value.
 keywords:
   - gatk4
-  - applyvqsr
-  - VQSR
+  - variant quality score recalibration
+  - vcf
+  - vqsr
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/asereadcounter/main.nf b/modules/nf-core/gatk4/asereadcounter/main.nf
@@ -36,7 +36,8 @@ process GATK4_ASEREADCOUNTER {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" ASEReadCounter \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        ASEReadCounter \\
         --output ${prefix}_ase.csv \\
         --input ${input} \\
         --variant ${vcf} \\

diff --git a/modules/nf-core/gatk4/asereadcounter/meta.yml b/modules/nf-core/gatk4/asereadcounter/meta.yml
@@ -1,9 +1,10 @@
 name: "gatk4_asereadcounter"
 description: Calculates the allele-specific read counts for alle-specific expression analysis of RNAseq data
 keywords:
+  - allele-specific
   - asereadcounter
   - gatk4
-  - allele-specific
+  - vcf
 tools:
   - "gatk4":
       description: |

diff --git a/modules/nf-core/gatk4/baserecalibrator/main.nf b/modules/nf-core/gatk4/baserecalibrator/main.nf
@@ -35,7 +35,8 @@ process GATK4_BASERECALIBRATOR {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" BaseRecalibrator  \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        BaseRecalibrator  \\
         --input $input \\
         --output ${prefix}.table \\
         --reference $fasta \\

diff --git a/modules/nf-core/gatk4/baserecalibrator/meta.yml b/modules/nf-core/gatk4/baserecalibrator/meta.yml
@@ -1,6 +1,10 @@
 name: gatk4_baserecalibrator
 description: Generate recalibration table for Base Quality Score Recalibration (BQSR)
 keywords:
+  - base quality score recalibration
+  - table
+  - bqsr
+  - gatk4
   - sort
 tools:
   - gatk4:

diff --git a/modules/nf-core/gatk4/baserecalibratorspark/main.nf b/modules/nf-core/gatk4/baserecalibratorspark/main.nf
@@ -33,7 +33,8 @@ process GATK4_BASERECALIBRATOR_SPARK {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" BaseRecalibratorSpark \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        BaseRecalibratorSpark \\
         --input $input \\
         --output ${prefix}.table \\
         --reference $fasta \\

diff --git a/modules/nf-core/gatk4/baserecalibratorspark/meta.yml b/modules/nf-core/gatk4/baserecalibratorspark/meta.yml
@@ -1,9 +1,12 @@
 name: gatk4_baserecalibrator_spark
 description: Generate recalibration table for Base Quality Score Recalibration (BQSR)
 keywords:
-  - sort
+  - base quality score recalibration
+  - table
   - bqsr
-  - gatk
+  - gatk4
+  - sort
+  - spark
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/bedtointervallist/main.nf b/modules/nf-core/gatk4/bedtointervallist/main.nf
@@ -29,7 +29,8 @@ process GATK4_BEDTOINTERVALLIST {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" BedToIntervalList \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        BedToIntervalList \\
         --INPUT $bed \\
         --OUTPUT ${prefix}.interval_list \\
         --SEQUENCE_DICTIONARY $dict \\

diff --git a/modules/nf-core/gatk4/bedtointervallist/meta.yml b/modules/nf-core/gatk4/bedtointervallist/meta.yml
@@ -2,8 +2,9 @@ name: gatk4_bedtointervallist
 description: Creates an interval list from a bed file and a reference dict
 keywords:
   - bed
-  - interval list
   - bedtointervallist
+  - gatk4
+  - interval list
 tools:
   - gatk4:
       description: |

diff --git a/modules/nf-core/gatk4/calculatecontamination/main.nf b/modules/nf-core/gatk4/calculatecontamination/main.nf
@@ -30,7 +30,8 @@ process GATK4_CALCULATECONTAMINATION {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" CalculateContamination \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        CalculateContamination \\
         --input $pileup \\
         --output ${prefix}.contamination.table \\
         $matched_command \\

diff --git a/modules/nf-core/gatk4/calibratedragstrmodel/main.nf b/modules/nf-core/gatk4/calibratedragstrmodel/main.nf
@@ -32,7 +32,8 @@ process GATK4_CALIBRATEDRAGSTRMODEL {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" CalibrateDragstrModel \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        CalibrateDragstrModel \\
         --input ${bam} \\
         --output ${prefix}.txt \\
         --reference ${fasta} \\

diff --git a/modules/nf-core/gatk4/cnnscorevariants/main.nf b/modules/nf-core/gatk4/cnnscorevariants/main.nf
@@ -40,7 +40,8 @@ process GATK4_CNNSCOREVARIANTS {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" CNNScoreVariants \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        CNNScoreVariants \\
         --variant $vcf \\
         --output ${prefix}.cnn.vcf.gz \\
         --reference $fasta \\

diff --git a/modules/nf-core/gatk4/cnnscorevariants/meta.yml b/modules/nf-core/gatk4/cnnscorevariants/meta.yml
@@ -1,7 +1,7 @@
 name: "gatk4_cnnscorevariants"
 description: Apply a Convolutional Neural Net to filter annotated variants
 keywords:
-  - gatk4_cnnscorevariants
+  - cnnscorevariants
   - gatk4
   - variants
 tools:

diff --git a/modules/nf-core/gatk4/collectreadcounts/main.nf b/modules/nf-core/gatk4/collectreadcounts/main.nf
@@ -37,7 +37,8 @@ process GATK4_COLLECTREADCOUNTS {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
     """
-    gatk --java-options "-Xmx${avail_mem}M" CollectReadCounts \\
+    gatk --java-options "-Xmx${avail_mem}M -XX:-UsePerfData" \\
+        CollectReadCounts \\
         --input $input \\
         --intervals $intervals \\
         --output ${prefix}.$extension \\