Add RSeqC tin.py module (#1174)

* Add RSeqC tin.py module

* Fix EC lint for unrelated hmmcopy module

* Remove md5sum for empty file

modules/rseqc/tin/main.nf

@@ -0,0 +1,33 @@
+process RSEQC_TIN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' :
+        'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }"
+
+    input:
+    tuple val(meta), path(bam)
+    path  bed
+
+    output:
+    tuple val(meta), path("*.txt"), emit: txt
+    path "versions.yml"           , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    tin.py \\
+        -i $bam \\
+        -r $bed \\
+        $args \\
+        > ${prefix}.tin.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rseqc: \$(tin.py --version | sed -e "s/tin.py //g")
+    END_VERSIONS
+    """
+}

modules/rseqc/tin/meta.yml

@@ -0,0 +1,40 @@
+name: rseqc_tin
+description: Calculte TIN (transcript integrity number) from RNA-seq reads
+keywords:
+  - rnaseq
+  - transcript
+  - integrity
+tools:
+  - rseqc:
+      description: |
+        RSeQC package provides a number of useful modules that can comprehensively evaluate
+        high throughput sequence data especially RNA-seq data.
+      homepage: http://rseqc.sourceforge.net/
+      documentation: http://rseqc.sourceforge.net/
+      doi: 10.1093/bioinformatics/bts356
+      licence: ['GPL-3.0-or-later']
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Input BAM file
+      pattern: "*.{bam}"
+  - bed:
+      type: file
+      description: BED file containing the reference gene model
+      pattern: "*.{bed}"
+output:
+  - txt:
+      type: file
+      description: tin.py results file
+      pattern: "*.tin.txt"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@drpatelh"

tests/config/pytest_modules.yml

@@ -270,21 +270,19 @@ cat/fastq:
   - modules/cat/fastq/**
   - tests/modules/cat/fastq/**
 
-cellranger/gtf: # &cellranger/gtf
-  - modules/cellranger/gtf/**
-  - tests/modules/cellranger/gtf/**
-
-cellranger/mkref: # &cellranger/mkref
-  - modules/cellranger/mkref/**
-  - tests/modules/cellranger/mkref/**
-  # - *cellranger/gtf
-  - modules/cellranger/gtf/**
-  - tests/modules/cellranger/gtf/**
-
 cellranger/count:
   - modules/cellranger/count/**
   - tests/modules/cellranger/count/**
-  # - *cellranger/mkref
+  - modules/cellranger/mkref/**
+  - tests/modules/cellranger/mkref/**
+  - modules/cellranger/gtf/**
+  - tests/modules/cellranger/gtf/**
+
+cellranger/gtf:
+  - modules/cellranger/gtf/**
+  - tests/modules/cellranger/gtf/**
+
+cellranger/mkref:
   - modules/cellranger/mkref/**
   - tests/modules/cellranger/mkref/**
   - modules/cellranger/gtf/**
@@ -514,7 +512,7 @@ gatk4/bedtointervallist:
   - modules/gatk4/bedtointervallist/**
   - tests/modules/gatk4/bedtointervallist/**
 
-gatk4/calculatecontamination: #&gatk4_calculatecontamination
+gatk4/calculatecontamination:
   - modules/gatk4/calculatecontamination/**
   - tests/modules/gatk4/calculatecontamination/**
 
@@ -522,7 +520,7 @@ gatk4/createsequencedictionary:
   - modules/gatk4/createsequencedictionary/**
   - tests/modules/gatk4/createsequencedictionary/**
 
-gatk4/createsomaticpanelofnormals: #&gatk4_createsomaticpanelofnormals
+gatk4/createsomaticpanelofnormals:
   - modules/gatk4/createsomaticpanelofnormals/**
   - tests/modules/gatk4/createsomaticpanelofnormals/**
 
@@ -534,7 +532,7 @@ gatk4/fastqtosam:
   - modules/gatk4/fastqtosam/**
   - tests/modules/gatk4/fastqtosam/**
 
-gatk4/filtermutectcalls: #&gatk4_filtermutectcalls
+gatk4/filtermutectcalls:
   - modules/gatk4/filtermutectcalls/**
   - tests/modules/gatk4/filtermutectcalls/**
 
@@ -542,7 +540,7 @@ gatk4/gatherbqsrreports:
   - modules/gatk4/gatherbqsrreports/**
   - tests/modules/gatk4/gatherbqsrreports/**
 
-gatk4/genomicsdbimport: #&gatk4_genomicsdbimport
+gatk4/genomicsdbimport:
   - modules/gatk4/genomicsdbimport/**
   - tests/modules/gatk4/genomicsdbimport/**
 
@@ -550,7 +548,7 @@ gatk4/genotypegvcfs:
   - modules/gatk4/genotypegvcfs/**
   - tests/modules/gatk4/genotypegvcfs/**
 
-gatk4/getpileupsummaries: #&gatk4_getpileupsummaries
+gatk4/getpileupsummaries:
   - modules/gatk4/getpileupsummaries/**
   - tests/modules/gatk4/getpileupsummaries/**
 
@@ -566,7 +564,7 @@ gatk4/intervallisttools:
   - modules/gatk4/intervallisttools/**
   - tests/modules/gatk4/intervallisttools/**
 
-gatk4/learnreadorientationmodel: #&gatk4_learnreadorientationmodel
+gatk4/learnreadorientationmodel:
   - modules/gatk4/learnreadorientationmodel/**
   - tests/modules/gatk4/learnreadorientationmodel/**
 
@@ -582,7 +580,7 @@ gatk4/mergevcfs:
   - modules/gatk4/mergevcfs/**
   - tests/modules/gatk4/mergevcfs/**
 
-gatk4/mutect2: #&gatk4_mutect2
+gatk4/mutect2:
   - modules/gatk4/mutect2/**
   - tests/modules/gatk4/mutect2/**
 
@@ -1207,6 +1205,10 @@ rseqc/readduplication:
   - modules/rseqc/readduplication/**
   - tests/modules/rseqc/readduplication/**
 
+rseqc/tin:
+  - modules/rseqc/tin/**
+  - tests/modules/rseqc/tin/**
+
 salmon/index:
   - modules/salmon/index/**
   - tests/modules/salmon/index/**
@@ -1251,7 +1253,7 @@ samtools/idxstats:
   - modules/samtools/idxstats/**
   - tests/modules/samtools/idxstats/**
 
-samtools/index: #&samtools_index
+samtools/index:
   - modules/samtools/index/**
   - tests/modules/samtools/index/**
 
@@ -1263,7 +1265,7 @@ samtools/mpileup:
   - modules/samtools/mpileup/**
   - tests/modules/samtools/mpileup/**
 
-samtools/sort: #&samtools_sort
+samtools/sort:
   - modules/samtools/sort/**
   - tests/modules/samtools/sort/**
 
@@ -1339,11 +1341,11 @@ spatyper:
   - modules/spatyper/**
   - tests/modules/spatyper/**
 
-sratools/fasterqdump: #&sratools_fasterqdump
+sratools/fasterqdump:
   - modules/sratools/fasterqdump/**
   - tests/modules/sratools/fasterqdump/**
 
-sratools/prefetch: #&sratools_prefetch
+sratools/prefetch:
   - modules/sratools/prefetch/**
   - tests/modules/sratools/prefetch/**
 
@@ -1462,56 +1464,3 @@ yara/index:
 yara/mapper:
   - modules/yara/mapper/**
   - tests/modules/yara/mapper/**
-
-# subworkflows/align_bowtie2:
-#   - subworkflows/nf-core/align_bowtie2/**
-#   - tests/subworkflows/nf-core/align_bowtie2/**
-#   - *subworkflows_bam_sort_samtools
-
-# subworkflows/annotation_ensemblvep: &subworkflows_annotation_ensemblvep
-#   - subworkflows/nf-core/annotation_ensemblvep/**
-#   - tests/subworkflows/nf-core/annotation_ensemblvep/**
-
-# subworkflows/annotation_snpeff: &subworkflows_annotation_snpeff
-#   - subworkflows/nf-core/annotation_snpeff/**
-#   - tests/subworkflows/nf-core/annotation_snpeff/**
-
-# subworkflows/bam_stats_samtools: &subworkflows_bam_stats_samtools
-#   - subworkflows/nf-core/bam_stats_samtools/**
-#   - tests/subworkflows/nf-core/bam_stats_samtools/**
-
-# subworkflows/bam_sort_samtools: &subworkflows_bam_sort_samtools
-#   - subworkflows/nf-core/bam_sort_samtools/**
-#   - tests/subworkflows/nf-core/bam_sort_samtools/**
-#   - *samtools_sort
-#   - *samtools_index
-#   - *subworkflows_bam_stats_samtools
-
-# subworkflows/gatk_create_som_pon:
-#   - subworkflows/nf-core/gatk_create_som_pon/**
-#   - tests/subworkflows/nf-core/gatk_create_som_pon/**
-#   - *gatk4_genomicsdbimport
-#   - *gatk4_createsomaticpanelofnormals
-
-# subworkflows/gatk_tumor_normal_somatic_variant_calling:
-#   - subworkflows/nf-core/gatk_tumor_normal_somatic_variant_calling/**
-#   - tests/subworkflows/nf-core/gatk_tumor_normal_somatic_variant_calling/**
-#   - *gatk4_mutect2
-#   - *gatk4_learnreadorientationmodel
-#   - *gatk4_getpileupsummaries
-#   - *gatk4_calculatecontamination
-#   - *gatk4_filtermutectcalls
-
-# subworkflows/gatk_tumor_only_somatic_variant_calling:
-#   - subworkflows/nf-core/gatk_tumor_only_somatic_variant_calling/**
-#   - tests/subworkflows/nf-core/gatk_tumor_only_somatic_variant_calling/**
-#   - *gatk4_mutect2
-#   - *gatk4_getpileupsummaries
-#   - *gatk4_calculatecontamination
-#   - *gatk4_filtermutectcalls
-
-# subworkflows/sra_fastq:
-#   - subworkflows/nf-core/sra_fastq/**
-#   - tests/subworkflows/nf-core/sra_fastq/**
-#   - *sratools_fasterqdump
-#   - *sratools_prefetch

tests/modules/rseqc/tin/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { RSEQC_TIN } from '../../../../modules/rseqc/tin/main.nf'
+
+workflow test_rseqc_tin {
+
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+    ]
+
+    bed = file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+
+    RSEQC_TIN ( input, bed )
+}

tests/modules/rseqc/tin/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/rseqc/tin/test.yml

@@ -0,0 +1,7 @@
+- name: rseqc tin
+  command: nextflow run ./tests/modules/rseqc/tin -entry test_rseqc_tin -c ./tests/config/nextflow.config -c ./tests/modules/rseqc/tin/nextflow.config
+  tags:
+    - rseqc
+    - rseqc/tin
+  files:
+    - path: output/rseqc/test.tin.txt