New subtool: hmmcopy/generatemap (#1168)

* Initial structure

* Working with local singularity image

* Working generateMap.pl script

* Remote not working bioconda

* Working generateMap with biocontainer

* Lint changes

* Updated hmmcopy container version to be consistent

* Fix failing test

* Remove path to perl

* No hardpath to script

* Update main.nf

Moved version outside of process, add support for zipped fasta file

* Revert to not allowing gzip via pipe, as perl script can't cope

Co-authored-by: Simon Pearce <simon.pearce@cruk.manchester.ac.uk>

modules/hmmcopy/gccounter/main.nf

@@ -5,8 +5,8 @@ process HMMCOPY_GCCOUNTER {
 
     conda (params.enable_conda ? "bioconda::hmmcopy=0.1.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/hmmcopy:0.1.1--h2e03b76_5' :
-        'quay.io/biocontainers/hmmcopy:0.1.1--h2e03b76_5' }"
+        'https://depot.galaxyproject.org/singularity/hmmcopy:0.1.1--h2e03b76_7' :
+        'quay.io/biocontainers/hmmcopy:0.1.1--h2e03b76_7' }"
 
     input:
     path fasta

modules/hmmcopy/generatemap/main.nf

@@ -0,0 +1,38 @@
+def VERSION = '0.1.1'
+    
+process HMMCOPY_GENERATEMAP {
+    tag '$bam'
+    label 'process_long'
+
+    conda (params.enable_conda ? "bioconda::hmmcopy=0.1.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hmmcopy:0.1.1--h2e03b76_7':
+        'quay.io/biocontainers/hmmcopy:0.1.1--h2e03b76_7' }"
+
+    input:
+    path fasta
+
+    output:
+    path "*.map.bw"              , emit: bigwig
+    path "versions.yml"          , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+
+    """
+    # build required indexes
+    generateMap.pl -b \\
+        $args \\
+        $fasta
+
+    # run
+    generateMap.pl \\
+        $args \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hmmcopy: \$(echo $VERSION)
+    END_VERSIONS
+    """
+}

modules/hmmcopy/generatemap/meta.yml

@@ -0,0 +1,32 @@
+name: hmmcopy_generatemap
+description: Perl script (generateMap.pl) generates the mappability of a genome given a certain size of reads, for input to hmmcopy mapcounter. Takes a very long time on large genomes, is not parallelised at all.
+keywords:
+  - hmmcopy
+  - mapcounter
+  - mappability
+tools:
+  - hmmcopy:
+      description: C++ based programs for analyzing BAM files and preparing read counts -- used with bioconductor-hmmcopy
+      homepage: https://github.com/shahcompbio/hmmcopy_utils
+      documentation: https://github.com/shahcompbio/hmmcopy_utils
+      tool_dev_url: https://github.com/shahcompbio/hmmcopy_utils
+      doi: ""
+      licence: ['GPL v3']
+
+input:
+  - fasta:
+      type: file
+      description: Input genome fasta file
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bigwig:
+      type: file
+      description: bigwig file containing the mappability of the genome
+      pattern: "*.{map.bw}"
+
+authors:
+  - "@sppearce"

modules/hmmcopy/readcounter/main.nf

@@ -6,8 +6,8 @@ process HMMCOPY_READCOUNTER {
 
     conda (params.enable_conda ? "bioconda::hmmcopy=0.1.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/hmmcopy:0.1.1--h2e03b76_5' :
-        'quay.io/biocontainers/hmmcopy:0.1.1--h2e03b76_5' }"
+        'https://depot.galaxyproject.org/singularity/hmmcopy:0.1.1--h2e03b76_7' :
+        'quay.io/biocontainers/hmmcopy:0.1.1--h2e03b76_7' }"
 
     input:
     tuple val(meta), path(bam), path(bai)

tests/config/pytest_modules.yml

@@ -685,6 +685,10 @@ hmmcopy/gccounter:
   - modules/hmmcopy/gccounter/**
   - tests/modules/hmmcopy/gccounter/**
 
+hmmcopy/generatemap:
+  - modules/hmmcopy/generatemap/**
+  - tests/modules/hmmcopy/generatemap/**
+
 hmmcopy/readcounter:
   - modules/hmmcopy/readcounter/**
   - tests/modules/hmmcopy/readcounter/**

tests/modules/hmmcopy/generatemap/main.nf

@@ -0,0 +1,12 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HMMCOPY_GENERATEMAP } from '../../../../modules/hmmcopy/generatemap/main.nf'
+
+workflow test_hmmcopy_generatemap {
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    HMMCOPY_GENERATEMAP ( fasta )
+}

tests/modules/hmmcopy/generatemap/nextflow.config

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

tests/modules/hmmcopy/generatemap/test.yml

@@ -0,0 +1,10 @@
+- name: hmmcopy generatemap test_hmmcopy_generatemap
+  command: nextflow run tests/modules/hmmcopy/generatemap -entry test_hmmcopy_generatemap -c tests/config/nextflow.config
+  tags:
+    - hmmcopy
+    - hmmcopy/generatemap
+  files:
+    - path: output/hmmcopy/genome.fasta.map.bw
+      md5sum: 7ad68224a1e40287978284c387e8eb70
+    - path: output/hmmcopy/versions.yml
+      md5sum: f950580f94d8a2d88332c477972cb9f0

tests/modules/hmmcopy/readcounter/test.yml

@@ -1,8 +1,10 @@
 - name: hmmcopy readcounter test_hmmcopy_readcounter
-  command: nextflow run ./tests/modules/hmmcopy/readcounter -entry test_hmmcopy_readcounter -c ./tests/config/nextflow.config -c ./tests/modules/hmmcopy/readcounter/nextflow.config
+  command: nextflow run tests/modules/hmmcopy/readcounter -entry test_hmmcopy_readcounter -c tests/config/nextflow.config
   tags:
     - hmmcopy
     - hmmcopy/readcounter
   files:
     - path: output/hmmcopy/test.wig
-      md5sum: 3655d8325baea81b3b690791262c6b57
+      md5sum: 4682778422b9a2510a3cb70bd13ccd08
+    - path: output/hmmcopy/versions.yml
+      md5sum: 624a85e6a1bc61abc33cac03aea33a1e