Picard createsequencedictionary (#1310)

* add picard/createsequencedictionary module

* add picard-CreateSequenceDictionary

* add picard/createsequencedictionary/

* add contains to test yml

* update test yml contains

* update test yml contains

Co-authored-by: Peri <rrx8@cdc.gov>
Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>

modules/picard/createsequencedictionary/main.nf

@@ -0,0 +1,42 @@
+process PICARD_CREATESEQUENCEDICTIONARY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::picard=2.26.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/picard:2.26.9--hdfd78af_0' :
+        'quay.io/biocontainers/picard:2.26.9--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("*.dict"), emit: reference_dict
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[Picard CreateSequenceDictionary] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+    """
+    picard \\
+        -Xmx${avail_mem}g \\
+        CreateSequenceDictionary  \\
+        $args \\
+        R=$fasta \\
+        O=${prefix}.dict
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        picard: \$(picard CreateSequenceDictionary --version 2>&1 | grep -o 'Version:.*' | cut -f2- -d:)
+    END_VERSIONS
+    """
+}

modules/picard/createsequencedictionary/meta.yml

@@ -0,0 +1,45 @@
+name: picard_createsequencedictionary
+description: Creates a sequence dictionary for a reference sequence.
+keywords:
+  - sequence
+  - dictionary
+  - picard
+tools:
+  - picard:
+      description: |
+            Creates a sequence dictionary file (with ".dict" extension) from a reference sequence provided in FASTA format, which is required by many processing and analysis tools. The output file contains a header but no SAMRecords, and the header contains only sequence records.
+      homepage: https://broadinstitute.github.io/picard/
+      documentation: https://gatk.broadinstitute.org/hc/en-us/articles/360036712531-CreateSequenceDictionary-Picard-
+      tool_dev_url: https://github.com/broadinstitute/picard
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - dict:
+    type: file
+    description: picard dictionary file
+    pattern: "*.{dict}"
+
+authors:
+  - "@sateeshperi"
+  - "@mjcipriano"
+  - "@hseabolt"

tests/config/pytest_modules.yml

@@ -1169,6 +1169,10 @@ picard/collectwgsmetrics:
   - modules/picard/collectwgsmetrics/**
   - tests/modules/picard/collectwgsmetrics/**
 
+picard/createsequencedictionary:
+  - modules/picard/createsequencedictionary/**
+  - tests/modules/picard/createsequencedictionary/**
+
 picard/filtersamreads:
   - modules/picard/filtersamreads/**
   - tests/modules/picard/filtersamreads/**

tests/modules/picard/createsequencedictionary/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PICARD_CREATESEQUENCEDICTIONARY } from '../../../../modules/picard/createsequencedictionary/main.nf'
+
+workflow test_picard_createsequencedictionary {
+    
+    input = [ 
+        [ id:'test' ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) 
+    ]
+
+    PICARD_CREATESEQUENCEDICTIONARY ( input )
+}

tests/modules/picard/createsequencedictionary/nextflow.config

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

tests/modules/picard/createsequencedictionary/test.yml

@@ -0,0 +1,10 @@
+- name: picard createsequencedictionary test_picard_createsequencedictionary
+  command: nextflow run tests/modules/picard/createsequencedictionary -entry test_picard_createsequencedictionary -c tests/config/nextflow.config
+  tags:
+    - picard/createsequencedictionary
+    - picard
+  files:
+    - path: output/picard/test.dict
+      contains: ['SN:MT192765.1']
+    - path: output/picard/versions.yml
+      md5sum: b3d8c7ea65b8a6d3237b153d13fe2014