From d8028dc1c3ef64c2ee3494ce65d4f4a76c42bde9 Mon Sep 17 00:00:00 2001
From: Ramprasad Neethiraj <20065894+ramprasadn@users.noreply.github.com>
Date: Thu, 3 Mar 2022 17:40:16 +0100
Subject: [PATCH] Add picard/sortvcf (#1370)

* sortvcf

* add files

* update meta

* update java mem

* update documentation link

* remove todo

* review suggestions

* fix test.yml

* fix conda error

* fix version code
---
 modules/picard/sortvcf/main.nf               | 49 ++++++++++++++++++++
 modules/picard/sortvcf/meta.yml              | 40 ++++++++++++++++
 tests/config/pytest_modules.yml              |  4 ++
 tests/modules/picard/sortvcf/main.nf         | 18 +++++++
 tests/modules/picard/sortvcf/nextflow.config |  5 ++
 tests/modules/picard/sortvcf/test.yml        |  7 +++
 6 files changed, 123 insertions(+)
 create mode 100644 modules/picard/sortvcf/main.nf
 create mode 100644 modules/picard/sortvcf/meta.yml
 create mode 100644 tests/modules/picard/sortvcf/main.nf
 create mode 100644 tests/modules/picard/sortvcf/nextflow.config
 create mode 100644 tests/modules/picard/sortvcf/test.yml

diff --git a/modules/picard/sortvcf/main.nf b/modules/picard/sortvcf/main.nf
new file mode 100644
index 00000000..0f10c1ab
--- /dev/null
+++ b/modules/picard/sortvcf/main.nf
@@ -0,0 +1,49 @@
+process PICARD_SORTVCF {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::picard=2.26.10" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' :
+        'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+    path reference
+    path sequence_dict
+
+    output:
+    tuple val(meta), path("*_sorted.vcf.gz"), emit: vcf
+    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 seq_dict = sequence_dict ? "-SEQUENCE_DICTIONARY $sequence_dict" : ""
+    def reference = reference ? "-REFERENCE_SEQUENCE $reference" : ""
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[Picard SortVcf] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    picard \\
+        SortVcf \\
+        -Xmx${avail_mem}g \\
+        --INPUT $vcf \\
+        $args \\
+        $seq_dict \\
+        $reference \\
+        --OUTPUT ${prefix}_sorted.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        picard: \$(picard SortVcf --version 2>&1 | grep -o 'Version:.*' | cut -f2- -d:)
+    END_VERSIONS
+    """
+}
diff --git a/modules/picard/sortvcf/meta.yml b/modules/picard/sortvcf/meta.yml
new file mode 100644
index 00000000..a2b46d5a
--- /dev/null
+++ b/modules/picard/sortvcf/meta.yml
@@ -0,0 +1,40 @@
+name: picard_sortvcf
+description: Sorts vcf files
+keywords:
+  - sort
+  - vcf
+tools:
+  - picard:
+      description: Java tools for working with NGS data in the BAM/CRAM/SAM and VCF format
+      homepage: https://broadinstitute.github.io/picard/
+      documentation: https://broadinstitute.github.io/picard/command-line-overview.html#SortVcf
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF file
+      pattern: "*.{vcf,vcf.gz}"
+
+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"
+  - vcf:
+      type: file
+      description: Sorted VCF file
+      pattern: "*.{vcf}"
+
+authors:
+  - "@ramprasadn"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index de03a379..553128de 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -1249,6 +1249,10 @@ picard/sortsam:
   - modules/picard/sortsam/**
   - tests/modules/picard/sortsam/**
 
+picard/sortvcf:
+  - modules/picard/sortvcf/**
+  - tests/modules/picard/sortvcf/**
+
 pirate:
   - modules/pirate/**
   - tests/modules/pirate/**
diff --git a/tests/modules/picard/sortvcf/main.nf b/tests/modules/picard/sortvcf/main.nf
new file mode 100644
index 00000000..a88c69fc
--- /dev/null
+++ b/tests/modules/picard/sortvcf/main.nf
@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PICARD_SORTVCF } from '../../../../modules/picard/sortvcf/main.nf'
+
+workflow test_picard_sortvcf {
+
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+            ]
+
+    fasta  = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    dict  = [ file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true) ]
+
+    PICARD_SORTVCF ( input, fasta, dict )
+}
diff --git a/tests/modules/picard/sortvcf/nextflow.config b/tests/modules/picard/sortvcf/nextflow.config
new file mode 100644
index 00000000..8730f1c4
--- /dev/null
+++ b/tests/modules/picard/sortvcf/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}
diff --git a/tests/modules/picard/sortvcf/test.yml b/tests/modules/picard/sortvcf/test.yml
new file mode 100644
index 00000000..26271077
--- /dev/null
+++ b/tests/modules/picard/sortvcf/test.yml
@@ -0,0 +1,7 @@
+- name: picard sortvcf
+  command: nextflow run ./tests/modules/picard/sortvcf -entry test_picard_sortvcf -c ./tests/config/nextflow.config -c ./tests/modules/picard/sortvcf/nextflow.config
+  tags:
+    - picard
+    - picard/sortvcf
+  files:
+    - path: output/picard/test_sorted.vcf.gz