From ab4c2e440d518b4815cc276cf621f89df4ffaa70 Mon Sep 17 00:00:00 2001
From: Priyanka Surana <86618929+priyanka-surana@users.noreply.github.com>
Date: Wed, 21 Sep 2022 14:12:59 +0100
Subject: [PATCH] samtools collate module (#2078)

* samtools collate module

* prettier fix

* prettier fix

* added cram functionality
---
 modules/samtools/collate/main.nf              | 46 +++++++++++++++++++
 modules/samtools/collate/meta.yml             | 44 ++++++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 tests/modules/samtools/collate/main.nf        | 27 +++++++++++
 .../modules/samtools/collate/nextflow.config  |  5 ++
 tests/modules/samtools/collate/test.yml       | 17 +++++++
 6 files changed, 143 insertions(+)
 create mode 100644 modules/samtools/collate/main.nf
 create mode 100644 modules/samtools/collate/meta.yml
 create mode 100644 tests/modules/samtools/collate/main.nf
 create mode 100644 tests/modules/samtools/collate/nextflow.config
 create mode 100644 tests/modules/samtools/collate/test.yml

diff --git a/modules/samtools/collate/main.nf b/modules/samtools/collate/main.nf
new file mode 100644
index 00000000..4944b70a
--- /dev/null
+++ b/modules/samtools/collate/main.nf
@@ -0,0 +1,46 @@
+process SAMTOOLS_COLLATE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0':
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(input)
+    path fasta
+
+    output:
+    tuple val(meta), path("*.bam"),  emit: bam, optional: true
+    tuple val(meta), path("*.cram"), emit: cram, optional: true
+    tuple val(meta), path("*.sam"),  emit: sam,  optional: true
+    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 reference = fasta ? "--reference ${fasta}" : ""
+    def extension = args.contains("--output-fmt sam") ? "sam" :
+                    args.contains("--output-fmt bam") ? "bam" :
+                    args.contains("--output-fmt cram") ? "cram" :
+                    "bam"
+    if ("$input" == "${prefix}.${extension}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    samtools \\
+        collate \\
+        $args \\
+        ${reference} \\
+        -@ $task.cpus \\
+        -o ${prefix}.${extension} \\
+        $input
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}
diff --git a/modules/samtools/collate/meta.yml b/modules/samtools/collate/meta.yml
new file mode 100644
index 00000000..0e78403c
--- /dev/null
+++ b/modules/samtools/collate/meta.yml
@@ -0,0 +1,44 @@
+name: "samtools_collate"
+description: shuffles and groups reads together by their names
+keywords:
+  - collate
+  - bam
+tools:
+  - "samtools":
+      description: "Tools for dealing with SAM, BAM and CRAM files"
+      homepage: "http://www.htslib.org"
+      documentation: "https://www.htslib.org/doc/samtools-collate.html"
+      tool_dev_url: "https://github.com/samtools/samtools"
+      doi: "10.1093/bioinformatics/btp352"
+      licence: "['MIT']"
+
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+output:
+  #Only when we have meta
+  - 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"
+  - output:
+      type: file
+      description: Collated BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@priyanka-surana"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 6b4ad00c..5fa0cb9f 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -2035,6 +2035,10 @@ samtools/bam2fq:
   - modules/samtools/bam2fq/**
   - tests/modules/samtools/bam2fq/**
 
+samtools/collate:
+  - modules/samtools/collate/**
+  - tests/modules/samtools/collate/**
+
 samtools/collatefastq:
   - modules/samtools/collatefastq/**
   - tests/modules/samtools/collatefastq/**
diff --git a/tests/modules/samtools/collate/main.nf b/tests/modules/samtools/collate/main.nf
new file mode 100644
index 00000000..5fec4913
--- /dev/null
+++ b/tests/modules/samtools/collate/main.nf
@@ -0,0 +1,27 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SAMTOOLS_COLLATE } from '../../../../modules/samtools/collate/main.nf'
+
+workflow test_samtools_collate {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    SAMTOOLS_COLLATE ( input, [] )
+}
+
+workflow test_samtools_collate_cram {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    SAMTOOLS_COLLATE ( input, fasta )
+}
diff --git a/tests/modules/samtools/collate/nextflow.config b/tests/modules/samtools/collate/nextflow.config
new file mode 100644
index 00000000..50f50a7a
--- /dev/null
+++ b/tests/modules/samtools/collate/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}
\ No newline at end of file
diff --git a/tests/modules/samtools/collate/test.yml b/tests/modules/samtools/collate/test.yml
new file mode 100644
index 00000000..784ede89
--- /dev/null
+++ b/tests/modules/samtools/collate/test.yml
@@ -0,0 +1,17 @@
+- name: samtools collate test_samtools_collate
+  command: nextflow run ./tests/modules/samtools/collate -entry test_samtools_collate -c ./tests/config/nextflow.config  -c ./tests/modules/samtools/collate/nextflow.config
+  tags:
+    - samtools/collate
+    - samtools
+  files:
+    - path: output/samtools/test.bam
+      md5sum: dbb8244c28778a970e49577731b158df
+
+- name: samtools collate test_samtools_collate_cram
+  command: nextflow run ./tests/modules/samtools/collate -entry test_samtools_collate_cram -c ./tests/config/nextflow.config  -c ./tests/modules/samtools/collate/nextflow.config
+  tags:
+    - samtools/collate
+    - samtools
+  files:
+    - path: output/samtools/test.bam
+      md5sum: 81aa61ed1f6f3bf6b9c94f70cbf2a177