Add new module: Pear (#1779)

* create pear module

* add command and tests

* remove md5sum from known empty file

* add force -f to gzip and gunzip to avoid problems with symbolic links

* apply suggestions from review

modules/pear/main.nf

@@ -0,0 +1,44 @@
+process PEAR {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::pear=0.9.6" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/pear:0.9.6--h67092d7_8':
+        'quay.io/biocontainers/pear:0.9.6--h67092d7_8' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.assembled.fastq.gz")                                                  , emit: assembled
+    tuple val(meta), path("*.unassembled.forward.fastq.gz"), path("*.unassembled.reverse.fastq.gz"), emit: unassembled
+    tuple val(meta), path("*.discarded.fastq.gz")                                                  , emit: discarded
+    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}"
+    """
+    gunzip -f ${reads[0]}
+    gunzip -f ${reads[1]}
+    pear \\
+        -f ${reads[0].baseName} \\
+        -r ${reads[1].baseName} \\
+        -o $prefix \\
+        -j $task.cpus \\
+        $args
+    gzip -f ${prefix}.assembled.fastq
+    gzip -f ${prefix}.unassembled.forward.fastq
+    gzip -f ${prefix}.unassembled.reverse.fastq
+    gzip -f ${prefix}.discarded.fastq
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pear: \$(pear -h | grep 'PEAR v' | sed 's/PEAR v//' | sed 's/ .*//' ))
+    END_VERSIONS
+    """
+}

modules/pear/meta.yml

@@ -0,0 +1,50 @@
+name: "pear"
+description: PEAR is an ultrafast, memory-efficient and highly accurate pair-end read merger.
+keywords:
+  - pair-end
+  - read
+tools:
+  - "pear":
+      description: "paired-end read merger"
+      homepage: "{https://cme.h-its.org/exelixis/web/software/pear/}"
+      documentation: "{https://cme.h-its.org/exelixis/web/software/pear/doc.html}"
+      tool_dev_url: "{}"
+      doi: ""
+      licence: "['Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files with paired-end reads forward and reverse.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - assembled:
+      type: file
+      description: FastQ file containing Assembled reads.
+      pattern: "*.{fastq.gz}"
+  - unassembled:
+      type: file
+      description: FastQ files containing Unassembled forward and reverse reads.
+      pattern: "*.{fastq.gz}"
+  - discarded:
+      type: file
+      description: FastQ file containing discarded reads.
+      pattern: "*.{fastq.gz}"
+
+authors:
+  - "@mirpedrol"

tests/config/pytest_modules.yml

@@ -1615,6 +1615,10 @@ pbccs:
   - modules/pbccs/**
   - tests/modules/pbccs/**
 
+pear:
+  - modules/pear/**
+  - tests/modules/pear/**
+
 peddy:
   - modules/peddy/**
   - tests/modules/peddy/**

tests/config/pytest_modules_test.yml

@@ -0,0 +1,23 @@
+abacas:
+  - modules/abacas/**
+  - tests/modules/abacas/**
+
+kallisto/index:
+  - modules/kallisto/index/**
+  - tests/modules/kallisto/index/**
+
+kallistobustools/count:
+  - modules/kallistobustools/count/**
+  - tests/modules/kallistobustools/count/**
+
+kallistobustools/ref:
+  - modules/kallistobustools/ref/**
+  - tests/modules/kallistobustools/ref/**
+
+kat/hist:
+  - modules/kat/hist/**
+  - tests/modules/kat/hist/**
+
+spades:
+  - modules/spades/**
+  - tests/modules/spades/**

tests/modules/pear/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PEAR } from '../../../modules/pear/main.nf'
+
+workflow test_pear {
+
+    input = [
+        [ id:'test' ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+
+    PEAR ( input )
+}

tests/modules/pear/nextflow.config

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

tests/modules/pear/test.yml

@@ -0,0 +1,12 @@
+- name: pear test_pear
+  command: nextflow run ./tests/modules/pear -entry test_pear -c ./tests/config/nextflow.config  -c ./tests/modules/pear/nextflow.config
+  tags:
+    - pear
+  files:
+    - path: output/pear/test.assembled.fastq.gz
+      md5sum: d02799ee04909655e7be5c9161c876b2
+    - path: output/pear/test.discarded.fastq.gz # Known empty file
+    - path: output/pear/test.unassembled.forward.fastq.gz
+      md5sum: 2e35f09a6abbb4559127c512f5652e7e
+    - path: output/pear/test.unassembled.reverse.fastq.gz
+      md5sum: 6e1c73c502230869c21b03a41faddafb