Merge pull request #2 from cibinsb/arima_filter_five_end

created module Arima filter_five_end.pl

modules/arima/filterfiveend/main.nf

@@ -0,0 +1,44 @@
+
+process ARIMA_FILTERFIVEEND {
+    tag "$meta.id"
+    label 'process_medium'
+    def version = '0.001-c24'
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the arima filter_five_end_v1 tool. Please use docker or singularity containers."
+    }
+    container "quay.io/sanger-tol/arima:${version}"
+
+    input:
+    tuple val(meta), path(read)
+
+    output:
+    tuple val(meta), path("*.bam"), emit: bam
+    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}"
+    if (meta.single_end) {
+        """
+        samtools view -h ${read} | filter_five_end.pl | samtools view -Sb $args -@ $task.cpus -o ${prefix}_filtered.bam -
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' )
+            arima: ${version}
+        END_VERSIONS
+        """
+    } else {
+        """
+        samtools view -h ${read[0]} | filter_five_end.pl | samtools view -Sb $args -@ $task.cpus -o ${prefix}_1_filtered.bam -
+        samtools view -h ${read[1]} | filter_five_end.pl | samtools view -Sb $args -@ $task.cpus -o ${prefix}_2_filtered.bam -
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' )
+            arima: ${version}
+        END_VERSIONS
+        """
+    }
+}

modules/arima/filterfiveend/meta.yml

@@ -0,0 +1,54 @@
+name: arima_filterfiveend
+description: Filter BAM files using Arima filter_five_end.pl
+keywords:
+  - bam
+  - filter
+  - filterfiveend
+  - samtools
+tools:
+  - arima:
+      description: A wrapper tool around Arima Genomics's filter_five_end.pl to filter BAM files.
+      homepage: https://arimagenomics.com
+      documentation: https://github.com/ArimaGenomics/mapping_pipeline/blob/master/Arima_Mapping_UserGuide_A160156_v02.pdf
+      tool_dev_url: https://github.com/ArimaGenomics/mapping_pipeline
+      licence: MIT
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+          List of input BAM files of size 1 and 2 for single-end and paired-end data,
+          respectively.
+  - bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+          List of input adapter trimmed FastQ files of size 1 and 2 for
+          single-end and paired-end data, respectively.
+      pattern: "*.{_filtered.bam}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@cibinsb"

tests/config/pytest_modules.yml

@@ -38,6 +38,10 @@ amrfinderplus/update:
   - modules/amrfinderplus/update/**
   - tests/modules/amrfinderplus/update/**
 
+arima/filterfiveend:
+  - modules/arima/filterfiveend/**
+  - tests/modules/arima/filterfiveend/**
+
 arriba:
   - modules/arriba/**
   - tests/modules/arriba/**

tests/modules/arima/filterfiveend/main.nf

@@ -0,0 +1,26 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ARIMA_FILTERFIVEEND } from '../../../../modules/arima/filterfiveend/main.nf'
+
+workflow test_arima_filterfiveend_single_end {
+
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true)
+    ]
+
+    ARIMA_FILTERFIVEEND ( input )
+}
+
+workflow test_arima_filterfiveend_paired_end {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [file(params.test_data['bacteroides_fragilis']['illumina']['test1_paired_end_bam'], checkIfExists: true),
+        file(params.test_data['bacteroides_fragilis']['illumina']['test2_paired_end_bam'], checkIfExists: true)]
+    ]
+
+    ARIMA_FILTERFIVEEND ( input )
+}

tests/modules/arima/filterfiveend/nextflow.config

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

tests/modules/arima/filterfiveend/test.yml

@@ -0,0 +1,23 @@
+- name: arima filterfiveend test_arima_filterfiveend_single_end
+  command: nextflow run tests/modules/arima/filterfiveend -entry test_arima_filterfiveend_single_end -c tests/config/nextflow.config
+  tags:
+    - arima
+    - arima/filterfiveend
+  files:
+    - path: output/arima/test_filtered.bam
+      md5sum: 1f31e75a195da133180d8201597d2841
+    - path: output/arima/versions.yml
+      md5sum: dcb824f6fc3ab7d5a20afcf2508aa099
+
+- name: arima filterfiveend test_arima_filterfiveend_paired_end
+  command: nextflow run tests/modules/arima/filterfiveend -entry test_arima_filterfiveend_paired_end -c tests/config/nextflow.config
+  tags:
+    - arima
+    - arima/filterfiveend
+  files:
+    - path: output/arima/test_1_filtered.bam
+      md5sum: 92cd899240cee1ec731ea071023fa56a
+    - path: output/arima/test_2_filtered.bam
+      md5sum: 65df90c6d00fbdfc849d2b72fdfbe1c8
+    - path: output/arima/versions.yml
+      md5sum: a2d3a97555e1ad30e0c157aef66d25ed