new tool: staden_io_lib (#1499)

* new tool: staden_io_lib

* update docker containers

* add test.yml

* add fai index input

* typo

* fix version.yml

* update md5sum

* omit md5sum for cram

* move scramble to submodule

* add missing in/output

* remove some comments

Co-authored-by: Sateesh Peri <33637490+sateeshperi@users.noreply.github.com>

modules/stadeniolib/scramble/main.nf

@@ -0,0 +1,61 @@
+process STADENIOLIB_SCRAMBLE {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::staden_io_lib=1.14.14" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/staden_io_lib:1.14.14--h0d9da7e_3' :
+        'quay.io/biocontainers/staden_io_lib:1.14.14--h0d9da7e_3' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path(fasta)
+    path(fai)
+    path(gzi)
+
+    output:
+    tuple val(meta), path("*.cram") ,emit: cram
+    path "*.gzi"                    ,emit: gzi, 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 inputformat = reads.getExtension
+    def outputformat = "cram"
+    if ("-O sam" in args) {
+        outputformat = "sam"
+    } else if ("-O bam" in args) {
+        outputformat = "bam"
+    }
+
+    def reference = if fasta && fai : "--r ${fasta}" else ""
+    if (outputformat == "cram" && !reference) {
+        error "Cannot convert to CRAM without a reference"
+    }
+
+    def gz_index = if gzi : "--g ${gzi}" else ""
+    if (outputformat == "cram" || outputformat == "sam") {
+        gz_index = ""
+        warning "Cannot use gzip index for CRAM or SAM output"
+    }
+
+    """
+    scramble \
+        $args \
+        -I ${inputformat} \
+        $reference \
+        -t $task.cpus \
+        ${reads} \
+        ${prefix}.${outputformat}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        stadeniolib: \$(echo \$(scramble -h | head -n 1 |sed 's/^.*version //'))
+    END_VERSIONS
+    """
+}

modules/stadeniolib/scramble/meta.yml

@@ -0,0 +1,58 @@
+name: "stadeniolib_scramble"
+description: Advanced sequence file format conversions
+keywords:
+  - sam
+  - bam
+  - cram
+  - compression
+tools:
+  - "scramble":
+      description: "Staden Package 'io_lib' (sometimes referred to as libstaden-read by distributions). This contains code for reading and writing a variety of Bioinformatics / DNA Sequence formats."
+      homepage: "https://github.com/jkbonfield/io_lib"
+      documentation: "https://github.com/jkbonfield/io_lib/blob/master/README.md"
+      tool_dev_url: "https://github.com/jkbonfield/io_lib"
+      licence: "['BSD']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - fasta:
+      type: file
+      description: Reference genome in FASTA format
+      pattern: "*.{fa,fasta}"
+  - fai:
+      type: file
+      description: FASTA index file from samtools faidx
+      pattern: "*.{fai}"
+  - gzi:
+      type: file
+      description: Optional gzip index file for BAM inputs
+      pattern: "*.gzi"
+
+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"
+  - reads:
+      type: file
+      description: Converted reads
+      pattern: "*.{sam, bam, cram}"
+  - gzi:
+      type: Optional file
+      description: gzip index file for BAM outputs
+      pattern: ".{bam.gzi}"
+authors:
+  - "@matthdsm"

tests/config/pytest_modules.yml

@@ -1707,6 +1707,10 @@ ssuissero:
   - modules/ssuissero/**
   - tests/modules/ssuissero/**
 
+stadeniolib/scramble:
+  - modules/stadeniolib/scramble/**
+  - tests/modules/stadeniolib/scramble/**
+
 staphopiasccmec:
   - modules/staphopiasccmec/**
   - tests/modules/staphopiasccmec/**

tests/modules/stadeniolib/scramble/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { STADENIOLIB_SCRAMBLE } from '../../../../modules/stadeniolib/scramble/main.nf'
+
+workflow test_stadeniolib {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    STADENIOLIB_SCRAMBLE ( input, file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true), file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true), [])
+}

tests/modules/stadeniolib/scramble/nextflow.config

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

tests/modules/stadeniolib/scramble/test.yml

@@ -0,0 +1,7 @@
+- name: stadeniolib test_stadeniolib
+  command: nextflow run tests/modules/stadeniolib -entry test_stadeniolib -c tests/config/nextflow.config
+  tags:
+    - stadeniolib
+  files:
+    - path: output/stadeniolib/test.cram
+    - path: output/stadeniolib/versions.yml