new tool snap-aligner/index (#1506)

* add snapaligner/index

* output fixes

* fix outputs

* fix tests

* update inputs

* fix more bugs

* fix linting

* Update modules/snapaligner/index/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/snapaligner/index/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* fix comments

* fix indents

* fix escaping

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/snapaligner/index/main.nf

@@ -0,0 +1,59 @@
+process SNAPALIGNER_INDEX {
+    tag '$fasta'
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::snap-aligner=2.0.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/snap-aligner:2.0.1--hd03093a_1':
+        'quay.io/biocontainers/snap-aligner:2.0.1--hd03093a_1' }"
+
+    input:
+    path fasta
+    path altcontigfile
+    path nonaltcontigfile
+    path altliftoverfile
+
+    output:
+    path "snap/*"            ,emit: index
+    path "versions.yml"      ,emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def altcontigfile_arg = altcontigfile ? '-altContigFile ' + altcontigfile : ''
+    def nonaltcontigfile_arg = nonaltcontigfile ? '-nonAltContigFile ' + nonaltcontigfile : ''
+    def altliftoverfile_arg = altliftoverfile ? '-altLiftoverFile ' + altliftoverfile : ''
+    """
+    mkdir snap
+
+    snap-aligner \\
+        index \\
+        $fasta \\
+        snap \\
+        -t${task.cpus} \\
+        $altcontigfile_arg \\
+        $nonaltcontigfile_arg \\
+        $altliftoverfile_arg \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        snapaligner: \$(snap-aligner 2>&1| head -n 1 | sed 's/^.*version //')
+    END_VERSIONS
+    """
+    stub:
+    """
+    mkdir snap
+    echo "Genome" > snap/Genome
+    echo "GenomeIndex" > snap/GenomeIndex
+    echo "GenomeIndexHash" > snap/GenomeIndexHash
+    echo "OverflowTable" > snap/OverflowTable
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        snapaligner: \$(snap-aligner 2>&1| head -n 1 | sed 's/^.*version //;s/\.\$//')
+    END_VERSIONS
+    """
+}

modules/snapaligner/index/meta.yml

@@ -0,0 +1,39 @@
+name: "snapaligner_index"
+description: Create a SNAP index for reference genome
+keywords:
+  - index
+  - fasta
+  - genome
+  - reference
+tools:
+  - "snapaligner":
+      description: "Scalable Nucleotide Alignment Program -- a fast and accurate read aligner for high-throughput sequencing data"
+      homepage: "http://snap.cs.berkeley.edu"
+      documentation: "https://1drv.ms/b/s!AhuEg_0yZD86hcpblUt-muHKYsG8fA?e=R8ogug"
+      tool_dev_url: "https://github.com/amplab/snap"
+      doi: "10.1101/2021.11.23.469039"
+      licence: "['Apache v2']"
+input:
+  - fasta:
+      type: file
+      description: Input genome fasta file
+  - altcontigfile:
+      type: file
+      description: Optional file with a list of alt contig names, one per line.
+  - nonaltcontigfile:
+      type: file
+      description: Optional file that contains a list of contigs (one per line) that will not be marked ALT regardless of size.
+  - altliftoverfile:
+      type: file
+      description: Optional file containing ALT-to-REF mappings (SAM format). e.g., hs38DH.fa.alt from bwa-kit.
+output:
+  - index:
+      type: file
+      description: SNAP genome index files
+      pattern: "{Genome,GenomeIndex,GenomeIndexHash,OverflowTable}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@matthdsm"

tests/config/pytest_modules.yml

@@ -1663,6 +1663,10 @@ sistr:
   - modules/sistr/**
   - tests/modules/sistr/**
 
+snapaligner/index:
+  - modules/snapaligner/index/**
+  - tests/modules/snapaligner/index/**
+
 snpdists:
   - modules/snpdists/**
   - tests/modules/snpdists/**

tests/modules/snapaligner/index/main.nf

@@ -0,0 +1,9 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SNAPALIGNER_INDEX } from '../../../../modules/snapaligner/index/main.nf'
+
+workflow test_snapaligner_index {
+    SNAPALIGNER_INDEX ( file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),[],[],[])
+}

tests/modules/snapaligner/index/nextflow.config

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

tests/modules/snapaligner/index/test.yml

@@ -0,0 +1,13 @@
+- name: snapaligner index test_snapaligner_index
+  command: nextflow run tests/modules/snapaligner/index -entry test_snapaligner_index -c tests/config/nextflow.config
+  tags:
+    - snapaligner/index
+    - snapaligner
+  files:
+    - path: output/snapaligner/snap/Genome
+      md5sum: 7e189c954142ba37460332b467e34ed4
+    - path: output/snapaligner/snap/GenomeIndex
+      md5sum: 298da8bcb1134f7b24379a792a7a46f8
+    - path: output/snapaligner/snap/GenomeIndexHash
+    - path: output/snapaligner/snap/OverflowTable
+    - path: output/snapaligner/versions.yml