Adding seqkit sliding command (nf-core#3637)

* Adding seqkit sliding command

* Linting fix

* Updating for better matching

* reverted to regex using end line markers for better matching other wise fastq gets caught by fa, error in other modules

* Added a test for fastq too

---------

Co-authored-by: Matthieu Muffato <[email protected]>

modules/nf-core/seqkit/sliding/main.nf

@@ -0,0 +1,40 @@
+process SEQKIT_SLIDING {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "bioconda::seqkit=2.1.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/seqkit:2.1.0--h9ee0642_0':
+        'biocontainers/seqkit:2.1.0--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(fastx)
+
+    output:
+    tuple val(meta), path("*.fast*"), emit: fastx
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def extension = "fastq"
+    if ("$fastx" ==~ /.+\.fasta$|.+\.fa$|.+\.fas$|.+\.fna$/) {
+        extension = "fasta"
+    }
+    """
+    seqkit \\
+        sliding \\
+        ${fastx} \\
+        ${args} \\
+        --threads ${task.cpus} \\
+        -o ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqkit: \$( seqkit | sed '3!d; s/Version: //' )
+    END_VERSIONS
+    """
+}

modules/nf-core/seqkit/sliding/meta.yml

@@ -0,0 +1,42 @@
+name: seqkit_sliding
+description: Use seqkit to generate sliding windows of input fasta
+keywords:
+  - seqkit
+  - sliding
+  - windows
+tools:
+  - seqkit:
+      description: Cross-platform and ultrafast toolkit for FASTA/Q file manipulation, written by Wei Shen.
+      homepage: https://bioinf.shenwei.me/seqkit/usage/
+      documentation: https://bioinf.shenwei.me/seqkit/usage/
+      tool_dev_url: https://github.com/shenwei356/seqkit/
+      doi: "10.1371/journal.pone.016396"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fastx:
+      type: file
+      description: fasta/q file
+      pattern: "*.{fasta,fastq,fa,fq,fas,fna,faa}*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - windows:
+      type: file
+      description: fasta/q window file
+      pattern: "*.{fasta,fastq,fa,fq,fas,fna,faa}*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@DLBPointon"

tests/config/pytest_modules.yml

@@ -3259,6 +3259,10 @@ seqkit/replace:
   - modules/nf-core/seqkit/replace/**
   - tests/modules/nf-core/seqkit/replace/**
 
+seqkit/sliding:
+  - modules/nf-core/seqkit/sliding/**
+  - tests/modules/nf-core/seqkit/sliding/**
+
 seqkit/split2:
   - modules/nf-core/seqkit/split2/**
   - tests/modules/nf-core/seqkit/split2/**

tests/modules/nf-core/seqkit/sliding/main.nf

@@ -0,0 +1,25 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQKIT_SLIDING                            } from '../../../../../modules/nf-core/seqkit/sliding/main.nf'
+
+workflow test_seqkit_sliding_fasta {
+
+    input = [ [ id:'test' ],   // meta map
+              [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+            ]
+
+    SEQKIT_SLIDING ( input )
+
+}
+
+workflow test_seqkit_sliding_fastq {
+
+    input = [ [ id:'test' ],   // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+            ]
+
+    SEQKIT_SLIDING ( input )
+
+}

tests/modules/nf-core/seqkit/sliding/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    withName: 'SEQKIT_SLIDING' {
+        ext.args        = "-s 2 -W 5"
+        publishDir      = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    }
+}

tests/modules/nf-core/seqkit/sliding/test.yml

@@ -0,0 +1,18 @@
+- name: seqkit sliding test_seqkit_sliding_fasta
+  command: nextflow run ./tests/modules/nf-core/seqkit/sliding -entry test_seqkit_sliding_fasta -c ./tests/config/nextflow.config
+  tags:
+    - seqkit/sliding
+    - seqkit
+  files:
+    - path: output/seqkit/test.fasta
+      md5sum: d5e112b55c37bef1f16f28ba16b323dd
+    - path: output/seqkit/versions.yml
+- name: seqkit sliding test_seqkit_sliding_fastq
+  command: nextflow run ./tests/modules/nf-core/seqkit/sliding -entry test_seqkit_sliding_fastq -c ./tests/config/nextflow.config
+  tags:
+    - seqkit/sliding
+    - seqkit
+  files:
+    - path: output/seqkit/test.fastq
+      md5sum: 59f475cac6d2c372ce2d3a1e3c40305b
+    - path: output/seqkit/versions.yml