🔀 Merge pull request #24 from cnr-ibba/issue-23

✨  add new module: seqkit/rmdup

modules/cnr-ibba/seqkit/rmdup/environment.yml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::seqkit=2.6.0

modules/cnr-ibba/seqkit/rmdup/main.nf

@@ -0,0 +1,56 @@
+process SEQKIT_RMDUP {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/seqkit:2.6.0--h9ee0642_0':
+        'quay.io/biocontainers/seqkit:2.6.0--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(sequence)
+
+    output:
+    tuple val(meta), path("*.{fa,fq}.gz")             , emit: unique
+    tuple val(meta), path("*.duplicated.detail.txt")  , emit: detail, optional: true
+    path "versions.yml"                               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    // fasta or fastq. Exact pattern match .fasta or .fa suffix with optional .gz (gzip) suffix
+    def suffix = task.ext.suffix ?: "${sequence}" ==~ /(.*f[astn]*a(.gz)?$)/ ? "fa" : "fq"
+
+    """
+    seqkit \\
+        rmdup \\
+        $args \\
+        --threads $task.cpus \\
+        ${sequence} \\
+        -o ${prefix}.${suffix}.gz \\
+        -D ${prefix}.duplicated.detail.txt \\
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqkit: \$( seqkit version | sed 's/seqkit v//' )
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    // fasta or fastq. Exact pattern match .fasta or .fa suffix with optional .gz (gzip) suffix
+    def suffix = task.ext.suffix ?: "${sequence}" ==~ /(.*f[astn]*a(.gz)?$)/ ? "fa" : "fq"
+    """
+    touch ${prefix}.${suffix}.gz
+    touch ${prefix}.duplicated.detail.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqkit: \$( seqkit version | sed 's/seqkit v//' )
+    END_VERSIONS
+    """
+}

modules/cnr-ibba/seqkit/rmdup/meta.yml

@@ -0,0 +1,56 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json
+name: "seqkit_rmdup"
+description: Remove duplicated sequences by ID/name/sequence
+keywords:
+  - filter
+  - set
+  - seqkit
+  - remove
+  - duplicates
+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.0163962"
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: >
+        Groovy Map containing sample information e.g. [ id:'test', single_end:false ]
+
+  - sequence:
+      type: file
+      description: >
+        Fasta or fastq file containing sequences to be filtered
+
+      pattern: "*.{fa,fna,faa,fasta,fq,fastq}[.gz]"
+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"
+  - unique:
+      type: file
+      description: >
+        Fasta or fastq file containing unique sequences
+
+      pattern: "*.{fa,fq}[.gz]"
+  - detail:
+      type: file
+      description: >
+        number and list of duplicated seqs
+
+      pattern: "*.duplicated.detail.txt"
+authors:
+  - "@bunop"
+maintainers:
+  - "@bunop"

tests/config/pytest_modules.yml

@@ -2411,6 +2411,10 @@ seqkit/replace:
   - modules/cnr-ibba/seqkit/replace/**
   - tests/modules/cnr-ibba/seqkit/replace/**
 
+seqkit/rmdup:
+  - modules/cnr-ibba/seqkit/rmdup/**
+  - tests/modules/cnr-ibba/seqkit/rmdup/**
+
 seqkit/split2:
   - modules/cnr-ibba/seqkit/split2/**
   - tests/modules/cnr-ibba/seqkit/split2/**

tests/modules/cnr-ibba/seqkit/rmdup/main.nf

@@ -0,0 +1,21 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQKIT_RMDUP } from '../../../../../modules/cnr-ibba/seqkit/rmdup/main.nf'
+
+workflow test_seqkit_rmdup {
+    input = [
+        [ id:'test' ],   // meta map
+        [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+    ]
+    SEQKIT_RMDUP ( input )
+}
+
+workflow test_seqkit_rmdup_fq {
+    input = [
+        [ id:'test' ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+    ]
+    SEQKIT_RMDUP ( input )
+}

tests/modules/cnr-ibba/seqkit/rmdup/nextflow.config

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

tests/modules/cnr-ibba/seqkit/rmdup/test.yml

@@ -0,0 +1,19 @@
+- name: seqkit rmdup test_seqkit_rmdup
+  command: nextflow run ./tests/modules/cnr-ibba/seqkit/rmdup -entry test_seqkit_rmdup -c ./tests/config/nextflow.config
+  tags:
+    - seqkit/rmdup
+    - seqkit
+  files:
+    - path: output/seqkit/test.fa.gz
+      md5sum: 62127df7a59139d8b16c2ea90c777ad2
+    - path: output/seqkit/versions.yml
+
+- name: seqkit rmdup test_seqkit_rmdup_fq
+  command: nextflow run ./tests/modules/cnr-ibba/seqkit/rmdup -entry test_seqkit_rmdup_fq -c ./tests/config/nextflow.config
+  tags:
+    - seqkit/rmdup
+    - seqkit
+  files:
+    - path: output/seqkit/test.fq.gz
+      md5sum: 994bc0f41ef4b198e0f2d99e1a8e9614
+    - path: output/seqkit/versions.yml