New module: fasta_windows (#1956)

* New module for fasta_windows

* Upgraded the code and the test to v2.4

* Standard list of Fasta file extensions

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

* Output file (and/or directory) names SHOULD just consist of only ${prefix}

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

modules/fastawindows/main.nf

@@ -0,0 +1,40 @@
+process FASTAWINDOWS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::fasta_windows=0.2.4" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fasta_windows:0.2.4--hec16e2b_0':
+        'quay.io/biocontainers/fasta_windows:0.2.4--hec16e2b_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("fw_out/*_freq_windows.tsv")    , emit: freq
+    tuple val(meta), path("fw_out/*_mononuc_windows.tsv") , emit: mononuc
+    tuple val(meta), path("fw_out/*_dinuc_windows.tsv")   , emit: dinuc
+    tuple val(meta), path("fw_out/*_trinuc_windows.tsv")  , emit: trinuc
+    tuple val(meta), path("fw_out/*_tetranuc_windows.tsv"), emit: tetranuc
+    path "versions.yml"                                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    rm -rf fw_out
+    env RAYON_NUM_THREADS=$task.cpus \\
+    fasta_windows \\
+        $args \\
+        --fasta $fasta \\
+        --output ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fasta_windows: \$(fasta_windows --version | cut -d' ' -f3)
+    END_VERSIONS
+    """
+}

modules/fastawindows/meta.yml

@@ -0,0 +1,57 @@
+name: "fastawindows"
+description: Quickly compute statistics over a fasta file in windows.
+keywords:
+  - genome
+  - fasta
+  - tsv
+  - bed
+tools:
+  - "fastawindows":
+      description: "fasta_windows is a tool written for Darwin Tree of Life chromosomal level genome assemblies. The executable takes a fasta formatted file and calculates some statistics of interest in windows"
+      homepage: "https://github.com/tolkit/fasta_windows"
+      documentation: "None"
+      licence: "['MIT']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: FASTA file
+      pattern: "*.{fa,fasta,fna}"
+
+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"
+  - freq:
+      type: file
+      description: TSV file with frequencies and statistics
+      pattern: "*.{tsv}"
+  - mononuc:
+      type: file
+      description: TSV file with mononucleotide counts
+      pattern: "*.{tsv}"
+  - dinuc:
+      type: file
+      description: TSV file with dinucleotide counts
+      pattern: "*.{tsv}"
+  - trinuc:
+      type: file
+      description: TSV file with trinucleotide counts
+      pattern: "*.{tsv}"
+  - tetranuc:
+      type: file
+      description: TSV file with tetranucleotide counts
+      pattern: "*.{tsv}"
+authors:
+  - "@muffato"

tests/config/pytest_modules.yml

@@ -739,6 +739,10 @@ fastani:
   - modules/fastani/**
   - tests/modules/fastani/**
 
+fastawindows:
+  - modules/fastawindows/**
+  - tests/modules/fastawindows/**
+
 fastk/fastk:
   - modules/fastk/fastk/**
   - tests/modules/fastk/fastk/**

tests/modules/fastawindows/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { FASTAWINDOWS } from '../../../modules/fastawindows/main.nf'
+
+workflow test_fastawindows {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    FASTAWINDOWS ( input )
+}

tests/modules/fastawindows/nextflow.config

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

tests/modules/fastawindows/test.yml

@@ -0,0 +1,15 @@
+- name: fastawindows test_fastawindows
+  command: nextflow run ./tests/modules/fastawindows -entry test_fastawindows -c ./tests/config/nextflow.config  -c ./tests/modules/fastawindows/nextflow.config
+  tags:
+    - fastawindows
+  files:
+    - path: output/fastawindows/fw_out/test_freq_windows.tsv
+      md5sum: 237d50ac5ec2bef3142020d569fa5765
+    - path: output/fastawindows/fw_out/test_mononuc_windows.tsv
+      md5sum: a1b4437d0c71d9cfd676de6bda2633f0
+    - path: output/fastawindows/fw_out/test_dinuc_windows.tsv
+      md5sum: 696a9f2a4b2114dfbd6b414694f56a11
+    - path: output/fastawindows/fw_out/test_trinuc_windows.tsv
+      md5sum: dfb05b758f0474e937e2d6ba6fe46dae
+    - path: output/fastawindows/fw_out/test_tetranuc_windows.tsv
+      md5sum: e621537175ee8019360f8b6e8f4330b7