Feat seqtk update (#503)

* hifiasm copied from fastqc

* hifiasm tests init from fastqc

* meta.yml init; test.yml and main.nf for printing version

* Add hifiasm version printing

* Removed spaced on an empty line

* Reverted hifiasm from main

* hifiasm copied from fastqc

* hifiasm tests init from fastqc

* meta.yml init; test.yml and main.nf for printing version

* Add hifiasm version printing

* Removed spaced on an empty line

* Reverted hifiasm from main

* Added seqtk/subseq and checking for seed in seqtk/sample

* Separate authors in software/seqtk/sample/meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Align commans in output channesl software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Define prefix in software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Use prefix in output file name software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Define suffix in options in tests/software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Change output file name in tests/software/seqtk/subseq/test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Remove a to-do point from tests/software/seqtk/subseq/test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Added --no-name into gzip commands

* Update samtools from 1.10 to 1.12 (#530)

* feat: remove social preview image to use GitHub OpenGraph

* feat: update samtools from 1.10 to 1.12

* fix: CI tests

* fix: add meta.yml file for samtools/merge

* Update software/samtools/merge/meta.yml

Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>

* Update software/samtools/merge/meta.yml

Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>

* hifiasm copied from fastqc

* hifiasm tests init from fastqc

* meta.yml init; test.yml and main.nf for printing version

* Add hifiasm version printing

* Removed spaced on an empty line

* Reverted hifiasm from main

* Added seqtk/subseq and checking for seed in seqtk/sample

* hifiasm copied from fastqc

* hifiasm tests init from fastqc

* meta.yml init; test.yml and main.nf for printing version

* Add hifiasm version printing

* Removed spaced on an empty line

* Reverted hifiasm from main

* Separate authors in software/seqtk/sample/meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Align commans in output channesl software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Define prefix in software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Use prefix in output file name software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Define suffix in options in tests/software/seqtk/subseq/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Change output file name in tests/software/seqtk/subseq/test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Remove a to-do point from tests/software/seqtk/subseq/test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Added --no-name into gzip commands

* Replaced functions.nf in seqtk/subseq

* Refreshed tests for sample and subseq

* Corrected paired-end test and YAML description for sample

Co-authored-by: Sviatoslav Sidorov <sviatoslav.sidorov@crick.ac.uk>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: Maxime U. Garcia <max.u.garcia@gmail.com>
Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>

software/seqtk/sample/main.nf

@@ -36,25 +36,28 @@ process SEQTK_SAMPLE {
             $options.args \\
             $reads \\
             $sample_size \\
-            | gzip > ${prefix}.fastq.gz \\
+            | gzip --no-name > ${prefix}.fastq.gz \\
 
         echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//' > ${software}.version.txt
         """
     } else {
+        if (!(options.args ==~ /.*-s[0-9]+.*/)) {
+            options.args = options.args + " -s100"
+        }
         """
         seqtk \\
             sample \\
             $options.args \\
-            $reads[0] \\
+            ${reads[0]} \\
             $sample_size \\
-            | gzip > ${prefix}_1.fastq.gz \\
+            | gzip --no-name > ${prefix}_1.fastq.gz \\
 
         seqtk \\
             sample \\
             $options.args \\
-            $reads[1] \\
+            ${reads[1]} \\
             $sample_size \\
-            | gzip > ${prefix}_2.fastq.gz \\
+            | gzip --no-name > ${prefix}_2.fastq.gz \\
 
         echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//' > ${software}.version.txt
         """

software/seqtk/sample/meta.yml

@@ -7,6 +7,7 @@ tools:
       description: Seqtk is a fast and lightweight tool for processing sequences in the FASTA or FASTQ format. Seqtk sample command subsamples sequences.
       homepage: https://github.com/lh3/seqtk
       documentation: https://docs.csc.fi/apps/seqtk/
+      tool_dev_url: https://github.com/lh3/seqtk
       licence: ['MIT']
 
 input:
@@ -19,6 +20,9 @@ input:
       type: file
       description: List of input FastQ files of size 1 and 2 for single-end and paired-end data,respectively.
       pattern: "*.{fastq.gz}"
+  - sample_size:
+      type: value
+      description: Number of reads to sample.
 
 output:
   - meta:
@@ -32,8 +36,9 @@ output:
       pattern: "*.{version.txt}"
   - reads:
       type: file
-      description: Subsampled FastQ files of size 1 and 2 for single-end and paired-end data,respectively.
+      description: Subsampled FastQ files, 1 for single-end data or 2 for paired-end data.
       pattern: "*.{fastq.gz}"
 
 authors:
   - "@kaurravneet4123"
+  - "@sidorov-si"

software/seqtk/subseq/functions.nf

@@ -0,0 +1,68 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                    }
+                    path = path instanceof String ? path : ''
+                    path_list.add(path)
+                }
+            }
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/seqtk/subseq/main.nf

@@ -0,0 +1,46 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SEQTK_SUBSEQ {
+    tag '$sequences'
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) }
+
+    conda (params.enable_conda ? "bioconda::seqtk=1.3" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/seqtk:1.3--h5bf99c6_3"
+    } else {
+        container "quay.io/biocontainers/seqtk:1.3--h5bf99c6_3"
+    }
+
+    input:
+    path sequences
+    path filter_list
+
+    output:
+    path "*.gz"         , emit: sequences
+    path "*.version.txt", emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ?: ''
+    def ext = "fa"
+    if ("$sequences" ==~ /.+\.fq|.+\.fq.gz|.+\.fastq|.+\.fastq.gz/) {
+        ext = "fq"
+    }
+    """
+    seqtk \\
+        subseq \\
+        $options.args \\
+        $sequences \\
+        $filter_list | \\
+        gzip --no-name > ${sequences}${prefix}.${ext}.gz
+
+    echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//' > ${software}.version.txt
+    """
+}

software/seqtk/subseq/meta.yml

@@ -0,0 +1,34 @@
+name: seqtk_subseq
+description: Select only sequences that match the filtering condition
+keywords:
+  - filtering,selection
+tools:
+  - seqtk:
+      description: Seqtk is a fast and lightweight tool for processing sequences in the FASTA or FASTQ format
+      homepage: https://github.com/lh3/seqtk
+      documentation: https://docs.csc.fi/apps/seqtk/
+      tool_dev_url: https://github.com/lh3/seqtk
+      licence: ['MIT']
+
+input:
+  - sequences:
+      type: file
+      description: FASTQ/FASTA file
+      pattern: "*.{fq,fq.gz,fa,fa.gz}"
+  - filter_list:
+      type: file
+      description: BED file or a text file with a list of sequence names
+      pattern: "*.{bed,lst}"
+
+output:
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - sequences:
+      type: file
+      description: FASTQ/FASTA file
+      pattern: "*.{fq.gz,fa.gz}"
+
+authors:
+  - "@sidorov-si"

tests/config/pytest_software.yml

@@ -639,6 +639,10 @@ seqtk/sample:
   - software/seqtk/sample/**
   - tests/software/seqtk/sample/**
 
+seqtk/subseq:
+  - software/seqtk/subseq/**
+  - tests/software/seqtk/subseq/**
+
 sequenzautils/bam2seqz:
   - software/sequenzautils/bam2seqz/**
   - tests/software/sequenzautils/bam2seqz/**

tests/software/seqtk/sample/main.nf

@@ -12,7 +12,7 @@ workflow test_seqtk_sample_single_end {
     input = [ [ id:'test', single_end:true ], // meta map
               file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
 
-    SEQTK_SAMPLE ( input, 250000 )
+    SEQTK_SAMPLE ( input, 50 )
 }
 
 //
@@ -25,5 +25,5 @@ workflow test_seqtk_sample_paired_end {
                 file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
             ]
 
-    SEQTK_SAMPLE ( input, 250000 )
+    SEQTK_SAMPLE ( input, 50 )
 }

tests/software/seqtk/sample/test.yml

@@ -1,19 +1,19 @@
-- name: seqtk sample single-end
+- name: seqtk sample test_seqtk_sample_single_end
-  command: nextflow run ./tests/software/seqtk/sample -entry test_seqtk_sample_single_end -c tests/config/nextflow.config
+  command: nextflow run tests/software/seqtk/sample -entry test_seqtk_sample_single_end -c tests/config/nextflow.config
   tags:
     - seqtk
     - seqtk/sample
   files:
     - path: output/seqtk/test.sampled.fastq.gz
-      md5sum: 875863b402f67403dac63ef59b9c9a8a
+      md5sum: 73c3e8f113860244f3ed3866a8b9d555
 
-- name: seqtk sample paired-end
+- name: seqtk sample test_seqtk_sample_paired_end
-  command: nextflow run ./tests/software/seqtk/sample -entry test_seqtk_sample_paired_end -c tests/config/nextflow.config
+  command: nextflow run tests/software/seqtk/sample -entry test_seqtk_sample_paired_end -c tests/config/nextflow.config
   tags:
     - seqtk
     - seqtk/sample
   files:
     - path: output/seqtk/test.sampled_1.fastq.gz
-      md5sum: 7029066c27ac6f5ef18d660d5741979a
+      md5sum: 73c3e8f113860244f3ed3866a8b9d555
     - path: output/seqtk/test.sampled_2.fastq.gz
-      md5sum: 7029066c27ac6f5ef18d660d5741979a
+      md5sum: 75457ddceea3a5688d05438cdbffba24

tests/software/seqtk/subseq/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQTK_SUBSEQ } from '../../../../software/seqtk/subseq/main.nf' addParams( options: ['suffix':'.filtered'] )
+
+workflow test_seqtk_subseq {
+    
+    sequences = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+
+    filter_list = file(params.test_data['sarscov2']['genome']['test_bed_gz'], checkIfExists: true)
+
+    SEQTK_SUBSEQ ( sequences, filter_list )
+}

tests/software/seqtk/subseq/test.yml

@@ -0,0 +1,8 @@
+- name: seqtk subseq test_seqtk_subseq
+  command: nextflow run tests/software/seqtk/subseq -entry test_seqtk_subseq -c tests/config/nextflow.config
+  tags:
+    - seqtk
+    - seqtk/subseq
+  files:
+    - path: output/seqtk/genome.fasta.filtered.fa.gz
+      md5sum: 488001c0fbedabf24d3e10fe7f96c78a