Add prinseq as alternative complexity filtering

2024-09-21 02:42:04 +00:00 · 2022-04-04 21:16:51 +02:00 · 2022-04-04 21:16:51 +02:00 · a384162810
commit a384162810
parent d3572e1878
8 changed files with 189 additions and 20 deletions
--- a/CITATIONS.md
+++ b/CITATIONS.md
@ -18,23 +18,27 @@

 - [fastp](https://doi.org/10.1093/bioinformatics/bty560)

-  > Chen, Shifu, Yanqing Zhou, Yaru Chen, and Jia Gu. 2018. “Fastp: An Ultra-Fast All-in-One FASTQ Preprocessor.” Bioinformatics 34 (17): i884-90. 10.1093/bioinformatics/bty560.
+  > Chen, Shifu, Yanqing Zhou, Yaru Chen, and Jia Gu. 2018. Fastp: An Ultra-Fast All-in-One FASTQ Preprocessor. Bioinformatics 34 (17): i884-90. 10.1093/bioinformatics/bty560.

 - [AdapterRemoval2](https://doi.org/10.1186/s13104-016-1900-2)

-  > Schubert, Mikkel, Stinus Lindgreen, and Ludovic Orlando. 2016. “AdapterRemoval v2: Rapid Adapter Trimming, Identification, and Read Merging.” BMC Research Notes 9 (February): 88. doi:10.1186/s13104-016-1900-2.
+  > Schubert, Mikkel, Stinus Lindgreen, and Ludovic Orlando. 2016. AdapterRemoval v2: Rapid Adapter Trimming, Identification, and Read Merging. BMC Research Notes 9 (February): 88. doi:10.1186/s13104-016-1900-2.

 - [Porechop](https://github.com/rrwick/Porechop)

 - [BBTools](http://sourceforge.net/projects/bbmap/)

+- [PRINSEQ++](https://doi.org/10.7287/peerj.preprints.27553v1)
+
+  > Cantu, Vito Adrian, Jeffrey Sadural, and Robert Edwards. 2019. PRINSEQ++, a Multi-Threaded Tool for Fast and Efficient Quality Control and Preprocessing of Sequencing Datasets. e27553v1. PeerJ Preprints. doi: 10.7287/peerj.preprints.27553v1.
+
 - [Kraken2](https://doi.org/10.1186/s13059-019-1891-0)

-  > Wood, Derrick E., Jennifer Lu, and Ben Langmead. 2019. “Improved Metagenomic Analysis with Kraken 2.” Genome Biology 20 (1): 257. doi: 10.1186/s13059-019-1891-0.
+  > Wood, Derrick E., Jennifer Lu, and Ben Langmead. 2019. Improved Metagenomic Analysis with Kraken 2. Genome Biology 20 (1): 257. doi: 10.1186/s13059-019-1891-0.

 - [MALT](https://doi.org/10.1038/s41559-017-0446-6)

-  > Vågene, Åshild J., Alexander Herbig, Michael G. Campana, Nelly M. Robles García, Christina Warinner, Susanna Sabin, Maria A. Spyrou, et al. 2018. “Salmonella Enterica Genomes from Victims of a Major Sixteenth-Century Epidemic in Mexico.” Nature Ecology & Evolution 2 (3): 520-28. doi: 10.1038/s41559-017-0446-6.
+  > Vågene, Åshild J., Alexander Herbig, Michael G. Campana, Nelly M. Robles García, Christina Warinner, Susanna Sabin, Maria A. Spyrou, et al. 2018. Salmonella Enterica Genomes from Victims of a Major Sixteenth-Century Epidemic in Mexico. Nature Ecology & Evolution 2 (3): 520-28. doi: 10.1038/s41559-017-0446-6.

 ## Software packaging/containerisation tools

--- a/conf/modules.config
+++ b/conf/modules.config
@ -143,7 +143,7 @@ process {

    withName: BBMAP_BBDUK {
        ext.args =  [
-                "entropy=${params.shortread_complexityfilter_bbduk_entropy}",
+                "entropy=${params.shortread_complexityfilter_entropy}",
                "entropywindow=${params.shortread_complexityfilter_bbduk_windowsize}",
                params.shortread_complexityfilter_bbduk_mask ?  "entropymask=t" : "entropymask=f"
            ].join(' ').trim()
@ -155,6 +155,19 @@ process {
        ]
    }

+    withName: PRINSEQPLUSPLUS {
+        ext.args =  [
+                params.shortread_complexityfilter_prinseqplusplus_mode == 'dust' ? "-lc_dust=${params.shortread_complexityfilter_prinseqplusplus_dustscore}" : "-lc_entropy=${params.shortread_complexityfilter_entropy}",
+                "-trim_qual_left=0 -trim_qual_left=0 -trim_qual_window=0 -trim_qual_step=0"
+            ].join(' ').trim()
+        ext.prefix = { "${meta.id}-${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/prinseqplusplus/" },
+            mode: params.publish_dir_mode,
+            pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz,log}'
+        ]
+    }
+
    withName: MALT_RUN {
        ext.args = { "${meta.db_params}" }
        ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
--- a/modules.json
+++ b/modules.json
@ -33,6 +33,9 @@
            "porechop": {
                "git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
            },
+            "prinseqplusplus": {
+                "git_sha": "f1c5384c31e985591716afdd732cf8c2ae29d05b"
+            },
            "untar": {
                "git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918"
            }
--- a/modules/nf-core/modules/prinseqplusplus/main.nf
+++ b/modules/nf-core/modules/prinseqplusplus/main.nf
@ -0,0 +1,61 @@
+process PRINSEQPLUSPLUS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::prinseq-plus-plus=1.2.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/prinseq-plus-plus:1.2.3--hc90279e_1':
+        'quay.io/biocontainers/prinseq-plus-plus:1.2.3--hc90279e_1' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*_good_out*.fastq.gz")                  , emit: good_reads
+    tuple val(meta), path("*_single_out*.fastq.gz"), optional: true, emit: single_reads
+    tuple val(meta), path("*_bad_out*.fastq.gz")   , optional: true, emit: bad_reads
+    tuple val(meta), path("*.log")                                 , emit: log
+    path "versions.yml"                                            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    if (meta.single_end) {
+        """
+        prinseq++ \\
+            -threads $task.cpus \\
+            -fastq ${reads} \\
+            -out_name ${prefix} \\
+            -out_gz \\
+            -VERBOSE 1 \\
+            $args \\
+            | tee ${prefix}.log
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            prinseqplusplus: \$(echo \$(prinseq++ --version | cut -f 2 -d ' ' ))
+        END_VERSIONS
+        """
+    } else {
+        """
+        prinseq++ \\
+            -threads $task.cpus \\
+            -fastq ${reads[0]} \\
+            -fastq2 ${reads[1]} \\
+            -out_name ${prefix} \\
+            -out_gz \\
+            -VERBOSE 1 \\
+            $args \\
+            | tee ${prefix}.log
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            prinseqplusplus: \$(echo \$(prinseq++ --version | cut -f 2 -d ' ' ))
+        END_VERSIONS
+        """
+    }
+}
--- a/modules/nf-core/modules/prinseqplusplus/meta.yml
+++ b/modules/nf-core/modules/prinseqplusplus/meta.yml
@ -0,0 +1,60 @@
+name: "prinseqplusplus"
+description: PRINSEQ++ is a C++ implementation of the prinseq-lite.pl program. It can be used to filter, reformat or trim genomic and metagenomic sequence data
+keywords:
+  - fastq
+  - fasta
+  - filter
+  - trim
+tools:
+  - "prinseqplusplus":
+      description: "PRINSEQ++ - Multi-threaded C++ sequence cleaning"
+      homepage: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
+      documentation: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
+      tool_dev_url: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
+      doi: "10.7287/peerj.preprints.27553v1"
+      licence: "['GPL v2']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end
+        data, respectively.
+
+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"
+  - good_reads:
+      type: file
+      description: Reads passing filter(s) in gzipped FASTQ format
+      pattern: "*_good_out_{R1,R2}.fastq.gz"
+  - single_reads:
+      type: file
+      description: |
+        Single reads without the pair passing filter(s) in gzipped FASTQ format
+      pattern: "*_single_out_{R1,R2}.fastq.gz"
+  - bad_reads:
+      type: file
+      description: |
+        Reads without not passing filter(s) in gzipped FASTQ format
+      pattern: "*_bad_out_{R1,R2}.fastq.gz"
+  - log:
+      type: file
+      description: |
+        Verbose level 2 STDOUT information in a log file
+      pattern: "*.log"
+
+authors:
+  - "@jfy133"
--- a/nextflow.config
+++ b/nextflow.config
@ -66,11 +66,14 @@ params {
    longread_clip                           = false

    // Complexity filtering
-    shortread_complexityfilter                  = false
-    shortread_complexityfilter_tool             = 'bbduk'
-    shortread_complexityfilter_bbduk_entropy    = 0.3
-    shortread_complexityfilter_bbduk_windowsize = 50
-    shortread_complexityfilter_bbduk_mask       = false
+    shortread_complexityfilter                           = false
+    shortread_complexityfilter_tool                      = 'bbduk'
+    shortread_complexityfilter_entropy                   = 0.3
+    shortread_complexityfilter_bbduk_windowsize          = 50
+    shortread_complexityfilter_bbduk_mask                = false
+    shortread_complexityfilter_prinseqplusplus_mode      = 'entropy'
+    shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
+

    // MALT
    run_malt                   = false
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@ -10,7 +10,10 @@
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
-            "required": ["input", "outdir"],
+            "required": [
+                "input",
+                "outdir"
+            ],
            "properties": {
                "input": {
                    "type": "string",
@ -173,7 +176,14 @@
                    "description": "Method used to save pipeline results to output directory.",
                    "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                    "fa_icon": "fas fa-copy",
-                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
+                    "enum": [
+                        "symlink",
+                        "rellink",
+                        "link",
+                        "copy",
+                        "copyNoFollow",
+                        "move"
+                    ],
                    "hidden": true
                },
                "email_on_fail": {
@ -284,7 +294,10 @@
        "shortread_clipmerge_tool": {
            "type": "string",
            "default": "fastp",
-            "enum": ["fastp", "adapterremoval"]
+            "enum": [
+                "fastp",
+                "adapterremoval"
+            ]
        },
        "shortread_clipmerge_skipadaptertrim": {
            "type": "boolean"
@ -308,10 +321,6 @@
            "type": "string",
            "default": "bbduk"
        },
-        "shortread_complexityfilter_bbduk_entropy": {
-            "type": "number",
-            "default": 0.3
-        },
        "shortread_complexityfilter_bbduk_windowsize": {
            "type": "integer",
            "default": 50
@ -321,6 +330,18 @@
        },
        "shortread_complexityfilter": {
            "type": "boolean"
+        },
+        "shortread_complexityfilter_entropy": {
+            "type": "number",
+            "default": 0.3
+        },
+        "shortread_complexityfilter_prinseqplusplus_mode": {
+            "type": "string",
+            "default": "entropy"
+        },
+        "shortread_complexityfilter_prinseqplusplus_dustscore": {
+            "type": "number",
+            "default": 0.5
        }
    }
 }
--- a/subworkflows/local/shortread_complexityfiltering.nf
+++ b/subworkflows/local/shortread_complexityfiltering.nf
@ -2,7 +2,8 @@
 // Check input samplesheet and get read channels
 //

-include { BBMAP_BBDUK } from '../../modules/nf-core/modules/bbmap/bbduk/main'
+include { BBMAP_BBDUK     } from '../../modules/nf-core/modules/bbmap/bbduk/main'
+include { PRINSEQPLUSPLUS } from '../../modules/nf-core/modules/prinseqplusplus/main'

 workflow SHORTREAD_COMPLEXITYFILTERING {
    take:
@ -16,6 +17,9 @@ workflow SHORTREAD_COMPLEXITYFILTERING {
        ch_filtered_reads = BBMAP_BBDUK ( reads, [] ).reads
        ch_versions        =  ch_versions.mix( BBMAP_BBDUK.out.versions.first() )
        ch_multiqc_files   =  ch_multiqc_files.mix( BBMAP_BBDUK.out.log )
+    } else if ( params.shortread_complexityfilter_tool == 'prinseqplusplus' ) {
+        ch_filtered_reads = PRINSEQPLUSPLUS ( reads ).good_reads
+        ch_versions        =  ch_versions.mix( PRINSEQPLUSPLUS.out.versions.first() )
    } else {
        ch_filtered_reads = reads
    }