Trim3p nextflex

CHANGELOG.md

@@ -5,6 +5,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## v2.4.0dev - 2024-XX-XX - X
 
+- [[#365]](https://github.com/nf-core/smrnaseq/issues/365) by [[#386]](https://github.com/nf-core/smrnaseq/pull/386). Fix Nextflex trimming support.
 - [[#332]](https://github.com/nf-core/smrnaseq/issues/332) by [[#361]](https://github.com/nf-core/smrnaseq/pull/361) - Fix documentation to use only single-end
 - [[#349]](https://github.com/nf-core/smrnaseq/pull/349) - Fix [MIRTOP_QUANT conda issue](https://github.com/nf-core/smrnaseq/issues/347), change conda-base to conda-forge channel
 - [[#350]](https://github.com/nf-core/smrnaseq/pull/350) - Fix [MIRTOP_QUANT conda issue](https://github.com/nf-core/smrnaseq/issues/347), set python version to 3.7 to fix pysam issue

conf/modules.config

@@ -49,7 +49,7 @@ process {
         ext.args = [ "",
             params.trim_fastq                           ? "" : "--disable_adapter_trimming",
             params.clip_r1 > 0                          ? "--trim_front1 ${params.clip_r1}" : "", // Remove bp from the 5' end of read 1.
-            params.three_prime_clip_r1 > 0              ? "--trim_tail1 ${params.three_prime_clip_r1}" : "", // Remove bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed.
+        //    params.three_prime_clip_r1 > 0              ? "--trim_tail1 ${params.three_prime_clip_r1}" : "", // Remove bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed.
             params.fastp_min_length > 0                 ? "-l ${params.fastp_min_length}" : "",
             params.fastp_max_length > 0                 ? "--max_len1 ${params.fastp_max_length}" : "",
             params.three_prime_adapter == "auto-detect" ?  "" : "--adapter_sequence ${params.three_prime_adapter}"
@@ -73,6 +73,30 @@ process {
             ]
         ]
     }
+    //
+    // FASTQ_FASTQC_UMITOOLS_FASTP
+    //
+    withName: '.*:FASTP3' {
+        ext.args = [ "",
+            "--disable_adapter_trimming",
+            "--disable_quality_filtering",
+            params.three_prime_clip_r1 > 0              ? "--trim_tail1 ${params.three_prime_clip_r1}" : "", // Remove bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed.
+            params.fastp_min_length > 0                 ? "-l ${params.fastp_min_length}" : "",
+            params.fastp_max_length > 0                 ? "--max_len1 ${params.fastp_max_length}" : "",
+        ].join(" ").trim()
+        publishDir = [
+            [
+                path: { "${params.outdir}/fastp/on_raw" },
+                mode: params.publish_dir_mode,
+                pattern: "*.{json,html}"
+            ],
+            [
+                path: { "${params.outdir}/fastp/on_raw/log" },
+                mode: params.publish_dir_mode,
+                pattern: "*.log"
+            ]
+        ]
+    }
     withName: '.*:FASTQ_FASTQC_UMITOOLS_FASTP:FASTQC_RAW' {
         //the prefix is required for multiqc to pickup the files separately from the other fastqc instances
         ext.prefix =  { "${meta.id}.raw" }

conf/test_no_genome_nextflex.config

@@ -0,0 +1,33 @@
+/*
+========================================================================================
+    Nextflow config file for running minimal tests
+========================================================================================
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/smrnaseq -profile test,<docker/singularity>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input               = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/samplesheet/v2.0/samplesheet_test_nextflex.csv'
+    mature              = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/mature.fa'
+    hairpin             = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/hairpin.fa'
+    mirna_gtf           = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/hsa.gff3'
+    mirtrace_species    = 'hsa'
+
+}
+
+// Include nextflex config to run test without additional profiles
+
+includeConfig 'protocol_nextflex.config'

modules/local/trim3p.nf

@@ -0,0 +1,42 @@
+process FASTP3 {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fastp:0.23.4--h5f740d0_0' :
+        'biocontainers/fastp:0.23.4--h5f740d0_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path('*fastp3.fastq.gz') , optional:true, emit: reads
+    tuple val(meta), path('*.json')           , emit: json
+    tuple val(meta), path('*.html')           , emit: html
+    tuple val(meta), path('*.log')            , emit: log
+    path "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    fastp \\
+        --in1 ${reads} \\
+        --out1  ${prefix}.fastp3.fastq.gz \\
+        --thread $task.cpus \\
+        --json ${prefix}.fastp3.json \\
+        --html ${prefix}.fastp3.html \\
+        $args \\
+        2> >(tee ${prefix}.fastp3.log >&2)
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastp: \$(fastp --version 2>&1 | sed -e "s/fastp //g")
+    END_VERSIONS
+    """
+    }

nextflow.config

@@ -247,7 +247,7 @@ profiles {
     test_index                     { includeConfig 'conf/test_index.config' }
     test_technical_repeats         { includeConfig 'conf/test_technical_repeats.config' }
     test_mirgenedb                 { includeConfig 'conf/test_mirgenedb.config' }
-
+    test_no_genome_nextflex        { includeConfig 'conf/test_no_genome_nextflex.config' }
 
 
     //Protocol specific profiles

workflows/smrnaseq.nf

@@ -7,6 +7,7 @@ include { CAT_FASTQ                        } from '../modules/nf-core/cat/fastq/
 include { CONTAMINANT_FILTER               } from '../subworkflows/local/contaminant_filter'
 include { FASTQC                           } from '../modules/nf-core/fastqc/main'
 include { FASTQ_FASTQC_UMITOOLS_FASTP      } from '../subworkflows/nf-core/fastq_fastqc_umitools_fastp'
+include { FASTP3                           } from '../modules/local/trim3p.nf'
 include { FASTP as FASTP_LENGTH_FILTER     } from '../modules/nf-core/fastp'
 include { GENOME_QUANT                     } from '../subworkflows/local/genome_quant'
 include { INDEX_GENOME                     } from '../modules/local/bowtie_genome'
@@ -110,6 +111,14 @@ workflow NFCORE_SMRNASEQ {
 
     ch_fasta = params.fasta ? file(params.fasta): []
     ch_reads_for_mirna = FASTQ_FASTQC_UMITOOLS_FASTP.out.reads
+    // Trim 3' end nucleotides after adapter is removed, otherwise they are not really trimmed
+    if (params.three_prime_clip_r1){
+        FASTP3(
+            ch_reads_for_mirna
+        )
+        ch_reads_for_mirna  = FASTP3.out.reads
+        //trim_json         = FASTP3.out.json
+    }
 
     // even if bowtie index is specified, there still needs to be a fasta.
     // without fasta, no genome analysis.