Trim3p nextflex

CHANGELOG.md

@@ -19,6 +19,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#382]](https://github.com/nf-core/smrnaseq/pull/382) - Add [collapse_mirtop.R](https://github.com/nf-core/smrnaseq/issues/174) - Add nf-tests for local modules using custom R scripts.
 - [[#383]](https://github.com/nf-core/smrnaseq/pull/383) - Fix [parameter `--skip_fastp` throws an error](https://github.com/nf-core/smrnaseq/issues/263) - Fix parameter --skip_fastp.
 - [[#384]](https://github.com/nf-core/smrnaseq/pull/384) - Fix [filter status bug fix](https://github.com/nf-core/smrnaseq/issues/360) - Fix filter stats module and add filter contaminants test profile.
+- [[#386]](https://github.com/nf-core/smrnaseq/pull/386) - Fix [Nextflex trimming support](https://github.com/nf-core/smrnaseq/issues/365) - Fix Nextflex trimming support.
 - [[#387]](https://github.com/nf-core/smrnaseq/pull/387) - Add [contaminant filter failure because the Docker image for BLAT cannot be pulled](https://github.com/nf-core/smrnaseq/issues/354) - Add nf-test to local module `blat_mirna` and fixes . Adds a small test profile to test contaminant filter results.
 - [[#388]](https://github.com/nf-core/smrnaseq/pull/388) - Fix [igenomes fix](https://github.com/nf-core/smrnaseq/issues/360) - Fix workflow scripts so that they can use igenome parameters.
 - [[#391]](https://github.com/nf-core/smrnaseq/pull/391) - Fix [error because of large chromosomes](https://github.com/nf-core/smrnaseq/issues/132) - Change `.bai` index for `.csi` index in `samtools_index` to fix .

conf/modules.config

@@ -49,7 +49,6 @@ 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.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 ${params.three_prime_adapter}"
@@ -79,6 +78,31 @@ process {
             ]
         ]
     }
+    //
+    // FASTQ_FASTQC_UMITOOLS_FASTP
+    //
+    withName: '.*:FASTP3' {
+        ext.prefix =  { "${meta.id}.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_nextflex.config

@@ -0,0 +1,36 @@
+/*
+========================================================================================
+    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_nextflex,<docker/singularity>
+
+----------------------------------------------------------------------------------------
+*/
+// This test profile tests nextflex without genome
+
+params {
+    config_profile_name        = 'Nextflex 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://raw.githubusercontent.com/nf-core/test-datasets/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'
+
+    skip_mirdeep             = true
+
+}
+
+// Include nextflex config to run test without additional profiles
+
+includeConfig 'protocol_nextflex.config'

nextflow.config

@@ -248,6 +248,7 @@ profiles {
     test_contamination             { includeConfig 'conf/test_contamination.config' }
     test_contamination_tech_reps   { includeConfig 'conf/test_contamination_tech_reps.config' }
     test_skipfastp                 { includeConfig 'conf/test_skipfastp.config' }
+    test_nextflex                  { includeConfig 'conf/test_nextflex.config' }
 
 
     //Protocol specific profiles

subworkflows/local/prepare_genome/main.nf

@@ -34,7 +34,7 @@ workflow PREPARE_GENOME {
 
     ch_mirtrace_species       = val_mirtrace_species          ? Channel.value(val_mirtrace_species) : Channel.empty()
     mirna_gtf_from_species    = val_mirtrace_species          ? (val_mirtrace_species == 'hsa' ? "https://github.com/nf-core/test-datasets/raw/smrnaseq/miRBase/hsa.gff3" : "https://mirbase.org/download/CURRENT/genomes/${val_mirtrace_species}.gff3") : false
-    ch_mirna_gtf              = val_mirna_gtf                 ? Channel.empty() : ( mirna_gtf_from_species ? Channel.fromPath(mirna_gtf_from_species, checkIfExists: true).collect() :  Channel.empty() )    //TODO for ch_mirna_gtf, shouldn't it try to build a channel.fromPath with params.mirna_gtf,  if true? (instead of setting it to empty). Is this parameter used for non mirgenedb runs?
+    ch_mirna_gtf              = val_mirna_gtf                 ? Channel.fromPath(val_mirna_gtf, checkIfExists: true) : ( mirna_gtf_from_species ? Channel.fromPath(mirna_gtf_from_species, checkIfExists: true).collect() :  Channel.empty() )
     ch_mirna_adapters         = params.with_umi               ? [] : Channel.fromPath(val_fastp_known_mirna_adapters, checkIfExists: true).collect()
 
     ch_rrna                   = val_rrna                      ? Channel.fromPath(val_rrna)                : Channel.empty()

tests/test_nextflex.nf.test

@@ -0,0 +1,122 @@
+
+nextflow_pipeline {
+
+    name "Test Workflow main.nf - test_nextflex"
+    script "main.nf"
+    profile "test_nextflex"
+    tag "test_nextflex"
+    tag "pipeline"
+
+    test("test_nextflex") {
+
+        when {
+            params {
+                outdir = "$outputDir"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") },
+                { assert workflow.trace.succeeded().size() == 65 },
+
+                { assert snapshot(
+                    path("$outputDir/mirna_quant/bam/mature/sample2_mature.sorted.idxstats"),
+                    path("$outputDir/mirna_quant/bam/mature/sample1_mature.sorted.flagstat"),
+                    path("$outputDir/mirna_quant/bam/mature/sample2_mature.sorted.stats"),
+                    path("$outputDir/mirna_quant/bam/mature/sample3_mature.sorted.stats"),
+                    path("$outputDir/mirna_quant/bam/mature/sample3_mature.sorted.flagstat"),
+                    path("$outputDir/mirna_quant/bam/mature/sample3_mature.sorted.idxstats"),
+                    path("$outputDir/mirna_quant/bam/mature/sample1_mature.sorted.stats"),
+                    path("$outputDir/mirna_quant/bam/mature/sample2_mature.sorted.flagstat"),
+                    path("$outputDir/mirna_quant/bam/mature/sample1_mature.sorted.idxstats"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample3_mature_hairpin.sorted.stats"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample2_mature_hairpin.sorted.flagstat"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample1_mature_hairpin.sorted.flagstat"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample1_mature_hairpin.sorted.idxstats"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample3_mature_hairpin.sorted.flagstat"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample2_mature_hairpin.sorted.stats"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample1_mature_hairpin.sorted.stats"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample3_mature_hairpin.sorted.idxstats"),
+                    path("$outputDir/mirna_quant/bam/hairpin/sample2_mature_hairpin.sorted.idxstats")
+                ).match("mirna_quant_bam") },
+
+                { assert snapshot(
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_counts.csv").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_edgeR_MDS_plot_coordinates.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_edgeR_MDS_distance_matrix.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_log2CPM_sample_distances.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_logtpm.csv").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_logtpm.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_normalized_CPM.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_edgeR_MDS_plot_coordinates.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_edgeR_MDS_distance_matrix.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_counts.csv").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_log2CPM_sample_distances.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/hairpin_unmapped_read_counts.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_normalized_CPM.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_logtpm.csv").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_logtpm.txt").exists(),
+                    path("$outputDir/mirna_quant/edger_qc/mature_unmapped_read_counts.txt").exists()
+                ).match("mirna_quant_edger_qc") },
+
+                { assert snapshot(
+                    path("$outputDir/mirtrace/mirtrace-report.html").exists(),
+                    path("$outputDir/mirtrace/mirtrace-stats-contamination_basic.tsv"),
+                    path("$outputDir/mirtrace/mirtrace-stats-mirna-complexity.tsv"),
+                    path("$outputDir/mirtrace/mirtrace-stats-phred.tsv"),
+                    path("$outputDir/mirtrace/mirtrace-stats-length.tsv"),
+                    path("$outputDir/mirtrace/mirtrace-stats-contamination_detailed.tsv"),
+                    path("$outputDir/mirtrace/mirtrace-stats-qcstatus.tsv"),
+                    path("$outputDir/mirtrace/mirtrace-stats-rnatype.tsv")
+                ).match("mirtrace") },
+
+                { assert snapshot(
+                    path("$outputDir/multiqc/multiqc_data/fastqc-status-check-heatmap.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastp_filtered_reads_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_overrepresented_sequences_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_top_overrepresented_sequences_table-1.txt").exists(),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_sequence_counts_plot-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/mirtrace_complexity_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_sequence_gc_content_plot-1_Percentages.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_citations.txt"),
+                    path("$outputDir/multiqc/multiqc_data/samtools-stats-dp.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_sequence_length_distribution_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastp-seq-content-n-plot_Read_1_Before_filtering.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_sequence_duplication_levels_plot-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_base_sequence_quality_plot-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_general_stats.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_base_n_content_plot-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_base_n_content_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastp-seq-quality-plot_Read_1_After_filtering.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_sequence_quality_scores_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/mirtrace_qc_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_sequence_quality_scores_plot-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/mirtrace_length_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_top_overrepresented_sequences_table.txt").exists(),
+                    path("$outputDir/multiqc/multiqc_data/fastqc-status-check-heatmap-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_sequence_counts_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/mirtrace_rna_categories_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastp-seq-quality-plot_Read_1_Before_filtering.txt"),
+                    path("$outputDir/multiqc/multiqc_data/samtools_alignment_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_base_sequence_quality_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastp-seq-content-n-plot_Read_1_After_filtering.txt"),
+                    path("$outputDir/multiqc/multiqc_data/mirtrace_contamination_check_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_adapter_content_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_sequence_duplication_levels_plot.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_sequence_gc_content_plot_Percentages.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_sequence_gc_content_plot-1_Counts.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_adapter_content_plot-1.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastp-seq-content-gc-plot_Read_1_Before_filtering.txt"),
+                    path("$outputDir/multiqc/multiqc_data/fastqc_per_sequence_gc_content_plot_Counts.txt"),
+                    path("$outputDir/multiqc/multiqc_data/multiqc_sources.txt").exists(),
+                    path("$outputDir/multiqc/multiqc_data/fastp-seq-content-gc-plot_Read_1_After_filtering.txt")
+                ).match("multiqc_multiqc_data") },
+
+            )
+        }
+
+    }
+
+}