output fastq.gz during trimming

main.nf

@@ -74,8 +74,8 @@ workflow {
             .flatMap { library, fq_files ->                 
                 def fq_list = fq_files instanceof List ? fq_files : [fq_files]
 
-                fq_list.findAll { it.baseName.contains('.1.trimmed') }.collect { fq1 ->
-                    def chunk_name = fq1.baseName.split(".1.trimmed")[0]
+                fq_list.findAll { it.baseName.contains('.1.trimmed.fastq') }.collect { fq1 ->
+                    def chunk_name = fq1.baseName.split(".1.trimmed.fastq")[0]
                     [library, chunk_name, fq1]
                 }
             }
@@ -85,18 +85,17 @@ workflow {
             .flatMap { library, fq_files ->
                 def fq_list = fq_files instanceof List ? fq_files : [fq_files]                
                 def chunk_groups = fq_list.groupBy { 
-                    it.baseName.replaceAll(/\.[12]\.trimmed$/, '') 
+                    it.baseName.replaceAll(/\.[12]\.trimmed\.fastq$/, '') 
                 }
 
                 chunk_groups.collect { chunk_prefix, files ->
-                    def r1 = files.find { it.baseName.contains('.1.trimmed') }
-                    def r2 = files.find { it.baseName.contains('.2.trimmed') }
+                    def r1 = files.find { it.baseName.contains('.1.trimmed.fastq') }
+                    def r2 = files.find { it.baseName.contains('.2.trimmed.fastq') }
 
                     [library, chunk_prefix, [r1, r2]]
                 }
             }
         }
-
         alignReads( passed_bams.combine(fastq_chunks, by:0), params.reference_list.bwa_index )
         mergeAndMarkDuplicates( alignReads.out.bam_files.groupTuple() )
         md_bams = mergeAndMarkDuplicates.out.md_bams

modules/fastp.nf

@@ -8,13 +8,13 @@ process fastp {
         tuple val(library), path(bam)
 
     output:
-        tuple val(library), path("*.trimmed.fastq"), emit: trimmed_fastq
+        tuple val(library), path("*.trimmed.fastq.gz"), emit: trimmed_fastq
         tuple val(library), path("${library}.fastp.json"), emit: fastp_json
         tuple val("${task.process}"), val('samtools'), eval('samtools --version | head -n 1 | sed \'s/^samtools //\''), topic: versions
         tuple val("${task.process}"), val('fastp'), eval('fastp --version 2>&1 | cut -f 2 -d " "'), topic: versions
 
     script:
-    def fastp_args = params.single_end ? "--out1 ${library}.1.trimmed.fastq" : "--interleaved_in --out1 ${library}.1.trimmed.fastq --out2 ${library}.2.trimmed.fastq"
+    def fastp_args = params.single_end ? "--out1 ${library}.1.trimmed.fastq.gz" : "--interleaved_in --out1 ${library}.1.trimmed.fastq.gz --out2 ${library}.2.trimmed.fastq.gz"
     """
     set +o pipefail
     inst_name=\$(samtools view ${bam} | head -n 1 | cut -d ":" -f 1)

modules/multiqc.nf

@@ -16,6 +16,8 @@ process multiqc {
     extra_fn_clean_exts:
         - '.md'
         - '_combined_fastp'
+    use_filename_as_sample_name:
+        - picard/gcbias
     custom_plot_config:
         picard_insert_size:
             xmax: 1000

nextflow.config

@@ -11,7 +11,6 @@ params {
     email                     = 'undefined'
     flowcell                  = 'undefined'
     ubam_dir                  = './' 
-    project                   = 'project_undefined'
     workflow                  = 'EM-seq'
     outputDir                 = "em-seq_output" 
     tmp_dir                   = '/tmp'
@@ -23,7 +22,7 @@ params {
     single_end                = false
 
     // NEB only
-    path_to_ngs_agg           = "/mnt/bioinfo/prg/ngs-aggregate_results/current"
+    path_to_ngs_agg           = null
     workflow_name_modifier    = null
 
 }
@@ -47,7 +46,6 @@ profiles {
         apptainer.enabled      = false
     }
     mamba {
-        conda.cacheDir         = '/data/seq-shepherd/.conda/envs'
         conda.enabled          = true
         conda.useMamba         = true
         docker.enabled         = false
@@ -58,7 +56,6 @@ profiles {
         apptainer.enabled      = false
     }
     micromamba {
-        conda.cacheDir         = '/data/seq-shepherd/.conda/envs'
         conda.enabled          = true
         conda.useMamba         = false
         conda.useMicromamba    = true
@@ -80,9 +77,6 @@ profiles {
 
 env {
     PYTHONNOUSERSITE = 1
-    R_PROFILE_USER   = "/.Rprofile"
-    R_ENVIRON_USER   = "/.Renviron"
-    JULIA_DEPOT_PATH = "/usr/local/share/julia"
 }
 
 executor {