Added queue size and formatted help

Author: olabiyi

Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/main.nf

@@ -37,22 +37,22 @@ if (params.help) {
   println("PLEASE NOTE: This workflow assumes that all your raw reads end with the same suffix. If they don't please modify your filenames to have the same suffix as shown below.")
   println("--raw_R1_suffix [STRING] Raw forward reads suffix (region following the unique part of the sample names). e.g. _R1_raw.fastq.gz.") 
   println("--raw_R2_suffix [STRING] Raw reverse reads suffix (region following the unique part of the sample names). e.g. _R2_raw.fastq.gz.") 
-
+  println()
   println("Cutadapt (trimming) parameters:")
   println("	    --F_primer [STRING] Forward primer sequence e.g. AGAGTTTGATCCTGGCTCAG. Default: emptry string.")
   println("	    --R_primer [STRING] Reverse primer sequence e.g. CTGCCTCCCGTAGGAGT. Default: emptry string.")
   println("	    --min_cutadapt_len [INTEGER] What should be the minimum read length after quality trimming with cutadapt. Default: 130.")
   println("	    --primers_linked [STRING] Are the primers linked?. https://cutadapt.readthedocs.io/en/stable/recipes.html#trimming-amplicon-primers-from-paired-end-reads. Default: TRUE. ")
   println("	    --discard_untrimmed [STRING] Should untrimmed reads be discarded? Any supplied string except TRUE will not discard them. Default: TRUE.")
-	
+  println()	
   println("Optional arguments:")  
   println("  --help  Print this help message and exit.")
   println("  --publishDir_mode [STRING]  How should nextflow publish file outputs. Options can be found here https://www.nextflow.io/docs/latest/process.html#publishdir. Default: link.")
   println("  --errorStrategy [STRING] How should nextflow handle errors. Options can be found here https://www.nextflow.io/docs/latest/process.html#errorstrategy. Default: terminate")
   println("  --enable_visualizations [BOOLEAN] Should ASV plots be made? true or false. if true supply a path to the ruhnsheet for plotting to the --runsheet option. Default: false.")
   println("  --runsheet [PATH] A 4-column file with these exact headers [Sample Name, read1_path, raw_R1_suffix, groups] for plotting. Only relevant if --enable_visualizations is true. Default: null.") 
   println("  --multiqc_config [PATH] Path to a custome multiqc config file. Default: config/multiqc.config.")
-
+  println()
   println("Dada2 parameters passed to filterAndTrim() function:")
   println("	    --left_trunc [INTEGER] truncate the sequences to the left by this number of bases. Default: 0.") 
   println("	    --right_trunc [INTEGER] truncate the sequences to the right by this number of bases. Default: 0.") 
@@ -62,12 +62,13 @@ if (params.help) {
   println("      This is typically used with primers like 515-926, that captured 18S fragments that are typically too long to merge.")
   println("      Note that 16S and 18S should have been separated already prior to running this workflow. This should likely be left as FALSE for any option other than 18S above.") 	    
   println("	     Values are TRUE or FALSE Default: FALSE.")
-
+  println()
   println("File Suffixes:")
   println("      --primer_trimmed_R1_suffix [STRING] Suffix to use for naming your primer trimmed forward reads. Default: _R1_trimmed.fastq.gz.")
   println("      --primer_trimmed_R2_suffix [STRING] Suffix to use for naming your primer trimmed reverse reads. Default: _R2_trimmed.fastq.gz.")  
   println("      --filtered_R1_suffix [STRING]  Suffix to use for naming your quality filtered forward reads. Default: _R1_filtered.fastq.gz.")
   println("      --filtered_R2_suffix [STRING]  Suffix to use for naming your quality filtered reverse reads. Default: _R2_filtered.fastq.gz.")
+  println()
   println("Output directories:")
   println("      --raw_reads_dir [PATH] Where should the fastqc report of the raw reads be stored. Default: Raw_Sequence_Data/.")
   println("      --fastqc_out_dir [PATH] Where should multiqc outputs be stored. Default: workflow_output/FastQC_Outputs/.")
@@ -76,10 +77,12 @@ if (params.help) {
   println("      --info_out_dir [PATH] Where should output metadata be stored. Default: workflow_output/Metadata/.")
   println("      --plots_dir [PATH] Where should your plots be stored if visualization is enabled. Default: workflow_output/Final_Outputs/Plots/.")
   println("      --final_outputs_dir [PATH] Where should most outputs and summary reports be stored.  Default: workflow_output/Final_Outputs/.")
+  println()
   println("Genelab specific arguements:")
   println("      --GLDS_accession [STRING]  A Genelab accession number if the --csv_file parameter is not set. If this parameter is set, it will ignore the --csv_file parameter.")
   println("      --assay_suffix [STRING]  Genelabs assay suffix. Default: GLAmpSeq.")
   println("      --output_prefix [STRING] Unique name to tag onto output files. Default: empty string.")
+  println()
   println("Paths to existing conda environments to use otherwise a new one will be created using the yaml file in envs/.")
   println("      --conda.qc [PATH] Path to a conda environment containing fastqc, multiqc, zip and python. Default: null.")
   println("      --conda.R [PATH] Path to a conda environment containing R along with the packages decipher and biomformat installed. Default: null.")

Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/workflow_code/nextflow.config

@@ -1,4 +1,3 @@
-
 params {
     // Mandatory parameters 
     target_region = "16S" // "16S", "18S", "ITS"
@@ -7,7 +6,6 @@ params {
     raw_reads_dir = "${baseDir}/Raw_Sequence_Data/"
     trim_primers = true
 
-
     // -------- Mandatory if not using GLDS_accession ---------------------------------//
     // A 3-column (single-end) or 4-column (paired-end) input file ( sample_id, forward, [reverse,] paired)
     csv_file = "${baseDir}/PE_file.csv" 
@@ -45,7 +43,6 @@ params {
           cutadapt = null
       }
 
-
     // Mandatory parameters  if using GLDS_accession
     GLDS_accession = false
 
@@ -59,7 +56,6 @@ params {
     filtered_R1_suffix = "_R1_filtered.fastq.gz"
     filtered_R2_suffix = "_R2_filtered.fastq.gz"
 
-
     // directories
     fastqc_out_dir = "${baseDir}/workflow_output/FastQC_Outputs/"
     trimmed_reads_dir = "${baseDir}/workflow_output/Trimmed_Sequence_Data/"
@@ -68,34 +64,29 @@ params {
     plots_dir =  "${baseDir}/workflow_output/Final_Outputs/Plots/"
     final_outputs_dir = "${baseDir}/workflow_output/Final_Outputs/"
 
-
     // Multiqc
     multiqc_config ="${baseDir}/config/multiqc.config"
     errorStrategy = "terminate"
 }
 
 profiles {
 
-
     slurm_conda {  
-        process.executor = 'slurm' 
+        process.executor = "slurm" 
        //process.queue = "normal,priority"
-        process.queueSize = 32 // how many jobs should be submitted at one time
         conda.enabled = true               
     }
     conda {   
         conda.enabled = true               
     }
 
     slurm_sing {
-        process.executor = 'slurm'
+        process.executor = "slurm"
        //process.queue = "normal,priority"
-        process.queueSize = 32 // how many jobs should be submitted at one time
         singularity.enabled    = true
         singularity.autoMounts = true
         singularity.cacheDir = "singularity/"
     }
-
 
     singularity {
         singularity.enabled    = true
@@ -111,6 +102,8 @@ profiles {
 
 }
 
+// how jobs should be run in parallel
+executor.queueSize = 10
 
 process {
 
@@ -174,7 +167,7 @@ process {
     withName: R_VISUALIZATION {
                   conda = {params.conda.R_visualizations != null ? params.conda.R_visualizations : "envs/R_visualizations.yaml"}
                   container = "olabiyi/r-tidyverse-vegan-deseq2-phyloseq:1.0"
-                  memory = '20 GB'
+                  memory = "20 GB"
                   cpus = 10
                   publishDir = [path: "${params.plots_dir}${params.output_prefix}", 
                                mode: params.publishDir_mode, saveAs: { fn -> fn.substring(fn.indexOf('/')+1)}]