Formatted nextflow.contig

Author: olabiyi

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

@@ -1,14 +1,14 @@
-
+//**************** Global parameters *****************//
 params {
     // Mandatory parameters 
     target_region = "16S" // "16S", "18S", "ITS"
     raw_R1_suffix = "_R1_raw.fastq.gz"
     raw_R2_suffix = "_R2_raw.fastq.gz"
     raw_reads_dir = "../Raw_Sequence_Data/"
-    trim_primers = true
+    trim_primers  = true // true or false
 
 
-    // -------- Mandatory if not using GLDS_accession ---------------------------------//
+    // -------- Required if GLDS_accession is false ---------------//
     // A 3-column (single-end) or 4-column (paired-end) input file ( sample_id, forward, [reverse,] paired)
     csv_file = "PE_file.csv" 
 
@@ -21,106 +21,125 @@ params {
     // -------- End of Mandatory if not using GLDS_accession ----------------//
 
     // Cutadapt parameters
-    min_cutadapt_len = 130
-    primers_linked = "TRUE"
-    discard_untrimmed = "TRUE"
+    min_cutadapt_len    = 130
+    primers_linked      = "TRUE"
+    discard_untrimmed   = "TRUE"
     F_primer = ""
     R_primer = ""
 
     // Dada2 parameters
-    left_trunc = 0
-    right_trunc = 0
-    left_maxEE = 1
-    right_maxEE = 1
+    left_trunc     = 0
+    right_trunc    = 0
+    left_maxEE     = 1
+    right_maxEE    = 1
     concatenate_reads_only = "FALSE"
 
     // If using conda environments specify their locations so new ones won't be created
     conda{
-          // Specify the paths to your existing conda environments (/path/to/envs/genelab-utils)
+          // Specify the paths to existing conda environments (/path/to/envs/genelab-utils)
           // leave as is if you want to create a new conda environment
-          genelab = null
-          qc = null
-          R = null
-          R_visualizations = null
-          cutadapt = null
+          genelab          = null      // /path/to/envs/genelab
+          qc               = null      // /path/to/envs/qc
+          R                = null      // /path/to/envs/R
+          R_visualizations = null      // /path/to/envs/R_visualizations
+          cutadapt         = null      // /path/to/envs/cutadapt
       }
 
 
     // Mandatory parameters  if using GLDS_accession
     GLDS_accession = false
- 
-    assay_suffix = "_GLAmpSeq"
+    assay_suffix   = "_GLAmpSeq"
+
     output_prefix = ""
     publishDir_mode = "link" // "link", "copy"
 
     // Suffixes
     primer_trimmed_R1_suffix = "_R1_trimmed.fastq.gz"
     primer_trimmed_R2_suffix =  "_R2_trimmed.fastq.gz"
-    filtered_R1_suffix = "_R1_filtered.fastq.gz"
-    filtered_R2_suffix = "_R2_filtered.fastq.gz"
+    filtered_R1_suffix       = "_R1_filtered.fastq.gz"
+    filtered_R2_suffix       = "_R2_filtered.fastq.gz"
 
 
-    // directories
-    fastqc_out_dir = "../workflow_output/FastQC_Outputs/"
-    trimmed_reads_dir = "../workflow_output/Trimmed_Sequence_Data/"
-    filtered_reads_dir = "../workflow_output/Filtered_Sequence_Data/"
-    info_out_dir = "../workflow_output/Metadata/"
-    plots_dir =  "../workflow_output/Final_Outputs/Plots/"
-    final_outputs_dir = "../workflow_output/Final_Outputs/"
-    metadata_dir = "../Metadata/"
-    genelab_dir = "../GeneLab/"
+    // Directories
+    fastqc_out_dir      = "../workflow_output/FastQC_Outputs/"
+    trimmed_reads_dir   = "../workflow_output/Trimmed_Sequence_Data/"
+    filtered_reads_dir  = "../workflow_output/Filtered_Sequence_Data/"
+    info_out_dir        = "../workflow_output/Metadata/"
+    plots_dir           =  "../workflow_output/Final_Outputs/Plots/"
+    final_outputs_dir   = "../workflow_output/Final_Outputs/"
+    metadata_dir        = "../Metadata/"
+    genelab_dir         = "../GeneLab/"
 
     // Multiqc
-    multiqc_config ="${baseDir}/config/multiqc.config"
-    errorStrategy = "terminate"
-    debug = false // set to true if you'd like to see the values of your set parameters
+    multiqc_config = "${baseDir}/config/multiqc.config"
+    errorStrategy  = "terminate"
+    debug          = false // set to true if you'd like to see the values of your set parameters
 }
 
-// Maximum number of jobs to submit in parallel
-executor.queueSize = 20
+// Setting the default container engine as singularity
+params.containerEngine = "singularity"
+// Conda shouldn't be used by default except when using conda-based profiles
+params.use_conda = false
+
+
+/*******************************************************************************************************
+*************************************** Workflow Profiles **********************************************
+********************************************************************************************************/
 
 profiles {
 
 
     slurm {  
-        process.executor = 'slurm'
+        process.executor      = 'slurm'
     }
 
     conda {   
-        conda.enabled = true               
+        conda.enabled = true
+        params.use_conda       = true               
     }
 
     singularity {
         singularity.enabled    = true
         singularity.autoMounts = true
-        singularity.cacheDir = "singularity/"
+        singularity.cacheDir   = "singularity/"
+        params.containerEngine = "singularity"
     }
 
     docker {
         docker.enabled         = true
         docker.runOptions      = '-u $(id -u):$(id -g)'
         docker.userEmulation   = true
+        params.containerEngine = "docker"
     }
 
 }
 
+// Maximum number of jobs to submit in parallel
+executor.queueSize = 20
+
+
+/******************************************************************************************************************
+***************** Tune process specific resources (cpu, container, memory etc.) ***********************************
+*******************************************************************************************************************/
 
 process {
 
+    //******************* Default process settings ************************//
     errorStrategy = { params.errorStrategy ? params.errorStrategy : "ignore" } 
     maxRetries = 2
     cpus = 2
     memory = '5 GB'
     cache = 'lenient'
   //debug = true  // uncomment to see what is being emitted to the standard output
 
-
+//************************* GLDS_accession runsheet and input file retrieval  **************************************//
     withName: GET_RUNSHEET {
                   conda = {params.conda.genelab != null ? params.conda.genelab : "envs/genelab.yaml"}
                   container = "olabiyi/genelab-utils:1.3.22"
                   publishDir = [path: params.genelab_dir, mode: params.publishDir_mode]
             }
 
+//********************************** Read quality control and assesment ********************************************//
     withLabel: fastqc {
                   conda = {params.conda.qc != null ? params.conda.qc : "envs/qc.yaml"}
                   container = "staphb/fastqc:0.12.1"
@@ -147,6 +166,7 @@ process {
                   publishDir = [path: params.filtered_reads_dir, mode: params.publishDir_mode ]
             } 
 
+//********************************** ASV table creation and plotting ********************************************//
     withName: "RUN_R_TRIM|RUN_R_NOTRIM" {
                   conda = {params.conda.R != null ?  params.conda.R : "envs/R.yaml"}
                   container = "olabiyi/r-dada-decipher-biomformat:1.0"
@@ -175,6 +195,9 @@ process {
 }
 
 
+/*****************************************************************************
+********************** Workflow Resource Usage Capturing *********************
+******************************************************************************/
 
 // Adapted from : https://github.com/nf-core/rnaseq/blob/master/nextflow.config
 def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
@@ -192,12 +215,17 @@ trace {
 }
 
 
+
+/******************************************************************************
+**************************** Workflow Metadata ********************************
+*******************************************************************************/
+
 manifest {
     author = 'Olabiyi Aderemi Obayomi, Mike D. Lee'
     homePage = 'https://github.com/nasa/GeneLab_Data_Processing/blob/master/Amplicon/'
-    description = 'GeneLab bioinformatics processing pipelines for amplicon sequencing data'
+    description = 'Amplicon Illumina workflow for pipeline document GL-DPPD-7104-B'
     mainScript = 'main.nf'
     defaultBranch = 'main'
     nextflowVersion = '>=22.10.1'
-    version = 'GL-DPPD-7104-B'
+    version = '1.0.0'
 }