Merge branch 'CW-1258-params-help' into 'dev'

CW-1258 - Extra help for wf params

See merge request epi2melabs/workflows/wf-mpx!17

README.md

@@ -1,25 +1,27 @@
-# wf-mpx | Monkeypox Virus Metagenomic Assembly
+# wf-mpx | Mpox Virus Metagenomic Assembly
 
 This repository contains a [nextflow](https://www.nextflow.io/) workflow for the
-assembly of reads originating from the Monkeypox virus obtained through
+assembly of reads originating from the mpox virus obtained through
 Oxford Nanopore metagenomic sequencing.
 ## Introduction
 
-This workflow provides a simple way to analyse Monkeypox sequencing data; taking
+This workflow provides a simple way to analyse mpox sequencing data; taking
 raw Oxford Nanopore Technologies reads and creating a draft consensus and assembly.
 
+We expect data to be generated from a mixed population sample hence the use of the term "metagenomics".
+
 > No trimming of sequences is carried out so be vigilant when using targeted data.
 
-Using community develped tools this workflow:
+Using community-develped tools, this workflow:
 * Maps reads to a reference genome (`minimap2`)
 * Assesses coverage
 * Discards reads not mapping to the chosen reference
-* Calls variants with resepect to reference (`medaka`)
+* Calls variants with resepect to the reference (`medaka`)
 * Filters variants with <20x coverage
 * Creates a draft consensus (`bcftools`)
 * Creats a de-novo assembly (`flye` & `medaka`)
 
-More information can be found in this [blog post](https://labs.epi2me.io/basic-monkeypox-workflow).
+More information can be found in this [blog post](https://labs.epi2me.io/basic-mpox-workflow).
 ## Quickstart
 
 The workflow uses [nextflow](https://www.nextflow.io/) to manage compute and

docs/header.md

@@ -1,5 +1,5 @@
-# wf-mpx | Monkeypox Virus Metagenomic Assembly
+# wf-mpx | Mpox Virus Metagenomic Assembly
 
 This repository contains a [nextflow](https://www.nextflow.io/) workflow for the
-assembly of reads originating from the Monkeypox virus obtained through
+assembly of reads originating from the mpox virus obtained through
 Oxford Nanopore metagenomic sequencing.

docs/intro.md

@@ -1,17 +1,19 @@
 ## Introduction
 
-This workflow provides a simple way to analyse Monkeypox sequencing data; taking
+This workflow provides a simple way to analyse mpox sequencing data; taking
 raw Oxford Nanopore Technologies reads and creating a draft consensus and assembly.
 
+We expect data to be generated from a mixed population sample hence the use of the term "metagenomics".
+
 > No trimming of sequences is carried out so be vigilant when using targeted data.
 
-Using community develped tools this workflow:
+Using community-develped tools, this workflow:
 * Maps reads to a reference genome (`minimap2`)
 * Assesses coverage
 * Discards reads not mapping to the chosen reference
-* Calls variants with resepect to reference (`medaka`)
+* Calls variants with resepect to the reference (`medaka`)
 * Filters variants with <20x coverage
 * Creates a draft consensus (`bcftools`)
 * Creats a de-novo assembly (`flye` & `medaka`)
 
-More information can be found in this [blog post](https://labs.epi2me.io/basic-monkeypox-workflow).
+More information can be found in this [blog post](https://labs.epi2me.io/basic-mpox-workflow).

main.nf

@@ -32,33 +32,31 @@ process summariseReads {
 
 process alignReads {
     label "wfmpx"
-    cpus params.threads
+    cpus params.align_threads
     input:
         tuple val(sample_id), val(type), path(sample_fastq), path(sample_stats)
         path reference
     output:
         tuple val(sample_id), val(type), path("${sample_id}.bam"), path("${sample_id}.bam.bai"), emit: alignment
         tuple path("${sample_id}.bamstats"), path("${sample_id}.bam.summary"), emit: bamstats
     """
-    mini_align -i ${sample_fastq} -r ${reference} -p ${sample_id} -t $task.cpus -m
-    stats_from_bam -o ${sample_id}.bamstats -s ${sample_id}.bam.summary -t $task.cpus ${sample_id}.bam
+    mini_align -i ${sample_fastq} -r ${reference} -p ${sample_id} -t ${params.align_threads} -m
+    stats_from_bam -o ${sample_id}.bamstats -s ${sample_id}.bam.summary -t ${params.align_threads} ${sample_id}.bam
 
     #Keep only mapped reads going forward
     #samtools view -b -F 4 ${sample_id}_all.bam > ${sample_id}.bam
     """
 }
 
 process coverageCalc {
-    depth_threads = {params.threads >= 4  ? 4 : params.threads}
     label "wfmpx"
-    cpus depth_threads
+    cpus 1
     input:
         tuple val(sample_id), val(type), path("${sample_id}.bam"), path("${sample_id}.bam.bai")
         path reference
     output:
-        tuple path("${sample_id}.depth.txt")
+        path "${sample_id}.depth.txt"
     """
-    #mosdepth --fast-mode --by 10 -t $task.cpus ${sample_id} ${sample_id}.bam
     coverage_from_bam -s 1 -p ${sample_id} ${sample_id}.bam
     mv ${sample_id}*.depth.txt ${sample_id}.depth.txt
     """
@@ -68,7 +66,7 @@ process coverageCalc {
 
 process medakaVariants {
     label "wfmpx"
-    cpus params.threads
+    cpus 2
     input:
         tuple val(sample_id), val(type), path("${sample_id}.bam"), path("${sample_id}.bam.bai")
         path reference
@@ -89,7 +87,7 @@ process medakaVariants {
 
 process makeConsensus {
     label "wfmpx"
-    cpus params.threads
+    cpus 1
     input:
         tuple val(sample_id), val(type), path("${sample_id}.annotate.filtered.vcf")
         path reference
@@ -107,7 +105,7 @@ process makeConsensus {
 
 process flyeAssembly {
     label "wfmpx"
-    cpus params.threads
+    cpus params.assembly_threads
     input:
         tuple val(sample_id), val(type), path("${sample_id}.bam"), path("${sample_id}.bam.bai")
         path reference
@@ -116,11 +114,11 @@ process flyeAssembly {
     script:
     """
     samtools bam2fq ${sample_id}.bam > ${sample_id}_restricted.fastq
-    flye --nano-raw ${sample_id}_restricted.fastq  -g 197k -t ${params.threads} --meta -o flye
+    flye --nano-raw ${sample_id}_restricted.fastq  -g 197k -t ${params.assembly_threads} --meta -o flye
 
     # polish assembly with medaka
 
-    medaka_consensus -i ${sample_id}_restricted.fastq -t ${params.threads} -d flye/assembly.fasta ${params.medaka_options}
+    medaka_consensus -i ${sample_id}_restricted.fastq -t ${params.assembly_threads} -d flye/assembly.fasta ${params.medaka_options}
 
     minimap2 -ax map-ont ${reference} medaka/consensus.fasta | samtools view -bh - | samtools sort - > ${sample_id}_assembly_mapped.bam
 
@@ -173,7 +171,7 @@ process makeReport {
     output:
         path "wf-mpx-*.html"
     script:
-        report_name = "wf-mpx-" + params.report_name + '.html'
+        report_name = "wf-mpx-report.html"
     """
 
     report.py $report_name \
@@ -273,7 +271,7 @@ workflow {
     samples = fastq_ingress([
        "input":params.fastq,
        "sample":params.sample,
-       "sample_sheet":params.sample_sheet])
+       "sample_sheet":null])
 
     pipeline(samples, params._reference, params._genbank)
     output(pipeline.out.results)

nextflow.config

@@ -16,16 +16,16 @@ params {
     fastq = null
     out_dir = "output"
     sample = null
-    sample_sheet = null
     wfversion = "v0.0.5"
-    threads = 4
+    align_threads = 4
+    assembly_threads = 4
     assembly = true
     medaka_options = null
     min_coverage = 20
     aws_image_prefix = null
     aws_queue = null
-    report_name = "report"
     disable_ping = false
+    analyse_unclassified = false
 
     reference = null
 
@@ -48,7 +48,7 @@ manifest {
     name            = 'epi2me-labs/wf-mpx'
     author          = 'Oxford Nanopore Technologies'
     homePage        = 'https://github.com/epi2me-labs/wf-mpx'
-    description     = 'Monkeypox metagenomics assembly workflow.'
+    description     = 'Mpox metagenomics assembly workflow.'
     mainScript      = 'main.nf'
     nextflowVersion = '>=20.10.0'
     version         = 'v0.0.5'