moving to nf-core compatible

UPHL-BioNGS · Jan 26, 2024 · a405ede · a405ede
1 parent ff0c46a
commit a405ede
Show file tree

Hide file tree

Showing 57 changed files with 1,083 additions and 1,144 deletions.
diff --git a/.github/workflows/legionella.yml b/.github/workflows/legionella.yml
@@ -42,7 +42,7 @@ jobs:
 
       - name: Check Legionella file
         run: |
-          for file in grandeur/legsta/legsta_summary.csv
+          for file in grandeur/elgato/elgato_summary.csv
           do
             head $file
             wc -l $file

diff --git a/assets/fastani_refs.tar.gz b/assets/fastani_refs.tar.gz
diff --git a/configs/fastani_refs.tar.gz b/configs/fastani_refs.tar.gz
diff --git a/grandeur.nf b/grandeur.nf
diff --git a/modules/bbmap.nf b/modules/bbmap.nf
diff --git a/modules/fastp.nf b/modules/fastp.nf
diff --git a/modules/kraken2.nf b/modules/kraken2.nf
diff --git a/modules/amrfinderplus.nf → modules/local/amrfinderplus.nf b/modules/amrfinderplus.nf → modules/local/amrfinderplus.nf
@@ -1,6 +1,6 @@
 process amrfinderplus {
-  tag           "${sample}"
-  label         "medcpus"
+  tag           "$meta.id"
+  label         "process_medium"
   publishDir    params.outdir, mode: 'copy'
   container     'staphb/ncbi-amrfinderplus:3.11.26-2023-11-15.1'
   maxForks      10
@@ -16,8 +16,14 @@ process amrfinderplus {
   output:
   path "ncbi-AMRFinderplus/${sample}_amrfinder_plus.txt"         , emit: collect
   path "logs/${task.process}/${sample}.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
+
+  when:
+  task.ext.when == null || task.ext.when
 
   shell:
+      def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
   '''
     mkdir -p ncbi-AMRFinderplus logs/!{task.process}
     log_file=logs/!{task.process}/!{sample}.!{workflow.sessionId}.log

diff --git a/modules/local/bbduk.nf b/modules/local/bbduk.nf
@@ -0,0 +1,45 @@
+process bbduk {
+  tag           "$meta.id"
+  label         "process_medium"
+  publishDir    params.outdir, mode: 'copy'
+  container     'staphb/bbtools:39.01'
+  //errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
+  time          '10m'
+
+  input:
+  tuple val(meta), file(reads)
+
+  output:
+  tuple val(meta), file("bbduk/*_rmphix_R{1,2}.fastq.gz"),  emit: fastq
+  path "bbduk/*",                                           emit: files
+  path "bbduk/*.phix.stats.txt",                            emit: stats
+  path "logs/${task.process}/*.log",  emit: log
+  path "versions.yml",                                      emit: versions
+
+  when:
+  task.ext.when == null || task.ext.when
+
+  shell:
+  def args   = task.ext.args   ?: 'k=31 hdist=1'
+  def prefix = task.ext.prefix ?: "${meta.id}"
+  """
+    mkdir -p bbduk logs/${task.process}
+    log_file=logs/${task.process}/${prefix}.${workflow.sessionId}.log
+
+    bbduk.sh ${args} \
+      in1=${reads[0]} \
+      in2=${reads[1]} \
+      out1=bbduk/${prefix}_rmphix_R1.fastq.gz \
+      out2=bbduk/${prefix}_rmphix_R2.fastq.gz \
+      outm=bbduk/${prefix}.matched_phix.fq \
+      ref=/opt/bbmap/resources/phix174_ill.ref.fa.gz \
+      stats=bbduk/${prefix}.phix.stats.txt \
+      threads=${task.cpus} \
+      | tee -a \$log_file
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+      "bbmap: \$(bbduk.sh --version 2>&1 | grep -v java | grep version)" >> versions.yml
+    END_VERSIONS
+  """
+}
diff --git a/modules/blast.nf → modules/local/blast.nf b/modules/blast.nf → modules/local/blast.nf
@@ -1,6 +1,6 @@
 process blastn {
-  tag           "${sample}"
-  label         "medcpus"
+  tag           "$meta.id"
+  label         "process_medium"
   publishDir    params.outdir, mode: 'copy'
   container     'staphb/blast:2.15.0'
   maxForks      10
@@ -16,8 +16,14 @@ process blastn {
   output:
   tuple val(sample), file("blastn/${sample}.tsv")                , emit: blastn
   path "logs/${task.process}/${sample}.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
+
+  when:
+  task.ext.when == null || task.ext.when
 
   shell:
+      def args = task.ext.args ?: '-max_target_seqs 10 -max_hsps 1 -evalue 1e-25'
+    def prefix = task.ext.prefix ?: "${meta.id}"
   '''
     mkdir -p blastn logs/!{task.process}
     log_file=logs/!{task.process}/!{sample}.!{workflow.sessionId}.log

diff --git a/modules/blobtools.nf → modules/local/blobtools.nf b/modules/blobtools.nf → modules/local/blobtools.nf
@@ -1,5 +1,6 @@
 process blobtools_create {
-  tag           "${sample}"
+  tag           "$meta.id"
+  label         "process_medium"
   publishDir    params.outdir, mode: 'copy'
   container     'chrishah/blobtools:v1.1.1'
   maxForks      10
@@ -16,8 +17,14 @@ process blobtools_create {
   tuple val(sample), file("blobtools/${sample}.blobDB.json")     , emit: json
   path "blobtools/${sample}.${sample}*.bam.cov"                  , emit: files
   path "logs/${task.process}/${sample}.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
+
+  when:
+  task.ext.when == null || task.ext.when
 
   shell:
+      def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
   '''
     mkdir -p blobtools logs/!{task.process}
     log_file=logs/!{task.process}/!{sample}.!{workflow.sessionId}.log
@@ -55,6 +62,7 @@ process blobtools_view {
   output:
   tuple val(sample), file("blobtools/${sample}.blobDB.table.txt"), emit: file
   path "logs/${task.process}/${sample}.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
 
   shell:
   '''
@@ -94,6 +102,7 @@ process blobtools_plot {
   tuple val(sample), file("blobtools/${sample}_blobtools.txt")   , emit: results
   path "blobtools/${sample}_summary.txt"                         , emit: collect
   path "logs/${task.process}/${sample}.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
 
   shell:
   '''

diff --git a/modules/datasets.nf → modules/local/datasets.nf b/modules/datasets.nf → modules/local/datasets.nf
@@ -1,5 +1,6 @@
 process datasets_summary {
   tag           "${taxon}"
+  label         "process_single"
   publishDir    params.outdir, mode: 'copy'
   container     'quay.io/uphl/datasets:15.34.0-2023-12-19'
   maxForks      10
@@ -8,6 +9,7 @@ process datasets_summary {
   //#UPHLICA memory 1.GB
   //#UPHLICA cpus 3
   //#UPHLICA time '10m'
+  path  "versions.yml"                          , emit: versions
 
   input:
   tuple val(taxon), file(script)
@@ -16,7 +18,12 @@ process datasets_summary {
   path "datasets/*_genomes.csv"                          , emit: genomes, optional: true
   path "logs/${task.process}/*.${workflow.sessionId}.log", emit: log
 
+  when:
+  task.ext.when == null || task.ext.when
+
   shell:
+      def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
   '''
     mkdir -p datasets logs/!{task.process}
     log_file=logs/!{task.process}/!{taxon}.!{workflow.sessionId}.log
@@ -53,6 +60,10 @@ process datasets_download {
   output:
   path "genomes/*"                                                       , emit: genomes, optional: true
   path "logs/${task.process}/datasets_download.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
+
+  when:
+  task.ext.when == null || task.ext.when
 
   shell:
   '''

diff --git a/modules/download_sra.nf → modules/local/download_sra.nf b/modules/download_sra.nf → modules/local/download_sra.nf
@@ -1,5 +1,6 @@
 process download_sra {
   tag           "${SRR}"
+  label         "process_single"
   publishDir    params.outdir, mode: 'copy'
   container     'quay.io/biocontainers/sra-tools:2.11.0--pl5321ha49a11a_3'
   maxForks      10
@@ -15,8 +16,14 @@ process download_sra {
   output:
   tuple val(SRR), file("reads/${SRR}_{1,2}.fastq.gz")         , emit: fastq
   path "logs/${task.process}/${SRR}.${workflow.sessionId}.log", emit: log
+  path  "versions.yml"                          , emit: versions
+
+  when:
+  task.ext.when == null || task.ext.when
 
   shell:
+      def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
   '''
     mkdir -p reads logs/!{task.process}
     log_file=logs/!{task.process}/!{SRR}.!{workflow.sessionId}.log