Update pb fq2bam

modules/nf-core/parabricks/deepvariant/meta.yml

@@ -53,10 +53,11 @@ output:
             e.g. [ id:'test' ]
       - "*.vcf":
           type: file
-          description: vcf file created with deepvariant (does not support .gz for normal vcf), optional
+          description: vcf file created with deepvariant (does not support .gz for normal
+            vcf), optional
           pattern: "*.vcf"
   - gvcf:
-      - meta:          
+      - meta:
           type: map
           description: |
             Groovy Map containing sample information.

modules/nf-core/parabricks/fq2bam/main.nf

@@ -2,24 +2,23 @@ process PARABRICKS_FQ2BAM {
     tag "$meta.id"
     label 'process_high'
     label 'process_gpu'
+    label 'gpu'
     stageInMode 'copy'
 
     container "nvcr.io/nvidia/clara/clara-parabricks:4.4.0-1"
 
     input:
-    tuple val(meta), path(reads)
-    tuple val(meta2), path(fasta)
-    tuple val(meta3), path(index)
-    tuple val(meta4), path(interval_file)
-    path(known_sites)
-
+    tuple val(meta), val(read_group), path (r1_fastq, stageAs: "?/*"), path (r2_fastq, stageAs: "?/*"), path(interval_file)
+    tuple path(fasta), path(fai)
+    tuple val(meta1), path(index)
+    path known_sites
+
     output:
-    tuple val(meta), path("*.bam")  , emit: bam
-    tuple val(meta), path("*.bai")  , emit: bai
-    tuple val(meta), path("*.table"), emit: bqsr_table         , optional:true
-    path("versions.yml")            , emit: versions
-    path("qc_metrics")              , emit: qc_metrics          , optional:true
-    path("duplicate-metrics.txt")   , emit: duplicate_metrics  , optional:true
+    tuple val(meta), path("*.bam"), path("*.bai") , emit: bam_bai
+    tuple val(meta), path("qc_metrics/*"), optional: true, emit: qc_metrics
+    tuple val(meta), path("*.table"), optional: true, emit: bqsr_table
+    tuple val(meta), path("*.duplicate-metrics.txt"), optional: true, emit: duplicate_metrics
+    path "versions.yml", emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -29,26 +28,42 @@ process PARABRICKS_FQ2BAM {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         error "Parabricks module does not support Conda. Please use Docker / Singularity / Podman instead."
     }
+
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
-    def in_fq_command = meta.single_end ? "--in-se-fq $reads" : "--in-fq $reads"
-    def known_sites_command = known_sites ? known_sites.collect{"--knownSites $it"}.join(' ') : ""
+    def prefix = task.ext.suffix ? "${meta.id}${task.ext.suffix}" : "${meta.id}"    
+    def known_sites_command = known_sites ? (known_sites instanceof List ? known_sites.collect { "--knownSites $it" }.join(' ') : "--knownSites ${known_sites}") : ""
     def known_sites_output = known_sites ? "--out-recal-file ${prefix}.table" : ""
-    def interval_file_command = interval_file ? interval_file.collect{"--interval-file $it"}.join(' ') : ""
+    def interval_file_command = interval_file ? (interval_file instanceof List ? interval_file.collect { "--interval-file $it" }.join(' ') : "--interval-file ${interval_file}") : ""
     def num_gpus = task.accelerator ? "--num-gpus $task.accelerator.request" : ''
+
+    def readgroups_string = read_group.collect { rg -> "@RG\\tID:${rg.read_group}__${rg.sample}\\tSM:${rg.sample}\\tPL:${rg.platform}\\tLB:${rg.sample}\\tPU:${rg.read_group}" }
+
+    def in_fq_command = meta.single_end 
+        ? (r1_fastq instanceof List 
+            ? r1_fastq.collect { "--in-se-fq $it" }.join(' ') 
+            : "--in-se-fq ${r1_fastq}"
+        )
+        : (r1_fastq instanceof List && r2_fastq instanceof List && readgroups_string instanceof List
+            ? (r1_fastq.indexed().collect { idx, r1 -> "--in-fq $r1 ${r2_fastq[idx]} \"${readgroups_string[idx]}\"" }).join(' ')
+            : "--in-fq ${r1_fastq} ${r2_fastq} \"${readgroups_string.join(' ')}\""
+        )
+
     """
     INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'`
     cp $fasta \$INDEX
-
+    
     pbrun \\
         fq2bam \\
         --ref \$INDEX \\
         $in_fq_command \\
+        --read-group-sm $meta.id \\
         --out-bam ${prefix}.bam \\
+        $num_gpus \\
         $known_sites_command \\
         $known_sites_output \\
         $interval_file_command \\
-        $num_gpus \\
+        --out-qc-metrics-dir qc_metrics \\
+        --out-duplicate-metrics ${prefix}.duplicate-metrics.txt \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
@@ -62,11 +77,38 @@ process PARABRICKS_FQ2BAM {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         error "Parabricks module does not support Conda. Please use Docker / Singularity / Podman instead."
     }
-    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    def args = task.ext.args ?: ''
+    def prefix     = task.ext.suffix ? "${meta.id}${task.ext.suffix}" : "${meta.id}"    
+    def known_sites_command = known_sites ? (known_sites instanceof List ? known_sites.collect { "--knownSites $it" }.join(' ') : "--knownSites ${known_sites}") : ""
+    def known_sites_output = known_sites ? "--out-recal-file ${prefix}.table" : ""
+    def interval_file_command = interval_file ? (interval_file instanceof List ? interval_file.collect { "--interval-file $it" }.join(' ') : "--interval-file ${interval_file}") : ""
+
+    def readgroups_string = read_group.collect { rg -> "@RG\\tID:${rg.read_group}__${rg.sample}\\tSM:${rg.sample}\\tPL:${rg.platform}\\tLB:${rg.sample}\\tPU:${rg.read_group}" }
+
+    def in_fq_command = meta.single_end 
+        ? (r1_fastq instanceof List 
+            ? r1_fastq.collect { "--in-se-fq $it" }.join(' ') 
+            : "--in-se-fq ${r1_fastq}"
+        )
+        : (r1_fastq instanceof List && r2_fastq instanceof List && readgroups_string instanceof List
+            ? (r1_fastq.indexed().collect { idx, r1 -> "--in-fq $r1 ${r2_fastq[idx]} \"${readgroups_string[idx]}\"" }).join(' ')
+            : "--in-fq ${r1_fastq} ${r2_fastq} \"${readgroups_string.join(' ')}\""
+        )
+
+    def metrics_output_command = args = "--out-duplicate-metrics duplicate-metrics.txt" ? "touch duplicate-metrics.txt" : ""
+    def known_sites_output_command = known_sites ? "touch ${prefix}.table" : ""
+    def qc_metrics_output_command = args = "--out-qc-metrics-dir qc_metrics " ? "mkdir qc_metrics && touch qc_metrics/alignment.txt" : ""
     """
+
+    echo $in_fq_command
+
+    touch run.log
     touch ${prefix}.bam
     touch ${prefix}.bam.bai
-
+    $metrics_output_command
+    $known_sites_output_command
+    $qc_metrics_output_command
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
             pbrun: \$(echo \$(pbrun version 2>&1) | sed 's/^Please.* //' )

modules/nf-core/parabricks/fq2bam/meta.yml

@@ -20,61 +20,69 @@ input:
         description: |
           Groovy Map containing sample information
           e.g. [ id:'test', single_end:false ]
-    - reads:
-        type: file
-        description: fastq.gz files
-        pattern: "*.fastq.gz"
-  - - meta2:
+    - read_group:
         type: map
         description: |
-          Groovy Map containing fasta information
-    - fasta:
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - r1_fastq:
+        type: file
+        description: R1 fastq file
+        pattern: "*.fastq.gz"
+    - r2_fastq:
+        type: file
+        description: R2 fastq file
+        pattern: "*.fastq.gz"
+    - interval_file:
+        type: file
+        description: file or files containing genomic intervals for use in base quality
+          score recalibration.
+        pattern: "*.{bed,interval_list,picard,list,intervals}"
+  - - fasta:
         type: file
         description: reference fasta file - must be unzipped
-        pattern: "*.fasta"
-  - - meta3:
+        pattern: "*.{fasta,fa}"
+    - fai:
+        type: file
+        description: reference fasta fai index
+        pattern: "*.fai"
+  - - meta1:
         type: map
         description: |
-          Groovy Map containing index information
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
     - index:
         type: file
         description: reference BWA index
         pattern: "*.{amb,ann,bwt,pac,sa}"
-  - - meta4:
-        type: map
-        description: |
-          Groovy Map containing index information
-    - interval_file:
-        type: file
-        description: (optional) file(s) containing genomic intervals for use in base
-          quality score recalibration (BQSR)
-        pattern: "*.{bed,interval_list,picard,list,intervals}"
   - - known_sites:
         type: file
         description: (optional) known sites file(s) for calculating BQSR. markdups must
           be true to perform BQSR.
         pattern: "*.vcf.gz"
 output:
-  - bam:
+  - bam_bai:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
-            e.g. [ id:'test', single_end:false ]
+            e.g. [ id:'test']
       - "*.bam":
           type: file
-          description: Sorted BAM file
+          description: output bam file
           pattern: "*.bam"
-  - bai:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. [ id:'test', single_end:false ]
       - "*.bai":
           type: file
-          description: index corresponding to sorted BAM file
+          description: output bam bai file
           pattern: "*.bai"
+  - qc_metrics:
+      - meta:
+          type: map
+          description: (optional) optional directory of qc metrics
+      - qc_metrics/*:
+          type: directory
+          description: (optional) optional directory of qc metrics
+          pattern: "qc_metrics"
   - bqsr_table:
       - meta:
           type: map
@@ -83,25 +91,21 @@ output:
             e.g. [ id:'test']
       - "*.table":
           type: file
-          description: (optional) table from base quality score recalibration calculation,
-            to be used with parabricks/applybqsr
+          description: bqsr table
           pattern: "*.table"
-  - versions:
-      - versions.yml:
-          type: file
-          description: File containing software versions
-          pattern: "versions.yml"
-  - qc_metrics:
-      - qc_metrics:
-          type: directory
-          description: (optional) optional directory of qc metrics
-          pattern: "qc_metrics"
   - duplicate_metrics:
-      - duplicate-metrics.txt:
+      - meta:
+          type: map
+          description: (optional) metrics calculated from marking duplicates in the bam
+      - "*.duplicate-metrics.txt":
           type: file
           description: (optional) metrics calculated from marking duplicates in the bam
-            file
           pattern: "*-duplicate-metrics.txt"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions.
+          pattern: "versions.yml"
 authors:
   - "@bsiranosian"
   - "@adamrtalbot"