Add and update - picard/gatk4 - addorreplacereadgroups

modules/nf-core/picard/addorreplacereadgroups/main.nf

@@ -9,34 +9,43 @@ process PICARD_ADDORREPLACEREADGROUPS {
 
     input:
     tuple val(meta), path(bam)
+    tuple val(meta2), path(fasta)
+    tuple val(meta3), path(fasta_index)
 
     output:
-    tuple val(meta), path("*.bam"), emit: bam
-    tuple val(meta), path("*.bai"), emit: bai,     optional: true
-    path "versions.yml"           , emit: versions
+    tuple val(meta), path("*.bam") , emit: bam,  optional: true
+    tuple val(meta), path("*.bai") , emit: bai,  optional: true
+    tuple val(meta), path("*.cram"), emit: cram, optional: true
+    tuple val(meta), path("*.crai"), emit: crai, optional: true
+    path "versions.yml"            , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args        ?: ''
     def prefix = task.ext.prefix    ?: "${meta.id}"
+    def suffix = task.ext.suffix    ?: "${bam.getExtension()}"
+    def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
+    def create_index = ( suffix == "bam" )? "--CREATE_INDEX" : ""
     def avail_mem = 3072
     if (!task.memory) {
         log.info '[Picard AddOrReplaceReadGroups] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
     } else {
         avail_mem = (task.memory.mega*0.8).intValue()
     }
 
-    if ("$bam" == "${prefix}.bam") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    if ("$bam" == "${prefix}.${suffix}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
 
     """
     picard \\
         -Xmx${avail_mem}M \\
         AddOrReplaceReadGroups \\
         $args \\
+        $reference \\
+        $create_index \\
         --INPUT ${bam} \\
-        --OUTPUT ${prefix}.bam
+        --OUTPUT ${prefix}.${suffix}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -46,10 +55,15 @@ process PICARD_ADDORREPLACEREADGROUPS {
 
     stub:
     def prefix = task.ext.prefix    ?: "${meta.id}"
-
-    if ("$bam" == "${prefix}.bam") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    def suffix = task.ext.suffix    ?: "${bam.getExtension()}"
+    if ("$bam" == "${prefix}.${suffix}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    def create_index = ""
+    if (suffix == "bam") {
+        create_index = "touch ${prefix}.${suffix}.bai"
+    }
     """
-    touch ${prefix}.bam
+    touch ${prefix}.${suffix}
+    ${create_index}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/nf-core/picard/addorreplacereadgroups/meta.yml

@@ -24,6 +24,14 @@ input:
       type: file
       description: Input BAM file
       pattern: "*.{bam}"
+  - fasta:
+      type: file
+      description: Reference genome file
+      pattern: "*.{fasta,fa,fasta.gz,fa.gz}"
+  - fasta_index:
+      type: file
+      description: Reference genome index file
+      pattern: "*.{fai,fasta.fai,fa.fai,fasta.gz.fai,fa.gz.fai}"
 output:
   - meta:
       type: map
@@ -40,8 +48,16 @@ output:
       pattern: "*.{bam}"
   - bai:
       type: file
-      description: BAM index file
+      description: An optional BAM index file
       pattern: "*.{bai}"
+  - cram:
+      type: file
+      description: Output CRAM file
+      pattern: "*.{cram}"
+  - crai:
+      type: file
+      description: An optional CRAM index file
+      pattern: "*.{crai}"
 authors:
   - "@sateeshperi"
   - "@mjcipriano"

tests/modules/nf-core/picard/addorreplacereadgroups/nextflow.config → modules/nf-core/picard/addorreplacereadgroups/tests/bam.config

@@ -1,7 +1,4 @@
 process {
-
-    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
     withName: 'PICARD_ADDORREPLACEREADGROUPS'{
         ext.prefix = { "${meta.id}.replaced"}
         ext.args = {[
@@ -11,4 +8,5 @@ process {
             "-SM ${meta.id}"
         ].join(' ').trim()}
     }
+
 }

modules/nf-core/picard/addorreplacereadgroups/tests/cram.config

@@ -0,0 +1,13 @@
+process {
+    withName: 'PICARD_ADDORREPLACEREADGROUPS'{
+        ext.prefix = { "${meta.id}.replaced"}
+        ext.args = {[
+            "-LB ${meta.id}",
+            "-PL ILLUMINA",
+            "-PU bc1",
+            "-SM ${meta.id}"
+        ].join(' ').trim()}
+        ext.suffix = { "cram" }
+    }
+
+}

modules/nf-core/picard/addorreplacereadgroups/tests/main.nf.test

@@ -0,0 +1,86 @@
+
+nextflow_process {
+
+    name "Test Process PICARD_ADDORREPLACEREADGROUPS"
+    script "../main.nf"
+    process "PICARD_ADDORREPLACEREADGROUPS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "picard"
+    tag "picard/addorreplacereadgroups"
+
+    test("sarscov2 - bam") {
+        config "./bam.config"
+
+        when {
+            process {
+                """
+                input[0] = [ [:], file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true) ]
+                input[1] = [ [:], [] ]
+                input[2] = [ [:], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(file(process.out.bam[0][1]).name).match("bam_name") },
+                { assert snapshot(file(process.out.bai[0][1]).name).match("bai_name") },
+            )
+        }
+
+    }
+
+    test("homo_sapiens - cram") {
+        config "./cram.config"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram', checkIfExists: true),                    ]
+                ]
+                input[1] = [ [:], file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) ]
+                input[2] = [ [:], file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta.fai', checkIfExists: true) ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(file(process.out.cram[0][1]).name).match("cram_name") },
+                { assert snapshot(process.out.versions).match("versions") },
+            )
+        }
+
+    }
+
+    test("sarscov2 - bam - stub") {
+        config "./bam.config"
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [ [:], file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true) ]
+                input[1] = [ [:], [] ]
+                input[2] = [ [:], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/picard/addorreplacereadgroups/tests/tags.yml

@@ -0,0 +1,2 @@
+picard/addorreplacereadgroups:
+  - "modules/nf-core/picard/addorreplacereadgroups/**"

tests/config/pytest_modules.yml

@@ -1573,9 +1573,6 @@ phispy:
 phyloflash:
   - modules/nf-core/phyloflash/**
   - tests/modules/nf-core/phyloflash/**
-picard/addorreplacereadgroups:
-  - modules/nf-core/picard/addorreplacereadgroups/**
-  - tests/modules/nf-core/picard/addorreplacereadgroups/**
 picard/bedtointervallist:
   - modules/nf-core/picard/bedtointervallist/**
   - tests/modules/nf-core/picard/bedtointervallist/**