Replace some params

.github/workflows/ci.yml

@@ -131,7 +131,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        profile: [test_split_fastq, test_targeted, test_trimming, test_no_gatk_spark, test_umi_tso, test_umi_qiaseq]
+        profile: [test_split_fastq, test_targeted, test_trimming, test_use_gatk_spark, test_umi_tso, test_umi_qiaseq]
     steps:
       - uses: actions/checkout@v2
       - name: Install Nextflow

conf/test_no_gatk_spark.config → conf/test_use_gatk_spark.config

@@ -4,11 +4,11 @@
  * -------------------------------------------------
  * Defines bundled input files and everything required
  * to run a fast and simple test. Use as follows:
- *   nextflow run nf-core/sarek -profile test_no_gatk_spark
+ *   nextflow run nf-core/sarek -profile test_use_gatk_spark
  */
 
 includeConfig 'test.config'
 
 params {
-  no_gatk_spark = true
+  use_gatk_spark = true
 }

docs/usage.md

@@ -84,9 +84,9 @@ If `-profile` is not specified, the pipeline will run locally and expect all sof
 * `test_annotation`
   * A profile with a complete configuration for automated testing
   * Input data is a `VCF` for testing annotation
-* `test_no_gatk_spark`
+* `test_use_gatk_spark`
   * A profile with a complete configuration for automated testing
-  * Specify `--no_gatk_spark`
+  * Specify `--use_gatk_spark`
 * `test_split_fastq`
   * A profile with a complete configuration for automated testing
   * Specify `--split_fastq 500`

main.nf

@@ -78,7 +78,7 @@ def helpMessage() {
     Preprocessing:
       --markdup_java_options        [str] Establish values for markDuplicates memory consumption
                                           Default: ${params.markdup_java_options}
-      --no_gatk_spark              [bool] Disable usage of GATK Spark implementation of their tools in local mode
+      --use_gatk_spark             [bool] Enable usage of GATK Spark implementation of their tools in local mode
       --save_bam_mapped            [bool] Save Mapped BAMs
       --skip_markduplicates        [bool] Skip MarkDuplicates
 
@@ -93,7 +93,7 @@ def helpMessage() {
                                           Default: ${params.cf_ploidy}
       --cf_window                   [int] Control-FREEC window size
                                           Default: Disabled
-      --no_gvcf                    [bool] No g.vcf output from GATK HaplotypeCaller
+      --generate_gvcf              [bool] Enable g.vcf output from GATK HaplotypeCaller
       --no_strelka_bp              [bool] Will not use Manta candidateSmallIndels for Strelka (not recommended by Best Practices)
       --pon                        [file] Panel-of-normals VCF (bgzipped) for GATK Mutect2 / Sentieon TNscope
                                           See: https://software.broadinstitute.org/gatk/documentation/tooldocs/current/org_broadinstitute_hellbender_tools_walkers_mutect_CreateSomaticPanelOfNormals.php
@@ -414,7 +414,7 @@ if (params.split_fastq)          summary['Reads in fastq']                   = p
 
 summary['MarkDuplicates'] = "Options"
 summary['Java options'] = params.markdup_java_options
-summary['GATK Spark']   = params.no_gatk_spark ? 'No' : 'Yes'
+summary['GATK Spark']   = params.use_gatk_spark ? 'Yes' : 'No'
 
 summary['Save BAMs mapped']   = params.save_bam_mapped ? 'Yes' : 'No'
 summary['Skip MarkDuplicates']   = params.skip_markduplicates ? 'Yes' : 'No'
@@ -432,7 +432,7 @@ if ('controlfreec' in tools) {
     if (params.cf_ploidy)    summary['ploidy']                 = params.cf_ploidy
 }
 
-if ('haplotypecaller' in tools)             summary['GVCF']       = params.no_gvcf ? 'No' : 'Yes'
+if ('haplotypecaller' in tools)             summary['GVCF']       = params.generate_gvcf ? 'Yes' : 'No'
 if ('strelka' in tools && 'manta' in tools) summary['Strelka BP'] = params.no_strelka_bp ? 'No' : 'Yes'
 if (params.pon && ('mutect2' in tools || (params.sentieon && 'tnscope' in tools))) summary['Panel of normals'] = params.pon
 
@@ -1387,7 +1387,18 @@ process MarkDuplicates {
     script:
     markdup_java_options = task.memory.toGiga() > 8 ? params.markdup_java_options : "\"-Xms" +  (task.memory.toGiga() / 2).trunc() + "g -Xmx" + (task.memory.toGiga() - 1) + "g\""
     metrics = 'markduplicates' in skipQC ? '' : "-M ${idSample}.bam.metrics"
-    if (params.no_gatk_spark)
+    if (params.use_gatk_spark)
+    """
+    gatk --java-options ${markdup_java_options} \
+        MarkDuplicatesSpark \
+        -I ${idSample}.bam \
+        -O ${idSample}.md.bam \
+        ${metrics} \
+        --tmp-dir . \
+        --create-output-bam-index true \
+        --spark-master local[${task.cpus}]
+    """
+    else
     """
     gatk --java-options ${markdup_java_options} \
         MarkDuplicates \
@@ -1401,17 +1412,6 @@ process MarkDuplicates {
 
     mv ${idSample}.md.bai ${idSample}.md.bam.bai
     """
-    else
-    """
-    gatk --java-options ${markdup_java_options} \
-        MarkDuplicatesSpark \
-        -I ${idSample}.bam \
-        -O ${idSample}.md.bam \
-        ${metrics} \
-        --tmp-dir . \
-        --create-output-bam-index true \
-        --spark-master local[${task.cpus}]
-    """
 }
 
 (tsv_bam_duplicates_marked, tsv_bam_duplicates_marked_sample) = tsv_bam_duplicates_marked.into(2)
@@ -2010,7 +2010,7 @@ process HaplotypeCaller {
 
 gvcfHaplotypeCaller = gvcfHaplotypeCaller.groupTuple(by:[0, 1, 2])
 
-if (params.no_gvcf) gvcfHaplotypeCaller.close()
+if (!params.generate_gvcf) gvcfHaplotypeCaller.close()
 else gvcfHaplotypeCaller = gvcfHaplotypeCaller.dump(tag:'GVCF HaplotypeCaller')
 
 // STEP GATK HAPLOTYPECALLER.2

nextflow.config

@@ -42,7 +42,7 @@ params {
   // Preprocessing
   aligner = 'bwa-mem'
   markdup_java_options = '"-Xms4000m -Xmx7g"' // Established values for markDuplicates memory consumption, see https://github.com/SciLifeLab/Sarek/pull/689 for details
-  no_gatk_spark = null // GATK Spark implementation of their tools in local mode used by default
+  use_gatk_spark = false // GATK Spark implementation of their tools in local mode not used by default
   save_bam_mapped = null // Mapped BAMs not saved
   skip_markduplicates = null // Do not skip markDuplicates by default
 
@@ -52,7 +52,7 @@ params {
   cf_coeff = "0.05"  // default value for Control-FREEC
   cf_ploidy = "2"     // you can use 2,3,4
   cf_window = null      // by default we are not using this in Control-FREEC
-  no_gvcf = null // g.vcf are produced by HaplotypeCaller
+  generate_gvcf = null // g.vcf are not produced by HaplotypeCaller by default
   no_strelka_bp = null // Strelka will use Manta candidateSmallIndels if available
   pon = false // No default PON (Panel of Normals) file for GATK Mutect2 / Sentieon TNscope
   pon_index = false // No default PON index for GATK Mutect2 / Sentieon TNscope
@@ -140,15 +140,15 @@ profiles {
   podman {
     podman.enabled = true
   }
-  test               { includeConfig 'conf/test.config' }
-  test_annotation    { includeConfig 'conf/test_annotation.config' }
-  test_no_gatk_spark { includeConfig 'conf/test_no_gatk_spark.config' }
-  test_split_fastq   { includeConfig 'conf/test_split_fastq.config' }
-  test_targeted      { includeConfig 'conf/test_targeted.config' }
-  test_tool          { includeConfig 'conf/test_tool.config' }
-  test_trimming      { includeConfig 'conf/test_trimming.config' }
-  test_umi_tso       { includeConfig 'conf/test_umi_tso.config' }
-  test_umi_qiaseq    { includeConfig 'conf/test_umi_qiaseq.config' }
+  test                { includeConfig 'conf/test.config' }
+  test_annotation     { includeConfig 'conf/test_annotation.config' }
+  test_use_gatk_spark { includeConfig 'conf/test_use_gatk_spark.config' }
+  test_split_fastq    { includeConfig 'conf/test_split_fastq.config' }
+  test_targeted       { includeConfig 'conf/test_targeted.config' }
+  test_tool           { includeConfig 'conf/test_tool.config' }
+  test_trimming       { includeConfig 'conf/test_trimming.config' }
+  test_umi_tso        { includeConfig 'conf/test_umi_tso.config' }
+  test_umi_qiaseq     { includeConfig 'conf/test_umi_qiaseq.config' }
 }
 
 // Load genomes.config or igenomes.config

nextflow_schema.json

@@ -217,11 +217,10 @@
                     "help_text": "See https://github.com/SciLifeLab/Sarek/pull/689",
                     "hidden": true
                 },
-                "no_gatk_spark": {
-                    "type": "string",
-                    "default": "null",
-                    "fa_icon": "fas fa-ban",
-                    "description": "Disable usage of GATK Spark implementation"
+                "use_gatk_spark": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-forward",
+                    "description": "Enable usage of GATK Spark implementation"
                 },
                 "save_bam_mapped": {
                     "type": "boolean",
@@ -230,7 +229,7 @@
                 },
                 "skip_markduplicates": {
                     "type": "boolean",
-                    "fa_icon": "fas fa-forward",
+                    "fa_icon": "fas fa-fast-forward",
                     "description": "Skip GATK MarkDuplicates",
                     "help_text": "This params will also save the mapped BAMS, to enable restart from step prepare_recalibration"
                 }
@@ -275,10 +274,10 @@
                     "description": "Overwrite Control-FREEC window size",
                     "help_text": "It is recommended to use a window size of 0 for exome data"
                 },
-                "no_gvcf": {
+                "generate_gvcf": {
                     "type": "boolean",
-                    "fa_icon": "fas fa-ban",
-                    "description": "No g.vcf output from GATK HaplotypeCaller"
+                    "fa_icon": "fas fa-copy",
+                    "description": "Generate g.vcf output from GATK HaplotypeCaller"
                 },
                 "no_strelka_bp": {
                     "type": "boolean",