Merge pull request #127 from nf-cmgg/dev

Release PR

Author: matthdsm

CHANGELOG.md

@@ -5,7 +5,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## dev
 
-# v2.0.4
+## v2.0.5
+
+- Panel coverage will now run all genelists' coverage analysis in one process per sample
+- Fix readgroup sample names for `snp_` prefixed samples
+- Edit `WGS` profile to include `samtools/sormadup` and enable UMI aware duplicate marking
+
+## v2.0.4
 
 - Add flag to `snap` to allow for more expansion of compressed data
 - Parse readgroup samplenames for `snp_` prefixed samples

assets/multiqc_config.yml

@@ -1,6 +1,6 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-cmgg/preprocessing/releases/tag/2.0.4/" target="_blank">nf-cmgg/preprocessing</a>
-  analysis pipeline.
+  This report has been generated by the <a href="https://github.com/nf-cmgg/preprocessing/releases/tag/2.0.5/"
+  target="_blank">nf-cmgg/preprocessing</a> analysis pipeline.
 report_section_order:
   "nf-cmgg-preprocessing-methods-description":
     order: -1000

conf/modules.config

@@ -209,11 +209,13 @@ process {
     withName: ".*FASTQ_TO_CRAM:SAMTOOLS_SORMADUP" {
         ext.prefix = {"${meta.id}.merged"}
         ext.args5 = {[
-            "--json",
-            "-d 2500",
-            "--write-index",
-            "--output-fmt cram",
-            "--output-fmt-option archive"
+            "-s",                                       // print some stats
+            "--json",                                   // output stats in json format for MultiQC
+            "-d 2500",                                  // The optical duplicate distance
+            params.umi_aware ? "--barcode-name" : "",   // Use the UMI/barcode embedded in the read name (eigth colon delimited part).
+            "--write-index",                            // Write csi/crai index
+            "--output-fmt cram",                        // Output format
+            "--output-fmt-option archive"               // Cram compression level
         ].join(" ").trim()}
         publishDir = [
             [
@@ -269,7 +271,8 @@ process {
 
     //// Samtools convert
     withName: ".*FASTQ_TO_CRAM:SAMTOOLS_CONVERT" {
-        label = "process_medium"
+        cpus   = 8
+        memory = 64.GB
         ext.args = {[
             "-C",
             "--output-fmt cram",
@@ -336,7 +339,7 @@ process {
     //// Picard
     withName: ".*PICARD.*" {
         memory = { 8.GB * task.attempt }
-        ext.args = "--MAX_RECORDS_IN_RAM 10000000"
+        ext.args = "--MAX_RECORDS_IN_RAM 15000000"
     }
 
 

conf/profiles/WGS.config

@@ -1,5 +1,7 @@
 params {
     aligner                 = "snap"
+    markdup                 = "samtools"
+    umi_aware               = true
     run_coverage            = true
     disable_picard_metrics  = false
 }

modules.json

@@ -99,28 +99,28 @@
                     },
                     "samtools/coverage": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/samtools/coverage/samtools-coverage.diff"
                     },
                     "samtools/flagstat": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
                         "installed_by": ["modules"]
                     },
                     "samtools/idxstats": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
                         "installed_by": ["modules"]
                     },
                     "samtools/import": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
                         "installed_by": ["modules"]
                     },
                     "samtools/sormadup": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "git_sha": "38f3b0200093498b70ac2d63a83eac5642e3c873",
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/samtools/sormadup/samtools-sormadup.diff"
                     },
@@ -132,7 +132,7 @@
                     },
                     "samtools/stats": {
                         "branch": "master",
-                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/samtools/stats/samtools-stats.diff"
                     },

modules/local/panelcoverage/main.nf

@@ -1,5 +1,5 @@
 process PANELCOVERAGE {
-    tag "$meta.id - $genelist"
+    tag "$meta.id"
     label 'process_single'
 
     conda "${moduleDir}/environment.yml"
@@ -8,7 +8,8 @@ process PANELCOVERAGE {
         'biocontainers/bedtools:2.31.1--hf5e1c6e_1' }"
 
     input:
-    tuple val(meta), path(perbase), path(perbase_index), path(genelist)
+    tuple val(meta), path(perbase), path(perbase_index)
+    path(genelists)
 
     output:
     tuple val(meta), path("*.mosdepth.region.dist.txt"), emit: regiondist
@@ -20,7 +21,10 @@ process PANELCOVERAGE {
     script:
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    cmgg_genelists regiondist --samplename ${prefix} --perbase ${perbase} --genelist ${genelist}
+    for GENELIST in $genelists
+    do
+        cmgg_genelists regiondist --samplename ${prefix} --perbase ${perbase} --genelist \$GENELIST
+    done
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -32,7 +36,11 @@ process PANELCOVERAGE {
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${prefix}_genelist.mosdepth.region.dist.txt
+    for GENELIST in $genelists
+    do
+        name=\$(basename \$GENELIST .bed)
+        touch ${prefix}_\${name}.mosdepth.region.dist.txt
+    done
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":