Merge pull request #122 from nf-cmgg/dev

v2.0.4

Author: matthdsm

CHANGELOG.md

@@ -5,6 +5,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## dev
 
+# v2.0.4
+
+- Add flag to `snap` to allow for more expansion of compressed data
+- Parse readgroup samplenames for `snp_` prefixed samples
+- Replace GRCh39 by mm10 as default genome for `Mus musculus`
+
 ## v2.0.3
 
 - Update modules

assets/multiqc_config.yml

@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-cmgg/preprocessing/releases/tag/2.0.3/" target="_blank">nf-cmgg/preprocessing</a>
+  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.
 report_section_order:
   "nf-cmgg-preprocessing-methods-description":

conf/igenomes.config

@@ -43,7 +43,21 @@ params {
             dragmap     = "${params.igenomes_base}/Mmusculus/GRCm39/dragmap"
             snap        = "${params.igenomes_base}/Mmusculus/GRCm39/snapaligner"
             star        = "${params.igenomes_base}/Mmusculus/GRCm39/star"
+        }
+        "mm10" {
+            // Genome reference
+            fai         = "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.fa.fai"
+            fasta       = "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.fa"
+            dict        = "${params.igenomes_base}/Mmusculus/mm10/seq/mm10.dict"
+            gtf         = "${params.igenomes_base}/Mmusculus/mm10/seq/Mus_musculus.GRCm38.102.chr.gtf"
 
+            // Aligner reference
+            bowtie2     = "${params.igenomes_base}/Mmusculus/mm10/bowtie2"
+            bwamem      = "${params.igenomes_base}/Mmusculus/mm10/bwa"
+            bwamem2     = "${params.igenomes_base}/Mmusculus/mm10/bwamem2"
+            dragmap     = "${params.igenomes_base}/Mmusculus/mm10/dragmap"
+            snap        = "${params.igenomes_base}/Mmusculus/mm10/snapaligner"
+            star        = "${params.igenomes_base}/Mmusculus/mm10/star"
         }
         "GRCz11" {
             // Genome reference

conf/modules.config

@@ -162,6 +162,7 @@ process {
     // -hc-   : enable DRAGEN compatible mode
     // -S id  : disable indexing and duplicate marking
     // -sa    : include secondary and supplementary alignments
+    // -xf 2  : expansion factor for reading compressed data
 
     //// SNAP
     withName: SNAP_ALIGN {
@@ -172,6 +173,7 @@ process {
             "-hc-",
             "-S id",
             "-sa",
+            "-xf 2",
             meta.readgroup ? "-R \"@RG\\t" + meta.readgroup.findResults{ it.value?.trim() ? "$it.key:$it.value" : null }.join("\\t") + "\"" : ""
         ].join(" ").trim()}
     }

nextflow.config

@@ -255,7 +255,7 @@ manifest {
     description     = """Demultiplexing, adapter trimming, alignment, and coverage calculation for NGS data."""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=24.10.0'
-    version         = '2.0.3'
+    version         = '2.0.4'
     doi             = ''
 }
 

workflows/preprocessing.nf

@@ -121,7 +121,9 @@ workflow PREPROCESSING {
         def single_end = fastq[1] ? false : true
         // add readgroup metadata
         def rg = readgroup_from_fastq(fastq[0])
-        rg = rg + [ 'SM': meta.samplename,
+        // if the sample name starts with "snp_", remove it so the sampletracking works later on.
+        def samplename = meta.samplename.startsWith("snp_") ? meta.samplename[4..-1] : meta.samplename
+        rg = rg + [ 'SM': samplename,
                     'LB': meta.library ?: "",
                     'PL': meta.platform ?: rg.PL,
                     'ID': meta.readgroup ?: rg.ID
@@ -145,7 +147,7 @@ workflow PREPROCESSING {
             if (meta.organism ==~ /(?i)Homo[\s_]sapiens/) {
                 meta = meta + ["genome":"GRCh38"]
             } else if (meta.organism ==~ /(?i)Mus[\s_]musculus/) {
-                meta = meta + ["genome":"GRCm39"]
+                meta = meta + ["genome":"mm10"]
             } else if (meta.organism ==~/(?i)Danio[\s_]rerio/) {
                 meta = meta + ["genome":"GRCz11"]
             } else {