Merge pull request #90 from CenterForMedicalGeneticsGhent/dev

Release 1.1.2

CHANGELOG.md

@@ -3,6 +3,16 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.1.2 - Groovy Ghent - [Mar 21 2023]
+
+### New features
+
+1. Added a parameter for setting the splitting depth threshold `--split_threshold FLOAT`
+
+### Changes
+
+1. Change the default splitting threshold to 0.2 instead of 0.3
+
 ## v1.1.1 - Golden Ghent - [Mar 20 2023]
 
 ### Changes

modules/local/split_beds/main.nf

@@ -9,6 +9,7 @@ process SPLIT_BEDS {
 
     input:
     tuple val(meta), path(bed), val(sample_count)
+    val(single_threshold)
 
     output:
     tuple val(meta), path("*.bed")  , emit: beds
@@ -19,15 +20,15 @@ process SPLIT_BEDS {
 
     script:
     def prefix = task.ext.prefix ?: meta.id
-    def threshold = sample_count * 0.3
+    def threshold = sample_count * single_threshold
     // This module will split a BED file created with goleft/indexsplit into 
-    // multiple BED files. All regions that have a scaled data size lower than 0.3 * amount of samples
+    // multiple BED files. All regions that have a scaled data size lower than single_threshold * amount of samples
     // will be merged into one BED file. All regions that have a higher scaled data size
     // will be put into their own BED file. Also all regions with no reads are removed.
     """
     awk -vFS="\t" '{
         if (\$0 ~ /^[^#].*\$/ && \$5 >= 1) {
-            if (\$4 >= ${threshold}) {
+            if (\$4 > ${threshold}) {
                 print \$0 > sprintf("${prefix}_%s_%s_%s.bed", \$1, \$2, \$3)
             } else {
                 print \$0 > "${prefix}_others.bed"

nextflow.config

@@ -14,7 +14,7 @@ params {
 
     // Pipeline specific parameters
     scatter_count              = 40
-    // bed_merge_distance         = 3000000
+    split_threshold            = 0.2
     filter                     = false
     annotate                   = false
     gemini                     = false
@@ -244,7 +244,7 @@ manifest {
     description     = 'A nextflow pipeline for calling and annotating variants'
     mainScript      = 'main.nf'
     nextflowVersion = '!>=22.10.5'
-    version = '1.1.1'
+    version = '1.1.2'
 }
 
 // Load modules.config for DSL2 module specific options

nextflow_schema.json

@@ -137,6 +137,11 @@
                     "default": 40,
                     "description": "The amount of scattering that should happen per sample. Increase this number to increase the pipeline run speed, but at the tradeoff of using more IO and disk space. The actual scatter value can differ a bit (usually not a bigger difference than 1) when using alt contigs in the reference."
                 },
+                "split_threshold": {
+                    "type": "number",
+                    "default": 0.2,
+                    "description": "The exclusive threshold to use when defining whether a region has very low depth. This value is used to concatenate all small, low depth regions for WGS"
+                },
                 "species": {
                     "type": "string",
                     "default": "homo_sapiens",

subworkflows/local/germline_variant_calling.nf

@@ -32,7 +32,8 @@ workflow GERMLINE_VARIANT_CALLING {
     //
 
     SPLIT_BEDS(
-        beds.map { it + [1] }
+        beds.map { it + [1] },
+        params.split_threshold.toFloat()
     )
     ch_versions = ch_versions.mix(SPLIT_BEDS.out.versions.first())
 

subworkflows/local/joint_genotyping.nf

@@ -53,7 +53,8 @@ workflow JOINT_GENOTYPING {
                 }
             }
             [ meta, bed, meta.family_count ]
-        }
+        },
+        params.split_threshold.toFloat()
     )
     ch_versions = ch_versions.mix(SPLIT_BEDS.out.versions.first())