Add split_cigarn_args parameter

Author: LKress

README.md

@@ -84,6 +84,8 @@ Optional input:
     * --skip_metrics: optionally skip metrics (default: false)
     * --output: the folder where to publish output (default: ./output)
     * --platform: the platform to be added to the BAM header. Valid values: [ILLUMINA, SOLID, LS454, HELICOS and PACBIO] (default: ILLUMINA)
+    * --split_cigarn: split reads that contain Ns in their cigar string (e.g. spanning splicing events in RNAseq data) using GATKs SplitNCigarReads
+    * --split_cigarn_args: additional arguments for SplitNCigarReads
 
 Computational resources:
     * --prepare_bam_cpus: (default: 3)

modules/02_mark_duplicates.nf

@@ -4,6 +4,7 @@ params.split_reads_cpus = 2
 params.split_reads_memory = "4g"
 params.remove_duplicates = true
 params.output = 'output'
+params.split_cigarn_args = ""
 
 
 process MARK_DUPLICATES {
@@ -76,8 +77,8 @@ process SPLIT_CIGAR_N_READS {
     --input ${bam} \
     --output ${name}.split_cigarn.bam \
     --create-output-bam-index true \
-    --process-secondary-alignments true \
-    --reference ${reference}
+    --reference ${reference} \
+    ${params.split_cigarn_args}
 
     cp ${name}.split_cigarn.bai ${name}.split_cigarn.bam.bai
 

nextflow.config

@@ -93,6 +93,8 @@ Optional input:
     * --skip_metrics: optionally skip metrics (default: false)
     * --output: the folder where to publish output (default: ./output)
     * --platform: the platform to be added to the BAM header. Valid values: [ILLUMINA, SOLID, LS454, HELICOS and PACBIO] (default: ILLUMINA)
+    * --split_cigarn: split reads that contain Ns in their cigar string (e.g. spanning splicing events in RNAseq data) using GATKs SplitNCigarReads
+    * --split_cigarn_args: additional arguments for SplitNCigarReads
 
 Computational resources:
     * --prepare_bam_cpus: (default: 3)