Merge pull request #17 from TRON-Bioinformatics/split-multimapper

Adapt SplitNCigarReads command to also split multimappers

Author: priesgo

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 {
@@ -76,7 +77,8 @@ process SPLIT_CIGAR_N_READS {
     --input ${bam} \
     --output ${name}.split_cigarn.bam \
     --create-output-bam-index true \
-    --reference ${reference}
+    --reference ${reference} \
+    ${params.split_cigarn_args}
 
     cp ${name}.split_cigarn.bai ${name}.split_cigarn.bam.bai
 

nextflow.config

@@ -8,9 +8,7 @@
 profiles {
   conda { params.enable_conda = true }
   debug { process.beforeScript = 'echo $HOSTNAME' }
-  test {
-    params.input_files = "test_data/test_input.txt"
-    params.reference = "$baseDir/test_data/ucsc.hg19.minimal.fasta"
+  ci {
     params.prepare_bam_cpus = 1
     params.prepare_bam_memory = "3g"
     params.mark_duplicates_cpus = 1
@@ -23,15 +21,19 @@ profiles {
     params.metrics_memory = "3g"
     params.index_cpus = 1
     params.index_memory = "3g"
-    params.known_indels1 = "$baseDir/test_data/1000G_phase1.indels.hg19.sites.minimal.vcf"
-    params.known_indels2 = "$baseDir/test_data/Mills_and_1000G_gold_standard.indels.hg19.sites.sorted.minimal.vcf"
-    params.intervals = "$baseDir/test_data/minimal_intervals.bed"
-    params.dbsnp = "$baseDir/test_data/dbsnp_138.hg19.minimal.vcf"
     timeline.enabled = false
     report.enabled = false
     trace.enabled = false
     dag.enabled = false
   }
+  test {
+    params.input_files = "test_data/test_input.txt"
+    params.reference = "$baseDir/test_data/ucsc.hg19.minimal.fasta"
+    params.known_indels1 = "$baseDir/test_data/1000G_phase1.indels.hg19.sites.minimal.vcf"
+    params.known_indels2 = "$baseDir/test_data/Mills_and_1000G_gold_standard.indels.hg19.sites.sorted.minimal.vcf"
+    params.intervals = "$baseDir/test_data/minimal_intervals.bed"
+    params.dbsnp = "$baseDir/test_data/dbsnp_138.hg19.minimal.vcf"
+  }
 }
 
 // Export this variable to prevent local Python libraries from conflicting with those in the container
@@ -91,6 +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)

tests/test_01.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test1
-nextflow main.nf -profile test,conda --output $output
+nextflow main.nf -profile test,conda,ci --output $output
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }

tests/test_02.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test2
-nextflow main.nf -profile test,conda --output $output --skip_bqsr
+nextflow main.nf -profile test,conda,ci --output $output --skip_bqsr
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }

tests/test_03.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test3
-nextflow main.nf -profile test,conda --output $output --skip_realignment
+nextflow main.nf -profile test,conda,ci --output $output --skip_realignment
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }

tests/test_04.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test4
-nextflow main.nf -profile test,conda --output $output --skip_deduplication
+nextflow main.nf -profile test,conda,ci --output $output --skip_deduplication
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }

tests/test_05.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test5
-nextflow main.nf -profile test,conda --output $output --skip_deduplication --skip_bqsr --skip_metrics --known_indels1 false --known_indels2 false
+nextflow main.nf -profile test,conda,ci --output $output --skip_deduplication --skip_bqsr --skip_metrics --known_indels1 false --known_indels2 false
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }

tests/test_06.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test6
-nextflow main.nf -profile test,conda --output $output --intervals false --skip_deduplication --skip_bqsr --skip_realignment
+nextflow main.nf -profile test,conda,ci --output $output --intervals false --skip_deduplication --skip_bqsr --skip_realignment
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }

tests/test_07.sh

@@ -3,7 +3,7 @@
 
 source tests/assert.sh
 output=output/test7
-nextflow main.nf -profile test,conda --output $output --skip_bqsr --skip_realignment
+nextflow main.nf -profile test,conda,ci --output $output --skip_bqsr --skip_realignment
 
 test -s $output/sample1/sample1.preprocessed.bam || { echo "Missing output BAM file!"; exit 1; }
 test -s $output/sample1/sample1.preprocessed.bai || { echo "Missing output BAI file!"; exit 1; }