Merge pull request #2 from TRON-Bioinformatics/picard2bedtools

replace picard by bedtools for the bam2fastq

Author: Pablo Riesgo-Ferreiro

CHANGELOG.md

@@ -0,0 +1,40 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+### Added
+
+### Changed
+
+### Removed
+
+
+## [0.3.0] - 2024-03-25
+
+### Changed
+
+- Replaced GATKs SamToFastq by bedtools bamtofastq to avoid issue with unmated reads
+
+
+## [0.2.0] - 2024-03-25
+
+### Added
+
+- Add support for BAM files as input files. It extracts the reads aligned to the MHC region in the canonical 
+chromosome 6 + all reads from chromosome 6 alt contigs + unmapped reads and converts into FASTQs
+
+
+## [0.1.0] - 2022-11-02
+
+- First release!
+
+
+[unreleased]: https://github.com/tron-bioinformatics/tronflow-hla-hd/compare/v0.3.0...HEAD
+[0.3.0]: https://github.com/tron-bioinformatics/tronflow-hla-hd/compare/v0.2.0...v0.3.0
+[0.2.0]: https://github.com/tron-bioinformatics/tronflow-hla-hd/compare/v0.1.0...v0.2.0
+[0.1.0]: https://github.com/tron-bioinformatics/tronflow-hla-hd/releases/tag/v0.1.0

modules/00_bam2fastq.nf

@@ -5,7 +5,7 @@ process BAM2FASTQ {
     publishDir "${params.output}/${name}", mode: "copy", pattern: "*.txt"
     module params.bowtie2_module
 
-    conda (params.enable_conda ? "bioconda::samtools=1.18 bioconda::gatk4=4.2.5.0" : null)
+    conda (params.enable_conda ? "bioconda::samtools=1.18 bioconda::bedtools=2.31.1" : null)
 
     input:
     tuple val(name), val(bam)
@@ -31,12 +31,21 @@ process BAM2FASTQ {
 
     #Merge bam files
     samtools merge -o ${name}.merge.bam ${name}.unmap.bam ${name}.mhc.bam
+    rm -f ${name}.unmap.bam
+    rm -f ${name}.mhc.bam
+
+    # sort BAM by read name
+    samtools sort -n ${name}.merge.bam -o ${name}.merge.sorted.bam
+    rm -f ${name}.merge.bam
 
     #Create fastq
-    gatk SamToFastq --VALIDATION_STRINGENCY SILENT -I ${name}.merge.bam -F ${name}.hlatmp.1.fastq -F2 ${name}.hlatmp.2.fastq
+    bedtools bamtofastq -i ${name}.merge.sorted.bam -fq ${name}.hlatmp.1.fastq -fq2 ${name}.hlatmp.2.fastq
 
     #Change fastq ID
     cat ${name}.hlatmp.1.fastq |awk '{if(NR%4 == 1){O=\$0;gsub("/1"," 1",O);print O}else{print \$0}}' | gzip > ${name}.hla.1.fastq.gz
     cat ${name}.hlatmp.2.fastq |awk '{if(NR%4 == 1){O=\$0;gsub("/2"," 2",O);print O}else{print \$0}}' | gzip > ${name}.hla.2.fastq.gz
+
+    rm -f ${name}.hlatmp.1.fastq
+    rm -f ${name}.hlatmp.2.fastq
     """
 }

nextflow.config

@@ -39,7 +39,7 @@ env {
 // Capture exit codes from upstream processes when piping
 process.shell = ['/bin/bash', '-euo', 'pipefail']
 
-VERSION = '0.2.0'
+VERSION = '0.3.0'
 
 manifest {
   name = 'TRON-Bioinformatics/tronflow-hlahd'