# Piped Commands from fastq to aligned BAM (ready for MarkDuplicatesSpark and then variant calling)

###### tags: 'expert level step'

## Pipe 1. Pipe FastqToSam and MarkIlluminaAdapters

#!/bin/bash
#SBATCH -e errs/%a_pipeline-%A.err 
#SBATCH -o outs/%a_pipeline-%A.out 
#SBATCH --mem-per-cpu=20G 
#SBATCH -p scavenger
#SBATCH --cpus-per-task=4 
#SBATCH --mail-type=ALL --mail-user=[e-mail]
#SBATCH -a 34,30,59,45,73

LL=${SLURM_ARRAY_TASK_ID}

module load GATK/4.1.9.0 

set -o pipefail

java -Xmx8G -jar $GATK FastqToSam \
--FASTQ ../data/2021_09_21_fastq/L${LL}_R1_001.fastq \
--FASTQ2 ../data/2021_09_21_fastq/L${LL}_R2_001.fastq \
--OUTPUT /dev/stdout \
--READ_GROUP_NAME L${LL} \
--SAMPLE_NAME L${LL} \
--LIBRARY_NAME L${LL} \
--PLATFORM Illumina \
--TMP_DIR /work/$USER | \
java -jar $GATK MarkIlluminaAdapters \
-I /dev/stdin \
-M ../data/2021_09_21_fastq/metrics/adapter_metrics_L${LL}.txt \
-O ../data/2021_09_21_fastq/uBAMs/unmapped_adapter_L${LL}.bam \
--TMP_DIR /work/$USER

## Pipe 2. Pipe SamToFastq, BWA mem and MergeBamAlignments

#!/bin/bash
#SBATCH -e errs/%a_pipeline-%A.err 
#SBATCH -o outs/%a_pipeline-%A.out 
#SBATCH --mem-per-cpu=20G 
#SBATCH -p scavenger
#SBATCH --cpus-per-task=4 
#SBATCH --mail-type=ALL --mail-user=[e-mail]
#SBATCH -a 30,34,45,59,73

LL=${SLURM_ARRAY_TASK_ID}

module load GATK/4.1.9.0 
module load BWA/0.7.17
module load Java/1.8.0_60

set -o pipefail

java -Xmx8G -jar $GATK SamToFastq --INTERLEAVE true \
--INPUT ../data/2021_09_21_fastq/uBAMs/unmapped_adapter_L${LL}.bam \
--FASTQ /dev/stdout \
--CLIPPING_ATTRIBUTE XT \
--CLIPPING_ACTION 2 \
--NON_PF true \
--TMP_DIR /work/$USER | \
bwa mem -M -t 4 -p ../ref/dmel-all-chromosome-r6.41.fasta /dev/stdin | \
java -Xmx16G -jar $GATK MergeBamAlignment \
-O ../data/2021_09_21_fastq/mergedBAMs/merged_L${LL}.bam \
-R ../ref/dmel-all-chromosome-r6.41.fasta \
-UNMAPPED_BAM ../data/2021_09_21_fastq/uBAMs/unmapped_adapter_L${LL}.bam \
-ALIGNED_BAM /dev/stdin \
-CREATE_INDEX true \
-ADD_MATE_CIGAR true \
-CLIP_ADAPTERS false \
-CLIP_OVERLAPPING_READS true \
-INCLUDE_SECONDARY_ALIGNMENTS true \
-MAX_INSERTIONS_OR_DELETIONS -1 \
-PRIMARY_ALIGNMENT_STRATEGY MostDistant \
-ATTRIBUTES_TO_RETAIN XS \
-TMP_DIR /work/$USER 


java -Xmx16G -jar $GATK MarkDuplicatesSpark \
-I ../data/2021_09_21_fastq/mergedBAMs/merged_L${LL}.bam \
-O ../data/2021_09_21_fastq/aligned_merged_mdup_BAMs/aligned_merged_mdup_L${LL}.bam \
-M ../data/2021_09_21_fastq/aligned_merged_mdup_BAMs/mdup_metrics_L${LL}.txt \
--tmp-dir /work/$USER