sam_compress

#!/bin/bash
#SBATCH -n 8                # Number of cores
#SBATCH -N 1                # Ensure that all cores are on one machine
#SBATCH --constraint=intel  # only use faster intel cores
#SBATCH -t 3-00:00          # Runtime in D-HH:MM, minimum of 10 minutes
#SBATCH -p shared  # Partition to submit to
#SBATCH --mem=16000           # Memory pool for all cores (see also --mem-per-cpu)
#SBATCH	-J sam_compress            # Job name for job
#SBATCH -o sam_compress_%j.out  # File to which STDOUT will be written, %j inserts jobid
#SBATCH -e sam_compress_%j.err  # File to which STDERR will be written, %j inserts jobid
#SBATCH --mail-type=ALL        # Type of email notification- BEGIN,END,FAIL,ALL
#SBATCH --mail-user= # Email to which notifications will be sent

# arguments
# ${1} = the folder location to compress SAM
# within this folder, all .sam files greater than 100 MB will be compressed
# and the original files will be deleted

if [[ $# -eq 0 ]]; then
	echo "ERROR: No directory provided to search for SAM files"
	echo "Try issuing the following commands with <target_directory> set to the directory where you want to compress SAM files:"
	echo "$ directory=<target_directory>"
	echo "$ sbatch -o \${directory}_sam_compress.out -e \${directory}_sam_compress.err sam_compress \${directory}"
	exit 1
fi

# load modules and environments
module purge
module load samtools

# commands to run
find ${1} -type f -name "*.sam" -size +100M | 
while read file; 
do
output=`echo ${file} | sed 's/\.sam$/\.bam/g'`; 
cat ${file} | samtools view -@ ${SLURM_NTASKS} -b - > ${output} 2> >(awk -v file=${file} '{ print file": " $0 }' >&2) &&
samtools index -@ ${SLURM_NTASKS} ${output} 2> >(awk -v file=${file} '{ print file": " $0 }' >&2) &&
rm ${file} 2> >(awk -v file=${file} '{ print file": " $0 }' >&2)
done