create_bqsr_ref_intervals.pbs

#!/bin/bash

#########################################################
# 
# Platform: NCI Gadi HPC
# Description: Create evenly sized intervals over which to parallelise 
#	GATK BQSR. The number of intervals is determined by the script,
#	setting minimum interval size to 100 Mb. 
# Author: Cali Willet
# cali.willet@sydney.edu.au
# Date last modified: 14/10/2020
#
# If you use this script towards a publication, please acknowledge the
# Sydney Informatics Hub (or co-authorship, where appropriate).
#
# Suggested acknowledgement:
# The authors acknowledge the scientific and technical assistance 
# <or e.g. bioinformatics assistance of <PERSON>> of Sydney Informatics
# Hub and resources and services from the National Computational 
# Infrastructure (NCI), which is supported by the Australian Government
# with access facilitated by the University of Sydney.
# 
######################################################### 

#PBS -P <project>
#PBS -N bqsr-int-gen
#PBS -l walltime=00:30:00
#PBS -l ncpus=1
#PBS -l mem=4GB
#PBS -q normal
#PBS -W umask=022
#PBS -l wd
#PBS -o ./Logs/bqsr_intervals.o
#PBS -e ./Logs/bqsr_intervals.e
#PBS -lstorage=<lstorage>

module load gatk/4.1.2.0

set -e

ref=<ref>
dict=<dict>

# Determine number of intervals based on genome size
min=100000000 # min 100 Mb per interval for scattered BQSR table creation
size=$(awk 'NR>1 {print $3}' ${dict} | cut -d ':' -f 2 | awk '{sum+=$1} END {print sum}')
int=$(expr $size / $min)

gatk SplitIntervals \
	--java-options "-Xmx3g" \
        -R $ref \
        -scatter-count ${int} \
        -O ./Reference/BQSR_intervals