Quality filtering VCF

#We quality filtered our VCF files before using them for the analysis 

------> gatk_filter.sh <------
#!/bin/bash
#SBATCH --job-name=gatk_filter
#SBATCH --partition=hpc
#SBATCH --nodes=1
#SBATCH --cpus-per-task=4
#SBATCH --ntasks-per-node=1
#SBATCH --mem=30g
#SBATCH --time=24:00:00
#SBATCH --output=/shared/home/mbxrs14/project_3/err_out/%x%r.out
#SBATCH --error=/shared/home/mbxrs14/project_3/err_out/%x%r.err

# These steps are required to activate conda
source $HOME/.bash_profile

gatk --java-options "-Xmx4g" VariantFiltration \
-V /shared/home/mbxrs14/project_3/LAB_NEN_ODN.clean_BI.ann.vcf.gz \
--filter-expression "ExcessHet > 54.69" \
--filter-name "ExcessHet" \
-O /shared/home/mbxrs14/project_3/gatk/cohort_excesshet.vcf.gz 


gatk SelectVariants \
-V /shared/home/mbxrs14/project_3/gatk/cohort_excesshet.vcf.gz \
-select-type SNP \
-O /shared/home/mbxrs14/project_3/gatk/snp_cohort_excesshet.vcf.gz

gatk VariantFiltration \
-V /shared/home/mbxrs14/project_3/gatk/snp_cohort_excesshet.vcf.gz \
-filter "DP < 10" --filter-name "DP10" \
-filter "DP > 200" --filter-name "DP200" \
-filter "GQ < 40" --filter-name "GQ40" \
-filter "AD < 10" --filter-name "AD10" \
-filter "AD > 200" --filter-name "AD200" \
-O /shared/home/mbxrs14/project_3/gatk/filt_snp_cohort_excesshet.vcf.gz