EAS and SAS data in GenomeAsia100K panel

# GenomeAsia100K data are available at the links below. Users can download GA100K data in compressed Variant Call Format (VCF) file.
mkdir ~/hpc/db/GenomeAsia100K
cd ~/hpc/db/GenomeAsia100K
for i in {1..22}
do
wget --no-check-certificate https://browser.genomeasia100k.org/service/web/download_files/$i.substitutions.annot.cont_withmaf.vcf.gz &
done

cd ~/hpc/rheumatology/RA/meta3000/MIR
panel="hsa.gff3"
mkdir temp
for i in {1..22} X Y
do
echo \#PBS -N $i  > $i.job
echo \#PBS -l nodes=1:ppn=1 >> $i.job
echo \#PBS -M Guo.shicheng\@marshfieldresearch.org >> $i.job
echo \#PBS -o $(pwd)/temp/ >>$i.job
echo \#PBS -e $(pwd)/temp/ >>$i.job
echo cd $(pwd) >> $i.job
echo \# bcftools norm -m \+ ~/hpc/db/GenomeAsia100K/$i.substitutions.annot.cont_withmaf.vcf.gz -Oz -o $i.substitutions.annot.cont_withmaf.norm.vcf.gz >> $i.job
echo \# tabix -p vcf $i.substitutions.annot.cont_withmaf.norm.vcf.gz >> $i.job
echo bcftools view -v snps -f PASS -i \'INFO/AF_SAS\>0.01 \&INFO/AF_SEA\>0.01\' -T $panel.hg19.bed $i.substitutions.annot.cont_withmaf.norm.vcf.gz -Oz -o  gnomad.genomes.r2.1.sites.chr$i.rec.$panel.vcf.gz >>$i.job
echo bcftools sort $i.substitutions.annot.cont_withmaf.norm.vcf.gz -Oz -o $i.substitutions.annot.cont_withmaf.norm.sort.vcf.gz >> $i.job
echo bcftools norm -d $i.substitutions.annot.cont_withmaf.norm.sort.vcf.gz -Oz -o $i.substitutions.annot.cont_withmaf.sort.vcf.gz >> $i.job
echo bcftools view -m2 -M2 -v snps $i.substitutions.annot.cont_withmaf.sort.vcf.gz -Oz -o $i.substitutions.annot.cont_withmaf.$panel.sort.vcf.gz >>$i.job
qsub $i.job
done