GQT CEPH pedigree analysis

gistfile1.sh

wget ftp://ftp-trace.ncbi.nih.gov/giab/ftp/data/NA12878/variant_calls/RTG/cohort-illumina-wgs.vcf.gz
bcftools index cohort-illumina-wgs.vcf.gz
gqt convert bcf -i cohort-illumina-wgs.vcf.gz
wget --trust-server-names http://bit.ly/ceph_ped
head ceph1463.ped
gqt convert ped \
    -i cohort-illumina-wgs.vcf.gz \
    -p ceph1463.ped
gqt query -i cohort-illumina-wgs.vcf.gz.gqt -d ceph1463.ped.db \
    -p "sample_id in ('NA12891','NA12892','NA12877')" \
    -g "HOM_REF" \
    -c
gqt query -i cohort-illumina-wgs.vcf.gz.gqt -d ceph1463.ped.db \
    -p "sample_id in ('NA12891','NA12892','NA12877')" \
    -g "HOM_REF" \
    -p "sample_id = 'NA12878'" \
    -g "HET" \
    -c
gqt query -i cohort-illumina-wgs.vcf.gz.gqt -d ceph1463.ped.db \
    -p "sample_id in ('NA12891','NA12892','NA12877')" \
    -g "HOM_REF" \
    -p "sample_id = 'NA12878'" \
    -g "HET" \
    -p "maternal_id = 'NA12878'" \
    -g "pct(HET)>=0.3" \
    -c
gqt query -i cohort-illumina-wgs.vcf.gz.gqt -d ceph1463.ped.db \
    -p "sample_id in ('NA12891','NA12892','NA12877')" \
    -g "HOM_REF" \
    -p "sample_id = 'NA12878'" \
    -g "HET" \
    -p "maternal_id = 'NA12878'" \
    -g "pct(HET)>=0.3" \
    | bcftools view - -H -i 'min(DP)>=500' \
    | wc -l
wget --trust-server-names http://bit.ly/gqt_exons
head exons.bed
gqt query -i cohort-illumina-wgs.vcf.gz.gqt -d ceph1463.ped.db \
    -p "sample_id in ('NA12891','NA12892','NA12877')" \
    -g "HOM_REF" \
    -p "sample_id = 'NA12878'" \
    -g "HET" \
    -p "maternal_id = 'NA12878'" \
    -g "pct(HET)>=0.3" \
    | bcftools view - -i 'min(DP)>=500' \
    | bedtools intersect -a exons.bed -b stdin \
    > denovo_cover_exons.bed
wc -l denovo_cover_exons.bed