Changes

===VATRV-TDT=== ### Variant Annotation vtools init rvtdt vtools import --format vcf data/data.vcf --build hg19 vtools phenotype --from_file data/phen.txt vtools execute ANNOVAR geneanno vtools select variant "variant.region_type like '%splicing%'or variant.mut_type like 'nonsynonymous%' or variant.mut_type like 'frameshift%' or variant.mut_type like 'stop%'" -t func_variant vtools export func_variant --format tped --samples 'phenotype is not null' > vat_raw.tped # set marker name as chr_pos, needs to avoid duplicate name sort -k4 -n vat_raw.tped | awk 'BEGIN{OFS="\t";prev="None";copy=1} {$2=$1"_"$4; $3=0; if($2==prev) {$2=$2"_"copy; copy=copy+1} else {prev=$2; copy=1}; print $0}' > vat_export.tped vtools phenotype --out family sample_name pid mid sex phenotype > vat_export.tfam vtools use refGene-hg19_20130904 vtools update func_variant --set 'maf=0.001' # set the maf to be 0.001 vtools select func_variant -o chr pos refGene.name2 maf --header > vat_export.anno ### Phasing Trio plink --noweb --tfile vat_export --recode12 --me 1 1 --set-me-missing --out "recode12_noME" sort -n -k1 -k6 -k2 recode12_noME.ped | sed 's/ /\t/g' | cut -f1,3,4,5 --complement > linkage.ped cut -f2 recode12_noME.map | awk 'BEGIN{OFS="\t";} {print "M",$0}' | sed '1i\I\tid\nA\tDisease' > linkage.dat java -Xmx10000m -jar java/linkage2beagle.jar linkage.dat linkage.ped > pre_beagle.bgl python script/pre_phase.py -i pre_beagle.bgl -a pre_beagle_withMissing.bgl java -Xmx10000m -jar java/beagle.jar missing=0 trios=pre_beagle.bgl out=bgl_phased verbose=false redundant=true gunzip bgl_phased.pre_beagle.bgl.phased.gz ### RV-TDT Analysis python script/post_phase.py -a vat_export.anno -b bgl_phased.pre_beagle.bgl.phased -o genes/ for g in `ls genes | grep tped | cut -d"." -f1 | head -20` do echo "running rvTDT on gene "${g} rvTDT exercise_proj -G ./genes/${g}.tped -P ./data/rvtdt.phen -M ./genes/${g}.map --adapt 500 --alpha 0.00001 --permut 2000 --lower_cutoff 0 --upper_cutoff 100 --minVariants 3 --maxMissRatio 1 done done

vtools select variant "filter==’PASS’" --count vtools select variant "filter==’PASS’" -o "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header vtools update variant --from_stat ’total==#(GT)’ ’num==#(alt)’ ’het==#(het)’ ’hom==#(hom)’ ’other==#(other)’ ’minDP==min(DP_geno)’ ’maxDP==max(DP_geno)’ ’meanDP==avg(DP_geno)’ ’maf==maf()’

vtools update variant --from_stat ’totalGD10==#(GT)’ ’numGD10==#(alt)’ ’hetGD10==#(het)’ ’homGD10==#(hom)’ ’otherGD10==#(other)’ ’mafGD10==maf()’ --genotypes "DP_geno > 10"

vtools phenotype --set "RACE==0" --samples "filename like ’YRI%’" vtools phenotype --set "RACE==1" --samples "filename like ’CEU%’"

vtools update variant --from_stat ’CEU_mafGD10==maf()’ --genotypes ’DP_geno>10’ --samples "RACE==1" vtools update variant --from_stat ’YRI_mafGD10==maf()’ --genotypes ’DP_geno>10’ --samples "RACE==0"

vtools phenotype --from_stat ’CEU_totalGD10==#(GT)’ ’CEU_numGD10==#(alt)’ --genotypes ’DP_geno>10’ --samples "RACE==1" vtools phenotype --from_stat ’YRI_totalGD10==#(GT)’ ’YRI_numGD10==#(alt)’ --genotypes ’DP_geno>10’ --samples "RACE==0"

vtools select variant "mut_type like ’non%’ or mut_type like ’stop%’ or region_type==’splicing’" -t v_funct

vtools select variant --samples "RACE==1" -t CEU

vtools init ceu --parent ../ --variants CEU --samples "RACE==1" --build hg19 vtools show project vtools select variant "CEU_mafGD10>==0.05" -t common_ceu

vtools select rare_ceu "refGene.name2==’ABCC1’" -o chr pos ref alt CEU_mafGD10 numGD10 mut_type --header

vtools select variant --samples "RACE==0" -t YRI

vtools init yri --parent ../ --variants YRI --samples "RACE==0" --build hg19 vtools select variant "YRI_mafGD10>==0.05" -t common_yri vtools select v_funct "YRI_mafGD10<0.01" -t rare_yri