Changes
From Statistical Genetics Courses
__NOTITLE__ ==RV-TDT==<pre>### Variant Annotation
vtools init rvtdt
vtools import --format vcf data/data.vcf --build hg19
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
