GWAS Data QC
cd GWAS_part2
plink --file GWAS --noweb
plink --file GWAS --mind 0.10 --recode --out GWAS_clean_mind --noweb
plink --file MAF_greater_5_clean --merge MAF_less_5_clean.ped MAF_less_5_clean.map --recode --out GWAS_MAF_clean --noweb
plink --file GWAS_MAF_clean --mind 0.03 --recode --out GWAS_clean2 --noweb
R
plink --file GWAS_clean2 --check-sex --out GWAS_sex_checking --noweb
R
sexcheck = read.table("GWAS_sex_checking.sexcheck", header=T)
names(sexcheck)
plink --file GWAS_clean2 --genome --out duplicates --noweb
R
dups = read.table(“duplicates"duplicates.genome”genome", header = T)
problem_pairs = dups[which(dups$PI_HAT > 0.4),]
problem_pairs
plink --file GWAS_clean3 --pheno pheno.txt --pheno-name Aff --hardy --noweb
R
hardy = read.table(“plink"plink.hwe”hwe", header = T)
names(hardy)
hwe_prob = hardy[which(hardy$P < 0.0000009),]