GWAS Data QC
cd plink/exercise/GWAS_part2 plink --file GWAS--noweb plink –-file GWAS –-mind 0.10 –-recode –-out GWAS_clean_mind--noweb plink –-file GWAS_clean_mind –-maf 0.05 –-recode –-out MAF_greater_5--noweb plink –-file GWAS_clean_mind –-exclude MAF_greater_5.map –-recode –-out MAF_less_5--noweb plink --file MAF_greater_5 --geno 0.05 --recode --out MAF_greater_5_clean--noweb plink --file MAF_less_5 --geno 0.01 --recode --out MAF_less_5_clean--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
sexcheck = read.table("GWAS_sex_checking.sexcheck", header=T)
names(sexcheck)
sex_problem
q()
plink –-file GWAS_clean2 –-genome –-out duplicates--noweb
R
dups = read.table(“duplicates.genome”, header = T)
problem_pairs[myvars]
q()
plink --file GWAS_clean2 --remove IBS_excluded.txt --recode --out GWAS_clean3--noweb plink –-file GWAS_clean3 –-het--noweb
R
Dataset <- read.table("plink.het", header=TRUE, sep="", na.strings="NA", dec=".",
dev.off()
q()
plink –-file GWAS_clean3 –-pheno pheno.txt –-pheno-name Aff –-hardy--noweb
R
hardy = read.table(“plink.hwe”, header = T)
hwe_prob
q()
plink –-file GWAS_clean3 –-exclude HWE_out.txt –-recode –-out GWAS_clean4--noweb
Multifactorial
dev.off()
q()
plink –-file GWAS_clean4 –-pheno pheno.txt –-pheno-name Aff –-logistic --adjust –-out unadj--noweb plink –-file GWAS_clean4 –-pheno pheno.txt –-pheno-name Aff –-covar plink.mds –-covar-name C1 –-logistic –-adjust –-out C1--noweb plink –-file GWAS_clean4 –-pheno pheno.txt –-pheno-name Aff –-covar plink.mds –-covar-name C1-C2 –-logistic –-adjust –-out C1-C2--noweb
R
broadqq <-function(pvals, title)