Difference between revisions of "Genome-wide Association-Quality Control Exercise"
From Statistical Genetics Courses
Serveradmin (Talk | contribs) (Created page with "__NOTITLE__ ==Genome-wide Association-Quality Control Exercise== plink --file GWAS plink --file GWAS --mind 0.10 --recode --out GWAS_clean_mind plink --file GWAS_clean_mi...") |
Serveradmin (Talk | contribs) |
||
(One intermediate revision by the same user not shown) | |||
Line 24: | Line 24: | ||
myvars = c("FID1", "IID1", "FID2", "IID2", "PI_HAT") | myvars = c("FID1", "IID1", "FID2", "IID2", "PI_HAT") | ||
problem_pairs[myvars] | problem_pairs[myvars] | ||
+ | plink --file GWAS_clean3 --pheno pheno.txt --pheno-name Aff --hardy | ||
+ | q() | ||
+ | plink --file GWAS_clean2 --remove IBS_excluded.txt --recode --out GWAS_clean3 | ||
+ | plink --file GWAS_clean3 --pheno pheno.txt --pheno-name Aff --hardy | ||
+ | R | ||
+ | hardy = read.table("plink.hwe", header = T) | ||
+ | names(hardy) | ||
+ | hwe_prob = hardy[which(hardy$P < 0.0000009),] | ||
+ | hwe_prob | ||
+ | q() | ||
+ | plink --file GWAS_clean3 --exclude HWE_out.txt --recode --out GWAS_clean4 |
Latest revision as of 18:07, 24 January 2019
Genome-wide Association-Quality Control Exercise
plink --file GWAS plink --file GWAS --mind 0.10 --recode --out GWAS_clean_mind plink --file GWAS_clean_mind --maf 0.05 --recode --out MAF_greater_5 plink --file GWAS_clean_mind --exclude MAF_greater_5.map --recode --out MAF_less_5 plink --file MAF_greater_5 --geno 0.05 --recode --out MAF_greater_5_clean plink --file MAF_less_5 --geno 0.01 --recode --out MAF_less_5_clean plink --file MAF_greater_5_clean --merge MAF_less_5_clean.ped MAF_less_5_clean.map --recode --out GWAS_MAF_clean plink --file GWAS_MAF_clean --mind 0.03 --recode --out GWAS_clean2 plink --file GWAS_clean2 --check-sex --out GWAS_sex_checking R sexcheck = read.table("GWAS_sex_checking.sexcheck", header=T) names(sexcheck) sex_problem = sexcheck[which(sexcheck$STATUS=="PROBLEM"),] sex_problem q() plink --file GWAS_clean2 --genome --out duplicates R dups = read.table("duplicates.genome", header = T) problem_pairs = dups[which(dups$PI_HAT > 0.4),] problem_pairs problem_pairs = dups[which(dups$PI_HAT > 0.05),] myvars = c("FID1", "IID1", "FID2", "IID2", "PI_HAT") problem_pairs[myvars] plink --file GWAS_clean3 --pheno pheno.txt --pheno-name Aff --hardy q() plink --file GWAS_clean2 --remove IBS_excluded.txt --recode --out GWAS_clean3 plink --file GWAS_clean3 --pheno pheno.txt --pheno-name Aff --hardy R hardy = read.table("plink.hwe", header = T) names(hardy) hwe_prob = hardy[which(hardy$P < 0.0000009),] hwe_prob q() plink --file GWAS_clean3 --exclude HWE_out.txt --recode --out GWAS_clean4