AdvGeneMap2018Commands

Plink - Part 1 - Data QC

#PLINK
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
#### in R - open R by simply typing R
setwd("to_your_working_directory/")
sexcheck = read.table("GWAS_sex_checking.sexcheck", header=T)
names(sexcheck)
sex_problem = sexcheck[which(sexcheck$STATUS=="PROBLEM"),]
sex_problem
q()
##################################
plink --file GWAS_clean2 --genome --out duplicates
#### in R
setwd("to_your_working_directory/")
dups = read.table("duplicates.genome", header = T)
problem_pairs = dups[which(dups$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]
q()
######
plink --file GWAS_clean2 --remove IBS_excluded.txt --recode --out GWAS_clean3
plink --file GWAS_clean3 --het
###### in R
Dataset

Plink - Part 2 - Controlling for Substructure

plink --file GWAS_clean4 --genome --cluster --mds-plot 10
 #### in R
 mydata = read.table("mds_components.txt", header=T)
 mydata$pch[mydata$Group==1 ]  	observed¶   	lobs

expected ¶ lexp plot(c(0,7), c(0,7), col="red", lwd=3, type="l", xlab="Expected (-logP)", ylab="Observed (-logP)", xlim=c(0,max(lobs)), ylim=c(0,max(lobs)), las=1, xaxs="i", yaxs="i", bty="l", main = title) points(lexp, lobs, pch=23, cex=.4, bg="black") }

 jpeg("qqplot_compare.jpeg", height=1000, width=500)
 par(mfrow=c(2,1))
 aff_unadj<-read.table("unadj.assoc.logistic", header=TRUE)
 aff_unadj.add.p<-aff_unadj[aff_unadj$TEST==c("ADD"),]$P
 broadqq(aff_unadj.add.p,"Some Trait Unadjusted")
 aff_C1C2<-read.table("PC1-PC2.assoc.logistic", header=TRUE)
 aff_C1C2.add.p<-aff_C1C2[aff_C1C2$TEST==c("ADD"),]$P
 broadqq(aff_C1C2.add.p, "Some Trait Adjusted for PC1 and PC2")
 dev.off()
 gws_unadj = aff_unadj[which(aff_unadj$P < 0.0000001),]
 gws_unadj
 gws_adjusted = aff_C1C2[which(aff_C1C2$P < 0.0000001),]
 gws_adjusted