View source for AdvGeneMap2017Commands

__NOTITLE__

==GeneABEL==

 plink --file GWAS_clean4 --pheno pheno.phen --pheno-name Aff --transpose --recode --out gwa_gabel --noweb
 plink --file GWAS_clean4 --pheno pheno.phen --pheno-name systolic --transpose --recode --out gwa_gabel_qtl --noweb
 R
 library(GenABEL)
 convert.snp.tped(tped = "gwa_gabel_qtl.tped", tfam = "gwa_gabel_qtl.tfam", out = "gwa_gabel_qtl.raw", strand = "u")
 g.dat &lt;- load.gwaa.data(phen = "gwa_gabel_qtl.praw", gen = "gwa_gabel_qtl.raw", force = T)
 slotNames(g.dat)
 slotNames(g.dat@gtdata)
 colnames(g.dat@phdata)
 sample.size &lt;- g.dat@gtdata@nids
 snps.total &lt;- g.dat@gtdata@nsnps
 print(c(sample.size, snps.total))
 summary(g.dat@phdata$disease)
 hist(g.dat@phdata$disease, main="Quantitative Phenotype data summary", xlab = "Systolic pressure", freq = F,breaks=20, col="gray")
 rug(g.dat@phdata$disease)
 test.snp &lt;- scan.glm('disease ~ CRSNP', family = gaussian(), data = g.dat)
 names(test.snp)  
 alpha &lt;- 5e-8
 test.snp$snpnames[test.snp$P1df < alpha]
 test.snp$P1df[test.snp$P1df < alpha]
 test.qt &lt;- qtscore(disease, data = g.dat, trait = "gaussian")
 slotNames(test.qt)
 names(test.qt@results)
 head(results(test.qt))
 test.qt@lambda
 descriptives.scan(test.qt)
 row.names(results(test.qt))[results(test.qt)$P1df < alpha]
 results(test.qt)$P1df[results(test.qt)$P1df < alpha] results(test.qt)$Pc1df[results(test.qt)$Pc1df < alpha]
 obs &lt;- sort(results(test.qt)$P1df) 
 ept &lt;- ppoints(obs) 
 plot(-log10(ept), -log10(obs), main = "GWAS QQ plot, qtl", xlab="Expected -log10(pvalue)", ylab="Observed -log10(pvalue)")
 abline(0, 1, col = "red")
 abline(h = 8, lty = 2)
 plot(test.qt, col = "black")
 test.qt.sex &lt;- qtscore(disease ~ sex, data = g.dat, trait = "gaussian")
 row.names(results(test.qt.sex))[results(test.qt)$P1df < alpha]
 summary(lm(disease ~ sex, data = g.dat))
 convert.snp.tped(tped = "gwa_gabel.tped", tfam = "gwa_gabel.tfam", out = "gwa_gabel.raw", strand = "u")
 b.dat &lt;- load.gwaa.data(phen = "gwa_gabel.praw", gen = "gwa_gabel.raw", force = T)
 slotNames(b.dat)
 slotNames(b.dat@gtdata)
 colnames(b.dat@phdata)
 b.dat@gtdata@nids
 case.size &lt;- length(which(b.dat@phdata$disease == 1))
 control.size &lt;- length(which(b.dat@phdata$disease == 0))
 case.size 
 control.size 
 snpsb.total &lt;- b.dat@gtdata@nsnps
 testb.snp &lt;- scan.glm('disease ~ CRSNP', family = binomial(), data = b.dat)
 names(testb.snp)  
 alpha &lt;- 5e-8
 testb.snp$snpnames[testb.snp$P1df < alpha]
 testb.snp$P1df[testb.snp$P1df < alpha]
 testb.qt &lt;- qtscore(disease, data = b.dat, trait = "binomial")
 slotNames(testb.qt)
 descriptives.scan(testb.qt)
 row.names(results(testb.qt))[results(testb.qt)$P1df < alpha]
 results(testb.qt)$P1df[results(testb.qt)$P1df < alpha]
 results(testb.qt)$Pc1df[results(testb.qt)$Pc1df < alpha]  
 gkin &lt;- ibs(g.dat, weight = "freq")
 gkin[1:10,1:10]
 cps.full &lt;- cmdscale(as.dist(.5 - gkin), eig = T, k = 10)
 names(cps.full)
 cps &lt;- cps.full$points
 plot(cps[,1], cps[,2], pch = g.dat@phdata$popn)
 legend("topright", c("TSI","MEX", "CEU"), pch = c(1,2,3))       
 colnames(cps)&lt;-c('C1','C2','C3','C4','C5','C6','C7','C8','C9','C10') 
 gpc.dat &lt;- g.dat
 gpc.dat@phdata&lt;-cbind(g.dat@phdata, cps)
 test.pc.a &lt;- scan.glm('disease ~ CRSNP + C1 + C2 + C3 + C4 + C5', family=gaussian(), data = gpc.dat)
 test.pc.a$snpnames[test.pc.a$P1df < alpha]
 test.pc.a$P1df[test.pc.a$P1df < alpha]
 test.pc.b &lt;- qtscore(disease ~  C1 + C2 + C3 + C4 + C5, data = gpc.dat, trait = "gaussian") 
 test.pc.b@lambda
 plot(cps.full$eig[1:10]/sum(cps.full$eig), axes = F, type = "b", xlab = "Components",  ylim = c(0,0.05), ylab = "Proportion of Variations", main = "MDS analysis scree plot") 
 axis(1, 1:10)
 axis(2)
 plot(cumsum(cps.full$eig[1:10])/sum(cps.full$eig), axes = F, type = "b", ylim = c(0,0.2), xlab = "Components", ylab = "Proportion of Variations", main = "MDS analysis cumulative plot") 
 axis(1, 1:10)
 axis(2)
 row.names(results(test.qt))[results(test.qt)$Pc1df < alpha]
 results(test.qt)$Pc1df[results(test.qt)$Pc1df < alpha]
 test.qt@lambda
 obs &lt;- sort(results(test.qt)$chi2.1df)
 ept &lt;- sort(qchisq(ppoints(obs), df = 1)) 
 plot(ept, obs, main = "Genomic control (lambda = slope of the dashed line)", xlab="Expected chisq, 1df", ylab="Observed chisq, 1df")
 abline(0, 1, col = "red")
 abline(0, test.qt@lambda[1], lty = 2)
 median(results(test.qt)$chi2.1df)/0.456
 obs &lt;- sort(results(test.qt)$Pc1df)
 ept &lt;- ppoints(obs) 
 plot(-log10(ept), -log10(obs), main = "GWAS QQ plot adj. via Genomic Control", xlab="Expected -log10(pvalue)", ylab="Observed -log10(pvalue)")
 abline(0, 1, col = "red")
 abline(h = 8, lty = 2) 
 adj.gkin = gkin
 diag(adj.gkin) = hom(g.dat)$Var
 test.eg &lt;- egscore(disease, data = g.dat, kin = adj.gkin, naxes = 2)
 descriptives.scan(test.eg)
 snp.eg &lt;- row.names(results(test.eg))[results(test.eg)$P1df < alpha]
 pvalue.eg &lt;- results(test.eg)$P1df[results(test.eg)$P1df < alpha]
 lambda.eg &lt;- test.eg@lambda
 snp.eg 
 pvalue.eg
 lambda.eg
 for (k in 1:10){
  test.tmp &lt;- egscore(disease, data = g.dat, kin = adj.gkin, naxes = k)
 print(test.tmp@lambda$estimate)
 }
 obs &lt;- sort(results(test.eg)$Pc1df)
 ept &lt;- ppoints(obs) 
 plot(-log10(ept), -log10(obs), main = "GWAS QQ plot adj. w/ EIGENSTRAT", xlab="Expected -log10(pvalue)", ylab="Observed -log10(pvalue)")
 abline(0, 1, col = "red")
 abline(h = 8, lty = 2)
 plot(test.qt, col = "black")
 add.plot(test.eg, col = "gray", pch = 3)
 legend("topright", c("Original plot","After correction w/ EIGENSTRAT"), pch = c(1,3))


==GWAS Data QC==

 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
 plink --file GWAS_clean2 --check-sex --out GWAS_sex_checking --noweb
 R
 sexcheck = read.table("GWAS_sex_checking.sexcheck", header=T)
 names(sexcheck)
 sex_problem = sexcheck[which(sexcheck$STATUS=="PROBLEM"),]
 sex_problem
 q()
 plink --file GWAS_clean2 --genome --out duplicates --noweb
 R
 dups = read.table("duplicates.genome", header = T)
 problem_pairs = dups[which(dups$PI_HAT > 0.4),]
 problem_pairs
 problem_pairs = dups[which(dups$PI_HAT > 0.05),]
 myvars = c("FID1", "IID1", "FID2", "IID2", "PI_HAT")
 problem_pairs[myvars]
 q()
 plink --file GWAS_clean2 --remove IBS_excluded.txt --recode --out GWAS_clean3 --noweb
 plink --file GWAS_clean3 --het --noweb
 R
 Dataset &lt;- read.table("plink.het", header=TRUE, sep="", na.strings="NA", dec=".",
 strip.white=TRUE)
 mean(Dataset$F)
 sd(Dataset$F)
 jpeg("hist.jpeg", height=1000, width=1000)
 hist(scale(Dataset$F), xlim=c(-4,4))
 dev.off()
 q()
 plink --file GWAS_clean3 --pheno pheno.txt --pheno-name Aff --hardy --noweb
 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 --noweb


==GWAS Control Substructure==

 plink --file GWAS_clean4 --genome --mds-plot 10 --noweb
 R
 mydata = read.table("mds_components.txt", header=T)
 mydata$pch[mydata$Group==1 ] &lt;-15
 mydata$pch[mydata$Group==2 ] &lt;-16
 mydata$pch[mydata$Group==3 ] &lt;-2
 jpeg("mds.jpeg", height=1000, width=1000)
 plot(mydata$C1, mydata$C2 ,pch=mydata$pch)
 dev.off()
 q()
 plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --logistic --adjust --out unadj --noweb
 plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --covar plink.mds --covar-name C1 --logistic --adjust --out C1 --noweb
 plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --covar plink.mds --covar-name C1-C2 --logistic --adjust --out C1-C2 --noweb
 R
 broadqq &lt;-function(pvals, title)
 {
 &nbsp;&nbsp;&nbsp;&nbsp;observed &lt;- sort(pvals)
 &nbsp;&nbsp;&nbsp;&nbsp;lobs &lt;- -(log10(observed))
 &nbsp;&nbsp;&nbsp;&nbsp;expected &lt;- c(1:length(observed))
 &nbsp;&nbsp;&nbsp;&nbsp;lexp &lt;- -(log10(expected / (length(expected)+1)))
 &nbsp;&nbsp;&nbsp;&nbsp;plot(c(0,7), c(0,7), col="red", lwd=3, type="l", xlab="Expected (-logP)", ylab="Observed (-logP)", xlim=c(0,max(lobs)), ylim=c(0,max(lobs)), las=1, xaxs="i", yaxs="i", bty="l", main = title)
 &nbsp;&nbsp;&nbsp;&nbsp;points(lexp, lobs, pch=23, cex=.4, bg="black") }
 jpeg("qqplot_compare.jpeg", height=1000, width=1000)
 par(mfrow=c(2,1))
 aff_unadj&lt;-read.table("unadj.assoc.logistic", header=TRUE)
 aff_unadj.add.p&lt;-aff_unadj[aff_unadj$TEST==c("ADD"),]$P
 broadqq(aff_unadj.add.p,"Some Trait Unadjusted")
 aff_C1C2&lt;-read.table("C1-C2.assoc.logistic", header=TRUE)
 aff_C1C2.add.p&lt;-aff_C1C2[aff_C1C2$TEST==c("ADD"),]$P
 broadqq(aff_C1C2.add.p, "Some Trait Adjusted")
 dev.off()
 gws_unadj = aff_unadj[which(aff_unadj$P < 0.0000001),]
 gws_unadj
 gws_adjusted = aff_C1C2[which(aff_C1C2$P < 0.0000001),] gws_adjusted
 q()