AdvGeneMap2017Commands
From Statistical Genetics Courses
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 <- 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 <- g.dat@gtdata@nids snps.total <- 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$disease) test.snp <- scan.glm('disease ~ CRSNP', family = gaussian(), data = g.dat) names(test.snp) alpha <- 5e-8 test.snp$snpnames[test.snp$P1df < alpha] test.snp$P1df[test.snp$P1df < alpha] test.qt <- qtscore(disease, data = g.dat, trait = "gaussian") slotNames(test.qt) names(test.qt@results) head(results(test.qt)) test.qt@lambda descriptives.scan(test.qt) row.names(results(test.qt))[results(test.qt)$P1df < alpha] results(test.qt)$P1df[results(test.qt)$P1df < alpha] results(test.qt)$Pc1df[results(test.qt)$Pc1df < alpha] obs <- sort(results(test.qt)$P1df) ept <- ppoints(obs) plot(-log10(ept), -log10(obs), main = "GWAS QQ plot, qtl", xlab="Expected -log10(pvalue)", ylab="Observed -log10(pvalue)") abline(0, 1, col = "red") abline(h = 8, lty = 2) plot(test.qt, col = "black") test.qt.sex <- qtscore(disease ~ sex, data = g.dat, trait = "gaussian") row.names(results(test.qt.sex))[results(test.qt)$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 <- 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 <- length(which(b.dat@phdata$disease == 1)) control.size <- length(which(b.dat@phdata$disease == 0)) case.size control.size snpsb.total <- b.dat@gtdata@nsnps testb.snp <- scan.glm('disease ~ CRSNP', family = binomial(), data = b.dat) names(testb.snp) alpha <- 5e-8 testb.snp$snpnames[testb.snp$P1df < alpha] testb.snp$P1df[testb.snp$P1df < alpha] testb.qt <- 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)$Pc1df < alpha] gkin <- ibs(g.dat, weight = "freq") gkin[1:10,1:10] cps.full <- cmdscale(as.dist(.5 - gkin), eig = T, k = 10) names(cps.full) cps <- cps.full$points plot(cps[,1], cps[,2], pch = g.dat@phdata$popn) legend("topright", c("TSI","MEX", "CEU"), pch = c(1,2,3)) colnames(cps)<-c('C1','C2','C3','C4','C5','C6','C7','C8','C9','C10') gpc.dat <- g.dat gpc.dat@phdata<-cbind(g.dat@phdata, cps) test.pc.a <- scan.glm('disease ~ CRSNP + C1 + C2 + C3 + C4 + C5', family=gaussian(), data = gpc.dat) test.pc.a$snpnames[test.pc.a$P1df < alpha] test.pc.a$P1df[test.pc.a$P1df < alpha] test.pc.b <- qtscore(disease ~ C1 + C2 + C3 + C4 + C5, data = gpc.dat, trait = "gaussian") test.pc.b@lambda plot(cps.full$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 <- sort(results(test.qt)$chi2.1df) ept <- sort(qchisq(ppoints(obs), df = 1)) plot(ept, obs, main = "Genomic control (lambda = slope of the dashed line)", xlab="Expected chisq, 1df", ylab="Observed chisq, 1df") abline(0, 1, col = "red") abline(0, test.qt@lambda[1], lty = 2) median(results(test.qt)$chi2.1df)/0.456 obs <- sort(results(test.qt)$Pc1df) ept <- ppoints(obs) plot(-log10(ept), -log10(obs), main = "GWAS QQ plot adj. via Genomic Control", xlab="Expected -log10(pvalue)", ylab="Observed -log10(pvalue)") abline(0, 1, col = "red") abline(h = 8, lty = 2) adj.gkin = gkin diag(adj.gkin) = hom(g.dat)$Var test.eg <- egscore(disease, data = g.dat, kin = adj.gkin, naxes = 2) descriptives.scan(test.eg) snp.eg <- row.names(results(test.eg))[results(test.eg)$P1df < alpha] pvalue.eg <- results(test.eg)$P1df[results(test.eg)$P1df < alpha] lambda.eg <- test.eg@lambda snp.eg pvalue.eg lambda.eg for (k in 1:10){ test.tmp <- egscore(disease, data = g.dat, kin = adj.gkin, naxes = k) print(test.tmp@lambda$estimate) } obs <- sort(results(test.eg)$Pc1df) ept <- ppoints(obs) plot(-log10(ept), -log10(obs), main = "GWAS QQ plot adj. w/ EIGENSTRAT", xlab="Expected -log10(pvalue)", ylab="Observed -log10(pvalue)") abline(0, 1, col = "red") abline(h = 8, lty = 2) plot(test.qt, col = "black") add.plot(test.eg, col = "gray", pch = 3) legend("topright", c("Original plot","After correction w/ EIGENSTRAT"), pch = c(1,3))
GWAS Data QC
plink --file GWAS --noweb plink --file GWAS --mind 0.10 --recode --out GWAS_clean_mind --noweb plink --file GWAS_clean_mind --maf 0.05 --recode --out MAF_greater_5 --noweb plink --file GWAS_clean_mind --exclude MAF_greater_5.map --recode --out MAF_less_5 --noweb plink --file MAF_greater_5 --geno 0.05 --recode --out MAF_greater_5_clean --noweb plink --file MAF_less_5 --geno 0.01 --recode --out MAF_less_5_clean --noweb plink --file MAF_greater_5_clean --merge MAF_less_5_clean.ped MAF_less_5_clean.map --recode --out GWAS_MAF_clean --noweb plink --file GWAS_MAF_clean --mind 0.03 --recode --out GWAS_clean2 --noweb plink --file GWAS_clean2 --check-sex --out GWAS_sex_checking --noweb R sexcheck = read.table("GWAS_sex_checking.sexcheck", header=T) names(sexcheck) sex_problem = sexcheck[which(sexcheck$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 <- 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 ] <-15 mydata$pch[mydata$Group==2 ] <-16 mydata$pch[mydata$Group==3 ] <-2 jpeg("mds.jpeg", height=1000, width=1000) plot(mydata$C1, mydata$C2 ,pch=mydata$pch) dev.off() q() plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --logistic --adjust --out unadj --noweb plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --covar plink.mds --covar-name C1 --logistic --adjust --out C1 --noweb plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --covar plink.mds --covar-name C1-C2 --logistic --adjust --out C1-C2 --noweb R broadqq <-function(pvals, title) { observed <- sort(pvals) lobs <- -(log10(observed)) expected <- c(1:length(observed)) lexp <- -(log10(expected / (length(expected)+1))) plot(c(0,7), c(0,7), col="red", lwd=3, type="l", xlab="Expected (-logP)", ylab="Observed (-logP)", xlim=c(0,max(lobs)), ylim=c(0,max(lobs)), las=1, xaxs="i", yaxs="i", bty="l", main = title) points(lexp, lobs, pch=23, cex=.4, bg="black") } jpeg("qqplot_compare.jpeg", height=1000, width=1000) par(mfrow=c(2,1)) aff_unadj<-read.table("unadj.assoc.logistic", header=TRUE) aff_unadj.add.p<-aff_unadj[aff_unadj$TEST==c("ADD"),]$P broadqq(aff_unadj.add.p,"Some Trait Unadjusted") aff_C1C2<-read.table("C1-C2.assoc.logistic", header=TRUE) aff_C1C2.add.p<-aff_C1C2[aff_C1C2$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()
VAT
vtools -h vtools init VATDemo vtools import *.vcf.gz --var_info DP filter --geno_info DP_geno --build hg18 -j1 vtools liftover hg19 head phenotypes.csv vtools phenotype --from_file phenotypes.csv --delimiter "," vtools show project vtools show tables vtools show table variant vtools show samples vtools show genotypes vtools show fields vtools select variant --count vtools show genotypes > GenotypeSummary.txt head GenotypeSummary.txt vtools output variant "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header vtools select variant "filter='PASS'" --count vtools select variant "filter='PASS'" -o "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header vtools update variant --from_stat 'total=#(GT)' 'num=#(alt)' 'het=#(het)' 'hom=#(hom)' 'other=#(other)' 'minDP=min(DP_geno)' 'maxDP=max(DP_geno)' 'meanDP=avg(DP_geno)' 'maf=maf()' vtools show fields vtools show table variant vtools update variant --from_stat 'totalGD10=#(GT)' 'numGD10=#(alt)' 'hetGD10=#(het)' 'homGD10=#(hom)' 'otherGD10=#(other)' 'mafGD10=maf()' --genotypes "DP_geno > 10" vtools show fields vtools show table variant vtools output variant chr pos maf mafGD10 --header --limit 20 vtools phenotype --set "RACE=0" --samples "filename like 'YRI%'" vtools phenotype --set "RACE=1" --samples "filename like 'CEU%'" vtools show samples --limit 10 vtools update variant --from_stat 'CEU_mafGD10=maf()' --genotypes 'DP_geno>10' --samples "RACE=1" vtools update variant --from_stat 'YRI_mafGD10=maf()' --genotypes 'DP_geno>10' --samples "RACE=0" vtools output variant chr pos mafGD10 CEU_mafGD10 YRI_mafGD10 --header --limit 10 vtools phenotype --from_stat 'CEU_totalGD10=#(GT)' 'CEU_numGD10=#(alt)' --genotypes 'DP_geno>10' --samples "RACE=1" vtools phenotype --from_stat 'YRI_totalGD10=#(GT)' 'YRI_numGD10=#(alt)' --genotypes 'DP_geno>10' --samples "RACE=0" vtools phenotype --output sample_name CEU_totalGD10 CEU_numGD10 YRI_totalGD10 YRI_numGD10 --header vtools select variant 'maf>=0.01' -t variant_MAFge01 'Variants that have MAF >= 0.01' vtools show tables vtools execute KING --var_table variant_MAFge01 vtools_report plot_pheno_fields KING_MDS1 KING_MDS2 RACE --dot KING.mds.race.pdf --discrete_color Dark2 vtools_report plot_pheno_fields KING_MDS1 KING_MDS2 panel --dot KING.mds.panel.pdf --discrete_color Dark2 vtools execute ANNOVAR geneanno vtools output variant chr pos ref alt mut_type --limit 20 --header vtools_report trans_ratio variant -n num vtools_report trans_ratio variant -n numGD10 vtools select variant "DP<15" -t to_remove vtools show tables vtools remove variants to_remove -v0 vtools show tables vtools remove genotypes "DP_geno<10" -v0
vtools select variant "mut_type like 'non%' or mut_type like 'stop%' or region_type='splicing'" -t v_funct
vtools show tables
vtools show samples --limit 5
vtools select variant --samples "RACE=1" -t CEU
mkdir -p ceu
cd ceu
vtools init ceu --parent ../ --variants CEU --samples "RACE=1" --build hg19 vtools show project vtools select variant "CEU_mafGD10>=0.05" -t common_ceu vtools select v_funct "CEU_mafGD10<0.01" -t rare_ceu
vtools use refGene
vtools show annotation refGene
vtools associate -h
vtools show tests
vtools show test LinRegBurden
vtools associate common_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db EA_CV > EA_CV.asso.res grep -i error *.log less EA_CV.asso.res sort -g -k7 EA_CV.asso.res | head vtools show fields vtools associate rare_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db EA_RV > EA_RV.asso.res grep -i error *.log | tail -22 less EA_RV.asso.res sort -g -k6 EA_RV.asso.res | head vtools associate rare_ceu BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db EA_RV > EA_RV_VT.asso.res grep -i error *.log | tail -22 less EA_RV_VT.asso.res sort -g -k6 EA_RV_VT.asso.res | head vtools select rare_ceu "refGene.name2='ABCC1'" -o chr pos ref alt CEU_mafGD10 numGD10 mut_type --header vtools_report plot_association qq -o QQRV -b --label_top 2 -f 6 < EA_RV.asso.res vtools_report plot_association manhattan -o MHRV -b --label_top 5 --color Dark2 --chrom_prefix None -f 6 < EA_RV.asso.res
vtools associate rare_ceu BMI --covariate SEX KING_MDS1 KING_MDS2 -m "LinRegBurden --name RVMDS2 --alternative 2" -g refGene.name2 -j1 --to_db EA_RV > EA_RV_MDS2.asso.res vtools_report plot_association qq -o QQRV_MDS2 -b --label_top 2 -f 6 < EA_RV_MDS2.asso.res
cd ..
vtools select variant --samples "RACE=0" -t YRI
mkdir -p yri
cd yri
vtools init yri --parent ../ --variants YRI --samples "RACE=0" --build hg19
vtools select variant "YRI_mafGD10>=0.05" -t common_yri vtools select v_funct "YRI_mafGD10<0.01" -t rare_yri
vtools use refGene
vtools associate common_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db YA_CV > YA_CV.asso.res vtools associate rare_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db YA_RV > YA_RV.asso.res vtools associate rare_yri BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db YA_RV > YA_RV_VT.asso.res cd .. vtools_report meta_analysis ceu/EA_RV_VT.asso.res yri/YA_RV_VT.asso.res --beta 5 --pval 6 --se 7 -n 2 --link 1 > META_RV_VT.asso.res cut -f1,3 META_RV_VT.asso.res | head