2016-genetic-association-commands

From Center for Statistical Genetics

Jump to: navigation, search

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))


Imputation exercise

plink --file chr22_imputation_ex --noweb
plink --file chr22_imputation_ex --maf 0.01 --mind 0.02 --geno 0.05 --hwe 0.001 --out qc_check --noweb
plink --file chr22_imputation_ex --maf 0.01 --mind 0.02 --geno 0.05 --hwe 0.001 --recode --out chr22_clean1 --noweb
plink --file chr22_clean1 --maf 0.01 --mind 0.02 --geno 0.05 --hwe 0.001 --out qc_check_2 --noweb
plink --file chr22_clean1 --filter-cases --hwe 0.001 --recode --out chr22_cases_clean --noweb
plink --file chr22_clean1 --filter-controls --recode --out chr22_controls_clean --noweb
plink --file chr22_controls_clean --merge chr22_cases_clean.ped chr22_cases_clean.map --hwe 0.001 --recode --out chr22_all_clean --noweb
plink --file chr22_all_clean --logistic --out chr22_all_clean_geno --noweb
R
mydata = read.table("chr22_all_clean_geno.assoc.logistic", header=T)
names(mydata)
plot(mydata$BP, -log10(mydata$P))
smallp = mydata[which(mydata$P < 1E-4),]
smallp
smallp = smallp[order(smallp$BP),]
smallp
q()
mach1 --hapmapFormat -d chr22_mach_merlin.map -p chr22_mach_merlin.ped --haps genotypes_chr22_CEU_r22_nr.b36_fwd.phase.gz --snps genotypes_chr22_CEU_r22_nr.b36_fwd_legend.txt.gz --greedy --rounds 100 --mle --mldetails --autoflip -o chr22_HIHII
plink --dosage chr22_HIHII_dose_mach4plink.txt.gz Zin --fam chr22_imputation_ex.fam --map chr22_imputed_snps_positions.map --out chr22_HIHII_dosage --noweb
R
dosage = read.table("chr22_HIHII_dosage.assoc.dosage", header= T)
names(dosage)
plot(dosage$BP, -log10(dosage$P))
dosagep = dosage[which(dosage$P < 5E-8),] dosagep = dosagep[order(dosagep$BP),]
dosagep
interest = dosage[which(dosage$SNP=='rs715586'),]
interest

PLINK_R

Introduction

plink --ped dbp.cc.ped --map dbp.map --map3 --missing --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --mind 0.10 --geno 0.05 --recode --out cleaned --noweb
plink --ped cleaned.ped --map cleaned.map --freq --out cleaned --noweb
plink --ped cleaned.ped --map cleaned.map --hardy --out cleaned --noweb
plink --ped cleaned.ped --map cleaned.map --out cleaned.R --recode --tab --noweb
R
city = c("Oslo", "Bergen", "Munich", "Berlin", "Rome", "Milan")
population = c(0.58, 0.25, 1.3, 3.4, 2.7, 1.3)
country = factor( c("Norway" , "Norway", "Germany", "Germany", "Italy", "Italy" ))
capital = c(TRUE, FALSE, FALSE, TRUE, TRUE, FALSE)
updated = 2009
city
population
country
capital
c(city, city)
c(population, updated)
summary (city)
summary (population)
summary (country)
summary (capital)
is.numeric(city)
is.character(city)
is.factor(city)
class (city)
class (population)
class (country)
class (capital)
length(city)
names(population) = city
population
city [3]
city [2:4]
city[c(1,5:6)]
population[3]
population["Oslo"]
population[c("Berlin","Rome")]
population
capital
population[capital]
population>=1.0
population[population>=1.0]
cities = data.frame (city=city, pop=population, country=country, capital=capital, stringsAsFactors=F)
cities
length(cities)
dim(cities)
is.data.frame(cities)
is.list(cities)
colnames(cities)
rownames(cities)
cities$city
cities[,1]
cities[2,]
cities[2,3]
cities$pop[3]
cities[capital,]
cities[cities$pop>=1.0,]
ls()
save(cities, city, country, file="myobjects.R")
write.table(cities, file="cities.txt")
sink("cities.output.txt")
print(cities)
sink()
dir()
rm(list=ls())
ls()
new.table = read.table ("cities.txt")
ls()
new.table
load ("myobjects.R")
ls()
cities
new.table
q()

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

Multifactorial Part 1

plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.add --logistic --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.add.ci --logistic --ci 0.95 --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.age.add --logistic --covar dbp.age.pheno --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.sex.add --logistic --sex --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.sexage.add --logistic --sex --covar dbp.age.pheno --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.snp1112.add --logistic --condition rs1112 --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.snp1117.add --logistic --condition rs1117 --noweb
plink --ped dbp.qt.ped --map dbp.map --map3 --out linreg.sex.add --linear --sex --noweb
R
load("dbp.R")
ls()
dbp[1:5,]
result.snp12 = glm (affection ~ rs1112, family=binomial("logit"), data=dbp)
print (result.snp12)
print ( class (result.snp12) )
print ( summary(result.snp12) )
dev.geno = anova (result.snp12, test="Chi")
lrt.pvalue = pchisq(dev.geno[dim(dev.geno)[1],"Deviance"], df=2, ncp=0, FALSE)
print ( lrt.pvalue )
print ( summary(result.snp12)$coefficients )
snp.beta = summary(result.snp12)$coefficients[2:3,1]
print ( snp.beta )
print ( exp(snp.beta) )
ci = confint (result.snp12)
print (ci)
print ( exp(ci) )
snp.data = dbp[,c("affection", "rs1112")]
summary(snp.data)
snp.data[,"rs1112"]<-as.numeric(snp.data[,"rs1112"])-1
summary(snp.data)
result.all=glm(affection ~ rs1112, family=binomial("logit"), data=snp.data)
dev.all = anova(result.all, test="Chi")
print(dev.all)
snp.data = dbp[,c("affection","trait","sex","age","rs1112","rs1117")]
summary(snp.data)
snp.data[,"rs1112"]<-as.numeric(snp.data[,"rs1112"])-1
snp.data[,"rs1117"]<-as.numeric(snp.data[,"rs1117"])-1
result.adj = glm(affection ~ sex + rs1112, family=binomial("logit"), data=snp.data)
summary(result.adj) result.adj = glm (affection ~ age + rs1112 , family=binomial("logit"), data=snp.data) summary(result.adj) result.adj = glm (affection ~ sex + age + rs1112, family=binomial("logit"), data=snp.data) summary(result.adj) result.adj = glm (affection ~ rs1117 + rs1112, family=binomial("logit"), data=snp.data) summary(result.adj) anova (result.adj, test="Chi") result.adj = glm (affection ~ rs1112 + rs1117, family=binomial("logit"), data=snp.data) summary(result.adj) anova (result.adj, test="Chi") result.adj = lm (trait ~ rs1112, data=snp.data) summary(result.adj) result.adj = lm (trait ~ sex + rs1112, data=snp.data) summary(result.adj)

Multifactorial Part 2

plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.sex.inter.add --logistic --sex --interaction --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out logreg.snp1112.inter.add --logistic --condition rs1112 --interaction --noweb
R
load("dbp.R")
ls()
dbp[1:5,]
summary(dbp) result.inter = glm (affection ~ sex * rs1112, family=binomial("logit"), data=snp.data) summary(result.inter) result.inter = glm (affection ~ age * rs1112, family=binomial("logit"), data=snp.data) summary(result.inter) result.inter = glm (affection ~ rs1112 * rs1117, family=binomial("logit"), data=snp.data) summary(result.inter) result.reg = glm (affection ~ sex + age + rs1112 + rs1117, family=binomial("logit"), data=snp.data) summary(result.reg) modelchoice.result<-step(result.reg)
summary(modelchoice.result)

 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()

 Multiple Testing

plink --ped dbp.cc.ped --map dbp.map --map3 --out multtest --assoc --adjust --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out multperm5000 --assoc --mperm 5000 --noweb
plink --ped dbp.cc.ped --map dbp.map --map3 --out multperm100000 --assoc --mperm 100000 --noweb
R
load("p.values.R")
ls()
p.values
library (multtest)
adj.p.values = mt.rawp2adjp(p.values,c("Bonferroni","Holm","SidakSS","BH"))
adj.p.values
rownames(adj.p.values$adjp) = names(p.values[adj.p.values$index])
adj.p.values$adjp

PSEQ exercise

Data analysis:

pseq help
pseq help all
pseq myproj new-project --resources hg19
pseq myproj load-vcf --vcf CEU.exon.2010_03.genotypes.hg19.vcf.gz YRI.exon.2010_03.genotypes.hg19.vcf.gz
pseq myproj load-pheno --file phenotype.phe
pseq myproj v-view | head
pseq myproj i-view | head
pseq myproj summary 
pseq myproj var-summary
pseq myproj ind-summary
pseq myproj loc-summary
pseq myproj ref-summary
pseq myproj seq-summary
pseq myproj file-summary
pseq myproj meta-summary
pseq myproj v-stats
pseq myproj i-stats | head
pseq myproj tag-file --id 1 --name CEU
pseq myproj tag-file --id 2 --name YRI
pseq myproj var-summary
pseq myproj v-freq | head
pseq myproj v-freq --mask file=CEU | head 
pseq myproj v-freq --mask file=YRI | head
pseq myproj v-view --mask any.filter.ex | head
pseq myproj v-view --mask any.filter.ex | wc -l
pseq myproj v-view --mask any.filter | wc -l
pseq myproj var-set --group pass --mask any.filter.ex
pseq myproj var-summary
pseq myproj var-set --group pass_DP15 --mask include="DP>14" var=pass
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10 --mask geno=DP:ge:11 var=pass_DP15
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_CEU --mask file=CEU var=pass_DP15_DPgeno10
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_CEU_HWE --mask hwe=5.7e-7:1 var=pass_DP15_DPgeno10_CEU
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_CEU_HWE_MAFgt05 --mask maf=0.05:0.5 var=pass_DP15_DPgeno10_CEU_HWE
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_CEU_HWE_MAFlt01 --mask "mac=1 maf=0.01" var=pass_DP15_DPgeno10_CEU_HWE
pseq myproj var-summary
pseq myproj glm --phenotype BMI --covar SEX --mask var=pass_DP15_DPgeno10_CEU_HWE_MAFgt05 > SNV_CEU.result 
head SNV_CEU.result
cat SNV_CEU.result | awk '{if(FNR==1) print $0; if(NR>1) print $0 | "sort -k9 2>/dev/null"}' | grep -v "NA\s\+NA\s\+NA" | head
pseq myproj assoc --tests fw vt --phenotype BMI
pseq myproj assoc --tests skat --phenotype BMI --covar SEX --mask var=pass_DP15_DPgeno10_CEU_HWE_MAFlt01 loc.group=refseq > SKAT_CEU.result
pseq myproj assoc --tests skat --phenotype BMI --covar SEX --mask include="DP>14" geno=DP:ge:11 file=CEU hwe=5.7e-7:1 "mac=1 maf=0.01" loc.group=refseq > SKAT_CEU.result
head -20 SKAT_CEU.result
cat SKAT_CEU.result | grep SKAT | grep -v "P=NA" | sort -k6 | head -15

Exercise analyzing YRI samples:

pseq myproj var-set --group pass_DP15_DPgeno10_YRI --mask file=YRI var=pass_DP15_DPgeno10
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_YRI_HWE --mask hwe=5.7e-7:1 var=pass_DP15_DPgeno10_YRI
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_YRI_HWE_MAFgt05 --mask maf=0.05:0.5 var=pass_DP15_DPgeno10_YRI_HWE
pseq myproj var-summary
pseq myproj var-set --group pass_DP15_DPgeno10_YRI_HWE_MAFlt01 --mask "mac=1 maf=0.01" var=pass_DP15_DPgeno10_YRI_HWE
pseq myproj var-summary
pseq myproj glm --phenotype BMI --covar SEX --mask var=pass_DP15_DPgeno10_YRI_HWE_MAFgt05 > SNV_YRI.result
head SNV_YRI.result
cat SNV_YRI.result | awk '{if(FNR==1) print $0; if(NR>1) print $0 | "sort -k9 2>/dev/null"}' | grep -v "NA\s\+NA\s\+NA" | head
pseq myproj assoc --tests skat --phenotype BMI --covar SEX --mask include="DP>14" geno=DP:ge:11 file=YRI hwe=5.7e-7:1 "mac=1 maf=0.01" loc.group=refseq > SKAT_YRI.result
head -20 SKAT_YRI.result
cat SKAT_YRI.result | grep SKAT | grep -v "P=NA" | sort -k6 | head -15

RV-TDT exercise

vtools init rvtdt
vtools import --format vcf data/data.vcf --build hg19
vtools phenotype --from_file data/phen.txt
# variant selection
vtools execute ANNOVAR  geneanno
vtools select variant "variant.region_type like '%splicing%'or variant.mut_type like 'nonsynonymous%' or variant.mut_type like 'frameshift%' or variant.mut_type like 'stop%'" -t func_variant
# tped file
vtools export func_variant --format tped --samples 'phenotype is not null'  > vat_raw.tped
sort -k4 -n vat_raw.tped | awk 'BEGIN{OFS="\t";prev="None";copy=1} {$2=$1"_"$4; $3=0; if($2==prev) {$2=$2"_"copy; copy=copy+1} else {prev=$2; copy=1}; print $0}' > vat_export.tped
# tfam file
vtools phenotype --out family sample_name pid mid sex phenotype > vat_export.tfam
# anno file
vtools use refGene-hg19_20130904
vtools update func_variant --set 'maf=0.001' 
vtools select func_variant -o chr pos refGene.name2 maf --header > vat_export.anno
# Mendelian error and recode
plink --noweb --tfile vat_export --recode12 --me 1 1 --set-me-missing --out "recode12_noME"
sort -n -k1 -k6 -k2 recode12_noME.ped | sed 's/ /\t/g' | cut -f1,3,4,5 --complement > linkage.ped
cut -f2 recode12_noME.map | awk 'BEGIN{OFS="\t";} {print "M",$0}' | sed '1i\I\tid\nA\tDisease' > linkage.dat
java -Xmx10000m -jar java/linkage2beagle.jar linkage.dat linkage.ped > pre_beagle.bgl
python script/pre_phase.py -i pre_beagle.bgl -a pre_beagle_withMissing.bgl
java -Xmx10000m -jar java/beagle.jar missing=0 trios=pre_beagle.bgl out=bgl_phased verbose=false redundant=true
gunzip bgl_phased.pre_beagle.bgl.phased.gz
python script/post_phase.py -a vat_export.anno -b bgl_phased.pre_beagle.bgl.phased -o genes/
for g in `ls genes | grep tped | cut -d"." -f1 | head -20` 
do 
    echo "runing rvTDT on gene "${g}
    rvTDT exercise_proj -G ./genes/${g}.tped -P ./data/rvtdt.phen -M ./genes/${g}.map --adapt 500 --alpha 0.00001 --permut 2000 --lower_cutoff 0 --upper_cutoff 100 -- minVariants 3 --maxMissRatio 1 
done 
# Answer
vtools show tables
ls genes/ | grep tped | wc
cat exercise_proj_pval/*.pval | grep -v "^#" | sort -k2
cat exercise_proj_pval/*.pval | grep -v "^#" | sort -k3
# clean
rm -r exercise_proj* genes/* bgl* linkage* recode12* pre_beagle* vat_export.*

SEQPower

spower -h
spower LOGIT -h
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.5 --method "CFisher --name CMC" -r 100 -j 4 -l 1 -o exercise
spower show exercise.csv
spower show exercise.csv power*
spower show exercise.loci.csv
spower show exercise.loci.csv maf
spower show tests
spower show test SKAT
spower LOGIT Kryukov2009European1800.sfs --def_rare 0.01 --def_neutral -0.00001 0.00001 --moi A --proportion_detrimental 1 --proportion_protective 0 --OR_rare_detrimental 1.5 --OR_common_detrimental 1 --baseline_effect 0.01 --sample_size 1000 --p1 0.5 --limit 1 --alpha 0.05 --method "KBAC --name K1 --mafupper 0.01 --maflower 0 --alternative 1 --moi additive --permutations 1000 --adaptive 0.1" --replicates 1000 --jobs 4 -o exercise
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.2 --ORmax_rare_detrimental 3.0 --method CFisher -r 100 -j 4 -l 1 -o exercise
spower show exercise.loci.csv effect*
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.2 --ORmax_rare_detrimental 3.0 --proportion_detrimental 0.8 --method CFisher -r 100 -j 4 -l 1 -o exercise
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.5 --missing_sites 0.05 --method CFisher -r 100 -j 4 -l 1 -o exercise 
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.5 --missing_low_maf 0.000125 --method CFisher -r 100 -j 4 -l 1 -o exercise 
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.5 --method "CFisher --alternative 1 --name CMC" "KBAC --permutations 1000 --alternative 1" "WSSRankTest --alternative 1 --name WSS" "VTtest --alternative 1 --permutations 1000" "SKAT disease" -r 100 -j 4 -l 1 -o exercise
spower show exercise.csv method power
spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.5 -j 1 -l 1 -o exercise
spower LOGIT Kryukov2009European1800.sfs --power 0.8 --OR_rare_detrimental 1.5 -j 1 -l 1 -o exercise
spower LNR Kryukov2009European1800.sfs --sample_size 1000 --meanshift_rare_detrimental 0.2 --method "CollapseQt --name CMC --alternative 2" -r 100 -j 4 -l 1 -o exercise
spower LNR Kryukov2009European1800.sfs --sample_size 1000 --meanshift_rare_detrimental 0.2 --meanshiftmax_rare_detrimental 0.5 --method "CollapseQt --alternative 2" -r 100 -j 4 -l 1 -o exercise
spower ELNR Kryukov2009European1800.sfs --sample_size 1000 --meanshift_rare_detrimental 0.2 --QT_thresholds 0.4 0.6 --method "CollapseQt --alternative 2" -r 100 -j 4 -l 1 -o exercise
spower show exercise.csv sample* power
spower ELNR Kryukov2009European1800.sfs --sample_size 1000 --p1 0.5 --meanshift_rare_detrimental 0.5 --QT_thresholds 0.4 0.6 --method "CollapseQt --alternative 2" -r 100 -j 4 -l 1 -o exercise spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental 1.5 --method "GroupWrite ExerciseSimulation" -j 4 -o exercise -v1 spower show exercise.SEQPowerDB spower show exercise.SEQPowerDB LOGIT spower show exercise.SEQPowerDB LOGIT method power title --condition "where power between 0.25 and 0.95" for i in 1 1.5 2 2.5 3 3.5 4; do spower LOGIT Kryukov2009European1800.sfs --sample_size 1000 --OR_rare_detrimental $i --method "CFisher --name CMC$i" --title FixedOR$i -r 100 -j 4 -l 1 -o exercise2 done
spower show exercise2.SEQPowerDB LOGIT method power title

Unphased

unphased.sh
unphased mypeds.ped –marker 1 2 3 –missing –permutation 10
unphased mypeds.ped –permuation 10 morepeds.ped
unphased mypeds.ped –window 2 –reference 1 2
unphased mypeds.ped –window 2 –reference 1 2 1 1
unphased all.ped -window 2 -LD
unphased all.ped -window 2 -LD >> results.txt


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