__NOTITLE__
__FORCETOC__
===Functional Annotation===
table_annovar.pl
table_annovar.pl APOC3.vcf humandb/ -buildver hg19 -out APOC3_Gene.vcf -remove -nastring . -protocol refGene -operation g -vcfinput
cat APOC3_Gene.vcf.hg19_multianno.txt
table_annovar.pl APOC3.vcf humandb/ -buildver hg19 -out APOC3_Gene.vcf -remove -nastring . -protocol refGene,knownGene,ensGene -operation g,g,g -arg '-splicing 12 -exonicsplicing','-splicing 12 -exonicsplicing','-splicing 12 -exonicsplicing' -vcfinput
awk -F'\t' '{print $1,$2,$6,$7,$8,$9,$10}' APOC3_Gene.vcf.hg19_multianno.txt
table_annovar.pl APOC3.vcf humandb/ -buildver hg19 -out APOC3_Region.vcf -remove -nastring . -protocol phastConsElements46way -operation r -vcfinput
table_annovar.pl APOC3.vcf humandb/ -buildver hg19 -out APOC3_Region.vcf -remove -nastring . -protocol gwasCatalog -operation r -vcfinput
table_annovar.pl APOC3.vcf humandb/ -buildver hg19 -out APOC3_Filter.vcf -remove -nastring . -protocol gnomad_genome,gnomad_exome,popfreq_max_20150413,gme,avsnp150,dbnsfp33a,dbscsnv11,cadd13gt20,clinvar_20170905,gwava -operation f,f,f,f,f,f,f,f,f,f -vcfinput
awk -F'\t' '{print $1,$2,$103,$104}' APOC3_Filter.vcf.hg19_multianno.txt
awk -F'\t' '{print $1,$2,$6,$14}' APOC3_Filter.vcf.hg19_multianno.txt
awk -F'\t' '{print $1,$2,$15,$16,$17,$18,$19,$20,$21,$22}' APOC3_Filter.vcf.hg19_multianno.txt
awk -F'\t' '{print $1,$2,$36,$86,$70}' APOC3_Filter.vcf.hg19_multianno.txt
awk -F'\t' '{print $1,$2,$99,$100}' APOC3_Filter.vcf.hg19_multianno.txt
table_annovar.pl APOC3.vcf humandb/ -buildver hg19 -out APOC3_ANN.vcf -remove -nastring . -protocol refGene,knownGene,ensGene,wgRna,targetScanS,phastConsElements46way,tfbsConsSites,gwasCatalog,gnomad_genome,gnomad_exome,popfreq_max_20150413,gme,avsnp150,dbnsfp33a,dbscsnv11,cadd13gt20,clinvar_20170905,gwava -operation g,g,g,r,r,r,r,r,f,f,f,f,f,f,f,f,f,f -arg '-splicing 12 -exonicsplicing','-splicing 12 -exonicsplicing','-splicing 12 -exonicsplicing',,,,,,,,,,,,,,, -vcfinput
===GenABEL===
convert.snp.tped(tped = "gwa_gabel_qtl.tped", tfam = "gwa_gabel_qtl.tfam", out = "gwa_gabel_qtl.raw", strand = "u")
g.dat <- load.gwaa.data(phen = "gwa_gabel_qtl.praw", gen = "gwa_gabel_qtl.raw", force = T)
slotNames(g.dat)
slotNames(g.dat@gtdata)
colnames(g.dat@phdata)
# sample size
sample.size <- g.dat@gtdata@nids
hist(g.dat@phdata$disease, main="Quantitative Phenotype data summary", xlab = "Systolic pressure measure", freq = F,breaks=20, col="gray")
rug(g.dat@phdata$disease)
###
# tests for association
names(test.snp)
alpha <- 5e-8
test.snp$snpnames[test.snp$P1df < < alpha] test.snp$P1df[test.snp$P1df < < alpha]
# Score test
test.qt <- qtscore(disease, data = g.dat, trait = "gaussian")
slotNames(test.qt)
names(test.qt@results)
test.qt@lambda
descriptives.scan(test.qt)
rownames(results(test.qt))[results(test.qt)$P1df < < alpha] results(test.qt)$P1df[results(test.qt)$P1df < < alpha] results(test.qt)$Pc1df[results(test.qt)$Pc1df < < alpha]
# QQ plot
obs <- sort(results(test.qt)$P1df)
# Manhattan plot
plot(test.qt, col = "black")
# Adding confounders
test.qt.sex <- qtscore(disease ~ sex, data = g.dat, trait = "gaussian")
rownames(results(test.qt.sex))[results(test.qt)$P1df < < alpha]
summary(lm(disease ~ sex, data = g.dat))
###
# MDS
###
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(-0.16, 0.06, c("TSI","MEX", "CEU"), pch = c(1,2,3))
###
# Corrected test
###
# Incorporating PCs as predictors
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
# scree plot
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)
# cumulative plot
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)
# Genomic control
# Uncorrected GIF
test.qt@lambda
# Corrected p-value
row.names(results(test.qt))[results(test.qt)$Pc1df < < alpha] results(test.qt)$Pc1df[results(test.qt)$Pc1df < < alpha]
# Check for inflation of statistic
obs <- sort(results(test.qt)$chi2.1df)
abline(0, 1, col = "red")
abline(0, test.qt@lambda[1], lty = 2)
# Definition of GIF
# Conventional definition
# GenABEL definition
lm(obs~ept)$coef[2]
# QQ plot
obs <- sort(results(test.qt)$Pc1df)
abline(0, 1, col = "red")
abline(h = 8, lty = 2)
# EIGENSTRAT
adj.gkin = gkin
diag(adj.gkin) = hom(g.dat)$Var
# naxes = 3 is default value
test.eg <- egscore(disease, data = g.dat, kin = adj.gkin, naxes = 2)
descriptives.scan(test.eg)
snp.eg <- row.names(results(test.eg))[results(test.eg)$P1df < < alpha] pvalue.eg <- results(test.eg)$P1df[results(test.eg)$P1df < < alpha]
lambda.eg <- test.eg@lambda
snp.eg
pvalue.eg
lambda.eg
# Change #PCs
for (k in 1:10){
print(test.tmp@lambda$estimate)
}
# QQ plot
obs <- sort(results(test.eg)$Pc1df)
add.plot(test.eg, col = "gray", pch = 3)
legend("topright", c("Original plot","After correction w/ EIGENSTRAT"), pch = c(1,3))
###
# Basic test, binary trait
###
# load files to GenABEL
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)
# sample size
b.dat@gtdata@nids
# number of cases and controls
case.size <- length(which(b.dat@phdata$disease == 1))
case.size
control.size
# number of SNPs
snpsb.total <- b.dat@gtdata@nsnps
# GLM test
testb.snp <- scan.glm('disease ~ CRSNP', family = binomial(), data = b.dat)
names(testb.snp)
alpha <- 5e-8
testb.snp$snpnames[testb.snp$P1df < < alpha] testb.snp$P1df[testb.snp$P1df < < alpha]
# Score test
testb.qt <- qtscore(disease, data = b.dat, trait = "binomial")
slotNames(testb.qt)
descriptives.scan(testb.qt)
row.names(results(testb.qt))[results(testb.qt)$P1df < < alpha] results(testb.qt)$P1df[results(testb.qt)$P1df < < alpha] results(testb.qt)$Pc1df[results(testb.qt)$Pc1df < < alpha]
===GxG Interaction===
./plink --noweb --ped simcasecon.ped --map simcasecon.map --assoc
./plink --noweb --ped simcasecon.ped --map simcasecon.map --fast-epistasis
./plink --noweb --ped simcasecon.ped --map simcasecon.map --fast-epistasis --case-only
./plink --noweb --ped simcasecon.ped --map simcasecon.map --epistasis
./plink --noweb --ped simcasecon.ped --map simcasecon.map --recodeA --out recoded
./plink --noweb --ped simcasecon.ped --map simcasecon.map --make-bed --out cassiformat
R
# The following commands are in the R environment
je <-read.table("cassi.out", header=T)
je
library(ORMDR)
recoded<-read.table("recoded.raw", header=T)
head(recoded)
newdata<-recoded[7:106]
ormdrdata<-cbind(newdata,recoded$PHENOTYPE-1)
names(ormdrdata)[101]<-"casestatus"
head(ormdrdata)
mdr1<-mdr.c(ormdrdata, colresp=101, cs=1, combi=1, cv.fold = 10)
mdr1$min.comb
mdr2<-mdr.c(ormdrdata, colresp=101, cs=1, combi=2, cv.fold = 10)
mdr2$min.comb
mdr3<-mdr.c(ormdrdata, colresp=101, cs=1, combi=3, cv.fold = 10)
mdr3$min.comb
mdr1$test.erate
mdr2$test.erate
mdr3$test.erate
mdr1mean<-mean(mdr1$test.erate)
mdr2mean<-mean(mdr2$test.erate)
mdr3mean<-mean(mdr3$test.erate)
mdr1mean
mdr2mean
mdr3mean
mdr2$best.combi
mdr2$min.comb
mdr3$best.combi
mdr3$min.comb
logreg12<-glm(casestatus ~ factor(snp1_2)*factor(snp2_1), family=binomial,
data=ormdrdata)
summary(logreg12)
anova(logreg12)
pchisq(701.68,4,lower.tail=F)
pchisq(703.82,8,lower.tail=F)
logreg345<-glm(casestatus ~ factor(snp3_2)*factor(snp4_2)*factor(snp5_2),
family=binomial, data=ormdrdata)
summary(logreg345)
anova(logreg345)
pchisq(45.6,8,lower.tail=F)
q()
### The following commands are in the linux shell
./BEAM3 beam3data.txt -o beam3results
./BEAM3 beam3data.txt -o beam3results -T 10
===Plink - Part 1 - Data QC===
#### 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$STATUS===="PROBLEM"),]
sex_problem
q()
#### in R
setwd("to_your_working_directory/")
dups = = read.table("duplicates.genome", header = = T) problem_pairs = = dups[which(dups$PI_HAT > > 0.4),]
problem_pairs
problem_pairs = = dups[which(dups$PI_HAT > > 0.05),] myvars = = c("FID1", "IID1", "FID2", "IID2", "PI_HAT")
problem_pairs[myvars]
q()
plink --file GWAS_clean3 --het
###### in R
Dataset <- read.table("plink.het", header==TRUE, sep=="", na.strings=="NA", dec==".", strip.white==TRUE)
mean(Dataset$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
##### in R
hardy = = read.table("plink.hwe", header = = T)
names(hardy)
hwe_prob = = hardy[which(hardy$P < < 0.0000009),]
hwe_prob
q()
##########
plink --file GWAS_clean3 --exclude HWE_out.txt --recode --out GWAS_clean4 ===Plink - Part 2 - Controlling for Substructure===
plink --file GWAS_clean4 --genome --cluster --mds-plot 10
#### in R
mydata = = read.table("mds_components.txt", header==T) mydata$pch[mydata$Group====1 ] <-15 mydata$pch[mydata$Group====2 ] <-16 mydata$pch[mydata$Group====3 ] <-2 jpeg("mds.jpeg", height==500, width==500) plot(mydata$C1, mydata$C2 ,pch==mydata$pch)
dev.off()
q()
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==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 ===RV-TDT=== ### Variant Annotation vtools init rvtdt vtools import --format vcf data/data.vcf --build hg19 vtools phenotype --from_file data/phen.txt 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 vtools export func_variant --format tped --samples 'phenotype is not null' > vat_raw.tped # set marker name as chr_pos, needs to avoid duplicate name 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 vtools phenotype --out family sample_name pid mid sex phenotype > vat_export.tfam vtools use refGene-hg19_20130904 vtools update func_variant --set 'maf=0.001' # set the maf to be 0.001 vtools select func_variant -o chr pos refGene.name2 maf --header > vat_export.anno ### Phasing Trio 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",$0}' | sed '1i\I\tid\nA\tDisease' > linkage.dat java -Xmx10000m -jar java/linkage2beagle.jar linkage.dat linkage.ped > pre_beagle.bgl python script/pre_phase.py -i pre_beagle.bgl -a pre_beagle_withMissing.bgl java -Xmx10000m -jar java/beagle.jar missing=0 trios=pre_beagle.bgl out=bgl_phased verbose=false redundant=true gunzip bgl_phased.pre_beagle.bgl.phased.gz ### RV-TDT Analysis python script/post_phase.py -a vat_export.anno -b bgl_phased.pre_beagle.bgl.phased -o genes/ for g in `ls genes | grep tped | cut -d"." -f1 | head -20` do echo "running rvTDT on gene "${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 done ===Seqspark=== hdfs dfs -put demo.vcf.bz2 hdfs dfs -put demo.tsv seqspark annotation.conf seqspark qc.conf seqspark demo.conf ===VAT===
vtools -h