Difference between revisions of "AdvGeneMap2018Commands"

Revision as of 15:09, 23 January 2018

Plink - Part 1 - Data QC

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$PI_HAT > 0.05),]
myvars = c("FID1", "IID1", "FID2", "IID2", "PI_HAT")
problem_pairs[myvars]
q()
######
plink --file GWAS_clean2 --remove IBS_excluded.txt --recode --out GWAS_clean3
plink --file GWAS_clean3 --het
###### in R
Dataset <- read.table("plink.het", header=TRUE, sep="", na.strings="NA", dec=".", strip.white=TRUE)
mean(Dataset$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$pch)
dev.off()
q()
######
plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --logistic --adjust --out unadj
plink --file GWAS_clean4 --genome --cluster --pca 10 header
plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --covar plink.eigenvec --covar-name PC1 --logistic --adjust --out PC1
plink --file GWAS_clean4 --pheno pheno.txt --pheno-name Aff --covar plink.eigenvec --covar-name PC1-PC2 --logistic --adjust --out PC1-PC2
#### in R
broadqq <-function(pvals, title)
{
	observed <- sort(pvals)
	lobs <- -(log10(observed))
	expected <- c(1:length(observed)) 
	lexp <- -(log10(expected / (length(expected)+1)))
	plot(c(0,7), c(0,7), col="red", lwd=3, type="l", xlab="Expected (-logP)", ylab="Observed (-logP)", xlim=c(0,max(lobs)), ylim=c(0,max(lobs)), las=1, xaxs="i", yaxs="i", bty="l", main = title)
	points(lexp, lobs, pch=23, cex=.4, bg="black") }
jpeg("qqplot_compare.jpeg", height=1000, width=500)
par(mfrow=c(2,1))
aff_unadj<-read.table("unadj.assoc.logistic", header=TRUE)
aff_unadj.add.p<-aff_unadj[aff_unadj$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

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_nameCEU_totalGD10CEU_numGD10YRI_totalGD10YRI_numGD10 --header
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 -10
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 -10
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
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 > ME\ TA_RV_VT.asso.res
cut -f1,3 META_RV_VT.asso.res | head