, stringsAsFactors = F)
x = as.numeric(grepl(i,raw_data$all_muts_pza))
# DV: pyrazinamide 0 or 1
y = as.numeric(raw_data$pyrazinamide)
table(y,x)
# run glm model
model = glm(y ~ x, family = binomial)
#model = glm(y ~ x, family = binomial(link = "logit"))
summary(model)
#**********
# extract relevant model output
#**********
# extract log OR i.e the Beta estimate of the logistic model for a given snp
my_logor = summary(model)$coefficients[2,1]
print(paste0('Beta:', my_logor))
# extract SE of the logistic model for a given snp
my_se = summary(model)$coefficients[2,2]
print(paste0('SE:', my_se))
# extract Z of the logistic model for a given snp
my_zval = summary(model)$coefficients[2,3]
print(paste0('Z-value:', my_zval))
# Dervive OR i.e exp(my_logor) from the logistic model for a given snp
#my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
my_or = exp(summary(model)$coefficients[2,1])
print(paste0('OR:', my_or))
# sanity check : should be True
log(my_or) == my_logor
# extract P-value of the logistic model for a given snp
my_pval = summary(model)$coefficients[2,4]
print(paste0('P-value:', my_pval))
# extract confint interval of snp (2 steps, since the output is a named number)
ci_mod = exp(confint(model))[2,]
my_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
print(paste0('CI:', my_ci))
#*************
# Assign the regression output in the original df
# you can use ('=' or '<-/->')
#*************
#pnca_snps_or$logistic_logOR[pnca_snps_or$Mutationinformation == i] = my_logor
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$Mutationinformation == i]
my_logor
pnca_snps_or$Mutationinformation == i
View(pnca_snps_or)
#===============
# Step 4: Calculate for one snp
# using i, when you run the loop, it is easy
#===============
i = "pnca_p.trp68gly"
pnca_snps_or = read.csv("../Data_original/pnca_snps_for_or_calcs.csv"
, stringsAsFactors = F
, header = T) #2133
# uncomment as necessary
pnca_snps_or = pnca_snps_or[1:5,]
pnca_snps_or = pnca_snps_or[c(1:5),]
#===============
pnca_snps_or = read.csv("../Data_original/pnca_snps_for_or_calcs.csv"
, stringsAsFactors = F
, header = T) #2133
pnca_snps_or = pnca_snps_or[1:5,]
pnca_snps_or = pnca_snps_or[c(1:5),]
pnca_snps_or = pnca_snps_or[1:5]
pnca_snps_or = read.csv("../Data_original/pnca_snps_for_or_calcs.csv"
, stringsAsFactors = F
, header = T) #2133
pnca_snps_or = pnca_snps_or[1:5]
pnca_snps_or = read.csv("../Data_original/pnca_snps_for_or_calcs.csv"
, stringsAsFactors = F
, header = T) #2133
foo = pnca_snps_or[c(1:5,)]
foo = pnca_snps_or[c(1:5),]
foo = as.data.frame(pnca_snps_or[c(1:5),])
View(foo)
# create an empty dataframe
pnca_snps_or = as.data.frame(pnca_snps_or[c(1:5),])
# IV: corresponds to each unique snp (extracted using grep)
x = as.numeric(grepl(i,raw_data$all_muts_pza))
# DV: pyrazinamide 0 or 1
y = as.numeric(raw_data$pyrazinamide)
table(y,x)
# run glm model
model = glm(y ~ x, family = binomial)
#model = glm(y ~ x, family = binomial(link = "logit"))
summary(model)
my_logor = summary(model)$coefficients[2,1]
print(paste0('Beta:', my_logor))
# extract SE of the logistic model for a given snp
my_se = summary(model)$coefficients[2,2]
print(paste0('SE:', my_se))
# extract Z of the logistic model for a given snp
my_zval = summary(model)$coefficients[2,3]
print(paste0('Z-value:', my_zval))
# Dervive OR i.e exp(my_logor) from the logistic model for a given snp
#my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
my_or = exp(summary(model)$coefficients[2,1])
print(paste0('OR:', my_or))
# sanity check : should be True
log(my_or) == my_logor
# extract P-value of the logistic model for a given snp
my_pval = summary(model)$coefficients[2,4]
print(paste0('P-value:', my_pval))
# extract confint interval of snp (2 steps, since the output is a named number)
ci_mod = exp(confint(model))[2,]
my_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
print(paste0('CI:', my_ci))
#*************
# Assign the regression output in the original df
# you can use ('=' or '<-/->')
#*************
#pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i] = my_logor
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i]
my_or -> pnca_snps_or$OR[pnca_snps_or$mutation == i]
my_pval -> pnca_snps_or$pvalue[pnca_snps_or$mutation == i]
my_zval -> pnca_snps_or$zvalue[pnca_snps_or$mutation == i]
my_se -> pnca_snps_or$logistic_se[pnca_snps_or$mutation == i]
my_ci -> pnca_snps_or$ci[pnca_snps_or$mutation == i]
#===============
# Step 4: Iterate through this unique list
# and calculate OR, but only for one snp
# this is test before you apply it all others
#===============
pnca_snps_or$mutation == i
View(pnca_snps_or)
# create an empty dataframe
pnca_snps_or = data.frame(mutation = i)
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i]
my_or -> pnca_snps_or$OR[pnca_snps_or$mutation == i]
my_pval -> pnca_snps_or$pvalue[pnca_snps_or$mutation == i]
my_zval -> pnca_snps_or$zvalue[pnca_snps_or$mutation == i]
my_se -> pnca_snps_or$logistic_se[pnca_snps_or$mutation == i]
my_ci -> pnca_snps_or$ci[pnca_snps_or$mutation == i]
View(pnca_snps_or_copy)
#===============
# Step 4: Iterate through this unique list
# and calculate OR, but only for one snp
# this is test before you apply it all others
#===============
#reset original df so you don't make a mistake
pnca_snps_or = pnca_snps_or_copy
for (i in pnca_snps_unique){
print(i)
}
pnca_snps_or = pnca_snps_or_copy #2133, 1
#........................................
# create an empty dataframe : uncomment as necessary
pnca_snps_or = data.frame(mutation = c(i, "blank_mut")
#........................................
# create an empty dataframe : uncomment as necessary
pnca_snps_or = data.frame(mutation = c(i, "blank_mut"))
#........................................
# create an empty dataframe : uncomment as necessary
pnca_snps_or = data.frame(mutation = c(i, "blank_mut"))
View(pnca_snps_or)
# IV: corresponds to each unique snp (extracted using grep)
x = as.numeric(grepl(i,raw_data$all_muts_pza))
# DV: pyrazinamide 0 or 1
y = as.numeric(raw_data$pyrazinamide)
table(y,x)
# run glm model
model = glm(y ~ x, family = binomial)
#model = glm(y ~ x, family = binomial(link = "logit"))
summary(model)
#**********
# extract relevant model output
#**********
# extract log OR i.e the Beta estimate of the logistic model for a given snp
my_logor = summary(model)$coefficients[2,1]
print(paste0('Beta:', my_logor))
# extract SE of the logistic model for a given snp
my_se = summary(model)$coefficients[2,2]
print(paste0('SE:', my_se))
# extract Z of the logistic model for a given snp
my_zval = summary(model)$coefficients[2,3]
print(paste0('Z-value:', my_zval))
# Dervive OR i.e exp(my_logor) from the logistic model for a given snp
#my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
my_or = exp(summary(model)$coefficients[2,1])
print(paste0('OR:', my_or))
# sanity check : should be True
log(my_or) == my_logor
# extract P-value of the logistic model for a given snp
my_pval = summary(model)$coefficients[2,4]
print(paste0('P-value:', my_pval))
# extract confint interval of snp (2 steps, since the output is a named number)
ci_mod = exp(confint(model))[2,]
my_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
print(paste0('CI:', my_ci))
#*************
# Assign the regression output in the original df
# you can use ('=' or '<-/->')
#*************
#pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i] = my_logor
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i]
my_or -> pnca_snps_or$OR[pnca_snps_or$mutation == i]
my_pval -> pnca_snps_or$pvalue[pnca_snps_or$mutation == i]
my_zval -> pnca_snps_or$zvalue[pnca_snps_or$mutation == i]
my_se -> pnca_snps_or$logistic_se[pnca_snps_or$mutation == i]
my_ci -> pnca_snps_or$ci[pnca_snps_or$mutation == i]
View(pnca_snps_or)
pnca_snps_or = pnca_snps_or_copy #2133, 1
for (i in pnca_snps_unique){
print(i)
#*************
# start logistic regression model building
#*************
# set the IV and DV for the logistic regression model
# IV: corresponds to each unique snp (extracted using grep)
x = as.numeric(grepl(i,raw_data$all_muts_pza))
# DV: pyrazinamide 0 or 1
y = as.numeric(raw_data$pyrazinamide)
table(y,x)
# run glm model
model = glm(y ~ x, family = binomial)
#model = glm(y ~ x, family = binomial(link = "logit"))
summary(model)
#**********
# extract relevant model output
#**********
# extract log OR i.e the Beta estimate of the logistic model for a given snp
my_logor = summary(model)$coefficients[2,1]
print(paste0('Beta:', my_logor))
# extract SE of the logistic model for a given snp
my_se = summary(model)$coefficients[2,2]
print(paste0('SE:', my_se))
# extract Z of the logistic model for a given snp
my_zval = summary(model)$coefficients[2,3]
print(paste0('Z-value:', my_zval))
# Dervive OR i.e exp(my_logor) from the logistic model for a given snp
#my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
my_or = exp(summary(model)$coefficients[2,1])
print(paste0('OR:', my_or))
# sanity check : should be True
log(my_or) == my_logor
# extract P-value of the logistic model for a given snp
my_pval = summary(model)$coefficients[2,4]
print(paste0('P-value:', my_pval))
# extract confint interval of snp (2 steps, since the output is a named number)
ci_mod = exp(confint(model))[2,]
my_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
print(paste0('CI:', my_ci))
#*************
# Assign the regression output in the original df
# you can use ('=' or '<-/->')
#*************
#pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i] = my_logor
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i]
my_or -> pnca_snps_or$OR[pnca_snps_or$mutation == i]
my_pval -> pnca_snps_or$pvalue[pnca_snps_or$mutation == i]
my_zval -> pnca_snps_or$zvalue[pnca_snps_or$mutation == i]
my_se -> pnca_snps_or$logistic_se[pnca_snps_or$mutation == i]
my_ci -> pnca_snps_or$ci[pnca_snps_or$mutation == i]
}
warnings()
View(pnca_snps_or)
View(pnca_snps_or_copy)
#sanity check
pnca_snps_or$mutation == i1
#sanity check
pnca_snps_or[pnca_snps_or$mutation == i1]
pnca_snps_or[pnca_snps_or$mutation == i2]
pnca_snps_or[pnca_snps_or$mutation == i2,]
pnca_snps_or1 = unique(pnca_snps_or)
write.csv(pnca_snps_or1, "../Data_original/valid_pnca_snps_with_OR.csv")
# you only need it for the unique mutations
pnca_snps_or = unique(pnca_snps_or) #2133, 1
for (i in pnca_snps_unique){
print(i)
#*************
# start logistic regression model building
#*************
# set the IV and DV for the logistic regression model
# IV: corresponds to each unique snp (extracted using grep)
x = as.numeric(grepl(i,raw_data$all_muts_pza))
# DV: pyrazinamide 0 or 1
y = as.numeric(raw_data$pyrazinamide)
table(y,x)
# run glm model
model = glm(y ~ x, family = binomial)
#model = glm(y ~ x, family = binomial(link = "logit"))
summary(model)
#**********
# extract relevant model output
#**********
# extract log OR i.e the Beta estimate of the logistic model for a given snp
my_logor = summary(model)$coefficients[2,1]
print(paste0('Beta:', my_logor))
# extract SE of the logistic model for a given snp
my_se = summary(model)$coefficients[2,2]
print(paste0('SE:', my_se))
# extract Z of the logistic model for a given snp
my_zval = summary(model)$coefficients[2,3]
print(paste0('Z-value:', my_zval))
# Dervive OR i.e exp(my_logor) from the logistic model for a given snp
#my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
my_or = exp(summary(model)$coefficients[2,1])
print(paste0('OR:', my_or))
# sanity check : should be True
log(my_or) == my_logor
# extract P-value of the logistic model for a given snp
my_pval = summary(model)$coefficients[2,4]
print(paste0('P-value:', my_pval))
# extract confint interval of snp (2 steps, since the output is a named number)
ci_mod = exp(confint(model))[2,]
my_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
print(paste0('CI:', my_ci))
#*************
# Assign the regression output in the original df
# you can use ('=' or '<-/->')
#*************
#pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i] = my_logor
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i]
my_or -> pnca_snps_or$OR[pnca_snps_or$mutation == i]
my_pval -> pnca_snps_or$pvalue[pnca_snps_or$mutation == i]
my_zval -> pnca_snps_or$zvalue[pnca_snps_or$mutation == i]
my_se -> pnca_snps_or$logistic_se[pnca_snps_or$mutation == i]
my_ci -> pnca_snps_or$ci[pnca_snps_or$mutation == i]
}
View(pnca_snps_or)
2.290256e+01
1.561132e+06
3.242285e-04
#sanity check
pnca_snps_or[pnca_snps_or$mutation == i1]
pnca_snps_or[pnca_snps_or$mutation == i2,]
write.csv(pnca_snps_or1, "../Data_original/valid_pnca_snps_with_OR.csv")
my_data = read.csv("../Data_original/meta_pza_with_AF.csv"
, stringsAsFactors = FALSE) #11374, 19
View(my_data)
# remove the first column
my_data = my_data[-1] #11374, 18
# check if first col is 'id': should be TRUE
colnames(my_data)[1] == 'id'
# sanity check
snps_all = unique(my_data$mutation)# 337
pnca_snps_or = snps_all
pnca_snps_or = as.data.frame(snps_all)
View(pnca_snps_or)
snps_all[-"true_wt"]
pnca_snps_or = as.data.frame(snps_all[-c(1,1)])
View(pnca_snps_or)
snps_all = as.data.frame(snps_all)
View(snps_all)
#remove true_wt entry
w1 = which(rownames(snps_all) == "true_wt")
View(snps_all)
#remove true_wt entry
w1 = which(snps_all$snps_all == "true_wt")
rm(pnca_snps_or)
pnca_snps_or = snps_all[-w1]
pnca_snps_or = snps_all[,-w1]
pnca_snps_or = as.data.frame(snps_all[-c(1,1)])
#remove true_wt entry
w1 = which(snps_all) == "true_wt"
pnca_snps_or = as.data.frame(snps_all[-c(1,1)])
my_data = read.csv("../Data_original/meta_pza_with_AF.csv"
, stringsAsFactors = FALSE) #11374, 19
# remove the first column
my_data = my_data[-1] #11374, 18
# check if first col is 'id': should be TRUE
colnames(my_data)[1] == 'id'
# sanity check
snps_all = unique(my_data$mutation)# 337
snps_all = as.data.frame(snps_all)
snps_all[-c(1,1)]
pnca_snps_or = as.data.frame(snps_all[-c(1,1)])
pnca_snps_or = as.data.frame(snps_all[, -c(1,1)])
#remove true_wt entry
#w1 = which(snps_all) == "true_wt"
pnca_snps_or = snps_all
pnca_snps_or = pnca_snps_or_copy
#remove true_wt entry
#w1 = which(snps_all) == "true_wt"
pnca_snps_or = snps_all
pnca_snps_or -> pnca_snps_or_copy
#===============
# Step 4: Iterate through this unique list
# and calculate OR for each snp
# and assign to the pnca_snps_or df that has
# each row as a unique snp
#===============
# reset original df so you don't make a mistake: IMPORTANT
pnca_snps_or = pnca_snps_or_copy #2133, 1
# you only need it for the unique mutations
pnca_snps_or = unique(pnca_snps_or) #337, 1
for (i in pnca_snps_unique){
print(i)
#*************
# start logistic regression model building
#*************
# set the IV and DV for the logistic regression model
# IV: corresponds to each unique snp (extracted using grep)
x = as.numeric(grepl(i,raw_data$all_muts_pza))
# DV: pyrazinamide 0 or 1
y = as.numeric(raw_data$pyrazinamide)
table(y,x)
# run glm model
model = glm(y ~ x, family = binomial)
#model = glm(y ~ x, family = binomial(link = "logit"))
summary(model)
#**********
# extract relevant model output
#**********
# extract log OR i.e the Beta estimate of the logistic model for a given snp
my_logor = summary(model)$coefficients[2,1]
print(paste0('Beta:', my_logor))
# extract SE of the logistic model for a given snp
my_se = summary(model)$coefficients[2,2]
print(paste0('SE:', my_se))
# extract Z of the logistic model for a given snp
my_zval = summary(model)$coefficients[2,3]
print(paste0('Z-value:', my_zval))
# Dervive OR i.e exp(my_logor) from the logistic model for a given snp
#my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
my_or = exp(summary(model)$coefficients[2,1])
print(paste0('OR:', my_or))
# sanity check : should be True
log(my_or) == my_logor
# extract P-value of the logistic model for a given snp
my_pval = summary(model)$coefficients[2,4]
print(paste0('P-value:', my_pval))
# extract confint interval of snp (2 steps, since the output is a named number)
ci_mod = exp(confint(model))[2,]
my_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
print(paste0('CI:', my_ci))
#*************
# Assign the regression output in the original df
# you can use ('=' or '<-/->')
#*************
#pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i] = my_logor
my_logor -> pnca_snps_or$logistic_logOR[pnca_snps_or$mutation == i]
my_or -> pnca_snps_or$OR[pnca_snps_or$mutation == i]
my_pval -> pnca_snps_or$pvalue[pnca_snps_or$mutation == i]
my_zval -> pnca_snps_or$zvalue[pnca_snps_or$mutation == i]
my_se -> pnca_snps_or$logistic_se[pnca_snps_or$mutation == i]
my_ci -> pnca_snps_or$ci[pnca_snps_or$mutation == i]
}
getwd()
#setwd("~/Documents/git/LSHTM_Y1_PNCA/meta_data_analysis") # work
setwd("~/git/LSHTM_Y1_PNCA/meta_data_analysis") # thinkpad
#setwd("/Users/tanu/git/LSHTM_Y1_PNCA/meta_data_analysis") # mac
getwd()
#===============
# Step 1: read raw data
#===============
raw_data<-read.csv("../Data_original/original_tanushree_data_v2.csv"
,stringsAsFactors = F)[,c("id","pyrazinamide","dr_mutations_pyrazinamide","other_mutations_pyrazinamide")]#19265, 4
raw_data<-raw_data[!is.na(raw_data$pyrazinamide),]#12511, 4
# combine the two mutation columns
raw_data$all_mutations_pyrazinamide<-paste(raw_data$dr_mutations_pyrazinamide, raw_data$other_mutations_pyrazinamide)#12511, 5
head(raw_data$all_mutations_pyrazinamide)
# create yet another column that contains all the mutations but in lower case
raw_data$all_muts_pza = tolower(raw_data$all_mutations_pyrazinamide) #12511, 6
table(grepl("pnca_p",raw_data$all_muts_pza))
#FALSE  TRUE
#10603  1908
pnca_snps_or = read.csv("../Data_original/pnca_snps_for_or_calcs.csv"
, stringsAsFactors = F
, header = T) #2133
# subset a snall section to test
#pnca_snps_or_copy = pnca_snps_or
#pnca_snps_or = pnca_snps_or_copy
pnca_snps_unique = unique(pnca_snps_or$mutation) #293
i2 = "pnca_p.trp68gly" # Should exist
grep(i2, pnca_snps_unique)
my_data = read.csv("../Data_original/meta_pza_with_AF.csv"
, stringsAsFactors = FALSE) #11374, 19
# remove the first column
my_data = my_data[-1] #11374, 18
# check if first col is 'id': should be TRUE
colnames(my_data)[1] == 'id'
# sanity check
head(my_data$mutation)
my_data = unique(my_data$mutation)
my_data[!duplicated(my_data$mutation)]
my_data_unique = my_data[!duplicated(my_data$mutation),]
my_data[!duplicated('mutation'),]
my_data_unique = my_data[!duplicated(my_data[,'mutation']),]
my_data_unique = my_data[!duplicated(my_data['mutation']),]
getwd()
setwd("/git/LSHTM_analysis/meta_data_analysis")
getwd()
getwd()
setwd("/git/github/LSHTM_analysis/meta_data_analysis")
getwd()
#===============
# Step 1: read GWAS raw data stored in Data_original/
#===============
infile = read.csv("../Data_original", file.choose(), stringsAsFactors = F))
c = file.choose()
c = file.choose(../Data_original)
c = read.csv(file.choose(), stringsAsFactors = F)
#===============
# Step 1: read GWAS raw data stored in Data_original/
#===============
infile = read.csv(file.choose(), stringsAsFactors = F))
c = read.csv(file.choose(), stringsAsFactors = F)
#===============
# Step 1: read GWAS raw data stored in Data_original/
#===============
infile = read.csv(file.choose(), stringsAsFactors = F)
#===============
# Step 1: read GWAS raw data stored in Data_original/
#===============
infile = read.csv(file.choose(), stringsAsFactors = F)
raw_data = infile[,c("id","pyrazinamide","dr_mutations_pyrazinamide","other_mutations_pyrazinamide")]
outdir = paste0("../mcsm_analysis",drug,"/Data/")
# define output variables
drug  = 'pyrazinamide'
outdir = paste0("../mcsm_analysis",drug,"/Data/")
outdir = paste0("../mcsm_analysis/",drug,"/Data/")
outFile = "meta_data_with_AFandOR.csv"
output_filename = paste0(outdir, outFile)
output_filename