#########################################################
# TASK: To compare OR from master data
# chisq, fisher test and logistic and adjusted logistic
#########################################################
getwd()
setwd('~/git/LSHTM_analysis/scripts')
getwd()

#install.packages("logistf")
library(logistf)
#########################################################
#%% variable assignment: input and output paths & filenames
drug = 'pyrazinamide'
gene = 'pncA'
gene_match = paste0(gene,'_p.')
cat(gene_match)

#===========
# input and output dirs
#===========
datadir = paste0('~/git/Data')
indir = paste0(datadir, '/', drug, '/', 'input')
outdir = paste0(datadir, '/', drug, '/', 'output')

#===========
# input and output files
#===========
in_filename  = 'original_tanushree_data_v2.csv'
#in_filename  = 'mtb_gwas_v3.csv'
infile = paste0(datadir, '/', in_filename)
cat(paste0('Reading infile1: raw data', ' ', infile) )

# infile2: _gene associated meta data file to extract valid snps and add calcs to.
# This is outfile3 from data_extraction.py
in_filename_metadata = paste0(tolower(gene), '_metadata.csv')
infile_metadata = paste0(outdir, '/', in_filename_metadata)
cat(paste0('Reading infile2: gene associated metadata:', infile_metadata))

#===========
# output
#===========
out_filename = paste0(tolower(gene),'_', 'meta_data_with_AF_OR.csv')
outfile = paste0(outdir, '/', out_filename)
cat(paste0('Output file with full path:', outfile))
#%% end of variable assignment for input and output files

#########################################################
# 1: Read master/raw data stored in Data/
#####################################################

#===============
# Step 1: read raw data (all remove entries with NA in pza column)
#===============
raw_data_all = read.csv(infile, stringsAsFactors = F)

# building cols to extract
dr_muts_col = paste0('dr_mutations_', drug)
other_muts_col = paste0('other_mutations_', drug)

cat('Extracting columns based on variables:\n'
    , drug
    , '\n'
    , dr_muts_col
    , '\n'
    , other_muts_col
    , '\n===============================================================')

raw_data = raw_data_all[,c("id"
                           , drug
                           , dr_muts_col
                           , other_muts_col)]
rm(raw_data_all)

rm(indir, in_filename, infile)

#===========
# 1a: exclude na
#===========
raw_data = raw_data[!is.na(raw_data[[drug]]),]

total_samples = length(unique(raw_data$id))
cat(paste0('Total samples without NA in', ' ', drug, 'is:', total_samples))

# sanity check: should  be true
is.numeric(total_samples) 

#===========
# 1b: combine the two mutation columns
#===========
#raw_data$all_mutations_pyrazinamide = paste(raw_data$dr_mutations_pyrazinamide, raw_data$other_mutations_pyrazinamide)

all_muts_colname = paste0('all_mutations_', drug)
raw_data[[all_muts_colname]] = paste(raw_data[[dr_muts_col]], raw_data[[other_muts_col]])
head(raw_data[[all_muts_colname]])

#===========
# 1c: create yet another column that contains all the mutations but in lower case
#===========
head(raw_data[[all_muts_colname]])
raw_data$all_muts_gene = tolower(raw_data[[all_muts_colname]]) 
head(raw_data$all_muts_gene)

# sanity checks
#table(grepl("gene_p",raw_data$all_muts_gene))
cat(paste0('converting gene match:', gene_match, ' ', 'to lowercase'))
gene_match = tolower(gene_match)

table(grepl(gene_match,raw_data$all_muts_gene))

# sanity check
if(sum(table(grepl(gene_match, raw_data$all_muts_gene))) == total_samples){
  cat('PASS: Total no. of samples match')
} else{
  cat('FAIL: No. of samples mismatch')
}

#########################################################
# 2: Read valid snps for which OR 
# can be calculated
#########################################################
cat(paste0('Reading metadata infile:', infile_metadata))

gene_metadata = read.csv(infile_metadata
                         #, file.choose()
                         , stringsAsFactors = F
                         , header = T)


# clear variables
rm(in_filename_metadata, infile_metadata)

# count na in pyrazinamide column
tot_pza_na = sum(is.na(gene_metadata$pyrazinamide))
expected_rows = nrow(gene_metadata) - tot_pza_na

# drop na from the pyrazinamide colum
gene_snps_or = gene_metadata[!is.na(gene_metadata[[drug]]),]

# sanity check
if(nrow(gene_snps_or) == expected_rows){
  cat('PASS: no. of rows match with expected_rows')
} else{
  cat('FAIL: nrows mismatch.')
}

# extract unique snps to iterate over for AF and OR calcs
gene_snps_unique = unique(gene_snps_or$mutation) 

cat(paste0('Total no. of distinct comp snps to perform OR calcs: ', length(gene_snps_unique)))

#=====================================
#OR calcs using the following 4
#1) chisq.test
#2) fisher
#3) modified chisq.test
#4) logistic
#5) adjusted logistic?
#6) kinship (separate script)

#======================================

################# modified chisq OR
# Define OR function
#x = as.numeric(mut)
#y = dst
my_chisq_or = function(x,y){
  tab = as.matrix(table(x,y))
  a = tab[2,2]
  if (a==0){ a<-0.5}
  b = tab[2,1]
  if (b==0){ b<-0.5}
  c = tab[1,2]
  if (c==0){ c<-0.5}
  d = tab[1,1]
  if (d==0){ d<-0.5}
  (a/b)/(c/d)
  
}

#========================
# TEST WITH ONE

i = "pnca_p.trp68gly"
i = "pnca_p.gln10pro"
i = "pnca_p.leu159arg"

# IV
table(grepl(i,raw_data$all_muts_gene))
mut = grepl(i,raw_data$all_muts_gene)

# DV
#dst = raw_data$pyrazinamide
dst = raw_data[[drug]] # or raw_data[,drug]

# 2X2 table
table(mut, dst)

# CV
#c = raw_data$id[mut]
c = raw_data$id[grepl(i,raw_data$all_muts_gene)] 
#sid = grepl(raw_data$id[mut], raw_data$id) # warning
#argument 'pattern' has length > 1 and only the first element will be used
#grepl(raw_data$id=="ERR2512440", raw_data$id)

sid = grepl(paste(c,collapse="|"), raw_data$id)
table(sid)   

# 3X2 table
table(mut, dst, sid)

#============================
# compare OR
chisq.test(table(mut,dst))
fisher.test(table(mut, dst))
fisher.test(table(mut, dst))$p.value
fisher.test(table(mut, dst))$estimate
my_chisq_or(mut,dst)

# logistic or
summary(model<-glm(dst ~ mut, family = binomial))
or_logistic = exp(summary(model)$coefficients[2,1]); print(or_logistic)
pval_logistic = summary(model)$coefficients[2,4]; print(pval_logistic)

# adjusted logistic or
summary(model2<-glm(dst ~ mut + sid, family = binomial))
or_logistic2 = exp(summary(model2)$coefficients[2,1]); print(or_logistic2)
pval_logistic2 = summary(model2)$coefficients[2,4]; print(pval_logistic2)

#=========================

ors = sapply(gene_snps_unique,function(m){
  mut = grepl(m,raw_data$all_muts_gene)
  my_chisq_or(mut,dst)
})

ors

pvals = sapply(gene_snps_unique,function(m){
  mut = grepl(m,raw_data$all_muts_gene)
  fisher.test(mut,dst)$p.value
})

pvals

afs = sapply(gene_snps_unique,function(m){
  mut = grepl(m,raw_data$all_muts_gene)
  mean(mut)
})

afs

# logistic
logistic_ors = sapply(gene_snps_unique,function(m){
  mut = grepl(m,raw_data$all_muts_gene)
  model<-glm(dst ~ mut, family = binomial)
  or_logistic = exp(summary(model)$coefficients[2,1])
  #pval_logistic = summary(model)$coefficients[2,4]
})
logistic_ors


# logistic adj # Doesn't seem to make a difference
logistic_ors2 = sapply(gene_snps_unique,function(m){
  mut = grepl(m,raw_data$all_muts_gene)
  c = raw_data$id[mut]
  sid = grepl(paste(c,collapse="|"), raw_data$id)
  model2<-glm(dst ~ mut + sid, family = binomial)
  or_logistic2 = exp(summary(model2)$coefficients[2,1])
  #pval_logistic2 = summary(model2)$coefficients[2,4]
})

logistic_ors2

or_logistic2; pval_logistic2


head(logistic_ors)
#====================================

# logistic
summary(model<-glm(dst ~ mut
                   , family = binomial
                   #, control = glm.control(maxit = 1)
                   #, options(warn = 1)
                   ))
or_logistic_maxit = exp(summary(model)$coefficients[2,1]); print(or_logistic_maxit)
pval_logistic_maxit = summary(model)$coefficients[2,4]; print(pval_logistic_maxit)


#####################
# iterate: subset
#####################

snps_test = c("pnca_p.trp68gly", "pnca_p.leu4ser", "pnca_p.leu159arg","pnca_p.his57arg" )

data = snps_test[1:2]

data




################# start loop
for (i in data){
  
  print(i)
  
  # IV
  #mut<-as.numeric(grepl(i,raw_data$all_muts_gene))
  mut = grepl(i,raw_data$all_muts_gene)
  table(mut)
  
  # DV
  #dst<-as.numeric(raw_data[[drug]])
  dst = raw_data[[drug]]
  
  # table
  print(table(dst, mut))
  

  #=====================
  # logistic regression, glm.control(maxit = n)
  #https://stats.stackexchange.com/questions/11109/how-to-deal-with-perfect-separation-in-logistic-regression
  #=====================
  #n = 1
  summary(model<-glm(dst ~ mut
                     , family = binomial
                     #, control = glm.control(maxit = 1)
                     #, options(warn = 1)
                     ))
  or_logistic_maxit = exp(summary(model)$coefficients[2,1]); print(or_logistic_maxit)
  pval_logistic_maxit = summary(model)$coefficients[2,4]; print(pval_logistic_maxit)
  
  #=====================
  # fishers test
  #=====================
  #attributes(fisher.test(table(dst, mut)))
  or_fisher = fisher.test(table(dst, mut))$estimate
  or_fisher = or_fisher[[1]]; or_fisher
  
  pval_fisher = fisher.test(table(dst, mut))$p.value ; pval_fisher
  
  #=====================
  # chi square
  #=====================
  #chisq.test(y = dst, x = mut)
  #attributes(chisq.test(table(dst, mut)))
  est_chisq = chisq.test(table(dst, mut))$statistic 
  est_chisq = est_chisq[[1]]; est_chisq
  
  pval_chisq = chisq.test(table(dst, mut))$p.value; pval_chisq
  
  # all output 
  writeLines(c(paste0("mutation:", i)
               , paste0("=========================")
               , paste0("OR_logistic_maxit:", or_logistic_maxit,"--->", "P-val_logistic_maxit:", pval_logistic_maxit )
               , paste0("OR_fisher:", or_fisher, "--->","P-val_fisher:", pval_fisher )
               , paste0("Chi_sq_estimate:", est_chisq, "--->","P-val_chisq:", pval_chisq)))
    

}


i  = "gene_p.leu159arg"

mut<-as.numeric(grepl(i,raw_data$all_muts_pza))
# DV
dst<-as.numeric(raw_data$pyrazinamide)
# tablehttps://mail.google.com/mail/?tab=rm&ogbl
table(dst, mut)

 #=====================
  # fishers test
  #=====================
  #attributes(fisher.test(table(dst, mut)))
  or_fisher = fisher.test(table(dst, mut))$estimate
  or_fisher = or_fisher[[1]]; or_fisher
  
  pval_fisher = fisher.test(table(dst, mut))$p.value ; pval_fisher
  
  
 # https://stats.stackexchange.com/questions/259635/what-is-the-difference-using-a-fishers-exact-test-vs-a-logistic-regression-for
  exact2x2(table(dst, mut),tsmethod="central")