all OR calcs using sapply and output as df

scripts/af_or_calcs_scratch.R

@@ -1,5 +1,5 @@
 #########################################################
-# TASK: To compare OR from master data
+# TASK: To compare OR from master snps
 # chisq, fisher test and logistic and adjusted logistic
 #########################################################
 getwd()
@@ -28,10 +28,10 @@ outdir = paste0(datadir, '/', drug, '/', 'output')
 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) )
+cat(paste0('Reading infile1: raw snps', ' ', infile) )
 
-# infile2: _gene associated meta data file to extract valid snps and add calcs to.
+# infile2: _gene associated meta snps file to extract valid snps and add calcs to.
-# This is outfile3 from data_extraction.py
+# This is outfile3 from snps_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))
@@ -39,17 +39,17 @@ cat(paste0('Reading infile2: gene associated metadata:', infile_metadata))
 #===========
 # output
 #===========
-out_filename = paste0(tolower(gene),'_', 'meta_data_with_AF_OR.csv')
+out_filename = paste0(tolower(gene),'_', '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/
+# 1: Read master/raw snps stored in snps/
 #####################################################
 
 #===============
-# Step 1: read raw data (all remove entries with NA in pza column)
+# Step 1: read raw snps (all remove entries with NA in pza column)
 #===============
 raw_data_all = read.csv(infile, stringsAsFactors = F)
 
@@ -147,7 +147,6 @@ if(nrow(gene_snps_or) == expected_rows){
 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
@@ -163,7 +162,7 @@ cat(paste0('Total no. of distinct comp snps to perform OR calcs: ', length(gene_
 # Define OR function
 #x = as.numeric(mut)
 #y = dst
-logistic_chisq_or = function(x,y){
+custom_chisq_or = function(x,y){
   tab = as.matrix(table(x,y))
   a = tab[2,2]
   if (a==0){ a<-0.5}
@@ -179,7 +178,7 @@ logistic_chisq_or = function(x,y){
 
 #========================
 # TEST WITH ONE
-
+#========================
 i = "pnca_p.trp68gly"
 i = "pnca_p.gln10pro"
 i = "pnca_p.leu159arg"
@@ -211,6 +210,11 @@ table(mut, dst, sid)
 #============================
 # compare OR
 chisq.test(table(mut,dst))
+chisq.test(table(mut,dst)) $ statistic
+
+f = chisq.test(table(mut,dst)) $ statistic
+chisq.test(dst, mut) $ statistic
+
 fisher.test(table(mut, dst))
 fisher.test(table(mut, dst))$p.value
 fisher.test(table(mut, dst))$estimate
@@ -219,53 +223,79 @@ logistic_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)
+pval_logistic_maxit = summary(model)$coefficients[2,4]; print(pval_logistic_maxit)
 
-# adjusted logistic or
+# extract SE of the logistic model for a given snp
+logistic_se = summary(model)$coefficients[2,2]
+print(paste0('SE:', logistic_se))
+    
+# extract Z of the logistic model for a given snp
+logistic_zval = summary(model)$coefficients[2,3]
+print(paste0('Z-value:', logistic_zval))
+  
+  
+# extract confint interval of snp (2 steps, since the output is a named number)
+ci_mod = exp(confint(model))[2,]
+print(paste0('CI:', ci_mod))
+#logistic_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
+  
+logistic_ci_lower = ci_mod[["2.5 %"]]
+logistic_ci_upper = ci_mod[["97.5 %"]]
+  
+print(paste0('CI_lower:', logistic_ci_lower))
+print(paste0('CI_upper:', logistic_ci_upper))
+
+
+# adjusted logistic or: doesn't seem to make a difference
 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)
 
-#=========================
+#============ looping with sapply
+#####################
+# iterate: subset
+#####################
 
-ors = sapply(gene_snps_unique,function(m){
+snps_test = c("pnca_p.trp68gly", "pnca_p.leu4ser", "pnca_p.leu159arg","pnca_p.his57arg" )
+
+snps = snps_test[1:4]
+
+snps
+
+
+ors = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   logistic_chisq_or(mut,dst)
 })
 
 ors
 
-pvals = sapply(gene_snps_unique,function(m){
+pvals = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   fisher.test(mut,dst)$p.value
 })
 
 pvals
 
-afs = sapply(gene_snps_unique,function(m){
+afs = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   mean(mut)
 })
 
 afs
 
-# logistic or
+## logistic or
- ors_logistic = sapply(gene_snps_unique,function(m){
+ ors_logistic = sapply(snps,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)$coefficients[2,4]
+
-  #logistic_se = summary(model)$coefficients[2,2]
-  #logistic_zval = summary(model)$coefficients[2,3]
-  #ci_mod = exp(confint(model))[2,]
-  #logistic_ci_lower = ci_mod[["2.5 %"]]
-  #logistic_ci_upper = ci_mod[["97.5 %"]]
 })
 ors_logistic
 head(ors_logistic); head(names(ors_logistic))
 
 ## logistic p-value
-pvals_logistic = sapply(gene_snps_unique,function(m){
+pvals_logistic = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   model<-glm(dst ~ mut , family = binomial)
   pval_logistic = summary(model)$coefficients[2,4]
@@ -274,7 +304,7 @@ pvals_logistic = sapply(gene_snps_unique,function(m){
 head(pvals_logistic); head(names(pvals_logistic))
 
 ## logistic se
-se_logistic = sapply(gene_snps_unique,function(m){
+se_logistic = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   model<-glm(dst ~ mut , family = binomial)
   logistic_se = summary(model)$coefficients[2,2]
@@ -293,7 +323,7 @@ zval_logistic = sapply(gene_snps_unique,function(m){
 head(zval_logistic); head(names(zval_logistic))
 
 ## logistic ci - lower bound
-ci_lb_logistic = sapply(gene_snps_unique,function(m){
+ci_lb_logistic = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   model<-glm(dst ~ mut , family = binomial)
   ci_mod = exp(confint(model))[2,]
@@ -303,7 +333,7 @@ ci_lb_logistic = sapply(gene_snps_unique,function(m){
 head(ci_lb_logistic); head(names(ci_lb_logistic))
 
 ## logistic ci - upper bound
-ci_ub_logistic = sapply(gene_snps_unique,function(m){
+ci_ub_logistic = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   model<-glm(dst ~ mut , family = binomial)
   ci_mod = exp(confint(model))[2,]
@@ -314,7 +344,7 @@ ci_ub_logistic = sapply(gene_snps_unique,function(m){
 head(ci_ub_logistic); head(names(ci_ub_logistic))
 
 # logistic adj # Doesn't seem to make a difference
-logistic_ors2 = sapply(gene_snps_unique,function(m){
+logistic_ors2 = sapply(snps,function(m){
   mut = grepl(m,raw_data$all_muts_gene)
   c = raw_data$id[mut]
   sid = grepl(paste(c,collapse="|"), raw_data$id)
@@ -327,50 +357,106 @@ logistic_ors2
 
 or_logistic2; pval_logistic2
 
-
 head(logistic_ors)
-#====================================
+#===========================================================
-# logistic
+#%%
-summary(model<-glm(dst ~ mut
+# sapply with multiple values
-                   , family = binomial
-                   #, control = glm.control(maxit = 1)
-                   #, options(warn = 1)
-                   ))
-or_logistic = exp(summary(model)$coefficients[2,1]); print(or_logistic)
-pval_logistic_maxit = summary(model)$coefficients[2,4]; print(pval_logistic_maxit)
 
-# extract SE of the logistic model for a given snp
+#https://gist.github.com/primaryobjects/33adabc337edd67b4a8d
-logistic_se = summary(model)$coefficients[2,2]
-print(paste0('SE:', logistic_se))
-  
-  
-# extract Z of the logistic model for a given snp
-logistic_zval = summary(model)$coefficients[2,3]
-print(paste0('Z-value:', logistic_zval))
-  
-  
-# extract confint interval of snp (2 steps, since the output is a named number)
-ci_mod = exp(confint(model))[2,]
-print(paste0('CI:', ci_mod))
-#logistic_ci = paste(ci_mod[["2.5 %"]], ",", ci_mod[["97.5 %"]])
-  
-logistic_ci_lower = ci_mod[["2.5 %"]]
-logistic_ci_upper = ci_mod[["97.5 %"]]
-  
-print(paste0('CI_lower:', logistic_ci_lower))
-print(paste0('CI_upper:', logistic_ci_upper))
-
-#####################
-# iterate: subset
-#####################
 
 snps_test = c("pnca_p.trp68gly", "pnca_p.leu4ser", "pnca_p.leu159arg","pnca_p.his57arg" )
 
-data = snps_test[1:2]
+snps = snps_test[1:4]
 
-data
+snps
-################# start loop
+
-for (i in data){
+# DV: pyrazinamide 0 or 1
+dst = raw_data[[drug]]
+
+# yayy works!
+testdf = data.frame()
+
+x = sapply(snps,function(m){
+
+  df = data.frame()
+  
+  mut = grepl(m,raw_data$all_muts_gene)
+  model<-glm(dst ~ mut, family = binomial)
+  
+  
+  # allele frequency
+  afs = mean(mut)
+  
+  # logistic model
+  beta_logistic = summary(model)$coefficients[2,1]
+
+  or_logistic = exp(summary(model)$coefficients[2,1])
+  print(paste0('logistic OR:', or_logistic))
+  
+  pval_logistic = summary(model)$coefficients[2,4]
+  print(paste0('logistic pval:', pval_logistic))
+  
+  se_logistic = summary(model)$coefficients[2,2]
+  zval_logistic = summary(model)$coefficients[2,3]
+  ci_mod = exp(confint(model))[2,]
+  ci_lower_logistic = ci_mod[["2.5 %"]]
+  ci_upper_logistic = ci_mod[["97.5 %"]]
+  
+  # custom_chisq and fisher: OR p-value and CI
+  or_mychisq = custom_chisq_or(dst, mut)
+  
+  or_fisher = fisher.test(dst, mut)$estimate
+  or_fisher = or_fisher[[1]]
+  
+  pval_fisher = fisher.test(dst, mut)$p.value
+  
+  ci_lower_fisher = fisher.test(dst, mut)$conf.int[1]
+  ci_upper_fisher = fisher.test(dst, mut)$conf.int[2]
+  
+  # chi sq estimates 
+  estimate_chisq = chisq.test(dst, mut)$statistic; estimate_chisq
+  est_chisq = estimate_chisq[[1]]; print(est_chisq)
+  
+  pval_chisq = chisq.test(dst, mut)$p.value                                                        
+                                                         
+  #build a row to append to df
+  row = data.frame(mutation = m
+                   , af = afs
+                   , beta_logistic = beta_logistic
+                   , or_logistic = or_logistic
+                   , pval_logistic = pval_logistic
+                   , se_logistic = se_logistic
+                   , zval_logistic = zval_logistic
+                   , ci_low_logistic = ci_lower_logistic
+                   , ci_hi_logistic = ci_upper_logistic
+                   , or_mychisq = or_mychisq 
+                   , or_fisher = or_fisher
+                   , pval_fisher = pval_fisher
+                   , ci_low_fisher= ci_lower_fisher
+                   , ci_hi_fisher = ci_upper_fisher
+                   , est_chisq = est_chisq
+                   , pval_chisq = pval_chisq
+                   )
+  #print(row)
+  
+  testdf <<- rbind(testdf, row)
+  
+})
+
+write.csv(testdf, 'test_ors.csv')
+#=================================
+####################
+# iterate: subset
+#####################
+print(paste0('subset to iterate over;', snps))
+
+# start loop
+ perfectSeparation <- function(w) {
+  if(grepl("fitted probabilities numerically 0 or 1 occurred",
+           as.character(w))) {ww <<- ww+1}
+}
+
+for (i in snps){
   
   print(i)
   
@@ -386,7 +472,6 @@ for (i in data){
   # 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
@@ -405,6 +490,7 @@ for (i in data){
   ci_mod = exp(confint(model))[2,]
   logistic_ci_lower = ci_mod[["2.5 %"]]
   logistic_ci_upper = ci_mod[["97.5 %"]]
+  
   #=====================
   # fishers test
   #=====================
@@ -431,17 +517,7 @@ for (i in data){
                , 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)))
@@ -455,3 +531,108 @@ table(dst, mut)
   exact2x2(table(dst, mut),tsmethod="central")
 
 
+#=====================================================================
+# iterate over a df and then add these values  
+#
+my_data = as.data.frame(gene_snps_unique)
+colnames(my_data) = "mutation"
+print(colnames(my_data))
+
+perfectSeparation <- function(w) {
+  if(grepl("fitted probabilities numerically 0 or 1 occurred",
+           as.character(w))) {ww <<- ww+1}
+}
+
+for(i in my_data$mutation) {
+  print(paste0('snp to iterate over:', i))
+}
+
+for(i in my_data$mutation) {
+  print(paste0('snp to iterate over:', i))
+
+  #####
+  # Run logistic regression
+  #####
+  
+  #*************
+  # start logistic regression model building
+  # set the IV and DV for the logistic regression model and model
+  #*************
+  # IV: corresponds to each unique snp (extracted using grep)
+  mut = as.numeric(grepl(i,raw_data$dr_muts_pza))
+  
+  # DV: pyrazinamide 0 or 1
+  dst = as.numeric(raw_data$pyrazinamide)
+  
+  tab = table(mut, dst)
+  print(tab)
+  
+  # glm model: with and without maxit
+  model = tryCatch( glm(dst ~ mut
+                        , family = binomial
+                        #, control = glm.control(maxit = 1) # only used when required for one step estimator
+  ), warning = perfectSeparation)
+  
+  model = glm(dst ~ mut, family = binomial)
+  
+  print(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)$coefficients[2,1]
+  print(paste0('Beta:', my_logor))
+  
+  # Dervive OR i.e exp(my_or) from the logistic model for a given snp
+  #my_or = round(exp(summary(model)$coefficients[2,1]), roundto)
+  my_or = exp(summary(model)$coefficients[2,1])
+  print(paste0('OR:', my_or))
+  
+  # extract SE of the logistic model for a given snp
+  my_se = summary(model)$coefficients[2,2]
+  print(paste0('SE:', my_se))
+  
+  # extract Z of the logistic model for a given snp
+  my_zval = summary(model)$coefficients[2,3]
+  print(paste0('Z-value:', my_zval))
+
+  # extract P-value of the logistic model for a given snp
+  my_pval = summary(model)$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 %"]])
+  
+  my_ci_lower = ci_mod[["2.5 %"]]
+  my_ci_upper = ci_mod[["97.5 %"]]
+  
+  print(paste0('CI_lower:', my_ci_lower))
+  print(paste0('CI_upper:', my_ci_upper))
+  
+  #*************
+  # Assign the regression output in the to df (meta_pza_pnca_snps_only)
+  # you can use ('=' or '<-/->')
+  #*************
+  #my_data$logistic_logOR[my_data$mutation == i] = my_logor
+ 
+  my_or -> my_data$OR[my_data$mutation == i]
+  
+  my_pval -> my_data$pvalue[my_data$mutation == i]
+  
+  my_zval -> my_data$zvalue[my_data$mutation == i]
+  
+  my_se -> my_data$logistic_se[my_data$mutation == i]
+  
+  my_ci_lower -> my_data$ci_lower[my_data$mutation == i]
+  
+  my_ci_upper -> my_data$ci_upper[my_data$mutation == i]
+  
+  #=#=#=#=#=#=#=#
+  # COMMENT: This assigns the relevant extracted output 
+  # to the df and fills NA where the mutation (row) doesn't exist 
+  # in my mutation list I am iterating over
+  #=#=#=#=#=#=#=#
+  
+}