diff --git a/asthma/check_stats.R b/asthma/check_stats.R
new file mode 100755
index 0000000..315c90c
--- /dev/null
+++ b/asthma/check_stats.R
@@ -0,0 +1,183 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+########################################################################
+# TASK: check stats
+########################################################################
+# load libraries, packages and local imports
+source("Header_TT.R")
+
+#=============
+# Input
+#=============
+source("data_extraction_mediators.R")
+#source("read_data.R")
+
+########################################################################
+#=============
+# Data extraction for non-severe
+#=============
+table(fp_adults_ics$asthma)
+table(fp_adults_ics$obesity)
+
+df = fp_adults_ics[fp_adults_ics$asthma == 1,]
+table(df$obesity)
+
+df_ob = df[df$obesity == 1,]
+df_nob = df[df$obesity == 0,]
+
+rm(npa_lf, npa_wf, sam_lf, sam_wf, serum_lf, serum_wf, fp_adults_ics)
+
+#============
+# npa
+#============
+# il8: t2
+wilcox.test(df_ob$il8_serum2, df_nob$il8_serum2)
+wilcox_test(il8_serum2 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il8_serum2)
+na_c = sum(is.na(foo$df.il8_serum2))
+nrow(df) - na_c
+
+tapply(df$il8_serum2, df$obesity, median, na.rm = T)
+tapply(df$il8_serum2, df$obesity, summary, na.rm = T)
+
+# il8_2: t2
+wilcox.test(df_ob$il8_2_serum2, df_nob$il8_2_serum2)
+wilcox_test(il8_2_serum2 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il8_2_serum2)
+na_c = sum(is.na(foo$df.il8_2_serum2))
+nrow(df) - na_c
+
+tapply(df$il8_2_serum2, df$obesity, median, na.rm = T)
+tapply(df$il8_2_serum2, df$obesity, summary, na.rm = T)
+
+
+# il4: t3
+wilcox.test(df_ob$il4_serum3, df_nob$il4_serum3)
+wilcox_test(il4_serum3 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il4_serum3)
+na_c = sum(is.na(foo$df.il4_serum3))
+nrow(df) - na_c
+
+tapply(df$il4_serum3, df$obesity, median, na.rm = T)
+tapply(df$il4_serum3, df$obesity, summary, na.rm = T)
+
+# ifnb: t3
+wilcox.test(df_ob$ifnb_serum3, df_nob$ifnb_serum3)
+wilcox_test(ifnb_serum3 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$ifnb_serum3)
+na_c = sum(is.na(foo$df.ifnb_serum3))
+nrow(df) - na_c
+
+tapply(df$ifnb_serum3, df$obesity, median, na.rm = T)
+tapply(df$ifnb_serum3, df$obesity, summary, na.rm = T)
+
+#============
+# sam
+#============
+# tarc: t3
+wilcox.test(df_ob$tarc_sam3
+            , df_nob$tarc_sam3)
+
+foo = data.frame(df$obesity, df$tarc_sam3)
+na_c = sum(is.na(foo$df.tarc_sam3))
+nrow(df) - na_c
+
+tapply(df$tarc_sam3, df$obesity, median, na.rm = T)
+
+
+# il13: t3
+wilcox.test(df_ob$il13_sam3
+            , df_nob$il13_sam3)
+
+foo = data.frame(df$obesity, df$il13_sam3)
+na_c = sum(is.na(foo$df.il13_sam3))
+nrow(df) - na_c
+
+tapply(df$il13_sam3, df$obesity, median, na.rm = T)
+
+
+# eotaxin: t1
+wilcox.test(df_ob$eotaxin_sam1
+            , df_nob$eotaxin_sam1)
+
+foo = data.frame(df$obesity, df$eotaxin_sam1)
+na_c = sum(is.na(foo$df.eotaxin_sam1))
+nrow(df) - na_c
+
+tapply(df$eotaxin_sam1, df$obesity, median, na.rm = T)
+
+
+#============
+# serum
+#============
+# ifna2a: t1
+wilcox.test(df_ob$ifna2a_serum1, 
+            df_nob$ifna2a_serum1)
+
+foo = data.frame(df$obesity, df$ifna2a_serum1)
+na_c = sum(is.na(foo$df.ifna2a_serum1))
+nrow(df) - na_c
+
+tapply(df$ifna2a_serum1, df$obesity, median, na.rm = T)
+
+
+# mip17: t1
+wilcox.test(df_ob$mip17_serum1, 
+            df_nob$mip17_serum1)
+
+foo = data.frame(df$obesity, df$mip17_serum1)
+na_c = sum(is.na(foo$df.mip17_serum1))
+nrow(df) - na_c
+
+tapply(df$mip17_serum1, df$obesity, median, na.rm = T)
+
+# il1: t1
+wilcox.test(df_ob$il1_serum1
+            , df_nob$il1_serum1)
+
+foo = data.frame(df$obesity, df$il1_serum1)
+na_c = sum(is.na(foo$df.il1_serum1))
+nrow(df) - na_c
+
+tapply(df$il1_serum1, df$obesity, median, na.rm = T)
+tapply(df$il1_serum1, df$obesity, summary, na.rm = T)
+boxplot(df_ob$il1_serum1, df_nob$il1_serum1)
+
+
+# ifna2a: t2 
+wilcox.test(df_ob$ifna2a_serum2, 
+            df_nob$ifna2a_serum2)
+
+foo = data.frame(df$obesity, df$ifna2a_serum2)
+na_c = sum(is.na(foo$df.ifna2a_serum2))
+nrow(df) - na_c
+
+
+tapply(df$ifna2a_serum2, df$obesity, median, na.rm = T)
+
+# ifna2a: t3
+wilcox.test(df_ob$ifna2a_serum3, 
+            df_nob$ifna2a_serum3)
+
+foo = data.frame(df$obesity, df$ifna2a_serum3)
+na_c = sum(is.na(foo$df.ifna2a_serum3))
+nrow(df) - na_c
+
+tapply(df$ifna2a_serum3, df$obesity, median, na.rm = T)
+
+
+# ifnb: t3
+wilcox.test(df_ob$ifnb_serum3
+            , df_nob$ifnb_serum3)
+
+foo = data.frame(df$obesity, df$ifnb_serum3)
+na_c = sum(is.na(foo$df.ifnb_serum3))
+nrow(df) - na_c
+
+tapply(df$ifnb_serum3, df$obesity, median, na.rm = T)
diff --git a/asthma/flu_a_stats_unpaired_npa.R b/asthma/flu_a_stats_unpaired_npa.R
new file mode 100755
index 0000000..fa07b41
--- /dev/null
+++ b/asthma/flu_a_stats_unpaired_npa.R
@@ -0,0 +1,386 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+############################################################
+# TASK: unpaired (time) analysis of mediators:
+# sample type: NPA
+# data: Flu positive adult patients
+# group: obesity
+############################################################
+my_sample_type = "npa"
+
+#=============
+# Input
+#=============
+#source("data_extraction_mediators.R")
+source("plot_data_a.R")
+
+# check: copd and asthma conflict
+table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1)
+
+#=============
+# Output
+#=============
+outfile_name = paste0("flu_stats_time_unpaired_a_", my_sample_type, ".csv")
+flu_stats_time_unpaired = paste0(outdir_stats_a, outfile_name)
+flu_stats_time_unpaired
+
+# quick checks
+table(wf_fp_npa$T1_resp_score)
+table(lf_fp_npa$mediator, lf_fp_npa$timepoint, lf_fp_npa$T1_resp_score)
+table(wf_fp_npa$obesity)
+
+#===============================
+# data assignment for stats
+#================================
+wf = wf_fp_npa
+lf = lf_fp_npa
+
+identical(wf, wf_fp_npa)
+identical(lf, lf_fp_npa)
+########################################################################
+# clear variables
+rm(lf_fp_sam, lf_fp_serum
+, wf_fp_sam, wf_fp_serum) 
+
+# sanity checks
+table(lf$timepoint)
+length(unique(lf$mosaic))
+
+########################################################################
+# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis 
+# with correction
+########################################################################
+# with adjustment: fdr and BH are identical
+my_adjust_method = "BH"
+
+#==============
+# unpaired: t1
+#==============
+lf_t1 = lf[lf$timepoint == "t1",]
+sum(is.na(lf_t1$value))
+
+foo = lf_t1[which(is.na(lf_t1$value)),]
+#ci = which(is.na(lf_t1$value))
+#lf_t1_comp = lf_t1[-ci,]
+
+lf_t1_comp = lf_t1[-which(is.na(lf_t1$value)),]
+stats_un_t1 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t1 
+                            , data = lf_t1_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+foo$mosaic[!unique(foo$mosaic)%in%unique(lf_t1_comp$mosaic)]
+
+# add timepoint and convert to df
+stats_un_t1$timepoint = "t1"
+stats_un_t1 = as.data.frame(stats_un_t1)
+class(stats_un_t1)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t1
+#----------------------------------------
+#n_t1 = data.frame(table(lf_t1_comp$mediator))
+n_t1_all = data.frame(table(lf_t1$mediator))
+colnames(n_t1_all) = c("mediator", "n_obs")
+n_t1_all$mediator = as.character(n_t1_all$mediator)
+
+n_t1_comp = data.frame(table(lf_t1_comp$mediator))
+colnames(n_t1_comp) = c("mediator", "n_obs_complete")
+n_t1_comp$mediator = as.character(n_t1_comp$mediator)
+
+merge_cols = intersect(names(n_t1_all), names(n_t1_comp)); merge_cols
+n_t1= merge(n_t1_all, n_t1_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#===================================
+merging_cols = intersect(names(stats_un_t1), names(n_t1)); merging_cols
+if (all(n_t1$mediator%in%stats_un_t1$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}else{
+  nf = n_t1$mediator[!n_t1$mediator%in%stats_un_t1$mediator]
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}
+
+# add bonferroni adjustment as well
+stats_un_t1$p_adj_bonferroni = p.adjust(stats_un_t1$p, method = "bonferroni")
+
+rm(n_t1)
+rm(lf_t1_comp)
+
+#==============
+# unpaired: t2
+#==============
+lf_t2 = lf[lf$timepoint == "t2",]
+lf_t2_comp = lf_t2[-which(is.na(lf_t2$value)),]
+                   
+stats_un_t2 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t2 
+                            , data = lf_t2_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+# add timepoint and convert to df
+stats_un_t2$timepoint = "t2"
+stats_un_t2 = as.data.frame(stats_un_t2)
+class(stats_un_t2)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t2
+#----------------------------------------
+#n_t2 = data.frame(table(lf_t2_comp$mediator))
+n_t2_all = data.frame(table(lf_t2$mediator))
+colnames(n_t2_all) = c("mediator", "n_obs")
+n_t2_all$mediator = as.character(n_t2_all$mediator)
+
+n_t2_comp = data.frame(table(lf_t2_comp$mediator))
+colnames(n_t2_comp) = c("mediator", "n_obs_complete")
+n_t2_comp$mediator = as.character(n_t2_comp$mediator)
+
+merge_cols = intersect(names(n_t2_all), names(n_t2_comp)); merge_cols
+n_t2= merge(n_t2_all, n_t2_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
+if (all(n_t2$mediator%in%stats_un_t2$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}else{
+  nf = n_t2$mediator[!n_t2$mediator%in%stats_un_t2$mediator]
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}
+
+# add bonferroni adjustment as well
+stats_un_t2$p_adj_bonferroni = p.adjust(stats_un_t2$p, method = "bonferroni")
+
+rm(n_t2)
+rm(lf_t2_comp)
+
+#==============
+# unpaired: t3
+#==============
+lf_t3 = lf[lf$timepoint == "t3",]
+lf_t3_comp = lf_t3[-which(is.na(lf_t3$value)),]
+
+stats_un_t3 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t3 
+                            , data = lf_t3_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+# add timepoint and convert to df
+stats_un_t3$timepoint = "t3"
+stats_un_t3 = as.data.frame(stats_un_t3)
+class(stats_un_t3)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t3
+#----------------------------------------
+#n_t3 = data.frame(table(lf_t3_comp$mediator))
+n_t3_all = data.frame(table(lf_t3$mediator))
+colnames(n_t3_all) = c("mediator", "n_obs")
+n_t3_all$mediator = as.character(n_t3_all$mediator)
+
+n_t3_comp = data.frame(table(lf_t3_comp$mediator))
+colnames(n_t3_comp) = c("mediator", "n_obs_complete")
+n_t3_comp$mediator = as.character(n_t3_comp$mediator)
+
+merge_cols = intersect(names(n_t3_all), names(n_t3_comp)); merge_cols
+n_t3= merge(n_t3_all, n_t3_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t3), names(n_t3)); merging_cols
+if (all(n_t3$mediator%in%stats_un_t3$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}else{
+  nf = n_t3$mediator[!n_t3$mediator%in%stats_un_t3$mediator]
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}
+
+# add bonferroni adjustment as well
+stats_un_t3$p_adj_bonferroni = p.adjust(stats_un_t3$p, method = "bonferroni")
+
+rm(n_t3)
+rm(lf_t3_comp)
+
+########################################################################
+#==============
+# Rbind these dfs
+#==============
+str(stats_un_t1);str(stats_un_t2); str(stats_un_t3)
+
+n_dfs = 3
+
+if ( all.equal(nrow(stats_un_t1), nrow(stats_un_t2), nrow(stats_un_t3)) && 
+     all.equal(ncol(stats_un_t1), ncol(stats_un_t2), ncol(stats_un_t3)) ) {
+  expected_rows = nrow(stats_un_t1) * n_dfs
+  expected_cols = ncol(stats_un_t1)
+  print("PASS: expected_rows and cols variables generated for downstream sanity checks")
+}else{
+  cat("FAIL: dfs have different no. of rows and cols"
+      , "\nCheck harcoded value of n_dfs"
+      , "\nexpected_rows and cols could not be generated")
+  quit()
+}
+
+if ( all.equal(colnames(stats_un_t1), colnames(stats_un_t2), colnames(stats_un_t3)) ){
+  print("PASS: colnames match. Rbind the 3 dfs...")
+  combined_unpaired_stats = rbind(stats_un_t1, stats_un_t2, stats_un_t3)
+} else{
+  cat("FAIL: cannot combined dfs. Colnames don't match!")
+  quit()
+}
+
+if ( nrow(combined_unpaired_stats) == expected_rows && ncol(combined_unpaired_stats) == expected_cols ){
+  cat("PASS: combined_df has expected dimension"
+      , "\nNo. of rows in combined_df:", nrow(combined_unpaired_stats)
+      , "\nNo. of cols in combined_df:", ncol(combined_unpaired_stats) )
+}else{
+  cat("FAIL: combined_df dimension mismatch")
+  quit()
+}
+
+#######################################################################
+#=================
+# formatting df
+#=================
+# delete: unnecessary column
+combined_unpaired_stats = subset(combined_unpaired_stats, select = -c(.y.))
+
+# add sample_type
+cat("Adding sample type info as a column", my_sample_type, "...")
+combined_unpaired_stats$sample_type = my_sample_type 
+
+# add: reflect stats method correctly i.e paired or unpaired
+# incase there are NA due to LLODs, the gsub won't work!
+#combined_unpaired_stats$method = gsub("Wilcoxon", "Wilcoxon_unpaired", combined_unpaired_stats$method)
+combined_unpaired_stats$method = "wilcoxon unpaired"
+combined_unpaired_stats$method
+
+# add an extra column for padjust_signif: my_adjust_method
+combined_unpaired_stats$padjust_signif = combined_unpaired_stats$p.adj
+# add appropriate symbols for padjust_signif: my_adjust_method
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, padjust_signif = case_when(padjust_signif == 0.05 ~ "."
+                                                                                             , padjust_signif <=0.0001 ~ '****'
+                                                                                             , padjust_signif <=0.001 ~ '***'
+                                                                                             , padjust_signif <=0.01 ~ '**'
+                                                                                             , padjust_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# add an extra column for p_bon_signif
+combined_unpaired_stats$p_bon_signif = combined_unpaired_stats$p_adj_bonferroni
+# add appropriate symbols for p_bon_signif
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, p_bon_signif = case_when(p_bon_signif == 0.05 ~ "."
+                                                                                             , p_bon_signif <=0.0001 ~ '****'
+                                                                                             , p_bon_signif <=0.001 ~ '***'
+                                                                                             , p_bon_signif <=0.01 ~ '**'
+                                                                                             , p_bon_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# reorder columns
+print("preparing to reorder columns...")
+colnames(combined_unpaired_stats)
+my_col_order2 = c("mediator"
+                  , "timepoint"
+                  , "sample_type"
+                  , "n_obs"
+                  , "n_obs_complete"
+                  , "group1"
+                  , "group2"
+                  , "method"
+                  , "p"
+                  , "p.format"
+                  , "p.signif"
+                  , "p.adj"
+                  , "padjust_signif"
+                  , "p_adj_bonferroni"
+                  , "p_bon_signif")
+
+if( length(my_col_order2) == ncol(combined_unpaired_stats) && (all(my_col_order2%in%colnames(combined_unpaired_stats))) ){
+  print("PASS: Reordering columns...")
+  combined_unpaired_stats_f = combined_unpaired_stats[, my_col_order2]
+  print("Successful: column reordering")
+  print("formatted df called:'combined_unpaired_stats_f'")
+  cat('\nformatted df has the following dimensions\n')
+  print(dim(combined_unpaired_stats_f ))
+} else{
+  cat(paste0("FAIL:Cannot reorder columns, length mismatch"
+             , "\nExpected column order for: ", ncol(combined_unpaired_stats)
+             , "\nGot:", length(my_col_order2)))
+  quit()
+}  
+# assign nice column names like replace "." with "_"
+colnames(combined_unpaired_stats_f) = c("mediator"
+                                        , "timepoint" 
+                                        , "sample_type"
+                                        , "n_obs" 
+                                        , "n_obs_complete"
+                                        , "group1"
+                                        , "group2"
+                                        , "method" 
+                                        , "p" 
+                                        , "p_format"
+                                        , "p_signif"
+                                        , paste0("p_adj_fdr_", my_adjust_method)
+                                        , paste0("p_", my_adjust_method, "_signif")
+                                        , "p_adj_bonferroni"
+                                        , "p_bon_signif")
+
+colnames(combined_unpaired_stats_f)
+
+#---------------
+# quick summary
+#---------------
+# count how many meds are significant
+n_sig  = length(combined_unpaired_stats_f$mediator[combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)])
+sig_meds = combined_unpaired_stats_f[(combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)),]
+
+sig_meds$med_time = paste0(sig_meds$mediator, "@", sig_meds$timepoint)
+
+cat("\nTotal no. of statistically significant mediators in", toupper(my_sample_type)
+    , "are:", n_sig
+    , "\nThese are:", sig_meds$med_time)
+
+########################################################################
+#******************
+# write output file
+#******************
+cat("\nUNpaired stats for groups will be:", flu_stats_time_unpaired)
+write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE)
diff --git a/asthma/flu_a_stats_unpaired_sam.R b/asthma/flu_a_stats_unpaired_sam.R
new file mode 100755
index 0000000..ef41a58
--- /dev/null
+++ b/asthma/flu_a_stats_unpaired_sam.R
@@ -0,0 +1,395 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+############################################################
+# TASK: unpaired (time) analysis of mediators:
+# sample type: SAM
+# data: Flu positive adult patients
+# group: obesity
+############################################################
+my_sample_type = "sam"
+
+#=============
+# Input
+#=============
+#source("data_extraction_mediators.R")
+source("plot_data_a.R")
+
+# check: copd and asthma conflict
+table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1)
+
+#=============
+# Output
+#=============
+outfile_name = paste0("flu_stats_time_unpaired_a_", my_sample_type, ".csv")
+flu_stats_time_unpaired = paste0(outdir_stats_a, outfile_name)
+flu_stats_time_unpaired
+
+# quick checks
+table(wf_fp_sam$T1_resp_score)
+table(lf_fp_sam$mediator, lf_fp_sam$timepoint, lf_fp_sam$T1_resp_score)
+table(wf_fp_sam$obesity)
+
+#===============================
+# data assignment for stats
+#================================
+wf = wf_fp_sam
+lf = lf_fp_sam
+
+identical(wf, wf_fp_sam)
+identical(lf, lf_fp_sam)
+
+########################################################################
+# clear variables
+rm(lf_fp_npa, lf_fp_serum
+   , wf_fp_npa, wf_fp_serum) 
+
+# sanity checks
+table(lf$timepoint)
+length(unique(lf$mosaic))
+
+#if (table(lf$flustat) == table(sam_lf$flustat)[[2]]){
+#  cat("Analysing Flu positive patients for:", my_sample_type)
+#}else{
+#  cat("FAIL: problem with subsetting data for:", my_sample_type)
+#  quit()
+#}
+
+########################################################################
+# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis 
+# with correction
+#######################################################################
+# with adjustment: fdr and BH are identical
+my_adjust_method = "BH"
+
+#==============
+# unpaired: t1
+#==============
+lf_t1 = lf[lf$timepoint == "t1",]
+sum(is.na(lf_t1$value))
+
+foo = lf_t1[which(is.na(lf_t1$value)),]
+#ci = which(is.na(lf_t1$value))
+#lf_t1_comp = lf_t1[-ci,]
+
+lf_t1_comp = lf_t1[-which(is.na(lf_t1$value)),]
+stats_un_t1 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t1 
+                            , data = lf_t1_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+foo$mosaic[!unique(foo$mosaic)%in%unique(lf_t1_comp$mosaic)]
+
+# add timepoint and convert to df
+stats_un_t1$timepoint = "t1"
+stats_un_t1 = as.data.frame(stats_un_t1)
+class(stats_un_t1)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t1
+#----------------------------------------
+#n_t1 = data.frame(table(lf_t1_comp$mediator))
+n_t1_all = data.frame(table(lf_t1$mediator))
+colnames(n_t1_all) = c("mediator", "n_obs")
+n_t1_all$mediator = as.character(n_t1_all$mediator)
+
+n_t1_comp = data.frame(table(lf_t1_comp$mediator))
+colnames(n_t1_comp) = c("mediator", "n_obs_complete")
+n_t1_comp$mediator = as.character(n_t1_comp$mediator)
+
+merge_cols = intersect(names(n_t1_all), names(n_t1_comp)); merge_cols
+n_t1= merge(n_t1_all, n_t1_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#===================================
+merging_cols = intersect(names(stats_un_t1), names(n_t1)); merging_cols
+if (all(n_t1$mediator%in%stats_un_t1$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}else{
+  nf = n_t1$mediator[!n_t1$mediator%in%stats_un_t1$mediator]
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}
+
+# add bonferroni adjustment as well
+stats_un_t1$p_adj_bonferroni = p.adjust(stats_un_t1$p, method = "bonferroni")
+
+rm(n_t1)
+rm(lf_t1_comp)
+
+#==============
+# unpaired: t2
+#==============
+lf_t2 = lf[lf$timepoint == "t2",]
+lf_t2_comp = lf_t2[-which(is.na(lf_t2$value)),]
+                   
+stats_un_t2 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t2 
+                            , data = lf_t2_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+# add timepoint and convert to df                           
+stats_un_t2$timepoint = "t2"
+stats_un_t2 = as.data.frame(stats_un_t2)
+class(stats_un_t2)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t2
+#----------------------------------------
+#n_t2 = data.frame(table(lf_t2_comp$mediator))
+n_t2_all = data.frame(table(lf_t2$mediator))
+colnames(n_t2_all) = c("mediator", "n_obs")
+n_t2_all$mediator = as.character(n_t2_all$mediator)
+
+n_t2_comp = data.frame(table(lf_t2_comp$mediator))
+colnames(n_t2_comp) = c("mediator", "n_obs_complete")
+n_t2_comp$mediator = as.character(n_t2_comp$mediator)
+
+merge_cols = intersect(names(n_t2_all), names(n_t2_comp)); merge_cols
+n_t2= merge(n_t2_all, n_t2_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#===================================
+merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
+if (all(n_t2$mediator%in%stats_un_t2$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}else{
+  nf = n_t2$mediator[!n_t2$mediator%in%stats_un_t2$mediator]
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}
+
+# add bonferroni adjustment as well
+stats_un_t2$p_adj_bonferroni = p.adjust(stats_un_t2$p, method = "bonferroni")
+
+rm(n_t2)
+rm(lf_t2_comp)
+
+#==============
+# unpaired: t3
+#==============
+lf_t3 = lf[lf$timepoint == "t3",]
+lf_t3_comp = lf_t3[-which(is.na(lf_t3$value)),]
+
+stats_un_t3 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t3 
+                            , data = lf_t3_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+# add timepoint and convert to df                            
+stats_un_t3$timepoint = "t3"
+stats_un_t3 = as.data.frame(stats_un_t3)
+class(stats_un_t3)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t3
+#----------------------------------------
+#n_t3 = data.frame(table(lf_t3_comp$mediator))
+n_t3_all = data.frame(table(lf_t3$mediator))
+colnames(n_t3_all) = c("mediator", "n_obs")
+n_t3_all$mediator = as.character(n_t3_all$mediator)
+
+n_t3_comp = data.frame(table(lf_t3_comp$mediator))
+colnames(n_t3_comp) = c("mediator", "n_obs_complete")
+n_t3_comp$mediator = as.character(n_t3_comp$mediator)
+
+merge_cols = intersect(names(n_t3_all), names(n_t3_comp)); merge_cols
+n_t3= merge(n_t3_all, n_t3_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t3), names(n_t3)); merging_cols
+if (all(n_t3$mediator%in%stats_un_t3$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}else{
+  nf = n_t3$mediator[!n_t3$mediator%in%stats_un_t3$mediator]
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}
+
+# check: satisfied!!!!
+# FIXME: supply the col name automatically?
+wilcox.test(wf$ifna2a_sam3[wf$obesity == 1], wf$ifna2a_sam3[wf$obesity == 0])
+
+# add bonferroni adjustment as well
+stats_un_t3$p_adj_bonferroni = p.adjust(stats_un_t3$p, method = "bonferroni")
+
+rm(n_t3)
+rm(lf_t3_comp)
+########################################################################
+#=================
+# Rbind these dfs
+#=================
+str(stats_un_t1);str(stats_un_t2); str(stats_un_t3)
+
+n_dfs = 3
+
+if ( all.equal(nrow(stats_un_t1), nrow(stats_un_t2), nrow(stats_un_t3)) && 
+     all.equal(ncol(stats_un_t1), ncol(stats_un_t2), ncol(stats_un_t3)) ) {
+  expected_rows = nrow(stats_un_t1) * n_dfs
+  expected_cols = ncol(stats_un_t1)
+  print("PASS: expected_rows and cols variables generated for downstream sanity checks")
+}else{
+  cat("FAIL: dfs have different no. of rows and cols"
+      , "\nCheck harcoded value of n_dfs"
+      , "\nexpected_rows and cols could not be generated")
+  quit()
+}
+
+if ( all.equal(colnames(stats_un_t1), colnames(stats_un_t2), colnames(stats_un_t3)) ){
+  print("PASS: colnames match. Rbind the 3 dfs...")
+  combined_unpaired_stats = rbind(stats_un_t1, stats_un_t2, stats_un_t3)
+} else{
+  cat("FAIL: cannot combined dfs. Colnames don't match!")
+  quit()
+}
+
+if ( nrow(combined_unpaired_stats) == expected_rows && ncol(combined_unpaired_stats) == expected_cols ){
+  cat("PASS: combined_df has expected dimension"
+      , "\nNo. of rows in combined_df:", nrow(combined_unpaired_stats)
+      , "\nNo. of cols in combined_df:", ncol(combined_unpaired_stats) )
+}else{
+  cat("FAIL: combined_df dimension mismatch")
+  quit()
+}
+
+#######################################################################
+#=================
+# formatting df
+#=================
+# delete: unnecessary column
+combined_unpaired_stats = subset(combined_unpaired_stats, select = -c(.y.))
+
+# add sample_type
+cat("Adding sample type info as a column", my_sample_type, "...")
+combined_unpaired_stats$sample_type = my_sample_type 
+
+# add: reflect stats method correctly i.e paired or unpaired
+# incase there are NA due to LLODs, the gsub won't work!
+#combined_unpaired_stats$method = gsub("Wilcoxon", "Wilcoxon_unpaired", combined_unpaired_stats$method)
+combined_unpaired_stats$method = "wilcoxon unpaired"
+combined_unpaired_stats$method
+
+# add an extra column for padjust_signif: my_adjust_method
+combined_unpaired_stats$padjust_signif = combined_unpaired_stats$p.adj
+# add appropriate symbols for padjust_signif: my_adjust_method
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, padjust_signif = case_when(padjust_signif == 0.05 ~ "."
+                                                                                             , padjust_signif <=0.0001 ~ '****'
+                                                                                             , padjust_signif <=0.001 ~ '***'
+                                                                                             , padjust_signif <=0.01 ~ '**'
+                                                                                             , padjust_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# add an extra column for p_bon_signif
+combined_unpaired_stats$p_bon_signif = combined_unpaired_stats$p_adj_bonferroni
+# add appropriate symbols for p_bon_signif
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, p_bon_signif = case_when(p_bon_signif == 0.05 ~ "."
+                                                                                             , p_bon_signif <=0.0001 ~ '****'
+                                                                                             , p_bon_signif <=0.001 ~ '***'
+                                                                                             , p_bon_signif <=0.01 ~ '**'
+                                                                                             , p_bon_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# reorder columns
+print("preparing to reorder columns...")
+colnames(combined_unpaired_stats)
+my_col_order2 = c("mediator"
+                  , "timepoint"
+                  , "sample_type"
+                  , "n_obs"
+                  , "n_obs_complete"
+                  , "group1"
+                  , "group2"
+                  , "method"
+                  , "p"
+                  , "p.format"
+                  , "p.signif"
+                  , "p.adj"
+                  , "padjust_signif"
+                  , "p_adj_bonferroni"
+                  , "p_bon_signif")
+
+if( length(my_col_order2) == ncol(combined_unpaired_stats) && (all(my_col_order2%in%colnames(combined_unpaired_stats))) ){
+  print("PASS: Reordering columns...")
+  combined_unpaired_stats_f = combined_unpaired_stats[, my_col_order2]
+  print("Successful: column reordering")
+  print("formatted df called:'combined_unpaired_stats_f'")
+  cat('\nformatted df has the following dimensions\n')
+  print(dim(combined_unpaired_stats_f ))
+} else{
+  cat(paste0("FAIL:Cannot reorder columns, length mismatch"
+             , "\nExpected column order for: ", ncol(combined_unpaired_stats)
+             , "\nGot:", length(my_col_order2)))
+  quit()
+}  
+# assign nice column names like replace "." with "_"
+colnames(combined_unpaired_stats_f) = c("mediator"
+                                        , "timepoint" 
+                                        , "sample_type"
+                                        , "n_obs" 
+                                        , "n_obs_complete"
+                                        , "group1"
+                                        , "group2"
+                                        , "method" 
+                                        , "p" 
+                                        , "p_format"
+                                        , "p_signif"
+                                        , paste0("p_adj_fdr_", my_adjust_method)
+                                        , paste0("p_", my_adjust_method, "_signif")
+                                        , "p_adj_bonferroni"
+                                        , "p_bon_signif")
+
+colnames(combined_unpaired_stats_f)
+
+#---------------
+# quick summary
+#---------------
+# count how many meds are significant
+n_sig  = length(combined_unpaired_stats_f$mediator[combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)])
+sig_meds = combined_unpaired_stats_f[(combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)),]
+
+sig_meds$med_time = paste0(sig_meds$mediator, "@", sig_meds$timepoint)
+
+cat("\nTotal no. of statistically significant mediators in", toupper(my_sample_type)
+    , "are:", n_sig
+    , "\nThese are:", sig_meds$med_time)
+
+#######################################################################
+#******************
+# write output file
+#******************
+cat("\nUNpaired stats for groups will be:", flu_stats_time_unpaired)
+write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE)
diff --git a/asthma/flu_a_stats_unpaired_serum.R b/asthma/flu_a_stats_unpaired_serum.R
new file mode 100755
index 0000000..e201081
--- /dev/null
+++ b/asthma/flu_a_stats_unpaired_serum.R
@@ -0,0 +1,376 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+############################################################
+# TASK: unpaired (time) analysis of mediators: serum
+############################################################
+my_sample_type = "serum"
+
+#=============
+# Input
+#=============
+#source("data_extraction_mediators.R")
+source("plot_data_a.R")
+
+# check: copd and asthma conflict
+table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1)
+
+#=============
+# Output
+#=============
+outfile_name = paste0("flu_stats_time_unpaired_a_", my_sample_type, ".csv")
+flu_stats_time_unpaired = paste0(outdir_stats_a, outfile_name)
+flu_stats_time_unpaired
+
+# quick checks
+table(wf_fp_serum$T1_resp_score)
+table(lf_fp_serum$mediator, lf_fp_npa$timepoint, lf_fp_npa$T1_resp_score)
+table(wf_fp_serum$obesity)
+
+#===============================
+# data assignment for stats
+#================================
+wf = wf_fp_serum
+lf = lf_fp_serum
+
+identical(wf, wf_fp_serum)
+identical(lf, lf_fp_serum)
+########################################################################
+# clear variables
+rm(lf_fp_sam, lf_fp_npa
+   , wf_fp_sam, wf_fp_npa) 
+########################################################################
+# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis
+# with correction
+#######################################################################
+# with adjustment: fdr and BH are identical
+my_adjust_method = "BH"
+
+#=============
+# unpaired: t1
+#==============
+lf_t1 = lf[lf$timepoint == "t1",]
+sum(is.na(lf_t1$value))
+
+foo = lf_t1[which(is.na(lf_t1$value)),]
+ci = which(is.na(lf_t1$value))
+#lf_t1_comp = lf_t1[-ci,]
+
+lf_t1_comp = lf_t1[-which(is.na(lf_t1$value)),]
+stats_un_t1 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t1 
+                            , data = lf_t1_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+foo$mosaic[!unique(foo$mosaic)%in%unique(lf_t1_comp$mosaic)]
+
+# add timepoint and convert to df
+stats_un_t1$timepoint = "t1"
+stats_un_t1 = as.data.frame(stats_un_t1)
+class(stats_un_t1)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t1
+#----------------------------------------
+#n_t1 = data.frame(table(lf_t1_comp$mediator))
+n_t1_all = data.frame(table(lf_t1$mediator))
+colnames(n_t1_all) = c("mediator", "n_obs")
+n_t1_all$mediator = as.character(n_t1_all$mediator)
+
+n_t1_comp = data.frame(table(lf_t1_comp$mediator))
+colnames(n_t1_comp) = c("mediator", "n_obs_complete")
+n_t1_comp$mediator = as.character(n_t1_comp$mediator)
+
+merge_cols = intersect(names(n_t1_all), names(n_t1_comp)); merge_cols
+n_t1= merge(n_t1_all, n_t1_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t1), names(n_t1)); merging_cols
+if (all(n_t1$mediator%in%stats_un_t1$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}else{
+  nf = n_t1$mediator[!n_t1$mediator%in%stats_un_t1$mediator]
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}
+
+# add bonferroni adjustment as well
+stats_un_t1$p_adj_bonferroni = p.adjust(stats_un_t1$p, method = "bonferroni")
+
+rm(n_t1)
+rm(lf_t1_comp)
+
+#==============
+# unpaired: t2
+#==============
+lf_t2 = lf[lf$timepoint == "t2",]
+lf_t2_comp = lf_t2[-which(is.na(lf_t2$value)),]
+                   
+stats_un_t2 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t2 
+                            , data = lf_t2_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+# add timepoint and convert to df
+stats_un_t2$timepoint = "t2"
+stats_un_t2 = as.data.frame(stats_un_t2)
+class(stats_un_t2)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t2
+#----------------------------------------
+#n_t2 = data.frame(table(lf_t2_comp$mediator))
+n_t2_all = data.frame(table(lf_t2$mediator))
+colnames(n_t2_all) = c("mediator", "n_obs")
+n_t2_all$mediator = as.character(n_t2_all$mediator)
+
+n_t2_comp = data.frame(table(lf_t2_comp$mediator))
+colnames(n_t2_comp) = c("mediator", "n_obs_complete")
+n_t2_comp$mediator = as.character(n_t2_comp$mediator)
+
+merge_cols = intersect(names(n_t2_all), names(n_t2_comp)); merge_cols
+n_t2= merge(n_t2_all, n_t2_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
+if (all(n_t2$mediator%in%stats_un_t2$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}else{
+  nf = n_t2$mediator[!n_t2$mediator%in%stats_un_t2$mediator]
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}
+
+# add bonferroni adjustment as well
+stats_un_t2$p_adj_bonferroni = p.adjust(stats_un_t2$p, method = "bonferroni")
+
+rm(n_t2)
+rm(lf_t2_comp)
+
+#==============
+# unpaired: t3
+#==============
+lf_t3 = lf[lf$timepoint == "t3",]
+lf_t3_comp = lf_t3[-which(is.na(lf_t3$value)),]
+
+stats_un_t3 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t3 
+                            , data = lf_t3_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+# add timepoint and convert to df
+stats_un_t3$timepoint = "t3"
+stats_un_t3 = as.data.frame(stats_un_t3)
+class(stats_un_t3)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t3
+#----------------------------------------
+#n_t3 = data.frame(table(lf_t3_comp$mediator))
+n_t3_all = data.frame(table(lf_t3$mediator))
+colnames(n_t3_all) = c("mediator", "n_obs")
+n_t3_all$mediator = as.character(n_t3_all$mediator)
+
+n_t3_comp = data.frame(table(lf_t3_comp$mediator))
+colnames(n_t3_comp) = c("mediator", "n_obs_complete")
+n_t3_comp$mediator = as.character(n_t3_comp$mediator)
+
+merge_cols = intersect(names(n_t3_all), names(n_t3_comp)); merge_cols
+n_t3 = merge(n_t3_all, n_t3_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t3), names(n_t3)); merging_cols
+if (all(n_t3$mediator%in%stats_un_t3$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}else{
+  nf = n_t3$mediator[!n_t3$mediator%in%stats_un_t3$mediator]
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}
+
+# add bonferroni adjustment as well
+stats_un_t3$p_adj_bonferroni = p.adjust(stats_un_t3$p, method = "bonferroni")
+
+rm(n_t3)
+rm(lf_t3_comp)
+########################################################################
+#==============
+# Rbind these dfs
+#==============
+str(stats_un_t1);str(stats_un_t2); str(stats_un_t3)
+
+n_dfs = 3
+
+if ( all.equal(nrow(stats_un_t1), nrow(stats_un_t2), nrow(stats_un_t3)) && 
+     all.equal(ncol(stats_un_t1), ncol(stats_un_t2), ncol(stats_un_t3)) ) {
+  expected_rows = nrow(stats_un_t1) * n_dfs
+  expected_cols = ncol(stats_un_t1)
+  print("PASS: expected_rows and cols variables generated for downstream sanity checks")
+}else{
+  cat("FAIL: dfs have different no. of rows and cols"
+      , "\nCheck harcoded value of n_dfs"
+      , "\nexpected_rows and cols could not be generated")
+  quit()
+}
+
+if ( all.equal(colnames(stats_un_t1), colnames(stats_un_t2), colnames(stats_un_t3)) ){
+  print("PASS: colnames match. Rbind the 3 dfs...")
+  combined_unpaired_stats = rbind(stats_un_t1, stats_un_t2, stats_un_t3)
+} else{
+  cat("FAIL: cannot combined dfs. Colnames don't match!")
+  quit()
+} 
+
+if ( nrow(combined_unpaired_stats) == expected_rows && ncol(combined_unpaired_stats) == expected_cols ){
+  cat("PASS: combined_df has expected dimension"
+      , "\nNo. of rows in combined_df:", nrow(combined_unpaired_stats)
+      , "\nNo. of cols in combined_df:", ncol(combined_unpaired_stats) )
+}else{
+  cat("FAIL: combined_df dimension mismatch")
+  quit()
+}
+
+#######################################################################
+#=================
+# formatting df
+#=================
+# delete: unnecessary column
+combined_unpaired_stats = subset(combined_unpaired_stats, select = -c(.y.))
+
+# add sample_type
+cat("Adding sample type info as a column", my_sample_type, "...")
+combined_unpaired_stats$sample_type = my_sample_type
+
+# add: reflect stats method correctly i.e paired or unpaired
+# incase there are NA due to LLODs, the gsub won't work!
+#combined_unpaired_stats$method = gsub("Wilcoxon", "Wilcoxon_unpaired", combined_unpaired_stats$method)
+combined_unpaired_stats$method = "wilcoxon unpaired"
+combined_unpaired_stats$method
+
+# add an extra column for padjust_signif: my_adjust_method
+combined_unpaired_stats$padjust_signif = combined_unpaired_stats$p.adj
+# add appropriate symbols for padjust_signif: my_adjust_method
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, padjust_signif = case_when(padjust_signif == 0.05 ~ "."
+                                                                                             , padjust_signif <=0.0001 ~ '****'
+                                                                                             , padjust_signif <=0.001 ~ '***'
+                                                                                             , padjust_signif <=0.01 ~ '**'
+                                                                                             , padjust_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# add an extra column for p_bon_signif
+combined_unpaired_stats$p_bon_signif = combined_unpaired_stats$p_adj_bonferroni
+# add appropriate symbols for p_bon_signif
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, p_bon_signif = case_when(p_bon_signif == 0.05 ~ "."
+                                                                                             , p_bon_signif <=0.0001 ~ '****'
+                                                                                             , p_bon_signif <=0.001 ~ '***'
+                                                                                             , p_bon_signif <=0.01 ~ '**'
+                                                                                             , p_bon_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# reorder columns
+print("preparing to reorder columns...")
+colnames(combined_unpaired_stats)
+my_col_order2 = c("mediator"
+                  , "timepoint"
+                  , "sample_type"
+                  , "n_obs"
+                  , "n_obs_complete"
+                  , "group1"
+                  , "group2"
+                  , "method"
+                  , "p"
+                  , "p.format"
+                  , "p.signif"
+                  , "p.adj"
+                  , "padjust_signif"
+                  , "p_adj_bonferroni"
+                  , "p_bon_signif")
+
+if( length(my_col_order2) == ncol(combined_unpaired_stats) && (all(my_col_order2%in%colnames(combined_unpaired_stats))) ){
+  print("PASS: Reordering columns...")
+  combined_unpaired_stats_f = combined_unpaired_stats[, my_col_order2]
+  print("Successful: column reordering")
+  print("formatted df called:'combined_unpaired_stats_f'")
+  cat('\nformatted df has the following dimensions\n')
+  print(dim(combined_unpaired_stats_f ))
+} else{
+  cat(paste0("FAIL:Cannot reorder columns, length mismatch"
+             , "\nExpected column order for: ", ncol(combined_unpaired_stats)
+             , "\nGot:", length(my_col_order2)))
+  quit()
+}  
+# assign nice column names like replace "." with "_"
+colnames(combined_unpaired_stats_f) = c("mediator"
+                                        , "timepoint" 
+                                        , "sample_type"
+                                        , "n_obs" 
+                                        , "n_obs_complete"
+                                        , "group1"
+                                        , "group2"
+                                        , "method" 
+                                        , "p" 
+                                        , "p_format"
+                                        , "p_signif"
+                                        , paste0("p_adj_fdr_", my_adjust_method)
+                                        , paste0("p_", my_adjust_method, "_signif")
+                                        , "p_adj_bonferroni"
+                                        , "p_bon_signif")
+
+colnames(combined_unpaired_stats_f)
+
+#---------------
+# quick summary
+#---------------
+# count how many meds are significant
+n_sig  = length(combined_unpaired_stats_f$mediator[combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)])
+sig_meds = combined_unpaired_stats_f[(combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)),]
+
+sig_meds$med_time = paste0(sig_meds$mediator, "@", sig_meds$timepoint)
+
+cat("\nTotal no. of statistically significant mediators in", toupper(my_sample_type)
+    , "are:", n_sig
+    , "\nThese are:", sig_meds$med_time)
+
+########################################################################
+#******************
+# write output file
+#******************
+cat("UNpaired stats for groups will be:", flu_stats_time_unpaired)
+write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE)
\ No newline at end of file
diff --git a/severe/check_stats.R b/severe/check_stats.R
new file mode 100755
index 0000000..3c013f4
--- /dev/null
+++ b/severe/check_stats.R
@@ -0,0 +1,244 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+########################################################################
+# TASK: check stats
+########################################################################
+# load libraries, packages and local imports
+source("Header_TT.R")
+
+#=============
+# Input
+#=============
+source("data_extraction_mediators.R")
+#source("read_data.R")
+
+########################################################################
+#=============
+# Data extraction for non-severe
+#=============
+table(fp_adults_ics$T1_resp_score)
+table(fp_adults_ics$obesity)
+
+df = fp_adults_ics[fp_adults_ics$T1_resp_score==3,]
+table(df$obesity)
+
+df_ob = df[df$obesity == 1,]
+df_nob = df[df$obesity == 0,]
+
+rm(npa_lf, npa_wf, sam_lf, sam_wf, serum_lf, serum_wf, fp_adults_ics)
+
+#============
+# npa
+#============
+# eotaxin: t1
+wilcox.test(df_ob$eotaxin_npa1, df_nob$eotaxin_npa1)
+wilcox_test(eotaxin_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$eotaxin_npa1)
+na_c = sum(is.na(foo$df.eotaxin_npa1))
+nrow(df) - na_c
+
+tapply(df$eotaxin_npa1, df$obesity, median, na.rm = T)
+tapply(df$eotaxin_npa1, df$obesity, summary, na.rm = T)
+
+# eotaxin: t1
+wilcox.test(df_ob$eotaxin3_npa1, df_nob$eotaxin3_npa1)
+wilcox_test(eotaxin3_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$eotaxin3_npa1)
+na_c = sum(is.na(foo$df.eotaxin3_npa1))
+nrow(df) - na_c
+
+tapply(df$eotaxin3_npa1, df$obesity, median, na.rm = T)
+tapply(df$eotaxin3_npa1, df$obesity, summary, na.rm = T)
+
+# il1: t1
+wilcox.test(df_ob$il1_npa1, df_nob$il1_npa1)
+wilcox_test(il1_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il1_npa1)
+na_c = sum(is.na(foo$df.il1_npa1))
+nrow(df) - na_c
+
+tapply(df$il1_npa1, df$obesity, median, na.rm = T)
+tapply(df$il1_npa1, df$obesity, summary, na.rm = T)
+
+# il10: t1
+wilcox.test(df_ob$il10_npa1, df_nob$il10_npa1)
+wilcox_test(il10_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il10_npa1)
+na_c = sum(is.na(foo$df.il10_npa1))
+nrow(df) - na_c
+
+tapply(df$il10_npa1, df$obesity, median, na.rm = T)
+tapply(df$il10_npa1, df$obesity, summary, na.rm = T)
+
+# il12p70: t1
+wilcox.test(df_ob$il12p70_npa1, df_nob$il12p70_npa1)
+wilcox_test(il12p70_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il12p70_npa1)
+na_c = sum(is.na(foo$df.il12p70_npa1))
+nrow(df) - na_c
+
+tapply(df$il12p70_npa1, df$obesity, median, na.rm = T)
+tapply(df$il12p70_npa1, df$obesity, summary, na.rm = T)
+
+# il17: t1
+wilcox.test(df_ob$il17_npa1, df_nob$il17_npa1)
+wilcox_test(il17_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il17_npa1)
+na_c = sum(is.na(foo$df.il7_npa1))
+nrow(df) - na_c
+
+tapply(df$il17_npa1, df$obesity, median, na.rm = T)
+tapply(df$il7_npa1, df$obesity, summary, na.rm = T)
+
+# il5: t1
+wilcox.test(df_ob$il5_npa1, df_nob$il5_npa1)
+wilcox_test(il5_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il5_npa1)
+na_c = sum(is.na(foo$df.il5_npa1))
+nrow(df) - na_c
+
+tapply(df$il5_npa1, df$obesity, median, na.rm = T)
+tapply(df$il5_npa1, df$obesity, summary, na.rm = T)
+
+
+# il6: t1
+wilcox.test(df_ob$il6_npa1, df_nob$il6_npa1)
+wilcox_test(il6_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il6_npa1)
+na_c = sum(is.na(foo$df.il6_npa1))
+nrow(df) - na_c
+
+tapply(df$il6_npa1, df$obesity, median, na.rm = T)
+tapply(df$il6_npa1, df$obesity, summary, na.rm = T)
+
+# mcp4: t1
+wilcox.test(df_ob$mcp4_npa1, df_nob$mcp4_npa1)
+wilcox_test(mcp4_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$mcp4_npa1)
+na_c = sum(is.na(foo$df.mcp4_npa1))
+nrow(df) - na_c
+
+tapply(df$mcp4_npa1, df$obesity, median, na.rm = T)
+tapply(df$mcp4_npa1, df$obesity, summary, na.rm = T)
+
+
+# mip17: t1
+wilcox.test(df_ob$mip17_npa1, df_nob$mip17_npa1)
+wilcox_test(mip17_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$mip17_npa1)
+na_c = sum(is.na(foo$df.mip17_npa1))
+nrow(df) - na_c
+
+tapply(df$mip17_npa1, df$obesity, median, na.rm = T)
+tapply(df$mip17_npa1, df$obesity, summary, na.rm = T)
+
+
+# neopterin: t1
+wilcox.test(df_ob$neopterin_npa1, df_nob$neopterin_npa1)
+wilcox_test(neopterin_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$neopterin_npa1)
+na_c = sum(is.na(foo$df.neopterin_npa1))
+nrow(df) - na_c
+
+tapply(df$neopterin_npa1, df$obesity, median, na.rm = T)
+tapply(df$neopterin_npa1, df$obesity, summary, na.rm = T)
+
+# tnfr1: t1
+wilcox.test(df_ob$tnfr1_npa1, df_nob$tnfr1_npa1)
+wilcox_test(tnfr1_npa1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$neopterin_npa1)
+na_c = sum(is.na(foo$df.tnfr1_npa1))
+nrow(df) - na_c
+
+tapply(df$tnfr1_npa1, df$obesity, median, na.rm = T)
+tapply(df$tnfr1_npa1 , df$obesity, summary, na.rm = T)
+
+#============
+# sam
+#============
+# il5: t1
+wilcox.test(df_ob$il5_sam1, df_nob$il5_sam1)
+wilcox_test(il5_sam1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il5_sam1)
+na_c = sum(is.na(foo$df.il5_sam1))
+nrow(df) - na_c
+
+tapply(df$il5_sam1, df$obesity, median, na.rm = T)
+tapply(df$il5_sam1 , df$obesity, summary, na.rm = T)
+
+#============
+# serum
+#============
+# il17: t1
+wilcox.test(df_ob$il17_serum1, df_nob$il17_serum1)
+wilcox_test(il17_serum1 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il17_serum1)
+na_c = sum(is.na(foo$df.il17_serum1))
+nrow(df) - na_c
+
+tapply(df$il17_serum1, df$obesity, median, na.rm = T)
+tapply(df$il17_serum1 , df$obesity, summary, na.rm = T)
+
+
+# il17: t3
+wilcox.test(df_ob$il17_serum3, df_nob$il17_serum3)
+wilcox_test(il17_serum3 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$il17_serum3)
+na_c = sum(is.na(foo$df.il17_serum3))
+nrow(df) - na_c
+
+tapply(df$il17_serum3, df$obesity, median, na.rm = T)
+tapply(df$il17_serum3 , df$obesity, summary, na.rm = T)
+
+# mcp4: t3
+wilcox.test(df_ob$mcp4_serum3, df_nob$mcp4_serum3)
+wilcox_test(mcp4_serum3 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$mcp4_serum3)
+na_c = sum(is.na(foo$df.mcp4_serum3))
+nrow(df) - na_c
+
+tapply(df$mcp4_serum3, df$obesity, median, na.rm = T)
+tapply(df$mcp4_serum3, df$obesity, summary, na.rm = T)
+
+
+# eotaxin3: t3
+wilcox.test(df_ob$eotaxin3_serum3, df_nob$eotaxin3_serum3)
+wilcox_test(eotaxin3_serum3 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$eotaxin3_serum3)
+na_c = sum(is.na(foo$df.eotaxin3_serum3))
+nrow(df) - na_c
+
+tapply(df$eotaxin3_serum3, df$obesity, median, na.rm = T)
+tapply(df$eotaxin3_serum3, df$obesity, summary, na.rm = T)
+
+
+# rantes: t3
+wilcox.test(df_ob$rantes_serum3, df_nob$rantes_serum3)
+wilcox_test(rantes_serum3 ~ obesity, data = df)
+
+foo = data.frame(df$obesity, df$rantes_serum3)
+na_c = sum(is.na(foo$df.rantes_serum3))
+nrow(df) - na_c
+
+tapply(df$rantes_serum3, df$obesity, median, na.rm = T)
+tapply(df$rantes_serum3, df$obesity, summary, na.rm = T)
+
diff --git a/severe/flu_s_stats_unpaired_npa.R b/severe/flu_s_stats_unpaired_npa.R
new file mode 100755
index 0000000..540185a
--- /dev/null
+++ b/severe/flu_s_stats_unpaired_npa.R
@@ -0,0 +1,386 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+############################################################
+# TASK: unpaired (time) analysis of mediators:
+# sample type: NPA
+# data: Flu positive adult patients
+# group: obesity
+############################################################
+my_sample_type = "npa"
+
+#=============
+# Input
+#=============
+#source("data_extraction_mediators.R")
+source("plot_data_s.R")
+
+# check: copd and asthma conflict
+table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1)
+
+#=============
+# Output
+#=============
+outfile_name = paste0("flu_stats_time_unpaired_s_", my_sample_type, ".csv")
+flu_stats_time_unpaired = paste0(outdir_stats_s, outfile_name)
+flu_stats_time_unpaired
+
+# quick checks
+table(wf_fp_npa$T1_resp_score)
+table(lf_fp_npa$mediator, lf_fp_npa$timepoint, lf_fp_npa$T1_resp_score)
+
+#===============================
+# data assignment for stats
+#================================
+wf = wf_fp_npa
+lf = lf_fp_npa
+
+identical(wf, wf_fp_npa)
+identical(lf, lf_fp_npa)
+########################################################################
+# clear variables
+rm(lf_fp_sam, lf_fp_serum
+, wf_fp_sam, wf_fp_serum) 
+
+# sanity checks
+table(lf$timepoint)
+length(unique(lf$mosaic))
+table(wf$obesity)
+
+########################################################################
+# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis 
+# with correction
+########################################################################
+# with adjustment: fdr and BH are identical
+my_adjust_method = "BH"
+
+#==============
+# unpaired: t1
+#==============
+lf_t1 = lf[lf$timepoint == "t1",]
+sum(is.na(lf_t1$value))
+
+foo = lf_t1[which(is.na(lf_t1$value)),]
+#ci = which(is.na(lf_t1$value))
+#lf_t1_comp = lf_t1[-ci,]
+
+lf_t1_comp = lf_t1[-which(is.na(lf_t1$value)),]
+stats_un_t1 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t1 
+                            , data = lf_t1_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+foo$mosaic[!unique(foo$mosaic)%in%unique(lf_t1_comp$mosaic)]
+
+# add timepoint and convert to df
+stats_un_t1$timepoint = "t1"
+stats_un_t1 = as.data.frame(stats_un_t1)
+class(stats_un_t1)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t1
+#----------------------------------------
+#n_t1 = data.frame(table(lf_t1_comp$mediator))
+n_t1_all = data.frame(table(lf_t1$mediator))
+colnames(n_t1_all) = c("mediator", "n_obs")
+n_t1_all$mediator = as.character(n_t1_all$mediator)
+
+n_t1_comp = data.frame(table(lf_t1_comp$mediator))
+colnames(n_t1_comp) = c("mediator", "n_obs_complete")
+n_t1_comp$mediator = as.character(n_t1_comp$mediator)
+
+merge_cols = intersect(names(n_t1_all), names(n_t1_comp)); merge_cols
+n_t1= merge(n_t1_all, n_t1_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#===================================
+merging_cols = intersect(names(stats_un_t1), names(n_t1)); merging_cols
+if (all(n_t1$mediator%in%stats_un_t1$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}else{
+  nf = n_t1$mediator[!n_t1$mediator%in%stats_un_t1$mediator]
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}
+
+# add bonferroni adjustment as well
+stats_un_t1$p_adj_bonferroni = p.adjust(stats_un_t1$p, method = "bonferroni")
+
+rm(n_t1)
+rm(lf_t1_comp)
+
+#==============
+# unpaired: t2
+#==============
+lf_t2 = lf[lf$timepoint == "t2",]
+lf_t2_comp = lf_t2[-which(is.na(lf_t2$value)),]
+                   
+stats_un_t2 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t2 
+                            , data = lf_t2_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+# add timepoint and convert to df
+stats_un_t2$timepoint = "t2"
+stats_un_t2 = as.data.frame(stats_un_t2)
+class(stats_un_t2)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t2
+#----------------------------------------
+#n_t2 = data.frame(table(lf_t2_comp$mediator))
+n_t2_all = data.frame(table(lf_t2$mediator))
+colnames(n_t2_all) = c("mediator", "n_obs")
+n_t2_all$mediator = as.character(n_t2_all$mediator)
+
+n_t2_comp = data.frame(table(lf_t2_comp$mediator))
+colnames(n_t2_comp) = c("mediator", "n_obs_complete")
+n_t2_comp$mediator = as.character(n_t2_comp$mediator)
+
+merge_cols = intersect(names(n_t2_all), names(n_t2_comp)); merge_cols
+n_t2= merge(n_t2_all, n_t2_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
+if (all(n_t2$mediator%in%stats_un_t2$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}else{
+  nf = n_t2$mediator[!n_t2$mediator%in%stats_un_t2$mediator]
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}
+
+# add bonferroni adjustment as well
+stats_un_t2$p_adj_bonferroni = p.adjust(stats_un_t2$p, method = "bonferroni")
+
+rm(n_t2)
+rm(lf_t2_comp)
+
+#==============
+# unpaired: t3
+#==============
+lf_t3 = lf[lf$timepoint == "t3",]
+lf_t3_comp = lf_t3[-which(is.na(lf_t3$value)),]
+
+stats_un_t3 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t3 
+                            , data = lf_t3_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+# add timepoint and convert to df
+stats_un_t3$timepoint = "t3"
+stats_un_t3 = as.data.frame(stats_un_t3)
+class(stats_un_t3)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t3
+#----------------------------------------
+#n_t3 = data.frame(table(lf_t3_comp$mediator))
+n_t3_all = data.frame(table(lf_t3$mediator))
+colnames(n_t3_all) = c("mediator", "n_obs")
+n_t3_all$mediator = as.character(n_t3_all$mediator)
+
+n_t3_comp = data.frame(table(lf_t3_comp$mediator))
+colnames(n_t3_comp) = c("mediator", "n_obs_complete")
+n_t3_comp$mediator = as.character(n_t3_comp$mediator)
+
+merge_cols = intersect(names(n_t3_all), names(n_t3_comp)); merge_cols
+n_t3= merge(n_t3_all, n_t3_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t3), names(n_t3)); merging_cols
+if (all(n_t3$mediator%in%stats_un_t3$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}else{
+  nf = n_t3$mediator[!n_t3$mediator%in%stats_un_t3$mediator]
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}
+
+# add bonferroni adjustment as well
+stats_un_t3$p_adj_bonferroni = p.adjust(stats_un_t3$p, method = "bonferroni")
+
+rm(n_t3)
+rm(lf_t3_comp)
+
+########################################################################
+#==============
+# Rbind these dfs
+#==============
+str(stats_un_t1);str(stats_un_t2); str(stats_un_t3)
+
+n_dfs = 3
+
+if ( all.equal(nrow(stats_un_t1), nrow(stats_un_t2), nrow(stats_un_t3)) && 
+     all.equal(ncol(stats_un_t1), ncol(stats_un_t2), ncol(stats_un_t3)) ) {
+  expected_rows = nrow(stats_un_t1) * n_dfs
+  expected_cols = ncol(stats_un_t1)
+  print("PASS: expected_rows and cols variables generated for downstream sanity checks")
+}else{
+  cat("FAIL: dfs have different no. of rows and cols"
+      , "\nCheck harcoded value of n_dfs"
+      , "\nexpected_rows and cols could not be generated")
+  quit()
+}
+
+if ( all.equal(colnames(stats_un_t1), colnames(stats_un_t2), colnames(stats_un_t3)) ){
+  print("PASS: colnames match. Rbind the 3 dfs...")
+  combined_unpaired_stats = rbind(stats_un_t1, stats_un_t2, stats_un_t3)
+} else{
+  cat("FAIL: cannot combined dfs. Colnames don't match!")
+  quit()
+}
+
+if ( nrow(combined_unpaired_stats) == expected_rows && ncol(combined_unpaired_stats) == expected_cols ){
+  cat("PASS: combined_df has expected dimension"
+      , "\nNo. of rows in combined_df:", nrow(combined_unpaired_stats)
+      , "\nNo. of cols in combined_df:", ncol(combined_unpaired_stats) )
+}else{
+  cat("FAIL: combined_df dimension mismatch")
+  quit()
+}
+
+#######################################################################
+#=================
+# formatting df
+#=================
+# delete: unnecessary column
+combined_unpaired_stats = subset(combined_unpaired_stats, select = -c(.y.))
+
+# add sample_type
+cat("Adding sample type info as a column", my_sample_type, "...")
+combined_unpaired_stats$sample_type = my_sample_type 
+
+# add: reflect stats method correctly i.e paired or unpaired
+# incase there are NA due to LLODs, the gsub won't work!
+#combined_unpaired_stats$method = gsub("Wilcoxon", "Wilcoxon_unpaired", combined_unpaired_stats$method)
+combined_unpaired_stats$method = "wilcoxon unpaired"
+combined_unpaired_stats$method
+
+# add an extra column for padjust_signif: my_adjust_method
+combined_unpaired_stats$padjust_signif = combined_unpaired_stats$p.adj
+# add appropriate symbols for padjust_signif: my_adjust_method
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, padjust_signif = case_when(padjust_signif == 0.05 ~ "."
+                                                                                             , padjust_signif <=0.0001 ~ '****'
+                                                                                             , padjust_signif <=0.001 ~ '***'
+                                                                                             , padjust_signif <=0.01 ~ '**'
+                                                                                             , padjust_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# add an extra column for p_bon_signif
+combined_unpaired_stats$p_bon_signif = combined_unpaired_stats$p_adj_bonferroni
+# add appropriate symbols for p_bon_signif
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, p_bon_signif = case_when(p_bon_signif == 0.05 ~ "."
+                                                                                             , p_bon_signif <=0.0001 ~ '****'
+                                                                                             , p_bon_signif <=0.001 ~ '***'
+                                                                                             , p_bon_signif <=0.01 ~ '**'
+                                                                                             , p_bon_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# reorder columns
+print("preparing to reorder columns...")
+colnames(combined_unpaired_stats)
+my_col_order2 = c("mediator"
+                  , "timepoint"
+                  , "sample_type"
+                  , "n_obs"
+                  , "n_obs_complete"
+                  , "group1"
+                  , "group2"
+                  , "method"
+                  , "p"
+                  , "p.format"
+                  , "p.signif"
+                  , "p.adj"
+                  , "padjust_signif"
+                  , "p_adj_bonferroni"
+                  , "p_bon_signif")
+
+if( length(my_col_order2) == ncol(combined_unpaired_stats) && (all(my_col_order2%in%colnames(combined_unpaired_stats))) ){
+  print("PASS: Reordering columns...")
+  combined_unpaired_stats_f = combined_unpaired_stats[, my_col_order2]
+  print("Successful: column reordering")
+  print("formatted df called:'combined_unpaired_stats_f'")
+  cat('\nformatted df has the following dimensions\n')
+  print(dim(combined_unpaired_stats_f ))
+} else{
+  cat(paste0("FAIL:Cannot reorder columns, length mismatch"
+             , "\nExpected column order for: ", ncol(combined_unpaired_stats)
+             , "\nGot:", length(my_col_order2)))
+  quit()
+}  
+# assign nice column names like replace "." with "_"
+colnames(combined_unpaired_stats_f) = c("mediator"
+                                        , "timepoint" 
+                                        , "sample_type"
+                                        , "n_obs" 
+                                        , "n_obs_complete"
+                                        , "group1"
+                                        , "group2"
+                                        , "method" 
+                                        , "p" 
+                                        , "p_format"
+                                        , "p_signif"
+                                        , paste0("p_adj_fdr_", my_adjust_method)
+                                        , paste0("p_", my_adjust_method, "_signif")
+                                        , "p_adj_bonferroni"
+                                        , "p_bon_signif")
+
+colnames(combined_unpaired_stats_f)
+
+#---------------
+# quick summary
+#---------------
+# count how many meds are significant
+n_sig  = length(combined_unpaired_stats_f$mediator[combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)])
+sig_meds = combined_unpaired_stats_f[(combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)),]
+
+sig_meds$med_time = paste0(sig_meds$mediator, "@", sig_meds$timepoint)
+
+cat("\nTotal no. of statistically significant mediators in", toupper(my_sample_type)
+    , "are:", n_sig
+    , "\nThese are:", sig_meds$med_time)
+
+########################################################################
+#******************
+# write output file
+#******************
+cat("\nUNpaired stats for groups will be:", flu_stats_time_unpaired)
+write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE)
diff --git a/severe/flu_s_stats_unpaired_sam.R b/severe/flu_s_stats_unpaired_sam.R
new file mode 100755
index 0000000..e38f652
--- /dev/null
+++ b/severe/flu_s_stats_unpaired_sam.R
@@ -0,0 +1,395 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+############################################################
+# TASK: unpaired (time) analysis of mediators:
+# sample type: SAM
+# data: Flu positive adult patients
+# group: obesity
+############################################################
+my_sample_type = "sam"
+
+#=============
+# Input
+#=============
+#source("data_extraction_mediators.R")
+source("plot_data_s.R")
+
+# check: copd and asthma conflict
+table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1)
+
+#=============
+# Output
+#=============
+outfile_name = paste0("flu_stats_time_unpaired_s_", my_sample_type, ".csv")
+flu_stats_time_unpaired = paste0(outdir_stats_s, outfile_name)
+flu_stats_time_unpaired
+
+# quick checks
+table(wf_fp_sam$T1_resp_score)
+table(lf_fp_sam$mediator, lf_fp_sam$timepoint, lf_fp_sam$T1_resp_score)
+table(wf$obesity)
+
+#===============================
+# data assignment for stats
+#================================
+wf = wf_fp_sam
+lf = lf_fp_sam
+
+identical(wf, wf_fp_sam)
+identical(lf, lf_fp_sam)
+
+########################################################################
+# clear variables
+rm(lf_fp_npa, lf_fp_serum
+   , wf_fp_npa, wf_fp_serum) 
+
+# sanity checks
+table(lf$timepoint)
+length(unique(lf$mosaic))
+
+#if (table(lf$flustat) == table(sam_lf$flustat)[[2]]){
+#  cat("Analysing Flu positive patients for:", my_sample_type)
+#}else{
+#  cat("FAIL: problem with subsetting data for:", my_sample_type)
+#  quit()
+#}
+
+########################################################################
+# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis 
+# with correction
+#######################################################################
+# with adjustment: fdr and BH are identical
+my_adjust_method = "BH"
+
+#==============
+# unpaired: t1
+#==============
+lf_t1 = lf[lf$timepoint == "t1",]
+sum(is.na(lf_t1$value))
+
+foo = lf_t1[which(is.na(lf_t1$value)),]
+#ci = which(is.na(lf_t1$value))
+#lf_t1_comp = lf_t1[-ci,]
+
+lf_t1_comp = lf_t1[-which(is.na(lf_t1$value)),]
+stats_un_t1 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t1 
+                            , data = lf_t1_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+foo$mosaic[!unique(foo$mosaic)%in%unique(lf_t1_comp$mosaic)]
+
+# add timepoint and convert to df
+stats_un_t1$timepoint = "t1"
+stats_un_t1 = as.data.frame(stats_un_t1)
+class(stats_un_t1)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t1
+#----------------------------------------
+#n_t1 = data.frame(table(lf_t1_comp$mediator))
+n_t1_all = data.frame(table(lf_t1$mediator))
+colnames(n_t1_all) = c("mediator", "n_obs")
+n_t1_all$mediator = as.character(n_t1_all$mediator)
+
+n_t1_comp = data.frame(table(lf_t1_comp$mediator))
+colnames(n_t1_comp) = c("mediator", "n_obs_complete")
+n_t1_comp$mediator = as.character(n_t1_comp$mediator)
+
+merge_cols = intersect(names(n_t1_all), names(n_t1_comp)); merge_cols
+n_t1= merge(n_t1_all, n_t1_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#===================================
+merging_cols = intersect(names(stats_un_t1), names(n_t1)); merging_cols
+if (all(n_t1$mediator%in%stats_un_t1$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}else{
+  nf = n_t1$mediator[!n_t1$mediator%in%stats_un_t1$mediator]
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}
+
+# add bonferroni adjustment as well
+stats_un_t1$p_adj_bonferroni = p.adjust(stats_un_t1$p, method = "bonferroni")
+
+rm(n_t1)
+rm(lf_t1_comp)
+
+#==============
+# unpaired: t2
+#==============
+lf_t2 = lf[lf$timepoint == "t2",]
+lf_t2_comp = lf_t2[-which(is.na(lf_t2$value)),]
+                   
+stats_un_t2 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t2 
+                            , data = lf_t2_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+# add timepoint and convert to df                           
+stats_un_t2$timepoint = "t2"
+stats_un_t2 = as.data.frame(stats_un_t2)
+class(stats_un_t2)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t2
+#----------------------------------------
+#n_t2 = data.frame(table(lf_t2_comp$mediator))
+n_t2_all = data.frame(table(lf_t2$mediator))
+colnames(n_t2_all) = c("mediator", "n_obs")
+n_t2_all$mediator = as.character(n_t2_all$mediator)
+
+n_t2_comp = data.frame(table(lf_t2_comp$mediator))
+colnames(n_t2_comp) = c("mediator", "n_obs_complete")
+n_t2_comp$mediator = as.character(n_t2_comp$mediator)
+
+merge_cols = intersect(names(n_t2_all), names(n_t2_comp)); merge_cols
+n_t2= merge(n_t2_all, n_t2_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#===================================
+merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
+if (all(n_t2$mediator%in%stats_un_t2$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}else{
+  nf = n_t2$mediator[!n_t2$mediator%in%stats_un_t2$mediator]
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}
+
+# add bonferroni adjustment as well
+stats_un_t2$p_adj_bonferroni = p.adjust(stats_un_t2$p, method = "bonferroni")
+
+rm(n_t2)
+rm(lf_t2_comp)
+
+#==============
+# unpaired: t3
+#==============
+lf_t3 = lf[lf$timepoint == "t3",]
+lf_t3_comp = lf_t3[-which(is.na(lf_t3$value)),]
+
+stats_un_t3 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t3 
+                            , data = lf_t3_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+# add timepoint and convert to df                            
+stats_un_t3$timepoint = "t3"
+stats_un_t3 = as.data.frame(stats_un_t3)
+class(stats_un_t3)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t3
+#----------------------------------------
+#n_t3 = data.frame(table(lf_t3_comp$mediator))
+n_t3_all = data.frame(table(lf_t3$mediator))
+colnames(n_t3_all) = c("mediator", "n_obs")
+n_t3_all$mediator = as.character(n_t3_all$mediator)
+
+n_t3_comp = data.frame(table(lf_t3_comp$mediator))
+colnames(n_t3_comp) = c("mediator", "n_obs_complete")
+n_t3_comp$mediator = as.character(n_t3_comp$mediator)
+
+merge_cols = intersect(names(n_t3_all), names(n_t3_comp)); merge_cols
+n_t3= merge(n_t3_all, n_t3_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t3), names(n_t3)); merging_cols
+if (all(n_t3$mediator%in%stats_un_t3$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}else{
+  nf = n_t3$mediator[!n_t3$mediator%in%stats_un_t3$mediator]
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}
+
+# check: satisfied!!!!
+# FIXME: supply the col name automatically?
+wilcox.test(wf$ifna2a_sam3[wf$obesity == 1], wf$ifna2a_sam3[wf$obesity == 0])
+
+# add bonferroni adjustment as well
+stats_un_t3$p_adj_bonferroni = p.adjust(stats_un_t3$p, method = "bonferroni")
+
+rm(n_t3)
+rm(lf_t3_comp)
+########################################################################
+#=================
+# Rbind these dfs
+#=================
+str(stats_un_t1);str(stats_un_t2); str(stats_un_t3)
+
+n_dfs = 3
+
+if ( all.equal(nrow(stats_un_t1), nrow(stats_un_t2), nrow(stats_un_t3)) && 
+     all.equal(ncol(stats_un_t1), ncol(stats_un_t2), ncol(stats_un_t3)) ) {
+  expected_rows = nrow(stats_un_t1) * n_dfs
+  expected_cols = ncol(stats_un_t1)
+  print("PASS: expected_rows and cols variables generated for downstream sanity checks")
+}else{
+  cat("FAIL: dfs have different no. of rows and cols"
+      , "\nCheck harcoded value of n_dfs"
+      , "\nexpected_rows and cols could not be generated")
+  quit()
+}
+
+if ( all.equal(colnames(stats_un_t1), colnames(stats_un_t2), colnames(stats_un_t3)) ){
+  print("PASS: colnames match. Rbind the 3 dfs...")
+  combined_unpaired_stats = rbind(stats_un_t1, stats_un_t2, stats_un_t3)
+} else{
+  cat("FAIL: cannot combined dfs. Colnames don't match!")
+  quit()
+}
+
+if ( nrow(combined_unpaired_stats) == expected_rows && ncol(combined_unpaired_stats) == expected_cols ){
+  cat("PASS: combined_df has expected dimension"
+      , "\nNo. of rows in combined_df:", nrow(combined_unpaired_stats)
+      , "\nNo. of cols in combined_df:", ncol(combined_unpaired_stats) )
+}else{
+  cat("FAIL: combined_df dimension mismatch")
+  quit()
+}
+
+#######################################################################
+#=================
+# formatting df
+#=================
+# delete: unnecessary column
+combined_unpaired_stats = subset(combined_unpaired_stats, select = -c(.y.))
+
+# add sample_type
+cat("Adding sample type info as a column", my_sample_type, "...")
+combined_unpaired_stats$sample_type = my_sample_type 
+
+# add: reflect stats method correctly i.e paired or unpaired
+# incase there are NA due to LLODs, the gsub won't work!
+#combined_unpaired_stats$method = gsub("Wilcoxon", "Wilcoxon_unpaired", combined_unpaired_stats$method)
+combined_unpaired_stats$method = "wilcoxon unpaired"
+combined_unpaired_stats$method
+
+# add an extra column for padjust_signif: my_adjust_method
+combined_unpaired_stats$padjust_signif = combined_unpaired_stats$p.adj
+# add appropriate symbols for padjust_signif: my_adjust_method
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, padjust_signif = case_when(padjust_signif == 0.05 ~ "."
+                                                                                             , padjust_signif <=0.0001 ~ '****'
+                                                                                             , padjust_signif <=0.001 ~ '***'
+                                                                                             , padjust_signif <=0.01 ~ '**'
+                                                                                             , padjust_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# add an extra column for p_bon_signif
+combined_unpaired_stats$p_bon_signif = combined_unpaired_stats$p_adj_bonferroni
+# add appropriate symbols for p_bon_signif
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, p_bon_signif = case_when(p_bon_signif == 0.05 ~ "."
+                                                                                             , p_bon_signif <=0.0001 ~ '****'
+                                                                                             , p_bon_signif <=0.001 ~ '***'
+                                                                                             , p_bon_signif <=0.01 ~ '**'
+                                                                                             , p_bon_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# reorder columns
+print("preparing to reorder columns...")
+colnames(combined_unpaired_stats)
+my_col_order2 = c("mediator"
+                  , "timepoint"
+                  , "sample_type"
+                  , "n_obs"
+                  , "n_obs_complete"
+                  , "group1"
+                  , "group2"
+                  , "method"
+                  , "p"
+                  , "p.format"
+                  , "p.signif"
+                  , "p.adj"
+                  , "padjust_signif"
+                  , "p_adj_bonferroni"
+                  , "p_bon_signif")
+
+if( length(my_col_order2) == ncol(combined_unpaired_stats) && (all(my_col_order2%in%colnames(combined_unpaired_stats))) ){
+  print("PASS: Reordering columns...")
+  combined_unpaired_stats_f = combined_unpaired_stats[, my_col_order2]
+  print("Successful: column reordering")
+  print("formatted df called:'combined_unpaired_stats_f'")
+  cat('\nformatted df has the following dimensions\n')
+  print(dim(combined_unpaired_stats_f ))
+} else{
+  cat(paste0("FAIL:Cannot reorder columns, length mismatch"
+             , "\nExpected column order for: ", ncol(combined_unpaired_stats)
+             , "\nGot:", length(my_col_order2)))
+  quit()
+}  
+# assign nice column names like replace "." with "_"
+colnames(combined_unpaired_stats_f) = c("mediator"
+                                        , "timepoint" 
+                                        , "sample_type"
+                                        , "n_obs" 
+                                        , "n_obs_complete"
+                                        , "group1"
+                                        , "group2"
+                                        , "method" 
+                                        , "p" 
+                                        , "p_format"
+                                        , "p_signif"
+                                        , paste0("p_adj_fdr_", my_adjust_method)
+                                        , paste0("p_", my_adjust_method, "_signif")
+                                        , "p_adj_bonferroni"
+                                        , "p_bon_signif")
+
+colnames(combined_unpaired_stats_f)
+
+#---------------
+# quick summary
+#---------------
+# count how many meds are significant
+n_sig  = length(combined_unpaired_stats_f$mediator[combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)])
+sig_meds = combined_unpaired_stats_f[(combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)),]
+
+sig_meds$med_time = paste0(sig_meds$mediator, "@", sig_meds$timepoint)
+
+cat("\nTotal no. of statistically significant mediators in", toupper(my_sample_type)
+    , "are:", n_sig
+    , "\nThese are:", sig_meds$med_time)
+
+#######################################################################
+#******************
+# write output file
+#******************
+cat("\nUNpaired stats for groups will be:", flu_stats_time_unpaired)
+write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE)
diff --git a/severe/flu_s_stats_unpaired_serum.R b/severe/flu_s_stats_unpaired_serum.R
new file mode 100755
index 0000000..956ccb4
--- /dev/null
+++ b/severe/flu_s_stats_unpaired_serum.R
@@ -0,0 +1,376 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+############################################################
+# TASK: unpaired (time) analysis of mediators: serum
+############################################################
+my_sample_type = "serum"
+
+#=============
+# Input
+#=============
+#source("data_extraction_mediators.R")
+source("plot_data_s.R")
+
+# check: copd and asthma conflict
+table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1)
+
+#=============
+# Output
+#=============
+outfile_name = paste0("flu_stats_time_unpaired_s_", my_sample_type, ".csv")
+flu_stats_time_unpaired = paste0(outdir_stats_s, outfile_name)
+flu_stats_time_unpaired
+
+# quick checks
+table(wf_fp_npa$T1_resp_score)
+table(lf_fp_npa$mediator, lf_fp_npa$timepoint, lf_fp_npa$T1_resp_score)
+table(wf$obesity)
+
+#===============================
+# data assignment for stats
+#================================
+wf = wf_fp_serum
+lf = lf_fp_serum
+
+identical(wf, wf_fp_serum)
+identical(lf, lf_fp_serum)
+########################################################################
+# clear variables
+rm(lf_fp_sam, lf_fp_npa
+   , wf_fp_sam, wf_fp_npa) 
+########################################################################
+# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis
+# with correction
+#######################################################################
+# with adjustment: fdr and BH are identical
+my_adjust_method = "BH"
+
+#==============
+# unpaired: t1
+#==============
+lf_t1 = lf[lf$timepoint == "t1",]
+sum(is.na(lf_t1$value))
+
+foo = lf_t1[which(is.na(lf_t1$value)),]
+ci = which(is.na(lf_t1$value))
+#lf_t1_comp = lf_t1[-ci,]
+
+lf_t1_comp = lf_t1[-which(is.na(lf_t1$value)),]
+stats_un_t1 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t1 
+                            , data = lf_t1_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+foo$mosaic[!unique(foo$mosaic)%in%unique(lf_t1_comp$mosaic)]
+
+# add timepoint and convert to df
+stats_un_t1$timepoint = "t1"
+stats_un_t1 = as.data.frame(stats_un_t1)
+class(stats_un_t1)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t1
+#----------------------------------------
+#n_t1 = data.frame(table(lf_t1_comp$mediator))
+n_t1_all = data.frame(table(lf_t1$mediator))
+colnames(n_t1_all) = c("mediator", "n_obs")
+n_t1_all$mediator = as.character(n_t1_all$mediator)
+
+n_t1_comp = data.frame(table(lf_t1_comp$mediator))
+colnames(n_t1_comp) = c("mediator", "n_obs_complete")
+n_t1_comp$mediator = as.character(n_t1_comp$mediator)
+
+merge_cols = intersect(names(n_t1_all), names(n_t1_comp)); merge_cols
+n_t1= merge(n_t1_all, n_t1_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t1), names(n_t1)); merging_cols
+if (all(n_t1$mediator%in%stats_un_t1$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}else{
+  nf = n_t1$mediator[!n_t1$mediator%in%stats_un_t1$mediator]
+  stats_un_t1 = merge(stats_un_t1, n_t1, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t1)
+      , "\nncol:", ncol(stats_un_t1))
+}
+
+# add bonferroni adjustment as well
+stats_un_t1$p_adj_bonferroni = p.adjust(stats_un_t1$p, method = "bonferroni")
+
+rm(n_t1)
+rm(lf_t1_comp)
+
+#==============
+# unpaired: t2
+#==============
+lf_t2 = lf[lf$timepoint == "t2",]
+lf_t2_comp = lf_t2[-which(is.na(lf_t2$value)),]
+                   
+stats_un_t2 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t2 
+                            , data = lf_t2_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+# add timepoint and convert to df
+stats_un_t2$timepoint = "t2"
+stats_un_t2 = as.data.frame(stats_un_t2)
+class(stats_un_t2)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t2
+#----------------------------------------
+#n_t2 = data.frame(table(lf_t2_comp$mediator))
+n_t2_all = data.frame(table(lf_t2$mediator))
+colnames(n_t2_all) = c("mediator", "n_obs")
+n_t2_all$mediator = as.character(n_t2_all$mediator)
+
+n_t2_comp = data.frame(table(lf_t2_comp$mediator))
+colnames(n_t2_comp) = c("mediator", "n_obs_complete")
+n_t2_comp$mediator = as.character(n_t2_comp$mediator)
+
+merge_cols = intersect(names(n_t2_all), names(n_t2_comp)); merge_cols
+n_t2= merge(n_t2_all, n_t2_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
+if (all(n_t2$mediator%in%stats_un_t2$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}else{
+  nf = n_t2$mediator[!n_t2$mediator%in%stats_un_t2$mediator]
+  stats_un_t2 = merge(stats_un_t2, n_t2, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t2)
+      , "\nncol:", ncol(stats_un_t2))
+}
+
+# add bonferroni adjustment as well
+stats_un_t2$p_adj_bonferroni = p.adjust(stats_un_t2$p, method = "bonferroni")
+
+rm(n_t2)
+rm(lf_t2_comp)
+
+#==============
+# unpaired: t3
+#==============
+lf_t3 = lf[lf$timepoint == "t3",]
+lf_t3_comp = lf_t3[-which(is.na(lf_t3$value)),]
+
+stats_un_t3 = compare_means(value~obesity
+                            , group.by = "mediator"
+                            #, data = lf_t3 
+                            , data = lf_t3_comp
+                            , paired = FALSE
+                            , p.adjust.method = my_adjust_method)
+
+# add timepoint and convert to df
+stats_un_t3$timepoint = "t3"
+stats_un_t3 = as.data.frame(stats_un_t3)
+class(stats_un_t3)
+
+#----------------------------------------
+# calculate n_obs for each mediator: t3
+#----------------------------------------
+#n_t3 = data.frame(table(lf_t3_comp$mediator))
+n_t3_all = data.frame(table(lf_t3$mediator))
+colnames(n_t3_all) = c("mediator", "n_obs")
+n_t3_all$mediator = as.character(n_t3_all$mediator)
+
+n_t3_comp = data.frame(table(lf_t3_comp$mediator))
+colnames(n_t3_comp) = c("mediator", "n_obs_complete")
+n_t3_comp$mediator = as.character(n_t3_comp$mediator)
+
+merge_cols = intersect(names(n_t3_all), names(n_t3_comp)); merge_cols
+n_t3 = merge(n_t3_all, n_t3_comp, by = merge_cols, all = T)
+
+#==================================
+# Merge: merge stats + n_obs df
+#==================================
+merging_cols = intersect(names(stats_un_t3), names(n_t3)); merging_cols
+if (all(n_t3$mediator%in%stats_un_t3$mediator)) {
+  cat("PASS: merging stats and n_obs on column/s:", merging_cols)
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all = T)
+  cat("\nsuccessfull merge:"
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}else{
+  nf = n_t3$mediator[!n_t3$mediator%in%stats_un_t3$mediator]
+  stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T)
+  cat("\nMerged with caution:"
+      , "\nnrows mismatch:", nf
+      , "not found in stats possibly due to all obs being LLODs"
+      , "\nintroduced NAs for:", nf
+      , "\nnrow:", nrow(stats_un_t3)
+      , "\nncol:", ncol(stats_un_t3))
+}
+
+# add bonferroni adjustment as well
+stats_un_t3$p_adj_bonferroni = p.adjust(stats_un_t3$p, method = "bonferroni")
+
+rm(n_t3)
+rm(lf_t3_comp)
+########################################################################
+#==============
+# Rbind these dfs
+#==============
+str(stats_un_t1);str(stats_un_t2); str(stats_un_t3)
+
+n_dfs = 3
+
+if ( all.equal(nrow(stats_un_t1), nrow(stats_un_t2), nrow(stats_un_t3)) && 
+     all.equal(ncol(stats_un_t1), ncol(stats_un_t2), ncol(stats_un_t3)) ) {
+  expected_rows = nrow(stats_un_t1) * n_dfs
+  expected_cols = ncol(stats_un_t1)
+  print("PASS: expected_rows and cols variables generated for downstream sanity checks")
+}else{
+  cat("FAIL: dfs have different no. of rows and cols"
+      , "\nCheck harcoded value of n_dfs"
+      , "\nexpected_rows and cols could not be generated")
+  quit()
+}
+
+if ( all.equal(colnames(stats_un_t1), colnames(stats_un_t2), colnames(stats_un_t3)) ){
+  print("PASS: colnames match. Rbind the 3 dfs...")
+  combined_unpaired_stats = rbind(stats_un_t1, stats_un_t2, stats_un_t3)
+} else{
+  cat("FAIL: cannot combined dfs. Colnames don't match!")
+  quit()
+} 
+
+if ( nrow(combined_unpaired_stats) == expected_rows && ncol(combined_unpaired_stats) == expected_cols ){
+  cat("PASS: combined_df has expected dimension"
+      , "\nNo. of rows in combined_df:", nrow(combined_unpaired_stats)
+      , "\nNo. of cols in combined_df:", ncol(combined_unpaired_stats) )
+}else{
+  cat("FAIL: combined_df dimension mismatch")
+  quit()
+}
+
+#######################################################################
+#=================
+# formatting df
+#=================
+# delete: unnecessary column
+combined_unpaired_stats = subset(combined_unpaired_stats, select = -c(.y.))
+
+# add sample_type
+cat("Adding sample type info as a column", my_sample_type, "...")
+combined_unpaired_stats$sample_type = my_sample_type
+
+# add: reflect stats method correctly i.e paired or unpaired
+# incase there are NA due to LLODs, the gsub won't work!
+#combined_unpaired_stats$method = gsub("Wilcoxon", "Wilcoxon_unpaired", combined_unpaired_stats$method)
+combined_unpaired_stats$method = "wilcoxon unpaired"
+combined_unpaired_stats$method
+
+# add an extra column for padjust_signif: my_adjust_method
+combined_unpaired_stats$padjust_signif = combined_unpaired_stats$p.adj
+# add appropriate symbols for padjust_signif: my_adjust_method
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, padjust_signif = case_when(padjust_signif == 0.05 ~ "."
+                                                                                             , padjust_signif <=0.0001 ~ '****'
+                                                                                             , padjust_signif <=0.001 ~ '***'
+                                                                                             , padjust_signif <=0.01 ~ '**'
+                                                                                             , padjust_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# add an extra column for p_bon_signif
+combined_unpaired_stats$p_bon_signif = combined_unpaired_stats$p_adj_bonferroni
+# add appropriate symbols for p_bon_signif
+combined_unpaired_stats  = dplyr::mutate(combined_unpaired_stats, p_bon_signif = case_when(p_bon_signif == 0.05 ~ "."
+                                                                                             , p_bon_signif <=0.0001 ~ '****'
+                                                                                             , p_bon_signif <=0.001 ~ '***'
+                                                                                             , p_bon_signif <=0.01 ~ '**'
+                                                                                             , p_bon_signif <0.05 ~ '*'
+                                                                                             , TRUE ~ 'ns'))
+# reorder columns
+print("preparing to reorder columns...")
+colnames(combined_unpaired_stats)
+my_col_order2 = c("mediator"
+                  , "timepoint"
+                  , "sample_type"
+                  , "n_obs"
+                  , "n_obs_complete"
+                  , "group1"
+                  , "group2"
+                  , "method"
+                  , "p"
+                  , "p.format"
+                  , "p.signif"
+                  , "p.adj"
+                  , "padjust_signif"
+                  , "p_adj_bonferroni"
+                  , "p_bon_signif")
+
+if( length(my_col_order2) == ncol(combined_unpaired_stats) && (all(my_col_order2%in%colnames(combined_unpaired_stats))) ){
+  print("PASS: Reordering columns...")
+  combined_unpaired_stats_f = combined_unpaired_stats[, my_col_order2]
+  print("Successful: column reordering")
+  print("formatted df called:'combined_unpaired_stats_f'")
+  cat('\nformatted df has the following dimensions\n')
+  print(dim(combined_unpaired_stats_f ))
+} else{
+  cat(paste0("FAIL:Cannot reorder columns, length mismatch"
+             , "\nExpected column order for: ", ncol(combined_unpaired_stats)
+             , "\nGot:", length(my_col_order2)))
+  quit()
+}  
+# assign nice column names like replace "." with "_"
+colnames(combined_unpaired_stats_f) = c("mediator"
+                                        , "timepoint" 
+                                        , "sample_type"
+                                        , "n_obs" 
+                                        , "n_obs_complete"
+                                        , "group1"
+                                        , "group2"
+                                        , "method" 
+                                        , "p" 
+                                        , "p_format"
+                                        , "p_signif"
+                                        , paste0("p_adj_fdr_", my_adjust_method)
+                                        , paste0("p_", my_adjust_method, "_signif")
+                                        , "p_adj_bonferroni"
+                                        , "p_bon_signif")
+
+colnames(combined_unpaired_stats_f)
+
+#---------------
+# quick summary
+#---------------
+# count how many meds are significant
+n_sig  = length(combined_unpaired_stats_f$mediator[combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)])
+sig_meds = combined_unpaired_stats_f[(combined_unpaired_stats_f$p_signif<0.05 & !is.na(combined_unpaired_stats_f$p_signif<0.05)),]
+
+sig_meds$med_time = paste0(sig_meds$mediator, "@", sig_meds$timepoint)
+
+cat("\nTotal no. of statistically significant mediators in", toupper(my_sample_type)
+    , "are:", n_sig
+    , "\nThese are:", sig_meds$med_time)
+
+########################################################################
+#******************
+# write output file
+#******************
+cat("UNpaired stats for groups will be:", flu_stats_time_unpaired)
+write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE)
\ No newline at end of file