tidy scripts and using age as criteria for adults

flu_stats_unpaired_sam.R

@@ -3,45 +3,54 @@ getwd()
 setwd("~/git/mosaic_2020/")
 getwd()
 ############################################################
-# TASK: unpaired (time) analysis of mediators: SAM
+# TASK: unpaired (time) analysis of mediators:
+# sample type: SAM
+# data: Flu positive adult patients
+# group: obesity
 ############################################################
+my_sample_type = "sam"
+
 #=============
 # Input
 #=============
 source("data_extraction_formatting.R")
 
-table(metadata_all$flustat[metadata_all$adult == 1])
+# check: adult variable and age variable discrepancy!
+metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18]
 
-# clear variables
-rm(npa_adults_lf, npa_df_adults_clean
-, serum_adults_lf, serum_df_adults_clean) 
-rm(colnames_npa_df, expected_rows_npa_lf
-, colnames_serum_df, expected_rows_serum_lf) 
-
-rm(pivot_cols)
-
-my_sample_type = "sam"
 #=============
 # Output: unpaired analysis of time for sam
 #=============
 outfile_name = paste0("flu_stats_time_unpaired_", my_sample_type, ".csv")
 flu_stats_time_unpaired = paste0(outdir_stats, outfile_name)
 
-#%%========================================================
+#===============================
 # data assignment for stats
-wf = sam_df_adults_clean[sam_df_adults_clean$flustat == 1,]
-lf = sam_adults_lf[sam_adults_lf$flustat == 1,]
- #%%========================================================
+#================================
+wf = sam_wf[sam_wf$flustat == 1,]
+lf = sam_lf[sam_lf$flustat == 1,]
+lf$timepoint = paste0("t", lf$timepoint)
+########################################################################
+# clear variables
+rm(npa_lf, npa_wf
+, serum_lf, serum_wf) 
+rm(colnames_npa_df, expected_rows_npa_lf
+, colnames_serum_df, expected_rows_serum_lf) 
+
+rm(pivot_cols)
+
+# sanity checks
 table(lf$timepoint)
 length(unique(lf$mosaic))
 lf$timepoint = paste0("t", lf$timepoint)
 
-if (table(lf$flustat) == table(sam_adults_lf$flustat)[[2]]){
+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
@@ -55,10 +64,10 @@ my_adjust_method = "BH"
 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))
-
+#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"
@@ -69,8 +78,8 @@ stats_un_t1 = compare_means(value~obesity
 
 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)
 
@@ -79,7 +88,9 @@ n_t1 = data.frame(table(lf_t1_comp$mediator))
 colnames(n_t1) = c("mediator", "n_obs")
 n_t1$mediator = as.character(n_t1$mediator)
 
-# merge stats + n_obs df
+#==================================
+# 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)
@@ -116,8 +127,8 @@ stats_un_t2 = compare_means(value~obesity
                             , 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)
 
@@ -126,7 +137,9 @@ n_t2 = data.frame(table(lf_t2_comp$mediator))
 colnames(n_t2) = c("mediator", "n_obs")
 n_t2$mediator = as.character(n_t2$mediator)
 
-# merge stats + n_obs df
+#==================================
+# 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)
@@ -163,9 +176,8 @@ stats_un_t3 = compare_means(value~obesity
                             , 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)
 
@@ -174,7 +186,9 @@ n_t3 = data.frame(table(lf_t3_comp$mediator))
 colnames(n_t3) = c("mediator", "n_obs")
 n_t3$mediator = as.character(n_t3$mediator)
 
-# merge stats + n_obs df
+#==================================
+# 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)
@@ -202,10 +216,10 @@ 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
@@ -322,6 +336,7 @@ colnames(combined_unpaired_stats_f) = c("mediator"
                                         , "p_bon_signif")
 
 colnames(combined_unpaired_stats_f)
+#######################################################################
 #******************
 # write output file
 #******************