340 lines
13 KiB
R
Executable file
340 lines
13 KiB
R
Executable file
#!/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_formatting.R")
|
|
|
|
# check: adult variable and age variable discrepancy!
|
|
metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18]
|
|
|
|
#=============
|
|
# Output
|
|
#=============
|
|
outfile_name = paste0("flu_stats_time_unpaired_", my_sample_type, ".csv")
|
|
flu_stats_time_unpaired = paste0(outdir_stats, outfile_name)
|
|
|
|
#===============================
|
|
# data assignment for stats
|
|
#================================
|
|
wf = npa_wf[npa_wf$flustat == 1,]
|
|
lf = npa_lf[npa_lf$flustat == 1,]
|
|
lf$timepoint = paste0("t", lf$timepoint)
|
|
|
|
########################################################################
|
|
# clear variables
|
|
rm(sam_lf, sam_wf
|
|
, serum_lf, serum_wf)
|
|
rm(colnames_sam_df, expected_rows_sam_lf
|
|
, colnames_serum_df, expected_rows_serum_lf)
|
|
|
|
rm(pivot_cols)
|
|
|
|
# sanity checks
|
|
table(lf$timepoint)
|
|
|
|
if (table(lf$flustat) == table(npa_lf$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$timepoint = "t1"
|
|
stats_un_t1 = as.data.frame(stats_un_t1)
|
|
class(stats_un_t1)
|
|
|
|
# calculate n_obs for each mediator
|
|
n_t1 = data.frame(table(lf_t1_comp$mediator))
|
|
colnames(n_t1) = c("mediator", "n_obs")
|
|
n_t1$mediator = as.character(n_t1$mediator)
|
|
|
|
#==================================
|
|
# Merge: 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
|
|
n_t2 = data.frame(table(lf_t2_comp$mediator))
|
|
colnames(n_t2) = c("mediator", "n_obs")
|
|
n_t2$mediator = as.character(n_t2$mediator)
|
|
|
|
#==================================
|
|
# Merge: merge stats + n_obs df
|
|
#==================================
|
|
merging_cols = intersect(names(stats_un_t2), names(n_t2)); merging_cols
|
|
if (all(n_t2$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$timepoint = "t3"
|
|
stats_un_t3 = as.data.frame(stats_un_t3)
|
|
class(stats_un_t3)
|
|
|
|
# calculate n_obs for each mediator
|
|
n_t3 = data.frame(table(lf_t3_comp$mediator))
|
|
colnames(n_t3) = c("mediator", "n_obs")
|
|
n_t3$mediator = as.character(n_t3$mediator)
|
|
|
|
#==================================
|
|
# Merge: 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"
|
|
, "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"
|
|
, "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)
|
|
########################################################################
|
|
#******************
|
|
# 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)
|