From 37f8cd619eb46a06c104f891048506b43cc2c326 Mon Sep 17 00:00:00 2001 From: Tanushree Tunstall Date: Fri, 27 Nov 2020 18:22:00 +0000 Subject: [PATCH] added stats for non_severe flu stats in resp dir --- non_severe/flu_ns_stats_unpaired_npa.R | 395 ++++++++++++++++++++++ non_severe/flu_ns_stats_unpaired_sam.R | 397 +++++++++++++++++++++++ non_severe/flu_ns_stats_unpaired_serum.R | 392 ++++++++++++++++++++++ 3 files changed, 1184 insertions(+) create mode 100755 non_severe/flu_ns_stats_unpaired_npa.R create mode 100755 non_severe/flu_ns_stats_unpaired_sam.R create mode 100755 non_severe/flu_ns_stats_unpaired_serum.R diff --git a/non_severe/flu_ns_stats_unpaired_npa.R b/non_severe/flu_ns_stats_unpaired_npa.R new file mode 100755 index 0000000..7535923 --- /dev/null +++ b/non_severe/flu_ns_stats_unpaired_npa.R @@ -0,0 +1,395 @@ +#!/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") + +# 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_ns_", my_sample_type, ".csv") +flu_stats_time_unpaired = paste0(outdir_stats_ns, outfile_name) +flu_stats_time_unpaired + +# quick checks +table(npa_wf$T1_resp_score) +table(npa_lf$mediator, npa_lf$timepoint, npa_lf$T1_resp_score) +table(npa_lf$T1_resp_score!=3) + +#=============================== +# Data assignment for stats: fp, non_severe patients +#================================ +wf = npa_wf[npa_wf$T1_resp_score != 3,] +lf = npa_lf[npa_lf$T1_resp_score != 3,] +lf$timepoint = paste0("t", lf$timepoint) +lf = lf[!lf$mediator == "vitd",] + +######################################################################## +# 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$timepoint) +length(unique(lf$mosaic)) + +#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$timepoint = "t1" +stats_un_t1 = as.data.frame(stats_un_t1) +class(stats_un_t1) + +#---------------------------------------- +# calculate n_obs for each mediator: t1 +#---------------------------------------- +#n_t1 = data.frame(table(lf_t1_comp$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$med_time) + +######################################################################## +#****************** +# write output file +#****************** +cat("\nUNpaired stats for groups will be:", flu_stats_time_unpaired) +write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired, row.names = FALSE) diff --git a/non_severe/flu_ns_stats_unpaired_sam.R b/non_severe/flu_ns_stats_unpaired_sam.R new file mode 100755 index 0000000..902ea9f --- /dev/null +++ b/non_severe/flu_ns_stats_unpaired_sam.R @@ -0,0 +1,397 @@ +#!/usr/bin/Rscript +getwd() +setwd("~/git/mosaic_2020/") +getwd() +############################################################ +# TASK: unpaired (time) analysis of mediators: +# sample type: SAM +# data: Flu positive adult patients +# group: obesity +############################################################ +my_sample_type = "sam" + +#============= +# Input +#============= +source("data_extraction_mediators.R") + +# check: copd and asthma conflict +table(fp_adults_ics$ia_exac_copd==1 & fp_adults_ics$asthma == 1) + +#============= +# Output +#============= +outfile_name = paste0("flu_stats_time_unpaired_ns_", my_sample_type, ".csv") +flu_stats_time_unpaired = paste0(outdir_stats_ns, outfile_name) +flu_stats_time_unpaired + +# quick checks +table(sam_wf$T1_resp_score) +table(sam_lf$mediator, sam_lf$timepoint, sam_lf$T1_resp_score) +table(sam_lf$T1_resp_score!=3) + +#=============================== +# Data assignment for stats: fp, non_severe patients +#================================ +wf = sam_wf[sam_wf$T1_resp_score != 3,] +lf = sam_lf[sam_lf$T1_resp_score != 3,] +lf$timepoint = paste0("t", lf$timepoint) +lf = lf[!lf$mediator == "vitd",] + +######################################################################## +# clear variables +rm(npa_lf, npa_wf +, serum_lf, serum_wf) +rm(colnames_npa_df, expected_rows_npa_lf +, colnames_serum_df, expected_rows_serum_lf) + +rm(pivot_cols) + +# sanity checks +table(lf$timepoint) +length(unique(lf$mosaic)) + +#if (table(lf$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/non_severe/flu_ns_stats_unpaired_serum.R b/non_severe/flu_ns_stats_unpaired_serum.R new file mode 100755 index 0000000..a9dd416 --- /dev/null +++ b/non_severe/flu_ns_stats_unpaired_serum.R @@ -0,0 +1,392 @@ +#!/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") + +# 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_ns_", my_sample_type, ".csv") +flu_stats_time_unpaired = paste0(outdir_stats_ns, outfile_name) +flu_stats_time_unpaired + +# quick checks +table(serum_wf$T1_resp_score) +table(serum_lf$mediator,serum_lf$timepoint, serum_lf$T1_resp_score) +table(serum_lf$T1_resp_score!=3) + +#=============================== +# data assignment for stats +#================================ +wf = serum_wf[serum_wf$T1_resp_score != 3,] +lf = serum_lf[serum_lf$T1_resp_score != 3,] +lf$timepoint = paste0("t", lf$timepoint) + +######################################################################## +# clear variables +rm(sam_lf, sam_wf +, npa_lf, npa_wf) +rm(colnames_sam_df, expected_rows_sam_lf +, colnames_npa_df, expected_rows_npa_lf) + +rm(pivot_cols) + +# sanity checks +table(lf$timepoint) + +if (table(lf$flustat) == table(serum_lf$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$mediator] + stats_un_t3 = merge(stats_un_t3, n_t3, by = merging_cols, all.y = T) + cat("\nMerged with caution:" + , "\nnrows mismatch:", nf + , "not found in stats possibly due to all obs being LLODs" + , "\nintroduced NAs for:", nf + , "\nnrow:", nrow(stats_un_t3) + , "\nncol:", ncol(stats_un_t3)) +} + +# add bonferroni adjustment as well +stats_un_t3$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) + + +