diff --git a/boxplot_linear_na.R b/boxplot_linear_na.R deleted file mode 100644 index 12f883e..0000000 --- a/boxplot_linear_na.R +++ /dev/null @@ -1,166 +0,0 @@ -#!/usr/bin/Rscript -getwd() -setwd("~/git/mosaic_2020/") -getwd() -############################################################ -# TASK: boxplots at T1 -# FIXME: currently not rendering, problem with NAs for stats? -############################################################ -my_samples = "npa_sam_serum" -#============= -# Input -#============= -#source("data_extraction_formatting_non_asthmatics.R") -source("plot_data_na.R") - -# check: adult variable and age variable discrepancy! -metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18] - -#============= -# Output: -#============= -outfile_bp = paste0("boxplots_linear_NA_", my_samples, ".pdf") -output_boxplot = paste0(outdir_plots, outfile_bp); output_boxplot - -#=============================== -# data assignment for plots -#================================ -#----------- -# npa -#----------- -##wf_fp_npa = npa_wf[npa_wf$flustat == 1,] -#lf_fp_npa = npa_lf[npa_lf$flustat == 1,] -#lf_fp_npa$timepoint = paste0("t", lf_fp_npa$timepoint) -#lf_fp_npa$timepoint = as.factor(lf_fp_npa$timepoint) -#lf_fp_npa$obesity = as.factor(lf_fp_npa$obesity) - -#table(lf_fp_npa$mediator) -#head(lf_fp_npa$value[lf_fp_npa$mediator == "vitd"]) -#lf_fp_npa = lf_fp_npa[!lf_fp_npa$mediator == "vitd",] - -#----------- -# sam -#----------- -##wf_fp_sam = samm_wf[samm_wf$flustat == 1,] -#lf_fp_sam = sam_lf[sam_lf$flustat == 1,] -#lf_fp_sam$timepoint = paste0("t", lf_fp_sam$timepoint) -#lf_fp_sam$timepoint = as.factor(lf_fp_sam$timepoint) -#lf_fp_sam$obesity = as.factor(lf_fp_sam$obesity) - -#table(lf_fp_sam$mediator) -#head(lf_fp_sam$value[lf_fp_sam$mediator == "vitd"]) -#lf_fp_sam = lf_fp_sam[!lf_fp_sam$mediator == "vitd",] - -#----------- -# serum -#----------- -##wf_fp_serum = serum_wf[serum_wf$flustat == 1,] -#lf_fp_serum = serum_lf[serum_lf$flustat == 1,] -#lf_fp_serum$timepoint = paste0("t", lf_fp_serum$timepoint) -#lf_fp_serum$timepoint = as.factor(lf_fp_serum$timepoint) -#lf_fp_serum$obesity = as.factor(lf_fp_serum$obesity) - -######################################################################## -cat("Output plots will be in:", output_boxplot) -pdf(output_boxplot, width = 20, height = 15) - -#======================================================================= -# NPA -#======================================================================= -if (is.factor(lf_fp_npa$timepoint) && is.factor(lf_fp_npa$timepoint)){ - cat ("PASS: required groups are factors") -} -#------------------------------------------ -title_npa_linear = "NPA (Linear)" -#----------------------------------------- -bxp_npa_linear <- ggboxplot(lf_fp_npa, x = "timepoint", y = "value", - color = "obesity", palette = c("#00BFC4", "#F8766D")) + - facet_wrap(~mediator, nrow = 7, ncol = 5, scales = "free_y", shrink = T)+ - #scale_y_log10() + - theme(axis.text.x = element_text(size = 15) - , axis.text.y = element_text(size = 15 - , angle = 0 - , hjust = 1 - , vjust = 0) - , axis.title.x = element_text(size = 15) - , axis.title.y = element_text(size = 15) - , plot.title = element_text(size = 20, hjust = 0.5) - , strip.text.x = element_text(size = 15, colour = "black") - , legend.title = element_text(color = "black", size = 20) - , legend.text = element_text(size = 15) - , legend.direction = "horizontal") + - labs(title = title_npa_linear - , x = "" - , y = "Levels") - -bxp_npa_linear - -#======================================================================= -# SAM -#======================================================================= -if (is.factor(lf_fp_sam$timepoint) && is.factor(lf_fp_sam$timepoint)){ - cat ("PASS: required groups are factors") -} - -#------------------------------------------ -title_sam_linear = "SAM (Linear)" -#----------------------------------------- -bxp_sam_linear <- ggboxplot(lf_fp_sam, x = "timepoint", y = "value", - color = "obesity", palette = c("#00BFC4", "#F8766D")) + - facet_wrap(~mediator, nrow = 7, ncol = 5, scales = "free_y", shrink = T)+ - #scale_y_log10() + - theme(axis.text.x = element_text(size = 15) - , axis.text.y = element_text(size = 15 - , angle = 0 - , hjust = 1 - , vjust = 0) - , axis.title.x = element_text(size = 15) - , axis.title.y = element_text(size = 15) - , plot.title = element_text(size = 20, hjust = 0.5) - , strip.text.x = element_text(size = 15, colour = "black") - , legend.title = element_text(color = "black", size = 20) - , legend.text = element_text(size = 15) - , legend.direction = "horizontal") + - labs(title = title_sam_linear - , x = "" - , y = "Levels") - -bxp_sam_linear - -#======================================================================= -# SERUM -#======================================================================= -if (is.factor(lf_fp_serum$timepoint) && is.factor(lf_fp_serum$timepoint)){ - cat ("PASS: required groups are factors") -} - -table(lf_fp_serum$mediator) - -#------------------------------------------ -title_serum_linear = "SERUM (Linear)" -#----------------------------------------- -bxp_serum_linear <- ggboxplot(lf_fp_serum, x = "timepoint", y = "value", - color = "obesity", palette = c("#00BFC4", "#F8766D")) + - facet_wrap(~mediator, nrow = 7, ncol = 5, scales = "free_y", shrink = T)+ - #scale_y_log10() + - theme(axis.text.x = element_text(size = 15) - , axis.text.y = element_text(size = 15 - , angle = 0 - , hjust = 1 - , vjust = 0) - , axis.title.x = element_text(size = 15) - , axis.title.y = element_text(size = 15) - , plot.title = element_text(size = 20, hjust = 0.5) - , strip.text.x = element_text(size = 15, colour = "black") - , legend.title = element_text(color = "black", size = 20) - , legend.text = element_text(size = 15) - , legend.direction = "horizontal") + - labs(title = title_serum_linear - , x = "" - , y = "Levels") - -bxp_serum_linear - -#========================================================================== -dev.off() -############################################################################ diff --git a/boxplot_log_na.R b/boxplot_log_na.R deleted file mode 100755 index 7eff01c..0000000 --- a/boxplot_log_na.R +++ /dev/null @@ -1,170 +0,0 @@ -#!/usr/bin/Rscript -getwd() -setwd("~/git/mosaic_2020/") -getwd() -############################################################ -# TASK: boxplots at T1 -# FIXME: currently not rendering, problem with NAs for stats? -############################################################ -my_samples = "npa_sam_serum" -#============= -# Input -#============= -#source("data_extraction_formatting_non_asthmatics.R") -source("plot_data_na.R") - -# check: adult variable and age variable discrepancy! -metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18] - -#============= -# Output: -#============= -outfile_bp_log = paste0("boxplots_log_NA_", my_samples, ".pdf") -output_boxplot_log = paste0(outdir_plots, outfile_bp_log); output_boxplot_log - -#=============================== -# data assignment for plots -#================================ -#----------- -# npa -#----------- -#wf_fp_npa = npa_wf[npa_wf$flustat == 1,] -lf_fp_npa = npa_lf[npa_lf$flustat == 1,] -lf_fp_npa$timepoint = paste0("t", lf_fp_npa$timepoint) -lf_fp_npa$timepoint = as.factor(lf_fp_npa$timepoint) -lf_fp_npa$obesity = as.factor(lf_fp_npa$obesity) - -table(lf_fp_npa$mediator) -head(lf_fp_npa$value[lf_fp_npa$mediator == "vitd"]) -lf_fp_npa = lf_fp_npa[!lf_fp_npa$mediator == "vitd",] - -#----------- -# sam -#----------- -#wf_fp_sam = samm_wf[samm_wf$flustat == 1,] -lf_fp_sam = sam_lf[sam_lf$flustat == 1,] -lf_fp_sam$timepoint = paste0("t", lf_fp_sam$timepoint) -lf_fp_sam$timepoint = as.factor(lf_fp_sam$timepoint) -lf_fp_sam$obesity = as.factor(lf_fp_sam$obesity) - -table(lf_fp_sam$mediator) -head(lf_fp_sam$value[lf_fp_sam$mediator == "vitd"]) -lf_fp_sam = lf_fp_sam[!lf_fp_sam$mediator == "vitd",] - -#----------- -# serum -#----------- -#wf_fp_serum = serum_wf[serum_wf$flustat == 1,] -lf_fp_serum = serum_lf[serum_lf$flustat == 1,] -lf_fp_serum$timepoint = paste0("t", lf_fp_serum$timepoint) -lf_fp_serum$timepoint = as.factor(lf_fp_serum$timepoint) -lf_fp_serum$obesity = as.factor(lf_fp_serum$obesity) - -######################################################################## -cat("Output plots will be in:", output_boxplot_log) -pdf(output_boxplot_log, width = 20, height = 15) - -#======================================================================= -# NPA -#======================================================================= -if (is.factor(lf_fp_npa$timepoint) && is.factor(lf_fp_npa$timepoint)){ - cat ("PASS: required groups are factors") -} - -#------------------------------------ -title_npa_log = "NPA (Log)" -#----------------------------------- - -bxp_npa_log <- ggboxplot(lf_fp_npa, x = "timepoint", y = "value", - color = "obesity", palette = c("#00BFC4", "#F8766D")) + - facet_wrap(~mediator, nrow = 7, ncol = 5, scales = "free_y", shrink = F)+ - scale_y_log10() + - theme(axis.text.x = element_text(size = 15) - , axis.text.y = element_text(size = 15 - , angle = 0 - , hjust = 1 - , vjust = 0) - , axis.title.x = element_text(size = 15) - , axis.title.y = element_text(size = 15) - , plot.title = element_text(size = 20, hjust = 0.5) - , strip.text.x = element_text(size = 15, colour = "black") - , legend.title = element_text(color = "black", size = 20) - , legend.text = element_text(size = 15) - , legend.direction = "horizontal") + - labs(title = title_npa_log - , x = "" - , y = "Levels (Log)") - -bxp_npa_log - -#======================================================================= -# SAM -#======================================================================= -if (is.factor(lf_fp_sam$timepoint) && is.factor(lf_fp_sam$timepoint)){ - cat ("PASS: required groups are factors") -} - -#------------------------------------ -title_sam_log = "SAM (Log)" -#----------------------------------- - -bxp_sam_log <- ggboxplot(lf_fp_sam, x = "timepoint", y = "value", - color = "obesity", palette = c("#00BFC4", "#F8766D")) + - facet_wrap(~mediator, nrow = 7, ncol = 5, scales = "free_y", shrink = T)+ - scale_y_log10() + - theme(axis.text.x = element_text(size = 15) - , axis.text.y = element_text(size = 15 - , angle = 0 - , hjust = 1 - , vjust = 0) - , axis.title.x = element_text(size = 15) - , axis.title.y = element_text(size = 15) - , plot.title = element_text(size = 20, hjust = 0.5) - , strip.text.x = element_text(size = 15, colour = "black") - , legend.title = element_text(color = "black", size = 20) - , legend.text = element_text(size = 15) - , legend.direction = "horizontal") + - labs(title = title_sam_log - , x = "" - , y = "Levels (Log)") - -bxp_sam_log - -#======================================================================= -# SERUM -#======================================================================= -if (is.factor(lf_fp_serum$timepoint) && is.factor(lf_fp_serum$timepoint)){ - cat ("PASS: required groups are factors") -} - -table(lf_fp_serum$mediator) - -#------------------------------------ -title_serum_log = "SERUM (Log)" -#----------------------------------- - -bxp_serum_log <- ggboxplot(lf_fp_serum, x = "timepoint", y = "value", - color = "obesity", palette = c("#00BFC4", "#F8766D")) + - facet_wrap(~mediator, nrow = 7, ncol = 5, scales = "free_y", shrink = T)+ - scale_y_log10() + - theme(axis.text.x = element_text(size = 15) - , axis.text.y = element_text(size = 15 - , angle = 0 - , hjust = 1 - , vjust = 0) - , axis.title.x = element_text(size = 15) - , axis.title.y = element_text(size = 15) - , plot.title = element_text(size = 20, hjust = 0.5) - , strip.text.x = element_text(size = 15, colour = "black") - , legend.title = element_text(color = "black", size = 20) - , legend.text = element_text(size = 15) - , legend.direction = "horizontal") + - labs(title = title_serum_log - , x = "" - , y = "Levels (Log)") - -bxp_serum_log - -#========================================================================== -dev.off() -############################################################################ diff --git a/colnames_clinical_meds.R b/colnames_clinical_meds.R index d809174..c8b7b14 100755 --- a/colnames_clinical_meds.R +++ b/colnames_clinical_meds.R @@ -6,18 +6,28 @@ getwd() # TASK: Extract relevant columns from mosaic fp adults data for regression # clinical and sig meds ######################################################################## + ######################################################################## -clinical_cols_data = c("mosaic" - , "ia_exac_copd" - , "death" - #, "obese2" #inc peaeds, but once you subset data for adults, its the same! - , "obesity" - , "flustat" +# meta data columns +meta_data_cols = c("mosaic" + , "gender" + , "age" + , "adult" + , "flustat" + , "type" + #, "obese2" #inc peaeds, but once you subset data for adults, its the same! + #, "height", "height_unit" + #, "weight", "weight_unit" + #, "ia_height_ftin", "ia_height_m", "ia_weight" + #, "visual_est_bmi", "bmi_rating" + , "obesity") + +clinical_cols = c("death" , "sfluv" , "h1n1v" - , "age" - , "gender" + , "ia_exac_copd" + , "onset_2_t1" , "asthma" , "vl_pfu_ul_npa1" , "los" @@ -36,13 +46,13 @@ clinical_cols_data = c("mosaic" , "inresp_sev" , "steroid") -clinical_cols_added = c("age_bins" - , "o2_sat_bin" - , "onset_initial_bin" - , "steroid_ics" - , "t1_resp_recoded" ) +#clinical_cols_added = c("age_bins" +# , "o2_sat_bin" +# , "onset_initial_bin" +# , "steroid_ics" +# , "t1_resp_recoded") -clinical_cols = c(clinical_cols_data, clinical_cols_added) +meta_clinical_cols = c(meta_data_cols, clinical_cols) sig_npa_cols = c("eotaxin_npa1" , "eotaxin3_npa1" @@ -83,15 +93,15 @@ sig_npa_cols = c("eotaxin_npa1" , "tnfr2_npa2" , "tnfr2_npa3") -cols_to_extract = c(clinical_cols, sig_npa_cols) +#cols_to_extract = c(clinical_cols, sig_npa_cols, clinical_cols_added) -if ( length(cols_to_extract) == length(clinical_cols) + length(sig_npa_cols) ){ - cat("PASS: length match" - , "\nTotal no. of cols to extract for regression:", length(cols_to_extract) - , "\nNo. of clinical cols:", length(clinical_cols) - , "\nNo. of sig npa cols: ", length(sig_npa_cols)) -}else{ - cat("FAIL: length mismatch" - , "\nAborting!") - quit() -} +#if ( length(cols_to_extract) == length(clinical_cols) + length(sig_npa_cols) + length(clinical_cols_added) ){ +# cat("PASS: length match" +# , "\nTotal no. of cols to extract for regression:", length(cols_to_extract) +# , "\nNo. of clinical cols:", length(clinical_cols) +# , "\nNo. of sig npa cols: ", length(sig_npa_cols)) +#}else{ +# cat("FAIL: length mismatch" +# , "\nAborting!") +# quit() +#} diff --git a/data_extraction_formatting_clinical.R b/data_extraction_formatting_clinical.R index b0b9753..dc95ff2 100755 --- a/data_extraction_formatting_clinical.R +++ b/data_extraction_formatting_clinical.R @@ -33,9 +33,9 @@ table(fp_adults$ia_exac_copd==1 & fp_adults$asthma == 1) ######################################################################## # Clinical_data extraction ######################################################################## -#cat("\nExtracting:", length(clinical_cols), "cols from fp_adults") +#cat("\nExtracting:", length(meta_clinical_cols), "cols from fp_adults") -#clinical_df = fp_adults[, clinical_cols] +#clinical_df = fp_adults[, meta_clinical_cols] # sanity checks #if ( sum(table(clinical_df$obesity)) & sum(table(clinical_df$age>=18)) & sum(table(clinical_df$death)) & sum(table(clinical_df$asthma)) == nrow(clinical_df) ){ @@ -56,24 +56,8 @@ table(fp_adults$ia_exac_copd==1 & fp_adults$asthma == 1) if ( table(fp_adults$ia_exac_copd, fp_adults$asthma) [[2,2]] == 0){ cat("PASS: asthma and copd do not conflict") }else{ - cat("Conflict detected in asthm and copd filed, attempting to resolve...") - # Reassign the copd and asthma status and do some checks - table(fp_adults$ia_exac_copd); sum(is.na(fp_adults$ia_exac_copd)) - fp_adults$ia_exac_copd[fp_adults$ia_exac_copd< 1]<- 0 - fp_adults$ia_exac_copd[is.na(fp_adults$ia_exac_copd)] <- 0 - table(fp_adults$ia_exac_copd); sum(is.na(fp_adults$ia_exac_copd)) - - # check copd and asthma status - table(fp_adults$ia_exac_copd, fp_adults$asthma) - check_copd_and_asthma_1<- subset(fp_adults, ia_exac_copd ==1 & asthma == 1) # check this is 3 - - # reassign these 3 so these are treated as non-asthmatics as copd with asthma is NOT TRUE asthma - fp_adults$asthma[fp_adults$ia_exac_copd == 1 & fp_adults$asthma == 1]= 0 - table(fp_adults$ia_exac_copd, fp_adults$asthma) - foo<- subset(fp_adults, asthma==1 & ia_exac_copd ==1) # check that its 0 - rm(check_copd_and_asthma_1, foo) - cat("Check status again...") - + cat("Conflict detected in asthma and copd filed. Check script: read_data.R") + quit() } #===================================================================== #================================= @@ -391,10 +375,37 @@ table(fp_adults_ics$steroid_ics) #str(fp_adults_ics) #========================= -# remove cols +# clinical_df only #========================= +clinical_df_ics = fp_adults_ics[, c(meta_clinical_cols, "steroid_ics")] -fp_adults_ics = subset(fp_adults_ics, select = -c(onset_2_initial)) +#========================= +# FIXME: decide! remove cols +#========================= +#fp_adults_ics = subset(fp_adults_ics, select = -c(onset_2_initial)) + +#========================= +# fp_adults_ics: without asthma +#========================= +#fp_adults_ics_na = fp_adults_ics[fp_adults_ics$asthma == 0,] + +#========================= +# fp_adults_ics: without severity 3 +#========================= +#table(fp_adults_ics$T1_resp_score) +#table(fp_adults_ics$T1_resp_score!=3)# + +#fp_adults_ics_ns = fp_adults_ics[fp_adults_ics$T1_resp_score!=3,] +#table(fp_adults_ics_ns$T1_resp_score) + +#========================= +# cols_added +#========================= +clinical_cols_added = c("age_bins" + , "o2_sat_bin" + , "onset_initial_bin" + , "steroid_ics" + , "t1_resp_recoded") #====================== # writing output file @@ -405,20 +416,13 @@ outfile_reg = paste0(outdir, outfile_name_reg) cat("\nWriting clinical file for regression:", outfile_reg) #write.csv(fp_adults_ics, file = outfile_reg) -#========================= -# fp_adults_ics: without asthma -#========================= -fp_adults_ics_na = fp_adults_ics[fp_adults_ics$asthma == 0,] - - -#========================= -# clinical_df only -#========================= -clinical_df_ics = fp_adults[, clinical_cols] ################################################################ rm(age_bins, max_age_interval, max_in, min_in + , min_age, min_age_interval , o2_sat_bin, onset_initial_bin, tot_o2 , n_text_code, n1, n2, tot_onset2ini, infile_ics - , tot_onset2ini, meta_data_cols , fp_adults, clinical_ics) ################################################################ + + + diff --git a/data_extraction_formatting_non_asthmatics.R b/data_extraction_formatting_non_asthmatics.R deleted file mode 100755 index b977b38..0000000 --- a/data_extraction_formatting_non_asthmatics.R +++ /dev/null @@ -1,357 +0,0 @@ -#!/usr/bin/Rscript -getwd() -setwd('~/git/mosaic_2020/') -getwd() -######################################################################## -# TASK: Extract relevant columns from mosaic adults data -# sam -# serum -# npa -######################################################################## -#==================== -# Input: source data -#==================== -source("read_data.R") - -#============================ -# Data to use: Important step -#============================ -# select df to use -my_data = fp_adults_na - -# clear unnecessary variables -rm(all_df, adult_df, fp_adults) - -######################################################################## -if ( sum(table(my_data$asthma)) && sum(table(my_data$asthma, my_data$ia_exac_copd)) && sum(table(my_data$obesity)) == nrow(my_data) ){ - cat("PASS: fp adults WITHOUT asthma extracted sucessfully") -}else{ - cat("FAIL: numbers mismatch. Please check") - quit() -} - -#========= -# sam -#========= -sam_regex = regex(".*_sam[1-3]{1}$", ignore_case = T) -sam_cols_i = str_extract(colnames(my_data), sam_regex) # not boolean -#sam_cols_b = colnames(my_data)%in%sam_cols_i # boolean - -sam_cols = colnames(my_data)[colnames(my_data)%in%sam_cols_i] -sam_cols - -# this contains log columns + daysamp_samXX: omitting these -sam_regex_log_days = regex("log|day.*_sam[1-3]{1}$", ignore_case = T, perl = T) -sam_cols_to_omit = sam_cols[grepl(sam_regex_log_days, sam_cols)]; sam_cols_to_omit -sam_cols_to_omit - -sam_cols_clean = sam_cols[!sam_cols%in%sam_cols_to_omit]; sam_cols_clean -length(sam_cols_clean) - -if( length(sam_cols_clean) == length(sam_cols) - length(sam_cols_to_omit) ){ - cat("PASS: clean cols extracted" - , "\nNo. of clean SAM cols to extract:", length(sam_cols_clean)) -}else{ - cat("FAIL: length mismatch. Aborting further cols extraction" - , "Expected length:", length(sam_cols) - length(sam_cols_to_omit) - , "Got:", length(sam_cols_clean) ) -} - -sam_cols_to_extract = c(meta_data_cols, sam_cols_clean) - -cat("Extracting SAM cols + metadata_cols") - -if ( length(sam_cols_to_extract) == length(meta_data_cols) + length(sam_cols_clean) ){ - cat("Extracing", length(sam_cols_to_extract), "columns for sam") - sam_df = my_data[, sam_cols_to_extract] -}else{ - cat("FAIL: length mismatch" - , "Expeceted to extract:", length(meta_data_cols) + length(sam_cols_clean), "columns" - , "Got:", length(sam_cols_to_extract)) -} - -colnames_sam_df = colnames(sam_df); colnames_sam_df - -#========= -# serum -#========= -serum_regex = regex(".*_serum[1-3]{1}$", ignore_case = T) -serum_cols_i = str_extract(colnames(my_data), serum_regex) # not boolean -#serum_cols_b = colnames(my_data)%in%serum_cols_i # boolean - -serum_cols = colnames(my_data)[colnames(my_data)%in%serum_cols_i] - -# this contains log columns + dayserump_serumXX: omitting these -serum_regex_log_days = regex("log|day.*_serum[1-3]{1}$", ignore_case = T, perl = T) -serum_cols_to_omit = serum_cols[grepl(serum_regex_log_days, serum_cols)]; serum_cols_to_omit - -serum_cols_clean = serum_cols[!serum_cols%in%serum_cols_to_omit]; serum_cols_clean -length(serum_cols_clean) - -if( length(serum_cols_clean) == length(serum_cols) - length(serum_cols_to_omit) ){ - cat("PASS: clean cols extracted" - , "\nNo. of clean serum cols to extract:", length(serum_cols_clean)) -}else{ - cat("FAIL: length mismatch. Aborting further cols extraction" - , "Expected length:", length(serum_cols) - length(serum_cols_to_omit) - , "Got:", length(serum_cols_clean) ) -} - -serum_cols_to_extract = c(meta_data_cols, serum_cols_clean) - -cat("Extracting SERUM cols + metadata_cols") - -if ( length(serum_cols_to_extract) == length(meta_data_cols) + length(serum_cols_clean) ){ - cat("Extracing", length(serum_cols_to_extract), "columns for serum") - serum_df = my_data[, serum_cols_to_extract] -}else{ - cat("FAIL: length mismatch" - , "Expeceted to extract:", length(meta_data_cols) + length(serum_cols_clean), "columns" - , "Got:", length(serum_cols_to_extract)) -} - -colnames_serum_df = colnames(serum_df); colnames_serum_df - -#========= -# npa -#========= -npa_regex = regex(".*_npa[1-3]{1}$", ignore_case = T) -npa_cols_i = str_extract(colnames(my_data), npa_regex) # not boolean -#npa_cols_b = colnames(my_data)%in%npa_cols_i # boolean - -npa_cols = colnames(my_data)[colnames(my_data)%in%npa_cols_i] - -# this contains log columns + daynpap_npaXX: omitting these -npa_regex_log_days = regex("log|day|vl_samptime|ct.*_npa[1-3]{1}$", ignore_case = T, perl = T) -npa_cols_to_omit = npa_cols[grepl(npa_regex_log_days, npa_cols)]; npa_cols_to_omit - -npa_cols_clean = npa_cols[!npa_cols%in%npa_cols_to_omit]; npa_cols_clean -length(npa_cols_clean) - -if( length(npa_cols_clean) == length(npa_cols) - length(npa_cols_to_omit) ){ - cat("PASS: clean cols extracted" - , "\nNo. of clean npa cols to extract:", length(npa_cols_clean)) -}else{ - cat("FAIL: length mismatch. Aborting further cols extraction" - , "Expected length:", length(npa_cols) - length(npa_cols_to_omit) - , "Got:", length(npa_cols_clean) ) -} - -npa_cols_to_extract = c(meta_data_cols, npa_cols_clean) - -cat("Extracting NPA cols + metadata_cols") - -if ( length(npa_cols_to_extract) == length(meta_data_cols) + length(npa_cols_clean) ){ - cat("Extracing", length(npa_cols_to_extract), "columns for npa") - npa_df = my_data[, npa_cols_to_extract] -}else{ - cat("FAIL: length mismatch" - , "Expeceted to extract:", length(meta_data_cols) + length(npa_cols_clean), "columns" - , "Got:", length(npa_cols_to_extract)) -} - -colnames_npa_df = colnames(npa_df); colnames_npa_df - -#============== -# quick checks -#============== -colnames_check = as.data.frame(cbind(colnames_sam_df, colnames_serum_df, colnames_npa_df)) -tail(colnames_check) # gives a warning message due to differing no. of rows for cbind! - -# put NA where a match doesn't exist -# unmatched lengths -#colnames_check[117,1] <- NA -#colnames_check[117,2] <- NA - -if ( ncol(sam_df) == ncol(serum_df) ){ - start = ncol(sam_df)+1 - extra_cols = start:ncol(npa_df) -} - -colnames_check_f = colnames_check -tail(colnames_check_f) - -for (i in extra_cols){ - for (j in 1:2) { - cat("\ni:", i - ,"\nj:", j) - colnames_check_f[i,j] <- NA - #colnames_check_f[i, j]< - NA - - } -} -tail(colnames_check_f) - -########################################################################## -# LF data -########################################################################## -cols_to_omit = c("adult" - #, "obese2" - #, "height", "height_unit", "weight" - #, "weight_unit", "visual_est_bmi", "bmi_rating" - ) - -pivot_cols = meta_data_cols -# subselect pivot_cols -pivot_cols = meta_data_cols[!meta_data_cols%in%cols_to_omit];pivot_cols -ncols_omitted = table(meta_data_cols%in%cols_to_omit)[[2]] -ncols_omitted - -#============== -# lf data: sam -#============== -str(sam_df) -table(sam_df$obesity) -#table(sam_df$obese2) - -#sam_df_adults = sam_df[sam_df$adult == 1,] # resolved at source and only dealing wit age as adult -sam_df_adults = sam_df - -wf_cols = colnames(sam_df_adults)[!colnames(sam_df_adults)%in%cols_to_omit] -sam_wf = sam_df_adults[wf_cols] - -if (length(pivot_cols) == length(meta_data_cols) - ncols_omitted){ - cat("PASS: pivot cols successfully extracted") -}else{ - cat("FAIL: length mismatch! pivot cols could not be extracted" - , "\nExpected length:", length(meta_data_cols) - ncols_omitted - , "\nGot:",length(pivot_cols) ) - quit() -} - -expected_rows_sam_lf = nrow(sam_wf) * (length(sam_wf) - length(pivot_cols)); expected_rows_sam_lf - -# using regex: -sam_lf = sam_wf %>% - tidyr::pivot_longer(-all_of(pivot_cols) - , names_to = c("mediator", "sample_type", "timepoint") - , names_pattern = "(.*)_(.*)([1-3]{1})" - , values_to = "value") - -if ( - (nrow(sam_lf) == expected_rows_sam_lf) & (sum(table(is.na(sam_lf$mediator))) == expected_rows_sam_lf) - ) { - cat(paste0("PASS: long format data has correct no. of rows and NA in mediator:" - , "\nNo. of rows: ", nrow(sam_lf) - , "\nNo. of cols: ", ncol(sam_lf))) -} else{ - cat(paste0("FAIL:long format data has unexpected no. of rows or NAs in mediator" - , "\nExpected no. of rows: ", expected_rows_sam_lf - , "\nGot: ", nrow(sam_lf) - , "\ncheck expected rows calculation!")) - quit() -} - -#library(data.table) -#foo = sam_df_adults[1:10] -#long <- melt(setDT(sam_df_adults), id.vars = pivot_cols, variable.name = "levels") - -#============== -# lf data: serum -#============== -str(serum_df) -table(serum_df$obesity) -#table(serum_df$obese2) - -#serum_df_adults = serum_df[serum_df$adult == 1,] # extract based on age -serum_df_adults = serum_df - -wf_cols = colnames(serum_df_adults)[!colnames(serum_df_adults)%in%cols_to_omit] -serum_wf = serum_df_adults[wf_cols] - -if (length(pivot_cols) == length(meta_data_cols) - ncols_omitted){ - cat("PASS: pivot cols successfully extracted") -}else{ - cat("FAIL: length mismatch! pivot cols could not be extracted" - , "\nExpected length:", length(meta_data_cols) - ncols_omitted - , "\nGot:",length(pivot_cols) ) - quit() -} - -expected_rows_serum_lf = nrow(serum_wf) * (length(serum_wf) - length(pivot_cols)); expected_rows_serum_lf - -# using regex: -serum_lf = serum_wf %>% - tidyr::pivot_longer(-all_of(pivot_cols) - , names_to = c("mediator", "sample_type", "timepoint") - , names_pattern = "(.*)_(.*)([1-3]{1})" - , values_to = "value") - -if ( - (nrow(serum_lf) == expected_rows_serum_lf) & (sum(table(is.na(serum_lf$mediator))) == expected_rows_serum_lf) -) { - cat(paste0("PASS: long format data has correct no. of rows and NA in mediator:" - , "\nNo. of rows: ", nrow(serum_lf) - , "\nNo. of cols: ", ncol(serum_lf))) -} else{ - cat(paste0("FAIL:long format data has unexpected no. of rows or NAs in mediator" - , "\nExpected no. of rows: ", expected_rows_serum_lf - , "\nGot: ", nrow(serum_lf) - , "\ncheck expected rows calculation!")) - quit() -} - -#============== -# lf data: npa -#============== -str(npa_df) -table(npa_df$obesity) -#table(npa_df$obese2) - -#npa_df_adults = npa_df[npa_df$adult == 1,] # extract based on age -npa_df_adults = npa_df - -wf_cols = colnames(npa_df_adults)[!colnames(npa_df_adults)%in%cols_to_omit] -npa_wf = npa_df_adults[wf_cols] - -if (length(pivot_cols) == length(meta_data_cols) - ncols_omitted){ - cat("PASS: pivot cols successfully extracted") -}else{ - cat("FAIL: length mismatch! pivot cols could not be extracted" - , "\nExpected length:", length(meta_data_cols) - ncols_omitted - , "\nGot:",length(pivot_cols) ) - quit() -} - -expected_rows_npa_lf = nrow(npa_wf) * (length(npa_wf) - length(pivot_cols)); expected_rows_npa_lf - -# using regex: -npa_lf = npa_wf %>% - tidyr::pivot_longer(-all_of(pivot_cols) - , names_to = c("mediator", "sample_type", "timepoint") - , names_pattern = "(.*)_(.*)([1-3]{1})" - , values_to = "value") - -if ( - (nrow(npa_lf) == expected_rows_npa_lf) & (sum(table(is.na(npa_lf$mediator))) == expected_rows_npa_lf) -) { - cat(paste0("PASS: long format data has correct no. of rows and NA in mediator:" - , "\nNo. of rows: ", nrow(npa_lf) - , "\nNo. of cols: ", ncol(npa_lf))) -} else{ - cat(paste0("FAIL:long format data has unexpected no. of rows or NAs in mediator" - , "\nExpected no. of rows: ", expected_rows_npa_lf - , "\nGot: ", nrow(npa_lf) - , "\ncheck expected rows calculation!")) - quit() -} - -############################################################################### -# remove unnecessary variables -rm(sam_regex, sam_regex_log_days, sam_cols, sam_cols_clean, sam_cols_i, sam_cols_to_extract, sam_cols_to_omit) -rm(serum_regex, serum_regex_log_days, serum_cols, serum_cols_clean, serum_cols_i, serum_cols_to_extract, serum_cols_to_omit) -rm(npa_regex, npa_regex_log_days, npa_cols, npa_cols_clean, npa_cols_i, npa_cols_to_extract, npa_cols_to_omit) -rm(my_data) -rm(colnames_check) -rm(i, j - #, expected_cols - , start, wf_cols, extra_cols, cols_to_omit) - -# rm not_clean dfs -rm(sam_df_adults, serum_df_adults, npa_df_adults) - -# rm df -rm(sam_df, serum_df, npa_df) -rm(colnames_check_f - #, fp_adults_na) -) diff --git a/data_extraction_formatting.R b/data_extraction_mediators.R similarity index 99% rename from data_extraction_formatting.R rename to data_extraction_mediators.R index ad6a4e3..f8c24b8 100755 --- a/data_extraction_formatting.R +++ b/data_extraction_mediators.R @@ -11,16 +11,17 @@ getwd() #==================== # Input: source data #==================== -source("read_data.R") +#source("read_data.R") +source("data_extraction_formatting_clinical.R") #============================ # Data to use: Important step #============================ # select df to use -my_data = fp_adults +my_data = fp_adults_ics # clear unnecessary variables -rm(all_df, adult_df, fp_adults_na) +rm(clinical_df_ics) ######################################################################## @@ -184,6 +185,7 @@ cols_to_omit = c("adult" ) pivot_cols = meta_data_cols + # subselect pivot_cols pivot_cols = meta_data_cols[!meta_data_cols%in%cols_to_omit];pivot_cols ncols_omitted = table(meta_data_cols%in%cols_to_omit)[[2]] @@ -202,6 +204,7 @@ wf_cols = colnames(sam_df_adults)[!colnames(sam_df_adults)%in%cols_to_omit] sam_wf = sam_df_adults[wf_cols] pivot_cols = meta_data_cols + # subselect pivot_cols pivot_cols = meta_data_cols[!meta_data_cols%in%cols_to_omit];pivot_cols diff --git a/flu_stats_unpaired_na_npa.R b/flu_stats_unpaired_na_npa.R deleted file mode 100755 index 3f5d3de..0000000 --- a/flu_stats_unpaired_na_npa.R +++ /dev/null @@ -1,381 +0,0 @@ -#!/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_non_asthmatics.R") - -# check: adult variable and age variable discrepancy! -metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18] - -#============= -# Output -#============= -outfile_name = paste0("flu_stats_time_unpaired_NA_", my_sample_type, ".csv") -flu_stats_time_unpaired_na = paste0(outdir_stats, outfile_name) - -#=============================== -# data assignment for stats -#================================ -wf = npa_wf[npa_wf$flustat == 1,] -lf = npa_lf[npa_lf$flustat == 1,] -lf$timepoint = paste0("t", lf$timepoint) -lf = lf[!lf$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$timepoint) - -######################################################################## -# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis -# with correction -######################################################################## -# with adjustment: fdr and BH are identical -my_adjust_method = "BH" - -#============== -# unpaired: t1 -#============== -lf_t1 = lf[lf$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_na) -#write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired_na, row.names = FALSE) diff --git a/flu_stats_unpaired_na_sam.R b/flu_stats_unpaired_na_sam.R deleted file mode 100755 index b90ac0d..0000000 --- a/flu_stats_unpaired_na_sam.R +++ /dev/null @@ -1,383 +0,0 @@ -#!/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_formatting_non_asthmatics.R") - -# check: adult variable and age variable discrepancy! -metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18] - -#============= -# Output -#============= -outfile_name = paste0("flu_stats_time_unpaired_NA_", my_sample_type, ".csv") -flu_stats_time_unpaired_na = paste0(outdir_stats, outfile_name) - -#=============================== -# data assignment for stats -#================================ -wf = sam_wf[sam_wf$flustat == 1,] -lf = sam_lf[sam_lf$flustat == 1,] -lf$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)) - -######################################################################## -# 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$med_time) - -####################################################################### -#****************** -# write output file -#****************** -cat("\nUNpaired stats for groups will be:", flu_stats_time_unpaired_na) -#write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired_na, row.names = FALSE) diff --git a/flu_stats_unpaired_na_serum.R b/flu_stats_unpaired_na_serum.R deleted file mode 100755 index 97649c3..0000000 --- a/flu_stats_unpaired_na_serum.R +++ /dev/null @@ -1,376 +0,0 @@ -#!/usr/bin/Rscript -getwd() -setwd("~/git/mosaic_2020/") -getwd() -############################################################ -# TASK: unpaired (time) analysis of mediators: serum -############################################################ -my_sample_type = "serum" - -#============= -# Input -#============= -source("data_extraction_formatting_non_asthmatics.R") - -# check: adult variable and age variable discrepancy! -metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18] - -#============= -# Output -#============= -outfile_name = paste0("flu_stats_time_unpaired_NA_", my_sample_type, ".csv") -flu_stats_time_unpaired_na = paste0(outdir_stats, outfile_name) - -#=============================== -# data assignment for stats -#================================ -wf = serum_wf[serum_wf$flustat == 1,] -lf = serum_lf[serum_lf$flustat == 1,] -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$timepoint) - -######################################################################## -# Unpaired stats at each timepoint b/w groups: wilcoxon UNpaired analysis -# with correction -####################################################################### -# with adjustment: fdr and BH are identical -my_adjust_method = "BH" - -#============== -# unpaired: t1 -#============== -lf_t1 = lf[lf$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_na) -#write.csv(combined_unpaired_stats_f, flu_stats_time_unpaired_na, row.names = FALSE) diff --git a/plot_data_na.R b/plot_data_na.R deleted file mode 100755 index 34640a9..0000000 --- a/plot_data_na.R +++ /dev/null @@ -1,60 +0,0 @@ -#!/usr/bin/Rscript -getwd() -setwd("~/git/mosaic_2020/") -getwd() -############################################################ -# TASK: boxplots at T1 -# FIXME: currently not rendering, problem with NAs for stats? -############################################################ - -#============= -# Input -#============= -source("data_extraction_formatting_non_asthmatics.R") - -# check: adult variable and age variable discrepancy! -metadata_all$mosaic[metadata_all$adult==1 & metadata_all$age<=18] - -#=============================== -# data assignment for plots -#================================ -#----------- -# npa -#----------- -wf_fp_npa = npa_wf[npa_wf$flustat == 1,] -lf_fp_npa = npa_lf[npa_lf$flustat == 1,] -lf_fp_npa$timepoint = paste0("t", lf_fp_npa$timepoint) -lf_fp_npa$timepoint = as.factor(lf_fp_npa$timepoint) -lf_fp_npa$obesity = as.factor(lf_fp_npa$obesity) - -table(lf_fp_npa$mediator) -head(lf_fp_npa$value[lf_fp_npa$mediator == "vitd"]) -lf_fp_npa = lf_fp_npa[!lf_fp_npa$mediator == "vitd",] -table(lf_fp_npa$mediator) - -#----------- -# sam -#----------- -wf_fp_sam = sam_wf[sam_wf$flustat == 1,] -lf_fp_sam = sam_lf[sam_lf$flustat == 1,] -lf_fp_sam$timepoint = paste0("t", lf_fp_sam$timepoint) -lf_fp_sam$timepoint = as.factor(lf_fp_sam$timepoint) -lf_fp_sam$obesity = as.factor(lf_fp_sam$obesity) - -table(lf_fp_sam$mediator) -head(lf_fp_sam$value[lf_fp_sam$mediator == "vitd"]) -lf_fp_sam = lf_fp_sam[!lf_fp_sam$mediator == "vitd",] -table(lf_fp_sam$mediator) - -#----------- -# serum -#----------- -wf_fp_serum = serum_wf[serum_wf$flustat == 1,] -lf_fp_serum = serum_lf[serum_lf$flustat == 1,] -lf_fp_serum$timepoint = paste0("t", lf_fp_serum$timepoint) -lf_fp_serum$timepoint = as.factor(lf_fp_serum$timepoint) -lf_fp_serum$obesity = as.factor(lf_fp_serum$obesity) - -head(lf_fp_sam$value[lf_fp_serum$mediator == "vitd"]) -######################################################################## - diff --git a/read_data.R b/read_data.R index 19c8292..c6be2f3 100755 --- a/read_data.R +++ b/read_data.R @@ -7,6 +7,8 @@ getwd() ######################################################################## # load libraries, packages and local imports source("Header_TT.R") +source("colnames_clinical_meds.R") + ######################################################################## maindir = "~/git/mosaic_2020/" outdir = paste0(maindir, "output/") @@ -15,6 +17,12 @@ ifelse(!dir.exists(outdir), dir.create(outdir), FALSE) outdir_stats = paste0(maindir, "output/stats/") ifelse(!dir.exists(outdir_stats), dir.create(outdir_stats), FALSE) +outdir_stats_na = paste0(maindir, "output/stats/non_asthmatics/") +ifelse(!dir.exists(outdir_stats_na), dir.create(outdir_stats_na), FALSE) + +outdir_stats_ns = paste0(maindir, "output/stats/non_severe/") +ifelse(!dir.exists(outdir_stats_ns), dir.create(outdir_stats_ns), FALSE) + outdir_plots = paste0(maindir, "output/plots/") ifelse(!dir.exists(outdir_plots), dir.create(outdir_plots), FALSE) ######################################################################## @@ -26,22 +34,22 @@ all_df <- read.csv("/home/backup/MOSAIC/MEDIATOR_Data/master_file/Mosaic_master_ , fileEncoding = 'latin1') # meta data columns -meta_data_cols = c("mosaic", "gender", "age" - , "adult" - , "flustat", "type" - , "obesity" +#meta_data_cols = c("mosaic", "gender", "age" +# , "adult" +# , "flustat", "type" +# , "obesity" #, "obese2" #, "height", "height_unit" #, "weight", "weight_unit" #, "ia_height_ftin", "ia_height_m", "ia_weight" #, "visual_est_bmi", "bmi_rating" - ) +# ) # check if these columns to select are present in the data -meta_data_cols%in%colnames(all_df) -all(meta_data_cols%in%colnames(all_df)) - -metadata_all = all_df[, meta_data_cols] +meta_clinical_cols%in%colnames(all_df) +if ( all(meta_clinical_cols%in%colnames(all_df)) ){ + metadata_all = all_df[, meta_clinical_cols] +} #============== # adult patients