157 lines
No EOL
5.2 KiB
R
157 lines
No EOL
5.2 KiB
R
df = read.csv("/home/backup/MOSAIC/MEDIATOR_Data/master_file/Mosaic_master_file_from_stata.csv"
|
|
, fileEncoding = "latin1"
|
|
, sep = ",")
|
|
|
|
install.packages("readr")
|
|
library(readr)
|
|
df2 = read_csv("/home/backup/MOSAIC/MEDIATOR_Data/master_file/Mosaic_master_file_from_stata.csv"
|
|
, col_names = T)
|
|
foo = as.data.frame(colnames(df2))
|
|
head(foo)
|
|
head(df2)
|
|
|
|
|
|
# sam
|
|
sam_df = read.csv("/home/backup/MOSAIC/MEDIATOR_Data/mediator_data_analysis/SAM-oct-2015/SAM_adults_publication/SAM_only.csv"
|
|
, fileEncoding = "latin1")
|
|
|
|
|
|
|
|
# extract the 36 HC
|
|
# master file for HC: called "Mediators_for_HC.csv" in /home/tanu/MASTERS/Birkbeck/MSc_Project/MOSAIC/MEDIATOR_Data/master_file
|
|
all_healthy<- read.csv(file.choose())
|
|
|
|
serum_hc<- subset(all_healthy, Timepoint == "HC" & Sample == "Serum")
|
|
length(unique(serum_hc$MOSAIC)) # check:36
|
|
|
|
#=====================
|
|
# File for patients(comprehensive): called "Mosaic_master_file_from_stata.csv"
|
|
all_df <- read.csv("/home/pub/Work/MOSAIC/MOSAIC_from_work/MASTER/MOSAIC_2015_MASTER_Aki_stata_20150721/Mosaic_master_file_from_stata.csv"
|
|
, fileEncoding='latin1') # as there is some weird encoding problems!
|
|
|
|
|
|
meta_data_cols = c("mosaic", "gender", "age", "adult", "flustat", "type"
|
|
, "obesity", "obese2", "height", "height_unit", "weight"
|
|
, "weight_unit", "visual_est_bmi", "bmi_rating")
|
|
|
|
|
|
|
|
# check if these columns to select are present in the data
|
|
meta_data_cols%in%colnames(all_df)
|
|
all(meta_data_cols%in%colnames(all_df))
|
|
metadata_all = all_df[, meta_data_cols]
|
|
|
|
|
|
sam = all_df[, grepl("_sam1", colnames(all_df))]
|
|
|
|
|
|
# use regex
|
|
library(stringr)
|
|
|
|
|
|
|
|
|
|
serum_regex = regex(".*_serum[1-3]{1}$", ignore_case = T)
|
|
npa_regex = regex(".*_npa[1-3]{1}$", ignore_case = T)
|
|
|
|
#=========
|
|
# sam
|
|
#=========
|
|
sam_regex = regex(".*_sam[1-3]{1}$", ignore_case = T)
|
|
sam_cols_i = str_extract(colnames(all_df), sam_regex) # not boolean
|
|
sam_cols_b = colnames(all_df)%in%sam_cols_i # boolean
|
|
|
|
sam_cols = colnames(all_df)[colnames(all_df)%in%sam_cols_i]
|
|
|
|
# this contains log columns as well as daysamp_samXX
|
|
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_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 cols to extract", length(sam_cols_clean))
|
|
|
|
}
|
|
|
|
sam_cols_to_extract = c(meta_data_cols, sam_cols_clean)
|
|
|
|
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 = all_df[, 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_cols_i = str_extract(colnames(all_df), serum_regex)
|
|
table(colnames(all_df)%in%serum_cols_i)
|
|
serum_cols = colnames(all_df)[colnames(all_df)%in%serum_cols_i]
|
|
|
|
serum_cols_to_extract = c(meta_data_cols, serum_cols)
|
|
|
|
if ( length(serum_cols_to_extract) == length(meta_data_cols) + length(serum_cols) ){
|
|
cat("Extracing", length(serum_cols_to_extract), "columns for serum")
|
|
serum_df = all_df[, serum_cols_to_extract]
|
|
}else{
|
|
cat("FAIL: length mismatch"
|
|
, "Expeceted to extract:", length(meta_data_cols) + length(serum_cols), "columns"
|
|
, "Got:", length(serum_cols_to_extract))
|
|
}
|
|
|
|
#=========
|
|
# npa
|
|
#=========
|
|
npa_cols_i= str_extract(colnames(all_df), npa_regex)
|
|
table(colnames(all_df)%in%npa_cols_i)
|
|
npa_cols = colnames(all_df)[colnames(all_df)%in%npa_cols_i]
|
|
|
|
npa_cols_to_extract = c(meta_data_cols, npa_cols)
|
|
|
|
if ( length(npa_cols_to_extract) == length(meta_data_cols) + length(npa_cols) ){
|
|
cat("Extracing", length(npa_cols_to_extract), "columns for NPA")
|
|
npa_df = all_df[, npa_cols_to_extract]
|
|
}else{
|
|
cat("FAIL: length mismatch"
|
|
, "Expeceted to extract:", length(meta_data_cols) + length(npa_cols), "columns"
|
|
, "Got:", length(npa_cols_to_extract))
|
|
}
|
|
|
|
#################################
|
|
#=========
|
|
# lf data: sam
|
|
#=========
|
|
sam_df_v2 = sam_df
|
|
sam_df = sam_df[1:10, ]
|
|
pivot_cols = meta_data_cols
|
|
|
|
expected_rows_sam_lf = nrow(sam_df) * (length(sam_df) - length(pivot_cols)); expected_rows_sam_lf
|
|
|
|
# using regex:
|
|
sam_lf = sam_df %>%
|
|
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()
|
|
} |