Calculate Total Polypenol Intakes

This script calculates total polyphenol intake (mg, mg/1000kcal) for provided dietary data.

INPUTS

  • Diet_FooDB_polyphenol_content.csv.bz2: Disaggregated dietary data, mapped to FooDB polyphenol content, at the compound-level
  • Diet_total_nutrients.csv - total daily nutrient data to go with dietary data.

OUTPUTS

  • summary_total_intake_by_subject.csv
  • summary_total_intake_by_entry.csv

SCRIPTS 

suppressMessages(library(dplyr))
suppressMessages(library(vroom))
suppressMessages(library(tidyr))
suppressMessages(library(stringr))

# Load provided file paths
source("provided_files.R")

# Load dietary data mapped to polyphenol content
input_polyphenol_content = vroom::vroom('outputs/Diet_FooDB_polyphenol_content.csv.bz2',
                                        show_col_types = FALSE)

input_kcal = vroom::vroom('outputs/Diet_total_nutrients.csv', show_col_types = FALSE) %>%
  # Ensure consistent KCAL naming whether ASA24 or NHANES
  dplyr::rename_with(~ "Total_KCAL", .cols = any_of(c("Total_KCAL", # Specific to ASA24
                                               "Total_DRXIKCAL"))) %>%  # Specific to NHANES
  dplyr::select(c(subject, 
           # Ensures we pull correct columns for record or recall
           any_of(c("RecallNo", "RecordNo", "RecordDayNo")),
           Total_KCAL))

# Merge the two files
input_polyphenol_kcal = dplyr::left_join(input_polyphenol_content, input_kcal)

## Joining with `by = join_by(subject, RecallNo)`

Specify grouping variables

Column grouping depends on whether output is from a record or recall.

if ("RecallNo" %in% names(input_polyphenol_kcal)) {
  group_vars = c("subject", "RecallNo")
  
} else if ("RecordNo" %in% names(input_polyphenol_kcal)) {
  group_vars = c("subject", "RecordNo", "RecordDayNo")
  
} else {
  stop("Data must contain RecallNo or RecordNo.")
}

Total daily Polyphenol Intake Numbers BY ENTRY (Record/Recall) 

content_by_entry = input_polyphenol_kcal %>%
  
  # Recall - Sum by Subject, Recall
  # Record - Sum by Subject, Record Number, Day in Record Number
  dplyr::group_by(across(all_of(group_vars))) %>%
  dplyr::mutate(pp_recallsum_mg = sum(pp_consumed, na.rm = TRUE),
         pp_recallsum_mg1000kcal = pp_recallsum_mg/(Total_KCAL/1000)) %>%
  dplyr::ungroup() %>%
  dplyr::distinct(across(all_of(group_vars)), .keep_all = TRUE) %>%
  dplyr::select(c(subject, 
                  any_of(c("RecallNo", "RecordNo", "RecordDayNo")),
                  pp_recallsum_mg, Total_KCAL, pp_recallsum_mg1000kcal))

# Write Output
vroom::vroom_write(content_by_entry, "outputs/summary_total_intake_by_entry.csv", delim = ",")

Total daily Polyphenol Intake Numbers AVERAGE FOR SUBJECT 

content_by_subject = content_by_entry %>%
  
  # Average by Participant
  dplyr::group_by(subject) %>%
  dplyr::mutate(pp_average_mg = mean(pp_recallsum_mg, na.rm = TRUE),
         kcal_average = mean(Total_KCAL, na.rm = TRUE),
         pp_average_mg_1000kcal = pp_average_mg/(kcal_average/1000)) %>%
  dplyr::ungroup() %>%
  dplyr::distinct(subject, .keep_all = TRUE) %>%
  dplyr::select(c(subject, pp_average_mg, kcal_average, pp_average_mg_1000kcal))

# Write Output
vroom::vroom_write(content_by_subject, "outputs/summary_total_intake_by_subject.csv", delim = ",")