• Food Contributors to Total Polyphenol Intake
• SCRIPTS
  • Food Consumption Counts
  • Total daily Polyphenol Intake Numbers BY RECALL
  • Total daily Polyphenol Intake Numbers AVERAGE FOR SUBJECT
  • Obtain food contributors to total polyphenol intake

Food Contributors to Total Polyphenol Intake

This script examines food contributors to total polyphenol intake.

INPUTS

• Recall_Disaggregated_mapped.csv.bz2; Dissagregated dietary data, mapped to FooDB foods
• Recall_FooDB_polyphenol_content.csv.bz2: Disaggregated dietary data, mapped to FooDB foods and polyphenol content
• Recall_total_nutrients.csv - total daily nutrient data to go with dietary data.

OUTPUTS

• summary_total_polyphenol_food_contributors.csv

SCRIPTS

# Load packages
suppressMessages(library(dplyr))
suppressMessages(library(vroom))
suppressMessages(library(tidyr))
suppressMessages(library(stringr))

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

# Foods Mapped
input_mappings = vroom::vroom('outputs/Recall_Disaggregated_mapped.csv.bz2',
                              show_col_types = FALSE)

# Foods Mapped with content
input_polyphenol_content = vroom::vroom('outputs/Recall_FooDB_polyphenol_content.csv.bz2',
                                        show_col_types = FALSE)
input_kcal = vroom::vroom('outputs/Recall_total_nutrients.csv', show_col_types = FALSE) %>%
  # Ensure consistent KCAL naming whether ASA24 or NHANES
  rename_with(~ "Total_KCAL", .cols = any_of(c("Total_KCAL", # Specific to ASA24
                                               "Total_DRXIKCAL"))) %>%  # Specific to NHANES
  select(c(subject, RecallNo, Total_KCAL))

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

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

Food Consumption Counts

This tells us how many times a food was reported and then if we see all participants consume a food.

food_counts = input_mappings %>%
  # Every time a subject consumed food, how much of it in total did they eat? 
  # How many instances did they eat this food in one day?
  group_by(subject, RecallNo, fdd_ingredient) %>%
  summarise(
    amount_consumed_g = sum(FoodAmt_Ing_g, na.rm =TRUE),
    times_consumed = n(),
    .groups = "drop") %>%
  
  # Across the cohort summary
  group_by(fdd_ingredient) %>%
  summarise(
    # How many instances was this food seen
    total_times_consumed = sum(times_consumed),
    
    # How many subjects consumed this food
    n_subjects = n_distinct(subject),
    
    # Information about the Ingredient consumed
    min_amount_consumed_g = min(amount_consumed_g),
    average_amount_consumed_g = mean(amount_consumed_g),
    median_amount_consumed_g= median(amount_consumed_g),
    max_amount_consumed_g = max(amount_consumed_g),
    
    .groups = "drop") %>%
  arrange(desc(total_times_consumed))

Total daily Polyphenol Intake Numbers BY RECALL

content_by_recall_food = input_polyphenol_kcal %>%
  
  # Sum by Recall and Participant
  group_by(subject, RecallNo, fdd_ingredient) %>%
  mutate(pp_recallsum_mg = sum(pp_consumed, na.rm = TRUE),
         pp_recallsum_mg1000kcal = pp_recallsum_mg/(Total_KCAL/1000)) %>%
  ungroup() %>%
  distinct(subject, RecallNo, fdd_ingredient, .keep_all = TRUE) %>%
  select(c(subject, RecallNo, fdd_ingredient, pp_recallsum_mg, Total_KCAL, pp_recallsum_mg1000kcal))

Total daily Polyphenol Intake Numbers AVERAGE FOR SUBJECT

content_by_subject_food = content_by_recall_food %>%
  
  # Average by Participant
  group_by(subject, fdd_ingredient) %>%
  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)) %>%
  ungroup() %>%
  distinct(subject, fdd_ingredient, .keep_all = TRUE) %>%
  select(c(subject, fdd_ingredient, pp_average_mg, kcal_average, pp_average_mg_1000kcal)) 

Obtain food contributors to total polyphenol intake

content_by_food = content_by_subject_food %>%
  
  # Average by food
  group_by(fdd_ingredient) %>%
  mutate(food_pp_average_mg1000kcal = mean(pp_average_mg_1000kcal, na.rm = TRUE)) %>%
  ungroup() %>%
  distinct(fdd_ingredient, .keep_all = TRUE) %>%
  select(c(fdd_ingredient, food_pp_average_mg1000kcal)) %>%
  left_join(food_counts, by = "fdd_ingredient") %>%
  arrange(desc(food_pp_average_mg1000kcal), desc(n_subjects))

# Export food contributors file 
vroom::vroom_write(content_by_food, 'outputs/summary_total_polyphenol_food_contributors.csv', delim = ",")