• Calculate Class-Level Polypenol Intakes
• SCRIPTS
  • Daily Class Polyphenol Intake Numbers BY RECALL
  • Daily Class Intakes by SUBJECT

Calculate Class-Level Polypenol Intakes

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

INPUTS

• Recall_FooDB_polyphenol_content.csv.bz2: Disaggregated dietary data, mapped to FooDB polyphenol content, at the compound-level
• Recall_total_nutrients.csv - total daily nutrient data to go with dietary data.
• FooDB_polyphenol_classtax_3072.csv - class taxonomy is derived from FooDB which uses ClassyFire, an automated chemical taxonomic classification application based on chemical structure

OUTPUTS

• summary_class_intake_by_recall.csv, polyphenol class intakes by recall for each participant
• summary_class_intake_by_subject.csv, polyphenol class intakes for each participant, provided in wide format (classes as rows)
• summary_class_intake_by_subject_wide.csv, polyphenol class intakes for each participant, provided in wide format (classes as columns)

SCRIPTS

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

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

#Content and kcal data
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))

# Class taxonomy for FooDB compounds
class_tax = vroom::vroom(class_tax, show_col_types = FALSE) %>%
  select(c(compound_public_id, class))

# Merge the two files
input_polyphenol_kcal = left_join(input_polyphenol_content, input_kcal)  %>%
  left_join(class_tax, by = "compound_public_id")

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

Daily Class Polyphenol Intake Numbers BY RECALL

class_intakes_recall = input_polyphenol_kcal%>%
  
  #Group by Taxonomic Class
  group_by(subject, RecallNo, class) %>%
  
  #gets the sum of each compound for each participant's recall
  mutate(class_intake_mg = sum(pp_consumed, na.rm = TRUE)) %>% 
  select(c(subject, RecallNo, class, class_intake_mg, Total_KCAL)) %>%
  ungroup()%>%
  
  #Remove duplicates since we've summed each polyphenol per recall
  distinct(subject, RecallNo, class, .keep_all = TRUE)  %>%
  
  #Filter out missing class, this is for foods that did not map
  filter(!is.na(class)) %>%
  
  #Standardize Intakes to caloric intake
  mutate(class_intake_mg1000kcal = class_intake_mg/(Total_KCAL/1000))

vroom::vroom_write(class_intakes_recall, "outputs/summary_class_intake_by_recall.csv", delim = ",")

Daily Class Intakes by SUBJECT

# First average caloric intakes
kcal_subject = input_kcal %>%
  group_by(subject) %>%
  summarise(avg_Total_KCAL = mean(Total_KCAL, na.rm = TRUE))

# Then let's average the class intakes
class_intakes_subject = class_intakes_recall %>%
  # We will replace these with the subject average
  select(-c(Total_KCAL,class_intake_mg1000kcal)) %>%
  
  #Average polyphenol intake across recalls for each class
  group_by(subject, class) %>%
  mutate(Avg_class_intake_mg = mean(class_intake_mg)) %>%
  ungroup() %>%
  
  #Remove duplicates
  distinct(subject, class, .keep_all = TRUE) %>%
  select(-class_intake_mg) %>%
  
  # Add kcal data
  left_join(kcal_subject, by = 'subject') %>%
  mutate(class_intake_mg1000kcal = Avg_class_intake_mg/(avg_Total_KCAL/1000)) 

vroom::vroom_write(class_intakes_subject,
                   "outputs/summary_class_intake_by_subject.csv", delim = ",")

Available for users who prefer wide format

class_intakes_subject_wide = class_intakes_subject %>%
  
  #Transpose dataframe where each column is a participant
  pivot_wider(id_cols = subject, names_from = class, 
              values_from = class_intake_mg1000kcal, values_fill = 0)

vroom::vroom_write(class_intakes_subject_wide,
                   "outputs/summary_class_intake_by_subject_wide.csv", delim = ",")