Preserve conc cols for later

qhtcp-workflow/apps/r/calculate_interaction_zscores.R

@@ -193,8 +193,7 @@ calculate_summary_stats <- function(df, variables, group_vars) {
   return(list(summary_stats = summary_stats, df_with_stats = df_joined))
 }
 
-calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "r", "AUC"),
-  group_vars = c("OrfRep", "Gene", "num")) {
+calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "r", "AUC")) {
 
   # Calculate total concentration variables
   total_conc_num <- length(unique(df$conc_num))
@@ -221,7 +220,7 @@ calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "
     )$df_with_stats
 
   calculations <- calculations %>%
-    group_by(across(all_of(group_vars))) %>%
+    group_by(OrfRep, Gene, num) %>%
     mutate(
       NG = sum(NG, na.rm = TRUE),
       DB = sum(DB, na.rm = TRUE),
@@ -303,12 +302,8 @@ calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "
 
   # Summarize some of the stats
   interactions <- calculations %>%
-    group_by(across(all_of(group_vars))) %>%
+    group_by(OrfRep, Gene, num) %>%
     mutate(
-      OrfRep = first(OrfRep),
-      Gene = first(Gene),
-      num = first(num),
-
       # Calculate raw shifts
       Raw_Shift_L = first(Raw_Shift_L),
       Raw_Shift_K = first(Raw_Shift_K),
@@ -355,7 +350,7 @@ calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "
 
   interactions <- interactions %>%
     select(
-      "OrfRep", "Gene", "num", "NG", "DB", "SM",
+      "OrfRep", "Gene", "conc_num", "conc_num_factor", "num", "NG", "DB", "SM",
       "Raw_Shift_L", "Raw_Shift_K", "Raw_Shift_r", "Raw_Shift_AUC",
       "Z_Shift_L", "Z_Shift_K", "Z_Shift_r", "Z_Shift_AUC",
       "Sum_Z_Score_L", "Sum_Z_Score_K", "Sum_Z_Score_r", "Sum_Z_Score_AUC",
@@ -364,21 +359,17 @@ calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "
       "R_Squared_L", "R_Squared_K", "R_Squared_r", "R_Squared_AUC",
       "Z_lm_L", "Z_lm_K", "Z_lm_r", "Z_lm_AUC")
     
-  # cleaned_df <- df %>%
-  #   select(-any_of(setdiff(intersect(names(df), names(calculations)), group_vars)))
-
-  # calculations_joined <- left_join(cleaned_df, calculations, by = c("OrfRep", "Gene", "num", "conc_num", "conc_num_factor"))
-
   cleaned_df <- df %>%
-    select(-any_of(setdiff(intersect(names(df), names(interactions)), group_vars)))
+    select(-any_of(
+      setdiff(intersect(names(df), names(interactions)),
+      c("OrfRep", "Gene", "num", "conc_num", "conc_num_factor"))))
 
   interactions_joined <- left_join(cleaned_df, interactions, by = c("OrfRep", "Gene", "num", "conc_num", "conc_num_factor"))
 
   return(list(
     calculations = calculations,
     interactions = interactions,
-    interactions_joined = interactions_joined
-  ))
+    interactions_joined = interactions_joined))
 }
 
 generate_and_save_plots <- function(out_dir, filename, plot_configs, grid_layout = NULL) {