Remove deprecated code and re-enable QC plots

workflow/apps/r/calculate_interaction_zscores5.R

@@ -556,13 +556,13 @@ main <- function() {
         df_na %>% filter(if_all(c(L), is.finite)) # Add L, r, AUC, K as needed for debugging
       }
     
-    # # Generate QC PDFs and HTMLs
+    # Generate QC PDFs and HTMLs
-    # message("Generating QC plots")
+    message("Generating QC plots")
-    # variables <- c("L", "K", "r", "AUC", "delta_bg")
+    variables <- c("L", "K", "r", "AUC", "delta_bg")
-    # generate_and_save_plots(df, out_dir_qc, "Before_QC", variables, include_qc = TRUE)
+    generate_and_save_plots(df, out_dir_qc, "Before_QC", variables, include_qc = TRUE)
-    # generate_and_save_plots(df_above_tolerance, out_dir_qc, "Raw_L_vs_K_above_delta_bg_threshold", variables, include_qc = TRUE)
+    generate_and_save_plots(df_above_tolerance, out_dir_qc, "Raw_L_vs_K_above_delta_bg_threshold", variables, include_qc = TRUE)
-    # generate_and_save_plots(df_na_filtered, out_dir_qc, "After_QC", variables)
+    generate_and_save_plots(df_na_filtered, out_dir_qc, "After_QC", variables)
-    # generate_and_save_plots(df_no_zeros, out_dir_qc, "No_Zeros", variables)
+    generate_and_save_plots(df_no_zeros, out_dir_qc, "No_Zeros", variables)
 
     rm(df, df_above_tolerance, df_no_zeros)
     
@@ -573,15 +573,7 @@ main <- function() {
     write.csv(stats, file = file.path(out_dir, "SummaryStats_ALLSTRAINS.csv"), row.names = FALSE)
     stats_joined <- left_join(df_na, stats, by = c("conc_num", "conc_num_factor"))
 
-    # Create separate dataframes for each variable (we'll use later for plotting)
-    # stats_by_l <- stats_joined %>% select(starts_with("L_"), "OrfRep", "conc_num", "conc_num_factor")
-    # stats_by_k <- stats_joined %>% select(starts_with("K_"), "OrfRep", "conc_num", "conc_num_factor")
-    # stats_by_r <- stats_joined %>% select(starts_with("r_"), "OrfRep", "conc_num", "conc_num_factor")
-    # stats_by_auc <- stats_joined %>% select(starts_with("AUC_"), "OrfRep", "conc_num", "conc_num_factor")
-
     # Originally this filtered L NA's
-    # I've removed that filtering for now since it didn't seem right but may need to add it back in later
-    # str(stats_by_k)
 
     # Filter data within 2SD
     within_2sd_k <- stats_joined %>%
@@ -624,10 +616,6 @@ main <- function() {
       # Recalculate summary statistics for the background strain
       message("Calculating summary statistics for background strain")
       stats_bg <- calculate_summary_stats(df_bg, variables, group_vars = c("OrfRep", "Gene", "conc_num", "conc_num_factor"))
-      # stats_by_l_bg <- stats_bg %>% select(starts_with("L_"), "OrfRep", "Gene", "conc_num", "conc_num_factor")
-      # stats_by_k_bg <- stats_bg %>% select(starts_with("K_"), "OrfRep", "Gene", "conc_num", "conc_num_factor")
-      # stats_by_r_bg <- stats_bg %>% select(starts_with("r_"), "OrfRep", "Gene", "conc_num", "conc_num_factor")
-      # stats_by_auc_bg <- stats_bg %>% select(starts_with("AUC_"), "OrfRep", "Gene", "conc_num", "conc_num_factor")
       write.csv(stats_bg,
         file = file.path(out_dir, paste0("SummaryStats_BackgroundStrains_", strain, ".csv")),
         row.names = FALSE)
@@ -649,15 +637,6 @@ main <- function() {
       message("Processing deletion strains")
       deletion_strains <- process_strains(df_deletion, l_within_2sd_k, strain)
       
-      # Deprecated
-      # Change OrfRep to include the reference strain, gene, and Num so each RF gets its own score
-      # reference_strain <- reference_strain %>%
-      #   mutate(OrfRep = paste(OrfRep, Gene, num, sep = "_"))
-      # We are leaving OrfRep unchanged and using group_by(OrfRep, Gene, num) by default
-      # This is synonymous with the legacy OrfRep mutation
-      # Use group_by in functions in lieu of mutating OrfRep
-      # default_group_vars <- c("OrfRep", "Gene", "num")
-
       # TODO we may need to add "num" to grouping vars
       
       # Calculate interactions