Make calculate_summary_stats() more explicit

workflow/apps/r/calculate_interaction_zscores5.R

@@ -114,7 +114,7 @@ load_and_process_data <- function(easy_results_file, sd = 3) {
   
   # Clean and convert columns to numeric where appropriate
   df <- df %>%
-    filter(!(.data[[1]] %in% c("", "Scan"))) %>%
+    filter(!(.[[1]] %in% c("", "Scan"))) %>%
     filter(!is.na(ORF) & ORF != "" & !Gene %in% c("BLANK", "Blank", "blank") & Drug != "BMH21") %>%
     mutate(
       Col = as.numeric(Col),
@@ -189,23 +189,31 @@ process_strains <- function(df) {
 
 # Calculate summary statistics for all variables
 calculate_summary_stats <- function(df, variables, group_vars = c("conc_num", "conc_num_factor")) {
-  # Calculate summary statistics with the grouping columns
   summary_stats <- df %>%
     group_by(across(all_of(group_vars))) %>%
     summarise(across(all_of(variables), list(
-      N = length(.x),
-      mean = ~mean(.x, na.rm = TRUE),
-      median = ~median(.x, na.rm = TRUE),
-      max = ~max(.x, na.rm = TRUE),
-      min = ~min(.x, na.rm = TRUE),
-      sd = ~sd(.x, na.rm = TRUE),
-      se = sd / sqrt(N - 1),
-      z_max = (max - mean) / sd
-    ), .names = "{.fn}_{.col}"))
+      N = ~length(.),
+      mean = ~mean(., na.rm = TRUE),
+      median = ~median(., na.rm = TRUE),
+      max = ~max(., na.rm = TRUE),
+      min = ~min(., na.rm = TRUE),
+      sd = ~sd(., na.rm = TRUE)
+    ), .names = "{.fn}_{.col}")) %>%
+    mutate(
+      se_L = sd_L / sqrt(N_L - 1),
+      se_K = sd_K / sqrt(N_K - 1),
+      se_r = sd_r / sqrt(N_r - 1),
+      se_AUC = sd_AUC / sqrt(N_AUC - 1),
+      z_max_L = (max_L - mean_L) / sd_L,
+      z_max_K = (max_K - mean_K) / sd_K,
+      z_max_r = (max_r - mean_r) / sd_r,
+      z_max_AUC = (max_AUC - mean_AUC) / sd_AUC
+    )
   
   return(summary_stats)
 }
 
+
 calculate_interaction_scores <- function(df_ref, df, max_conc, variables, group_vars = c("OrfRep", "Gene", "num")) {
 
   # Calculate total concentration variables