From 5d0d017a67ed7d8b11e01d8c7586f704361b188e Mon Sep 17 00:00:00 2001
From: Bryan Roessler <bryanroessler@gmail.com>
Date: Tue, 17 Sep 2024 21:03:19 -0400
Subject: [PATCH] Cleanup output

---
 .../apps/r/calculate_interaction_zscores.R    | 32 ++++++++-----------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/qhtcp-workflow/apps/r/calculate_interaction_zscores.R b/qhtcp-workflow/apps/r/calculate_interaction_zscores.R
index 1d5b857b..2e193437 100644
--- a/qhtcp-workflow/apps/r/calculate_interaction_zscores.R
+++ b/qhtcp-workflow/apps/r/calculate_interaction_zscores.R
@@ -168,10 +168,10 @@ calculate_summary_stats <- function(df, variables, group_vars) {
       across(all_of(variables), list(
         mean = ~mean(., na.rm = TRUE),
         median = ~median(., na.rm = TRUE),
-        max = ~max(., na.rm = TRUE),
-        min = ~min(., na.rm = TRUE),
+        max = ~ ifelse(all(is.na(.)), NA, max(., na.rm = TRUE)),
+        min = ~ ifelse(all(is.na(.)), NA, min(., na.rm = TRUE)),
         sd = ~sd(., na.rm = TRUE),
-        se = ~sd(., na.rm = TRUE) / sqrt(N)  # Corrected SE calculation
+        se = ~sd(., na.rm = TRUE) / sqrt(N) - 1 # TODO needs comment for explanation
       ), .names = "{.fn}_{.col}"),
       .groups = "drop"
     )
@@ -331,7 +331,7 @@ calculate_interaction_scores <- function(df, max_conc, variables, group_vars) {
   # Declare column order for output
   calculations <- stats %>%
     select(
-      "OrfRep", "Gene", "conc_num", "conc_num_factor", "N",
+      "OrfRep", "Gene", "num", "conc_num", "conc_num_factor", "N",
       "mean_L", "mean_K", "mean_r", "mean_AUC",
       "median_L", "median_K", "median_r", "median_AUC",
       "sd_L", "sd_K", "sd_r", "sd_AUC",
@@ -932,7 +932,7 @@ filter_data <- function(df, variables, nf = FALSE, missing = FALSE, adjust = FAL
   
   # Adjust NAs to .001 for linear model
   if (adjust) {
-    if (verbose) message("Replacing NA with 0.001 for Avg_Zscore_ and Z_lm_ columns.")
+    if (verbose) message("Replacing NA with 0.001 for Avg_Zscore_ and Z_lm_ columns")
     df <- df %>%
       mutate(
         across(all_of(avg_zscore_cols), ~ ifelse(is.na(.), 0.001, .)),
@@ -942,14 +942,12 @@ filter_data <- function(df, variables, nf = FALSE, missing = FALSE, adjust = FAL
   
   # Filter non-finite values
   if (nf) {
-    if (verbose) message("Filtering non-finite values for variables: ", paste(variables, collapse = ", "))
-    
     non_finite_df <- df %>%
       filter(if_any(all_of(variables), ~ !is.finite(.)))
     
     if (verbose && nrow(non_finite_df) > 0) {
-      message("Filtering non-finite rows for variables ", paste(variables, collapse = ", "), ":")
-      print(non_finite_df)
+      message("Filtering non-finite rows for variable(s) ", paste(variables, collapse = ", "), ":")
+      print(non_finite_df %>% select(all_of(c("scan", "Plate", "Row", "Col", "num", "conc_num", variables))), n = 30)
     }
     
     df <- df %>%
@@ -958,18 +956,15 @@ filter_data <- function(df, variables, nf = FALSE, missing = FALSE, adjust = FAL
   
   # Filter missing values
   if (missing) {
-    if (verbose) message("Filtering missing values for variables: ", paste(variables, collapse = ", "))
     
-    # Identify missing rows for logging
     missing_df <- df %>%
       filter(if_any(all_of(variables), ~ is.na(.)))
     
     if (verbose && nrow(missing_df) > 0) {
-      message("Missing data for variables ", paste(variables, collapse = ", "), ":")
-      print(missing_df)
+      message("Filtering missing data for variable(s) ", paste(variables, collapse = ", "), ":")
+      print(missing_df %>% select(all_of(c("scan", "Plate", "Row", "Col", "num", "conc_num", variables))), n = 30)
     }
     
-    # Keep only rows where all specified variables are not missing
     df <- df %>%
       filter(if_all(all_of(variables), ~ !is.na(.)))
   }
@@ -980,14 +975,13 @@ filter_data <- function(df, variables, nf = FALSE, missing = FALSE, adjust = FAL
       if (variable %in% variables) {
         ylim_vals <- limits_map[[variable]]
         
-        if (verbose) message("Applying limits for variable ", variable, ": [", ylim_vals[1], ", ", ylim_vals[2], "].")
-        
         out_of_range_df <- df %>%
           filter(.data[[variable]] < ylim_vals[1] | .data[[variable]] > ylim_vals[2])
         
         if (verbose && nrow(out_of_range_df) > 0) {
-          message("Out-of-range data for variable ", variable, ":")
-          print(out_of_range_df)
+          message("Applying limits for variable ", variable, ": [", ylim_vals[1], ", ", ylim_vals[2], "].")
+          message("Filtering out-of-range data for variable ", variable, ":")
+          print(out_of_range_df %>% select(all_of(c("scan", "Plate", "Row", "Col", "num", "conc_num", variables))), n = 30)
         }
         
         df <- df %>%
@@ -998,7 +992,7 @@ filter_data <- function(df, variables, nf = FALSE, missing = FALSE, adjust = FAL
   
   # Calculate Rank Columns if 'rank' is TRUE
   if (rank) {
-    if (verbose) message("Calculating rank columns for variables: ", paste(variables, collapse = ", "))
+    if (verbose) message("Calculating ranks for variable(s): ", paste(variables, collapse = ", "))
 
     for (col in avg_zscore_cols) {
       rank_col <- paste0("Rank_", col)