Fix update_gene_names

workflow/apps/r/calculate_interaction_zscores5.R

@@ -140,18 +140,24 @@ load_and_process_data <- function(easy_results_file, sd = 3) {
 
 # Update Gene names using the SGD gene list
 update_gene_names <- function(df, sgd_gene_list) {
+  # Load SGD gene list
   genes <- read.delim(file = sgd_gene_list,
     quote = "", header = FALSE,
     colClasses = c(rep("NULL", 3), rep("character", 2), rep("NULL", 11)))
-  
+
+  # Create a named vector for mapping ORF to GeneName
   gene_map <- setNames(genes$V5, genes$V4)
   
-  df <- df %>%
-    rowwise() %>%
-    mutate(Gene = ifelse(OrfRep != "YDL227C", gene_map[[ORF]], Gene)) %>%
-    ungroup() %>%
-    mutate(Gene = ifelse(Gene == "" | Gene == "OCT1", OrfRep, Gene))
+  # Vectorized match to find the GeneName from gene_map
+  mapped_genes <- gene_map[df$ORF]
   
+  # Replace NAs in mapped_genes with original Gene names (preserves existing Gene names if ORF is not found)
+  updated_genes <- ifelse(is.na(mapped_genes) | df$OrfRep == "YDL227C", df$Gene, mapped_genes)
+  
+  # Ensure Gene is not left blank or incorrectly updated to "OCT1"
+  df <- df %>%
+    mutate(Gene = ifelse(updated_genes == "" | updated_genes == "OCT1", OrfRep, updated_genes))
+
   return(df)
 }
 
@@ -453,6 +459,7 @@ adjust_missing_and_rank <- function(df) {
       r_Rank_lm = rank(Z_lm_r),
       AUC_Rank_lm = rank(Z_lm_AUC)
     )
+
   return(df)
 }