From 93c3b82140a02f29371a3ba14d738a4095c6a8e8 Mon Sep 17 00:00:00 2001 From: Bryan Roessler Date: Wed, 4 Sep 2024 21:27:31 -0400 Subject: [PATCH] Before debugging --- .../apps/r/calculate_interaction_zscores5.R | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/workflow/apps/r/calculate_interaction_zscores5.R b/workflow/apps/r/calculate_interaction_zscores5.R index 89eefb2e..c688aab8 100644 --- a/workflow/apps/r/calculate_interaction_zscores5.R +++ b/workflow/apps/r/calculate_interaction_zscores5.R @@ -10,7 +10,6 @@ suppressMessages({ options(warn = 2, max.print = 1000) - # Set the memory limit to 30GB (30 * 1024 * 1024 * 1024 bytes) soft_limit <- 30 * 1024 * 1024 * 1024 hard_limit <- 30 * 1024 * 1024 * 1024 @@ -115,7 +114,7 @@ load_and_process_data <- function(easy_results_file, sd = 3) { # Clean and convert columns to numeric where appropriate df <- df %>% - filter(!(pull(select(., 1)) %in% c("", "Scan"))) %>% + filter(!(.data[[1]] %in% c("", "Scan"))) %>% filter(!is.na(ORF) & ORF != "" & !Gene %in% c("BLANK", "Blank", "blank") & Drug != "BMH21") %>% mutate( Col = as.numeric(Col), @@ -200,14 +199,13 @@ calculate_summary_stats <- function(df, variables, group_vars = c("conc_num", "c max = ~max(.x, na.rm = TRUE), min = ~min(.x, na.rm = TRUE), sd = ~sd(.x, na.rm = TRUE), - se = sd / sqrt(N - 1), # TODO why - 1? + se = sd / sqrt(N - 1), z_max = (max - mean) / sd ), .names = "{.fn}_{.col}")) return(summary_stats) } - calculate_interaction_scores <- function(df_ref, df, max_conc, variables, group_vars = c("OrfRep", "Gene", "num")) { # Calculate total concentration variables @@ -323,14 +321,13 @@ calculate_interaction_scores <- function(df_ref, df, max_conc, variables, group_ ) %>% ungroup() - interactions_scores_all <- interactions_scores_all %>% + interaction_scores_all <- interactions_scores_all %>% arrange(desc(Z_lm_L)) %>% arrange(desc(NG)) return(list(zscores_calculations = interaction_scores_all, zscores_interactions = interaction_scores)) } - generate_plot <- function(df, x_var, y_var = NULL, plot_type, color_var = "conc_num", title, x_label = NULL, y_label = NULL, ylim_vals = NULL) { @@ -362,7 +359,6 @@ generate_plot <- function(df, x_var, y_var = NULL, plot_type, color_var = "conc_ return(plot) } - generate_and_save_plots <- function(df, output_dir, file_prefix, variables, plot_type = "scatter", include_qc = FALSE, ylim_vals = NULL) { plots <- list() @@ -396,8 +392,6 @@ generate_and_save_plots <- function(df, output_dir, file_prefix, variables, plot save_plots(file_prefix, plots, output_dir) } - - # Ensure all plots are saved and printed to PDF save_plots <- function(file_name, plot_list, output_dir) { # Save to PDF @@ -426,8 +420,6 @@ save_plots <- function(file_name, plot_list, output_dir) { }) } - - generate_interaction_plots <- function(df, output_file) { message("Generating interaction plots") @@ -472,8 +464,6 @@ generate_interaction_plots <- function(df, output_file) { dev.off() } - - generate_cpp_correlation_plots <- function(df_na_rm, lm_list, output_dir) { lm_summaries <- lapply(lm_list, summary) plot_titles <- c("Interaction L vs. Interaction K", "Interaction L vs. Interaction r", "Interaction L vs. Interaction AUC", @@ -516,7 +506,6 @@ adjust_missing_and_rank <- function(df) { return(df) } - # Function to create and save all ranked plots create_ranked_plots <- function(df, output_dir) { df_adjusted <- adjust_missing_and_rank(df) @@ -528,7 +517,6 @@ create_ranked_plots <- function(df, output_dir) { generate_and_save_ranked_plots(df_adjusted, output_dir, "RankPlots_lm_naRM") } - generate_plots <- function(df, x_var, y_vars, plot_type, color_var = "conc_num", title_prefix = "", x_label = NULL, y_label = NULL, ylim_vals = NULL, output_dir, file_prefix = "plot") { plot_list <- list()