bryan/hartman-server
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Put bg_stats into its own df to be reused

Browse Source
This commit is contained in:
Bryan Roessler
2024-09-24 22:26:05 -04:00
parent 4741996694
commit 81174db065
1 changed files with 28 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
qhtcp-workflow/apps/r/calculate_interaction_zscores.R
View File

@@ -193,15 +193,13 @@ calculate_summary_stats <- function(df, variables, group_vars) {
return(list(summary_stats = summary_stats, df_with_stats = df_joined))
}
calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "r", "AUC"),
calculate_interaction_scores <- function(df, max_conc, bg_stats, variables = c("L", "K", "r", "AUC"),
group_vars = c("OrfRep", "Gene", "num")) {
# Calculate total concentration variables
total_conc_num <- length(unique(df$conc_num))
calculations <- calculations %>%
calculations <- df %>%
group_by(OrfRep, Gene, num) %>%
mutate(
NG = sum(NG, na.rm = TRUE),
@@ -210,14 +208,14 @@ calculate_interaction_scores <- function(df, max_conc, variables = c("L", "K", "
num_non_removed_concs = total_conc_num - sum(DB, na.rm = TRUE) - 1,
# Store the background data
WT_L = bg_means$L,
WT_K = bg_means$K,
WT_r = bg_means$r,
WT_AUC = bg_means$AUC,
WT_sd_L = bg_sd$L,
WT_sd_K = bg_sd$K,
WT_sd_r = bg_sd$r,
WT_sd_AUC = bg_sd$AUC,
WT_L = bg_stats$WT_L,
WT_K = bg_stats$WT_K,
WT_r = bg_stats$WT_r,
WT_AUC = bg_stats$WT_AUC,
WT_sd_L = bg_stats$WT_sd_L,
WT_sd_K = bg_stats$WT_sd_K,
WT_sd_r = bg_stats$WT_sd_r,
WT_sd_AUC = bg_stats$WT_sd_AUC,
Raw_Shift_L = first(mean_L) - bg_means$L,
Raw_Shift_K = first(mean_K) - bg_means$K,
Raw_Shift_r = first(mean_r) - bg_means$r,
@@ -1050,7 +1048,7 @@ main <- function() {
df_no_zeros <- df_na %>% filter(L > 0) # formerly X_noZero
# Save some constants
max_conc <- max(df$conc_num_factor)
max_conc <- max(as.numeric(df$conc_num_factor))
l_half_median <- (median(df_above_tolerance$L, na.rm = TRUE)) / 2
k_half_median <- (median(df_above_tolerance$K, na.rm = TRUE)) / 2
@@ -1072,6 +1070,20 @@ main <- function() {
write.csv(df_na_ss, file = file.path(out_dir, "summary_stats_all_strains.csv"), row.names = FALSE)
# df_na_filtered_stats <- process_data(df_na_stats, c("L"), filter_nf = TRUE)
# Pull the background means and standard deviations from zero concentration
bg_stats <- df_na_stats %>%
filter(conc_num == 0) %>%
summarise(
WT_L = first(mean_L),
WT_K = first(mean_K),
WT_r = first(mean_r),
WT_AUC = first(mean_AUC),
WT_sd_L = first(sd_L),
WT_sd_K = first(sd_K),
WT_sd_r = first(sd_r),
WT_sd_AUC = first(sd_AUC)
)
message("Calculating summary statistics after quality control excluding zero values")
ss <- calculate_summary_stats(
df = df_no_zeros,
@@ -1308,11 +1320,11 @@ main <- function() {
message("Calculating reference strain interaction scores")
df_reference_stats <- calculate_summary_stats(
df = refrence_strain,
df = reference_strain,
variables = interaction_vars,
group_vars = c("OrfRep", "Gene", "num", "conc_num", "conc_num_factor")
)$df_with_stats
reference_results <- calculate_interaction_scores(df_reference_stats, max_conc, group_vars = c("OrfRep", "Gene", "num"))
reference_results <- calculate_interaction_scores(df_reference_stats, max_conc, bg_stats, group_vars = c("OrfRep", "Gene", "num"))
zscores_calculations_reference <- reference_results$calculations
zscores_interactions_reference <- reference_results$interactions
zscores_interactions_reference_joined <- reference_results$interactions_joined
@@ -1323,7 +1335,7 @@ main <- function() {
variables = interaction_vars,
group_vars = c("OrfRep", "Gene", "conc_num", "conc_num_factor")
)$df_with_stats
deletion_results <- calculate_interaction_scores(df_deletion_stats, max_conc, group_vars = c("OrfRep"))
deletion_results <- calculate_interaction_scores(df_deletion_stats, max_conc, bg_stats, group_vars = c("OrfRep"))
zscores_calculations <- deletion_results$calculations
zscores_interactions <- deletion_results$interactions
zscores_interactions_joined <- deletion_results$interactions_joined