Add pgRNA annotations files

R/03-annotate.R

@@ -31,18 +31,31 @@ gimap_annotate <- function(.data = NULL,
     if (!file.exists(annotation_file)) stop("The annotation_file specified cannot be found. Please double check the file path")
   }
 
-  # TODO: Put the code that annotates the data here!
-
-  # This file is from https://depmap.org/portal/download/all/ and from DepMap Public 19Q3 All Files
-  # Read in from inst/extdata/Achilles_common_essentials.csv
-
   # We'll take a look at the gimap_dataset$pg_ids and see what kinds of gene ids are there
   # If we need to do gene conversion we'd do something like:
 
   # biocLite('org.Hs.eg.db')
   # mapIds(org.Hs.eg.db, <column of gene IDs>, 'ENTREZID', 'SYMBOL')
   # https://github.com/FredHutch/GI_mapping/blob/main/workflow/scripts/02-get_pgRNA_annotations.Rmd
 
+  # This file is from https://depmap.org/portal/download/all/ and from DepMap Public 19Q3 All Files
+  # Essential gene labeling is from inst/extdata/Achilles_common_essentials.csv
+  # ctrl vs gene labels are from inst/extdata/pgPEN_annotations.txt
+
+  # This is the core of the code we'll need but we'll need to refactor
+  #d.annot <- d.annot %>%
+  #mutate(norm_ctrl_flag = case_when(
+  #  target_type == "gene_gene" ~ "double_targeting",
+  #  target_type == "gene_ctrl" & gene1_essential_flag == TRUE ~ "positive_control",
+  #  target_type == "ctrl_gene" & gene2_essential_flag == TRUE ~ "positive_control",
+  #  target_type == "gene_ctrl" & gene1_essential_flag != TRUE ~ "single_targeting",
+  #  target_type == "ctrl_gene" & gene2_essential_flag != TRUE ~ "single_targeting",
+  #  target_type == "ctrl_ctrl" ~ "negative_control")) %>%
+  #mutate(norm_ctrl_flag = factor(norm_ctrl_flag, levels = c("negative_control",
+  #                                                          "positive_control",
+  #                                                          "single_targeting",
+  #                                                          "double_targeting")))
+
   gimap_dataset$annotation <- NULL #TODO: Final step is annotations that line up to the same order as the pg gene data should be stored here.
 
   return(gimap_dataset)

R/04-foldchange.R

@@ -36,7 +36,7 @@ calc_lfc <- function(.data = NULL,
     }
   }
 
-  # TODO: we need to think about what happens if there are or are not replicates
+  # TODO: we need to think about what happens if there are or are not timepoints
   if (!is.null(timepoints)) {
     if (!(timepoints %in% colnames(gimap_dataset$metadata$sample_metadata))) {
       stop("The column name specified for 'timepoints' does not exist in gimap_dataset$metadata$sample_metadata")
@@ -53,6 +53,9 @@ calc_lfc <- function(.data = NULL,
   # TODO:  Here's where the log fold change calculations and other handling will go based on the code in:
   # https://github.com/FredHutch/GI_mapping/blob/main/workflow/scripts/03-filter_and_calculate_LFC.Rmd
 
+  # lfc_plasmid_vs_late = log2_cpm - plasmid_log2_cpm,
+  # lfc_early_vs_late = log2_cpm - early_log2_cpm
+
   gimap_dataset$log_fc <- NULL # TODO: the log fold changes calculated can be returned here
 
   return(gimap_dataset)