making all examples run-able for biocCheck

ytakemon · Apr 4, 2023 · 5691082 · 5691082
1 parent f467258
commit 5691082
Show file tree

Hide file tree

Showing 35 changed files with 35,387 additions and 37,347 deletions.
diff --git a/NAMESPACE b/NAMESPACE
@@ -2,17 +2,17 @@
 
 export("%>%")
 export(GI_screen)
-export(annotate_coessential_df)
+export(annotate_coess)
 export(coessential_map)
-export(extract_protein_expr)
-export(extract_rna_expr)
+export(extract_prot)
+export(extract_rna)
 export(get_DepMapID)
 export(get_GeneNameID)
 export(get_inflection_points)
-export(list_available_cancer_subtypes)
-export(list_available_cancer_types)
-export(list_available_mutations)
-export(plot_coessential_genes)
+export(list_cancer_subtypes)
+export(list_cancer_types)
+export(list_mutations)
+export(plot_coess)
 export(plot_screen)
 export(select_cell_lines)
 import(dplyr)

diff --git a/R/GI_screen.R b/R/GI_screen.R
@@ -35,18 +35,16 @@
 #' @md
 #' 
 #' @examples 
-#' \dontrun{
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
 #' 
 #' Screen_results <- GI_screen(
 #' control_id = c('ACH-001354', 'ACH-000274', 'ACH-001799'), 
 #' mutant_id = c('ACH-000911', 'ACH-001957', 'ACH-000075'), 
 #' gene_list = c("ARID1A", "ARID1B", "SMARCA2"),
 #' core_num = 2, 
-#' output_dir = '~/Desktop/GRETTA_test_dir/',
-#' data_dir = '/path/to/DepMap_data/',
-#' test = TRUE) # turn on for shorter test runs
-#' 
-#' }
+#' output_dir = gretta_output_dir,
+#' data_dir = gretta_data_dir)
 #' 
 #' @rdname GI_screen
 #' @export 

diff --git a/R/annotate_coessential_df.R → R/annotate_coess.R b/R/annotate_coessential_df.R → R/annotate_coess.R
@@ -16,20 +16,24 @@
 #' @md
 #' 
 #' @examples 
-#' \dontrun{
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
 #' 
-#' annotated_coessential_df <- annotate_coessential_df(
-#' input_ess = co_ess_res,
-#' input_inflec = inflection_points)
+#' load(paste0(
+#' gretta_data_dir,"/sample_22Q2_ARID1A_coessential_result.rda"), 
+#' envir = environment())
+#' load(paste0(
+#' gretta_data_dir,"/sample_22Q2_ARID1A_coessential_inflection.rda"), 
+#' envir = environment())
 #' 
-#' }
+#' annotated_df <- annotate_coess(coess_df, coess_inflection_df)
 #' 
-#' @rdname annotate_coessential_df
+#' @rdname annotate_coess
 #' @export 
 #' @importFrom dplyr mutate filter pull rename arrange case_when
 #' @importFrom tibble tibble
 
-annotate_coessential_df <- function(input_ess = NULL, input_inflec = NULL) {
+annotate_coess <- function(input_ess = NULL, input_inflec = NULL) {
   # Checkpoint
   if (is.null(input_ess)) {
     stop("No coessential dataframe found!")

diff --git a/R/coessential_map.R b/R/coessential_map.R
@@ -29,15 +29,16 @@
 #' @md
 #' 
 #' @examples 
-#' \dontrun{
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
 #' 
-#' Screen_results <- GINI_screen(
-#' input_gene = 'ARID1A', 
-#' output_dir = '~/Desktop/GINI_test_dir/',
-#' data_dir = '/path/to/DepMap_data/',
-#' test = TRUE) # turn on for shorter test runs
-#' 
-#' }
+#' coess_df <- coessential_map(
+#' input_gene = "ARID1A",
+#' input_disease = "Pancreatic Cancer",
+#' core_num = 2,
+#' data_dir = gretta_data_dir, 
+#' output_dir = gretta_output_dir,
+#' test = TRUE)
 #' 
 #' @rdname coessential_map
 #' @export 

diff --git a/R/extract_protein_expr.R → R/extract_prot.R b/R/extract_protein_expr.R → R/extract_prot.R
@@ -11,18 +11,20 @@
 #' @details See also `extract_protein_rna` to extract proteomics profile data
 #' 
 #' @examples 
-#' \dontrun{
-#' extract_protein_expr(
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
+#' 
+#' extract_prot(
 #' input_samples = c('ACH-000004', 'ACH-000146'), 
-#' input_genes = c('ATM','TOP1'),
-#' data_dir = '/path/to/DepMap_data/')
-#' }
-#' @rdname extract_protein_expr
+#' input_genes = c('ATM'),
+#' data_dir = gretta_data_dir)
+#' 
+#' @rdname extract_prot
 #' @export 
 #' @importFrom dplyr select contains left_join filter
 #' @importFrom tidyr pivot_longer
 
-extract_protein_expr <- function(input_samples = NULL, input_genes = NULL, data_dir = NULL) {
+extract_prot <- function(input_samples = NULL, input_genes = NULL, data_dir = NULL) {
 
   # Print and check to see input was provided
   if (is.null(input_samples)) {

diff --git a/R/extract_rna_expr.R → R/extract_rna.R b/R/extract_rna_expr.R → R/extract_rna.R
@@ -8,20 +8,22 @@
 #' @return Data frame containing RNA expression (TPM) for sample provided in the input. 
 #' If no genes were specified, the function will return a data frame of all genes profiled in DepMap
 #' 
-#' @details See also `extract_protein_expr` to extract proteomics profile data
+#' @details See also `extract_prot` to extract proteomics profile data
 #' 
 #' @examples 
-#' \dontrun{
-#' extract_rna_expr(
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
+#' 
+#' extract_rna(
 #' input_samples = c('ACH-001642','ACH-000688'), 
-#' input_genes = c('TP53','ARID1A'),
-#' data_dir = '/path/to/DepMap_data/')
-#' }
-#' @rdname extract_rna_expr
+#' input_genes = c('ARID1A'),
+#' data_dir = gretta_data_dir)
+#' 
+#' @rdname extract_rna
 #' @export 
 #' @importFrom dplyr filter select
 
-extract_rna_expr <- function(input_samples = NULL, input_genes = NULL, data_dir = NULL) {
+extract_rna <- function(input_samples = NULL, input_genes = NULL, data_dir = NULL) {
 
   # Print and check to see input was provided
   if (is.null(input_samples)) {

diff --git a/R/get_names.R b/R/get_names.R
@@ -14,9 +14,10 @@
 #' 
 #' @export
 #' @examples
-#' \dontrun{
-#' get_GeneNameID('A1CF', data_dir = '/path/to/DepMap_data/')
-#' }
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' 
+#' get_GeneNameID('A1CF', data_dir = gretta_data_dir)
+#' 
 get_GeneNameID <- function(gene_name, data_dir) {
   if (is.null(data_dir)) {
     stop(
@@ -74,9 +75,11 @@ get_GeneNameID <- function(gene_name, data_dir) {
 #' 
 #' @export
 #' @examples
-#' \dontrun{
-#' get_DepMapID('JURKAT', data_dir = '/path/')
-#' }
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
+#' 
+#' get_DepMapID('JURKAT', data_dir = gretta_data_dir)
+#' 
 get_DepMapID <- function(sample_name, data_dir) {
   # Load necessary data
   protein_annot <- sample_annot <- NULL  # see: https://support.bioconductor.org/p/24756/

diff --git a/R/list_available_cancer_type.R → R/list_cancer_type.R b/R/list_available_cancer_type.R → R/list_cancer_type.R
@@ -1,7 +1,7 @@
 #' List cancer types that are available
 #' 
 #' @description 
-#' `list_available_cancer_types()` and `list_available_cancer_subtypes()` provide tools for identifying cancer (sub)types that are available in DepMap.
+#' `list_cancer_types()` and `list_cancer_subtypes()` provide tools for identifying cancer (sub)types that are available in DepMap.
 #' 
 #' @return string A vector containing unique cancer types available
 
@@ -12,11 +12,12 @@
 #' 
 #' @export
 #' @examples
-#' \dontrun{
-#' list_available_cancer_types(data_dir = '/path/to/data')
-#' }
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
 #' 
-list_available_cancer_types <- function(data_dir) {
+#' list_cancer_types(data_dir = gretta_data_dir)
+#' 
+list_cancer_types <- function(data_dir) {
   # Load necessary data
   sample_annot <- NULL  # see: https://support.bioconductor.org/p/24756/
   load(
@@ -30,17 +31,18 @@ list_available_cancer_types <- function(data_dir) {
     unique
 }
 
-#' @describeIn list_available_cancer_types List cancer subtypes that are available
+#' @describeIn list_cancer_types List cancer subtypes that are available
 #' 
-#' @param input_disease string A vector of unique with one or more cancer types listed in `list_available_cancer_types()`
+#' @param input_disease string A vector of unique with one or more cancer types listed in `list_cancer_types()`
 #' @param data_dir string Path to GINIR_data
 #' @importFrom rlang .data
 #' @export
 #' @examples
-#' \dontrun{
-#' list_available_cancer_subtypes('Lung Cancer', data_dir = '/path/to/DepMap_data/')
-#' } 
-list_available_cancer_subtypes <- function(input_disease, data_dir) {
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' 
+#' list_cancer_subtypes('Lung Cancer', data_dir = gretta_data_dir)
+#' 
+list_cancer_subtypes <- function(input_disease, data_dir) {
   if (is.null(data_dir)) {
     stop(
       paste0("No directory to data was specified. Please provide path to DepMap data.")

diff --git a/R/list_available_mutations.R → R/list_mutations.R b/R/list_available_mutations.R → R/list_mutations.R
@@ -17,15 +17,19 @@
 #' @return A data frame containing mutations matching criteria of input arguments
 #' 
 #' @examples 
-#' \dontrun{
-#' list_available_mutations(gene = 'TP53', data_dir = '/path/to/DepMap_data/')
-#' list_available_mutations(chr = 12, data_dir = '/path/to/DepMap_data/')
-#' }
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
 #' 
-#' @rdname list_available_mutations
+#' list_mutations(
+#' gene = 'TP53', 
+#' is_damaging = TRUE,
+#' data_dir = gretta_data_dir)
+#' 
+#' @rdname list_mutations
 #' @export 
 #' @importFrom dplyr filter select arrange distinct
-list_available_mutations <- function(
+#' 
+list_mutations <- function(
     gene = NULL, chr = NULL, start_bp = NULL, end_bp = NULL, is_hotspot = NULL, is_damaging = NULL,
     variant_classification = NULL, data_dir = NULL
 ) {

diff --git a/R/plot_coessential_genes.R → R/plot_coess.R b/R/plot_coessential_genes.R → R/plot_coess.R
@@ -11,22 +11,29 @@
 #' @md
 #' 
 #' @examples 
-#' \dontrun{
-#' plot_coessential_genes(
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' gretta_output_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_troubleshooting/"
+#' 
+#' load(paste0(
+#' gretta_data_dir,"/sample_22Q2_ARID1A_coessential_result.rda"), 
+#' envir = environment())
+#' load(paste0(
+#' gretta_data_dir,"/sample_22Q2_ARID1A_coessential_inflection.rda"), 
+#' envir = environment())
+#' 
+#' plot_coess(
 #' result_df = coess_df, 
-#' inflection_df = inflection_points_df, 
-#' label_genes = TRUE, 
-#' label_n = 3)
-#' }
+#' inflection_df = coess_inflection_df, 
+#' label_genes = FALSE)
 #' 
-#' @rdname plot_coessential_genes
+#' @rdname plot_coess
 #' @export 
 #' @importFrom dplyr mutate filter arrange case_when
 #' @importFrom ggplot2 ggplot aes geom_hline geom_point scale_colour_identity scale_x_reverse scale_y_continuous theme theme_light
 #' @importFrom stringr str_split_fixed
 #' @importFrom ggrepel geom_label_repel
 
-plot_coessential_genes <- function(result_df = NULL, inflection_df = NULL, label_genes = FALSE, label_n = NULL) {
+plot_coess <- function(result_df = NULL, inflection_df = NULL, label_genes = FALSE, label_n = NULL) {
   # Check data is provided
   if (is.null(result_df)) {
     stop("No result data frame provided")
@@ -58,15 +65,10 @@ plot_coessential_genes <- function(result_df = NULL, inflection_df = NULL, label
       dplyr::slice(1:label_n) %>%
       dplyr::pull(.data$GeneName_B)
     Label_on_plot <- c(pos_gene, neg_gene)
+  } else {
+    Label_on_plot <- c("")
   }
 
-
-  plot_df <- plot_df %>%
-    dplyr::mutate(
-      Label_on_plot = dplyr::case_when(.data$GeneName_B %in% Label_on_plot ~ TRUE, TRUE ~ FALSE),
-      point_colour = dplyr::case_when(.data$Candidate_gene == TRUE ~ "red", TRUE ~ "grey")
-    )
-
   # get cor. coef of threshold
   pos_inflection_cor <- plot_df %>%
     dplyr::filter(.data$Rank <= inflection_df$Inflection_point_pos_byRank) %>%
@@ -77,6 +79,15 @@ plot_coessential_genes <- function(result_df = NULL, inflection_df = NULL, label
     dplyr::pull(.data$estimate) %>%
     max
 
+  plot_df <- plot_df %>%
+    dplyr::mutate(
+      Label_on_plot = ifelse(.data$GeneName_B %in% Label_on_plot, TRUE, FALSE),
+      Candidate_gene = ifelse(
+        .data$Padj_BH < 0.05 & (.data$estimate > pos_inflection_cor | .data$estimate < neg_inflection_cor),
+        TRUE, FALSE),
+      point_colour = ifelse(.data$Candidate_gene == TRUE, "red", "grey")
+    )
+
   plot <- ggplot2::ggplot(
     plot_df, ggplot2::aes(
       x = .data$Rank, y = .data$estimate, colour = .data$point_colour, label = ifelse(.data$Label_on_plot, .data$GeneName_B, "")

diff --git a/R/plot_screen.R b/R/plot_screen.R
@@ -10,9 +10,11 @@
 #' @md
 #' 
 #' @examples 
-#' \dontrun{
-#' plot_screen(sample_ARID1A_KO_screen, label_genes = TRUE, label_n = 3)
-#' }
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
+#' 
+#' load(paste0(gretta_data_dir,"/sample_22Q2_ARID1A_KO_screen.rda"), envir = environment())
+#' 
+#' plot_screen(screen_results, label_genes = FALSE)
 #' 
 #' @rdname plot_screen
 #' @export 

diff --git a/R/select_cell_lines.R b/R/select_cell_lines.R
@@ -34,31 +34,12 @@
 #' * `Others` cell lines that do not meet above criteria.
 #' 
 #' @examples
-#' \dontrun{
-#' # Looking for TP53 mutants in all cancer cell lines (pan-cancer search)
-#' select_cell_lines(input_gene = "TP53", data_dir = "/path/to/DepMap_data/")
+#' gretta_data_dir <- "/projects/marralab/ytakemon_prj/DepMap/GRETTA_data/22Q2/data"
 #' 
-#' select_cell_lines(
-#' input_gene = "TP53", 
-#' input_aa_change = "R175H", 
-#' data_dir = "/path/to/DepMap_data/")
-#' 
-#' # TP53 mutants only in SCLC subtypes
 #' select_cell_lines(input_gene = "TP53", 
 #' input_disease = "Lung Cancer", 
-#' input_disease_subtype = "Small Cell Lung Cancer (SCLC)",
-#' data_dir = "/path/to/DepMap_data/")
-#' 
-#' select_cell_lines(input_gene = "TP53", 
-#' input_aa_change = "R175H", 
-#' input_disease = "Lung Cancer", 
-#' input_disease_subtype = "Small Cell Lung Cancer (SCLC)",
-#' data_dir = "/path/to/DepMap_data/")
-#' 
-#' # All cancer cell lines that are from Lung Cancers
-#' select_cell_lines(input_disease = "Lung Cancer", data_dir = "/path/to/DepMap_data/")
+#' data_dir = gretta_data_dir)
 #' 
-#' }
 
 select_cell_lines <- function(input_gene = NULL, input_aa_change = NULL, input_disease = NULL, input_disease_subtype = NULL, data_dir = NULL){