Merge branch 'main' into addMainPlots

.Rbuildignore

@@ -12,4 +12,11 @@ docs/*
 gimap_QC_Report.html
 gimap_QC_Report.Rmd
 qc_plots
-missing_ids_file.csv
+missing_ids_file.csv
+CODE_OF_CONDUCT.md
+SECURITY.md
+gimap_QC_Report.Rmd
+gimap_QC_Report.html
+gimap_dataset_final.RDS’
+missing_ids_file.csv
+qc_plots/*

.github/workflows/R-CMD-check.yaml

@@ -41,7 +41,8 @@ jobs:
 
       - name: Query dependencies
         run: |
-          install.packages('remotes')
+          install.packages('remotes', repos='http://cran.us.r-project.org')
+          install.packages('rcmdcheck', repos='http://cran.us.r-project.org')
           saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
           writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
         shell: Rscript {0}
@@ -68,26 +69,13 @@ jobs:
           remotes::install_cran("rcmdcheck")
         shell: Rscript {0}
 
-      - name: Check
-        run: |
-          options(crayon.enabled = TRUE)
-          rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), check_dir = "check")
-        shell: Rscript {0}
-
-      - name: Check testthat
-        if: runner.os != 'Windows'
-        id: check_check
-        run: |
-            error_num=$(Rscript --vanilla '.github/workflows/check_testthat.R')
-            echo "error_num=$error_num" >> $GITHUB_OUTPUT
-
-      - name: Stop if there are errors!
-        if: ${{ steps.check_check.outputs.error_num != '0' }}
-        run: exit 1
+      - name: Check package
+        uses: r-lib/actions/check-r-package@v2
+        with:
+          args: 'c("--no-manual")'
 
       - name: Upload check results
         if: failure()
         uses: actions/upload-artifact@main
         with:
-          name: ${{ runner.os }}-r${{ matrix.config.r }}-results
           path: check

DESCRIPTION

@@ -17,7 +17,7 @@ Authors@R: c(
     )
     )
 Description: This package allows a pipeline to be built for analyzing genetic interactions of paired guide CRISPR screens. It is based off of original research from the Alice Berger lab at Fred Hutchinson Cancer Center.
-License: GPL-3
+License: GPL-3 + file LICENSE
 URL: https://github.com/FredHutch/gimap
 BugReports: https://github.com/FredHutch/gimap/issues
 Imports:

NAMESPACE

@@ -29,15 +29,12 @@ importFrom(magrittr,"%>%")
 importFrom(pheatmap,pheatmap)
 importFrom(purrr,map)
 importFrom(purrr,reduce)
-importFrom(readr,write_rds)
-importFrom(readr,write_tsv)
 importFrom(stats,cor)
 importFrom(stats,p.adjust)
 importFrom(stats,quantile)
 importFrom(stats,t.test)
 importFrom(stats,var)
 importFrom(stats,wilcox.test)
-importFrom(stringr,str_split)
 importFrom(stringr,word)
 importFrom(tidyr,pivot_longer)
 importFrom(tidyr,pivot_wider)

R/03-annotate.R

@@ -89,7 +89,7 @@ gimap_annotate <- function(.data = NULL,
     # Read in the CN data
     depmap_cn <- readr::read_csv(cn_file,
       show_col_types = FALSE,
-      col_select = c("genes", my_depmap_id)
+      col_select = c("genes", dplyr::all_of(my_depmap_id))
     ) %>%
       dplyr::rename(log2_cn = my_depmap_id)
 

R/04-normalize.R

@@ -44,7 +44,7 @@
 #'   gimap_filter() %>%
 #'   gimap_annotate(cell_line = "HELA") %>%
 #'   gimap_normalize(
-#'     timepoints = "day",
+#'     timepoints = "day"
 #'   )
 #'
 #' # To see results

R/06-calculate_gi.R

@@ -26,7 +26,7 @@
 #' @param .data Data can be piped in with tidyverse pipes from function to function. But the data must still be a gimap_dataset
 #' @param gimap_dataset A special dataset structure that is setup using the `setup_data()` function.
 #' @export
-#' @examples {
+#' @examples \dontrun{
 #'   gimap_dataset <- get_example_data("gimap")
 #'
 #'   # Highly recommended but not required
@@ -171,7 +171,8 @@ calc_gi <- function(.data = NULL,
 #' Do tests for each replicate --an internal function used by calc_gi() function
 #' @description Create results table that has t test p values
 #' @param replicate a name of a replicate to filter out from gi_calc_adj
-#' @param gi_calc_adj a data.frame with adjusted gi scores
+#' @param gi_calc_single a data.frame with adjusted single gi scores
+#' @param gi_calc_double a data.frame with adjusted double gi scores
 #' @importFrom stats p.adjust t.test wilcox.test
 gimap_rep_stats <- function(replicate, gi_calc_double,  gi_calc_single) {
   ## get a vector of GI scores for all single-targeting ("control") pgRNAs for each rep

R/missing_ids_file.csv

@@ -0,0 +1 @@
+missing_ids

R/utils.R

@@ -1,21 +1,24 @@
 utils::globalVariables(c(
-  "timepoints", "value", "timepoint_avg", "target_type",
+  "mean_observed_cs", "timepoints", "value", "timepoint_avg", "target_type",
   "unexpressed_ctrl_flag", "median", "lfc_adj", "median", "gRNA1_seq", "gRNA2_seq",
   "control_gRNA_seq", "crispr_score", "pgRNA_target", "mean_double_control_crispr",
-  "pgRNA_target", "targeting_gRNA_seq", "mean_single_target_crispr", "double_crispr_score",
-  "single_crispr_score_1", "single_crispr_score_2", "pgRNA_target_double", "mean_single_target_crispr_1",
-  "mean_single_target_crispr_2", "mean_double_control_crispr_2", "pgRNA_target_double",
+  "pgRNA_target", "targeting_gRNA_seq", "mean_single_crispr", "double_crispr_score",
+  "single_crispr_score_1", "single_crispr_score_2", "pgRNA_target_double", "mean_single_crispr_1",
+  "mean_single_crispr_2", "mean_double_control_crispr_2",
   "expected_crispr", "term", "estimate", "mean_expected_crispr", "intercept", "slope",
-  "p_val_ttest", "p_val_wil", "fde_vals_ttest", "fdr_vals_wil", "double_target_gi_score",
-  "single_target_gi_score_1", "single_target_gi_score_2", "gene", "DepMap_ID",
+  "p_val_ttest", "p_val_wil", "fde_vals_ttest", "fdr_vals_wil", "double_gi_score",
+  "single_gi_score_1", "single_gi_score_2", "gene", "DepMap_ID",
   "gene1_symbol", "gene2_symbol", "expressed_flag", "norm_ctrl_flag", "bool_vals",
   "filter_name", "counts", "numzero", "name", "value", "lfc_plasmid_vs_late", "lfc_adj",
-  "pg_RNA_target_double", "double_target_gi_score", "count_normalized", "construct",
+   "double_gi_score", "count_normalized", "construct",
   "filterFlag", "plasmid_log2_cpm", "log2_cpm", "gene_symbol", "gene_symbol_1", "gene_symbol_2",
   "mean_double_control_crispr_1", "expected_crispr_double", "expected_crispr_single_1",
   "expected_crispr_single_2", "fdr_vals_ttest", "read_table", "stripped_cell_line_name",
   "comparison", ".", "col_names", "lfc_adj1", "t.test", "wilcox.test", "p.adjust",
-  "cor", "quantile", "var", "browseURL", "mean_expected_single_crispr", "expected_crispr_single"
+  "cor", "quantile", "var", "browseURL", 'single_crispr', "mean_single_crispr_2",
+  "mean_single_crispr_1", "expected_single_crispr", "double_crispr", "double_gi_score",
+  "fdr", "lfc",  "mean_expected_cs", "mean_gi_score", "mean_single_crispr",
+  "expected_double_crispr", "p_val", "single_gi_score"
 ))
 
 
@@ -89,76 +92,6 @@ get_example_data <- function(which_data) {
   }
 }
 
-#' @import ggplot2
-
-## ggplot themes
-## see: https://www.rdocumentation.org/packages/ggplot2/versions/2.1.0/topics/theme_update
-## and https://stackoverflow.com/questions/23173915/can-ggplot-theme-formatting-be-saved-as-an-object
-plot_theme <- function() {
-  theme(
-    axis.text = element_text(colour = "black"),
-    axis.ticks = element_line(color = "black")
-  )
-}
-
-#' @import ggplot2
-plot_options <- function() {
-  list(theme_bw(base_size = 12))
-}
-
-#' @import kableExtra
-print_kbl <- function(tbl) {
-  kbl(tbl) %>%
-    kable_styling(
-      full_width = FALSE,
-      position = "left",
-      bootstrap_options = c("striped", "hover", "responsive")
-    )
-}
-
-#' Save tbl
-#' @description This function saves table
-#' @importFrom stringr str_split
-#' @importFrom readr write_tsv write_rds
-save_tbl <- function(tbl, out_dir = NULL, params = NULL) {
-  tbl_str <- deparse(substitute(tbl))
-  tbl_name <- str_split(tbl_str, pattern = "\\.")[[1]][2]
-  write_tsv(tbl, file.path(out_dir, "tables", "tsv", paste0(params$cell_line, "_", tbl_name, ".txt")))
-  write_rds(tbl, file.path(out_dir, "tables", "rds", paste0("d.", params$cell_line, "_", tbl_name)))
-}
-
-#' @import ggplot2
-save_plot <- function(plt, out_dir = NULL, params = list(cell_line = NULL)) {
-  plt_str <- deparse(substitute(plt))
-  if (!dir.exists(file.path(out_dir, "plots", "pdf"))) {
-    dir.create(file.path(out_dir, "plots", "pdf"), recursive = TRUE)
-  }
-  ggsave(
-    plot = plt,
-    filename = file.path(out_dir, "plots", "pdf", paste0(params$cell_line, "_", plt_str, ".pdf"))
-  )
-  if (!dir.exists(file.path(out_dir, "plots", "png"))) {
-    dir.create(file.path(out_dir, "plots", "png"), recursive = TRUE)
-  }
-  ggsave(
-    plot = plt,
-    filename = file.path(out_dir, "plots", "png", paste0(params$cell_line, "_", plt_str, ".png"))
-  )
-}
-
-make_out_dir <- function(out_dir) {
-  if (dir.exists(out_dir)) {
-    ## print a message with the output directory location
-    print(paste("Output directory already exists at:", out_dir, sep = " "))
-  } else {
-    ## make output dirs
-    dir.create(file.path(out_dir, "tables", "rds"), recursive = TRUE)
-    dir.create(file.path(out_dir, "tables", "tsv"), recursive = TRUE)
-    dir.create(file.path(out_dir, "plots", "png"), recursive = TRUE)
-    dir.create(file.path(out_dir, "plots", "pdf"), recursive = TRUE)
-    print(paste("Output directory created at:", out_dir, sep = " "))
-  }
-}
 
 #' Get file path to an default credentials RDS
 #' @export

README.md

@@ -135,7 +135,7 @@ Now you can [go to our quick start tutorial to get started!](https://fredhutch.g
 We also have tutorial examples that show how to run timepoint or treatment experimental set ups with gimap:
 
 - [Timepoint example](https://fredhutch.github.io/gimap/articles/timepoint-example.html)
-- [Treatment example](https://fredhutch.github.io/gimap/articles/treatment-example.html)
+- [Treatment example](https://fredhutch.github.io/gimap/articles/treatment_example.html)
 
 Follow the steps there that will walk you through the example data. Then you can tailor that tutorial to use your own data.