From d112d869f1bd18a88c290e487f651dbeb5695e77 Mon Sep 17 00:00:00 2001
From: Kdreval <k.dreval@gmail.com>
Date: Fri, 22 Nov 2024 10:22:32 -0800
Subject: [PATCH 1/4] cleanup: drop stringr dependency

---
 DESCRIPTION                | 1 -
 NAMESPACE                  | 5 -----
 R/GAMBLR.helpers-package.R | 4 ----
 R/get_gambl_colours.R      | 4 ++--
 R/get_template_wildcards.R | 2 +-
 R/grob_wildcards.R         | 4 ++--
 6 files changed, 5 insertions(+), 15 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index c69cdad..5af1546 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -17,7 +17,6 @@ Imports:
     ggthemes,
     philentropy,
     readr,
-    stringr,
     tibble,
     tidyr,
     workflowr
diff --git a/NAMESPACE b/NAMESPACE
index d9aa630..9433009 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -35,7 +35,6 @@ import(GAMBLR.data)
 import(dplyr)
 import(ggplot2)
 import(readr)
-import(stringr)
 import(tibble)
 import(tidyr)
 import(workflowr)
@@ -45,10 +44,6 @@ importFrom(philentropy,KL)
 importFrom(stats,end)
 importFrom(stats,quantile)
 importFrom(stats,start)
-importFrom(stringr,str_c)
-importFrom(stringr,str_extract)
-importFrom(stringr,str_remove)
-importFrom(stringr,str_remove_all)
 importFrom(tidyr,unnest_auto)
 importFrom(utils,head)
 importFrom(utils,read.csv)
diff --git a/R/GAMBLR.helpers-package.R b/R/GAMBLR.helpers-package.R
index 0af4d14..2c32605 100644
--- a/R/GAMBLR.helpers-package.R
+++ b/R/GAMBLR.helpers-package.R
@@ -7,10 +7,6 @@
 #' @importFrom stats end
 #' @importFrom stats quantile
 #' @importFrom stats start
-#' @importFrom stringr str_c
-#' @importFrom stringr str_extract
-#' @importFrom stringr str_remove
-#' @importFrom stringr str_remove_all
 #' @importFrom tidyr unnest_auto
 #' @importFrom utils head
 #' @importFrom utils read.csv
diff --git a/R/get_gambl_colours.R b/R/get_gambl_colours.R
index dab03b6..c7397ee 100644
--- a/R/get_gambl_colours.R
+++ b/R/get_gambl_colours.R
@@ -18,7 +18,7 @@
 #'
 #' @return A named vector of colour codes for lymphgen classes and pathology.
 #'
-#' @import dplyr stringr tidyr
+#' @import dplyr tidyr
 #' @export
 #'
 #' @examples
@@ -318,7 +318,7 @@ get_gambl_colours = function(classification = "all",
     everything = c(everything, all_colours[[this_group]])
   }
   #return matching value from lowercase version of the argument if it exists
-  lc_class = stringr::str_to_lower(classification)
+  lc_class = tolower(classification)
   if(return_available){
     return(names(all_colours))
   }
diff --git a/R/get_template_wildcards.R b/R/get_template_wildcards.R
index f50d6fd..cc3b46e 100644
--- a/R/get_template_wildcards.R
+++ b/R/get_template_wildcards.R
@@ -16,6 +16,6 @@ get_template_wildcards = function(parent_key,
   }else{
     wildcard_string = config::get(paste0(parent_key,"_wildcards"))[template_key]
   }
-  wildcards = stringr::str_split(wildcard_string,",")
+  wildcards = strsplit(wildcard_string,",")
   return(unlist(wildcards))
 }
diff --git a/R/grob_wildcards.R b/R/grob_wildcards.R
index ab77166..ffa12e1 100644
--- a/R/grob_wildcards.R
+++ b/R/grob_wildcards.R
@@ -8,7 +8,7 @@
 #'
 #' @export
 grob_wildcards = function(wildcarded_string){
-  wildcards = unlist(stringr::str_extract_all(wildcarded_string,"\\{[^\\{]+\\}"))
-  wildcards = stringr::str_remove_all(wildcards,"\\{") %>%  stringr::str_remove_all(.,"\\}")
+  wildcards = unlist(regmatches(wildcarded_string, gregexpr("\\{[^\\{]+\\}", wildcarded_string)))
+  wildcards = gsub("\\{", "", wildcards) %>% gsub("\\}", "", .)
   return(wildcards)
 }

From 2f3ecbc6bc7f89dea46a252e27dc3298a32d50ed Mon Sep 17 00:00:00 2001
From: Kdreval <k.dreval@gmail.com>
Date: Fri, 22 Nov 2024 10:57:12 -0800
Subject: [PATCH 2/4] cleanup: drop philentropy dependency

---
 NAMESPACE                           |  2 +-
 R/GAMBLR.helpers-package.R          |  1 -
 R/compare_coding_mutation_pattern.R | 12 +++++++---
 R/kl_divergence.R                   | 36 ++++++++++++++++++++++++++++
 man/kl_divergence.Rd                | 37 +++++++++++++++++++++++++++++
 5 files changed, 83 insertions(+), 5 deletions(-)
 create mode 100644 R/kl_divergence.R
 create mode 100644 man/kl_divergence.Rd

diff --git a/NAMESPACE b/NAMESPACE
index 9433009..2119e85 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -19,6 +19,7 @@ export(get_template_wildcards)
 export(get_unmatched_normals)
 export(grob_wildcards)
 export(handle_metadata)
+export(kl_divergence)
 export(maf_header)
 export(normalize_expression_data)
 export(rainfall_conv)
@@ -40,7 +41,6 @@ import(tidyr)
 import(workflowr)
 importFrom(dplyr,left_join)
 importFrom(ggthemes,theme_foundation)
-importFrom(philentropy,KL)
 importFrom(stats,end)
 importFrom(stats,quantile)
 importFrom(stats,start)
diff --git a/R/GAMBLR.helpers-package.R b/R/GAMBLR.helpers-package.R
index 2c32605..1dd1b12 100644
--- a/R/GAMBLR.helpers-package.R
+++ b/R/GAMBLR.helpers-package.R
@@ -3,7 +3,6 @@
 
 ## usethis namespace: start
 #' @importFrom dplyr left_join
-#' @importFrom philentropy KL
 #' @importFrom stats end
 #' @importFrom stats quantile
 #' @importFrom stats start
diff --git a/R/compare_coding_mutation_pattern.R b/R/compare_coding_mutation_pattern.R
index 281f090..20a7772 100644
--- a/R/compare_coding_mutation_pattern.R
+++ b/R/compare_coding_mutation_pattern.R
@@ -17,9 +17,9 @@ compare_coding_mutation_pattern = function(maf_df1,maf_df2,gene){
     stop("Must provide the Hugo_Symbol of a single gene that is present in both maf files")
   }
   missense_positions1 = dplyr::filter(maf_df1,Hugo_Symbol==gene,!Variant_Classification %in% c("Silent","Splice_Site","Splice_Region"),Variant_Type=="SNP") %>%
-    pull(HGVSp_Short) %>% str_remove_all("p.\\w") %>% str_extract("\\d+") %>% as.numeric()
+    pull(HGVSp_Short) %>% gsub("p\\.\\w", "", .) %>% regmatches(., regexpr("\\d+", .)) %>% as.numeric()
   missense_positions2 = dplyr::filter(maf_df2,Hugo_Symbol==gene,!Variant_Classification %in% c("Silent","Splice_Site","Splice_Region"),Variant_Type=="SNP") %>%
-    pull(HGVSp_Short) %>% str_remove_all("p.\\w") %>% str_extract("\\d+") %>% as.numeric()
+    pull(HGVSp_Short) %>% gsub("p\\.\\w", "", .) %>% regmatches(., regexpr("\\d+", .)) %>% as.numeric()
  if(length(missense_positions1)==0 | length(missense_positions2)==0 ){
    message(paste("no mutations for",gene,"in one or both data sets"))
    return(list(kl=15))
@@ -35,6 +35,12 @@ compare_coding_mutation_pattern = function(maf_df1,maf_df2,gene){
   all_counts = dplyr::select(full_df,-position) %>% t()
   all_counts[1,]=all_counts[1,]/sum(all_counts[1,])
   all_counts[2,]=all_counts[2,]/sum(all_counts[2,])
-  kl_out = KL(all_counts)
+
+  # Normalize the rows to turn counts into probabilities
+  P <- all_counts[1, ] / sum(all_counts[1, ])
+  Q <- all_counts[2, ] / sum(all_counts[2, ])
+
+  kl_out <- kl_divergence(P, Q)
+
   return(list(df=full_df,kl=unname(kl_out)))
 }
diff --git a/R/kl_divergence.R b/R/kl_divergence.R
new file mode 100644
index 0000000..2fb5291
--- /dev/null
+++ b/R/kl_divergence.R
@@ -0,0 +1,36 @@
+#' Calculate Kullback-Leibler Divergence
+#'
+#' This function computes the Kullback-Leibler (KL) divergence between two
+#'      probability distributions, with an optional small constant (epsilon)
+#'      added to avoid zero probabilities, which would otherwise cause division
+#'      by zero or undefined logarithms.
+#'
+#' @param P A numeric vector representing the first probability distribution.
+#'      The sum of "P" should be 1, but the function will normalize it if
+#'      necessary.
+#' @param Q A numeric vector representing the second probability distribution.
+#'      The sum of "Q" should be 1, but the function will normalize it if
+#'      necessary.
+#' @param epsilon A small positive number (default = 1e-7) to be added to each
+#'      probability in P and Q to avoid zero probabilities. This helps to
+#'      prevent division by zero or log(0).
+#'
+#' @return float
+#'
+#' @examples
+#' P <- c(0.1, 0.4, 0.3, 0.2)
+#' Q <- c(0.2, 0.3, 0.4, 0.1)
+#'
+#' kl_divergence(P, Q)
+#'
+#' @export
+kl_divergence <- function(P, Q, epsilon = 1e-7) {
+    P <- P + epsilon
+    Q <- Q + epsilon
+
+    P <- P / sum(P)
+    Q <- Q / sum(Q)
+
+    # KL divergence formula: sum(P * log(P / Q))
+    return(sum(P * log(P / Q), na.rm = TRUE))
+}
diff --git a/man/kl_divergence.Rd b/man/kl_divergence.Rd
new file mode 100644
index 0000000..5652dbe
--- /dev/null
+++ b/man/kl_divergence.Rd
@@ -0,0 +1,37 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/kl_divergence.R
+\name{kl_divergence}
+\alias{kl_divergence}
+\title{Calculate Kullback-Leibler Divergence}
+\usage{
+kl_divergence(P, Q, epsilon = 1e-07)
+}
+\arguments{
+\item{P}{A numeric vector representing the first probability distribution.
+The sum of "P" should be 1, but the function will normalize it if
+necessary.}
+
+\item{Q}{A numeric vector representing the second probability distribution.
+The sum of "Q" should be 1, but the function will normalize it if
+necessary.}
+
+\item{epsilon}{A small positive number (default = 1e-7) to be added to each
+probability in P and Q to avoid zero probabilities. This helps to
+prevent division by zero or log(0).}
+}
+\value{
+float
+}
+\description{
+This function computes the Kullback-Leibler (KL) divergence between two
+probability distributions, with an optional small constant (epsilon)
+added to avoid zero probabilities, which would otherwise cause division
+by zero or undefined logarithms.
+}
+\examples{
+P <- c(0.1, 0.4, 0.3, 0.2)
+Q <- c(0.2, 0.3, 0.4, 0.1)
+
+kl_divergence(P, Q)
+
+}

From 0050e497422ea4574c9b69a96265e90fa98e4440 Mon Sep 17 00:00:00 2001
From: Kdreval <k.dreval@gmail.com>
Date: Fri, 22 Nov 2024 11:15:14 -0800
Subject: [PATCH 3/4] clenaup: switch to consistent import definition

---
 DESCRIPTION                         |  1 -
 NAMESPACE                           | 11 -----------
 R/GAMBLR.helpers-package.R          | 17 -----------------
 R/compare_coding_mutation_pattern.R |  1 +
 R/gene_mutation_tally.R             |  1 +
 R/sanity_check_metadata.R           |  2 +-
 man/GAMBLR.helpers-package.Rd       | 15 ---------------
 7 files changed, 3 insertions(+), 45 deletions(-)
 delete mode 100644 R/GAMBLR.helpers-package.R
 delete mode 100644 man/GAMBLR.helpers-package.Rd

diff --git a/DESCRIPTION b/DESCRIPTION
index 5af1546..e33c01b 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -15,7 +15,6 @@ Imports:
     GAMBLR.data,
     ggplot2,
     ggthemes,
-    philentropy,
     readr,
     tibble,
     tidyr,
diff --git a/NAMESPACE b/NAMESPACE
index 2119e85..ad6b74c 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -39,15 +39,4 @@ import(readr)
 import(tibble)
 import(tidyr)
 import(workflowr)
-importFrom(dplyr,left_join)
 importFrom(ggthemes,theme_foundation)
-importFrom(stats,end)
-importFrom(stats,quantile)
-importFrom(stats,start)
-importFrom(tidyr,unnest_auto)
-importFrom(utils,head)
-importFrom(utils,read.csv)
-importFrom(utils,read.socket)
-importFrom(utils,tail)
-importFrom(utils,write.socket)
-importFrom(utils,write.table)
diff --git a/R/GAMBLR.helpers-package.R b/R/GAMBLR.helpers-package.R
deleted file mode 100644
index 1dd1b12..0000000
--- a/R/GAMBLR.helpers-package.R
+++ /dev/null
@@ -1,17 +0,0 @@
-#' @keywords internal
-"_PACKAGE"
-
-## usethis namespace: start
-#' @importFrom dplyr left_join
-#' @importFrom stats end
-#' @importFrom stats quantile
-#' @importFrom stats start
-#' @importFrom tidyr unnest_auto
-#' @importFrom utils head
-#' @importFrom utils read.csv
-#' @importFrom utils read.socket
-#' @importFrom utils tail
-#' @importFrom utils write.socket
-#' @importFrom utils write.table
-## usethis namespace: end
-NULL
diff --git a/R/compare_coding_mutation_pattern.R b/R/compare_coding_mutation_pattern.R
index 20a7772..2ea0d72 100644
--- a/R/compare_coding_mutation_pattern.R
+++ b/R/compare_coding_mutation_pattern.R
@@ -8,6 +8,7 @@
 #'
 #' @return list
 #'
+#' @import dplyr
 #' @export
 compare_coding_mutation_pattern = function(maf_df1,maf_df2,gene){
   if(missing(maf_df1) | missing(maf_df2)){
diff --git a/R/gene_mutation_tally.R b/R/gene_mutation_tally.R
index 10f0964..32a3aec 100644
--- a/R/gene_mutation_tally.R
+++ b/R/gene_mutation_tally.R
@@ -17,6 +17,7 @@
 #'
 #' @return data frame
 #'
+#' @import dplyr
 #' @export
 gene_mutation_tally = function(maf_df,these_samples_metadata,these_genes,grouping_variable="cohort"){
   meta = dplyr::select(these_samples_metadata,sample_id,{{grouping_variable}})
diff --git a/R/sanity_check_metadata.R b/R/sanity_check_metadata.R
index 0faa1f4..8a1b461 100644
--- a/R/sanity_check_metadata.R
+++ b/R/sanity_check_metadata.R
@@ -6,7 +6,7 @@
 #'
 #' @return A table.
 #'
-#' @import tibble readr dplyr
+#' @import tibble readr dplyr tidyr
 #'
 #'
 #' @examples
diff --git a/man/GAMBLR.helpers-package.Rd b/man/GAMBLR.helpers-package.Rd
deleted file mode 100644
index 90c6164..0000000
--- a/man/GAMBLR.helpers-package.Rd
+++ /dev/null
@@ -1,15 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/GAMBLR.helpers-package.R
-\docType{package}
-\name{GAMBLR.helpers-package}
-\alias{GAMBLR.helpers}
-\alias{GAMBLR.helpers-package}
-\title{GAMBLR.helpers: Provide helper functions for GAMBLR-based packages}
-\description{
-This package is part of the Genomic Analysis of Mature B-cell Lymphomas (GAMBL) project developed by the Morin Lab.
-}
-\author{
-\strong{Maintainer}: Vladimir Souza \email{vsouza@bcgsc.ca}
-
-}
-\keyword{internal}

From 2dda8459598618453105a854614187e7874cbb3d Mon Sep 17 00:00:00 2001
From: Kdreval <k.dreval@gmail.com>
Date: Fri, 22 Nov 2024 12:31:22 -0800
Subject: [PATCH 4/4] cleanup: remove workflowr

---
 DESCRIPTION                      |  3 +--
 NAMESPACE                        |  2 --
 R/web_initialize_gambl_site.R    | 22 ----------------------
 man/web_initialize_gambl_site.Rd | 25 -------------------------
 4 files changed, 1 insertion(+), 51 deletions(-)
 delete mode 100644 R/web_initialize_gambl_site.R
 delete mode 100644 man/web_initialize_gambl_site.Rd

diff --git a/DESCRIPTION b/DESCRIPTION
index e33c01b..ac813c6 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -17,8 +17,7 @@ Imports:
     ggthemes,
     readr,
     tibble,
-    tidyr,
-    workflowr
+    tidyr
 Remotes:
     morinlab/GAMBLR.data
 Encoding: UTF-8
diff --git a/NAMESPACE b/NAMESPACE
index ad6b74c..6b5fe8a 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -31,12 +31,10 @@ export(subset_cnstates)
 export(theme_Morons)
 export(trim_scale_expression)
 export(vc_nonSynonymous)
-export(web_initialize_gambl_site)
 import(GAMBLR.data)
 import(dplyr)
 import(ggplot2)
 import(readr)
 import(tibble)
 import(tidyr)
-import(workflowr)
 importFrom(ggthemes,theme_foundation)
diff --git a/R/web_initialize_gambl_site.R b/R/web_initialize_gambl_site.R
deleted file mode 100644
index a781ee4..0000000
--- a/R/web_initialize_gambl_site.R
+++ /dev/null
@@ -1,22 +0,0 @@
-#' @title Web Initialize GAMBL Site.
-#'
-#' @description Set up a fresh instance of a website to host on gitlab.
-#'
-#' @param site_base_name Base name for site.
-#' @param base_directory Path to base directory.
-#' @param my_name My name.
-#' @param my_gitlab_email The email used for gitlab.
-#'
-#' @import workflowr
-#'
-#' @export
-web_initialize_gambl_site = function(site_base_name,
-                                     base_directory = "/home/rmorin/",
-                                     my_name = "Ryan Morin",
-                                     my_gitlab_email = "rdmorin@sfu.ca"){
-
-  wflow_git_config(user.name = my_name, user.email = my_gitlab_email)
-  setwd(base_directory)
-  wflow_start(site_base_name)
-  wflow_build()
-}
diff --git a/man/web_initialize_gambl_site.Rd b/man/web_initialize_gambl_site.Rd
deleted file mode 100644
index 66a8b9b..0000000
--- a/man/web_initialize_gambl_site.Rd
+++ /dev/null
@@ -1,25 +0,0 @@
-% Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/web_initialize_gambl_site.R
-\name{web_initialize_gambl_site}
-\alias{web_initialize_gambl_site}
-\title{Web Initialize GAMBL Site.}
-\usage{
-web_initialize_gambl_site(
-  site_base_name,
-  base_directory = "/home/rmorin/",
-  my_name = "Ryan Morin",
-  my_gitlab_email = "rdmorin@sfu.ca"
-)
-}
-\arguments{
-\item{site_base_name}{Base name for site.}
-
-\item{base_directory}{Path to base directory.}
-
-\item{my_name}{My name.}
-
-\item{my_gitlab_email}{The email used for gitlab.}
-}
-\description{
-Set up a fresh instance of a website to host on gitlab.
-}