fix anti-androgen classification

NEWS.md

@@ -1,6 +1,7 @@
-# Version 1.5.1 (January 28th 2024)
+# Version 1.5.2 (January 28th 2024)
 
 * Refine possible values in `treatment_category` argument to `get_drugs()` function
+* Fix anti-androgen classification
 
 # Version 1.5.0 (January 25th 2024)
 

R/helpers.R

@@ -40,6 +40,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
  "disease_efo_id",
  "disease_efo_label",
  "primary_site",
+ "drug_type",
  "drug_action_type",
  "nci_concept_definition",
  "drug_name",
@@ -61,6 +62,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
  .data$molecule_chembl_id,
  .data$drug_name,
  .data$drug_action_type,
+ .data$drug_type,
  .data$primary_site,
  .data$drug_link,
  .data$atc_level3,
@@ -123,6 +125,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
  "molecule_chembl_id",
  "symbol",
  "drug_name",
+ "drug_type",
  "drug_action_type",
  "drug_link",
  "atc_level3",

data-raw/drug_utilities.R

@@ -620,11 +620,12 @@ get_atc_drug_classification <- function(
  atc_code_level3 == "L01CD" ~ "Taxanes",
  atc_code_level3 == "L04AX" ~ "Other immunosuppressants",
  atc_code_level3 == "L04AB" ~ "TNF-alpha inhibitors",
- atc_code_level3 == "L02BX" ~ "Other hormone antagonists and related agents",
- atc_code_level3 == "L02AE" ~ "GnRH analogs, endocrine therapy drugs",
+ atc_code_level3 == "L02BX" ~ "Other hormone antagonists",
+ atc_code_level3 == "L02AE" ~ "GnRH analogs",
  atc_code_level3 == "L01XK" ~ "PARP inhibitors",
  atc_code_level3 == "L01XX" ~ "Other antineoplastic agents",
  atc_code_level3 == "L02AX" ~ "Other hormones for endocrine therapy",
+ atc_code_level3 == "L02BB" ~ "Anti-androgens",
  atc_code_level3 == "L01XH" ~ "HDAC inhibitors",
  atc_code_level3 == "L01XG" ~ "Proteasome inhibitors",
  atc_code_level3 == "L01XA" ~ "Platinum compounds",
@@ -2335,6 +2336,13 @@ assign_drug_category <- function(drug_df = NULL,
  target_symbol == "EGFR" &
  !is.na(drug_name) &
  stringr::str_detect(drug_name, "MAB") ~ "L01FE",
+ target_symbol == "ERBB2" &
+ !is.na(drug_name) &
+ stringr::str_detect(drug_name, "MAB") ~ "L01FD",
+ target_symbol == "ERBB2" &
+ (is.na(drug_name) |
+ (!is.na(drug_name) &
+ !stringr::str_detect(drug_name, "MAB"))) ~ "L01EH",
  !is.na(drug_name) &
  drug_name == "SIROLIMUS" ~ "L01EG",
  target_symbol == "EGFR" &
@@ -2425,7 +2433,7 @@ assign_drug_category <- function(drug_df = NULL,
  stringr::str_detect(target_symbol, "^AR$") & 
  (!is.na(nci_concept_definition) &
  stringr::str_detect(
- nci_concept_definition, "androgen receptor")) ~ "L01XXH",
+ nci_concept_definition, "androgen receptor")) ~ "L02BB",
  (target_symbol == "PDCD1" |
  target_symbol == "CD274") ~ "L01FF",
  TRUE ~ as.character(NA)
@@ -2744,6 +2752,16 @@ clean_final_drug_list <- function(drug_df = NULL){
  tolower(nci_concept_definition),
  "a( (synthetic|diagnostic|targeted))?( radio(immuno)conjugate)")
  ) |>
+ dplyr::filter(
+ is.na(drug_action_type) |
+ !stringr::str_detect(tolower(drug_action_type),"vaccine")
+ ) |>
+ dplyr::filter(
+ is.na(nci_concept_definition) |
+ !stringr::str_detect(
+ tolower(nci_concept_definition),
+ "(^(a|any)|cancer|tumor|dna|autologous|cell-based|synthetic|cell|peptide|valent)( cell)? vaccine")
+ ) |>
  dplyr::filter(
  is.na(nci_cd_name) |
  !stringr::str_detect(

vignettes/pharmOncoX.Rmd

@@ -44,14 +44,17 @@ cache_dir <- tempdir()
 
 ## Targeted agents
 
-* Plotted below are key statistics with respect to drug classification
+Plotted below are key statistics with respect to drug classification
 numbers for targeted and chemotherapy agents found in _pharmOncoX_. Existing drug classifications have been retrieved from [ATC](https://www.whocc.no/), and these have been extended with manual addition/curation, and also through the establishment of multiple novel levels in the ATC tree, particularly for targeted therapies. Note that only drugs that are indicated for cancer conditions (as harvested from the Open Targets platform) are considered in the numbers plotted below.
 
+<br>
+
 ```{r targeted_agents, echo = F, eval = T, results="hide"}
 
 drugs <- get_drugs(
  cache_dir = cache_dir,
- treatment_category = c("targeted_therapy_classified"),
+ treatment_category = c("targeted_therapy_classified",
+ "hormone_therapy_classified"),
  output_resolution = "drug",
  drug_action_inhibition = T, drug_source_opentargets = T)
 
@@ -68,7 +71,8 @@ drug_classifications <-
  dplyr::group_by(atc_level3) |>
  dplyr::summarise(n = dplyr::n()) |>
  dplyr::mutate(pct = round(n/sum(n) * 100, digits = 2)) |>
- dplyr::arrange(dplyr::desc(pct))
+ dplyr::arrange(dplyr::desc(pct)) |>
+ dplyr::filter(n >= 2)
 
 p_targeted_classifications <- ggplot2::ggplot(
  data = drug_classifications, ggplot2::aes(x = reorder(atc_level3, pct), y = pct)) + 
@@ -78,7 +82,8 @@ p_targeted_classifications <- ggplot2::ggplot(
  ggplot2::ylab("Percent of targeted agents") + 
  ggplot2::xlab("") +
  ggplot2::scale_y_continuous(breaks=seq(0,12,2)) +
- ggplot2::geom_text(ggplot2::aes(label=n), hjust=1.4, vjust=0.50, color="white", size=4) +
+ ggplot2::geom_text(
+ ggplot2::aes(label=n), hjust=1.4, vjust=0.50, color="white", size=4) +
  ggplot2::theme(
  legend.title = ggplot2::element_blank(),
  axis.text.x = ggplot2::element_text(size = 14, vjust = 0.5),
@@ -102,19 +107,12 @@ p_targeted_classifications
 drugs <- get_drugs(
  cache_dir = cache_dir,
  treatment_category = c("chemo_therapy_classified"),
- output_resolution = "drug",
+ output_resolution = "drug",drug_classified_cancer = T,
  drug_source_opentargets = T)
 
 drug_classifications_chemo <- 
  drugs$records |>
  dplyr::select(drug_name, atc_level3) |>
- dplyr::mutate(
- atc_level3 = stringr::str_replace_all(
- atc_level3, 
- "\\|(Antineovascularisation agents|Selective immunosuppressants)",
- ""
- )
- ) |>
  dplyr::group_by(atc_level3) |>
  dplyr::summarise(n = dplyr::n()) |>
  dplyr::mutate(pct = round(n/sum(n) * 100, digits = 2)) |>
@@ -128,8 +126,9 @@ p_chemo_classifications <- ggplot2::ggplot(
  ggplot2::coord_flip() + 
  ggplot2::ylab("Percent of chemotherapy agents") + 
  ggplot2::xlab("") +
- ggplot2::scale_y_continuous(breaks=seq(0,20,2)) +
- ggplot2::geom_text(ggplot2::aes(label=n), hjust=1.4, vjust=0.50, color="white", size=4) +
+ ggplot2::scale_y_continuous(breaks=seq(0,30,5)) +
+ ggplot2::geom_text(ggplot2::aes(label=n), 
+ hjust=1.4, vjust=0.50, color="white", size=4) +
  ggplot2::theme(
  legend.title = ggplot2::element_blank(),
  axis.text.x = ggplot2::element_text(size = 14, vjust = 0.5),