more curation

sigven · Jan 30, 2024 · 36eccb3 · 36eccb3
1 parent f49baa0
commit 36eccb3
Show file tree

Hide file tree

Showing 9 changed files with 54 additions and 27 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,7 +2,7 @@ Package: pharmOncoX
 Type: Package
 Title: Molecularly targeted cancer drugs and biomarkers
 Version: 1.5.4
-Date: 2024-01-28
+Date: 2024-01-30
 Authors@R: 
     c(person(given = "Sigve",
              family = "Nakken",

diff --git a/NEWS.md b/NEWS.md
@@ -1,9 +1,9 @@
-# Version 1.5.4 (January 29th 2024)
+# Version 1.5.5 (January 30th 2024)
 
 * Refine possible values in `treatment_category` argument to `get_drugs()` function
 * Fix anti-androgen classification
 * Fixed bug in alias type notation for copy numbers and expression biomarkers
-* Filter noise in output from `get_targeted_agents`
+* Filter noise and rank output in helper function `get_targeted_drugs`
 
 # Version 1.5.0 (January 25th 2024)
 

diff --git a/R/helpers.R b/R/helpers.R
@@ -38,6 +38,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
                     "drug_approved_indication",
                     "drug_cancer_relevance",
                     "drug_frac_cancer_indications",
+                    "drug_year_first_approval",
                     "drug_clinical_id",
                     "disease_efo_id",
                     "disease_efo_label",
@@ -71,6 +72,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
                       .data$atc_treatment_category,
                       .data$drug_cancer_relevance,
                       .data$drug_frac_cancer_indications,
+                      .data$drug_year_first_approval,
                       .data$nci_concept_definition) |>
       dplyr::summarise(
         drug_clinical_id =
@@ -138,6 +140,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
                     "max_all_phase",
                     "drug_frac_cancer_indications",
                     "drug_cancer_relevance",
+                    "drug_year_first_approval",
                     "approved_indication",
                     "drug_indication_label")) |>
       dplyr::rename(drug_primary_site = primary_site,
@@ -170,6 +173,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
                       .data$drug_max_phase_indication > 2) |>
       dplyr::distinct() |>
       dplyr::arrange(dplyr::desc(.data$drug_max_phase_indication),
+                     dplyr::desc(.data$drug_year_first_approval),
                      .data$atc_treatment_category,
                      dplyr::desc(.data$drug_frac_cancer_indications),
                      .data$symbol) |>
@@ -182,6 +186,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
                       .data$drug_max_phase_indication <= 2) |>
       dplyr::distinct() |>
       dplyr::arrange(dplyr::desc(.data$drug_max_phase_indication),
+                     dplyr::desc(.data$drug_year_first_approval),
                      .data$atc_treatment_category,
                      dplyr::desc(.data$drug_frac_cancer_indications),
                      .data$symbol) |>
@@ -202,6 +207,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
         by = c("molecule_chembl_id","drug_name","symbol")) |>
       dplyr::distinct() |>
       dplyr::arrange(dplyr::desc(.data$drug_max_phase_indication),
+                     dplyr::desc(.data$drug_year_first_approval),
                      .data$atc_treatment_category,
                      dplyr::desc(.data$drug_frac_cancer_indications),
                      .data$symbol) |>
@@ -222,6 +228,7 @@ get_targeted_drugs <- function(cache_dir = NA) {
 
     targeted_drugs_per_site[[t]][['other_any_phase']] <- other_any_phase |>
       dplyr::arrange(dplyr::desc(.data$drug_max_phase_indication),
+                     dplyr::desc(.data$drug_year_first_approval),
                      .data$atc_treatment_category,
                      dplyr::desc(.data$drug_frac_cancer_indications),
                      .data$symbol) |>
@@ -292,10 +299,11 @@ get_targeted_drugs <- function(cache_dir = NA) {
   }
 
   all_tt_records <- all_tt_records |>
-    dplyr::filter(!(atc_treatment_category == "cancer_unclassified" & 
-                    drug_cancer_relevance == "by_cancer_condition_otp" & 
-                    drug_frac_cancer_indications < 0.7 & 
-                    approved_indication == F))
+    dplyr::filter(!(.data$atc_treatment_category == "cancer_unclassified" & 
+                    .data$drug_cancer_relevance == "by_cancer_condition_otp" & 
+                    .data$drug_frac_cancer_indications < 0.7 & 
+                    .data$approved_indication == F)) |>
+    dplyr::filter(!stringr::str_detect(.data$symbol,"^RRM"))
 
   return(list('records' = all_tt_records, 
               'metadata' = metadata))

diff --git a/R/sysdata.rda b/R/sysdata.rda
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 &nbsp;
 
-# pharmOncoX <a href="https://sigven.github.io/pharmOncoX/"><img src="man/figures/logo.png" align="right" height="130" width="113"/></a>
+# pharmOncoX <a href="https://sigven.github.io/pharmOncoX/"><img src="man/figures/logo.png" align="right" height="104" width="90"/></a>
 
 **pharmOncoX** is an R package that provides access to targeted and non-targeted cancer drugs, and genomic cancer biomarkers. Cancer drugs include comprehensive annotations per target, drug mechanism-of-action, approval dates, clinical trial phases for various indications etc. Drugs are further classified according to the [Anatomical Therapeutic Chemical (ATC) Classification System](https://www.whocc.no/atc_ddd_index/), enabling a filtering of cancer drugs according to their main types of action.
 

diff --git a/data-raw/data-raw.R b/data-raw/data-raw.R
@@ -179,12 +179,15 @@ raw_biomarkers[['civic']] <-
     compound_synonyms = compound_synonyms,
     datestamp = package_datestamp,
     cache_dir = file.path(path_data_raw, "biomarkers"))
-raw_biomarkers[['cgi']] <- load_cgi_biomarkers(
-  compound_synonyms = compound_synonyms,
-  cache_dir = file.path(path_data_raw, "biomarkers"))
-raw_biomarkers[['mitelmandb']] <- load_mitelman_db(
-  cache_dir = file.path(path_data_raw, "biomarkers"))
-raw_biomarkers[['custom_fusions']] <- load_custom_fusion_db()
+raw_biomarkers[['cgi']] <- 
+  load_cgi_biomarkers(
+    compound_synonyms = compound_synonyms,
+    cache_dir = file.path(path_data_raw, "biomarkers"))
+raw_biomarkers[['mitelmandb']] <- 
+  load_mitelman_db(
+    cache_dir = file.path(path_data_raw, "biomarkers"))
+raw_biomarkers[['custom_fusions']] <- 
+  load_custom_fusion_db()
 
 raw_biomarkers[['custom_fusions']]$variant <- 
   raw_biomarkers[['custom_fusions']]$variant |>

diff --git a/data-raw/drug_utilities.R b/data-raw/drug_utilities.R
@@ -2449,11 +2449,11 @@ assign_drug_category <- function(drug_df = NULL,
              "FORETINIB|FAMITINIB|MOTESANIB|",
              "LESTAURTINIB|OSI-930|PACRITINIB|KW-2449|",
              "CABOZANTINIB|BMS-817378|BMS-794833|",
-             "GOLVATINIB|TAK-593|XL-820|TANDUTINIB|",
+             "GOLVATINIB|TAK-593|XL-820|TANDUTINIB|IMATINIB|",
              "CERDULATINIB|CEP-2563|FEDRATINIB|IBCASERTIB|",
              "VANDETANIB|TESEVATINIB|TARLOXOTINIB|",
              "TAK-285|SKLB1028|PUQUITINIB|KBP5209|REPOTRECTINIB|",
-             "VATALANIB|QUIZARTINIB|BMS-690514|IMATINIB|",
+             "VATALANIB|QUIZARTINIB|BMS-690514|IMATINIB|DASATINIB|",
              "CANERTINIB|CEP-32496|REGORAFENIB|GUSACITINIB|",
              "SU-014813|X-82|XL-999|LINIFANIB|NINGETINIB|",
              "PEXIDARTINIB|RG-1530|SITRAVATINIB|SORAFENIB|SUNITINIB|",
@@ -2508,31 +2508,45 @@ assign_drug_category <- function(drug_df = NULL,
     dplyr::bind_rows(
       dplyr::filter(drugs_non_classified, is.na(target_symbol))) |>
     dplyr::mutate(atc_code_level3 = dplyr::case_when(
-      is.na(atc_code_level3) & 
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
         (!is.na(nci_concept_definition) &
          stringr::str_detect(
            tolower(nci_concept_definition),
            "anthracycline|anthracenedione")) ~ "L01DB",
-      is.na(atc_code_level3) & !stringr::str_detect(drug_entry,"/") &
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        stringr::str_detect(tolower(drug_entry),"hydroxyurea|eniluracil") ~ "L01BA",
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        stringr::str_detect(tolower(drug_entry),"arsenic trioxide") ~ "L01BA",
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        stringr::str_detect(tolower(drug_entry),
+                            "thioguanine|aspacytarabine|aspacytarabine|troxacitabine") ~ "L01BB",
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        !stringr::str_detect(drug_entry,"/| ") &
         stringr::str_detect(drug_entry, "xel$") ~ "L01CD",
-      is.na(atc_code_level3) & !stringr::str_detect(drug_entry,"/") &
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        !stringr::str_detect(drug_entry,"/| ") &
         stringr::str_detect(drug_entry, "platin$") ~ "L01XA",
-      is.na(atc_code_level3) & !is.na(nci_concept_definition) &
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        !is.na(nci_concept_definition) &
         stringr::str_detect(tolower(nci_concept_definition), "anti-estrogen") ~ "L02BA",
-      is.na(atc_code_level3) & !is.na(nci_concept_definition) &
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        !is.na(nci_concept_definition) &
         stringr::str_detect(tolower(nci_concept_definition), "aromatase inhibitor") ~ "L02BG",
-      is.na(atc_code_level3) & !is.na(nci_concept_definition) &
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        !is.na(nci_concept_definition) &
         stringr::str_detect(tolower(nci_concept_definition), "nitrogen mustard") ~ "L01AA",
-      is.na(atc_code_level3) & stringr::str_detect(
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        stringr::str_detect(
         tolower(nci_concept_definition), "purine( nucleoside)? analog") ~ "L01BB",
-      is.na(atc_code_level3) & stringr::str_detect(
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
+        stringr::str_detect(
         tolower(nci_concept_definition), "pyrimidine( nucleoside)? analog") ~ "L01BC",
-      is.na(atc_code_level3) &
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") &
         !is.na(drug_entry) &
         !stringr::str_detect(drug_entry, "/") &
         stringr::str_detect(
           tolower(nci_concept_definition), "vinca alkaloid") ~ "L01CA",
-      is.na(atc_code_level3) & 
+      (is.na(atc_code_level3) | atc_code_level3 == "NA") & 
       ((!is.na(nci_concept_definition) &
           stringr::str_detect(
             tolower(nci_concept_definition),

diff --git a/pkgdown/_pkgdown.yml b/pkgdown/_pkgdown.yml
@@ -13,6 +13,8 @@ template:
          gtag('js', new Date());
          gtag('config', 'G-K1KDXWGEWK');
        </script>
+  bslib:
+    primary: "#BD3039"
 authors:
   Sigve Nakken:
     href: "https://github.com/sigven"

diff --git a/pkgdown/index.md b/pkgdown/index.md
@@ -1,6 +1,6 @@
 &nbsp;
 
-# pharmOncoX <a href="https://sigven.github.io/pharmOncoX/"><img src="man/figures/logo.png" align="right" height="130" width="113"/></a>
+# pharmOncoX <a href="https://sigven.github.io/pharmOncoX/"><img src="man/figures/logo.png" align="right" height="104" width="90"/></a>
 
 **pharmOncoX** provides access to targeted and non-targeted cancer drugs, including comprehensive annotations per target, drug mechanism-of-action, approval dates, clinical trial phases for various indications etc.