DO january 2024 release

sigven · Feb 8, 2024 · 6b02ef8 · 6b02ef8
1 parent dc49732
commit 6b02ef8
Show file tree

Hide file tree

Showing 7 changed files with 13 additions and 10 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: phenOncoX
 Type: Package
 Title: A phenotype ontology map for cancer
-Date: 2024-01-26
+Date: 2024-02-08
 Version: 0.7.0
 Authors@R: 
     c(person(given = "Sigve",

diff --git a/R/sysdata.rda b/R/sysdata.rda
diff --git a/README.md b/README.md
@@ -40,11 +40,11 @@ For each entry in the final list of phenotype terms, we make cross-mappings
 with phenotype terms from [EFO](https://github.com/EBISPOT/efo), 
 [DO](https://disease-ontology.org/), and the [ICD10 classification](https://www.who.int/standards/classifications/classification-of-diseases).
 
-As of early January 2024, the following ontology versions are used to create the mapping:
+As of early February 2024, the following ontology versions are used to create the mapping:
 
 -   OncoTree (2021_11_02)
 -   Experimental Factor Ontology v3.62.0 (2024-01-15)
--   Disease Ontology (v2023-12-20)
+-   Disease Ontology (v2024-01-31)
 
 **IMPORTANT NOTE**: The mapping established by **phenOncoX** attempts 
 to be comprehensive, but we acknowledge that the presence of missing or 

diff --git a/data-raw/data-raw.R b/data-raw/data-raw.R
@@ -21,7 +21,7 @@ lgr::lgr$appenders$console$set_layout(
 )
 ## Get UMLS / DiseaseOntology / EFO mappings
 umls_map <- map_umls(
-  update = F,
+  update = T,
   basedir = here::here())
 
 icd10_map <- map_icd10(
@@ -40,7 +40,7 @@ efo_map <- map_efo(
   umls_map = umls_map,
   efo_release = metadata$phen_oncox[
     metadata$phen_oncox$source == "Experimental Factor Ontology",]$source_version,
-  update = T,
+  update = F,
   basedir = here::here())
 
 ## Use OncoTree as starting point for phenotype cross-map
@@ -73,7 +73,7 @@ db[['oncotree_core']] <- oncotree_core
 db[['oncotree_expanded']] <- oncotree_expanded
 db[['auxiliary_maps']] <- auxiliary_maps
 
-version_bumped <- "0.6.8"
+version_bumped <- "0.7.1"
 gd_records <- list()
 db_id_ref <- data.frame()
 

diff --git a/data-raw/metadata_phen_oncox.xlsx b/data-raw/metadata_phen_oncox.xlsx
diff --git a/data-raw/phen_oncox_utilities.R b/data-raw/phen_oncox_utilities.R
@@ -171,12 +171,15 @@ map_efo <- function(umls_map,
     }
     if (stringr::str_detect(
       line,
-      "property_value: exactMatch NCIT:")) {
+      "^xref: NCIt:")) {
       nci_t <- stringr::str_replace_all(
         line,
-        "property_value: exactMatch NCIT:","")
+        "xref: NCIt:","")
       nci_all <- c(nci_all, nci_t)
     }
+    if(i %% 10000 == 0){
+      cat(paste0("Processing line: ", i), sep="",'\n')
+    }
     i <- i + 1
   }
 

diff --git a/pkgdown/index.md b/pkgdown/index.md
@@ -40,11 +40,11 @@ For each entry in the final list of phenotype terms, we make cross-mappings
 with phenotype terms from [EFO](https://github.com/EBISPOT/efo), 
 [DO](https://disease-ontology.org/), and the [ICD10 classification](https://www.who.int/standards/classifications/classification-of-diseases).
 
-As of early January 2014, the following ontology versions are used to create the mapping:
+As of early February 2024, the following ontology versions are used to create the mapping:
 
 -   OncoTree (2021_11_02)
 -   Experimental Factor Ontology v3.62.0 (2024-01-15)
--   Disease Ontology (v2023-12-20)
+-   Disease Ontology (v2024-01-31)
 
 The package offers a few pre-processed datasets, along with metadata, that 
 the user can retrieve and use for their own projects or set-ups. The package