Merge pull request #339 from MSKCC-Epi-Bio/extract-patient-id

Add extract patient function

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: gnomeR
 Title: Wrangle and analyze IMPACT and TCGA mutation data 
-Version: 1.3.0
+Version: 1.2.0.9004
 Authors@R: 
     c(person(given = "Karissa",
              family = "Whiting",

NAMESPACE

@@ -7,6 +7,7 @@ export(add_pathways)
 export(annotate_any_panel)
 export(annotate_specific_panel)
 export(create_gene_binary)
+export(extract_patient_id)
 export(ggcomut)
 export(gggenecor)
 export(ggsamplevar)

NEWS.md

@@ -1,5 +1,6 @@
 # gnomeR (development version)
 
+- Added `extract_patient_id()` function to get IMPACT patient ID from sample ID
 - Deprecated `freq_cutoff`, `freq_cutoff_by_gene`, and `gene_subset` arguments in `tbl_genomic()`. It is now recommended that users use `subset_by_frequency()` instead before passing data to `tbl_genomic()`.
 - Added `other_vars` argument to `subset_by_frequency()`, `subset_by_panel()`, `summarize_by_gene()` and `add_pathways()` to allow retention of other clinical vars when using functions within pipeline.
 - Deprecated `count_pathways_by` argument of `add_pathways()` function. Now, user must specify which specific alteration to count towards the pathway via the `.mut`, `.Amp`, `.Del`, `.fus` suffix (e.g. `custom_pathways = c('TP53.mut', 'APC.Del)`). 

R/utils.R

@@ -135,7 +135,29 @@ recode_cna <- function(alteration_vector){
   }
 
 
+#' Extract IMPACT Patient ID From Sample ID
+#'
+#' @param sample_id A character vector of IMPACT Tumor sample IDs
+#'
+#' @return Returns a vector of patient IDs
+#' @export
+#'
+#' @examples
+#' sample_id = c("P-0000071-T01-IM3", "P-0000072-T02-IM4", "P-0000073-T03-IM5")
+#' extract_patient_id(sample_id)
+#'
+extract_patient_id <- function(sample_id) {
+
+  # Checks ----------------------------------------------------------------
+  wrong_format <- sample_id[!stringr::str_detect(sample_id, "^P-\\d{1,}-T.*")]
 
+  if (length(wrong_format) > 0) {
+    cli::cli_abort("Some {.code sample_id} values do not match the expected IMPACT sample format (e.g `P-0000XX-T01-IM3`)")
+  }
+
+  patient_id = stringr::str_replace(sample_id, "-T.*", "")
+  return(patient_id)
+}
 
 #' Create binary data.frames depending on type of mutation data
 #'

_pkgdown.yml

@@ -51,6 +51,7 @@ reference:
     - recode_cna
     - rename_columns
     - resolve_alias
+    - extract_patient_id
   - subtitle: Color Palette
   - contents:
     - gnomer_colors

codemeta.json

@@ -8,13 +8,13 @@
   "codeRepository": "https://github.com/MSKCC-Epi-Bio/gnomeR",
   "issueTracker": "https://github.com/MSKCC-Epi-Bio/gnomeR/issues",
   "license": "https://spdx.org/licenses/MIT",
-  "version": "1.3.0",
+  "version": "1.2.0.9004",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",
     "url": "https://r-project.org"
   },
-  "runtimePlatform": "R version 4.2.2 (2022-10-31 ucrt)",
+  "runtimePlatform": "R version 4.2.3 (2023-03-15)",
   "author": [
     {
       "@type": "Person",
@@ -371,7 +371,7 @@
     },
     "SystemRequirements": null
   },
-  "fileSize": "2582.696KB",
+  "fileSize": "2349.143KB",
   "releaseNotes": "https://github.com/MSKCC-Epi-Bio/gnomeR/blob/master/NEWS.md",
   "readme": "https://github.com/MSKCC-Epi-Bio/gnomeR/blob/main/README.md",
   "contIntegration": ["https://github.com/MSKCC-Epi-Bio/gnomeR/actions", "https://app.codecov.io/gh/MSKCC-Epi-Bio/gnomeR?branch=main"],

tests/testthat/test-utils.R

@@ -0,0 +1,13 @@
+
+test_that("test extracting patient_id from sample_id works", {
+
+  expect_no_error(extract_patient_id(gnomeR::mutations[1:10,]$sampleId))
+
+})
+
+test_that("test error thrown when non IMPACT ID", {
+
+  sample_id =  c("P-0000071-T01-IM3", "XX", "P-0000073-T03-IM5")
+  expect_error(extract_patient_id(sample_id))
+
+})