From 1d9da184700e52ec9741d8739a04e34040cc735f Mon Sep 17 00:00:00 2001
From: Stephen Watts <hello@stephen.ac>
Date: Sat, 17 Aug 2024 12:58:14 +1000
Subject: [PATCH 1/3] Switch back to new gene panel column names

---
 R/purple.R | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/R/purple.R b/R/purple.R
index 16c00f3..4a358d6 100644
--- a/R/purple.R
+++ b/R/purple.R
@@ -41,7 +41,7 @@ purple_cnv_som_gene_read <- function(x) {
 #'
 #' @param x Path to `purple.cnv.gene.tsv` file.
 #' @param g Path to gene file containing at least three columns:
-#' * `symbol`: gene name (character).
+#' * `ensembl_gene_symbol`: gene name (character).
 #' * `tsgene`: is this gene a tumor suppressor (TRUE/FALSE).
 #' * `oncogene`: is this gene an oncogene (TRUE/FALSE).
 #'
@@ -64,9 +64,9 @@ purple_cnv_som_gene_process <- function(x, g = NULL) {
   }
   genes <-
     readr::read_tsv(g, col_types = readr::cols(
-      symbol = "c", oncogene = "l", tumorsuppressor = "l"
+      ensembl_gene_symbol = "c", oncogene = "l", tumorsuppressor = "l"
     )) |>
-    dplyr::select("symbol", "oncogene", tsgene = "tumorsuppressor")
+    dplyr::select(symbol = "ensembl_gene_symbol", "oncogene", "tsgene")
   oncogenes <- genes |>
     dplyr::filter(.data$oncogene) |>
     dplyr::pull(.data$symbol)

From f261120135501ae8656260055dee03eaf38835ff Mon Sep 17 00:00:00 2001
From: Stephen Watts <hello@stephen.ac>
Date: Sat, 17 Aug 2024 12:59:14 +1000
Subject: [PATCH 2/3] Restore changes for latest PURPLE release

---
 R/purple.R | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/R/purple.R b/R/purple.R
index 4a358d6..b269486 100644
--- a/R/purple.R
+++ b/R/purple.R
@@ -556,7 +556,7 @@ purple_qc_read <- function(x) {
     "QCStatus", "Method", "CopyNumberSegments",
     "UnsupportedCopyNumberSegments", "Purity", "AmberGender",
     "CobaltGender", "DeletedGenes", "Contamination", "GermlineAberrations",
-    "AmberMeanDepth"
+    "AmberMeanDepth", "LohPercent"
   )
 
   assertthat::assert_that(all(purple_qc$key == nm))
@@ -622,7 +622,6 @@ purple_purity_read <- function(x) {
     "maxPloidy", "d",
     "minDiploidProportion", "d",
     "maxDiploidProportion", "d",
-    "version", "c",
     "somaticPenalty", "d",
     "wholeGenomeDuplication", "c",
     "msIndelsPerMb", "d",

From 84af19ed9dfe198c7fc2fcceadbf3d9ff21975e8 Mon Sep 17 00:00:00 2001
From: Stephen Watts <hello@stephen.ac>
Date: Sat, 17 Aug 2024 12:59:32 +1000
Subject: [PATCH 3/3] Fix whitespace and quoting in SV processing

Use of quoting places breakend table entries into a single group
("BND_group") rather expected groups according to BND_group column
values.
---
 R/sv.R | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/R/sv.R b/R/sv.R
index 1803bee..b5fcf69 100644
--- a/R/sv.R
+++ b/R/sv.R
@@ -161,7 +161,7 @@ sash_read_sv_tsv <- function(x) {
 }
 
 split_svs <- function(x) {
-  bps_types <- c("BND", "DEL", "DUP", " INS", "INV")
+  bps_types <- c("BND", "DEL", "DUP", "INS", "INV")
 
   x.grouped <- x |>
     dplyr::group_by(
@@ -186,7 +186,7 @@ join_breakpoint_entries <- function(x) {
   # Group by GRIDSS identifier (clipping trailing h/o [h: High, o: lOwer])
   bps <- x |>
     tidyr::separate("ID", into = c("BND_group", "BND_mate"), sep = -1, convert = TRUE, remove = FALSE) |>
-    dplyr::group_by("BND_group")
+    dplyr::group_by(BND_group)
 
   # Set a sequential breakpoint identifier
   bps_groups <- bps |> dplyr::n_groups()