adding cds_start

sigven · Sep 13, 2024 · c2ebb1c · c2ebb1c
1 parent d5c4cb2
commit c2ebb1c
Show file tree

Hide file tree

Showing 5 changed files with 28 additions and 3 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,8 @@
+# Version 0.9.9
+
+- Updated NCBI gene information
+- Added `cds_start` to GENCODE transcripts
+
 # Version 0.9.7
 
 - fixed bug in Entrez gene identifiers (grch37)

diff --git a/R/sysdata.rda b/R/sysdata.rda
diff --git a/data-raw/custom_gene_aliases.tsv b/data-raw/custom_gene_aliases.tsv
@@ -15,6 +15,7 @@ KIT	c-Kit	3815
 KIT	c-kit	3815
 MYC	c-MYC	4609
 MTOR	mTOR	2475
+RPTOR	RAPTOR	57521
 MYCN	N-MYC	4613
 ROS1	ROS-1	6098
 CD274	B7-H1	29126

diff --git a/data-raw/data-raw.R b/data-raw/data-raw.R
@@ -270,7 +270,7 @@ for(vbump in c('major','minor','patch')){
 
 bump_version_level <- "patch"
 #version_bump <- version_bumps[[bump_version_level]]
-version_bump <- "0.9.7"
+version_bump <- "0.9.9"
 
 gd_records <- list()
 db_id_ref <- data.frame()

diff --git a/data-raw/utils_gencode_annotation.R b/data-raw/utils_gencode_annotation.R
@@ -74,7 +74,21 @@ gencode_get_transcripts <-
     #https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_45/gencode.v45.chr_patch_hapl_scaff.annotation.gtf.gz
 
     options(timeout = 10000000)
-    gencode_gtf_transcripts <- valr::read_gtf(remote_gtf_all) |>
+    gencode_gtf_all <- valr::read_gtf(remote_gtf_all)
+
+    cds_start_positions <- gencode_gtf_all |>
+      dplyr::filter(.data$type == "start_codon" & phase == 0) |>
+      dplyr::mutate(cds_start = dplyr::if_else(
+        .data$strand == "-", 
+        as.numeric(.data$end),
+        as.numeric(.data$start)
+      )) |>
+      dplyr::select(c("transcript_id", "cds_start")) |>
+      dplyr::rename(
+        ensembl_transcript_id_full = "transcript_id") |>
+      dplyr::distinct()
+
+    gencode_gtf_transcripts <- gencode_gtf_all |>
       dplyr::filter(type == "transcript")
 
     if(gencode_version == 19){
@@ -147,7 +161,11 @@ gencode_get_transcripts <-
       )) |>
       dplyr::filter(!is.na(ensembl_gene_id) &
         !is.na(ensembl_transcript_id)) |>
-      dplyr::distinct()
+      dplyr::distinct() |>
+      dplyr::left_join(
+        cds_start_positions, 
+        by = "ensembl_transcript_id_full"
+      )
 
     #
     lgr::lgr$info(paste0(
@@ -309,6 +327,7 @@ gencode_get_transcripts <-
         end,
         transcript_start,
         transcript_end,
+        cds_start,
         strand,
         ensembl_gene_id,
         ensembl_gene_id_full,