#494 - using gene version in key, don't use old GTFs w/o versions

SACGF · Oct 1, 2021 · d014dbe · d014dbe
1 parent 4d8362b
commit d014dbe
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 9 deletions.
diff --git a/genes/management/commands/import_gene_annotation2.py b/genes/management/commands/import_gene_annotation2.py
@@ -96,7 +96,7 @@ def _convert_to_merged_data(self, pyreference_data: Iterable[Dict], most_recent_
                         need_gene = True
 
                 if need_gene:
-                    gene_version[gene_id] = convert_gene_pyreference_to_gene_version_data(gene)
+                    gene_version[gv_accession] = convert_gene_pyreference_to_gene_version_data(gene)
 
             for transcript_accession in transcripts:
                 transcript = prd["transcripts_by_id"][transcript_accession]

diff --git a/genes/scripts/ensembl/download_ensembl_gene_annotation_grch37.sh b/genes/scripts/ensembl/download_ensembl_gene_annotation_grch37.sh
@@ -1,14 +1,7 @@
 #!/bin/bash
 
-# 75 is last GRCh37 in main directory
-for release in 60 65 70 75; do
-  filename=Homo_sapiens.GRCh37.${release}.gtf.gz
-  if [[ ! -e ${filename} ]]; then
-    wget ftp://ftp.ensembl.org/pub/release-${release}/gtf/homo_sapiens/${filename}
-  fi
-done
+# v81 (points to 75) and earlier at GTFs that don't have transcript versions - just skip them
 
-#81 is 75 again
 #82 is first GFF3 for GRCh37
 #83 has no data
 #84 is 82 again