#51 - historical GRCh38 - get right URL for alignments

SACGF · Aug 10, 2023 · d755146 · d755146
1 parent 181fa70
commit d755146
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 2 deletions.
diff --git a/generate_transcript_data/gff_parser.py b/generate_transcript_data/gff_parser.py
@@ -462,7 +462,14 @@ def handle_feature(self, feature):
                             self.transcript_proteins[transcript_accession] = genbank
 
                 if transcript_accession:
-                    transcript = self.transcript_data_by_accession[transcript_accession]
+                    transcript = self.transcript_data_by_accession.get(transcript_accession)
+                    if not transcript:
+                        msg = f"Couldn't find transcript data for accession '{transcript_accession}'"
+                        if self.skip_missing_parents:
+                            logging.warning(msg)
+                            self.skipped_features_no_parents[feature.type] += 1
+                            return
+                        raise ValueError(msg)
                     self._handle_transcript_data(transcript_accession, transcript, feature)
             else:
                 # There are so many different transcript ontology terms just taking everything that

diff --git a/generate_transcript_data/refseq_transcripts_grch38.sh b/generate_transcript_data/refseq_transcripts_grch38.sh
@@ -36,7 +36,7 @@ if [[ ! -e ${annotation_filename} ]]; then
   wget ${url} --output-document=${annotation_filename}
 fi
 
-url=https://ftp.ncbi.nlm.nih.gov/genomes/all/annotation_releases/9606/GCF_000001405.40-RS_2023_03/RefSeq_historical_alignments/GCF_000001405.40-RS_2023_03_genomic.gff.gz
+url=https://ftp.ncbi.nlm.nih.gov/genomes/all/annotation_releases/9606/GCF_000001405.40-RS_2023_03/RefSeq_historical_alignments/GCF_000001405.40-RS_2023_03_knownrefseq_alns.gff.gz
 alignments_filename=$(basename $url)
 if [[ ! -e ${alignments_filename} ]]; then
   wget ${url} --output-document=${alignments_filename}