Merge pull request #85 from leexgh/hgnc-2023-12

Update HGNC symbol 2023.10

data/Makefile

@@ -155,7 +155,7 @@ $(TMP_DIR)/ensembl_transcript_info.txt: $(TMP_DIR)/$(SPECIES).gff3.gz
 	python ../scripts/transform_gff_to_tsv_for_exon_info_from_ensembl.py $^ $@
 
 # Add HGNC symbols, exons, UTRs, PFAM domains and Uniprot id to Ensembl Transcript
-$(TMP_DIR)/ensembl_biomart_transcripts.json.gz: $(TMP_DIR)/ensembl_biomart_transcripts.txt $(TMP_DIR)/ensembl_transcript_info.txt $(VERSION)/input/ensembl_biomart_pfam.txt $(VERSION)/input/ensembl_biomart_refseq.txt $(VERSION)/input/ensembl_biomart_ccds.txt uniprot/export/$(VERSION)_enst_to_uniprot_mapping_id.txt common_input/isoform_overrides_uniprot.txt common_input/$(MSKCC_ISOFORM_OVERRIDES_FILE_NAME) common_input/hgnc_complete_set_2023-04-01.txt
+$(TMP_DIR)/ensembl_biomart_transcripts.json.gz: $(TMP_DIR)/ensembl_biomart_transcripts.txt $(TMP_DIR)/ensembl_transcript_info.txt $(VERSION)/input/ensembl_biomart_pfam.txt $(VERSION)/input/ensembl_biomart_refseq.txt $(VERSION)/input/ensembl_biomart_ccds.txt uniprot/export/$(VERSION)_enst_to_uniprot_mapping_id.txt common_input/isoform_overrides_uniprot.txt common_input/$(MSKCC_ISOFORM_OVERRIDES_FILE_NAME) common_input/hgnc_complete_set_2023-10.txt
 	python ../scripts/add_domains_hugo_ccds_refseq_exon_info_uniprot_to_ensembl_transcript.py $^ $@
 
 # for mouse a specific recipe without overrides
@@ -165,9 +165,9 @@ $(TMP_DIR)/ensembl_biomart_transcripts_mouse.json.gz: $(TMP_DIR)/ensembl_biomart
 # give default/canonical geneid/transcript based on given hugo symbol takes
 # about 50m to run (TODO: this can be easily optimized)
 # isoform_overrides_genome_nexus.txt is made for genome nexus, others files are generated for vcf2maf
-# Please note: we should keep hgnc_complete_set_2023-04-01 in sync with https://github.com/cBioPortal/datahub-study-curation-tools/blob/master/gene-table-update/build-input-for-importer/hgnc_complete_set.txt
+# Please note: we should keep hgnc_complete_set_2023-10 in sync with https://github.com/cBioPortal/datahub-study-curation-tools/blob/master/gene-table-update/build-input-for-importer/hgnc_complete_set.txt
 # isoform_overrides_oncokb_grch3*.txt is a list of OncoKB transcripts and genes, it's generated by download_oncokb_isoform_overrides.py
-$(TMP_DIR)/ensembl_biomart_canonical_transcripts_per_hgnc.txt: $(TMP_DIR)/ensembl_canonical_data.txt common_input/hgnc_complete_set_2023-04-01.txt common_input/isoform_overrides_uniprot.txt common_input/$(MSKCC_ISOFORM_OVERRIDES_FILE_NAME) common_input/$(GENOME_NEXUS_ISOFORM_OVERRIDES_FILE_NAME) common_input/$(ONCOKB_ISOFORM_OVERRIDES_FILE_NAME) common_input/ignored_genes.txt
+$(TMP_DIR)/ensembl_biomart_canonical_transcripts_per_hgnc.txt: $(TMP_DIR)/ensembl_canonical_data.txt common_input/hgnc_complete_set_2023-10.txt common_input/isoform_overrides_uniprot.txt common_input/$(MSKCC_ISOFORM_OVERRIDES_FILE_NAME) common_input/$(GENOME_NEXUS_ISOFORM_OVERRIDES_FILE_NAME) common_input/$(ONCOKB_ISOFORM_OVERRIDES_FILE_NAME) common_input/ignored_genes.txt
 	python ../scripts/make_one_canonical_transcript_per_gene.py $^ $@
 
 # mouse version. A different script is called that set the canonicals based on Ensembl lookup.

data/common_input/ignored_genes.txt

@@ -903,4 +903,7 @@ smim11b
 mkrn3-as1
 kcne1b
 cbsl
-sik3-it1
+sik3-it1
+upp2-it1
+dnajb5p1
+slc7a2-it1