af06f485943b58470dccd7c832b97042f0c8ddb8 gperez2 Sun Jan 18 21:44:31 2026 -0800 Adding process_hgmd.py script, updating makedoc, and updating the hgmd track, refs #36779 diff --git src/hg/makeDb/doc/hg38/ncbiRefSeq.txt src/hg/makeDb/doc/hg38/ncbiRefSeq.txt index 601a838fce7..b911944d703 100644 --- src/hg/makeDb/doc/hg38/ncbiRefSeq.txt +++ src/hg/makeDb/doc/hg38/ncbiRefSeq.txt @@ -221,30 +221,31 @@ # updated Dec 2020 # updated Aug 2023 # updated May 2024 # updated Dec 2024 year=2024 cd /hive/data/genomes/hg38/bed/ncbiRefSeq.p14.2023-11-23/ # change in 2019: ignore the version numbers, otherwise only 1815 transcripts left, big update by HGMD in 2019? # adding "." so NM_123 doesn't match NM_123123 cat /hive/data/outside/hgmd/$year.4-hgmd-public_hg38.tsv | cut -f7 | cut -d. -f1 | sort -u | awk '{print $1"."}' > hgmdTranscripts.txt zcat process/hg38.curated.gp.gz | fgrep -f hgmdTranscripts.txt - > hgmd.curated.gp hgLoadGenePred -genePredExt hg38 ncbiRefSeqHgmd hgmd.curated.gp # wc -l says: 10772 hgmd.curated.gp for the 2021 version 12602 hgmd.curated.gp for the 2023 version 15167 hgmd.curated.gp for the 2024 version +15691 hgmd.curated.gp for the 2025 version (See hg38/hgmd.txt for details) ############################################################################# # ncbiRefSeq.p13 update (DONE - 2019-12-06 - Hiram) # current version information cat /gbdb/hg38/ncbiRefSeq/ncbiRefSeqVersion.txt # NCBI Homo sapiens Annotation Release 109 (2018-03-29) # Version information from the file: # /hive/data/outside/ncbi/genomes/refseq/vertebrate_mammalian/Homo_sapiens/ # all_assembly_versions/GCF_000001405.39_GRCh38.p13/ # GCF_000001405.39_GRCh38.p13_genomic.gff.gz #!annotation-date 09/05/2019 #!annotation-source NCBI Homo sapiens Updated Annotation Release 109.20190905