798448cccf611f094f46094dd1c7bc98d1488358 max Wed Jun 26 03:26:12 2019 -0700 docing hgmd for gbib update, refs #23721 diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt index 813647b..a623ee4 100644 --- src/hg/makeDb/doc/hg19.txt +++ src/hg/makeDb/doc/hg19.txt @@ -32568,30 +32568,32 @@ # with Nature paper pub. V2 revised schema (added ensembl gene ID, additional summary fields) # and color conventions. ########################################################################### # HGMD (updated 01/25/18 max) # got hgmd 2017 from Frank Schacherer Frank.Schacherer@qiagen.com and Rupert Yip Rupert.Yip@qiagen.com # see also the file hg38/hgmd.txt cd /hive/data/genomes/hg19/bed/hgmd cat /hive/data/outside/hgmd/2017.4-hgmd-public.tsv | grep -v \# | tawk '{if ($5=="I") {start=$4-1; end=$4+1; col="100,100,100"} else if ($5=="D") {start=$4-1; end=$4; col="170,170,170"} else {start=$4-1; end=$4; col="0,0,0"}; print "chr"$3,start,end,$2":"$1,0,".",start,end,col,$2,$1,$5}' | sed -e 's/M$/substitution/' | sed -e 's/I$/insertion (between the two basepairs, sequence not provided by HGMD)/' | sed -e 's/D$/deletion (endpoint not provided by HGMD)/' | sed -e 's/X$/insertion-deletion (endpoint not provided by HGMD)/' | sed -e 's/R$/regulatory variant/' | sed -e 's/S$/splicing variant/' | sort -k1,1 -k2,2n > hgmd.bed bedToBigBed hgmd.bed /hive/data/genomes/hg19/chrom.sizes hgmd.bb -type=bed9+ -as=hgmd.as -tab ln -s /hive/data/genomes/hg19/bed/hgmd/hgmd.bb /gbdb/hg19/bbi/hgmd.bb hgBbiDbLink hg19 hgmd /gbdb/hg19/bbi/hgmd.bb # Forgot, finally done Oct 24: also updated hgBeacon bigBedToBed /gbdb/hg19/bbi/hgmd.bb /tmp/temp.bed /usr/local/apache/cgi-bin/hgBeacon -f hgmd temp.bed hgmd +# Forgot, finally done June 26: updated GBIB as qateam +scp /gbdb/hg19/bbi/hgmd.bb hgdownload:/usr/local/apache/gbib/prot/ ########################################################################### 2018-03-08: update UCSC GENCODE V19 to include protein id (for VAI) cd /hive/data/genomes/hg19/bed/gencodeV19/ # move tables that need to be rebuilt mkdir -p prev/pre-proteinId mv tables/wgEncodeGencodeAttrsV19.tab tables/wgEncodeGencodeTagV19.tab prev/pre-proteinId/ mv loaded/wgEncodeGencodeAttrsV19.tab.loaded loaded/wgEncodeGencodeTagV19.tab.loaded prev/pre-proteinId/ # V19 didn't have protein ids in GTF, need to get from ensembl database cd ~/hive/tmp ftp://ftp.ensembl.org/pub/release-74/mysql/homo_sapiens_core_74_37/homo_sapiens_core_74_37.sql.gz ftp://ftp.ensembl.org/pub/release-74/mysql/homo_sapiens_core_74_37/transcript.txt.gz