d52cbc57618c1635024918518f864f9a5f79ca12 max Tue Dec 10 03:52:17 2019 -0800 updating HGMD to 2019 version, refs #24625 diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt index f229b37..4cff0d1 100644 --- src/hg/makeDb/doc/hg19.txt +++ src/hg/makeDb/doc/hg19.txt @@ -32561,35 +32561,37 @@ # # this caused a load problem. One instance in the entire file where tissues not combined, ugh chr21 45650008 45650009 rs56323213 5 ENSG00000160223.12 ICOSLG -10840 -0.484 - 0 1 skinExposed, -0.484, 7.064, 0.005, chr21 45650008 45650008 rs145424134 8 ENSG00000160223.12 ICOSLG -10841 -0.070 - 0 1 esophagusMuscular, -0.070, 5.106, 0.008, # refine generated trackDb.gtexEqtl.ra file and install in makeDb/trackDb/human/hg19 ######## # Load 44 per-tissue tracks: gtexEqtlTissue csh $bin/getxEqtlLoadTissues.csh UCSC_output >&! loadTissuesV2.log & #NOTE: V2 was a second release that followed immediately after first release (which was timed to coincide # with Nature paper pub. V2 revised schema (added ensembl gene ID, additional summary fields) # and color conventions. ########################################################################### +# HGMD (updated 12/10/19 max) # 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 +year=2019 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$/splicing variant/' | sort -k1,1 -k2,2n > hgmd.bed +cat /hive/data/outside/hgmd/$year.4-hgmd-public_hg19.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