4ef2450efd0812268ae30457f8c5d2494821e5a3
max
Thu Dec 5 04:56:51 2024 -0800
HGMD 2024 update, refs #34903
diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt
index 73a5eb3..10a8186 100644
--- src/hg/makeDb/doc/hg19.txt
+++ src/hg/makeDb/doc/hg19.txt
@@ -32185,59 +32185,63 @@
# refine generated trackDb.gtexEqtl.ra file and install in makeDb/trackDb/human/hg19
########
# Load 44 per-tissue tracks: gtexEqtlTissue<tissueName>
csh $bin/getxEqtlLoadTissues.csh UCSC_output >&! loadTissuesV2.log &
#NOTE: V2 was a second release that followed immediately after first release (which was timed to coincide
# with Nature paper pub. V2 revised schema (added ensembl gene ID, additional summary fields)
# and color conventions.
###########################################################################
# HGMD (updated 12/10/19 max)
# HGMD (updated 01/25/18 max)
# HGMD (updated 12/12/20 max)
# HGMD (updated 08/18/23 max)
-# HGMD (updated 05/28/24 max)
-# got hgmd from Frank Schacherer Frank.Schacherer@qiagen.com and Rupert Yip Rupert.Yip@qiagen.com
+# HGMD (updated 05/28/24 max) from Elias.Hage@qiagen.com
+# HGMD (updated 12/05/24 max) from Elias.Hage@qiagen.com
+# got hgmd from Frank Schacherer Frank.Schacherer@qiagen.com
# see also the file hg38/hgmd.txt
-# Got it from Georgios.Stamoulis@qiagen.com, Georgius left
-# Got it from Elias.Hage@qiagen.com
-year=2023
+year=2024
cd /hive/data/genomes/hg19/bed/hgmd
cat /hive/data/outside/hgmd/$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$/splicing variant/' | sort -k1,1 -k2,2n > hgmd.bed
bedToBigBed hgmd.bed /hive/data/genomes/hg19/chrom.sizes hgmd.bb -type=bed9+ -as=hgmd.as -tab
ln -s /hive/data/genomes/hg19/bed/hgmd/hgmd.bb /gbdb/hg19/bbi/hgmd.bb
hgBbiDbLink hg19 hgmd /gbdb/hg19/bbi/hgmd.bb
-# Forgot, finally done Oct 24: also updated hgBeacon
+wc -l hgmd.bed
+# 2024: 301348 lines in hgmd.bed
+# update hgBeacon
bigBedToBed /gbdb/hg19/bbi/hgmd.bb /tmp/temp.bed
python2 /usr/local/apache/cgi-bin/hgBeacon -f hgmd /tmp/temp.bed hgmd
# Forgot, finally done June 26: updated GBIB as qateam
+ssh qateam
scp /gbdb/hg19/bbi/hgmd.bb hgdownload:/usr/local/apache/htdocs/gbib/prot/
+exit
# next restrict RefSeq down to HGMD subset
-# addition of HGMD-restricted subset, Max, Jan 29 2019, updated Dec 10 2019, again Aug 2023, May 2024
-cd /hive/data/genomes/hg19/bed/ncbiRefSeq.p13.2022-03-16/
+# addition of HGMD-restricted subset, Max, Jan 29 2019, updated Dec 10 2019, again Aug 2023, May 2024, Dec 2024
+cd /hive/data/genomes/hg19/bed/ncbiRefSeq.p13.2024-09-18/
# change in 2019: ignore the version numbers, otherwise only 1815 transcripts left, big update by HGMD in 2019
# adding "." so NM_123 doesn't match NM_123123
cat /hive/data/outside/hgmd/$year.4-hgmd-public_hg38.tsv | cut -f7 | cut -d. -f1 | sort -u | awk '{print $1"."}' > hgmdTranscripts.txt
zcat process/hg19.curated.gp.gz | fgrep -f hgmdTranscripts.txt - > hgmd.curated.gp
hgLoadGenePred -genePredExt hg19 ncbiRefSeqHgmd hgmd.curated.gp
$ wc -l hgmd.curated.gp
7965 hgmd.curated.gp in 2019
8971 hgmd.curated.gp in 2020
10451 hgmd.curated.gp in 2021
+14693 hgmd.curated.gp in 2024
# now continue the process at ../hg38/hgmd.txt
# or ideally make a shell script for all this...
#############################################################################
# LASTZ human/hg19 vs. pig/susScr11 - (DONE - 2018-04-02 - Hiram)
mkdir /hive/data/genomes/hg19/bed/lastzSusScr11.2018-04-02
cd /hive/data/genomes/hg19/bed/lastzSusScr11.2018-04-02
printf '# human vs pig
BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz
BLASTZ_O=400
BLASTZ_E=30
BLASTZ_M=254
# default BLASTZ_Q score matrix: