3f4772e689c620fa0db33a2522e362cdcc216047 braney Sat Oct 17 07:24:30 2020 -0700 almost done with the clinvar submissions track! diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt index 95522b0..d5ad7a5 100644 --- src/hg/makeDb/doc/hg19.txt +++ src/hg/makeDb/doc/hg19.txt @@ -33697,44 +33697,52 @@ $buildDir/$db.rna.fa \ $pre) # pslMismatchGapToBed: NM_001365372.1 gapIx 9 shifted right 74 bases, but next block size is only 38; report to NCBI # pslMismatchGapToBed: NM_001288811.1 gapIx 1 shifted left 6 bases, but previous block size is only 5; report to NCBI # real 0m21.265s bedToBigBed -type=bed9+ -tab -as=$HOME/kent/src/hg/lib/txAliDiff.as $pre.bed \ /hive/data/genomes/$db/chrom.sizes $pre.bb # pass1 - making usageList (180 chroms): 77 millis # pass2 - checking and writing primary data (27362 records, 20 fields): 234 millis ln -sf `pwd`/$pre.bb /gbdb/hg19/ncbiRefSeq/$pre.bb ############################################################################# -# clinvarSubLolly track IN PROGRESS BRANEY 10/11/2020 +# clinvarSubLolly track IN PROGRESS BRANEY 10/17/2020 mkdir /cluster/data/hg19/bed/clinvarSubLolly cd /cluster/data/hg19/bed/clinvarSubLolly -bigBedToBed /gbdb/hg19/bbi/clinvar/clinvarMain.bb stdout | tawk '{print $40, $1,$2,$3,$4}' | sort -S 40g > sort.main.bed +bigBedToBed /gbdb/hg19/bbi/clinvar/clinvarMain.bb stdout | tawk '{print $40, $1,$2,$2+1,$4}' | sort -S 40g > sort.main.bed hgsql hg19 -Ne "select varId,clinSign,scv from clinvarSub" | sort -S 40g > clinvarSubSub.txt join -t $'\t' sort.main.bed clinvarSubSub.txt | tawk '{print $2,$3,$4,$5,$6,$1, $7}' | sort -S 40g -k1,1 -k2,2n -k5,5 | tawk -f makeFranklin | tawk -f assignColors > tmp1 tawk '{print $1":"$2 + 1"-"$3"āVariants (submissions):"$11}' tmp1 > tmp2 paste tmp1 tmp2 > bigBedInput.bed bedToBigBed -as=$HOME/kent/src/hg/lib/clinvarSubLolly.as -type=bed9+5 -tab bigBedInput.bed /cluster/data/hg19/chrom.sizes clinvarSubLolly.bb mkdir -p /gbdb/hg19/clinvarSubLolly ln -s `pwd`/clinvarSubLolly.bb /gbdb/hg19/clinvarSubLolly/clinvarSubLolly.bb +bigBedToBed /gbdb/hg19/bbi/clinvar/clinvarMain.bb stdout | tawk '{print $40, $1,$2,$2+1,$4,$13,$15,$18,$19}' | sort -S 40g > sort.main.bed +hgsql hg19 -Ne "select * from clinvarSub" | sort -S 40g > clinvarSubSub.txt +join -t $'\t' sort.main.bed clinvarSubSub.txt | tawk '{print $2,$3,$4,$5,0,"+",0,0,"0,0,0",$6,$20,$8, $9,$1,$10,$7,$11,$12,$13,$14,$15,$16,$17,$18,$19,$21}' | sort -S 40g -k1,1 -k2,2n | tawk -f assignScore > bigBedInput.bed + +bedToBigBed -as=clinvarSubBB.as -type=bed9+11 -tab bigBedInput.bed /cluster/data/hg19/chrom.sizes clinvarSub.bb +ln -s `pwd`/clinvarSub.bb /gbdb/hg19/clinvarSubLolly/clinvarSub.bb + + ############################################################################# # Trios for Genome In a Bottle - DONE 08/04/2020 ChrisL # see ~/kent/src/hg/makeDb/giab/make.txt ############################################################################# # COVID GWAS from COVID-19 Host Genetics Initiative Sep 2020 Kate # see ~kent/src/hg/makeDb/doc/covid/covidHgiGwas.txt ############################################################################# # gnomAD PEXT scores # PEXT data: # The baselevel is the sum of the expression value for all transcripts touching that base # The annotation-level is the sum of the expression of transcripts on which a variant has a # given annotation