f8575fe7f3223c6279b66e2abc6b3472dad916ef
hiram
  Thu Nov 21 15:48:59 2019 -0800
update ncbiRefSeq tables refs #20215

diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt
index c69f2a7..dd97abe 100644
--- src/hg/makeDb/doc/hg19.txt
+++ src/hg/makeDb/doc/hg19.txt
@@ -33640,15 +33640,77 @@
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_K562_combined.hic
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_KBM7_combined.hic
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_NHEK_combined.hic
 
 mkdir -p /gbdb/hg19/bbi/hic
 cd /gbdb/hg19/bbi/hic
 ln -s /hive/data/genomes/hg19/bed/hic/*.hic .
 #########################################################################
 
 # Illumina GDA  (DONE braney 2019-10-16)
 cd /cluster/data/hg19/bed/gda
 wget "http://webdata.illumina.com.s3-website-us-east-1.amazonaws.com/downloads/productfiles/global-diversity-array/infinium-global-diversity-array-8-d1-csv.zip"
 unzip *.zip
 awk 'BEGIN {FS=","; OFS="\t"} { print "chr" $10, $11-1, $11, $2,0, $21,$4}' *.csv | sort -k1,1 -k2,2n | bedClip stdin /cluster/data/hg19/chrom.sizes gda.bed
 hgLoadSqlTab hg19 snpArrayIlluminaGDA gda.sql gda.bed
+
+#########################################################################
+# ncbiRefSeq.p13 update (DONE - 2019-11-21 - Hiram)
+
+    mkdir /hive/data/genomes/hg19/bed/ncbiRefSeq.p13.2019-11-21
+    cd /hive/data/genomes/hg19/bed/ncbiRefSeq.p13.2019-11-21
+
+    # running step wise just to be careful
+    time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \
+      -bigClusterHub=ku -dbHost=hgwdev \
+      -stop=download -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \
+      refseq vertebrate_mammalian Homo_sapiens \
+      GCF_000001405.25_GRCh37.p13 hg19) > download.log 2>&1
+    # real    2m27.137s
+
+    time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \
+      -continue=process -bigClusterHub=ku -dbHost=hgwdev \
+      -stop=process -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \
+      refseq vertebrate_mammalian Homo_sapiens \
+      GCF_000001405.25_GRCh37.p13 hg19) > process.log 2>&1
+    # real    2m9.450s
+
+    ### BEFORE loading this updated table
+    cat fb.ncbiRefSeq.hg19.txt
+    #  85414465 bases of 2991694177 (2.855%) in intersection
+
+    featureBits -enrichment hg19 refGene ncbiRefSeq
+ # refGene 3.002%, ncbiRefSeq 2.855%, both 2.690%, cover 89.59%, enrich 31.38x
+
+    featureBits -enrichment hg19 ncbiRefSeq refGene
+ # ncbiRefSeq 2.855%, refGene 3.002%, both 2.690%, cover 94.21%, enrich 31.38x
+
+    featureBits -enrichment hg19 ncbiRefSeqCurated refGene
+ # ncbiRefSeqCurated 2.855%, refGene 3.002%, both 2.690%, cover 94.21%, enrich 31.38x
+
+    featureBits -enrichment hg19 refGene ncbiRefSeqCurated
+ # refGene 3.002%, ncbiRefSeqCurated 2.855%, both 2.690%, cover 89.59%, enrich 31.38x
+
+    time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \
+      -continue=load -bigClusterHub=ku -dbHost=hgwdev \
+      -stop=load -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \
+      refseq vertebrate_mammalian Homo_sapiens \
+      GCF_000001405.25_GRCh37.p13 hg19) > load.log 2>&1
+    # real    0m21.982s
+
+    ### AFTER loading this updated table
+    cat fb.ncbiRefSeq.hg19.txt
+    # 93708953 bases of 2991694177 (3.132%) in intersection
+
+    featureBits -enrichment hg19 refGene ncbiRefSeq
+ # refGene 3.002%, ncbiRefSeq 3.132%, both 2.983%, cover 99.35%, enrich 31.72x
+
+    featureBits -enrichment hg19 ncbiRefSeq refGene
+ # ncbiRefSeq 3.132%, refGene 3.002%, both 2.983%, cover 95.23%, enrich 31.72x
+
+    featureBits -enrichment hg19 ncbiRefSeqCurated refGene
+ # ncbiRefSeqCurated 3.132%, refGene 3.002%, both 2.983%, cover 95.23%, enrich 31.72x
+
+    featureBits -enrichment hg19 refGene ncbiRefSeqCurated
+ # refGene 3.002%, ncbiRefSeqCurated 3.132%, both 2.983%, cover 99.35%, enrich 31.72x
+
+#########################################################################