e6144b05283954b766bbbb9098cf63dda0dd957a
braney
  Wed Oct 16 11:20:19 2019 -0700
add the Illumina GDA probeset

diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt
index 01a19e0..275887a 100644
--- src/hg/makeDb/doc/hg19.txt
+++ src/hg/makeDb/doc/hg19.txt
@@ -33633,15 +33633,22 @@
 
 # Files are located on GEO at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE63525.  I grabbed the hic files
 # and used a subset of them (the combined files that haven't been filtered).
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_GM12878_insitu_primary%2Breplicate_combined.hic
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_HMEC_combined.hic
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_HUVEC_combined.hic
 wget ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE63nnn/GSE63525/suppl/GSE63525_IMR90_combined.hic
 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