ecfd1eef6885909797fafb4c5da8f934971de265
kate
  Thu May 30 07:47:34 2019 -0700
Remove chrEBV from tables. refs #23243

diff --git src/hg/makeDb/doc/encode3/tfbs.txt src/hg/makeDb/doc/encode3/tfbs.txt
index 1c42f25..e5becbc 100644
--- src/hg/makeDb/doc/encode3/tfbs.txt
+++ src/hg/makeDb/doc/encode3/tfbs.txt
@@ -329,30 +329,31 @@
 
 hgsql hg38 -e "alter table encode3RegTfbsCluster rename to encRegTfbsClustered"
 hgsql hg38 -e "alter table encode3RegTfbsClusterInput rename to encRegTfbsClusteredInputs"
 hgsql hg38 -e "alter table encode3RegTfbsExp rename to encRegTfbsClusteredSources"
 
 ################
 # Load per-factor tables (needed for clusters track details
 # Consider also creating a track for these (composite with 1200 subtracks)
 
 cat > scorePeaks.csh << 'EOF'
     set db = $1
     set f = $2
     set t = $f:r:r
     set table = encode3TfbsPk$t
     echo $table
+# next time grep out chrEBV
     zcat $f > $table.bed
     bedScore -col=7 -verbose=2 -method=reg -uniform $f $table.scored.bed
     hgLoadBed -noNameIx -trimSqlTable \
             -sqlTable=$HOME/kent/src/hg/lib/encode/narrowPeak.sql -renameSqlTable \
             -as=$HOME/kent/src/hg/lib/encode/narrowPeak.as $db $table $table.scored.bed
     gzip -c $table.scored.bed > ../scoredPeaks/$table.bed.gz
     rm $table.bed $table.scored.bed
     end
 'EOF'
 
 cd hg19
 mkdir scoredPeaks
 cd peaks
 
 awk '{print $1}' ../fileCellAbTarget.tab | sed 's/peaks\///' | \
@@ -374,30 +375,34 @@
 
 # Fix up subGroup members w/ punctuation and initial numbers:
 #       Peyer's_patch -> Peyers_patch
 #       NT2/D1 -> NT2_D1
 #       22Rv1 -> X22Rv1
 #       MM.1S -> MM_1S
 
 # rename tables (encode3Tfbs -> encTfChipPk)
 
 hgsql hg19 -e 'show tables like "encode3TfbsPk%"' > tables.old.txt
 sed -e 's/^/alter table /' -e 's/$/ rename to /' tables.old.txt > rename.1.sql
 sed -e 's/encode3TfbsPk/encTfChipPk/' tables.old.txt | paste rename.1.sql -  | \
     sed 's/$/;/' > rename.sql
 hgsql hg19 < rename.sql
 
+# drop chrEBV from tables
+# edit/copy rename.sql to dropEbv.csh:  delete from <table> where chrom='chrEBV'
+hgsql hg19 < dropEbv.sql
+
 # add colors to tier1-3 cell experiments (using ENCODE 2 color conventions)
 #
 # GM12878           color 153,38,0
 # H1-hESC           color 0,107,27
 # K562              color 46,0,184
 # HeLa-S3           color 0,119,158
 # HepG2             color 189,0,157
 # HUVEC             color 224,75,0
 
 raToLines encode3.ra encode3.lines
 sed -e '/GM12878/s/$/| color 153,38,0/' \
     -e '/H1-hESC/s/$/| color 0,107,27/' \
     -e '/K562/s/$/| color 46,0,184/' \
     -e '/HeLa-S3/s/$/| color 0,119,158/' \
     -e '/HepG2/s/$/| color 189,0,157/' \
@@ -444,30 +449,34 @@
 
 # Fix up subGroup members w/ punctuation and initial numbers:
 #       Peyer's_patch -> Peyers_patch
 #       NT2/D1 -> NT2_D1
 #       22Rv1 -> X22Rv1
 #       MM.1S -> MM_1S
 
 # rename tables (encode3Tfbs -> encTfChipPk)
 
 hgsql hg38 -e 'show tables like "encode3TfbsPk%"' > tables.old.txt
 sed -e 's/^/alter table /' -e 's/$/ rename to /' tables.old.txt > rename.1.sql
 sed -e 's/encode3TfbsPk/encTfChipPk/' tables.old.txt | paste rename.1.sql -  | \       
     sed 's/$/;/' > rename.sql
 hgsql hg38 < rename.sql
 
+# drop chrEBV from tables
+# edit/copy rename.sql to dropEbv.csh:  delete from <table> where chrom='chrEBV'
+hgsql hg38 < dropEbv.sql
+
 # add colors, using DNase similarity track 
 raToLines encode3.ra encode3.lines
 
 # edit to leave only subtracks
 # generate edit script from DNase similarity .ra file
 
 cd ~/kent/src/hg/makeDb/trackDb/human/hg38
 csh addColors.csh encode3.lines > encode3.color.lines
 linesToRa encode3.color.lines encode3.color.ra
 
 # missed a few (punctuation diffs, etc.)
 csh addColors2.csh encode3.color.lines encode3.color2.lines
 linesToRa encode3.color2.lines encode3.color.ra
 
 # merge in to encode3.ra