src/hg/makeDb/doc/makeEnsembl.txt 1.14
1.14 2009/10/27 21:32:38 hiram
Rat rn4 v56 update done
Index: src/hg/makeDb/doc/makeEnsembl.txt
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/makeDb/doc/makeEnsembl.txt,v
retrieving revision 1.13
retrieving revision 1.14
diff -b -B -U 1000000 -r1.13 -r1.14
--- src/hg/makeDb/doc/makeEnsembl.txt 5 Aug 2009 23:29:26 -0000 1.13
+++ src/hg/makeDb/doc/makeEnsembl.txt 27 Oct 2009 21:32:38 -0000 1.14
@@ -1,4537 +1,4561 @@
# for emacs: -*- mode: sh; -*-
# This file is a record of building the Ensembl gene track for all UCSC
# genome browsers. The end of this file has a historical record of
# Robert's experiments with an automated process.
#
############################################################################
+# ensembl 56 update (WORKING - 2009-10-27 - Hiram)
+
+############################################################################
+# rn4 - Rat - Ensembl Genes version 56 (DONE - 2009-10-27 - hiram)
+ ssh kkr14u08
+ cd /hive/data/genomes/rn4
+ cat << '_EOF_' > rn4.ensGene.ra
+# required db variable
+db rn4
+# optional nameTranslation, the sed command that will transform
+# Ensemble names to UCSC names. With quotes just to make sure.
+nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
+# optionally update the knownToEnsembl table after ensGene updated
+knownToEnsembl yes
+'_EOF_'
+# << happy emacs
+
+ doEnsGeneUpdate.pl -ensVersion=56 rn4.ensGene.ra
+ ssh hgwdev
+ cd /hive/data/genomes/rn4/bed/ensGene.56
+ featureBits rn4 ensGene
+ # 46518438 bases of 2571531505 (1.809%) in intersection
+
+############################################################################
# ensembl 54 update (DONE - 2009-08-05 - Hiram)
# hg18 needs to get to its last version
############################################################################
# hg18 - Human - Ensembl Genes version 54 (DONE - 2009-08-05 - hiram)
ssh hgwdev
cd /hive/data/genomes/hg18
cat << '_EOF_' > hg18.ensGene.ra
# required db variable
db hg18
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
haplotypeLift /hive/data/genomes/hg18/jkStuff/ensGene.haplotype.lift
liftUp /hive/data/genomes/hg18/jkStuff/liftContigs.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=54 hg18.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/hg18/bed/ensGene.54
featureBits hg18 ensGene
# 70647021 bases of 2881515245 (2.452%) in intersection
############################################################################
# To finish off the update to 55 and 54, run the following:
hgsql -e \
'update trackVersion set dateReference="dec2008" where version="52";' hgFixed
hgsql -e \
'update trackVersion set dateReference="may2009" where version="54";' hgFixed
hgsql -e \
'update trackVersion set dateReference="current" where version="55";' hgFixed
############################################################################
############################################################################
# ensembl 55 updates (WORKING - 2009-07-14 - Hiram)
# see also: more notes about how this is done in the "ensembl 50 updates"
# section below (and in /hive/users/hiram/ensGene/)
############################################################################
# macEug1 - Wallaby - (BROKEN - 2009-07-20 - Hiram)
# can not get this one to work, either a broken GeneScaffold lift
# or a different set of scaffold names, need to investigate
############################################################################
# danRer6 - Zebrafish - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u05
cd /hive/data/genomes/danRer6
cat << '_EOF_' > danRer6.ensGene.ra
# required db variable
db danRer6
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 danRer6.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/danRer6/bed/ensGene.55
featureBits danRer6 ensGene
# 44586206 bases of 1506896106 (2.959%) in intersection
############################################################################
# hg19 - Human - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/hg19
cat << '_EOF_' > hg19.ensGene.ra
# required db variable
db hg19
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
haplotypeLift /hive/data/genomes/hg19/jkStuff/ensGene.haplotype.lift
# liftUp /hive/data/genomes/hg19/jkStuff/liftContigs.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 hg19.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/hg19/bed/ensGene.55
featureBits hg19 ensGene
# 85295627 bases of 2897316137 (2.944%) in intersection
############################################################################
# anoCar1 - Lizard - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u07
cd /hive/data/genomes/anoCar1
cat << '_EOF_' > anoCar1.ensGene.ra
# required db variable
db anoCar1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 anoCar1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/anoCar1/bed/ensGene.55
featureBits anoCar1 ensGene
# 26956669 bases of 1741478929 (1.548%) in intersection
############################################################################
# choHof1 - Sloth - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u03
cd /hive/data/genomes/choHof1
cat << '_EOF_' > choHof1.ensGene.ra
# required db variable
db choHof1
# need to translate Ensembl GeneScaffold coordinates to UCSC scaffolds
geneScaffolds yes
# during the loading of the gene pred, skip all invalid genes
skipInvalid yes
# 18938: ENSCHOT00000005046 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 choHof1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/choHof1/bed/ensGene.55
featureBits choHof1 ensGene
# 18231244 bases of 2060419685 (0.885%) in intersection
############################################################################
# dasNov2 - Armadillo - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u02
cd /hive/data/genomes/dasNov2
cat << '_EOF_' > dasNov2.ensGene.ra
# required db variable
db dasNov2
# need to translate Ensembl GeneScaffold coordinates to UCSC scaffolds
geneScaffolds yes
# during the loading of the gene pred, skip all invalid genes
skipInvalid yes
# 13843: ENSDNOT00000025033 no exonFrame on CDS exon 5
# 23044: ENSDNOT00000004471 no exonFrame on CDS exon 1
# 30976: ENSDNOT00000003424 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 dasNov2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/dasNov2/bed/ensGene.55
featureBits dasNov2 ensGene
# 21864229 bases of 2371493872 (0.922%) in intersection
############################################################################
# loxAfr2 - Elephant - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh swarm
cd /hive/data/genomes/loxAfr2
cat << '_EOF_' > loxAfr2.ensGene.ra
# required db variable
db loxAfr2
# need to translate Ensembl GeneScaffold coordinates to UCSC scaffolds
geneScaffolds yes
# during the loading of the gene pred, skip all invalid genes
skipInvalid yes
# ENSLAFT00000000586 no exonFrame on CDS exon 4
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 loxAfr2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/loxAfr2/bed/ensGene.55
featureBits loxAfr2 ensGene
# 23586871 bases of 2444975542 (0.965%) in intersection
############################################################################
# bosTau4 - Cow - Ensembl Genes version 55 (DONE - 2009-07-15 - hiram)
ssh kkr14u02
cd /hive/data/genomes/bosTau4
cat << '_EOF_' > bosTau4.ensGene.ra
# required db variable
db bosTau4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9UX][0-9n]*\)/chr\1/; s/^MT/chrM/"
# cause SQL tables to be fetched to see if chrUn can be fixed up
# geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 bosTau4.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/bosTau4/bed/ensGene.55
featureBits bosTau4 ensGene
# 42207115 bases of 2731830700 (1.545%) in intersection
############################################################################
# canFam2 - Dog - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u07
cd /hive/data/genomes/canFam2
cat << '_EOF_' > canFam2.ensGene.ra
# required db variable
db canFam2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 canFam2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/canFam2/bed/ensGene.55
featureBits canFam2 ensGene
# 34634472 bases of 2384996543 (1.452%) in intersection
############################################################################
# cavPor3 - Guinea Pig - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u01
cd /hive/data/genomes/cavPor3
cat << '_EOF_' > cavPor3.ensGene.ra
# required db variable
db cavPor3
# do we need to translate geneScaffold coordinates
# geneScaffolds yes
nameTranslation "s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 cavPor3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/cavPor3/bed/ensGene.55
featureBits cavPor3 ensGene
# 30852014 bases of 2663369733 (1.158%) in intersection
############################################################################
# ci2 - C. intestinalis - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/ci2
cat << '_EOF_' > ci2.ensGene.ra
# required db variable
db ci2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][pq]\)/chr0\1/; s/^\([0-9][0-9][pq]\)/chr\1/; "
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 ci2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ci2/bed/ensGene.55
featureBits ci2 ensGene
# 20113161 bases of 141233565 (14.241%) in intersection
############################################################################
# cioSav2 - C. savignyi - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/cioSav2
cat << '_EOF_' > cioSav2.ensGene.ra
# required db variable
db cioSav2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
# nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 cioSav2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/cioSav2/bed/ensGene.55
featureBits cioSav2 ensGene
# 16616680 bases of 173749524 (9.564%) in intersection
############################################################################
# dipOrd1 - Kangaroo rat - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh swarm
cd /hive/data/genomes/dipOrd1
cat << '_EOF_' > dipOrd1.ensGene.ra
# required db variable
db dipOrd1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that have invalid structures from Ensembl:
# 11275: ENSDORT00000004734 no exonFrame on CDS exon 12
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 dipOrd1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/dipOrd1/bed/ensGene.55
featureBits dipOrd1 ensGene
# 25275613 bases of 1844961421 (1.370%) in intersection
############################################################################
# echTel1 - Tenrec - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u03
cd /hive/data/genomes/echTel1
cat << '_EOF_' > echTel1.ensGene.ra
# required db variable
db echTel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 29277: ENSETET00000011172 no exonFrame on CDS exon 14
# 44942: ENSETET00000018714 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 echTel1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/echTel1/bed/ensGene.55
featureBits echTel1 ensGene
# 25563184 bases of 2111581369 (1.211%) in intersection
############################################################################
# equCab2 - Horse - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/equCab2
cat << '_EOF_' > equCab2.ensGene.ra
# required db variable
db equCab2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# translate Ensembl chrUnNNNN names to chrUn coordinates
liftUp /cluster/data/equCab2/jkStuff/chrUn.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 equCab2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/equCab2/bed/ensGene.55
featureBits equCab2 ensGene
# 39506745 bases of 2428790173 (1.627%) in intersection
############################################################################
# eriEur1 - Hedgehog - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u01
cd /hive/data/genomes/eriEur1
cat << '_EOF_' > eriEur1.ensGene.ra
# required db variable
db eriEur1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 4691: ENSEEUT00000004188 no exonFrame on CDS exon 7
# 35795: ENSEEUT00000003156 no exonFrame on CDS exon 4
# 40908: ENSEEUT00000001064 no exonFrame on CDS exon 2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 eriEur1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/eriEur1/bed/ensGene.55
featureBits eriEur1 ensGene
# 22480171 bases of 2133134836 (1.054%) in intersection
############################################################################
# felCat3 - Cat - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u05
cd /hive/data/genomes/felCat3
cat << '_EOF_' > felCat3.ensGene.ra
# required db variable
db felCat3
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 2100: ENSFCAT00000006929 no exonFrame on CDS exon 16
# 14578: ENSFCAT00000010965 no exonFrame on CDS exon 1
# 26634: ENSFCAT00000009384 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 felCat3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/felCat3/bed/ensGene.55
featureBits felCat3 ensGene
# 22220711 bases of 1642698377 (1.353%) in intersection
############################################################################
# fr2 - Fugu - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u06
cd /hive/data/genomes/fr2
cat << '_EOF_' > fr2.ensGene.ra
# required db variable
db fr2
nameTranslation "s/^MT/chrM/;"
# lift Ensembl scaffolds to UCSC chrUn coordinates
liftUp /cluster/data/fr2/jkStuff/liftAll.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 fr2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/fr2/bed/ensGene.55
featureBits fr2 ensGene
# 34560383 bases of 393312790 (8.787%) in intersection
############################################################################
# galGal3 - Chicken - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u07
cd /hive/data/genomes/galGal3
cat << '_EOF_' > galGal3.ensGene.ra
# required db variable
db galGal3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9EWXYZ][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 galGal3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/galGal3/bed/ensGene.55
featureBits galGal3 ensGene
# 30733557 bases of 1042591351 (2.948%) in intersection
############################################################################
# gasAcu1 - Stickleback - Ensembl Genes version 55 (DONE - 2009-07-15 - hiram)
ssh kkr14u07
cd /hive/data/genomes/gasAcu1
cat << '_EOF_' > gasAcu1.ensGene.ra
# required db variable
db gasAcu1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^group\([IUVX]\)/chr\1/; s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 gasAcu1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/gasAcu1/bed/ensGene.55
featureBits gasAcu1 ensGene
# 36789271 bases of 446627861 (8.237%) in intersection
############################################################################
# gorGor1 - Gorilla - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u04
cd /hive/data/genomes/gorGor1
cat << '_EOF_' > gorGor1.ensGene.ra
# required db variable
db gorGor1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC
# names
liftUp /hive/data/genomes/gorGor1/jkStuff/ensemblLiftToUcsc.lift
# ignore the single gene that has an invalid structure from Ensembl:
skipInvalid yes
# 8939: ENSGGOT00000010340 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 gorGor1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/gorGor1/bed/ensGene.55
featureBits gorGor1 ensGene
# 23242041 bases of 2075548667 (1.120%) in intersection
############################################################################
# micMur1 - Mouse lemur - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/micMur1
cat << '_EOF_' > micMur1.ensGene.ra
# required db variable
db micMur1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 micMur1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/micMur1/bed/ensGene.55
featureBits micMur1 ensGene
# 25659397 bases of 1852394361 (1.385%) in intersection
############################################################################
# mm9 - Mouse - Ensembl Genes version 55 (DONE - 2009-07-15 - hiram)
ssh kkr14u07
cd /hive/data/genomes/mm9
cat << '_EOF_' > mm9.ensGene.ra
# required db variable
db mm9
# optional liftRandoms yes/no or absent
liftRandoms yes
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 mm9.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/mm9/bed/ensGene.55
featureBits mm9 ensGene
# 63272128 bases of 2620346127 (2.415%) in intersection
############################################################################
# monDom5 - Opossum - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u03
cd /hive/data/genomes/monDom5
cat << '_EOF_' > monDom5.ensGene.ra
# required db variable
db monDom5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 monDom5.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/monDom5/bed/ensGene.55
featureBits monDom5 ensGene
# 32999268 bases of 3501660299 (0.942%) in intersection
############################################################################
# myoLuc1 - Microbat - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh swarm
cd /hive/data/genomes/myoLuc1
cat << '_EOF_' > myoLuc1.ensGene.ra
# required db variable
db myoLuc1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 1265: ENSMLUT00000004658 no exonFrame on CDS exon 1
# 17770: ENSMLUT00000003427 no exonFrame on CDS exon 10
# 32743: ENSMLUT00000009601 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 myoLuc1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/myoLuc1/bed/ensGene.55
featureBits myoLuc1 ensGene
# 24630744 bases of 1673855868 (1.471%) in intersection
############################################################################
# ochPri2 - Pika - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u07
cd /hive/data/genomes/ochPri2
cat << '_EOF_' > ochPri2.ensGene.ra
# required db variable
db ochPri2
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that has an invalid structure from Ensembl:
# 10995: ENSOPRT00000002716 no exonFrame on CDS exon 2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 ochPri2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ochPri2/bed/ensGene.55
featureBits ochPri2 ensGene
# 25342444 bases of 1923624051 (1.317%) in intersection
############################################################################
# ornAna1 - Platypus - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u02
cd /hive/data/genomes/ornAna1
cat << '_EOF_' > ornAna1.ensGene.ra
# required db variable
db ornAna1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^\(X[0-9]\)/chr\1/; s/^MT/chrM/"
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly, 365 items
skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 ornAna1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ornAna1/bed/ensGene.55
featureBits ornAna1 ensGene
# 24537221 bases of 1842236818 (1.332%) in intersection
############################################################################
# oryCun1 - Rabbit - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh swarm
cd /hive/data/genomes/oryCun1
cat << '_EOF_' > oryCun1.ensGene.ra
# required db variable
db oryCun1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 24994: ENSOCUT00000009485 no exonFrame on CDS exon 9
# 26897: ENSOCUT00000004627 no exonFrame on CDS exon 3
# 32794: ENSOCUT00000014840 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 oryCun1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/oryCun1/bed/ensGene.55
featureBits oryCun1 ensGene
# 22839824 bases of 2076044328 (1.100%) in intersection
############################################################################
# oryLat2 - Medaka - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh swarm
cd /hive/data/genomes/oryLat2
cat << '_EOF_' > oryLat2.ensGene.ra
# required db variable
db oryLat2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^MT/chrM/"
# ignore 2,687 genes that haven't lifted properly yet
# skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 oryLat2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/oryLat2/bed/ensGene.55
featureBits oryLat2 ensGene
# 32301732 bases of 700386597 (4.612%) in intersection
############################################################################
# otoGar1 - Bushbaby - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kolossus
cd /hive/data/genomes/otoGar1
cat << '_EOF_' > otoGar1.ensGene.ra
# required db variable
db otoGar1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/otoGar1/jkStuff/ensGene.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 otoGar1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/otoGar1/bed/ensGene.55
featureBits otoGar1 ensGene
# 23597902 bases of 1969052059 (1.198%) in intersection
############################################################################
# panTro2 - Chimp - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/panTro2
cat << '_EOF_' > panTro2.ensGene.ra
# required db variable
db panTro2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 panTro2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/panTro2/bed/ensGene.55
featureBits panTro2 ensGene
# 49983145 bases of 2909485072 (1.718%) in intersection
############################################################################
# ponAbe2 - Orangutan - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u03
cd /hive/data/genomes/ponAbe2
cat << '_EOF_' > ponAbe2.ensGene.ra
# required db variable
db ponAbe2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 ponAbe2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ponAbe2/bed/ensGene.55
featureBits ponAbe2 ensGene
# 38087987 bases of 3093572278 (1.231%) in intersection
############################################################################
# proCap1 - Rock hyrax - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u03
cd /hive/data/genomes/proCap1
cat << '_EOF_' > proCap1.ensGene.ra
# required db variable
db proCap1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 4595: ENSPCAT00000007286 no exonFrame on CDS exon 1
# 28894: ENSPCAT00000000699 no exonFrame on CDS exon 4
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 proCap1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/proCap1/bed/ensGene.55
featureBits proCap1 ensGene
# 25296156 bases of 2407847681 (1.051%) in intersection
############################################################################
# pteVam1 - Megabat - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u08
cd /hive/data/genomes/pteVam1
cat << '_EOF_' > pteVam1.ensGene.ra
# required db variable
db pteVam1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 6381: ENSPVAT00000012919 no exonFrame on CDS exon 14
# 23522: ENSPVAT00000010661 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 pteVam1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/pteVam1/bed/ensGene.55
featureBits pteVam1 ensGene
# 28914790 bases of 1839436660 (1.572%) in intersection
############################################################################
# rheMac2 - Rhesus - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kolossus
cd /hive/data/genomes/rheMac2
cat << '_EOF_' > rheMac2.ensGene.ra
# required db variable
db rheMac2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^109[0-9]*/d; /^MT/d; s/^\([0-9XY][0-9]*\)/chr\1/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 rheMac2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/rheMac2/bed/ensGene.55
featureBits rheMac2 ensGene
# 44519581 bases of 2646704109 (1.682%) in intersection
############################################################################
# rn4 - Rat - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh swarm
cd /hive/data/genomes/rn4
cat << '_EOF_' > rn4.ensGene.ra
# required db variable
db rn4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 rn4.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/rn4/bed/ensGene.55
featureBits rn4 ensGene
# 43758167 bases of 2571531505 (1.702%) in intersection
############################################################################
# sacCer2 - S. cerevisiae - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u02
cd /hive/data/genomes/sacCer2
cat << '_EOF_' > sacCer2.ensGene.ra
# required db variable
db sacCer2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^VIII/chrVIII/; s/^VII/chrVII/; s/^VI/chrVI/; s/^V/chrV/; s/^XIII/chrXIII/; s/^XII/chrXII/; s/^XIV/chrXIV/; s/^XI/chrXI/; s/^XVI/chrXVI/; s/^XV/chrXV/; s/^X/chrX/; s/^III/chrIII/; s/^IV/chrIV/; s/^II/chrII/; s/^IX/chrIX/; s/^I/chrI/; s/^MT/chrM/; s/2-micron/2micron/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 sacCer2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/sacCer2/bed/ensGene.55
featureBits sacCer2 ensGene
# 8912793 bases of 12162995 (73.278%) in intersection
############################################################################
# sorAra1 - Shrew - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u04
cd /hive/data/genomes/sorAra1
cat << '_EOF_' > sorAra1.ensGene.ra
# required db variable
db sorAra1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 sorAra1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/sorAra1/bed/ensGene.55
featureBits sorAra1 ensGene
# 19509213 bases of 1832864697 (1.064%) in intersection
############################################################################
# speTri1 - Squirrel - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kolossus
cd /hive/data/genomes/speTri1
cat << '_EOF_' > speTri1.ensGene.ra
# required db variable
db speTri1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that has an invalid structure from Ensembl:
# 1071: ENSSTOT00000007455 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 speTri1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/speTri1/bed/ensGene.55
featureBits speTri1 ensGene
# 21590338 bases of 1913367893 (1.128%) in intersection
############################################################################
# taeGut1 - Zebra finch - Ensembl Genes version 55 (DONE - 2009-07-15 - hiram)
ssh kkr14u03
cd /hive/data/genomes/taeGut1
cat << '_EOF_' > taeGut1.ensGene.ra
# required db variable
db taeGut1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9LXYZ][0-9ABG]*\)/chr\1/; s/^Un/chrUn/"
# need to translate Ensembl GeneScaffold coordinates to UCSC scaffolds
# geneScaffolds yes
# during the loading of the gene pred, skip all invalid genes
# skipInvalid yes
# 13843: ENSDNOT00000025033 no exonFrame on CDS exon 5
# 23044: ENSDNOT00000004471 no exonFrame on CDS exon 1
# 30976: ENSDNOT00000003424 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 taeGut1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/taeGut1/bed/ensGene.55
featureBits taeGut1 ensGene
# 25428670 bases of 1222864691 (2.079%) in intersection
############################################################################
# tarSyr1 - Tarsier - Ensembl Genes version 55 (DONE - 2009-07-20 - hiram)
ssh kkr14u01
cd /hive/data/genomes/tarSyr1
cat << '_EOF_' > tarSyr1.ensGene.ra
# required db variable
db tarSyr1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 tarSyr1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/tarSyr1/bed/ensGene.55
featureBits tarSyr1 ensGene
# 21282560 bases of 2768536343 (0.769%) in intersection
############################################################################
# tupBel1 - TreeShrew - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u05
cd /hive/data/genomes/tupBel1
cat << '_EOF_' > tupBel1.ensGene.ra
# required db variable
db tupBel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/tupBel1/jkStuff/ensGene.lft
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 2993: ENSTBET00000015831 no exonFrame on CDS exon 11
# 3556: ENSTBET00000013522 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 tupBel1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/tupBel1/bed/ensGene.55
featureBits tupBel1 ensGene
# 22808448 bases of 2137225476 (1.067%) in intersection
############################################################################
# turTru1 - Dolphin - Ensembl Genes version 55 (DONE - 2009-07-20 - hiram)
ssh kkr14u06
cd /hive/data/genomes/turTru1
cat << '_EOF_' > turTru1.ensGene.ra
# required db variable
db turTru1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 turTru1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/turTru1/bed/ensGene.55
featureBits turTru1 ensGene
# 28534327 bases of 2298444090 (1.241%) in intersection
############################################################################
# vicPac1 - Alpaca - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kkr14u06
cd /hive/data/genomes/vicPac1
cat << '_EOF_' > vicPac1.ensGene.ra
# required db variable
db vicPac1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the 53 genes that do not translate properly to UCSC coordinates
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 vicPac1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/vicPac1/bed/ensGene.55
featureBits vicPac1 ensGene
# 17833823 bases of 1922910435 (0.927%) in intersection
############################################################################
# xenTro2 - X. tropicalis - Ensembl Genes version 55 (DONE - 2009-07-14 - hiram)
ssh kolossus
cd /hive/data/genomes/xenTro2
cat << '_EOF_' > xenTro2.ensGene.ra
# required db variable
db xenTro2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=55 xenTro2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/xenTro2/bed/ensGene.55
featureBits xenTro2 ensGene
# 29158032 bases of 1359412157 (2.145%) in intersection
############################################################################
############################################################################
# ensembl 52 updates (DONE - 2009-01-21,22 - Hiram)
# see also: more notes about how this is done in the "ensembl 50 updates"
# section below
############################################################################
# bosTau4 - Cow - Ensembl Genes version 52 (DONE - 2009-01-22 - hiram)
ssh swarm
cd /hive/data/genomes/bosTau4
cat << '_EOF_' > bosTau4.ensGene.ra
# required db variable
db bosTau4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9UX][0-9n]*\)/chr\1/; s/^MT/chrM/"
# cause SQL tables to be fetched to see if chrUn can be fixed up
# geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 bosTau4.ensGene.ra \
> ensGene.52.log 2>&1
# v52 introduced the chrM genes as MT genes, needed to alter
# the nameTranslation sed command to include s/^MT/chrM/
# And then, it breaks down in the process step due to this single
# stray gene definition, to fix it:
ssh hgwdev
cd /hive/data/genomes/bosTau4/bed/ensGene.52/process
mv bosTau4.allGenes.gp.gz bosTau4.allGenes.gp.gz.broken
zcat bosTau4.allGenes.gp.gz.broken | grep -v AAFC03011182 \
| gzip -c > bosTau4.allGenes.gp.gz
# verify that:
genePredCheck -db=bosTau4 bosTau4.allGenes.gp.gz
# checked: 29802 failed: 0
# continuing:
cd /hive/data/genomes/bosTau4
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl -verbose=2 \
-ensVersion=52 -continue=load bosTau4.ensGene.ra >> ensGene.52.log 2>&1
cd /hive/data/genomes/bosTau4/bed/ensGene.52
featureBits bosTau4 ensGene
# 41476954 bases of 2731830700 (1.518%) in intersection
############################################################################
# canFam2 - Dog - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/canFam2
cat << '_EOF_' > canFam2.ensGene.ra
# required db variable
db canFam2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 canFam2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/canFam2/bed/ensGene.52
featureBits canFam2 ensGene
# 34634856 bases of 2384996543 (1.452%) in intersection
############################################################################
# cavPor3 - Guinea Pig - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh hgwdev
cd /hive/data/genomes/cavPor3
cat << '_EOF_' > cavPor3.ensGene.ra
# required db variable
db cavPor3
# do we need to translate geneScaffold coordinates
# geneScaffolds yes
nameTranslation "s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 cavPor3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/cavPor3/bed/ensGene.52
featureBits cavPor3 ensGene
# 30852014 bases of 2663369733 (1.158%) in intersection
############################################################################
# ce6 - C. elegans - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/ce6
cat << '_EOF_' > ce6.ensGene.ra
# required db variable
db ce6
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([IVX]\)/chr\1/; s/^MtDNA/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 ce6.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ce6/bed/ensGene.52
featureBits ce6 ensGene
# 29421784 bases of 100281426 (29.339%) in intersection
############################################################################
# ci2 - C. intestinalis - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh swarm
cd /hive/data/genomes/ci2
cat << '_EOF_' > ci2.ensGene.ra
# required db variable
db ci2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][pq]\)/chr0\1/; s/^\([0-9][0-9][pq]\)/chr\1/; "
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 ci2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ci2/bed/ensGene.52
featureBits ci2 ensGene
# 20113161 bases of 141233565 (14.241%) in intersection
############################################################################
# cioSav2 - C. savignyi - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh kolossus
cd /hive/data/genomes/cioSav2
cat << '_EOF_' > cioSav2.ensGene.ra
# required db variable
db cioSav2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
# nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 cioSav2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/cioSav2/bed/ensGene.52
featureBits cioSav2 ensGene
# 16616680 bases of 173749524 (9.564%) in intersection
############################################################################
# danRer5 - Zebrafish - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/danRer5
cat << '_EOF_' > danRer5.ensGene.ra
# required db variable
db danRer5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 danRer5.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/danRer5/bed/ensGene.52
featureBits danRer5 ensGene
# 36854235 bases of 1435609608 (2.567%) in intersection
############################################################################
# dasNov1 - Armadillo - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/dasNov1
cat << '_EOF_' > dasNov1.ensGene.ra
# required db variable
db dasNov1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 18192: ENSDNOT00000004471 no exonFrame on CDS exon 7
# 35247: ENSDNOT00000007696 no exonFrame on CDS exon 8
# 38952: ENSDNOT00000019234 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 dasNov1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/dasNov1/bed/ensGene.52
featureBits dasNov1 ensGene
# 22721709 bases of 2146362222 (1.059%) in intersection
############################################################################
# dipOrd1 - Kangaroo rat - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh swarm
cd /hive/data/genomes/dipOrd1
cat << '_EOF_' > dipOrd1.ensGene.ra
# required db variable
db dipOrd1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that have invalid structures from Ensembl:
# 11275: ENSDORT00000004734 no exonFrame on CDS exon 12
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 dipOrd1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/dipOrd1/bed/ensGene.52
featureBits dipOrd1 ensGene
# 25213442 bases of 1844961421 (1.367%) in intersection
############################################################################
# echTel1 - Tenrec - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/echTel1
cat << '_EOF_' > echTel1.ensGene.ra
# required db variable
db echTel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 29277: ENSETET00000011172 no exonFrame on CDS exon 14
# 44942: ENSETET00000018714 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 echTel1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/echTel1/bed/ensGene.52
featureBits echTel1 ensGene
# 25563184 bases of 2111581369 (1.211%) in intersection
############################################################################
# equCab2 - Horse - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/equCab2
cat << '_EOF_' > equCab2.ensGene.ra
# required db variable
db equCab2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# translate Ensembl chrUnNNNN names to chrUn coordinates
liftUp /cluster/data/equCab2/jkStuff/chrUn.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 equCab2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/equCab2/bed/ensGene.52
featureBits equCab2 ensGene
# 39198296 bases of 2428790173 (1.614%) in intersection
############################################################################
# eriEur1 - Hedgehog - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/eriEur1
cat << '_EOF_' > eriEur1.ensGene.ra
# required db variable
db eriEur1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 4691: ENSEEUT00000004188 no exonFrame on CDS exon 7
# 35795: ENSEEUT00000003156 no exonFrame on CDS exon 4
# 40908: ENSEEUT00000001064 no exonFrame on CDS exon 2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 eriEur1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/eriEur1/bed/ensGene.52
featureBits eriEur1 ensGene
# 22480171 bases of 2133134836 (1.054%) in intersection
############################################################################
# felCat3 - Cat - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/felCat3
cat << '_EOF_' > felCat3.ensGene.ra
# required db variable
db felCat3
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 2100: ENSFCAT00000006929 no exonFrame on CDS exon 16
# 14578: ENSFCAT00000010965 no exonFrame on CDS exon 1
# 26634: ENSFCAT00000009384 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 felCat3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/felCat3/bed/ensGene.52
featureBits felCat3 ensGene
############################################################################
# fr2 - Fugu - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/fr2
cat << '_EOF_' > fr2.ensGene.ra
# required db variable
db fr2
nameTranslation "s/^MT/chrM/;"
# lift Ensembl scaffolds to UCSC chrUn coordinates
liftUp /cluster/data/fr2/jkStuff/liftAll.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 fr2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/fr2/bed/ensGene.52
featureBits fr2 ensGene
# 34560383 bases of 393312790 (8.787%) in intersection
############################################################################
# galGal3 - Chicken - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/galGal3
cat << '_EOF_' > galGal3.ensGene.ra
# required db variable
db galGal3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9EWXYZ][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 galGal3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/galGal3/bed/ensGene.52
featureBits galGal3 ensGene
# 30733654 bases of 1042591351 (2.948%) in intersection
############################################################################
# gasAcu1 - Stickleback - Ensembl Genes version 52 (DONE - 2009-01-22 - hiram)
ssh swarm
cd /hive/data/genomes/gasAcu1
cat << '_EOF_' > gasAcu1.ensGene.ra
# required db variable
db gasAcu1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^group\([IUVX]\)/chr\1/; s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 gasAcu1.ensGene.ra
# requires extra attention after the all database for loop attempt
cd /hive/data/genomes/gasAcu1/bed/ensGene.52/process
mv gasAcu1.allGenes.gp.gz gasAcu1.allGenes.gp.beforeLift.gz
zcat gasAcu1.allGenes.gp.beforeLift.gz \
| liftUp -extGenePred -type=.gp gasAcu1.scaffolds.gp \
../../../jkStuff/contigsToScaffolds.lft carry stdin
liftUp -extGenePred gasAcu1.allGenes.gp \
../../../jkStuff/UCSC.chromToScaffoldSansGaps.lft carry \
gasAcu1.scaffolds.gp
gzip gasAcu1.scaffolds.gp
gzip gasAcu1.allGenes.gp
# verify OK
genePredCheck -db=gasAcu1 gasAcu1.allGenes.gp.gz
# checked: 29109 failed: 0
# then continue with the load
cd /hive/data/genomes/gasAcu1
doEnsGeneUpdate.pl -continue=load -ensVersion=52 gasAcu1.ensGene.ra \
>> ensGene.52.load.log 2>&1
featureBits gasAcu1 ensGene
# 36789458 bases of 446627861 (8.237%) in intersection
############################################################################
# gorGor1 - Gorilla - Ensembl Genes version 52 (DONE - 2008-12-19 - hiram)
ssh kolossus
cd /hive/data/genomes/gorGor1
cat << '_EOF_' > gorGor1.ensGene.ra
# required db variable
db gorGor1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC
# names
liftUp /hive/data/genomes/gorGor1/jkStuff/ensemblLiftToUcsc.lift
# ignore the single gene that has an invalid structure from Ensembl:
skipInvalid yes
# 8939: ENSGGOT00000010340 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 gorGor1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/gorGor1/bed/ensGene.52
featureBits gorGor1 ensGene
# 23242041 bases of 2075548667 (1.120%) in intersection
############################################################################
# hg18 - Human - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
# v52 introduced genes on contig coordinates, needed to add
# the liftUp liftContigs.lft specification to the .ra file:
ssh kolossus
cd /hive/data/genomes/hg18
cat << '_EOF_' > hg18.ensGene.ra
# required db variable
db hg18
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
haplotypeLift /hive/data/genomes/hg18/jkStuff/ensGene.haplotype.lift
liftUp /hive/data/genomes/hg18/jkStuff/liftContigs.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 hg18.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/hg18/bed/ensGene.52
featureBits hg18 ensGene
# 70647021 bases of 2881515245 (2.452%) in intersection
############################################################################
# loxAfr1 - Elephant - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/loxAfr1
cat << '_EOF_' > loxAfr1.ensGene.ra
# required db variable
db loxAfr1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the one gene that has an invalid structure from Ensembl:
# 13002: ENSLAFT00000000586 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 loxAfr1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/loxAfr1/bed/ensGene.52
featureBits loxAfr1 ensGene
# 21706063 bases of 2295548473 (0.946%) in intersection
############################################################################
# micMur1 - Mouse lemur - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh kolossus
cd /hive/data/genomes/micMur1
cat << '_EOF_' > micMur1.ensGene.ra
# required db variable
db micMur1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 micMur1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/micMur1/bed/ensGene.52
featureBits micMur1 ensGene
# 25659397 bases of 1852394361 (1.385%) in intersection
############################################################################
# mm9 - Mouse - Ensembl Genes version 52 (DONE - 2009-01-22 - hiram)
ssh swarm
cd /hive/data/genomes/mm9
cat << '_EOF_' > mm9.ensGene.ra
# required db variable
db mm9
# optional liftRandoms yes/no or absent
liftRandoms yes
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 mm9.ensGene.ra
# ran into trouble with the ensGtp table load, the names of
# the proteins have gotten longer and the standard sql definition
# was no longer adequate. So, after the load failed, increase
# protein char and index size to 23:
cat << '_EOF_' > ensGtp.sql
# This creates the table holding the relationship between
# ensemble genes, transcripts, and peptides.
CREATE TABLE ensGtp (
gene char(20) NOT NULL,
transcript char(20) NOT NULL,
protein char(23) NOT NULL,
# INDICES
INDEX(gene(19)),
UNIQUE(transcript(19)),
INDEX(protein(23))
)
'_EOF_'
# << happy emacs
# Then, running the rest of the load script:
ssh hgwdev
cd /hive/data/genomes/mm9/bed/ensGene.52
./finiLoad.csh > ensGene.52.log 2>&1
doEnsGeneUpdate -ensVersion=52 -verbose=2 -continue=cleanup mm9.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/mm9/bed/ensGene.52
featureBits mm9 ensGene
# 63272128 bases of 2620346127 (2.415%) in intersection
############################################################################
# monDom5 - Opossum - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/monDom5
cat << '_EOF_' > monDom5.ensGene.ra
# required db variable
db monDom5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 monDom5.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/monDom5/bed/ensGene.52
featureBits monDom5 ensGene
# 33008124 bases of 3501660299 (0.943%) in intersection
############################################################################
# myoLuc1 - Microbat - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/myoLuc1
cat << '_EOF_' > myoLuc1.ensGene.ra
# required db variable
db myoLuc1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 1265: ENSMLUT00000004658 no exonFrame on CDS exon 1
# 17770: ENSMLUT00000003427 no exonFrame on CDS exon 10
# 32743: ENSMLUT00000009601 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 myoLuc1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/myoLuc1/bed/ensGene.52
featureBits myoLuc1 ensGene
# 24630744 bases of 1673855868 (1.471%) in intersection
############################################################################
# ochPri2 - Pika - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/ochPri2
cat << '_EOF_' > ochPri2.ensGene.ra
# required db variable
db ochPri2
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that has an invalid structure from Ensembl:
# 10995: ENSOPRT00000002716 no exonFrame on CDS exon 2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 ochPri2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ochPri2/bed/ensGene.52
featureBits ochPri2 ensGene
# 25342444 bases of 1923624051 (1.317%) in intersection
############################################################################
# ornAna1 - Platypus - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/ornAna1
cat << '_EOF_' > ornAna1.ensGene.ra
# required db variable
db ornAna1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^\(X[0-9]\)/chr\1/; s/^MT/chrM/"
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly, 365 items
skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 ornAna1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ornAna1/bed/ensGene.52
featureBits ornAna1 ensGene
# 24537443 bases of 1842236818 (1.332%) in intersection
############################################################################
# oryCun1 - Rabbit - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kkr14u03
cd /hive/data/genomes/oryCun1
cat << '_EOF_' > oryCun1.ensGene.ra
# required db variable
db oryCun1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# 24994: ENSOCUT00000009485 no exonFrame on CDS exon 9
# 26897: ENSOCUT00000004627 no exonFrame on CDS exon 3
# 32794: ENSOCUT00000014840 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 oryCun1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/oryCun1/bed/ensGene.52
featureBits oryCun1 ensGene
# 22839824 bases of 2076044328 (1.100%) in intersection
############################################################################
# oryLat2 - Medaka - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/oryLat2
cat << '_EOF_' > oryLat2.ensGene.ra
# required db variable
db oryLat2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^MT/chrM/"
# ignore 2,687 genes that haven't lifted properly yet
# skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 oryLat2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/oryLat2/bed/ensGene.52
featureBits oryLat2 ensGene
# 32301878 bases of 700386597 (4.612%) in intersection
############################################################################
# otoGar1 - Bushbaby - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/otoGar1
cat << '_EOF_' > otoGar1.ensGene.ra
# required db variable
db otoGar1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/otoGar1/jkStuff/ensGene.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 otoGar1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/otoGar1/bed/ensGene.52
featureBits otoGar1 ensGene
# 23597902 bases of 1969052059 (1.198%) in intersection
############################################################################
# panTro2 - Chimp - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/panTro2
cat << '_EOF_' > panTro2.ensGene.ra
# required db variable
db panTro2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 panTro2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/panTro2/bed/ensGene.52
featureBits panTro2 ensGene
# 49983145 bases of 2909485072 (1.718%) in intersection
############################################################################
# ponAbe2 - Orangutan - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/ponAbe2
cat << '_EOF_' > ponAbe2.ensGene.ra
# required db variable
db ponAbe2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 ponAbe2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ponAbe2/bed/ensGene.52
featureBits ponAbe2 ensGene
############################################################################
# proCap1 - Rock hyrax - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/proCap1
cat << '_EOF_' > proCap1.ensGene.ra
# required db variable
db proCap1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 4595: ENSPCAT00000007286 no exonFrame on CDS exon 1
# 28894: ENSPCAT00000000699 no exonFrame on CDS exon 4
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 proCap1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/proCap1/bed/ensGene.52
featureBits proCap1 ensGene
# 25234470 bases of 2407847681 (1.048%) in intersection
############################################################################
# pteVam1 - Megabat - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/pteVam1
cat << '_EOF_' > pteVam1.ensGene.ra
# required db variable
db pteVam1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 6381: ENSPVAT00000012919 no exonFrame on CDS exon 14
# 23522: ENSPVAT00000010661 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 pteVam1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/pteVam1/bed/ensGene.52
featureBits pteVam1 ensGene
# 28832895 bases of 1839436660 (1.567%) in intersection
############################################################################
# rheMac2 - Rhesus - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/rheMac2
cat << '_EOF_' > rheMac2.ensGene.ra
# required db variable
db rheMac2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^109[0-9]*/d; /^MT/d; s/^\([0-9XY][0-9]*\)/chr\1/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 rheMac2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/rheMac2/bed/ensGene.52
featureBits rheMac2 ensGene
# 44519581 bases of 2646704109 (1.682%) in intersection
############################################################################
# rn4 - Rat - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/rn4
cat << '_EOF_' > rn4.ensGene.ra
# required db variable
db rn4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 rn4.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/rn4/bed/ensGene.52
featureBits rn4 ensGene
# 43758167 bases of 2571531505 (1.702%) in intersection
############################################################################
# sacCer1 - S. cerevisiae - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh swarm
cd /hive/data/genomes/sacCer1
cat << '_EOF_' > sacCer1.ensGene.ra
# required db variable
db sacCer1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^VIII/chr8/; s/^VII/chr7/; s/^VI/chr6/; s/^V/chr5/; s/^XIII/chr13/; s/^XII/chr12/; s/^XIV/chr14/; s/^XI/chr11/; s/^XVI/chr16/; s/^XV/chr15/; s/^X/chr10/; s/^III/chr3/; s/^IV/chr4/; s/^II/chr2/; s/^IX/chr9/; s/^I/chr1/; s/^MT/chrM/; /2-micron/d"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 sacCer1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/sacCer1/bed/ensGene.52
featureBits sacCer1 ensGene
# 8908962 bases of 12156302 (73.287%) in intersection
# this complains about table 'gap' missing
############################################################################
# sorAra1 - Shrew - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh swarm
cd /hive/data/genomes/sorAra1
cat << '_EOF_' > sorAra1.ensGene.ra
# required db variable
db sorAra1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 sorAra1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/sorAra1/bed/ensGene.52
featureBits sorAra1 ensGene
# 19509213 bases of 1832864697 (1.064%) in intersection
############################################################################
# speTri1 - Squirrel - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/speTri1
cat << '_EOF_' > speTri1.ensGene.ra
# required db variable
db speTri1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that has an invalid structure from Ensembl:
# 1071: ENSSTOT00000007455 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 speTri1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/speTri1/bed/ensGene.52
featureBits speTri1 ensGene
# 21590338 bases of 1913367893 (1.128%) in intersection
############################################################################
# tarSyr1 - Tarsier - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/tarSyr1
cat << '_EOF_' > tarSyr1.ensGene.ra
# required db variable
db tarSyr1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the 2,819 genes that do not translate properly to UCSC # coordinates
# out of 43,529 genes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 tarSyr1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/tarSyr1/bed/ensGene.52
featureBits tarSyr1 ensGene
# 20286934 bases of 2768536343 (0.733%) in intersection
############################################################################
# tupBel1 - TreeShrew - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
ssh kolossus
cd /hive/data/genomes/tupBel1
cat << '_EOF_' > tupBel1.ensGene.ra
# required db variable
db tupBel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/tupBel1/jkStuff/ensGene.lft
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# 2993: ENSTBET00000015831 no exonFrame on CDS exon 11
# 3556: ENSTBET00000013522 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 tupBel1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/tupBel1/bed/ensGene.52
featureBits tupBel1 ensGene
# 22808448 bases of 2137225476 (1.067%) in intersection
############################################################################
# turTru1 - Dolphin - Ensembl Genes version 52 (DONE - 2009-01-21 - hiram)
# this one does not work currently. Something is fishy with
# the protein vs. peptide names
############################################################################
# vicPac1 - Alpaca - Ensembl Genes version 52 (DONE - 2009-01-22 - hiram)
ssh kolossus
cd /hive/data/genomes/vicPac1
cat << '_EOF_' > vicPac1.ensGene.ra
# required db variable
db vicPac1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the 53 genes that do not translate properly to UCSC coordinates
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 vicPac1.ensGene.ra
# ran into a little problem with this one, one of the files at
# the Ensembl FTP site was not gzipped and we were looking for
# and expect to find the .gz file. So, after the download failed,
# fixup the doDownload.csh script to fetch the unzipped gtf file,
# and gzip it for the rest of the sequence, then continuing:
doEnsGeneUpdate.pl -ensVersion=52 -verbose=2 -continue=process \
vicPac1.ensGene.ra >> ensGene.52.log 2>&1
ssh hgwdev
cd /hive/data/genomes/vicPac1/bed/ensGene.52
featureBits vicPac1 ensGene
# 17768749 bases of 1922910435 (0.924%) in intersection
############################################################################
# xenTro2 - X. tropicalis - Ensembl Genes version 52 (DONE - 2009-01-21 -
# hiram)
ssh swarm
cd /hive/data/genomes/xenTro2
cat << '_EOF_' > xenTro2.ensGene.ra
# required db variable
db xenTro2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=52 xenTro2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/xenTro2/bed/ensGene.52
featureBits xenTro2 ensGene
# 29158101 bases of 1359412157 (2.145%) in intersection
#############################################################################
#############################################################################
# ensembl 51 updates (DONE - 2008-12-05 - Hiram)
# see also: more notes about how this is done in the "ensembl 50 updates"
# section below
############################################################################
# canFam2 - Dog - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/canFam2
cat << '_EOF_' > canFam2.ensGene.ra
# required db variable
db canFam2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 canFam2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/canFam2/bed/ensGene.51
featureBits canFam2 ensGene
# 34551623 bases of 2384996543 (1.449%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/canFam2/bed/ensGene.51
############################################################################
# ce6 - C. elegans - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/ce6
cat << '_EOF_' > ce6.ensGene.ra
# required db variable
db ce6
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([IVX]\)/chr\1/; s/^MtDNA/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 ce6.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ce6/bed/ensGene.51
featureBits ce6 ensGene
# 29421784 bases of 100281426 (29.339%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/ce6/bed/ensGene.51
############################################################################
# ci2 - C. intestinalis - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/ci2
cat << '_EOF_' > ci2.ensGene.ra
# required db variable
db ci2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][pq]\)/chr0\1/; s/^\([0-9][0-9][pq]\)/chr\1/; "
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 ci2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ci2/bed/ensGene.51
featureBits ci2 ensGene
# 20106805 bases of 141233565 (14.237%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/ci2/bed/ensGene.51
############################################################################
# cioSav2 - C. savignyi - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/cioSav2
cat << '_EOF_' > cioSav2.ensGene.ra
# required db variable
db cioSav2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
# nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 cioSav2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/cioSav2/bed/ensGene.51
featureBits cioSav2 ensGene
# 16601350 bases of 173749524 (9.555%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/cioSav2/bed/ensGene.51
############################################################################
# danRer5 - Zebrafish - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/danRer5
cat << '_EOF_' > danRer5.ensGene.ra
# required db variable
db danRer5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 danRer5.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/danRer5/bed/ensGene.51
featureBits danRer5 ensGene
# 36864148 bases of 1435609608 (2.568%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/danRer5/bed/ensGene.51
############################################################################
# equCab2 - Horse - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/equCab2
cat << '_EOF_' > equCab2.ensGene.ra
# required db variable
db equCab2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# translate Ensembl chrUnNNNN names to chrUn coordinates
liftUp /cluster/data/equCab2/jkStuff/chrUn.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 equCab2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/equCab2/bed/ensGene.51
featureBits equCab2 ensGene
# 39169781 bases of 2428790173 (1.613%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/equCab2/bed/ensGene.51
############################################################################
# fr2 - Fugu - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/fr2
cat << '_EOF_' > fr2.ensGene.ra
# required db variable
db fr2
nameTranslation "s/^MT/chrM/;"
# lift Ensembl scaffolds to UCSC chrUn coordinates
liftUp /cluster/data/fr2/jkStuff/liftAll.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 fr2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/fr2/bed/ensGene.51
featureBits fr2 ensGene
# 34554303 bases of 393312790 (8.785%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/fr2/bed/ensGene.51
############################################################################
# galGal3 - Chicken - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/galGal3
cat << '_EOF_' > galGal3.ensGene.ra
# required db variable
db galGal3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9EWXYZ][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 galGal3.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/galGal3/bed/ensGene.51
featureBits galGal3 ensGene
# 30700613 bases of 1042591351 (2.945%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/galGal3/bed/ensGene.51
############################################################################
# hg18 - Human - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/hg18
cat << '_EOF_' > hg18.ensGene.ra
# required db variable
db hg18
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 hg18.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/hg18/bed/ensGene.51
featureBits hg18 ensGene
# 69963186 bases of 2881515245 (2.428%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/hg18/bed/ensGene.51
############################################################################
# micMur1 - Mouse lemur - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/micMur1
cat << '_EOF_' > micMur1.ensGene.ra
# required db variable
db micMur1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 micMur1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/micMur1/bed/ensGene.51
featureBits micMur1 ensGene
# 25425991 bases of 1852394361 (1.373%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/micMur1/bed/ensGene.51
############################################################################
# mm9 - Mouse - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/mm9
cat << '_EOF_' > mm9.ensGene.ra
# required db variable
db mm9
# optional liftRandoms yes/no or absent
liftRandoms yes
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 mm9.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/mm9/bed/ensGene.51
featureBits mm9 ensGene
# 60671138 bases of 2620346127 (2.315%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/mm9/bed/ensGene.51
############################################################################
# oryLat2 - Medaka - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/oryLat2
cat << '_EOF_' > oryLat2.ensGene.ra
# required db variable
db oryLat2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^MT/chrM/"
# ignore 2,687 genes that haven't lifted properly yet
# skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 oryLat2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/oryLat2/bed/ensGene.51
featureBits oryLat2 ensGene
# 32293719 bases of 700386597 (4.611%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/oryLat2/bed/ensGene.51
############################################################################
# otoGar1 - Bushbaby - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/otoGar1
cat << '_EOF_' > otoGar1.ensGene.ra
# required db variable
db otoGar1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/otoGar1/jkStuff/ensGene.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 otoGar1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/otoGar1/bed/ensGene.51
featureBits otoGar1 ensGene
# 23463097 bases of 1969052059 (1.192%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/otoGar1/bed/ensGene.51
############################################################################
# panTro2 - Chimp - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/panTro2
cat << '_EOF_' > panTro2.ensGene.ra
# required db variable
db panTro2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 panTro2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/panTro2/bed/ensGene.51
featureBits panTro2 ensGene
# 49736660 bases of 2909485072 (1.709%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/panTro2/bed/ensGene.51
############################################################################
# ponAbe2 - Orangutan - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/ponAbe2
cat << '_EOF_' > ponAbe2.ensGene.ra
# required db variable
db ponAbe2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 ponAbe2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/ponAbe2/bed/ensGene.51
featureBits ponAbe2 ensGene
# 37839545 bases of 3093572278 (1.223%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/ponAbe2/bed/ensGene.51
############################################################################
# rheMac2 - Rhesus - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/rheMac2
cat << '_EOF_' > rheMac2.ensGene.ra
# required db variable
db rheMac2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^109[0-9]*/d; /^MT/d; s/^\([0-9XY][0-9]*\)/chr\1/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 rheMac2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/rheMac2/bed/ensGene.51
featureBits rheMac2 ensGene
# 44297247 bases of 2646704109 (1.674%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/rheMac2/bed/ensGene.51
############################################################################
# rn4 - Rat - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/rn4
cat << '_EOF_' > rn4.ensGene.ra
# required db variable
db rn4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 rn4.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/rn4/bed/ensGene.51
featureBits rn4 ensGene
# 43712046 bases of 2571531505 (1.700%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/rn4/bed/ensGene.51
############################################################################
# sacCer1 - S. cerevisiae - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/sacCer1
cat << '_EOF_' > sacCer1.ensGene.ra
# required db variable
db sacCer1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^VIII/chr8/; s/^VII/chr7/; s/^VI/chr6/; s/^V/chr5/; s/^XIII/chr13/; s/^XII/chr12/; s/^XIV/chr14/; s/^XI/chr11/; s/^XVI/chr16/; s/^XV/chr15/; s/^X/chr10/; s/^III/chr3/; s/^IV/chr4/; s/^II/chr2/; s/^IX/chr9/; s/^I/chr1/; s/^MT/chrM/; /2-micron/d"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 sacCer1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/sacCer1/bed/ensGene.51
featureBits sacCer1 ensGene
# table gap doesn't exist
# 8908962 bases of 12156302 (73.287%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/sacCer1/bed/ensGene.51
############################################################################
# xenTro2 - X. tropicalis - Ensembl Genes version 51 (DONE - 2008-12-03 - hiram)
ssh kkr14u07
cd /hive/data/genomes/xenTro2
cat << '_EOF_' > xenTro2.ensGene.ra
# required db variable
db xenTro2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 xenTro2.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/xenTro2/bed/ensGene.51
featureBits xenTro2 ensGene
# 29135083 bases of 1359412157 (2.143%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/xenTro2/bed/ensGene.51
############################################################################
#############################################################################
# ensembl 50 updates (DONE - 2009-08-07 - Hiram)
# When a new Ensembl release is available. Some manual work needs
# to be done to src/hg/utils/automation/EnsGeneAutomate.pm
# to specify the files for each release.
# Fixups:
# version correspondence with their date strings:
# add $verToDate[##] = "monYYYY";
# add new ## to @versionList
# create lists for FtpFileNames_##, FtpPeptideFileNames_## and
# FtpMySqlFileNames_##
# and associated reference pointers to those specific new lists
# These lists relate our database names with their file names.
# This could perhaps be done in an automated fashion by scanning
# their FTP directories and relating their scientific names to
# our names. However, there is a difficulty involved even if that
# could be done. And that is, the exact correspondence between
# which genome version they are annotating vs. the genome version
# we have here. I prefer to do this manually once at the beginning.
# It can be argued this could be error prone since it is manually
# done. But, for now it is good enough for me. If someone else wants
# to take on this task, and it would actually be interesting, be my guest.
# new Dbs at Ensembl for build 50:
# bosTau4, ce6, tetNig2 (ucsc is tetNig1)
# new Dbs here for build 50
# micMur1 myoLuc1 ochPri2 speTri1
# any new Dbs listed above will need to be run manually the first time
# to debug their <db>.ensGene.ra configuration file in /cluster/data/<db>
# no Db here:
# aedAeg0 dm5 monDom5 sorAra0 tetNig2
# The following three shell scripts can be run to make up the
# three different lists. All that needs to be filled in are the
# UCSC database names. For the gtf file names:
echo "user anonymous qa@ucsc
cd pub/release-50/gtf
ls -lR gtfFiles.fl
bye" > gtf50.rsp
ftp -n -v -i ftp.ensembl.org < gtf50.rsp
awk '
BEGIN { D = "" }
/^\.\// { D = $0 }
/^-/ { printf "%s/%s\n", D, $9 }
' gtfFiles.fl | sed -e "s#:/#/#; s#^./#'abcDef0' => '#; s/$/',/"
# for the peptide names:
echo "user anonymous qa@ucsc
cd pub/release-50/fasta
ls -lR pepFiles.fl
bye" > pep50.rsp
ftp -n -v -i ftp.ensembl.org < pep50.rsp
awk '
BEGIN { D = "" }
/^\.\// { D = $0 }
/^-/ { printf "%s/%s\n", D, $9 }
' pepFiles.fl | sed -e "s#:/#/#; s#^./#'abcDef0' => '#; s/$/',/" \
| grep pep.all.fa.gz
# for the MySQL directory names:
echo "user anonymous qa@ucsc
cd pub/release-50/mysql
ls -lR mysqlFiles.fl
bye" > mysql50.rsp
ftp -n -v -i ftp.ensembl.org < mysql50.rsp
awk '
BEGIN { D = "" }
/^\.\// { D = $0 }
/seq_region.txt/ { printf "%s\n", D }
' mysqlFiles.fl | sed -e "s#:##g; s#^./#'abcDef0' => '#; s/$/',/" \
| grep _core_
# quick verification that all the UCSC database names were entered
# correctly, the counts on each name should all be == 3
egrep "_50_|\.50\." EnsGeneAutomate.pm | awk '{print $1}' | sort | uniq -c
# to see which DBs can be run:
cd ~/kent/src/hg/utils/automation
./ensVersions 50 | grep -v "NOT FOUND" | sort
# manually ran the following to verify functionality and get
# ensGene.ra files established for new organisms:
# mm9 bosTau4 ce6 micMur1 myoLuc1 ochPri2 speTri1 hg18
# Then, running the following loop:
cd /scratch/tmp
for D in canFam2 ci2 cioSav2 danRer5 dasNov1 echTel1 \
equCab2 felCat3 fr2 galGal3 gasAcu1 loxAfr1 ornAna1 \
oryCun1 oryLat1 otoGar1 panTro2 ponAbe2 rheMac2 rn4 sacCer1 \
tupBel1 xenTro2
do
cd /cluster/data/${D}
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl -verbose=2 \
-ensVersion=50 ${D}.ensGene.ra > ${D}.ensGene.update.50.log 2>&1
cat ${D}.ensGene.update.50.log
mv ${D}.ensGene.update.50.log bed/ensGene.50
done > ensGene.update.50.log
# individual makeDoc entries are attached below
# Failed: gasAcu1 oryLat1
# OK: canFam2 ci2 cioSav2 danRer5 dasNov1 echTel1 equCab2 felCat3
# OK: fr2 galGal3 loxAfr1 ornAna1 oryCun1 otoGar1 panTro2 ponAbe2
# OK: rheMac2 rn4 sacCer1 (no gap table ?) tupBel1 xenTro2
# the ones that used to have skipInvalid need to be verified to
# see if that really still applies:
# skipInvalid: dasNov1 echTel1 felCat3 loxAfr1 ornAna1 oryCun1 oryLat1
# skipInvalid: tupBel1
# To check these skipInvalid:
cd /cluster/data/<db>/bed/ensGene.50/process
zcat <db>.allGenes.gp.gz | genePredCheck -db=<db> stdin
# you should see errors on the specific items mentioned in their
# <db>.ensGene.ra file
# the above were verified to have the same few errors as before.
# ornAna1 is a bit wierd. Ensembl seems to have Contigs that we do not.
# gasAcu1 and oryLat1 needed special lifts
# To finalize the build, update the "current" status in the trackVersion
# table in hgFixed
hgsql -e \
'update trackVersion set dateReference="mar2008" where version="49";' hgFixed
hgsql -e \
'update trackVersion set dateReference="current" where version="50";' hgFixed
# to establish a new ensGene.ra file, start out with simply:
# required db variable
db newDb
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# It is probably a geneScaffold assembly, if not, leave this out
# run the script with -stop=process to see if it reports any
# errors at that point. You will then know what type of
# nameTranslation sed string you need to add, or any other
# special lifts, and if there are bugs in some of the Ensembl
# predictions. Add whatever new arguments you need to, then
# continue the script with --continue. Remove the process
# directory to re-run the process step again.
# manually running mm9 to see if it works:
cd /cluster/data/mm9
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-verbose=2 -ensVersion=50 mm9.ensGene.ra > ensGene50.log 2>&1
# This run reports completion as follows:
############################################################################
# mm9 - Mouse - Ensembl Genes version 50 (DONE - 2008-08-07 - hiram)
ssh kkstore06
cd /cluster/data/mm9
cat << '_EOF_' > mm9.ensGene.ra
# required db variable
db mm9
# optional liftRandoms yes/no or absent
liftRandoms yes
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 mm9.ensGene.ra
ssh hgwdev
cd /cluster/data/mm9/bed/ensGene.50
featureBits mm9 ensGene
# 60671138 bases of 2620346127 (2.315%) in intersection
############################################################################
# bosTau4 - Cow - Ensembl Genes version 51 (DONE - 2008-12-03,04 - hiram)
ssh kkr14u04
cd /hive/data/genomes/bosTau4
cat << '_EOF_' > bosTau4.ensGene.ra
# required db variable
db bosTau4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9UX][0-9n]*\)/chr\1/"
# cause SQL tables to be fetched to see if chrUn can be fixed up
# geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 bosTau4.ensGene.ra
# broke down during process step, fix it:
cd /hive/data/genomes/bosTau4/bed/ensGene.51/process
mv bosTau4.allGenes.gp.gz bosTau4.allGenes.broken.gp.gz
zcat bosTau4.allGenes.broken.gp.gz | grep -v AAFC03011182 | \
gzip -c > bosTau4.allGenes.gp.gz
# check it, from last line in doProcess.csh
genePredCheck -db=bosTau4 bosTau4.allGenes.gp.gz
# checked: 29516 failed: 0
# now, continuing
cd /hive/data/genomes/bosTau4
doEnsGeneUpdate.pl -verbose=2 -ensVersion=51 -continue=load \
bosTau4.ensGene.ra > ensGene51.load.log 2>&1
ssh hgwdev
cd /hive/data/genomes/bosTau4/bed/ensGene.51
featureBits bosTau4 ensGene
# 41425444 bases of 2731830700 (1.516%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/bosTau4/bed/ensGene.51
############################################################################
# bosTau4 - Cow - Ensembl V50 Genes (DONE - 2008-04-22 - hiram)
# This one had to be done manually. They have a mistake
# in their gtf file. A single line has a gene name in the
# chromosome column. The lifting business for chrUn seems to
# be unnecessary as it was done for bosTau3. It looks like
# they properly have their chrUn names the same as ours
ssh hgwdev
cd /cluster/data/bosTau4
ssh kkstore05
cd /cluster/data/bosTau4
cat << '_EOF_' > bosTau4.ensGene.ra
# required db variable
db bosTau4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9UX][0-9n]*\)/chr\1/"
# cause SQL tables to be fetched to see if chrUn can be fixed up
# geneScaffolds yes
'_EOF_'
# << happy emacs
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-verbose=2 -ensVersion=50 -stop=process bosTau4.ensGene.ra \
> ensGene50.process.log 2>&1
# the load step is broken due to the single bogus name.
# strip it out by fixing the load script to grep it out
# the fixed step:
zcat process/bosTau4.allGenes.gp.gz | grep -v AAFC03011182 \
| hgLoadGenePred -genePredExt bosTau4 \
ensGene stdin >& loadGenePred.errors.txt
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-continue=load -ensVersion=50 bosTau4.ensGene.ra \
> ensGene50.load.log 2>&1
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-continue=cleanup -ensVersion=50 bosTau4.ensGene.ra \
> ensGene50.cleanup.log 2>&1
ssh hgwdev
cd /cluster/data/bosTau4/bed/ensGene.50
featureBits bosTau4 ensGene
# 41259085 bases of 2731830700 (1.510%) in intersection
############################################################################
# ce6 - C. elegans - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore06
cd /cluster/data/ce6
cat << '_EOF_' > ce6.ensGene.ra
# required db variable
db ce6
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([IVX]\)/chr\1/; s/^MtDNA/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 ce6.ensGene.ra
ssh hgwdev
cd /cluster/data/ce6/bed/ensGene.50
featureBits ce6 ensGene
# 29421784 bases of 100281426 (29.339%) in intersection
############################################################################
# micMur1 - Mouse lemur - Ensembl Genes version 50 (DONE - 2008-08-08 -
# hiram)
ssh kkstore05
cd /cluster/data/micMur1
cat << '_EOF_' > micMur1.ensGene.ra
# required db variable
db micMur1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 micMur1.ensGene.ra
ssh hgwdev
cd /cluster/data/micMur1/bed/ensGene.50
featureBits micMur1 ensGene
# 25425991 bases of 1852394361 (1.373%) in intersection
############################################################################
# myoLuc1 - Microbat - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/myoLuc1
cat << '_EOF_' > myoLuc1.ensGene.ra
# required db variable
db myoLuc1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSMLUT00000004658 no exonFrame on CDS exon 1
# ENSMLUT00000003427 no exonFrame on CDS exon 10
# ENSMLUT00000009601 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 myoLuc1.ensGene.ra
ssh hgwdev
cd /cluster/data/myoLuc1/bed/ensGene.50
featureBits myoLuc1 ensGene
# 24559555 bases of 1673855868 (1.467%) in intersection
############################################################################
# ochPri2 - Pika - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/ochPri2
cat << '_EOF_' > ochPri2.ensGene.ra
# required db variable
db ochPri2
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that has an invalid structure from Ensembl:
# ENSOPRT00000002716 no exonFrame on CDS exon 2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 ochPri2.ensGene.ra
ssh hgwdev
cd /cluster/data/ochPri2/bed/ensGene.50
featureBits ochPri2 ensGene
# 25069963 bases of 1923624051 (1.303%) in intersection
############################################################################
# speTri1 - Squirrel - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/speTri1
cat << '_EOF_' > speTri1.ensGene.ra
# required db variable
db speTri1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the single gene that has an invalid structure from Ensembl:
# ENSSTOT00000007455 no exonFrame on CDS exon
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 speTri1.ensGene.ra
ssh hgwdev
cd /cluster/data/speTri1/bed/ensGene.50
featureBits speTri1 ensGene
# 21525994 bases of 1913367893 (1.125%) in intersection
############################################################################
# hg18 - Human - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore02
cd /cluster/data/hg18
cat << '_EOF_' > hg18.ensGene.ra
# required db variable
db hg18
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 hg18.ensGene.ra
ssh hgwdev
cd /cluster/data/hg18/bed/ensGene.50
featureBits hg18 ensGene
# 69928854 bases of 2881515245 (2.427%) in intersection
############################################################################
# canFam2 - Dog - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore04
cd /cluster/data/canFam2
cat << '_EOF_' > canFam2.ensGene.ra
# required db variable
db canFam2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 canFam2.ensGene.ra
ssh hgwdev
cd /cluster/data/canFam2/bed/ensGene.50
featureBits canFam2 ensGene
# 34550366 bases of 2384996543 (1.449%) in intersection
############################################################################
# ci2 - C. intestinalis - Ensembl Genes version 50 (DONE - 2008-08-08 -
# hiram)
ssh kkstore02
cd /cluster/data/ci2
cat << '_EOF_' > ci2.ensGene.ra
# required db variable
db ci2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][pq]\)/chr0\1/; s/^\([0-9][0-9][pq]\)/chr\1/; "
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 ci2.ensGene.ra
ssh hgwdev
cd /cluster/data/ci2/bed/ensGene.50
featureBits ci2 ensGene
# 20124353 bases of 141233565 (14.249%) in intersection
############################################################################
# cioSav2 - C. savignyi - Ensembl Genes version 50 (DONE - 2008-08-08 -
# hiram)
ssh kkstore02
cd /cluster/data/cioSav2
cat << '_EOF_' > cioSav2.ensGene.ra
# required db variable
db cioSav2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
# nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 cioSav2.ensGene.ra
ssh hgwdev
cd /cluster/data/cioSav2/bed/ensGene.50
featureBits cioSav2 ensGene
# 16601350 bases of 173749524 (9.555%) in intersection
############################################################################
# danRer5 - Zebrafish - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore06
cd /cluster/data/danRer5
cat << '_EOF_' > danRer5.ensGene.ra
# required db variable
db danRer5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 danRer5.ensGene.ra
ssh hgwdev
cd /cluster/data/danRer5/bed/ensGene.50
featureBits danRer5 ensGene
# 36864148 bases of 1435609608 (2.568%) in intersection
############################################################################
# dasNov1 - Armadillo - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore04
cd /cluster/data/dasNov1
cat << '_EOF_' > dasNov1.ensGene.ra
# required db variable
db dasNov1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSDNOT00000004471 no exonFrame on CDS exon 7
# ENSDNOT00000007696 no exonFrame on CDS exon 8
# ENSDNOT00000019234 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 dasNov1.ensGene.ra
ssh hgwdev
cd /cluster/data/dasNov1/bed/ensGene.50
featureBits dasNov1 ensGene
# 22658142 bases of 2146362222 (1.056%) in intersection
############################################################################
# echTel1 - Tenrec - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore02
cd /cluster/data/echTel1
cat << '_EOF_' > echTel1.ensGene.ra
# required db variable
db echTel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSETET00000011172 no exonFrame on CDS exon 14
# ENSETET00000018714 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 echTel1.ensGene.ra
ssh hgwdev
cd /cluster/data/echTel1/bed/ensGene.50
featureBits echTel1 ensGene
# 25441754 bases of 2111581369 (1.205%) in intersection
############################################################################
# equCab2 - Horse - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/equCab2
cat << '_EOF_' > equCab2.ensGene.ra
# required db variable
db equCab2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# translate Ensembl chrUnNNNN names to chrUn coordinates
liftUp /cluster/data/equCab2/jkStuff/chrUn.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 equCab2.ensGene.ra
ssh hgwdev
cd /cluster/data/equCab2/bed/ensGene.50
featureBits equCab2 ensGene
# 39169781 bases of 2454424288 (1.596%) in intersection
############################################################################
# felCat3 - Cat - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/felCat3
cat << '_EOF_' > felCat3.ensGene.ra
# required db variable
db felCat3
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSFCAT00000006929 no exonFrame on CDS exon 15
# ENSFCAT00000009384 no exonFrame on CDS exon 0
# ENSFCAT00000010965 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 felCat3.ensGene.ra
ssh hgwdev
cd /cluster/data/felCat3/bed/ensGene.50
featureBits felCat3 ensGene
# 22020647 bases of 1642698377 (1.341%) in intersection
############################################################################
# fr2 - Fugu - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore02
cd /cluster/data/fr2
cat << '_EOF_' > fr2.ensGene.ra
# required db variable
db fr2
nameTranslation "s/^MT/chrM/;"
# lift Ensembl scaffolds to UCSC chrUn coordinates
liftUp /cluster/data/fr2/jkStuff/liftAll.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 fr2.ensGene.ra
ssh hgwdev
cd /cluster/data/fr2/bed/ensGene.50
featureBits fr2 ensGene
# 34554303 bases of 393312790 (8.785%) in intersection
############################################################################
# galGal3 - Chicken - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore03
cd /cluster/data/galGal3
cat << '_EOF_' > galGal3.ensGene.ra
# required db variable
db galGal3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9EWXYZ][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 galGal3.ensGene.ra
ssh hgwdev
cd /cluster/data/galGal3/bed/ensGene.50
featureBits galGal3 ensGene
# 30853095 bases of 1042591351 (2.959%) in intersection
############################################################################
# loxAfr1 - Elephant - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore04
cd /cluster/data/loxAfr1
cat << '_EOF_' > loxAfr1.ensGene.ra
# required db variable
db loxAfr1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the one gene that has an invalid structure from Ensembl:
# ENSLAFT00000000586 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 loxAfr1.ensGene.ra
ssh hgwdev
cd /cluster/data/loxAfr1/bed/ensGene.50
featureBits loxAfr1 ensGene
# 23295034 bases of 2295548473 (1.015%) in intersection
############################################################################
# ornAna1 - Platypus - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/ornAna1
cat << '_EOF_' > ornAna1.ensGene.ra
# required db variable
db ornAna1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^\(X[0-9]\)/chr\1/; s/^MT/chrM/"
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
'_EOF_'
# << happy emacs
# There are 362 items that have invalid chrom messages
doEnsGeneUpdate.pl -ensVersion=50 ornAna1.ensGene.ra
ssh hgwdev
cd /cluster/data/ornAna1/bed/ensGene.50
featureBits ornAna1 ensGene
# 24505297 bases of 1842236818 (1.330%) in intersection
############################################################################
# oryCun1 - Rabbit - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore04
cd /cluster/data/oryCun1
cat << '_EOF_' > oryCun1.ensGene.ra
# required db variable
db oryCun1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSOCUT00000004627 no exonFrame on CDS exon 3
# ENSOCUT00000009485 no exonFrame on CDS exon 9
# ENSOCUT00000014840 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 oryCun1.ensGene.ra
ssh hgwdev
cd /cluster/data/oryCun1/bed/ensGene.50
featureBits oryCun1 ensGene
# 22733387 bases of 2076044328 (1.095%) in intersection
############################################################################
# otoGar1 - Bushbaby - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/otoGar1
cat << '_EOF_' > otoGar1.ensGene.ra
# required db variable
db otoGar1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/otoGar1/jkStuff/ensGene.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 otoGar1.ensGene.ra
ssh hgwdev
cd /cluster/data/otoGar1/bed/ensGene.50
featureBits otoGar1 ensGene
# 23463097 bases of 1969052059 (1.192%) in intersection
############################################################################
# panTro2 - Chimp - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore04
cd /cluster/data/panTro2
cat << '_EOF_' > panTro2.ensGene.ra
# required db variable
db panTro2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 panTro2.ensGene.ra
ssh hgwdev
cd /cluster/data/panTro2/bed/ensGene.50
featureBits panTro2 ensGene
# 49736660 bases of 2909485072 (1.709%) in intersection
############################################################################
# ponAbe2 - Orangutan - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore02
cd /cluster/data/ponAbe2
cat << '_EOF_' > ponAbe2.ensGene.ra
# required db variable
db ponAbe2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 ponAbe2.ensGene.ra
ssh hgwdev
cd /cluster/data/ponAbe2/bed/ensGene.50
featureBits ponAbe2 ensGene
# 37737277 bases of 3093572278 (1.220%) in intersection
############################################################################
# rheMac2 - Rhesus - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore01
cd /cluster/data/rheMac2
cat << '_EOF_' > rheMac2.ensGene.ra
# required db variable
db rheMac2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^109[0-9]*/d; /^MT/d; s/^\([0-9XY][0-9]*\)/chr\1/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 rheMac2.ensGene.ra
ssh hgwdev
cd /cluster/data/rheMac2/bed/ensGene.50
featureBits rheMac2 ensGene
# 44297247 bases of 2646704109 (1.674%) in intersection
############################################################################
# rn4 - Rat - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore06
cd /cluster/data/rn4
cat << '_EOF_' > rn4.ensGene.ra
# required db variable
db rn4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 rn4.ensGene.ra
ssh hgwdev
cd /cluster/data/rn4/bed/ensGene.50
featureBits rn4 ensGene
# 43712046 bases of 2571531505 (1.700%) in intersection
############################################################################
# sacCer1 - S. cerevisiae - Ensembl Genes version 50 (DONE - 2008-08-08 -
# hiram)
ssh kkstore03
cd /cluster/data/sacCer1
cat << '_EOF_' > sacCer1.ensGene.ra
# required db variable
db sacCer1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^VIII/chr8/; s/^VII/chr7/; s/^VI/chr6/; s/^V/chr5/; s/^XIII/chr13/; s/^XII/chr12/; s/^XIV/chr14/; s/^XI/chr11/; s/^XVI/chr16/; s/^XV/chr15/; s/^X/chr10/; s/^III/chr3/; s/^IV/chr4/; s/^II/chr2/; s/^IX/chr9/; s/^I/chr1/; s/^MT/chrM/; /2-micron/d"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 sacCer1.ensGene.ra
ssh hgwdev
cd /cluster/data/sacCer1/bed/ensGene.50
featureBits sacCer1 ensGene
# 8908962 bases of 12156302 (73.287%) in intersection
############################################################################
# tupBel1 - TreeShrew - Ensembl Genes version 50 (DONE - 2008-08-08 - hiram)
ssh kkstore05
cd /cluster/data/tupBel1
cat << '_EOF_' > tupBel1.ensGene.ra
# required db variable
db tupBel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/tupBel1/jkStuff/ensGene.lft
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSTBET00000015831 no exonFrame on CDS exon 11
# ENSTBET00000013522 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 tupBel1.ensGene.ra
ssh hgwdev
cd /cluster/data/tupBel1/bed/ensGene.50
featureBits tupBel1 ensGene
# 22746299 bases of 2137225476 (1.064%) in intersection
############################################################################
# xenTro2 - X. tropicalis - Ensembl Genes version 50 (DONE - 2008-08-08 -
# hiram)
ssh kkstore04
cd /cluster/data/xenTro2
cat << '_EOF_' > xenTro2.ensGene.ra
# required db variable
db xenTro2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 xenTro2.ensGene.ra
ssh hgwdev
cd /cluster/data/xenTro2/bed/ensGene.50
featureBits xenTro2 ensGene
# 29150618 bases of 1359412157 (2.144%) in intersection
############################################################################
# gasAcu1 - Stickleback - Ensembl Genes version 51 (DONE - 2008-08-11 - hiram)
# requires extra attention after the all database for loop attempt
cd /hive/data/genomes/gasAcu1/bed/ensGene.51/process
mv gasAcu1.allGenes.gp.gz gasAcu1.allGenes.gp.beforeLift.gz
zcat gasAcu1.allGenes.gp.beforeLift.gz \
| liftUp -extGenePred -type=.gp gasAcu1.scaffolds.gp \
../../../jkStuff/contigsToScaffolds.lft carry stdin
liftUp -extGenePred gasAcu1.allGenes.gp \
../../../jkStuff/UCSC.chromToScaffoldSansGaps.lft carry \
gasAcu1.scaffolds.gp
gzip gasAcu1.scaffolds.gp
gzip gasAcu1.allGenes.gp
# verify OK
genePredCheck -db=gasAcu1 gasAcu1.allGenes.gp.gz
# checked: 29096 failed: 0
# then continue with the load
cd /hive/data/genomes/gasAcu1
doEnsGeneUpdate.pl -continue=load -ensVersion=51 gasAcu1.ensGene.ra \
> ensGene.51.load.log 2>&1
# it responds with the following make doc output:
########
# gasAcu1 - Stickleback - Ensembl Genes version 51 (DONE - 2008-12-04 hiram)
ssh kkr14u07
cd /hive/data/genomes/gasAcu1
cat << '_EOF_' > gasAcu1.ensGene.ra
# required db variable
db gasAcu1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^group\([IUVX]\)/chr\1/; s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=51 gasAcu1.ensGene.ra
ssh hgwdev
cd /hive/data/genomes/gasAcu1/bed/ensGene.51
featureBits gasAcu1 ensGene
# 36787204 bases of 446627861 (8.237%) in intersection
*** All done! (through the 'makeDoc' step)
*** Steps were performed in /hive/data/genomes/gasAcu1/bed/ensGene.51
############################################################################
# gasAcu1 - Stickleback - Ensembl Genes version 50 (DONE - 2008-08-11 - hiram)
# requires extra attention after the all database for loop attempt
cd /cluster/data/gasAcu1/bed/ensGene.50/process
mv mv gasAcu1.allGenes.gp.gz gasAcu1.allGenes.gp.beforeLift.gz
zcat gasAcu1.allGenes.gp.beforeLift.gz \
| liftUp -extGenePred -type=.gp gasAcu1.scaffolds.gp \
../../../jkStuff/contigsToScaffolds.lft carry stdin
liftUp -extGenePred gasAcu1.allGenes.gp \
../../../jkStuff/UCSC.chromToScaffoldSansGaps.lft carry \
gasAcu1.scaffolds.gp
gzip gasAcu1.scaffolds.gp
gzip gasAcu1.allGenes.gp
# then continue with the load
cd /cluster/data/gasAcu1
doEnsGeneUpdate.pl -continue=load -ensVersion=50 gasAcu1.ensGene.ra \
> bed/ensGene.50/load.log 2>&1
# it responds with the following make doc output:
# gasAcu1 - Stickleback - Ensembl Genes version 50 (DONE - 2008-08-11 -
# hiram)
ssh kkstore05
cd /cluster/data/gasAcu1
cat << '_EOF_' > gasAcu1.ensGene.ra
# required db variable
db gasAcu1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^group\([IUVX]\)/chr\1/; s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=50 gasAcu1.ensGene.ra
ssh hgwdev
cd /cluster/data/gasAcu1/bed/ensGene.50
featureBits gasAcu1 ensGene
# 36956798 bases of 446627861 (8.275%) in intersection
############################################################################
# oryLat1 - Medaka - Ensembl Genes version 50 (DONE - 2008-08-11 - hiram)
# need to eliminate the bad lifts due to our chrUn error at this time
cd /cluster/data/oryLat1/bed/ensGene.50
grep "invalid chrom" *.errors.txt | cut -d\ -f2 | sort -u > badLifts.name
hgsql -N -e "select transcript from ensGtp;" oryLat1 \
| sort > ensGtp.transcript
comm -13 ensGene.name ensGtp.transcript | sort > ensGtp.not.ensGene.name
comm -13 ensGene.name ensPep.name | sort > ensPep.not.ensGene.name
# do the badLifts account for all the missing peptides:
comm -12 badLifts.name ensPep.not.ensGene.name | wc -l
# 2608 -> yes, this is the count of missing peptides.
# So, remove this set of business from ensPep table
for N in `cat badLifts.name`
do
hgsql -e "delete from ensPep where name=\"$N\";" oryLat1
echo $N
done
# And from the ensGtp table
for N in `cat badLifts.name`
do
hgsql -e "delete from ensGtp where transcript=\"$N\";" oryLat1
echo $N
done
#
genePredCheck -db=oryLat1 ensGene
# checked: 22463 failed: 0
#############################################################################
#############################################################################
# ensembl 49 updates (DONE - 2009-03-31 - Hiram)
# hg18 and loxAfr1 were done manually to verify operations, then,
# all at once, except for those two:
ssh hgwdev
cd /scratch/tmp
hgsql -N -e "select db from trackVersion where version=48;" hgFixed \
| sort -u | egrep -v "hg18|loxAfr1" | while read DB
do
echo $DB
cd /cluster/data/${DB} && \
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-verbose=2 -ensVersion=49 ${DB}.ensGene.ra
done > ensGene.49.update.log 2>&1
# bosTau3 failed due to the peptides to gene ratio check
# oryLat1 failed due to the peptides to gene ratio check
# fr2 failed due to chrMT naming problem - chrMT is new to their release
# gasAcu1 failed due to attempted genePredCheck from kkr1u00 ?
# actually gasAcu1 needs special processing, it has an extra couple
# of lifts to be done.
# mm9 failed, says "download" was already done
# sacCer1 failed, due to incorrect peptide file name
# felCat3, ornAna1, otoGar1, tupBel1 failed due to wget failures
for DB in felCat3 ornAna1 otoGar1 tupBel1
do
echo $DB
rm -fr /cluster/data/${DB}/bed/ensGene.49/download
cd /cluster/data/${DB} && \
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-verbose=2 -ensVersion=49 ${DB}.ensGene.ra
done > ensGene.49.secondTry.log 2>&1
# Interestingly, when the chooseFileServer discovers the file server
# is busy, it goes to chooseWorkhorse and gets one of the kki nodes
# which can not wget. So, trying a couple of these again, and
# the new to v49 genome ponAbe2:
for DB in felCat3 mm9 ponAbe2
do
echo $DB
rm -fr /cluster/data/${DB}/bed/ensGene.49/download
cd /cluster/data/${DB} && \
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-verbose=2 -ensVersion=49 ${DB}.ensGene.ra
done > ensGene.49.thirdTry.log 2>&1
# that worked just fine.
############################################################################
# The version 49 update individual entries follow:
############################################################################
# bosTau3 - Cow - Ensembl Genes (DONE - 2008-04-22 - hiram)
# This one had to be done manually. There was a chrUn lift file that
# needed to be made to turn the Ensembl chrUn coordinates into
# the UCSC chrUn.003.N contig coordinates
# It was run with a geneScaffolds yes to fetch the MySQL tables,
# Then a script was run:
ssh hgwdev
cd /cluster/data/bosTau3
cat << '_EOF_' > jkStuff/chrUnLiftAcross.pl
#!/usr/bin/env perl
use strict;
use warnings;
open (FH,"<chrUn.seq_region.txt") or die "can not read chrUn.seq_region.txt";
my $start = 0;
my $end = 0;
my $gap = 10000;
while (my $line = <FH>) {
chomp $line;
my ($region_id, $name, $type, $size) = split('\s+', $line);
$end = $start + $size;
printf "chrUn\t%d\t%d\t%s\t%d\t%d\t+\n", $start, $end, $name, 0, $size;
$start += $size + $gap;
}
close (FH);
'_EOF_'
# << happy emacs
chmod +x jkStuff/chrUnLiftAcross.pl
cd bed/ensGene.49/download
../../../jkStuff/chrUnLiftAcross.pl > ../../../jkStuff/chrUn.liftAcross.txt
# then use that chrUn.liftAcross.txt in the process script procedure
# after that, comment out the gene Scaffolds and -continue=load
ssh kkstore05
cd /cluster/data/bosTau3
cat << '_EOF_' > bosTau3.ensGene.ra
# required db variable
db bosTau3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9UX][0-9n]*\)/chr\1/; /^MT/d"
# cause SQL tables to be fetched to see if chrUn can be fixed up
# geneScaffolds yes
'_EOF_'
# << happy emacs
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-ensVersion=49 -stop=process bosTau3.ensGene.ra
# do the manual fixups as described above
doEnsGeneUpdate.pl -continue=load -ensVersion=49 bosTau3.ensGene.ra
ssh hgwdev
cd /cluster/data/bosTau3/bed/ensGene.49
featureBits bosTau3 ensGene
# 39278215 bases of 2731807384 (1.438%) in intersection
############################################################################
# canFam2 - Dog - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore04
cd /cluster/data/canFam2
cat << '_EOF_' > canFam2.ensGene.ra
# required db variable
db canFam2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 canFam2.ensGene.ra
ssh hgwdev
cd /cluster/data/canFam2/bed/ensGene.49
featureBits canFam2 ensGene
# 34551622 bases of 2384996543 (1.449%) in intersection
############################################################################
# ci2 - C. intestinalis - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore02
cd /cluster/data/ci2
cat << '_EOF_' > ci2.ensGene.ra
# required db variable
db ci2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][pq]\)/chr0\1/; s/^\([0-9][0-9][pq]\)/chr\1/; "
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 ci2.ensGene.ra
ssh hgwdev
cd /cluster/data/ci2/bed/ensGene.49
featureBits ci2 ensGene
# 20121618 bases of 141233565 (14.247%) in intersection
############################################################################
# cioSav2 - C. savignyi - Ensembl Genes (DONE - 2008-04-03 - hiram)
ssh kkstore02
cd /cluster/data/cioSav2
cat << '_EOF_' > cioSav2.ensGene.ra
# required db variable
db cioSav2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
# nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 cioSav2.ensGene.ra
# the names in this assembly exceeded our usual size of 18 characters
# have to do the load manually with a customized ensGtp.sql
# to set the index sizes to 19
ssh hgwdev
cd /cluster/data/cioSav2/bed/ensGene.49
featureBits cioSav2 ensGene
# 16603725 bases of 173749524 (9.556%) in intersection
############################################################################
# danRer5 - Zebrafish - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore06
cd /cluster/data/danRer5
cat << '_EOF_' > danRer5.ensGene.ra
# required db variable
db danRer5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 danRer5.ensGene.ra
ssh hgwdev
cd /cluster/data/danRer5/bed/ensGene.49
featureBits danRer5 ensGene
# 36884539 bases of 1435609608 (2.569%) in intersection
############################################################################
# dasNov1 - Armadillo - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore04
cd /cluster/data/dasNov1
cat << '_EOF_' > dasNov1.ensGene.ra
# required db variable
db dasNov1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSDNOT00000004471 no exonFrame on CDS exon 7
# ENSDNOT00000007696 no exonFrame on CDS exon 8
# ENSDNOT00000019234 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 dasNov1.ensGene.ra
ssh hgwdev
cd /cluster/data/dasNov1/bed/ensGene.49
featureBits dasNov1 ensGene
# 22682674 bases of 2146362222 (1.057%) in intersection
############################################################################
# echTel1 - Tenrec - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore02
cd /cluster/data/echTel1
cat << '_EOF_' > echTel1.ensGene.ra
# required db variable
db echTel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSETET00000011172 no exonFrame on CDS exon 14
# ENSETET00000018714 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 echTel1.ensGene.ra
ssh hgwdev
cd /cluster/data/echTel1/bed/ensGene.49
featureBits echTel1 ensGene
# 25450282 bases of 2111581369 (1.205%) in intersection
############################################################################
# felCat3 - Cat - Ensembl Genes (DONE - 2008-04-01 - hiram)
ssh kkstore05
cd /cluster/data/felCat3
cat << '_EOF_' > felCat3.ensGene.ra
# required db variable
db felCat3
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSFCAT00000006929 no exonFrame on CDS exon 15
# ENSFCAT00000009384 no exonFrame on CDS exon 0
# ENSFCAT00000010965 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 felCat3.ensGene.ra
ssh hgwdev
cd /cluster/data/felCat3/bed/ensGene.49
featureBits felCat3 ensGene
# 20984470 bases of 1642698377 (1.277%) in intersection
############################################################################
# galGal3 - Chicken - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore03
cd /cluster/data/galGal3
cat << '_EOF_' > galGal3.ensGene.ra
# required db variable
db galGal3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9EWXYZ][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 galGal3.ensGene.ra
ssh hgwdev
cd /cluster/data/galGal3/bed/ensGene.49
featureBits galGal3 ensGene
# 30853095 bases of 1042591351 (2.959%) in intersection
############################################################################
# gasAcu1 - Stickleback - Ensembl Genes (DONE - 2008-04-02 - hiram)
ssh kkstore05
cd /cluster/data/gasAcu1
cat << '_EOF_' > gasAcu1.ensGene.ra
# required db variable
db gasAcu1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^group\([IUVX]\)/chr\1/; s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 gasAcu1.ensGene.ra
# to fix the processing failures, in the process directory:
zcat gasAcu1.allGenes.gp.beforeLift.gz \
| liftUp -extGenePred -type=.gp gasAcu1.scaffolds.gp \
../../../jkStuff/contigsToScaffolds.lft carry stdin
liftUp -extGenePred gasAcu1.allGenes.gp \
../../../jkStuff/UCSC.chromToScaffoldSansGaps.lft carry \
gasAcu1.scaffolds.gp
gzip gasAcu1.scaffolds.gp
# then continue with the load
doEnsGeneUpdate.pl -continue=load -ensVersion=49 gasAcu1.ensGene.ra
ssh hgwdev cd /cluster/data/gasAcu1/bed/ensGene.49 featureBits gasAcu1 ensGene
# 36957312 bases of 446627861 (8.275%) in intersection
############################################################################
# fr2 - Fugu - Ensembl Genes (DONE - 2008-04-02 - hiram)
# fixed the fr2.ensGene.ra file to translate MT into chrM
ssh kkstore02
cd /cluster/data/fr2
cat << '_EOF_' > fr2.ensGene.ra
# required db variable
db fr2
nameTranslation "s/^MT/chrM/;"
# lift Ensembl scaffolds to UCSC chrUn coordinates
liftUp /cluster/data/fr2/jkStuff/liftAll.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 fr2.ensGene.ra
ssh hgwdev cd /cluster/data/fr2/bed/ensGene.49 featureBits fr2 ensGene
# 34552659 bases of 393312790 (8.785%) in intersection
############################################################################
# mm9 - Mouse - Ensembl Genes (DONE - 2008-04-01 - hiram)
ssh kkstore06
cd /cluster/data/mm9
cat << '_EOF_' > mm9.ensGene.ra
# required db variable
db mm9
# optional liftRandoms yes/no or absent
liftRandoms yes
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 mm9.ensGene.ra
ssh hgwdev
cd /cluster/data/mm9/bed/ensGene.49
featureBits mm9 ensGene
# 60655001 bases of 2620346127 (2.315%) in intersection
############################################################################
# ornAna1 - Platypus - Ensembl Genes (DONE - 2008-04-03 - hiram)
ssh kkstore05
cd /cluster/data/ornAna1
cat << '_EOF_' > ornAna1.ensGene.ra
# required db variable
db ornAna1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^\(X[0-9]\)/chr\1/; s/^MT/chrM/"
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 ornAna1.ensGene.ra
ssh hgwdev
cd /cluster/data/ornAna1/bed/ensGene.49
featureBits ornAna1 ensGene
# 24473045 bases of 1842236818 (1.328%) in intersection
############################################################################
# oryCun1 - Rabbit - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore04
cd /cluster/data/oryCun1
cat << '_EOF_' > oryCun1.ensGene.ra
# required db variable
db oryCun1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSOCUT00000004627 no exonFrame on CDS exon 3
# ENSOCUT00000009485 no exonFrame on CDS exon 9
# ENSOCUT00000014840 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 oryCun1.ensGene.ra
ssh hgwdev
cd /cluster/data/oryCun1/bed/ensGene.49
featureBits oryCun1 ensGene
# 22761080 bases of 2076044328 (1.096%) in intersection
############################################################################
# oryLat1 - Medaka - Ensembl Genes (DONE - 2008-03-31 - 04-15 - hiram)
ssh kkstore04
cd /cluster/data/oryLat1
cat << '_EOF_' > oryLat1.ensGene.ra
# required db variable
db oryLat1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^MT/chrM/"
# ignore 2,687 genes that haven't lifted properly yet
skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 oryLat1.ensGene.ra
featureBits oryLat1 ensGene
# 29680340 bases of 700386597 (4.238%) in intersection
# version 49 update had a big change in the Medaka genes.
# Many of the new genes are in the Ensembl Gene Scaffold
# (actually here ultracontigs) coordinate space that will not
# translate to our chrUn assembly. So, some fixups are
# necessary to get joinerCheck to be a bit more happy.
ssh hgwdev
cd ~/kent/src/hg/makeDb/schema
joinerCheck -keys -database=oryLat1 -identifier=ensemblTranscriptId \
all.joiner
# Checking keys on database oryLat1
# oryLat1.ensGtp.transcript - hits 22447 of 25134
# Error: 2687 of 25134 elements of oryLat1.ensGtp.transcript are not in key ensGene.name line 1726 of all.joiner
# Example miss: ENSORLT00000022895
# oryLat1.ensPep.name - hits 22053 of 24661
# Error: 2608 of 24661 elements of oryLat1.ensPep.name are not in key ensGene.name line 1728 of all.joiner
# Example miss: ENSORLT00000022872
cd /cluster/data/oryLat1/bed/ensGene.49
grep "invalid chrom" *.errors.txt | cut -d\ -f2 | sort -u > badLifts.name
hgsql -N -e "select transcript from ensGtp;" oryLat1 \
| sort > ensGtp.transcript
comm -13 ensGene.name ensGtp.transcript | sort > ensGtp.not.ensGene.name
comm -13 ensGene.name ensPep.name | sort > ensPep.not.ensGene.name
# do the badLifts account for all the missing peptides:
comm -12 badLifts.name ensPep.not.ensGene.name | wc -l
# 2608 -> yes, this is the count of missing peptides.
# So, remove this set of business from ensPep table
for N in `cat badLifts.name`
do
hgsql -e "delete from ensPep where name=\"$N\";" oryLat1
echo $N
done
# And from the ensGtp table
for N in `cat badLifts.name`
do
hgsql -e "delete from ensGtp where transcript=\"$N\";" oryLat1
echo $N
done
############################################################################
############################################################################
# otoGar1 - Bushbaby - Ensembl Genes (DONE - 2008-04-03 - hiram)
ssh kkstore05
cd /cluster/data/otoGar1
cat << '_EOF_' > otoGar1.ensGene.ra
# required db variable
db otoGar1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/otoGar1/jkStuff/ensGene.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 otoGar1.ensGene.ra
ssh hgwdev
cd /cluster/data/otoGar1/bed/ensGene.49
featureBits otoGar1 ensGene
# 23497004 bases of 1969052059 (1.193%) in intersection
############################################################################
# panTro2 - Chimp - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore04
cd /cluster/data/panTro2
cat << '_EOF_' > panTro2.ensGene.ra
# required db variable
db panTro2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 panTro2.ensGene.ra
ssh hgwdev
cd /cluster/data/panTro2/bed/ensGene.49
featureBits panTro2 ensGene
# 51932042 bases of 2909485072 (1.785%) in intersection
############################################################################
# ponAbe2 - Orangutan - Ensembl Genes (DONE - 2008-04-01 - hiram)
ssh kkstore02
cd /cluster/data/ponAbe2
cat << '_EOF_' > ponAbe2.ensGene.ra
# required db variable
db ponAbe2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
# haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 ponAbe2.ensGene.ra
ssh hgwdev
cd /cluster/data/ponAbe2/bed/ensGene.49
featureBits ponAbe2 ensGene
# 37382766 bases of 3093572278 (1.208%) in intersection
############################################################################
# rheMac2 - Rhesus - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore01
cd /cluster/data/rheMac2
cat << '_EOF_' > rheMac2.ensGene.ra
# required db variable
db rheMac2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^109[0-9]*/d; /^MT/d; s/^\([0-9XY][0-9]*\)/chr\1/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 rheMac2.ensGene.ra
ssh hgwdev
cd /cluster/data/rheMac2/bed/ensGene.49
featureBits rheMac2 ensGene
# 44288934 bases of 2646704109 (1.673%) in intersection
############################################################################
# rn4 - Rat - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore06
cd /cluster/data/rn4
cat << '_EOF_' > rn4.ensGene.ra
# required db variable
db rn4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 rn4.ensGene.ra
ssh hgwdev
cd /cluster/data/rn4/bed/ensGene.49
featureBits rn4 ensGene
# 43706532 bases of 2571531505 (1.700%) in intersection
############################################################################
# sacCer1 - S. cerevisiae - Ensembl Genes (DONE - 2008-04-03 - hiram)
ssh kkstore03
cd /cluster/data/sacCer1
cat << '_EOF_' > sacCer1.ensGene.ra
# required db variable
db sacCer1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^VIII/chr8/; s/^VII/chr7/; s/^VI/chr6/; s/^V/chr5/; s/^XIII/chr13/; s/^XII/chr12/; s/^XIV/chr14/; s/^XI/chr11/; s/^XVI/chr16/; s/^XV/chr15/; s/^X/chr10/; s/^III/chr3/; s/^IV/chr4/; s/^II/chr2/; s/^IX/chr9/; s/^I/chr1/; s/^MT/chrM/; /2-micron/d"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 sacCer1.ensGene.ra
ssh hgwdev
cd /cluster/data/sacCer1/bed/ensGene.49
featureBits sacCer1 ensGene
# 8908962 bases of 12156302 (73.287%) in intersection
# this genome has trouble with featureBits: table gap doesn't exist
############################################################################
# tetNig1 - Tetraodon - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore03
cd /cluster/data/tetNig1
cat << '_EOF_' > tetNig1.ensGene.ra
# required db variable
db tetNig1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 tetNig1.ensGene.ra
ssh hgwdev
cd /cluster/data/tetNig1/bed/ensGene.49
featureBits tetNig1 ensGene
# 37844709 bases of 342403326 (11.053%) in intersection
############################################################################
# tupBel1 - TreeShrew - Ensembl Genes (DONE - 2008-04-03 - hiram)
ssh kkstore05
cd /cluster/data/tupBel1
cat << '_EOF_' > tupBel1.ensGene.ra
# required db variable
db tupBel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/tupBel1/jkStuff/ensGene.lft
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSTBET00000015831 no exonFrame on CDS exon 11
# ENSTBET00000013522 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 tupBel1.ensGene.ra
ssh hgwdev
cd /cluster/data/tupBel1/bed/ensGene.49
featureBits tupBel1 ensGene
# 22740204 bases of 2137225476 (1.064%) in intersection
############################################################################
# xenTro2 - X. tropicalis - Ensembl Genes (DONE - 2008-03-31 - hiram)
ssh kkstore04
cd /cluster/data/xenTro2
cat << '_EOF_' > xenTro2.ensGene.ra
# required db variable
db xenTro2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=49 xenTro2.ensGene.ra
ssh hgwdev
cd /cluster/data/xenTro2/bed/ensGene.49
featureBits xenTro2 ensGene
# 29161645 bases of 1359412157 (2.145%) in intersection
############################################################################
############################################################################
# ensembl 48 updates
############################################################################
# The following was generated in the following manner:
ssh hgwdev
cd /tmp
for D in bosTau3 canFam2 ci2 danRer5 dasNov1 echTel1 felCat3 fr2 galGal3 \
gasAcu1 hg18 loxAfr1 mm9 ornAna1 oryCun1 oryLat1 otoGar1 panTro2 \
rheMac2 rn4 sacCer1 tetNig1 tupBel1 xenTro2
do
cd /cluster/data/${D}
$HOME/kent/src/hg/utils/automation/doEnsGeneUpdate.pl \
-verbose=0 -ensVersion=48 ${D}.ensGene.ra -continue=makeDoc
done
# The database names were found by the following:
cd /cluster/data
ls -d */*.ensGene.ra | sed -e "s#/.*##"
# The following is the output of the above for loop:
############################################################################
# bosTau3 - Cow - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore05
cd /cluster/data/bosTau3
cat << '_EOF_' > bosTau3.ensGene.ra
# required db variable
db bosTau3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^Un/d; s/^\([0-9X][0-9]*\)/chr\1/; /^MT/d"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 bosTau3.ensGene.ra
featureBits bosTau3 ensGene
# 35387571 bases of 2731807384 (1.295%) in intersection
############################################################################
# canFam2 - Dog - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore04
cd /cluster/data/canFam2
cat << '_EOF_' > canFam2.ensGene.ra
# required db variable
db canFam2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 canFam2.ensGene.ra
featureBits canFam2 ensGene
# 34551622 bases of 2384996543 (1.449%) in intersection
############################################################################
# ci2 - C. intestinalis - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore02
cd /cluster/data/ci2
cat << '_EOF_' > ci2.ensGene.ra
# required db variable
db ci2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][pq]\)/chr0\1/; s/^\([0-9][0-9][pq]\)/chr\1/; "
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 ci2.ensGene.ra
featureBits ci2 ensGene
# 20121618 bases of 141233565 (14.247%) in intersection
############################################################################
# danRer5 - Zebrafish - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore06
cd /cluster/data/danRer5
cat << '_EOF_' > danRer5.ensGene.ra
# required db variable
db danRer5
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 danRer5.ensGene.ra
featureBits danRer5 ensGene
# 36884539 bases of 1435609608 (2.569%) in intersection
############################################################################
############################################################################
# dasNov1 - Armadillo - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore04
cd /cluster/data/dasNov1
cat << '_EOF_' > dasNov1.ensGene.ra
# required db variable
db dasNov1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSDNOT00000004471 no exonFrame on CDS exon 7
# ENSDNOT00000007696 no exonFrame on CDS exon 8
# ENSDNOT00000019234 no exonFrame on CDS exon 0
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 dasNov1.ensGene.ra
featureBits dasNov1 ensGene
# 22684492 bases of 2146362222 (1.057%) in intersection
############################################################################
############################################################################
# echTel1 - Tenrec - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore02
cd /cluster/data/echTel1
cat << '_EOF_' > echTel1.ensGene.ra
# required db variable
db echTel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSETET00000011172 no exonFrame on CDS exon 14
# ENSETET00000018714 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 echTel1.ensGene.ra
featureBits echTel1 ensGene
# 25450282 bases of 2111581369 (1.205%) in intersection
############################################################################
############################################################################
# felCat3 - Cat - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore05
cd /cluster/data/felCat3
cat << '_EOF_' > felCat3.ensGene.ra
# required db variable
db felCat3
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSFCAT00000006929 no exonFrame on CDS exon 15
# ENSFCAT00000009384 no exonFrame on CDS exon 0
# ENSFCAT00000010965 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 felCat3.ensGene.ra
featureBits felCat3 ensGene
# 20984470 bases of 1642698377 (1.277%) in intersection
############################################################################
############################################################################
# fr2 - Fugu - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore02
cd /cluster/data/fr2
cat << '_EOF_' > fr2.ensGene.ra
# required db variable
db fr2
# lift Ensembl scaffolds to UCSC chrUn coordinates
liftUp /cluster/data/fr2/jkStuff/liftAll.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 fr2.ensGene.ra
featureBits fr2 ensGene
# 32309856 bases of 393312790 (8.215%) in intersection
############################################################################
############################################################################
# galGal3 - Chicken - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore03
cd /cluster/data/galGal3
cat << '_EOF_' > galGal3.ensGene.ra
# required db variable
db galGal3
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9EWXYZ][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 galGal3.ensGene.ra
featureBits galGal3 ensGene
# 30853095 bases of 1042591351 (2.959%) in intersection
############################################################################
############################################################################
# gasAcu1 - Stickleback - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore05
cd /cluster/data/gasAcu1
cat << '_EOF_' > gasAcu1.ensGene.ra
# required db variable
db gasAcu1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^group\([IUVX]\)/chr\1/; s/^MT/chrM/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 gasAcu1.ensGene.ra
featureBits gasAcu1 ensGene
# 36960585 bases of 446627861 (8.275%) in intersection
############################################################################
############################################################################
# hg18 - Human - Ensembl Genes (DONE - 2008-02-27 - hiram)
ssh kkstore02
cd /cluster/data/hg18
cat << '_EOF_' > hg18.ensGene.ra
# required db variable
db hg18
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
# optional haplotype lift-down from Ensembl full chrom coordinates
# to UCSC simple haplotype coordinates
haplotypeLift /cluster/data/hg18/jkStuff/ensGene.haplotype.lift
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 hg18.ensGene.ra
featureBits hg18 ensGene
# 66667439 bases of 2881515245 (2.314%) in intersection
############################################################################
############################################################################
# loxAfr1 - Elephant - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore04
cd /cluster/data/loxAfr1
cat << '_EOF_' > loxAfr1.ensGene.ra
# required db variable
db loxAfr1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the one gene that has an invalid structure from Ensembl:
# ENSLAFT00000000586 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 loxAfr1.ensGene.ra
featureBits loxAfr1 ensGene
# 23294087 bases of 2295548473 (1.015%) in intersection
############################################################################
############################################################################
# mm9 - Mouse - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore06
cd /cluster/data/mm9
cat << '_EOF_' > mm9.ensGene.ra
# required db variable
db mm9
# optional liftRandoms yes/no or absent
liftRandoms yes
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 mm9.ensGene.ra
featureBits mm9 ensGene
# 62429979 bases of 2620346127 (2.383%) in intersection
############################################################################
############################################################################
# ornAna1 - Platypus - Ensembl Genes (DONE - 2008-02-26 - hiram)
ssh kkstore05
cd /cluster/data/ornAna1
cat << '_EOF_' > ornAna1.ensGene.ra
# required db variable
db ornAna1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^\(X[0-9]\)/chr\1/; s/^MT/chrM/"
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 ornAna1.ensGene.ra
featureBits ornAna1 ensGene
# 24477086 bases of 1842236818 (1.329%) in intersection
############################################################################
############################################################################
# oryCun1 - Rabbit - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore04
cd /cluster/data/oryCun1
cat << '_EOF_' > oryCun1.ensGene.ra
# required db variable
db oryCun1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the three genes that have invalid structures from Ensembl:
# ENSOCUT00000004627 no exonFrame on CDS exon 3
# ENSOCUT00000009485 no exonFrame on CDS exon 9
# ENSOCUT00000014840 no exonFrame on CDS exon 3
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 oryCun1.ensGene.ra
featureBits oryCun1 ensGene
# 22763228 bases of 2076044328 (1.096%) in intersection
############################################################################
############################################################################
# oryLat1 - Medaka - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore04
cd /cluster/data/oryLat1
cat << '_EOF_' > oryLat1.ensGene.ra
# required db variable
db oryLat1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9][0-9]*\)/chr\1/; s/^MT/chrM/"
# ignore 66 genes that haven't lifted properly yet
skipInvalid yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 oryLat1.ensGene.ra
featureBits oryLat1 ensGene
# 31757387 bases of 700386597 (4.534%) in intersection
############################################################################
############################################################################
# otoGar1 - Bushbaby - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore05
cd /cluster/data/otoGar1
cat << '_EOF_' > otoGar1.ensGene.ra
# required db variable
db otoGar1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/otoGar1/jkStuff/ensGene.lft
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 otoGar1.ensGene.ra
featureBits otoGar1 ensGene
# 23498471 bases of 1969052059 (1.193%) in intersection
############################################################################
############################################################################
# panTro2 - Chimp - Ensembl Genes (DONE - 2008-02-26 - hiram)
ssh kkstore04
cd /cluster/data/panTro2
cat << '_EOF_' > panTro2.ensGene.ra
# required db variable
db panTro2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 panTro2.ensGene.ra
featureBits panTro2 ensGene
# 51969416 bases of 2909485072 (1.786%) in intersection
############################################################################
############################################################################
# rheMac2 - Rhesus - Ensembl Genes (DONE - 2008-02-28 - hiram)
ssh kkstore01
cd /cluster/data/rheMac2
cat << '_EOF_' > rheMac2.ensGene.ra
# required db variable
db rheMac2
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "/^109[0-9]*/d; /^MT/d; s/^\([0-9XY][0-9]*\)/chr\1/;"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 rheMac2.ensGene.ra
featureBits rheMac2 ensGene
# 44305902 bases of 2646704109 (1.674%) in intersection
############################################################################
############################################################################
# rn4 - Rat - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore06
cd /cluster/data/rn4
cat << '_EOF_' > rn4.ensGene.ra
# required db variable
db rn4
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/"
# optionally update the knownToEnsembl table after ensGene updated
knownToEnsembl yes
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 rn4.ensGene.ra
featureBits rn4 ensGene
# 44218002 bases of 2571531505 (1.720%) in intersection
############################################################################
############################################################################
# sacCer1 - S. cerevisiae - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore03
cd /cluster/data/sacCer1
cat << '_EOF_' > sacCer1.ensGene.ra
# required db variable
db sacCer1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^VIII/chr8/; s/^VII/chr7/; s/^VI/chr6/; s/^V/chr5/; s/^XIII/chr13/; s/^XII/chr12/; s/^XIV/chr14/; s/^XI/chr11/; s/^XVI/chr16/; s/^XV/chr15/; s/^X/chr10/; s/^III/chr3/; s/^IV/chr4/; s/^II/chr2/; s/^IX/chr9/; s/^I/chr1/; s/^MT/chrM/; /2-micron/d"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 sacCer1.ensGene.ra
featureBits sacCer1 ensGene
# table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
table gap doesn't exist
8908962 bases of 12156302 (73.287%) in intersection
############################################################################
############################################################################
# tetNig1 - Tetraodon - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore03
cd /cluster/data/tetNig1
cat << '_EOF_' > tetNig1.ensGene.ra
# required db variable
db tetNig1
# optional nameTranslation, the sed command that will transform
# Ensemble names to UCSC names. With quotes just to make sure.
nameTranslation "s/^\([0-9XY][0-9]*\)/chr\1/; s/^MT/chrM/; s/^Un/chrUn/"
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 tetNig1.ensGene.ra
featureBits tetNig1 ensGene
# 37871392 bases of 342403326 (11.060%) in intersection
############################################################################
############################################################################
# tupBel1 - TreeShrew - Ensembl Genes (DONE - 2008-02-29 - hiram)
ssh kkstore05
cd /cluster/data/tupBel1
cat << '_EOF_' > tupBel1.ensGene.ra
# required db variable
db tupBel1
# do we need to translate geneScaffold coordinates
geneScaffolds yes
# after geneScaffold conversions, change Ensembl chrom names to UCSC names
liftUp /cluster/data/tupBel1/jkStuff/ensGene.lft
# ignore genes that do not properly convert to a gene pred, and contig
# names that are not in the UCSC assembly
skipInvalid yes
# ignore the two genes that have invalid structures from Ensembl:
# ENSTBET00000015831 no exonFrame on CDS exon 11
# ENSTBET00000013522 no exonFrame on CDS exon 1
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 tupBel1.ensGene.ra
featureBits tupBel1 ensGene
# 22740204 bases of 2137225476 (1.064%) in intersection
############################################################################
############################################################################
# xenTro2 - X. tropicalis - Ensembl Genes (DONE - 2008-03-03 - hiram)
ssh kkstore04
cd /cluster/data/xenTro2
cat << '_EOF_' > xenTro2.ensGene.ra
# required db variable
db xenTro2
'_EOF_'
# << happy emacs
doEnsGeneUpdate.pl -ensVersion=48 xenTro2.ensGene.ra
featureBits xenTro2 ensGene
# 29163250 bases of 1359412157 (2.145%) in intersection
############################################################################
############################################################################
############################################################################
# Archive of Robert's procedure to update the Ensembl gene tracks
############################################################################
#load ensembl gene predictions (build 43) and related tables by downloading from ensembl ftp site (Robert Mar 14,2007)
#following tables are loaded
#ensGene ensGeneChk ensGeneChkDetails ensGeneXref ensGtp ensInfo ensPseudo superfamily sfDescription knownToEnsembl
#scripts used:
#hgLoadEnsembl - main driver script that calls ensemblDownload, ensemblDbImport and loadEnsembl
#ensemblDownload - downloads data from ensembl ftp site to directory, creates tables.tmp containing list of ensembl tables to be loaded
#ensemblDbImport - loads tables into temporary database using the native ensembl mysql table structure
#exportEnsembl - creates genePred files from the ensembl temporary database
#geneCheckAndLoad - runs gene-check on a genePred and loads the two details tables into the database.
#ensemblSuperfamily - load superfamily track using Ensembl cross reference
#loadEnsembl - loads data created by exportEnsembl into ensGene, creates and loads ensInfo table with attributes
#ensemblGetAll - generates script to load all ensembl builds, requires manual editting to add ucsc database
#ensGeneToGenePred - awk script called by loadEnsembl that converts dump of ensembl exons to genePred format
#mkRandomNTLift - read ctgPos table and make lift file
cd ~/kent/src/hg/makeDb/outside/ensembl
make
mkdir -p /cluster/store8/ensembl/run.build43
cd /cluster/store8/ensembl/run.build43
mkRandomNTLift hg18 > lift.hg18
mkRandomNTLift mm8 > lift.mm8
hgLoadEnsembl -l /cluster/store8/ensembl/run.build43/lift.hg18 homo_sapiens core_43_36e /cluster/store8/ensembl/homo_sapiens_43_36e hg18
hgLoadEnsembl -l /cluster/store8/ensembl/run.build43/lift.mm8 mus_musculus core_43_36d /cluster/store8/ensembl/mus_musculus_43_36d mm8
hgLoadEnsembl rattus_norvegicus core_43_34m /cluster/store8/ensembl/rattus_norvegicus_43_34m rn4
hgLoadEnsembl pan_troglodytes core_43_21b /cluster/store8/ensembl/pan_troglodytes_43_21b panTro2
hgLoadEnsembl canis_familiaris core_43_2a /cluster/store8/ensembl/canis_familiaris_43_2a canFam2
#hgLoadEnsembl danio_rerio core_43_6d /cluster/store8/ensembl/danio_rerio_43_6d danRer4