44ac62ce8e655528d624d2b861b358981599d044
hiram
  Wed Jun 2 12:08:22 2021 -0700
Ensembl v104 update complete refs #27616

diff --git src/hg/makeDb/doc/makeEnsembl.txt src/hg/makeDb/doc/makeEnsembl.txt
index f3918db..8aabb5f 100644
--- src/hg/makeDb/doc/makeEnsembl.txt
+++ src/hg/makeDb/doc/makeEnsembl.txt
@@ -1,22 +1,71 @@
 # 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 104 update (DONE - 2021-05-11 - Hiram)
+############################################################################
+# when all done, reset the dateReference:  (DONE - 2021-06-02 - Hiram)
+     # next time, this first one will be 104 at 'may2021'
+     hgsql -e \
+'update trackVersion set dateReference="aug2020" where name="ensGene" AND version="101";' hgFixed
+     hgsql -e \
+'update trackVersion set dateReference="current" where name="ensGene" AND version="104";' hgFixed
+
+# Prepare for asmEquivalent construction
+  cd /cluster/home/hiram/kent/src/hg/utils/automation
+  ./findEnsFtpNames.sh  104
+  # constructs files:
+# -rw-rw-r-- 1   149366 May 11 09:50 release.104.gtf.ls-lR
+# -rw-rw-r-- 1    22739 May 11 09:50 release.104.gtf.names
+# -rw-rw-r-- 1 10922563 May 11 09:52 release.104.MySQL.ls-lR
+# -rw-rw-r-- 1    12686 May 11 09:52 release.104.MySQL.names
+# -rw-rw-r-- 1  2173791 May 11 09:52 release.104.fasta.ls-lR
+# -rw-rw-r-- 1    25090 May 11 09:52 release.104.fasta.names
+
+  mkdir /hive/data/outside/ensembl/genomes/release-104
+  cd /hive/data/outside/ensembl/genomes/release-104
+  sed -e 's/103/104/;' ../release-103/fromPepNames.sh > fromPepNames.sh
+  ./fromPepNames.sh > dnaTopLevel.list
+  wc -l *.list
+  # 310 dnaTopLevel.list
+  diff dnaTopLevel.list ../release-103/dnaTopLevel.list
+# 104c104
+# < ficedula_albicollis/dna/Ficedula_albicollis.FicAlb1.5.dna.toplevel.fa.gz
+# ---
+# > ficedula_albicollis/dna/Ficedula_albicollis.FicAlb_1.4.dna.toplevel.fa.gz
+# 259c259
+# < scophthalmus_maximus/dna/Scophthalmus_maximus.ASM1334776v1.dna.toplevel.fa.gz
+# ---
+# > scophthalmus_maximus/dna/Scophthalmus_maximus.ASM318616v1.dna.toplevel.fa.gz
+
+  sed -e 's/103/104/; s/101/103/;' ../release-103/fetch.sh > fetch.sh
+  time (./fetch.sh) >> fetch.log 2>&1
+
+
+
+############################################################################
+# ensembl 103 update (DONE - 2021-03-12 - Hiram)
+############################################################################
+# The asmEquivalent table needs to be brought up to date first
+# following the instructions in: assemblyEquivalence/update.2021-03-10.txt
+# to perform that update
+
+############################################################################
 # ensembl 101 update (DONE - 2020-08-31 - Hiram)
 ############################################################################
 # when all done, reset the dateReference:  (DONE - 2020-09-01 - Hiram)
      # next time, this first one will be 101 at 'aug2020'
      hgsql -e \
 'update trackVersion set dateReference="jan2020" where name="ensGene" AND version="99";' hgFixed
      hgsql -e \
 'update trackVersion set dateReference="current" where name="ensGene" AND version="101";' hgFixed
 
 # follow the procedure in assemblyEquivalence/update.2020-08-31.txt
 # to construct equivalence listings.  After that is completed and
 # the hgFixed.asmEquivalent table is reloaded, continue here:
 
   mkdir /hive/data/outside/ensembl/ensGene/v101
   cd /hive/data/outside/ensembl/ensGene/v101