ec42546aa8efd2a5801969e60dd52bb7d9d5948d
galt
  Sat Apr 10 01:33:17 2021 -0700
fixing small error

diff --git src/hg/makeDb/doc/grcM38P6.txt src/hg/makeDb/doc/grcM38P6.txt
index 0c8d548..dfa7a34 100644
--- src/hg/makeDb/doc/grcM38P6.txt
+++ src/hg/makeDb/doc/grcM38P6.txt
@@ -13,34 +13,34 @@
     mkdir -p /hive/data/genomes/grcM38P6/genbank
     cd /hive/data/genomes/grcM38P6/genbank
 
     # Releases have already been downloaded to /hive/data/outside/ncbi/genomes/.
     ln -s /hive/data/outside/ncbi/genomes/genbank/vertebrate_mammalian/Mus_musculus/all_assembly_versions/GCA_000001635.8_GRCm38.p6/* .
 
 
 ##############################################################################
 # Set up fasta and agp with UCSC names (DONE - 2020-02-27 - Angie)
 
     mkdir /hive/data/genomes/grcM38P6/ucsc
     cd /hive/data/genomes/grcM38P6/ucsc
 
     # identify sequences not in existing genome db
     faCount ../genbank/GCA_000001635.8_GRCm38.p6_genomic.fna.gz \
-      > faCount.GRCm38.p13.txt
+      > faCount.GRCm38.p6.txt
     ~/kent/src/hg/makeDb/doc/mm10.scanAssemblyReport.pl \
       /hive/data/genomes/mm10/chrom.sizes \
-      faCount.GRCm38.p13.txt ../genbank/GCA_000001635.8_GRCm38.p6_assembly_report.txt \
+      faCount.GRCm38.p6.txt ../genbank/GCA_000001635.8_GRCm38.p6_assembly_report.txt \
     | grep -w new > new.sequences.list
     wc -l new.sequences.list
 #173 new.sequences.list
 
     # Extract UCSC-named FASTA for the new sequences
     cut -f3 new.sequences.list > extract.new.list
     awk '{printf "s/%s/%s/; ", $3,$1}' new.sequences.list > genbankToUCSC.sed
     faSomeRecords ../genbank/GCA_000001635.8_GRCm38.p6_genomic.fna.gz extract.new.list stdout \
     | sed -e 's/ .*//;' \
     | sed -f genbankToUCSC.sed \
     | gzip -c > grcM38P6.fa.gz
     faSize grcM38P6.fa.gz
 
 #88102774 bases (1347579 N's 86755195 real 55734044 upper 31021151 lower) in 173 sequences in 1 files
 #Total size: mean 509264.6 sd 841533.2 min 25407 (chr19_JH584319_alt) max 5956088 (chr6_GL456054_alt) median 250595
@@ -70,52 +70,52 @@
     twoBitInfo grcM38P6.unmasked.2bit stdout | sort -k2nr > chrom.sizes
     # take a look at chrom.sizes to verify it looks OK.
 
     # Make sure AGP and FASTA/2bit agree:
     checkAgpAndFa ucsc/grcM38P6.agp grcM38P6.unmasked.2bit | tail -1
 #All AGP and FASTA entries agree - both files are valid
 
 
 ##############################################################################
 # establish config.ra file (DONE - Angie - 2020-02-27)
     # arguments here are: <db> <clade> <trackDbDir> <assembly_report.txt>
     cd /hive/data/genomes/grcM38P6
     # Must make photoReference.txt first -- copy from mm10
     cp /hive/data/genomes/mm10/photoReference.txt .
     $HOME/kent/src/hg/utils/automation/prepConfig.pl grcM38P6 haplotypes \
-        GRCm38.p13 genbank/*_assembly_report.txt > grcM38P6.config.ra
+        GRCm38.p6 genbank/*_assembly_report.txt > grcM38P6.config.ra
     # Edit grcM38P6.config.ra to avoid confusion with actual mm10
 assemblyDate Sep. 2017 p6
 
     sed -e 's/^/#/' grcM38P6.config.ra
 ## config parameters for makeGenomeDb.pl:
 #db grcM38P6
 #clade haplotypes
 #genomeCladePriority 134
 #scientificName Mus musculus
 #commonName House mouse
 #assemblyDate Sep. 2017 p6
 #assemblyLabel Genome Reference Consortium
 #assemblyShortLabel GRCm38.p6
 #orderKey 8695
 ## mitochondrial sequence included in refseq release
 ## mitoAcc AY172335.1
 #mitoAcc none
 #fastaFiles /hive/data/genomes/grcM38P6/ucsc/*.fa.gz
 #agpFiles /hive/data/genomes/grcM38P6/ucsc/*.agp
 ## qualFiles none
-#dbDbSpeciesDir GRCm38.p13
+#dbDbSpeciesDir GRCm38.p6
 #photoCreditURL http://www.jax.org/
 #photoCreditName        Photo courtesy of The Jackson Laboratory
 #ncbiGenomeId 52
 #ncbiAssemblyId 1198761
 #ncbiAssemblyName GRCm38.p6
 #ncbiBioProject 20689
 #ncbiBioSample notFound
 #genBankAccessionID GCF_000001635.26
 #taxId 10090
 
 
 ##############################################################################
 #  Initial database build (DONE - 2020-02-27 - Angie)
 
     cd /hive/data/genomes/grcM38P6