# for emacs: -*- mode: sh; -*-

# This file describes browser build for the nanPar1
# Nanorana parkeri - Tibetan frog

# http://www.ncbi.nlm.nih.gov/Traces/wgs/?val=JYOU01

# the description page is missing from the genbank directory

# there is no chrMt sequence in this release or in NCBI nucleotide

#############################################################################
# fetch sequence from new style download directory (DONE - 2015-03-03 - Hiram)
    # NCBI has redesigned their FTP download site, new type of address
    #      and naming scheme
    mkdir -p /hive/data/genomes/nanPar1/genbank
    cd /hive/data/genomes/nanPar1/genbank

    time rsync -L -a -P \
rsync://ftp.ncbi.nlm.nih.gov/genomes/genbank/vertebrate_other/Nanorana_parkeri/all_assembly_versions/GCA_000935625.1_ASM93562v1/ ./
    # sent 242 bytes  received 1239116378 bytes  14492592.05 bytes/sec
    # total size is 1238963527  speedup is 1.00
    # real    1m25.355s

    # measure what we have here:
    faSize GCA_000935625.1_ASM93562v1_genomic.fna.gz
    # 2053849526 bases (76078142 N's 1977771384 real 1221140057
    #    upper 756631327 lower) in 25187 sequences in 1 files
    # Total size: mean 81544.0 sd 330701.2 min 200 (JYOU01147511.1)
    #    max 8606022 (KN905849.1) median 453
    # %36.84 masked total, %38.26 masked real

    # that top-level file is the same as the unplaced scaffold file:
    faSize GCA_000935625.1_ASM93562v1_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz
    # 2053849526 bases (76078142 N's 1977771384 real 1977771384 upper 0 lower)
    #     in 25187 sequences in 1 files
    # Total size: mean 81544.0 sd 330701.2 min 200 (JYOU01147511.1)
    #    max 8606022 (KN905849.1) median 453
    # %0.00 masked total, %0.00 masked real

#############################################################################
# Assembly name:  ASM93562v1
# Organism name:  Nanorana parkeri (frogs & toads)
# Isolate:  BGI_ZX_2015
# Sex:  female
# Taxid:          125878
# BioSample:      SAMN02720813
# BioProject:     PRJNA344660
# Submitter:      BGI-Shenzhen
# Date:           2015-3-17
# Assembly type:  haploid
# Release type:   major
# Assembly level: Scaffold
# Genome representation: full
# WGS project:    JYOU01
# Assembly method: SOAPdenovo v. 1.06
# Genome coverage: 83x
# Sequencing technology: Illumina Genome Analyzer II
# RefSeq category: Representative Genome
# GenBank assembly accession: GCA_000935625.1
# RefSeq assembly accession: GCF_000935625.1
# RefSeq assembly and GenBank assemblies identical: no
#
## Assembly-Units:
## GenBank Unit Accession       RefSeq Unit Accession   Assembly-Unit name
## GCA_000935635.1      GCF_000935635.1 Primary Assembly
##      GCF_001746995.1 non-nuclear
#

#############################################################################
# fixup to UCSC naming scheme (DONE - 2015-03-19 - Hiram)
    mkdir /hive/data/genomes/nanPar1/ucsc
    cd /hive/data/genomes/nanPar1/ucsc

    # since this is a scaffold-only assembly, merely use the accession names
    # and since there are all .1 versions, this sed statement will make them
    # all v1 version names:
    zcat ../genbank//GCA_000935625.1_ASM93562v1_assembly_structure/Primary_Assembly/unplaced_scaffolds/AGP/unplaced.scaf.agp.gz \
       | grep -v "^#" | sed -e 's/\.1/v1/;' > chrUn.nanPar1.agp

    zcat ../genbank//GCA_000935625.1_ASM93562v1_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz \
       | sed -e 's/.1 Nanorana .*/v1/;' > chrUn.nanPar1.fa

    # verify these two files are compatible:
    faToTwoBit chrUn.nanPar1.fa test.2bit
    checkAgpAndFa chrUn.nanPar1.agp test.2bit 2>&1 | tail
    # All AGP and FASTA entries agree - both files are valid
    rm test.2bit

    # fetch photo:
    mkdir /hive/data/genomes/nanPar1/photo
    cd /hive/data/genomes/nanPar1/photo
    wget --timestamping \
https://cns.utexas.edu/images/easyblog_shared/2015/nanorana-wang700.jpg
    convert -quality 80 -geometry "400x300" nanorana-wang700.jpg \
       Nanorana_parkeri.jpg

    # check that into the source tree hg/htdocs/images/
    git commit -m "photo courtesy Copyright (C) 2013 Kai Wang http://wangwenzhiwen.blog.163.com/ refs #14560" Nanorana_parkeri.jpg

    # and copy over to /usr/local/apache/htdocs/images/Nanorana_parkeri.jpg
    # permission obtained:
# Subject: Re: photo usage request
# From: Kai Wang
# Date: Thu, 19 Mar 2015 15:06:52 -0700
# To: Hiram Clawson

# Hi Hram

#         Sure. You are welcome to use the image at the website of U. Texas, and the reference URL looks good. 

# Best

# Kai

#  2015-3-19, # # 2:17,  Hiram Clawson # # : 
# > Good Afternoon Kai Wang:
# > I'd like to use your photo on the U.C. Santa Cruz genome browser as
# > identification for this species Nanorana parkeri:
# > 
# >   http://calphotos.berkeley.edu/cgi/img_query?enlarge=0000+0000+0813+0727
# >   http://calphotos.berkeley.edu/cgi/img_query?seq_num=578340&one=T
# > 
# > I note it has been used at U. Texas:
# >   https://cns.utexas.edu/images/easyblog_shared/2015/nanorana-wang700.jpg
# > 
# > We add credit notices and URL references to the photographer, note example:
# >   http://genome.ucsc.edu/cgi-bin/hgGateway?db=cavPor3
# > 
# > Would this be a good URL for your reference: http://wangwenzhiwen.blog.163.com/
# > 
# > --Hiram

#############################################################################
#  Initial database build (DONE - 2015-03-19 - Hiram)

    cd /hive/data/genomes/nanPar1
    cat << '_EOF_' > nanPar1.config.ra
# Config parameters for makeGenomeDb.pl:
db nanPar1
clade vertebrate
genomeCladePriority 50
scientificName Nanorana parkeri
commonName Tibetan frog
assemblyDate Mar. 2015
assemblyLabel ASM93562v1
assemblyShortLabel BGI_ZX_2015
orderKey 20312
mitoAcc none
fastaFiles /hive/data/genomes/nanPar1/ucsc/*.fa
agpFiles /hive/data/genomes/nanPar1/ucsc/*.agp
# qualFiles none
dbDbSpeciesDir frog
photoCreditURL http://wangwenzhiwen.blog.163.com/
photoCreditName Copyright (C) 2013 Kai Wang
ncbiGenomeId 36384
ncbiAssemblyId 302061
ncbiAssemblyName ASM93562v1
ncbiBioProject 243398
genBankAccessionID GCA_000935625.1
taxId 125878
'_EOF_'
    # << happy emacs

    # verify sequence and AGP are OK:
    time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \
         -stop=agp nanPar1.config.ra) > agp.log 2>&1
    # *** All done!  (through the 'agp' step)
    # real    1m35.746s

    # then finish it off:
    time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \
       -fileServer=hgwdev -continue=db nanPar1.config.ra) > db.log 2>&1
    # real    15m49.649s

    # check in the trackDb files created and add to trackDb/makefile

##############################################################################
# cpgIslands on UNMASKED sequence (DONE - 2015-03-19 - Hiram)
    mkdir /hive/data/genomes/nanPar1/bed/cpgIslandsUnmasked
    cd /hive/data/genomes/nanPar1/bed/cpgIslandsUnmasked

    time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \
       -tableName=cpgIslandExtUnmasked \
          -maskedSeq=/hive/data/genomes/nanPar1/nanPar1.unmasked.2bit \
             -workhorse=hgwdev -smallClusterHub=ku nanPar1) > do.log 2>&1
    # real    16m17.756s

    cat fb.nanPar1.cpgIslandExtUnmasked.txt
    # 80597444 bases of 1977771384 (4.075%) in intersection

#############################################################################
# cytoBandIdeo - (DONE - 2015-03-19 - Hiram)
    mkdir /hive/data/genomes/nanPar1/bed/cytoBand
    cd /hive/data/genomes/nanPar1/bed/cytoBand
    makeCytoBandIdeo.csh nanPar1

#########################################################################
# ucscToRefSeq table/track (DONE - 2017-03-13 - Hiram)
    cut -f1 ../../chrom.sizes | sed -e 's/v1//;' \
       | awk '{printf "%sv1\t%s.1\n", $1, $1}' | sort > ucscToINSDC.txt
    awk '{printf "%s\t%s\n", $2, $1}' ucscToINSDC.txt | sort > insdcToUcsc.txt
    grep -v "^#" ../../refseq/GCF*_assembly_report.txt | cut -f5,7 \
      | awk '{printf "%s\t%s\n", $2, $1}' | sort > refseq.insdc.txt
    awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \
         | sort > ucsc.coordinate.tab

    sort -k2 refseq.insdc.txt \
       | join -1 2 -2 2 - ucscToINSDC.txt  | sort -k3 \
         | join -2 3 ucsc.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-4 \
              > ucscToINSDC.bed

    sort -k2 refseq.insdc.txt \
       | join -1 2 -2 2 - ucscToINSDC.txt  | sort -k3 \
         | join -2 3 ucsc.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-3,5 \
              > ucscToRefSeq.bed

    # this UCSC assembly is missing the RefSeq chrM sequence:
    wc -l *
#  25187 insdcToUcsc.txt
#  25188 refseq.insdc.txt
#  25187 ucsc.coordinate.tab
#  25187 ucscToINSDC.bed
#  25187 ucscToINSDC.txt
#  25187 ucscToRefSeq.bed

    export chrSize=`cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1`
    echo $chrSize
    #  14
    sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \
       | sed -e 's/INSDC/RefSeq/g;' > ucscToRefSeq.sql
    hgLoadSqlTab nanPar1 ucscToRefSeq ./ucscToRefSeq.sql ucscToRefSeq.bed

    # checkTableCoords should be silent
    checkTableCoords tupChi1
    # each should cover %100 entirely:
    featureBits -countGaps nanPar1 ucscToINSDC
    # 2053849526 bases of 2053849526 (100.000%) in intersection

    featureBits -countGaps nanPar1 ucscToRefSeq
    # 2053849526 bases of 2053849526 (100.000%) in intersection

#########################################################################
# ucscToINSDC table/track (DONE - 2015-03-20 - Hiram)
    mkdir /hive/data/genomes/nanPar1/bed/ucscToINSDC
    cd /hive/data/genomes/nanPar1/bed/ucscToINSDC

    ~/kent/src/hg/utils/automation/ucscToINSDC.sh \
       ../../genbank/GCA_*assembly_structure/Primary_Assembly

    awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \
         | sort > name.coordinate.tab
    join name.coordinate.tab ucscToINSDC.txt | tr '[ ]' '[\t]' \
         > ucscToINSDC.bed
    # verify all names are coming through, should be same line count:
    wc -l *
    # 25187 name.coordinate.tab
    # 25187 ucscToINSDC.bed
    # 25187 ucscToINSDC.txt

    cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1
    # 14
    # use the 14 in this sed
    sed -e "s/21/14/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \
         | hgLoadSqlTab nanPar1 ucscToINSDC stdin ucscToINSDC.bed
    checkTableCoords nanPar1
    # should cover %100 entirely:
    featureBits -countGaps nanPar1 ucscToINSDC
    # 2053849526 bases of 2053849526 (100.000%) in intersection

#########################################################################
# add chromAlias table (DONE - 2017-03-13 - Hiram)

    mkdir /hive/data/genomes/nanPar1/bed/chromAlias
    cd /hive/data/genomes/nanPar1/bed/chromAlias

    hgsql -N -e 'select chrom,name,"refseq" from ucscToRefSeq;' nanPar1 \
        > ucsc.refseq.tab
    hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' nanPar1 \
        > ucsc.genbank.tab

    awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab ucsc.refseq.tab \
        | sort > nanPar1.chromAlias.tab

    hgLoadSqlTab nanPar1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \
        nanPar1.chromAlias.tab

#########################################################################
# fixup search rule for assembly track/gold table (DONE - 2015-03-20 - Hiram)
    hgsql -N -e "select frag from gold;" nanPar1 | sort | head -1
JYOU01000001.1

    hgsql -N -e "select frag from gold;" nanPar1 | sort | tail -2
JYOU01147511.1
JYOU01147512.1

    # verify this rule will find them all or eliminate them all:
    hgsql -N -e "select frag from gold;" nanPar1 | wc -l
    # 147512

    hgsql -N -e "select frag from gold;" nanPar1 \
       | egrep -e 'JYOU01[0-9]+(\.1)?' | wc -l
    # 147512

    hgsql -N -e "select frag from gold;" nanPar1 \
       | egrep -v -e 'JYOU01[0-9]+(\.1)?' | wc -l
    # 0

    # hence, add to trackDb/tarsier/nanPar1/trackDb.ra
searchTable gold
shortCircuit 1
termRegex JYOU01[0-9]+(\.1)?
query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%'
searchPriority 8

##########################################################################
# running repeat masker (DONE - 2015-03-19 - Hiram)
    mkdir /hive/data/genomes/nanPar1/bed/repeatMasker
    cd /hive/data/genomes/nanPar1/bed/repeatMasker
    time (doRepeatMasker.pl -buildDir=`pwd` \
        -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \
        -smallClusterHub=ku nanPar1) > do.log 2>&1
    # real    232m59.124s

    cat faSize.rmsk.txt
    # 2053849526 bases (76078142 N's 1977771384 real 1950559334 upper
    #    27212050 lower) in 25187 sequences in 1 files
    # Total size: mean 81544.0 sd 330701.2 min 200 (JYOU01147511v1)
    #    max 8606022 (KN905849v1) median 453
    # %1.32 masked total, %1.38 masked real

    # most interesting, NCBI had %36.84 masked total, %38.26 masked real
    # I wonder how they did that ?

    egrep -i "versi|relea" do.log
    # RepeatMasker version open-4.0.5
    #    January 31 2015 (open-4-0-5) version of RepeatMasker
    # CC   RELEASE 20140131;    

    time featureBits -countGaps nanPar1 rmsk
    # 63129821 bases of 1192725744 (5.293%) in intersection
    # real    0m6.633s

    # why is it different than the faSize above ?
    # because rmsk masks out some N's as well as bases, the count above
    #   separates out the N's from the bases, it doesn't show lower case N's

##########################################################################
# running simple repeat (DONE - 2015-03-19 - Hiram)

    mkdir /hive/data/genomes/nanPar1/bed/simpleRepeat
    cd /hive/data/genomes/nanPar1/bed/simpleRepeat
    time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \
        -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \
        nanPar1) > do.log 2>&1
    # real    20m20.609s

    cat fb.simpleRepeat
    # 112563839 bases of 1977771384 (5.691%) in intersection

    # using the Window Masker result:
    cd /hive/data/genomes/nanPar1
    twoBitMask bed/windowMasker/nanPar1.cleanWMSdust.2bit \
       -add bed/simpleRepeat/trfMask.bed  nanPar1.2bit
    #   you can safely ignore the warning about fields >= 13
    twoBitToFa nanPar1.2bit stdout | faSize stdin > faSize.nanPar1.2bit.txt
    cat faSize.nanPar1.2bit.txt
    # 2053849526 bases (76078142 N's 1977771384 real 1208345365
    #    upper 769426019 lower) in 25187 sequences in 1 files
    # Total size: mean 81544.0 sd 330701.2 min 200 (JYOU01147511v1)
    #    max 8606022 (KN905849v1) median 453
    # %37.46 masked total, %38.90 masked real

    rm /gbdb/nanPar1/nanPar1.2bit
    ln -s `pwd`/nanPar1.2bit /gbdb/nanPar1/nanPar1.2bit

##########################################################################
# CREATE MICROSAT TRACK (DONE - 2015-06-22 - Hiram)
     ssh hgwdev
     mkdir /cluster/data/nanPar1/bed/microsat
     cd /cluster/data/nanPar1/bed/microsat
     awk '($5==2 || $5==3) && $6 >= 15 && $8 == 100 && $9 == 0 {printf("%s\t%s\t%s\t%dx%s\n", $1, $2, $3, $6, $16);}' \
	../simpleRepeat/simpleRepeat.bed > microsat.bed
    hgLoadBed nanPar1 microsat microsat.bed
    #	Read 8213 elements of size 4 from microsat.bed

##########################################################################
## WINDOWMASKER (DONE - 2015-03-20 - Hiram)

    mkdir /hive/data/genomes/nanPar1/bed/windowMasker
    cd /hive/data/genomes/nanPar1/bed/windowMasker
    time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \
        -dbHost=hgwdev nanPar1) > do.log 2>&1
    # real    153m54.144s

    # Masking statistics
    cat faSize.nanPar1.cleanWMSdust.txt
    # 2053849526 bases (76078142 N's 1977771384 real 1208849805 upper
    #     768921579 lower) in 25187 sequences in 1 files
    # Total size: mean 81544.0 sd 330701.2 min 200 (JYOU01147511v1)
    #    max 8606022 (KN905849v1) median 453
    # %37.44 masked total, %38.88 masked real

    cat fb.nanPar1.rmsk.windowmaskerSdust.txt
    # 23839116 bases of 2053849526 (1.161%) in intersection

##########################################################################
# cpgIslands - (DONE - 2015-03-20 - Hiram)
    mkdir /hive/data/genomes/nanPar1/bed/cpgIslands
    cd /hive/data/genomes/nanPar1/bed/cpgIslands
    time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \
      -workhorse=hgwdev -smallClusterHub=ku nanPar1) > do.log 2>&1 &
    # real    117m34.561s
    # failed during kluster hardMask operation, continuing:
    time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \
      -continue=cpg -workhorse=hgwdev -smallClusterHub=ku nanPar1) \
         > cpg.log 2>&1 &
    # real    10m28.915s

    cat fb.nanPar1.cpgIslandExt.txt
    # 13717904 bases of 1977771384 (0.694%) in intersection

#########################################################################
# genscan - (DONE - 2015-03-20 - Hiram)
    mkdir /hive/data/genomes/nanPar1/bed/genscan
    cd /hive/data/genomes/nanPar1/bed/genscan
    time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \
      -bigClusterHub=ku nanPar1) > do.log 2>&1
    # real    57m21.101s

    cat fb.nanPar1.genscan.txt
    #   55630505 bases of 1977771384 (2.813%) in intersection

    cat fb.nanPar1.genscanSubopt.txt
    #   58340692 bases of 1977771384 (2.950%) in intersection

########################################################################
# Create kluster run files (DONE - 2015-03-24 - Hiram)

    cd /hive/data/genomes/nanPar1
    # numerator is nanPar1 gapless bases "real" as reported by:
    head -1 faSize.nanPar1.2bit.txt
# 2053849526 bases (76078142 N's 1977771384 real 1208345365 upper
#    76942601 lower) in 25187 sequences in 1 files

    # numerator is 'real' base count
    # denominator is hg19 gapless bases as reported by:
    #   featureBits -noRandom -noHap hg19 gap
    #     234344806 bases of 2861349177 (8.190%) in intersection
    # 1024 is threshold used for human -repMatch:
    calc \( 1977771384 / 2861349177 \) \* 1024
    # ( 1977771384 / 2861349177 ) * 1024 = 707.791245

    # ==> use -repMatch=700 according to size scaled down from 1024 for human.
    #   and rounded down to nearest 50
    cd /hive/data/genomes/nanPar1
    time blat nanPar1.2bit \
         /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/nanPar1.11.ooc \
        -repMatch=700
    # Wrote 23756 overused 11-mers to jkStuff/nanPar1.11.ooc
    #  real    0m32.961s

    # there are no non-bridged gaps, do not need to do this
    #   check non-bridged gaps to see what the typical size is:
#     hgsql -N -e 'select * from gap where bridge="no" order by size;' nanPar1 
#       | ave -tableOut -col=7 stdin
# # min Q1 median Q3 max mean N sum stddev
# 50076 58368.8 70128 100495 1.07816e+07 178173 670 1.19376e+08 672006

    # note the minimum non-bridged gap size is 50,076

#  gapToLift -verbose=2 -minGap=50000 nanPar1 jkStuff/nanPar1.nonBridged.lft \
#         -bedFile=jkStuff/nanPar1.nonBridged.bed

#    hgsql -N \
#        -e 'select * from gap where bridge="no" order by size;' nanPar1 \
#        | ave -col=7 stdin

    # not needed:
#    gapToLift -verbose=2 -minGap=100 bosTau7 jkStuff/nonBridged.lft \
#        -bedFile=jkStuff/nonBridged.bed

    # survey sizes:
    n50.pl chrom.sizes
#       reading: chrom.sizes
#       contig count: 25187, total size: 2053849526, one half size: 1026924763
# cumulative    N50 count       contig  contig size
# 1026149130      545     KN906416v1      1073586
# 1026924763 one half size
# 1027218231      546     KN906384v1      1069101

#############################################################################
# GENBANK AUTO UPDATE (DONE - 2015-06-09 - Hiram)
    ssh hgwdev
    cd $HOME/kent/src/hg/makeDb/genbank
    git pull
    # /cluster/data/genbank/data/organism.lst shows:
    # #organism       mrnaCnt estCnt  refSeqCnt
    #  Nanorana parkeri	3	0	0
    #  Nanorana pleskei	3	0	0
    #  Nanorana yunnanensis	1	0	0

    # edit etc/genbank.conf to add nanPar1 just before xenTro7

# nanPar1 (tibetan frog)
nanPar1.serverGenome = /hive/data/genomes/nanPar1/nanPar1.2bit
nanPar1.clusterGenome = /hive/data/genomes/nanPar1/nanPar1.2bit
nanPar1.ooc = /hive/data/genomes/nanPar1/jkStuff/nanPar1.11.ooc
nanPar1.lift = no
nanPar1.perChromTables = no
nanPar1.refseq.mrna.xeno.pslCDnaFilter    = ${lowCover.refseq.mrna.xeno.pslCDnaFilter}
nanPar1.genbank.mrna.native.pslCDnaFilter = ${lowCover.genbank.mrna.native.pslCDnaFilter}
nanPar1.genbank.mrna.xeno.pslCDnaFilter   = ${lowCover.genbank.mrna.xeno.pslCDnaFilter}
nanPar1.genbank.est.native.pslCDnaFilter  = ${lowCover.genbank.est.native.pslCDnaFilter}
nanPar1.genbank.est.xeno.pslCDnaFilter    = ${lowCover.genbank.est.xeno.pslCDnaFilter}
nanPar1.downloadDir = nanPar1
nanPar1.refseq.mrna.native.load  = no
nanPar1.refseq.mrna.xeno.load = yes
nanPar1.refseq.mrna.xeno.loadDesc  = yes
nanPar1.genbank.mrna.native.load = no
nanPar1.genbank.mrna.native.loadDesc = no
nanPar1.genbank.mrna.xeno.load = yes
nanPar1.genbank.mrna.xeno.loadDesc = yes
nanPar1.genbank.est.native.load = no
nanPar1.genbank.est.native.loadDesc = no
# nanPar1.upstreamGeneTbl = ensGene

    # Edit src/lib/gbGenome.c to add new species.
    git commit -m "Added nanPar Nanorana parkeri refs #15056" \
         etc/genbank.conf src/lib/gbGenome.c
    git push
    # update /cluster/data/genbank/etc/:
    make etc-update
    # update /cluster/data/genbank/bin/:
    make install-server

    screen      #  control this business with a screen since it takes a while
    cd /cluster/data/genbank

    time ./bin/gbAlignStep -initial nanPar1
    # logFile: var/build/logs/2015.05.27-15:45:35.nanPar1.initalign.log
    # real    1651m57.350s

    #   To re-do, rm the dir first:
    #     /cluster/data/genbank/work/initial.nanPar1

    # load database when finished
    ssh hgwdev
    cd /cluster/data/genbank
    time ./bin/gbDbLoadStep -drop -initialLoad nanPar1
    # logFile: var/dbload/hgwdev/logs/2015.06.09-14:34:12.nanPar1.dbload.log
    # real    128m32.009s

    # enable daily alignment and update of hgwdev
    cd ~/kent/src/hg/makeDb/genbank
    git pull
    # add nanPar1 to:
    #   vi etc/align.dbs etc/hgwdev.dbs
    git commit -m "Added nanPar1 - Tibetan frog refs #15056" \
      etc/align.dbs etc/hgwdev.dbs
    git push
    make etc-update

############################################################################
#  BLATSERVERS ENTRY (DONE - 2017-03-22 - Hiram)
#	After getting a blat server assigned by the Blat Server Gods,
    ssh hgwdev

    hgsql -e 'INSERT INTO blatServers (db, host, port, isTrans, canPcr) \
	VALUES ("nanPar1", "blat1b", "17874", "1", "0"); \
	INSERT INTO blatServers (db, host, port, isTrans, canPcr) \
	VALUES ("nanPar1", "blat1b", "17875", "0", "1");' \
	    hgcentraltest
    #	test it with some sequence

############################################################################
## reset default position to MAOA gene (Monoamine Oxidase A from monDom5)
##  (DONE - 2017-03-22 - Hiram)

    ssh hgwdev
    hgsql -e 'update dbDb set defaultPos="KN906736v1:655217-696237"
	where name="nanPar1";' hgcentraltest

############################################################################
# all.joiner update, downloads and in pushQ - (DONE - 2015-06-22 - Hiram)
    cd $HOME/kent/src/hg/makeDb/schema
    # fixup all.joiner until this is a clean output
    joinerCheck -database=nanPar1 -tableCoverage all.joiner
    joinerCheck -database=nanPar1 -times all.joiner
    joinerCheck -database=nanPar1 -keys all.joiner

    cd /hive/data/genomes/nanPar1
    time makeDownloads.pl nanPar1 > downloads.log 2>&1
    # real    13m42.027s

    #   now ready for pushQ entry
    mkdir /hive/data/genomes/nanPar1/pushQ
    cd /hive/data/genomes/nanPar1/pushQ
    makePushQSql.pl nanPar1 > nanPar1.pushQ.sql 2> stderr.out
    #   check for errors in stderr.out, some are OK, e.g.:
    # WARNING: hgwdev does not have /gbdb/nanPar1/wib/gc5Base.wib
    # WARNING: hgwdev does not have /gbdb/nanPar1/wib/quality.wib
    # WARNING: hgwdev does not have /gbdb/nanPar1/bbi/qualityBw/quality.bw
    # WARNING: nanPar1 does not have seq
    # WARNING: nanPar1 does not have extFile
    # WARNING: nanPar1 does not have estOrientInfo
    # WARNING: nanPar1 does not have mrnaOrientInfo

    #   copy it to hgwbeta
    scp -p nanPar1.pushQ.sql qateam@hgwbeta:/tmp
    ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/nanPar1.pushQ.sql"

    #   in that pushQ entry walk through each entry and see if the
    #   sizes will set properly

#########################################################################
