# for emacs: -*- mode: sh; -*- # This file describes building the browser database for the archaeal # species Methanosarcina mazei Go1. ssh eieio mkdir /cluster/store5/archae/methMaze1 ln -s /cluster/store5/archae/methMaze1 /cluster/data/methMaze1 cd /cluster/data/methMaze1 cp /projects/lowelab/db/Bacteria/Methanosarcina_mazei/NC_003901.fna . cp NC_00390l.fna methMaze1.fa # Edit header of *.fa to '> chr ' faToTwoBit methMaze1.fa methMaze1.2bit # CREATE DATABASES AND A BUNCH OF INITIAL STUFF (DONE) ssh hgwdev echo 'create database methMaze1' | hgsql '' cd /cluster/data/methMaze1 faSize -detailed methMaze1.fa > chrom.sizes echo "create table grp (PRIMARY KEY(NAME)) select * from hg16.grp" \ | hgsql methMaze1 echo 'INSERT INTO dbDb \ (name, description, nibPath, organism, \ defaultPos, active, orderKey, genome, scientificName, \ htmlPath, hgNearOk) values \ ("methMaze1", "July 2002", "/gbdb/methMaze1", "Methanosarcina mazei", \ "chr:500000-550000", 1, 252, "Methanosarcina mazei", \ "Methanosarcina mazei Go1", "/gbdb/methMaze1/html/description.html", \ 0);' \ | hgsql hgcentraltest echo 'INSERT INTO defaultDb (genome, name) values ("Methanosarcina mazei", "methMaze1");' \ | hgsql hgcentraltest echo 'INSERT INTO genomeClade (genome, clade, priority) values ("Methanosarcina mazei", "archaea",85);' \ | hgsql hgcentraltest # CREATE CHROMINFO TABLE ssh hgwdev cd /cluster/data/methMaze1 cp ~baertsch/kent/src/hg/lib/chromInfo.sql . hgsql methMaze1 < chromInfo.sql echo "load data local infile 'chrom.sizes' into table chromInfo" | hgsql methMaze1 echo "update chromInfo set fileName = '/gbdb/methMaze1/methMaze1.2bit'" | hgsql methMaze1 cd ~/kent/src/hg/makeDb/trackDb # add the trackDb directories mkdir -p archae/methMaze1 cvs add archae/methMaze1 cvs commit # GC20BASE (DONE) ssh kkstore02 mkdir -p /cluster/data/methMaze1/bed/gc20Base cd /cluster/data/methMaze1/bed/gc20Base hgGcPercent -wigOut -doGaps -file=stdout -win=20 methMaze1 \ /cluster/data/methMaze1/ | wigEncode stdin gc20Base.wig gc20Base.wib ssh hgwdev cd /cluster/data/methMaze1/bed/gc20Base mkdir /gbdb/methMaze1/wib ln -s `pwd`/gc20Base.wib /gbdb/methMaze1/wib hgLoadWiggle -pathPrefix=/gbdb/methMaze1/wib methMaze1 gc20Base gc20Base.wig # verify index is correct: hgsql methMaze1 -e "show index from gc20Base;" # should see good numbers in Cardinality column # TANDEM REPEAT MASKER (DONE) ssh hgwdev mkdir -p /cluster/data/methMaze1/bed/simpleRepeat cd /cluster/data/methMaze1 trfBig methMaze1.fa /dev/null -bedAt=/cluster/data/methMaze1/bed/simpleRepeat/chr.bed cd /cluster/data/methMaze1/bed/simpleRepeat hgLoadBed methMaze1 simpleRepeat *.bed -sqlTable=/cluster/home/baertsch/kent/src/hg/lib/simpleRepeat.sql # MULTIZ with other methanogens # DONE (10/9/05), kpollard cd /cluster/data/methMaze1/bed/ mkdir conservation cd conservation cp /cluster/data/metAce1/bed/conservation/HoxD55.q . cp /cluster/data/metAce1/bed/conservation/*.chr . cp /cluster/data/metAce1/bed/conservation/*.nib . #fix names to be methMaze1, methBark1, methBurt1 faToNib metMaz1.chr methMaze1.chr.nib faToTwoBit metBak0.chr metBak0.2bit faToTwoBit metBur0.chr metBur0.2bit #chrom sizes faSize -detailed *.chr > chrom.sizes #blastz blastz metMaz1.chr metAce1.chr Q=HoxD55.q > metMaz1-metAce1.lav blastz metMaz1.chr metBak0.chr Q=HoxD55.q > metMaz1-metBak0.lav blastz metMaz1.chr metBur0.chr Q=HoxD55.q > metMaz1-metBur0.lav /cluster/bin/i386/lavToAxt metMaz1-metAce1.lav . . metMaz1-metAce1.axt /cluster/bin/i386/lavToAxt metMaz1-metBak0.lav . metBak0.2bit metMaz1-metBak0.axt /cluster/bin/i386/lavToAxt metMaz1-metBur0.lav . metBur0.2bit metMaz1-metBur0.axt axtBest metMaz1-metAce1.axt metMaz1.chr -winSize=500 -minScore=5000 metMaz1-metAce1-best.axt axtBest metMaz1-metBak0.axt metMaz1.chr -winSize=500 -minScore=5000 metMaz1-metBak0-best.axt axtBest metMaz1-metBur0.axt metMaz1.chr -winSize=500 -minScore=5000 metMaz1-metBur0-best.axt axtToMaf metMaz1-metAce1-best.axt chrom.sizes chrom.sizes metMaz1-metAce1.maf axtToMaf metMaz1-metBak0-best.axt chrom.sizes chrom.sizes metMaz1-metBak0.maf axtToMaf metMaz1-metBur0-best.axt chrom.sizes chrom.sizes metMaz1-metBur0.maf #multiz #remove extra header lines multiz metMaz1-metAce1.maf metMaz1-metBak0.maf - > metMaz1-metAce1-metBak0.maf multiz metMaz1-metBur0.maf metMaz1-metAce1-metBak0.maf - > metMaz1-metAce1-metBak0-metBur0.maf #phyloHMM /cluster/bin/phast/msa_view -i MAF -M metMaz1.chr -o SS metMaz1-metAce1-metBak0-metBur0.maf > metMaz1.ss /cluster/bin/phast/phyloFit -i SS metMaz1.ss -t "(metBur0,(metBak0,(metAce1,metMaz1)))" -o Mz1Ma1Mbk0Mbr0 /cluster/bin/phast/msa_view -i SS metMaz1.ss --summary-only #add GC content to next call /cluster/bin/phast/phastCons metMaz1.ss Mz1Ma1Mbk0Mbr0.mod --gc 0.4190 \ --target-coverage 0.7 --estimate-trees met-tree \ --expected-lengths 25 --no-post-probs --ignore-missing \ --nrates 1,1 /cluster/bin/phast/phastCons metMaz1.ss \ met-tree.cons.mod,met-tree.noncons.mod \ --target-coverage 0.7 --expected-lengths 25 \ --viterbi metMaz1-elements.bed --score \ --require-informative 0 --seqname chr > cons.dat wigEncode cons.dat phastCons.wig phastCons.wib /cluster/bin/phast/draw_tree Mz1Ma1Mbk0Mbr0.mod > met-tree.ps #compare to metAce1 tree #move data mkdir wib mv phastCons.wib wib/phastCons.wib mv phastCons.wig wib/phastCons.wig ln -s /cluster/data/methMaze1/bed/conservation/wib/phastCons.wib /gbdb/methMaze1/wib mkdir /gbdb/methMaze1/pwMaf mkdir -p otherMet/metAce1 otherMet/metBak1 otherMet/metBur0 mv metMaz1-metBak0.maf otherMet/metBak0/chr.maf mv metMaz1-metAce1.maf otherMet/metAce1/chr.maf mv metMaz1-metBur0.maf otherMet/metBur0/chr.maf ln -s /cluster/data/methMaze1/bed/conservation/otherMet/metBak0 /gbdb/methMaze1/pwMaf/methBark0_pwMaf ln -s /cluster/data/methMaze1/bed/conservation/otherMet/metBur0 /gbdb/methMaze1/pwMaf/methBurt0_pwMaf ln -s /cluster/data/methMaze1/bed/conservation/otherMet/metAce1 /gbdb/methMaze1/pwMaf/metAce1_pwMaf mkdir multiz mv metMaz1-metAce1-metBak0-metBur0.maf multiz/chr.maf ln -s /cluster/data/methMaze1/bed/conservation/multiz /gbdb/methMaze1/multizMz1Ma1Mbk0Mbr0 #load hgLoadWiggle methMaze1 phastCons /cluster/data/methMaze1/bed/conservation/wib/phastCons.wig hgLoadMaf -warn methMaze1 multizMz1Ma1Mbk0Mbr0 hgLoadMaf -warn methMaze1 methBark0_pwMaf -pathPrefix=/gbdb/methMaze1/pwMaf/methBark0_pwMaf hgLoadMaf -warn methMaze1 methBurt0_pwMaf -pathPrefix=/gbdb/methMaze1/pwMaf/methBurt0_pwMaf hgLoadMaf -warn methMaze1 metAce1_pwMaf -pathPrefix=/gbdb/methMaze1/pwMaf/metAce1_pwMaf hgLoadBed methMaze1 phastConsElements metMaz1-elements.bed #trackDb cd ~/kent/src/hg/makeDb/trackDb/archae/methMaze1 #trackDb.ra entry # track multizMz1Ma1Mbk0Mbr0 # shortLabel Cons 4way # longLabel Methosarcina 4-way multiz alignments # group compGeno # priority 10.0 # visibility pack # type wigMaf 0.0 1.0 # maxHeightPixels 100:40:11 # wiggle phastCons # yLineOnOff Off # autoScale Off # pairwise pwMaf # speciesOrder metAce1 methBark1 methBurt1 cvs commit -m "New multiz track" trackDb.ra #html page cvs add multizMz1Ma1Mbk0Mbr0.html cvs commit -m "Details page for multiz track" multizMz1Ma1Mbk0Mbr0.html # DESCRIPTION PAGE () ssh hgwdev # Write ~/kent/src/hg/makeDb/trackDb/archae/methMaze1/description.html chmod a+r ~/kent/src/hg/makeDb/trackDb/archae/methMaze1/description.html # Check it in. mkdir /gbdb/methMaze1/html ln -s /cluster/data/methMaze1/html/description.html /gbdb/methMaze1/html/ # GENBANK PROTEIN-CODING GENES () ssh hgwdev mkdir /cluster/data/methMaze1/genbank cd /cluster/data/methMaze1/genbank wget ftp://ftp.ncbi.nlm.nih.gov/genomes/Bacteria/Methanosarcina_acetivorans/NC_003552.gbk mv NC_003552.gbk methMaze1.gbk # Create 3 files to assist parsing of the genbank # 1. for a bed file echo 'chr start end gene 1000 strand' > methMaze1-params-bed.txt # 2. for the peptide parts echo 'gene translation' > methMaze1-params-pep.txt # 3. for the other gene information echo 'gene product note' > methMaze1-params-xra.txt # Now extract the genes and information: gbArchaeGenome methMaze1.gbk methMaze1-params-bed.txt methMaze1-genbank-cds.bed gbArchaeGenome methMaze1.gbk methMaze1-params-pep.txt methMaze1-genbank-cds.pep gbArchaeGenome methMaze1.gbk methMaze1-params-xra.txt methMaze1-genbank-cds.xra hgLoadBed methMaze1 gbProtCode methMaze1-genbank-cds.bed hgsql methMaze1 < ~/kent/src/hg/lib/pepPred.sql hgsql methMaze1 < ~/kent/src/hg/lib/minGeneInfo.sql echo rename table pepPred to gbProtCodePep | hgsql methMaze1 echo rename table minGeneInfo to gbProtCodeXra | hgsql methMaze1 echo load data local infile \'methMaze1-genbank-cds.pep\' into table gbProtCodePep | hgsql methMaze1 echo load data local infile \'methMaze1-genbank-cds.xra\' into table gbProtCodeXra | hgsql methMaze1 #genbank to genePred csh tawk '{print $1,$2,$3,$4,$5,$6,$2,$3,0,1,$3-$2,0}' methMaze1-genbank-cds.bed | bedToGenePred stdin tmp.gp tawk '{print $1,$2,$3,$4,$5,$6,$7,$8,$9,$10,substr($1,3,4),name2,"cmpl","cmpl",0}' tmp.gp > tmp2.gp join -t " " -o 1.1,1.2 1.3 1.4 1.5 1.6 1.7 1.8 1.9 1.10 1.11 2.3 1.13 1.14 1.15 tmp2.gp methMaze1-genbank-cds.xra > methMaze1.gp # GENBANK rRNA GENES () ssh hgdev cd /cluster/data/methMaze1/genbank gbArchaeGenome -kind=rRNA methMaze1.gbk methMaze1-params-bed.txt methMaze1-rrnas.bed echo 'gene product NA' > methMaze1-params-rrna-xra.txt gbArchaeGenome -kind=rRNA methMaze1.gbk methMaze1-params-rrna-xra.txt methMaze1-rrnas-xra.txt hgLoadBed methMaze1 gbRRNA methMaze1-rrnas.bed hgsql methMaze1 < ~/kent/src/hg/lib/minGeneInfo.sql echo rename table minGeneInfo to gbRRNAXra | hgsql methMaze1 echo load data local infile \'methMaze1-rrnas-xra.txt\' into table gbRRNAXra | hgsql methMaze1 # COG STUFF # Cut and paste http://www.ncbi.nlm.nih.gov/cgi-bin/COG/palox into emacs (COG list) # and save as cogpage.txt awk '{printf("%s\t%s\n",$6,$5)}' < cogpage.txt | sed -e 's/\[//' -e 's/\]//' > cogs.txt rm cogpage.txt # Now we have the basic list of cogs and the letter code for each one. # TODD LOWE tRNA GENES () # This one is a bed 6+ file created by hand of 46 tRNAs and 1 pseudo tRNA by Todd # Lowe. See ~/kent/src/hg/lib/loweTrnaGene.as for a description of the fields. # **Showing the tRNAScanSE instructions would be nice in the future. ssh hgwdev mkdir /cluster/data/methMaze1/bed/loweTrnaGene cd /cluster/data/methMaze1/bed/loweTrnaGene hgLoadBed -tab methMaze1 loweTrnaGene methMaze1-lowe-trnas.bed -sqlTable=~/kent/src/hg/lib/loweTrnaGene.sql # TODD LOWE snoRNA GENES () # This is a bed 6 file created by hand. ssh hgwdev mkdir /cluster/data/methMaze1/bed/loweSnoGene cd /cluster/data/methMaze1/bed/loweSnoGene hgLoadBed -tab methMaze1 loweSnoGene methMaze1-snos.bed # TIGR GENES () # First go to http://www.tigr.org/tigr-scripts/CMR2/gene_attribute_form.dbi # and fill out the web form as follows: # - Pick "Retrieve attributes for the specified DNA feature within a specific # organism and/or a specific role category". # * Pick "Pyrobaculum aerophilum IM2", and "Primary and TIGR annotation ORFs" # from the 1st and 3rd box. # * Select everything from "Choose TIGR Annotation Gene Attributes" # * Select "Primary Locus Name" from "Choose Primary Annotation Gene Attributes" # * Select everything from "Choose Other Gene Attributes" # - Click submit, and click save as tab-delimited file. ssh hgwdev mkdir /cluster/data/methMaze1/bed/tigrCmrORFs cp methMaze1-tigr.tab /cluster/data/methMaze1/bed/tigrCmrORFs cd /cluster/data/methMaze1/bed/tigrCmrORFs /projects/lowelab/users/aamp/bin/i386/tigrCmrToBed methMaze1-tigr.tab methMaze1-tigr.bed hgLoadBed -tab methMaze1 tigrCmrORFs methMaze1-tigr.bed -sqlTable=~/kent/src/hg/lib/tigrCmrGene.sql