# for emacs: -*- mode: sh; -*- # This file describes building the browser database for the archaeal # species Methanosarcina acetivorans. # # if this is the first time you are making your own hgwdev browser, need to do # cd ~/kent/src/, then a make # DOWNLOAD SEQUENCE FROM GENBANK (DONE 10/05) mkdir /cluster/store5/archae/sulfAcid1 ln -s /cluster/store5/archae/sulfAcid1 /cluster/data/sulfAcid1 cd /cluster/data/sulfAcid1 cp /projects/lowelab/db/Bacteria/Sulfolobus_acidocaldarius_DSM_639/Sulf_acid* . mv Sulf_acid_DSM_639.fa sulfAcid1.fa grep ">" sulfAcid1.fa # Edit header of sulfAcid1.fa seqs to '>chr >plasmid_pNRC100 >plasmid_pNRC200' faToTwoBit sulfAcid1.fa sulfAcid1.2bit mkdir /gbdb/sulfAcid1 ln -s /cluster/data/sulfAcid1/sulfAcid1.2bit /gbdb/sulfAcid1/sulfAcid1.2bit # CREATE DATABASES AND A BUNCH OF INITIAL STUFF (DONE 10/05) ssh hgwdev echo 'create database sulfAcid1' | hgsql '' cd /cluster/data/sulfAcid1 faSize -detailed sulfAcid1.fa > chrom.sizes echo "create table grp (PRIMARY KEY(NAME)) select * from hg16.grp" \ | hgsql sulfAcid1 echo 'INSERT INTO dbDb (name, description, nibPath, organism, defaultPos, active, orderKey, genome, scientificName, htmlPath, hgNearOk) values ("sulfAcid1", "July 2005", "/gbdb/sulfAcid1", "Sulfolobus acidocaldarius", "chr:500000-550000", 1, 220, "Sulfolobus acidocaldarius","Sulfolobus acidocaldarius DSM 639", "/gbdb/sulfAcid1/html/description.html", 0);' | hgsql hgcentraltest echo 'INSERT INTO defaultDb (genome, name) values ("Sulfolobus acidocaldarius", "sulfAcid1");' | hgsql hgcentraltest echo 'INSERT INTO genomeClade (genome, clade, priority) values ("Sulfolobus acidocaldarius", "archaea",85);' | hgsql hgcentraltest # CREATE CHROMINFO TABLE (DONE 10/05) ssh hgwdev cd /cluster/data/sulfAcid1 cp ~baertsch/kent/src/hg/lib/chromInfo.sql . hgsql sulfAcid1 < chromInfo.sql echo "load data local infile 'chrom.sizes' into table chromInfo" | hgsql sulfAcid1 echo "update chromInfo set fileName = '/gbdb/sulfAcid1/sulfAcid1.2bit'" | hgsql sulfAcid1 cd ~/kent/src/hg/makeDb/trackDb # add the trackDb directories mkdir -p archae/sulfAcid1 cvs add archae/sulfAcid1 cvs commit archae/sulfAcid1 make DBS=sulfAcid1 # GC20BASE (DONE 10/05) mkdir -p /cluster/data/sulfAcid1/bed/gc20Base cd /cluster/data/sulfAcid1/bed/gc20Base hgGcPercent -wigOut -doGaps -file=stdout -win=20 sulfAcid1 /cluster/data/sulfAcid1/ | wigEncode stdin gc20Base.wig gc20Base.wib cd /cluster/data/sulfAcid1/bed/gc20Base mkdir /gbdb/sulfAcid1/wib ln -s `pwd`/gc20Base.wib /gbdb/sulfAcid1/wib hgLoadWiggle -pathPrefix=/gbdb/sulfAcid1/wib sulfAcid1 gc20Base gc20Base.wig # verify index is correct: hgsql sulfAcid1 -e "show index from gc20Base;" # should see good numbers in Cardinality column # TANDEM REPEAT MASKER (DONE 10/05) ssh hgwdev mkdir -p /cluster/data/sulfAcid1/bed/simpleRepeat cd /cluster/data/sulfAcid1 trfBig sulfAcid1.fa /dev/null -bedAt=/cluster/data/sulfAcid1/bed/simpleRepeat/chr.bed cd /cluster/data/sulfAcid1/bed/simpleRepeat hgLoadBed sulfAcid1 simpleRepeat *.bed -sqlTable=/cluster/home/lowe/kent/src/hg/lib/simpleRepeat.sql # MULTIZ (DONE 10/8/05) cd /cluster/data/sulfAcid1/bed mkdir conservation cd conservation cp /cluster/data/pyrFur2/bed/conservation/HoxD55.q . cp /cluster/data/sulSol1/bed/conservation/sulAci1.chr sulfAcid1.chr cp /cluster/data/sulSol1/bed/conservation/sulTok1.chr sulfToko1.chr cp /cluster/data/sulSol1/bed/conservation/sulSol1.chr . #edit headers for Aci and Tok to be sulfAcid1, sulfToko1 /cluster/bin/i386/faToNib sulfAcid1.chr sulfAcid1.chr.nib /cluster/bin/i386/faToNib sulfToko1.chr sulfToko1.chr.nib cp /cluster/data/sulSol1/bed/conservation/sulSol1.chr.nib . faSize -detailed *.chr > chrom.sizes #blastz for Aci-Tok blastz sulfAcid1.chr sulfToko1.chr Q=HoxD55.q > sulfAcid1-sulfToko1.lav /cluster/bin/i386/lavToAxt sulfAcid1-sulfToko1.lav . . sulfAcid1-sulfToko1.axt axtBest sulfAcid1-sulfToko1.axt sulfAcid1.chr -winSize=500 -minScore=5000 sulfAcid1-sulfToko1-best.axt axtToMaf sulfAcid1-sulfToko1-best.axt chrom.sizes chrom.sizes sulfAcid1-sulfToko1.maf #blastz for Aci-Sol blastz sulfAcid1.chr sulSol1.chr Q=HoxD55.q > sulfAcid1-sulSol1.lav /cluster/bin/i386/lavToAxt sulfAcid1-sulSol1.lav . . sulfAcid1-sulSol1.axt axtBest sulfAcid1-sulSol1.axt sulfAcid1.chr -winSize=500 -minScore=5000 sulfAcid1-sulSol1-best.axt axtToMaf sulfAcid1-sulSol1-best.axt chrom.sizes chrom.sizes sulfAcid1-sulSol1.maf #multiz #delete extra header lines from maf files multiz sulfAcid1-sulfToko1.maf sulfAcid1-sulSol1.maf - > sulfAcid1-sulfToko1-sulSol1.maf #phyloHMM /cluster/bin/phast/msa_view -i MAF -M sulfAcid1.chr -o SS sulfAcid1-sulfToko1-sulSol1.maf > sulfAcid1.ss /cluster/bin/phast/phyloFit -i SS sulfAcid1.ss -t "(sulSol1,(sulfToko1,sulfAcid1))" /cluster/bin/phast/msa_view -i SS sulfAcid1.ss --summary-only /cluster/bin/phast/phastCons sulfAcid1.ss phyloFit.mod --gc 0.3507 \ --target-coverage 0.7 --estimate-trees sul-tree \ --expected-lengths 25 --no-post-probs --ignore-missing \ --nrates 1,1 /cluster/bin/phast/phastCons sulfAcid1.ss \ sul-tree.cons.mod,sul-tree.noncons.mod \ --target-coverage 0.7 --expected-lengths 25 \ --viterbi sulfAcid1-elements.bed --score \ --require-informative 0 --seqname chr > cons.dat wigEncode cons.dat phastCons.wig phastCons.wib draw_tree phyloFit.mod > sulfAcid1-tree.ps #check that tree is similar to sul-tree.ps from sulSol1 #move data mkdir wib mv phastCons.wib wib/phastCons.wib mv phastCons.wig wib/phastCons.wig ln -s /cluster/data/sulfAcid1/bed/conservation/wib/phastCons.wib /gbdb/sulfAcid1/wib mkdir -p /gbdb/sulfAcid1/pwMaf mkdir -p otherSul/sulfToko1 otherSul/sulSol1 mv sulfAcid1-sulfToko1.maf otherSul/sulfToko1/chr.maf mv sulfAcid1-sulSol1.maf otherSul/sulSol1/chr.maf ln -s /cluster/data/sulfAcid1/bed/conservation/otherSul/sulfToko1 /gbdb/sulfAcid1/pwMaf/sulfToko1_pwMaf ln -s /cluster/data/sulfAcid1/bed/conservation/otherSul/sulSol1 /gbdb/sulfAcid1/pwMaf/sulSol1_pwMaf mkdir multiz mv sulfAcid1-sulfToko1-sulSol1.maf multiz/chr.maf ln -s /cluster/data/sulfAcid1/bed/conservation/multiz /gbdb/sulfAcid1/multizSa1St1Ss1 #load hgLoadWiggle sulfAcid1 phastCons /cluster/data/sulfAcid1/bed/conservation/wib/phastCons.wig hgLoadMaf -warn sulfAcid1 multizSa1St1Ss1 hgLoadMaf -warn sulfAcid1 sulfToko1_pwMaf -pathPrefix=/gbdb/sulfAcid1/pwMaf/sulfToko1_pwMaf hgLoadMaf -warn sulfAcid1 sulSol1_pwMaf -pathPrefix=/gbdb/sulfAcid1/pwMaf/sulSol1_pwMaf hgLoadBed sulfAcid1 phastConsElements sulfAcid1-elements.bed #trackDb cd ~/kent/src/hg/makeDb/trackDb/archae mkdir sulfAcid1 cvs add sulfAcid1 cd sulfAcid1 #trackDb.ra entry # track multizSa1St1Ss1 # shortLabel Conservation # longLabel Sulfolobus 3-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 sulfToko1 sulSol1 cvs add trackDb.ra cvs commit -m "Added multiz track" trackDb.ra #html page for multizSa1St1Ss1 cd ~/kent/src/hg/makeDb/trackDb/archae/sulfAcid1 cvs add multizSa1St1Ss1.html cvs commit -m "Details page for multiz track" multizSa1St1Ss1.html # DESCRIPTION PAGE (DONE 10/20/05), kpollard # Write ~/kent/src/hg/makeDb/trackDb/archae/sulfAcid1/description.html cd ~/kent/src/hg/makeDb/trackDb/archae/sulfAcid1/ chmod a+r description.html cvs add description.html cvs commit -m "description page" description.html mkdir -p /cluster/data/sulfAcid1/html/ cp ~/kent/src/hg/makeDb/trackDb/archae/sulfAcid1/description.html \ /cluster/data/sulfAcid1/html/description.html mkdir -p /gbdb/sulfAcid1/html ln -s /cluster/data/sulfAcid1/html/description.html /gbdb/sulfAcid1/html/ # GENBANK PROTEIN-CODING GENES (TO DO) ssh hgwdev mkdir /cluster/data/sulfAcid1/genbank cd /cluster/data/sulfAcid1/genbank cp /projects/lowelab/db/Bacteria/Sulfolobus_acidocaldarius_DSM_639/ . mv NC_003552.gbk sulfAcid1.gbk # Create 3 files to assist parsing of the genbank # 1. for a bed file echo 'chr start end gene 1000 strand' > sulfAcid1-params-bed.txt # 2. for the peptide parts echo 'gene translation' > sulfAcid1-params-pep.txt # 3. for the other gene information echo 'gene product note' > sulfAcid1-params-xra.txt # Now extract the genes and information: gbArchaeGenome sulfAcid1.gbk sulfAcid1-params-bed.txt sulfAcid1-genbank-cds.bed gbArchaeGenome sulfAcid1.gbk sulfAcid1-params-pep.txt sulfAcid1-genbank-cds.pep gbArchaeGenome sulfAcid1.gbk sulfAcid1-params-xra.txt sulfAcid1-genbank-cds.xra hgLoadBed sulfAcid1 gbProtCode sulfAcid1-genbank-cds.bed hgsql sulfAcid1 < ~/kent/src/hg/lib/pepPred.sql hgsql sulfAcid1 < ~/kent/src/hg/lib/minGeneInfo.sql echo rename table pepPred to gbProtCodePep | hgsql sulfAcid1 echo rename table minGeneInfo to gbProtCodeXra | hgsql sulfAcid1 echo load data local infile \'sulfAcid1-genbank-cds.pep\' into table gbProtCodePep | hgsql sulfAcid1 echo load data local infile \'sulfAcid1-genbank-cds.xra\' into table gbProtCodeXra | hgsql sulfAcid1 #genbank to genePred csh tawk '{print $1,$2,$3,$4,$5,$6,$2,$3,0,1,$3-$2,0}' sulfAcid1-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 sulfAcid1-genbank-cds.xra > sulfAcid1.gp # GENBANK rRNA GENES (TO DO) ssh hgdev cd /cluster/data/sulfAcid1/genbank gbArchaeGenome -kind=rRNA sulfAcid1.gbk sulfAcid1-params-bed.txt sulfAcid1-rrnas.bed echo 'gene product NA' > sulfAcid1-params-rrna-xra.txt gbArchaeGenome -kind=rRNA sulfAcid1.gbk sulfAcid1-params-rrna-xra.txt sulfAcid1-rrnas-xra.txt hgLoadBed sulfAcid1 gbRRNA sulfAcid1-rrnas.bed hgsql sulfAcid1 < ~/kent/src/hg/lib/minGeneInfo.sql echo rename table minGeneInfo to gbRRNAXra | hgsql sulfAcid1 echo load data local infile \'sulfAcid1-rrnas-xra.txt\' into table gbRRNAXra | hgsql sulfAcid1 # 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 (TO DO) # 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/sulfAcid1/bed/loweTrnaGene cd /cluster/data/sulfAcid1/bed/loweTrnaGene hgLoadBed -tab sulfAcid1 loweTrnaGene sulfAcid1-lowe-trnas.bed -sqlTable=~/kent/src/hg/lib/loweTrnaGene.sql # TODD LOWE snoRNA GENES (TO DO) # This is a bed 6 file created by hand. ssh hgwdev mkdir /cluster/data/sulfAcid1/bed/loweSnoGene cd /cluster/data/sulfAcid1/bed/loweSnoGene hgLoadBed -tab sulfAcid1 loweSnoGene sulfAcid1-snos.bed # TIGR GENES (TO DO) # 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/sulfAcid1/bed/tigrCmrORFs cp sulfAcid1-tigr.tab /cluster/data/sulfAcid1/bed/tigrCmrORFs cd /cluster/data/sulfAcid1/bed/tigrCmrORFs /projects/lowelab/users/aamp/bin/i386/tigrCmrToBed sulfAcid1-tigr.tab sulfAcid1-tigr.bed hgLoadBed -tab sulfAcid1 tigrCmrORFs sulfAcid1-tigr.bed -sqlTable=~/kent/src/hg/lib/tigrCmrGene.sql