# tempdata - this is the directory used by the test databases TEMBL, TSW, etc. # If you use these databases for testing you must uncomment this line and set # the definition to the directory where the databases are installed. # By default this is /usr/local/share/EMBOSS/test but the directory can # be changed with --prefix when you configure EMBOSS. # SET emboss_tempdata path_to_directory_$EMBOSS/test # Proxy - set this if any databases are accessed through a proxy web server. # Turn off in the DB definition with proxy: ":" for any # databases that are internal and should not go through the proxy. # SET emboss_proxy "proxy.mydomain.ac.uk:8080" # Logfile - set this to a file that any user can append to # and EMBOSS applications will automatically write log information # SET emboss_logfile /packages/emboss/emboss/log # Pagesize - this is the size of disc page blocks and is # required by the 'dbx' indexing programs and 'method: emboss' # We recommend a value of 2048 SET PAGESIZE 2048 # Cachesize - a cache of disc pages to be used by the 'dbx' # indexing system and is required for 'method emboss'. It is # the number of PAGESIZE blocks to cache. We recommend # a value of 200 SET CACHESIZE 200 ################################################################## # Test Databases # Used by the qatest.pl script to test an EMBOSS installation. # Comment them out if you do not want your users to use them. # Examples in the EMBOSS documentation should all run by using # TEMBL: in place of EMBL:, TSW: in place of SW:, and so on. ################################################################## # swissprot (Puffer fish entries) # ========= DB tsw [ type: P dir: $emboss_tempdata/swiss method: emblcd format: swiss release: 36 fields: "sv des org key" comment: "Swissprot native format with EMBL CD-ROM index" ] # swnew (Puffer fish entries) # ===== DB tswnew [ type: P dir: $emboss_tempdata/swnew method: emblcd format: swiss release: 37 fields: "sv des org key" comment: "Swissnew as 3 files in native format with EMBL CD-ROM index" ] # wormpep (cosmid ZK637) # ======= DB twp [ type: P dir: $emboss_tempdata/wormpep method: emblcd format: fasta release: 16 fields: "des" comment: "EMBL new in native format with EMBL CD-ROM index" ] # embl (worm cosmid ZK637 and a few other entries) # ==== DB tembl [ type: N dir: $emboss_tempdata/embl method: emblcd format: embl release: 57 fields: "sv des org key" comment: "EMBL in native format with EMBL CD-ROM index" ] # pir (cytochrome C plus first entries in other divisions) # === DB tpir [ type: P dir: $emboss_tempdata/pir method: gcg file: pir*.seq format: nbrf fields: "des org key" comment: "PIR using NBRF access for 4 files" ] # Genbank (Canadian EMBnet node - so long as they are running SRS version 6) # ======= DB tgb [ type: N method: srswww format: genbank url: "http://cbr-rbc.nrc-cnrc.gc.ca/srs6bin/cgi-bin/wgetz" dbalias: genbankrelease fields: "sv des org key" comment: "Genbank IDs" ] # Genbank (local copy of the TEMBL entries from Genbank) # ======= DB tgenbank [ type: N dir: $emboss_tempdata/genbank method: emblcd format: genbank release: 01 fields: "sv des org key" comment: "GenBank in native format with EMBL CD-ROM index" ] ############################################# # DATABASE SETTING EXAMPLES # # Modify these for your own # local and remote database definitions # # See the EMBOSS Administrators Guide 3.0.0 # for full documentation on DB definitions. ############################################# ####################################################################### # GENBANK from the Canadian EMBnet node SRSWWW server ####################################################################### #DB genbank [ type: N method: url format: genbank # url: "http://www.ca.embnet.org/srs6bin/cgi-bin/wgetz?-id+-e+[genbank-id:'%s']+-vn+2" # comment: "Genbank IDs" ] #DB gb [ type: N method: url format: genbank # url: "http://www.ca.embnet.org/srs6bin/cgi-bin/wgetz?-id+-e+[genbank-id:'%s']+-vn+2" # comment: "Genbank IDs" ] #DB genbanka [ type: N method: url format: genbank # url: "http://www.ca.embnet.org/srs6bin/cgi-bin/wgetz?-id+-e+[genbank-acc:'%s']+-vn+2" # comment: "Genbank ACs" ] #DB gba [ type: N method: url format: genbank # url: "http://www.ca.embnet.org/srs6bin/cgi-bin/wgetz?-id+-e+[genbank-acc:'%s']+-vn+2" # comment: "Genbank ACs" ] ## N.B. # For older SRS servers use e.g. #DB gb [ type: N method: url format: genbank # url: "http://srs.csc.fi:8002/srs6bin/cgi-bin/wgetz?-e+[genbank-id:%s]" # comment: "Genbank IDs" ] ####################################################################### # PIR/NBRF indexed with dbigcg ####################################################################### # Set the directory to where the database is stored # Assumed the dbigcg index files are in the same directory # DB pir [ type: P dir: /data/pir # method: gcg # file: pir*.seq # format: nbrf # comment: "PIR/NBRF" ] # DB nbrf [ type: P dir: /data/pir # method: gcg # file: pir*.seq # format: nbrf # comment: "PIR/NBRF" ] ########################################################################## # SWISSPROT indexed with dbiflat ########################################################################## # SWISSPROT: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # DB swissprot [ # type: P # comment: "SWISSPROT sequences" # method: emblcd # format: swiss # dbalias: swissprot # dir: /data/swissprot/ # file: seq.dat # ] # SWISSNEW: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # DB sw [ # type: P # comment: "SWISSPROT sequences" # method: emblcd # format: swiss # dbalias: swissprot # dir: /data/swissprot/ # file: seq.dat # ] ######################################################### # EMBL indexed with dbiflat ######################################################### # EMBL: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # Second definition is another name for the first. #DB embl [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ # file: *.dat comment: "EMBL sequences" #] #DB em [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ # file: *.dat comment: "EMBL sequences" #] ## Old EMBL definitions (for historical reasons) using SRSWWW ##DB embla [ type: N method: url format: embl ## url: "http://srs.hgmp.mrc.ac.uk/srs6bin/cgi-bin/wgetz?-e+[embl-acc:%s]" ## comment: "Use embl instead!" ] ## ##DB ema [ type: N method: url format: embl ## url: "http://srs.hgmp.mrc.ac.uk/srs6bin/cgi-bin/wgetz?-e+[embl-acc:%s]" ## comment: "Use embl instead!" ] ######################################################### # EMBL NEW ######################################################### # EMBLNEW: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # DB emblnew [ type: N method: emblcd release: "0.0" # format: embl dir: /data/embl/newdata/ # file: *.dat comment: "New EMBL sequences" # ] ########################################################## # EMBL subdivisions using the original EMBL dbiflat indices ########################################################## # Simply redefine EMBL with exclude: and file: to limit # the database files available # DB fungal [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */fun*.dat comment: "EMBL fungal sequences" # ] # DB est [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */est*.dat comment: "EMBL EST sequences" # ] # DB gss [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */gss*.dat comment: "EMBL GSS sequences" # ] # DB htg [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */htg*.dat comment: "EMBL HTG sequences" # ] # DB human [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */hum?.dat comment: "EMBL human sequences" # ] # DB humanest [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/est/ exclude: *.dat # file: */humanest*.dat comment: "EMBL human EST sequences" # ] # DB invertebrate [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */inv*.dat comment: "EMBL invertebrate sequences" # ] # DB mammalian [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */mam*.dat comment: "EMBL mammalian sequences" # ] # DB mouseest [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/est/ exclude: *.dat # file: */mouseest*.dat comment: "EMBL mouse EST sequences" # ] # DB organelle [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */org*.dat comment: "EMBL organelle sequences" # ] # DB otherest [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/est/ exclude: *.dat # file: */otherest*.dat comment: "EMBL other EST sequences" # ] # DB patent [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */patent*.dat comment: "EMBL patented sequences" # ] # DB phage [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */phg*.dat comment: "EMBL phage sequences" # ] # DB plant [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */pln*.dat comment: "EMBL plant sequences" # ] # DB prokaryotic [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */pro*.dat comment: "EMBL prokaryotic sequences" # ] # DB rodent [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */rod*.dat comment: "EMBL rodent sequences" # ] # DB sts [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */sts*.dat comment: "EMBL STS sequences" # ] # DB synthetic [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */syn*.dat comment: "EMBL synthetic sequences" # ] # DB unclassified [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */unc*.dat comment: "EMBL unclassified sequences" # ] # DB viral [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */vrl*.dat comment: "EMBL viral sequences" # ] # DB othervertebrate [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: */vrt*.dat comment: "EMBL other vertebrate sequences" # ] # DB vertebrate [ type: N method: emblcd release: "61.0" # format: embl dir: /data/embl/ exclude: *.dat # file: "*/vrt*.dat */mam*.dat */rod*.dat" # comment: "EMBL vertebrate sequences" # ] #################################################################### # TREMBL databases indexed with dbiflat #################################################################### # TREMBL: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # DB trembl [ # type: P # comment: "TREMBL sequences" # method: emblcd # format: swiss # dir: /data/trembl/ # file: tr_*.dat # ] # SPTREMBL: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # DB sptrembl [ # type: P # comment: "SPTREMBL sequences" # method: emblcd # format: swiss # dir: /data/trembl/sptrembl/ # file: tr_*.dat # ] # DB remtrembl [ # type: P # comment: "REMTREMBL sequences" # method: emblcd # format: swiss # dir: /data/trembl/sptrembl/ # file: tr_*.dat # ] #################################################################### # New TREMBL #################################################################### # TREMBLNEW: Set the directory to where the database is stored # Assumed the dbiflat index files are in the same directory # DB tremblnew [ # type: P # comment: "New TREMBL sequences" # method: emblcd # format: swiss # dir: /data/trembl/emboss/ # file: tremblnew*.dat # ] #################################################################### # Trembl subsections #################################################################### # Simply redefine TREMBL with exclude: and file: to limit # the database files available # DB trarc [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_arc*.dat comment: "TREMBL ARC sequences" # ] # DB trfungal [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_fun*.dat comment: "TREMBL fungal sequences" # ] # DB trhuman [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_hum*.dat comment: "TREMBL human sequences" # ] # DB trimmuno [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_immuno*.dat comment: "TREMBL immunological sequences" # ] # DB trinvertebrate [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_inv*.dat comment: "TREMBL invertebrate sequences" # ] # DB trmammalian [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_mam*.dat comment: "TREMBL mammalian sequences" # ] # DB trmhc [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_mhc*.dat comment: "TREMBL MHC sequences" # ] # DB trorganelle [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_org*.dat comment: "TREMBL organelle sequences" # ] # DB trpatent [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_patent*.dat comment: "TREMBL patented sequences" # ] # DB trphage [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_phg*.dat comment: "TREMBL phage sequences" # ] # DB trplant [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_pln*.dat comment: "TREMBL plant sequences" # ] # DB trprokaryotic [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/embl/ exclude: *.dat # file: */tr_pro*.dat comment: "TREMBL prokaryotic sequences" # ] # DB trpseudo [ type: P method: emblcd release: "61.0" # format: embl dir: /data/trembl/ exclude: *.dat # file: */tr_pseudo*.dat comment: "TREMBL pseudo sequences" # ] # DB trrodent [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_rod*.dat comment: "TREMBL rodent sequences" # ] # DB trsmall [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_smalls*.dat comment: "TREMBL small sequences" # ] # DB trsynthetic [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_syn*.dat comment: "TREMBL synthetic sequences" # ] # DB trtruncated [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_truncated*.dat comment: "TREMBL truncated sequences" # ] # DB trunclassified [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_unc*.dat comment: "TREMBL unclassified sequences" # ] # DB trviral [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_vrl*.dat comment: "TREMBL viral sequences" # ] # DB trothervertebrate [ type: P method: emblcd release: "61.0" # format: swiss dir: /data/trembl/ exclude: *.dat # file: */tr_vrt*.dat comment: "TREMBL other vertebrate sequences" # ] #################################################################### # Biomart example #################################################################### #DB martensembl [ # method: "biomart" # type: "P" # url: "http://www.biomart.org:80/biomart/martservice" # dbalias is the dataset # dbalias: "hsapiens_gene_ensembl" # # The format must be 'biomart' # format: "biomart" # # identifier is the biomart filter the query will be performed with # e.g. seqret martensembl:ENST00000380152 # # identifier: "ensembl_transcript_id" # # Additional filters may be added here e.g. # # filter: "chromosome_name=13" # # This is the biomart attribute specifying the sequence # # sequence: "peptide" # # These are fields you want returned as part of the description # # return: "ensembl_gene_id,description,external_gene_id,chromosome_name" #] #################################################################### # SQL example (dummy) #################################################################### #DB sqlexample [ # method: "sql" # type: "N" # # method://username:password@host/databasename # url: "mysql://dummy:pass@machine.somedomain.org:3306/dummyseqs" # # dbalias is the table name containing the sequence information # dbalias: "sequences" # # The SQL data is processed using biomart format. That is not a typo. # format: "biomart" # # Column name containing IDs|Accs i.e. the column the query will be # performed against # identifier: "accession" # # Any additional SQL restrictions can be put here e.g. # filter: "AND version IS NOT NULL" # # Column containing sequence # sequence: "sequence" # # Columns you want to add to the description # return: "version,description" #] ################################################################## # Ensembl datatabase access example via public MySQL instances. # # Please note that these public MySQL instances are only provided # for small-scale access. For extended analyses and if in doubt, # please copy the relevant databases to a private MySQL instance # and configure access accordingly. Please see the following # instructions on how to setup your own MySQL server. # http://www.ensembl.org/info/docs/webcode/install/build.html ################################################################## # DB ensembl [ # type: "Nucleotide" # format: "ensembl" # method: "ensembl" # url: "mysql://anonymous:@ensembldb.ensembl.org:5306/" # comment: "Ensembl test database" # ] # # DB ensemblgenomes [ # type: "Nucleotide" # format: "ensembl" # method: "ensembl" # url: "mysql://anonymous:@mysql.ebi.ac.uk:4157/" # comment: "Ensembl test database" # ] ################################################################## # Resource definitions for the dbx indexing system. ################################################################## # #RES embl [ type: Index # idlen: 15 # acclen: 15 # svlen: 15 # keylen: 15 # deslen: 15 # orglen: 15 #]