####################################### # emboss.standard definition file ####################################### ####################################### # This file is included in the EMBOSS distribution # and installed automatically. # # The definitions are required by EMBOSS applications # to use the EDAM annotations of ACD files and # public data resources, and to make a set of # public data servers available without the # need for additional configuration. ############################################ ####################################### # Standard databases ####################################### ####################################### # Evidence codes ontology (ECO) # used to define sequence database evidence ####################################### DB eco [ type: "obo" format: "obo" method: "emboss" indexdirectory: "$emboss_standard/index" directory: "$emboss_standard/data/OBO" # fields: "id acc nam isa des" field: "id ! identifier without the prefix" field: "acc ! full name and any alternate identifier(s)" field: "nam ! words in the name" field: "isa ! parent identifier from is_a relation(s)" field: "des ! words in the description" ] ####################################### # EDAM ontology (EMBRACE Data And Methods) # used to annotate all ACD files # and the Data Resource Catalogue ####################################### DB edam [ type: "obo" format: "obo" method: "emboss" indexdirectory: "$emboss_standard/index" directory: "$emboss_standard/data" # fields: "id acc nam isa des ns hasattr hasin hasout # isid isfmt issrc" field: "id ! identifier without the prefix" field: "acc ! full name and any alternate identifier(s)" field: "nam ! words in the name" field: "isa ! parent identifier from is_a relation(s)" field: "des ! words in the description" field: "ns ! namespace" field: "hasattr ! identifier(s) from has_attribute relation(s)" field: "hasin ! identifier(s) from has_input relation(s)" field: "hasout ! identifier(s) from has_output relation(s)" field: "isid ! identifier(s) from is_identifier_of relation(s)" field: "isfmt ! identifier(s) from is_format_of relation(s)" field: "issrc ! identifier(s) from is_source_of relation(s)" ] ############################################ # Gene ontology (GO) # used to annotate public sequence databases ############################################ DB go [ type: "obo" format: "obo" method: "emboss" indexdirectory: "$emboss_standard/index" directory: "$emboss_standard/data/OBO" # fields: "id acc nam isa des ns" field: "id ! identifier without the prefix" field: "acc ! full name and any alternate identifier(s)" field: "nam ! words in the name" field: "isa ! parent identifier from is_a relation(s)" field: "des ! words in the description" field: "ns ! namespace" ] ####################################### # Pathways ontology (PW) ####################################### DB pw [ type: "obo" format: "obo" method: "emboss" indexdirectory: "$emboss_standard/index" directory: "$emboss_standard/data/OBO" # fields: "id acc nam isa des" field: "id ! identifier without the prefix" field: "acc ! full name and any alternate identifier(s)" field: "nam ! words in the name" field: "isa ! parent identifier from is_a relation(s)" field: "des ! words in the description" ] ####################################### # Relations ontology (RO) # used to define OBO file relations ####################################### DB ro [ type: "obo" format: "obo" method: "emboss" indexdirectory: "$emboss_standard/index" directory: "$emboss_standard/data/OBO" # fields: "id acc nam isa des" field: "id ! identifier without the prefix" field: "acc ! full name and any alternate identifier(s)" field: "nam ! words in the name" field: "isa ! parent identifier from is_a relation(s)" field: "des ! words in the description" ] ####################################### # Sequence ontology (RO) # used to define sequence features ####################################### DB so [ type: "obo" format: "obo" method: "emboss" indexdirectory: "$emboss_standard/index" directory: "$emboss_standard/data/OBO" # fields: "id acc nam isa des" field: "id ! identifier without the prefix" field: "acc ! full name and any alternate identifier(s)" field: "nam ! words in the name" field: "isa ! parent identifier from is_a relation(s)" field: "des ! words in the description" ] ############################################# # Data Resource Catalogue DRCAT.dat # lists all available public data resources # with example queries and annotation # using EDAM ontology terms to describe the # resource, and also the data type, format # and identifier for each query ############################################# DB drcat [ type: "resource" format: "drcat" method: "emboss" indexdirectory: "$emboss_standard/index/" directory: "$emboss_standard/data/" # fields: "id acc nam des url cat edat efmt eid etpc xref # qout qfmt qin qurl cc stat" field: "id ! identifier without the prefix" field: "acc ! any alternate identifier(s)" field: "nam ! words in the name" field: "des ! words in the description" field: "url ! words in the main resource URL" field: "cat ! category" field: "edat ! EDAM data term(s) for query results" field: "efmt ! EDAM format term(s) for query results" field: "eid ! EDAM data term(s) for query identifier(s)" field: "etpc ! EDAM topic term(s)" field: "xref ! Data base cross-reference records" field: "qout ! Query output data type" field: "qfmt ! Query format name" field: "qin ! Query identifier name(s)" field: "qurl ! Query URLs" field: "cc ! words in the comment(s)" field: "rest ! REST service" field: "soap ! SOAP service" field: "stat ! status" field: "xref ! Database cross-reference" field: "taxid ! NCBI taxonomy identifier" ] ############################################# # NCBI taxonomy nodes.dmp and names.dmp # lists all taxons in the public sequence databases ############################################# DB taxon [ type: "taxonomy" format: "ncbi" method: "embosstax" indexdirectory: "$emboss_standard/index/" directory: "$emboss_standard/data/TAXONOMY" # fields: "id acc tax rnk up gc mgc" field: "id ! identifier without the prefix" field: "acc ! any alternate identifier(s)" field: "tax ! taxon name" field: "rnk ! taxon rank name" field: "up ! parent taxon id" field: "gc ! genetic code" field: "mgc ! mitochondrial genetic code" taxon: "1 ! all" ] ################################################ # Servers providing standard sets of databases ################################################ ###################### # SRS server at EBI ###################### SERVER srs [ method: "srswww" type: "unknown" url: "http://srs.ebi.ac.uk/srs7bin/cgi-bin/wgetz" comment: "SRS from EBI" serverversion: "7.1.3" cachefile: "server.srs" ] SERVER dkfz [ method: "srswww" type: "sequence features text obo" # url: "http://www.dkfz-heidelberg.de/srs/srs7131bin/cgi-bin/wgetz" url: "http://www.dkfz.de/menu/cgi-bin/srs7.1.3.1/wgetz" comment: "SRS from DKFZ Heidelberg" serverversion: "7.1.3" cachefile: "server.dkfz" ] ####################### # ENSEMBL ####################### SERVER ensembl [ method: "ensembl" type: "sequence" cachefile: "server.ensembl" caseidmatch: "N" comment: "Public Ensembl MySQL instance, use for small-scale queries only." field: "id ! identifier" field: "eid ! Ensembl Exon stable identifier" field: "pid ! Ensembl Translation stable identifier" field: "tid ! Ensembl Transcript stable identifier" field: "grp ! Ensembl Database Adaptor group" format: "ensembl" hasaccession: "N" identifier: "id" url: "mysql://anonymous@ensembldb.ensembl.org:5306/" ] SERVER ensemblgenomes [ method: "ensembl" type: "sequence" cachefile: "server.ensemblgenomes" caseidmatch: "N" comment: "Public Ensembl Genomes MySQL instance, use for small-scale queries only." field: "id ! identifier" field: "eid ! Ensembl Exon stable identifier" field: "pid ! Ensembl Translation stable identifier" field: "tid ! Ensembl Transcript stable identifier" field: "grp ! Ensembl Database Adaptor group" format: "ensembl" hasaccession: "N" identifier: "id" url: "mysql://anonymous@mysql.ebi.ac.uk:4157/" ] ####################### # DAS ####################### SERVER das [ method: "das" type: "sequence, features" url: "http://www.dasregistry.org/das/" comment: "DAS sequence/feature sources listed on the DAS registry" cachefile: "server.dasregistry" ] ####################### # BioMart ####################### SERVER biomart [ method: "biomart" type: "sequence" url: "http://www.biomart.org:80/biomart/martservice" cachefile: "server.biomart" ] ####################### # MRS ####################### SERVER mrs [ methodquery: "mrs" type: "unknown" url: "http://mrs.cmbi.ru.nl/mrs-5/search" cachefile: "server.mrs" serverversion: "MRS-5" ] SERVER mrs4 [ methodquery: "mrs4" type: "unknown" url: "http://mrs.cmbi.ru.nl/mrs-web/plain.do" cachefile: "server.mrs4" serverversion: "MRS-4" ] SERVER mrs3 [ methodquery: "mrs3" type: "unknown" url: "http://mrs.cmbi.ru.nl/mrs-3/plain.do" cachefile: "server.mrs3" serverversion: "MRS-3" ] ####################### # Entrez at NCBI ####################### SERVER entrez [ methodquery: "entrez" type: "unknown" cachefile: "server.entrez" ] IFDEF EMBOSS_AXIS2C ############################# # EBI's EB-eye search service ############################# SERVER ebeye [ methodquery: "ebeye" type: "text" url: "http://www.ebi.ac.uk/ebisearch/service.ebi" comment: "EB-eye text search service that allows searching across EBI public databases" cachefile: "server.ebeye" ] ########################### # EBI's WsDbFetch service ########################### SERVER wsdbfetch [ methodentry: "wsdbfetch" type: "sequence, features, text, obo" url: "http://www.ebi.ac.uk/ws/services/WSDbfetchDoclit" comment: "EBI dbfetch webservices(SOAP)" cachefile: "server.wsdbfetch" ] ENDIF ########################### # EBI's DbFetch service ########################### SERVER dbfetch [ methodentry: "dbfetch" type: "sequence, features, text, obo" url: "http://www.ebi.ac.uk/Tools/dbfetch/" comment: "EBI dbfetch webservices(REST)" cachefile: "server.dbfetch" ] ################################################################## # Resource definitions for the dbx indexing system. ################################################################## RES dbxresource [ type: "Index" ] RES taxresource [ type: "Index" fields: "id acc tax rnk up gc mgc" rnklen: "16" idlen: "7" uplen: "7" taxlen: "110" gclen: "2" mgclen: "2" ] RES emblresource [ type: "Index" idlen: "15" acclen: "15" svlen: "15" keylen: "50" deslen: "20" orglen: "30" ] RES swissresource [ type: "Index" idlen: "15" acclen: "15" svlen: "15" keylen: "15" deslen: "15" orglen: "15" ] RES pirresource [ type: "Index" idlen: "15" acclen: "15" svlen: "15" keylen: "25" deslen: "15" orglen: "35" ] RES chebiresource [ type: "Index" fields: "id acc nam isa des ns" acclen: "400" namlen: "125" deslen: "50" nslen: "20" accpagesize: "16384" nampagesize: "8192" despagesize: "8192" ] RES oboresource [ type: "Index" fields: "id acc nam isa des ns" acclen: "200" namlen: "75" deslen: "40" nslen: "20" accpagesize: "16384" nampagesize: "8192" despagesize: "4096" ] RES edamresource [ type: "Index" fields: "id acc nam isa des ns hasattr hasin hasout isid isfmt issrc" acclen: "80" namlen: "20" deslen: "30" accpagesize: "8192" despagesize: "4096" ] RES drcatresource [ type: "Index" fields: "id acc nam des url cat taxid edat efmt eid etpc xref qout qfmt qin qurl rest soap cc stat" idlen: "32" acclen: "18" qfmtlen: "30" qinlen: "65" qoutlen: "90" qurllen: "30" namlen: "20" deslen: "20" urllen: "25" restlen: "20" cclen: "40" catlen: "40" taxidlen: "6" ] # 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