protk 1.1.8 → 1.1.9

data/lib/protk/setup_rakefile.rake

@@ -115,8 +115,7 @@ file perl_locallib_installed_file =>  [@build_dir,"#{@download_dir}/#{perl_local
 		sh "echo 'eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir})' >>~/.bash_profile"
 	end
 
-	sh "eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir})"
-	sh "curl -L http://cpanmin.us | perl - --self-upgrade"
+	sh "eval $(perl -I#{perl_dir}/lib/perl5 -Mlocal::lib=#{perl_dir});curl -L http://cpanmin.us | perl - --self-upgrade"
 end
 
 task :perl_locallib => [perl_locallib_installed_file]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.1.8
+  version: 1.1.9
   prerelease: 
 platform: ruby
 authors:
@@ -174,13 +174,11 @@ extensions:
 - ext/protk/extconf.rb
 extra_rdoc_files: []
 files:
-- lib/protk/big_search_tool.rb
 - lib/protk/bio_sptr_extensions.rb
 - lib/protk/biotools_excel_converter.rb
 - lib/protk/command_runner.rb
 - lib/protk/constants.rb
 - lib/protk/convert_util.rb
-- lib/protk/data/make_uniprot_table.rb
 - lib/protk/eupathdb_gene_information_table.rb
 - lib/protk/fastadb.rb
 - lib/protk/galaxy_stager.rb
@@ -203,7 +201,6 @@ files:
 - lib/protk/uniprot_mapper.rb
 - lib/protk/xtandem_defaults.rb
 - lib/protk.rb
-- lib/protk/big_search_rakefile.rake
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/setup_rakefile.rake
 - bin/annotate_ids.rb
@@ -229,7 +226,6 @@ files:
 - bin/repair_run_summary.rb
 - bin/sixframe.rb
 - bin/tandem_search.rb
-- bin/template_search.rb
 - bin/toppas_pipeline.rb
 - bin/unimod_to_loc.rb
 - bin/uniprot_mapper.rb
@@ -250,9 +246,6 @@ files:
 - lib/protk/data/tandem_params.xml
 - lib/protk/data/taxonomy_template.xml
 - lib/protk/data/unimod.xml
-- lib/protk/data/uniprot_accessions.loc
-- lib/protk/data/uniprot_accessions_table.txt
-- lib/protk/data/uniprot_input_accessions.loc
 - lib/protk/data/yum_packages.yaml
 - ext/protk/protk.c
 - ext/protk/extconf.rb

data/bin/template_search.rb

@@ -1,144 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 14/12/2010
-#
-# Runs an MS/MS search using the MSGFPlus search engine
-#
-require 'protk/search_tool'
-
-
-# Setup specific command-line options for this tool. Other options are inherited from SearchTool
-#
-search_tool=SearchTool.new({:msms_search=>true,:background=>false,:glyco=>true,:database=>true,:explicit_output=>true,:over_write=>true,:msms_search_detailed_options=>true})
-search_tool.option_parser.banner = "Run an msms search on a set of msms spectrum input files.\n\nUsage: template_search.rb [options] file1.mzML file2.mzML ..."
-search_tool.options.output_suffix="_template"
-
-search_tool.options.custom_option="default"
-search_tool.option_parser.on('--custom-opt value','Custom option relevant to this tool only (Default default)') do |val|
-  search_tool.options.custom_option=val
-end
-  
-search_tool.option_parser.parse!
-
-# Set search engine specific parameters on the SearchTool object
-#
-msgf_bin="#{genv.msgf_bin}/MSGFPlus.jar"
-
-case 
-when Pathname.new(search_tool.database).exist? # It's an explicitly named db
-  current_db=Pathname.new(search_tool.database).realpath.to_s
-else
-  current_db=search_tool.current_database :fasta
-end
-
-fragment_tol = search_tool.fragment_tol
-precursor_tol = search_tool.precursor_tol
-
-
-throw "When --output is set only one file at a time can be run" if  ( ARGV.length> 1 ) && ( search_tool.explicit_output!=nil ) 
-
-# Run the search engine on each input file
-#
-ARGV.each do |filename|
-
-  if ( search_tool.explicit_output!=nil)
-    output_path=search_tool.explicit_output
-  else
-    output_path="#{search_tool.output_base_path(filename.chomp)}.mzid"
-  end
-  
-  # (*.mzML, *.mzXML, *.mgf, *.ms2, *.pkl or *_dta.txt)
-  # Get the input file extension
-  ext = Pathname.new(filename).extname
-
-
-
-  input_path="#{search_tool.input_base_path(filename.chomp)}#{ext}"
-
-  # Only proceed if the output file is not present or we have opted to over-write it
-  #
-  if ( search_tool.over_write || !Pathname.new(output_path).exist? )
-  
-    # The basic command
-    #
-    cmd= "java -Xmx#{search_tool.java_mem} -jar #{msgf_bin} -d #{current_db} -s #{input_path} -o #{output_path} "
-
-    #Missed cleavages
-    #
-    throw "Maximum value for missed cleavages is 2" if ( search_tool.missed_cleavages > 2)
-    cmd << " -ntt #{search_tool.missed_cleavages}"
-
-    # Precursor tolerance
-    #
-    cmd << " -t #{search_tool.precursor_tol}#{search_tool.precursor_tolu}"
-    
-    # Instrument type
-    #
-    cmd << " -inst 2"
-    
-#    cmd << " -m 4"
-
-    cmd << " -addFeatures 1"
-
-    # Enzyme
-    #
-  #    if ( search_tool.enzyme!="Trypsin")
-  #      cmd << " -e #{search_tool.enzyme}"
-  #    end
-
-  mods_path="#{search_tool.input_base_path(filename.chomp)}.msgfplus_mods.txt"
-  mods_file=File.open(mods_path,'w+')
-
-    # Variable Modifications
-    #
-    if ( search_tool.var_mods !="" && !search_tool.var_mods =~/None/) # Checking for none is to cope with galaxy input
-      var_mods = search_tool.var_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject {|e| e.empty? }.join(",")
-      if ( var_mods !="" )
-        cmd << " -mv #{var_mods}"
-      end
-    else 
-      # Add options related to peptide modifications
-      #
-      if ( search_tool.glyco )
-        cmd << " -mv 119 "
-      end
-    end
-
-  # Fixed modifications
-  #
-    if ( search_tool.fix_mods !="" && !search_tool.fix_mods=~/None/)
-      fix_mods = search_tool.fix_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject { |e| e.empty? }.join(",")
-      if ( fix_mods !="")
-        cmd << " -mf #{fix_mods}"    
-      end
-    else
-      if ( search_tool.has_modifications )
-        cmd << " -mf "
-        if ( search_tool.carbamidomethyl )
-          cmd<<"3 "
-        end
-
-        if ( search_tool.methionine_oxidation )
-          cmd<<"1 "
-        end
-
-      end
-    end
-    
-    # Up to here we've formulated the omssa command. The rest is cleanup
-    p "Running:#{cmd}"
-    
-    # Run the search
-    #
-    job_params= {:jobid => search_tool.jobid_from_filename(filename) }
-    job_params[:queue]="lowmem"
-    job_params[:vmem]="900mb"    
-    search_tool.run(cmd,genv,job_params)
-
-
-  else
-    genv.log("Skipping search on existing file #{output_path}",:warn)       
-  end
-
-end

data/lib/protk/big_search_rakefile.rake

@@ -1,16 +0,0 @@
-require 'protk/constants'
-
-$genv=Constants.new()
-
-ARGV.each do |fname| 
-
-	file fname do
-		puts fname
-	end
-
-	multitask :run => fname
-
-end
-
-
-task :default => :run

data/lib/protk/big_search_tool.rb

@@ -1,23 +0,0 @@
-# create rake dependencies
-# run rakefile
-#
-require 'optparse'
-require 'pathname'
-require 'protk/tool'
-require 'protk/command_runner'
-require 'pp'
-require 'rake'
-
-class BigSearchTool < Tool
-
-  def run input_files
-	command = "rake -f #{rakefile_path} #{input_files.join(" ")}"
-	runner=CommandRunner.new(Constants.new)
-    runner.run_local(command)
-  end
-
-  def rakefile_path
-    "#{File.dirname(__FILE__)}/big_search_rakefile.rake"
-  end
-
-end

data/lib/protk/data/make_uniprot_table.rb

@@ -1,29 +0,0 @@
-#!/usr/bin/env ruby
-
-file_name = ARGV[0]
-
-out_fh = File.new("uniprot_accessions.loc",'w')
-
-File.foreach(file_name) { |line|  
-	cols= line.chomp.split("\t")
-	if ( cols[2]!="from" )
-		db_key = "#{cols[0].gsub(" ","_").downcase}_"
-		out_fh.write "#{cols[0]}\t#{db_key}\t#{cols[1]}\t#{db_key}\n"
-	end
-}
-
-out_fh.close
-
-
-
-out_fh = File.new("uniprot_input_accessions.loc",'w')
-
-File.foreach(file_name) { |line|  
-	cols= line.chomp.split("\t")
-	if ( cols[2]!="to" )
-		db_key = "#{cols[0].gsub(" ","_").downcase}_"
-		out_fh.write "#{cols[0]}\t#{db_key}\t#{cols[1]}\t#{db_key}\n"
-	end
-}
-
-out_fh.close

data/lib/protk/data/uniprot_accessions.loc

@@ -1,96 +0,0 @@
-UniProtKB AC	uniprotkb_ac_	ACC	uniprotkb_ac_
-UniProtKB ID	uniprotkb_id_	ID	uniprotkb_id_
-UniParc	uniparc_	UPARC	uniparc_
-UniRef50	uniref50_	NF50	uniref50_
-UniRef90	uniref90_	NF90	uniref90_
-UniRef100	uniref100_	NF100	uniref100_
-EMBL/GenBank/DDBJ	embl/genbank/ddbj_	EMBL_ID	embl/genbank/ddbj_
-EMBL/GenBank/DDBJ CDS	embl/genbank/ddbj_cds_	EMBL	embl/genbank/ddbj_cds_
-PIR	pir_	PIR	pir_
-UniGene	unigene_	UNIGENE_ID	unigene_
-Entrez Gene (GeneID)	entrez_gene_(geneid)_	P_ENTREZGENEID	entrez_gene_(geneid)_
-GI number*	gi_number*_	P_GI	gi_number*_
-IPI	ipi_	P_IPI	ipi_
-RefSeq Protein	refseq_protein_	P_REFSEQ_AC	refseq_protein_
-RefSeq Nucleotide	refseq_nucleotide_	REFSEQ_NT_ID	refseq_nucleotide_
-PDB	pdb_	PDB_ID	pdb_
-DisProt	disprot_	DISPROT_ID	disprot_
-HSSP	hssp_	HSSP_ID	hssp_
-DIP	dip_	DIP_ID	dip_
-MINT	mint_	MINT_ID	mint_
-Allergome	allergome_	ALLERGOME_ID	allergome_
-MEROPS	merops_	MEROPS_ID	merops_
-PeroxiBase	peroxibase_	PEROXIBASE_ID	peroxibase_
-PptaseDB	pptasedb_	PPTASEDB_ID	pptasedb_
-REBASE	rebase_	REBASE_ID	rebase_
-TCDB	tcdb_	TCDB_ID	tcdb_
-PhosSite	phossite_	PHOSSITE_ID	phossite_
-DMDM	dmdm_	DMDM_ID	dmdm_
-Aarhus/Ghent-2DPAGE	aarhus/ghent-2dpage_	AARHUS_GHENT_2DPAGE_ID	aarhus/ghent-2dpage_
-World-2DPAGE	world-2dpage_	WORLD_2DPAGE_ID	world-2dpage_
-DNASU	dnasu_	DNASU_ID	dnasu_
-Ensembl	ensembl_	ENSEMBL_ID	ensembl_
-Ensembl Protein	ensembl_protein_	ENSEMBL_PRO_ID	ensembl_protein_
-Ensembl Transcript	ensembl_transcript_	ENSEMBL_TRS_ID	ensembl_transcript_
-Ensembl Genomes	ensembl_genomes_	ENSEMBLGENOME_ID	ensembl_genomes_
-Ensembl Genomes Protein	ensembl_genomes_protein_	ENSEMBLGENOME_PRO_ID	ensembl_genomes_protein_
-Ensembl Genomes Transcript	ensembl_genomes_transcript_	ENSEMBLGENOME_TRS_ID	ensembl_genomes_transcript_
-GeneID	geneid_	P_ENTREZGENEID	geneid_
-GenomeReviews	genomereviews_	GENOMEREVIEWS_ID	genomereviews_
-KEGG	kegg_	KEGG_ID	kegg_
-PATRIC	patric_	PATRIC_ID	patric_
-UCSC	ucsc_	UCSC_ID	ucsc_
-VectorBase	vectorbase_	VECTORBASE_ID	vectorbase_
-AGD	agd_	AGD_ID	agd_
-ArachnoServer	arachnoserver_	ARACHNOSERVER_ID	arachnoserver_
-CGD	cgd_	CGD	cgd_
-ConoServer	conoserver_	CONOSERVER_ID	conoserver_
-CYGD	cygd_	CYGD_ID	cygd_
-dictyBase	dictybase_	DICTYBASE_ID	dictybase_
-EchoBASE	echobase_	ECHOBASE_ID	echobase_
-EcoGene	ecogene_	ECOGENE_ID	ecogene_
-euHCVdb	euhcvdb_	EUHCVDB_ID	euhcvdb_
-EuPathDB	eupathdb_	EUPATHDB_ID	eupathdb_
-FlyBase	flybase_	FLYBASE_ID	flybase_
-GeneCards	genecards_	GENECARDS_ID	genecards_
-GeneFarm	genefarm_	GENEFARM_ID	genefarm_
-GenoList	genolist_	GENOLIST_ID	genolist_
-H-InvDB	h-invdb_	H_INVDB_ID	h-invdb_
-HGNC	hgnc_	HGNC_ID	hgnc_
-HPA	hpa_	HPA_ID	hpa_
-LegioList	legiolist_	LEGIOLIST_ID	legiolist_
-Leproma	leproma_	LEPROMA_ID	leproma_
-MaizeGDB	maizegdb_	MAIZEGDB_ID	maizegdb_
-MIM	mim_	MIM_ID	mim_
-MGI	mgi_	MGI_ID	mgi_
-neXtProt	nextprot_	NEXTPROT_ID	nextprot_
-Orphanet	orphanet_	ORPHANET_ID	orphanet_
-PharmGKB	pharmgkb_	PHARMGKB_ID	pharmgkb_
-PomBase	pombase_	POMBASE_ID	pombase_
-PseudoCAP	pseudocap_	PSEUDOCAP_ID	pseudocap_
-RGD	rgd_	RGD_ID	rgd_
-SGD	sgd_	SGD_ID	sgd_
-TAIR	tair_	TAIR_ID	tair_
-TubercuList	tuberculist_	TUBERCULIST_ID	tuberculist_
-WormBase	wormbase_	WORMBASE_ID	wormbase_
-WormBase Transcript	wormbase_transcript_	WORMBASE_TRS_ID	wormbase_transcript_
-WormBase Protein	wormbase_protein_	WORMBASE_PRO_ID	wormbase_protein_
-Xenbase	xenbase_	XENBASE_ID	xenbase_
-ZFIN	zfin_	ZFIN_ID	zfin_
-eggNOG	eggnog_	EGGNOG_ID	eggnog_
-GeneTree	genetree_	GENETREE_ID	genetree_
-HOGENOM	hogenom_	HOGENOM_ID	hogenom_
-HOVERGEN	hovergen_	HOVERGEN_ID	hovergen_
-KO	ko_	KO_ID	ko_
-OMA	oma_	OMA_ID	oma_
-OrthoDB	orthodb_	ORTHODB_ID	orthodb_
-ProtClustDB	protclustdb_	PROTCLUSTDB_ID	protclustdb_
-BioCyc	biocyc_	BIOCYC_ID	biocyc_
-Reactome	reactome_	REACTOME_ID	reactome_
-UniPathWay	unipathway_	UNIPATHWAY_ID	unipathway_
-CleanEx	cleanex_	CLEANEX_ID	cleanex_
-GermOnline	germonline_	GERMONLINE_ID	germonline_
-ChEMBL	chembl_	CHEMBL	chembl_
-DrugBank	drugbank_	DRUGBANK_ID	drugbank_
-GenomeRNAi	genomernai_	GENOMERNAI_ID	genomernai_
-NextBio	nextbio_	NEXTBIO_ID	nextbio_

data/lib/protk/data/uniprot_accessions_table.txt

@@ -1,97 +0,0 @@
-UniProtKB AC/ID	ACC+ID	from
-UniProtKB AC	ACC	to
-UniProtKB ID	ID	to
-UniParc	UPARC	both
-UniRef50	NF50	both
-UniRef90	NF90	both
-UniRef100	NF100	both
-EMBL/GenBank/DDBJ	EMBL_ID	both
-EMBL/GenBank/DDBJ CDS	EMBL	both
-PIR	PIR	both
-UniGene	UNIGENE_ID	both
-Entrez Gene (GeneID)	P_ENTREZGENEID	both
-GI number*	P_GI	both
-IPI	P_IPI	both
-RefSeq Protein	P_REFSEQ_AC	both
-RefSeq Nucleotide	REFSEQ_NT_ID	both
-PDB	PDB_ID	both
-DisProt	DISPROT_ID	both
-HSSP	HSSP_ID	both
-DIP	DIP_ID	both
-MINT	MINT_ID	both
-Allergome	ALLERGOME_ID	both
-MEROPS	MEROPS_ID	both
-PeroxiBase	PEROXIBASE_ID	both
-PptaseDB	PPTASEDB_ID	both
-REBASE	REBASE_ID	both
-TCDB	TCDB_ID	both
-PhosSite	PHOSSITE_ID	both
-DMDM	DMDM_ID	both
-Aarhus/Ghent-2DPAGE	AARHUS_GHENT_2DPAGE_ID	both
-World-2DPAGE	WORLD_2DPAGE_ID	both
-DNASU	DNASU_ID	both
-Ensembl	ENSEMBL_ID	both
-Ensembl Protein	ENSEMBL_PRO_ID	both
-Ensembl Transcript	ENSEMBL_TRS_ID	both
-Ensembl Genomes	ENSEMBLGENOME_ID	both
-Ensembl Genomes Protein	ENSEMBLGENOME_PRO_ID	both
-Ensembl Genomes Transcript	ENSEMBLGENOME_TRS_ID	both
-GeneID	P_ENTREZGENEID	both
-GenomeReviews	GENOMEREVIEWS_ID	both
-KEGG	KEGG_ID	both
-PATRIC	PATRIC_ID	both
-UCSC	UCSC_ID	both
-VectorBase	VECTORBASE_ID	both
-AGD	AGD_ID	both
-ArachnoServer	ARACHNOSERVER_ID	both
-CGD	CGD	both
-ConoServer	CONOSERVER_ID	both
-CYGD	CYGD_ID	both
-dictyBase	DICTYBASE_ID	both
-EchoBASE	ECHOBASE_ID	both
-EcoGene	ECOGENE_ID	both
-euHCVdb	EUHCVDB_ID	both
-EuPathDB	EUPATHDB_ID	both
-FlyBase	FLYBASE_ID	both
-GeneCards	GENECARDS_ID	both
-GeneFarm	GENEFARM_ID	both
-GenoList	GENOLIST_ID	both
-H-InvDB	H_INVDB_ID	both
-HGNC	HGNC_ID	both
-HPA	HPA_ID	both
-LegioList	LEGIOLIST_ID	both
-Leproma	LEPROMA_ID	both
-MaizeGDB	MAIZEGDB_ID	both
-MIM	MIM_ID	both
-MGI	MGI_ID	both
-neXtProt	NEXTPROT_ID	both
-Orphanet	ORPHANET_ID	both
-PharmGKB	PHARMGKB_ID	both
-PomBase	POMBASE_ID	both
-PseudoCAP	PSEUDOCAP_ID	both
-RGD	RGD_ID	both
-SGD	SGD_ID	both
-TAIR	TAIR_ID	both
-TubercuList	TUBERCULIST_ID	both
-WormBase	WORMBASE_ID	both
-WormBase Transcript	WORMBASE_TRS_ID	both
-WormBase Protein	WORMBASE_PRO_ID	both
-Xenbase	XENBASE_ID	both
-ZFIN	ZFIN_ID	both
-eggNOG	EGGNOG_ID	both
-GeneTree	GENETREE_ID	both
-HOGENOM	HOGENOM_ID	both
-HOVERGEN	HOVERGEN_ID	both
-KO	KO_ID	both
-OMA	OMA_ID	both
-OrthoDB	ORTHODB_ID	both
-ProtClustDB	PROTCLUSTDB_ID	both
-BioCyc	BIOCYC_ID	both
-Reactome	REACTOME_ID	both
-UniPathWay	UNIPATHWAY_ID	both
-CleanEx	CLEANEX_ID	both
-GermOnline	GERMONLINE_ID	both
-ChEMBL	CHEMBL	both
-DrugBank	DRUGBANK_ID	both
-GenomeRNAi	GENOMERNAI_ID	both
-NextBio	NEXTBIO_ID	both

data/lib/protk/data/uniprot_input_accessions.loc

@@ -1,95 +0,0 @@
-UniProtKB AC/ID	uniprotkb_ac/id_	ACC+ID	uniprotkb_ac/id_
-UniParc	uniparc_	UPARC	uniparc_
-UniRef50	uniref50_	NF50	uniref50_
-UniRef90	uniref90_	NF90	uniref90_
-UniRef100	uniref100_	NF100	uniref100_
-EMBL/GenBank/DDBJ	embl/genbank/ddbj_	EMBL_ID	embl/genbank/ddbj_
-EMBL/GenBank/DDBJ CDS	embl/genbank/ddbj_cds_	EMBL	embl/genbank/ddbj_cds_
-PIR	pir_	PIR	pir_
-UniGene	unigene_	UNIGENE_ID	unigene_
-Entrez Gene (GeneID)	entrez_gene_(geneid)_	P_ENTREZGENEID	entrez_gene_(geneid)_
-GI number*	gi_number*_	P_GI	gi_number*_
-IPI	ipi_	P_IPI	ipi_
-RefSeq Protein	refseq_protein_	P_REFSEQ_AC	refseq_protein_
-RefSeq Nucleotide	refseq_nucleotide_	REFSEQ_NT_ID	refseq_nucleotide_
-PDB	pdb_	PDB_ID	pdb_
-DisProt	disprot_	DISPROT_ID	disprot_
-HSSP	hssp_	HSSP_ID	hssp_
-DIP	dip_	DIP_ID	dip_
-MINT	mint_	MINT_ID	mint_
-Allergome	allergome_	ALLERGOME_ID	allergome_
-MEROPS	merops_	MEROPS_ID	merops_
-PeroxiBase	peroxibase_	PEROXIBASE_ID	peroxibase_
-PptaseDB	pptasedb_	PPTASEDB_ID	pptasedb_
-REBASE	rebase_	REBASE_ID	rebase_
-TCDB	tcdb_	TCDB_ID	tcdb_
-PhosSite	phossite_	PHOSSITE_ID	phossite_
-DMDM	dmdm_	DMDM_ID	dmdm_
-Aarhus/Ghent-2DPAGE	aarhus/ghent-2dpage_	AARHUS_GHENT_2DPAGE_ID	aarhus/ghent-2dpage_
-World-2DPAGE	world-2dpage_	WORLD_2DPAGE_ID	world-2dpage_
-DNASU	dnasu_	DNASU_ID	dnasu_
-Ensembl	ensembl_	ENSEMBL_ID	ensembl_
-Ensembl Protein	ensembl_protein_	ENSEMBL_PRO_ID	ensembl_protein_
-Ensembl Transcript	ensembl_transcript_	ENSEMBL_TRS_ID	ensembl_transcript_
-Ensembl Genomes	ensembl_genomes_	ENSEMBLGENOME_ID	ensembl_genomes_
-Ensembl Genomes Protein	ensembl_genomes_protein_	ENSEMBLGENOME_PRO_ID	ensembl_genomes_protein_
-Ensembl Genomes Transcript	ensembl_genomes_transcript_	ENSEMBLGENOME_TRS_ID	ensembl_genomes_transcript_
-GeneID	geneid_	P_ENTREZGENEID	geneid_
-GenomeReviews	genomereviews_	GENOMEREVIEWS_ID	genomereviews_
-KEGG	kegg_	KEGG_ID	kegg_
-PATRIC	patric_	PATRIC_ID	patric_
-UCSC	ucsc_	UCSC_ID	ucsc_
-VectorBase	vectorbase_	VECTORBASE_ID	vectorbase_
-AGD	agd_	AGD_ID	agd_
-ArachnoServer	arachnoserver_	ARACHNOSERVER_ID	arachnoserver_
-CGD	cgd_	CGD	cgd_
-ConoServer	conoserver_	CONOSERVER_ID	conoserver_
-CYGD	cygd_	CYGD_ID	cygd_
-dictyBase	dictybase_	DICTYBASE_ID	dictybase_
-EchoBASE	echobase_	ECHOBASE_ID	echobase_
-EcoGene	ecogene_	ECOGENE_ID	ecogene_
-euHCVdb	euhcvdb_	EUHCVDB_ID	euhcvdb_
-EuPathDB	eupathdb_	EUPATHDB_ID	eupathdb_
-FlyBase	flybase_	FLYBASE_ID	flybase_
-GeneCards	genecards_	GENECARDS_ID	genecards_
-GeneFarm	genefarm_	GENEFARM_ID	genefarm_
-GenoList	genolist_	GENOLIST_ID	genolist_
-H-InvDB	h-invdb_	H_INVDB_ID	h-invdb_
-HGNC	hgnc_	HGNC_ID	hgnc_
-HPA	hpa_	HPA_ID	hpa_
-LegioList	legiolist_	LEGIOLIST_ID	legiolist_
-Leproma	leproma_	LEPROMA_ID	leproma_
-MaizeGDB	maizegdb_	MAIZEGDB_ID	maizegdb_
-MIM	mim_	MIM_ID	mim_
-MGI	mgi_	MGI_ID	mgi_
-neXtProt	nextprot_	NEXTPROT_ID	nextprot_
-Orphanet	orphanet_	ORPHANET_ID	orphanet_
-PharmGKB	pharmgkb_	PHARMGKB_ID	pharmgkb_
-PomBase	pombase_	POMBASE_ID	pombase_
-PseudoCAP	pseudocap_	PSEUDOCAP_ID	pseudocap_
-RGD	rgd_	RGD_ID	rgd_
-SGD	sgd_	SGD_ID	sgd_
-TAIR	tair_	TAIR_ID	tair_
-TubercuList	tuberculist_	TUBERCULIST_ID	tuberculist_
-WormBase	wormbase_	WORMBASE_ID	wormbase_
-WormBase Transcript	wormbase_transcript_	WORMBASE_TRS_ID	wormbase_transcript_
-WormBase Protein	wormbase_protein_	WORMBASE_PRO_ID	wormbase_protein_
-Xenbase	xenbase_	XENBASE_ID	xenbase_
-ZFIN	zfin_	ZFIN_ID	zfin_
-eggNOG	eggnog_	EGGNOG_ID	eggnog_
-GeneTree	genetree_	GENETREE_ID	genetree_
-HOGENOM	hogenom_	HOGENOM_ID	hogenom_
-HOVERGEN	hovergen_	HOVERGEN_ID	hovergen_
-KO	ko_	KO_ID	ko_
-OMA	oma_	OMA_ID	oma_
-OrthoDB	orthodb_	ORTHODB_ID	orthodb_
-ProtClustDB	protclustdb_	PROTCLUSTDB_ID	protclustdb_
-BioCyc	biocyc_	BIOCYC_ID	biocyc_
-Reactome	reactome_	REACTOME_ID	reactome_
-UniPathWay	unipathway_	UNIPATHWAY_ID	unipathway_
-CleanEx	cleanex_	CLEANEX_ID	cleanex_
-GermOnline	germonline_	GERMONLINE_ID	germonline_
-ChEMBL	chembl_	CHEMBL	chembl_
-DrugBank	drugbank_	DRUGBANK_ID	drugbank_
-GenomeRNAi	genomernai_	GENOMERNAI_ID	genomernai_
-NextBio	nextbio_	NEXTBIO_ID	nextbio_