protk 1.2.0 → 1.2.1

data/lib/convert_util.rb

@@ -0,0 +1,27 @@
+require 'libxml'
+require 'constants'
+
+class ConvertUtil
+
+  def self.ensure_mzml_indexed(run_file)
+    if unindexed_mzml?(run_file)
+      index_mzml(run_file)
+    end
+  end
+
+  def self.index_mzml(mzml_file)
+    Dir.mktmpdir do |tmpdir|
+      genv=Constants.new
+      %x["#{genv.tpp_bin}/msconvert -o #{tmpdir} #{mzml_file}"]
+      indexed_file = Dir["#{tmpdir}/*"][0]
+      FileUtils.mv(indexed_file, mzml_file)
+    end
+  end
+  
+  def self.unindexed_mzml?(mzml_file)
+    reader = LibXML::XML::Reader.file(mzml_file)
+    reader.read
+    reader.name == "mzML"
+  end
+
+end

data/lib/pepxml.rb

@@ -0,0 +1,22 @@
+require 'rubygems'
+require 'rexml/document'
+require 'rexml/xpath'
+
+class PepXML
+  def initialize(file_name)
+    @doc=REXML::Document.new(File.new(file_name))
+  end
+
+  def find_runs() 
+    runs = {}
+    REXML::XPath.each(@doc,"//msms_run_summary") do |summary|
+      base_name = summary.attributes["base_name"]
+      if not runs.has_key?(base_name)
+        runs[base_name] = {:base_name => summary.attributes["base_name"],
+                           :type => summary.attributes["raw_data"]}
+      end
+    end
+    runs
+  end
+  
+end

data/lib/protk/big_search_rakefile.rake

@@ -0,0 +1,16 @@
+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

@@ -0,0 +1,23 @@
+# 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/bio_sptr_extensions.rb

@@ -177,7 +177,26 @@ class Bio::SPTR < Bio::EMBLDB
     return self.safely_get_drentry_for_key("NextBio")
   end
   
-  
+  def uniprot_link
+    return "http://www.uniprot.org/uniprot/#{self.accession}.html"
+  end
+
+  def nextbio_link
+    return "http://www.nextbio.com/b/home/home.nb?id=#{self.nextbio}&type=feature"
+  end
+
+  def intact_link
+    return "http://www.ebi.ac.uk/intact/pages/interactions/interactions.xhtml?query=#{self.intact}*"
+  end
+
+  def pride_link
+    return "http://www.ebi.ac.uk/pride/searchSummary.do?queryTypeSelected=identification%20accession%20number&identificationAccessionNumber=#{self.pride}"
+  end
+
+  def ensembl_link
+    return "http://www.ensembl.org/Homo_sapiens/Transcript/Summary?db=core;t=#{self.ensembl}"
+  end
+
   # Number of transmembrane regions
   #
   def num_transmem
@@ -206,5 +225,25 @@ class Bio::SPTR < Bio::EMBLDB
       p "Warning: Unable to parse feature table for entry #{self.accession}"      
     end
   end
-  
+
+  def ref_dump
+    return self.ref.to_s
+  end
+
+  def seq_dump
+    return self.seq.to_s
+  end
+
+  def tax_dump
+    return self.ox.to_s
+  end
+
+  def species_dump
+    return self.os.to_s
+  end
+
+  def feature_dump
+    return self.ft.to_s
+  end
+
 end

data/lib/protk/constants.rb

@@ -169,6 +169,19 @@ class Constants
     return "#{self.openms_root}/bin/ExecutePipeline"
   end
 
+  def tandem_root
+    path=@env['tandem_root']
+    if ( path =~ /^\//)
+      return path 
+    else
+      return "#{@protk_dir}/#{@env['tandem_root']}"
+    end
+  end
+
+  def gpmtandem
+    return "#{self.tandem_root}/bin/tandem"
+  end
+
   def protein_database_root
     path=@env['protein_database_root']
     if ( path =~ /^\// )

data/lib/protk/data/apt-get_packages.yaml

@@ -45,6 +45,10 @@ tpp:
 - libcurl4-openssl-dev
 - libxml2-dev
 - libgd2-xpm-dev
+- perl-ExtUtils-MakeMaker
+- perl-ExtUtils-AutoInstall
+- perl-ExtUtils-CBuilder
+- perl-CPAN
 
 msgfplus:
 - java-1.7.0-openjdk

data/lib/protk/data/default_config.yml

@@ -18,4 +18,5 @@ openms_root: tools/openms
 msgfplus_root: tools/msgfplus
 blast_root: tools/blast
 pwiz_root: tools/pwiz
+tandem_root: tools/tandem
 log_file: Logs/protk.log

data/lib/protk/data/make_uniprot_table.rb

@@ -0,0 +1,29 @@
+#!/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/predefined_db.trembl_annotation.yaml

@@ -0,0 +1,20 @@
+#
+# This is a predefined setup file for manage_db 
+#
+# Swissprot_uniprot annotation database (full entries for each protein)
+#
+--- 
+:description: Swissprot Trembl annotation database (full entries for each protein)
+:archive_old: false
+:is_annotation_db: true
+:decoy_prefix: decoy_
+:include_filters: []
+
+:format: dat
+:id_regexes: []
+
+:make_blast_index: false
+:sources: 
+- - ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.dat.gz
+  - ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/reldate.txt
+:decoys: false

data/lib/protk/data/uniprot_accessions.loc

@@ -0,0 +1,96 @@
+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

@@ -0,0 +1,97 @@
+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

@@ -0,0 +1,95 @@
+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_