rbbt-sources 1.2.0 → 2.0.0

data/lib/rbbt/sources/tfacts.rb

@@ -1,64 +1,65 @@
 require 'rbbt'
 require 'rbbt/resource'
-require 'nokogiri'
+require 'spreadsheet'
 
 module TFacts
   extend Resource
   self.subdir = "share/databases/TF"
 
-  def self.targets_for_gene_unsigned(gene_name)
-    doc = Nokogiri::HTML(Open.read("http://www.tfacts.org/source/tfsResultsns.php", :post => "TFS_ID=#{ gene_name }"))
+  TFacts.claim TFacts.source["Catalogues.xls"], :url, "http://www.tfacts.org/TFactS-new/TFactS-v2/tfacts/data/Catalogues.xls"
 
-    doc.css("td a").collect{|link| link.content.strip}
-  end
+  TFacts.claim TFacts.targets, :proc do
+    book = Spreadsheet.open TFacts.source["Catalogues.xls"].produce.find
+    sheet = book.worksheet 0
 
-  def self.targets_for_gene_signed(gene_name)
-    doc = Nokogiri::HTML(Open.read("http://www.tfacts.org/source/tfsResults.php", :post => "TFS_ID=#{ gene_name }"))
+    tsv = TSV.setup({}, :key_field => "Associated Gene Name", :fields => ["Transcription Factor Associated Gene Name"], :namespace => "Hsa", :type => :flat)
+    sheet.each do |row|
+      target, tf = row.values_at 0, 1
+      tsv[target] ||= []
+      tsv[target] << tf
+    end
 
-    rows = doc.css("tr")
-    rows.shift
-    targets = {}
-    rows.each{|row| gene, sign = row.css("td"); targets[gene.css("a").first.content.strip] = sign.content.strip}
-    targets
+    tsv.to_s
   end
 
-  def self.known_transcription_factors_signed
-    Open.read("http://www.tfacts.org/source/tfs.php").scan(/OPTION VALUE=([^\s]+)/).flatten
-  end
+  TFacts.claim TFacts.targets_signed, :proc do
+    book = Spreadsheet.open TFacts.source["Catalogues.xls"].produce.find
+    sheet = book.worksheet 0
 
-  def self.known_transcription_factors_unsigned
-    Open.read("http://www.tfacts.org/source/tfsns.php").scan(/OPTION VALUE=([^\s]+)/).flatten
-  end
+    tsv = TSV.setup({}, :key_field => "Associated Gene Name", :fields => ["Transcription Factor Associated Gene Name", "Sign"], :namespace => "Hsa", :type => :double)
+    sheet.each do |row|
+      target, tf, sign = row.values_at 0, 1, 2
+      tsv[target] ||= [[],[]]
+      tsv[target][0] << tf
+      tsv[target][1] << sign
+    end
 
-  TFacts.claim TFacts.targets, :proc do
-    tsv = Misc.process_to_hash(TFacts.known_transcription_factors_unsigned){|list| list.collect{|tf| TFacts.targets_for_gene_unsigned(tf)}}
-    TSV.setup tsv, :key_field => "Associated Gene Name", :fields => ["Target Associated Gene Name"], :type => :flat
     tsv.to_s
   end
 
-  TFacts.claim TFacts.targets_signed, :proc do
-    tsv = TSV.setup({}, :key_field => "Associated Gene Name", :fields => ["Target Associated Gene Name", "Target Sign"], :type => :double)
-    Misc.process_to_hash(TFacts.known_transcription_factors_signed){|list| list.collect{|tf| TFacts.targets_for_gene_signed(tf)}}.each do |tf, targets|
-      tsv[tf] = [targets.keys, targets.values]
-    end
-    tsv.to_s
+  TFacts.claim TFacts.regulators, :proc do
+    TFacts.targets.tsv.reorder("Transcription Factor Associated Gene Name").to_s
   end
+
 end
 
 if defined? Entity and defined? Gene and Entity === Gene
 
   module Gene
     property :is_transcription_factor? => :array2single do
-      @is_trasncription_factor ||= begin
-                                     tfs = TFacts.targets.keys
-                                     self.name.collect{|gene| tfs.include? gene}
-                                   end
+      tfs = TFacts.targets.keys
+      self.name.collect{|gene| tfs.include? gene}
+    end
+    persist :_ary_is_transcription_factor?
+
+    property :transcription_regulators => :array2single do
+      Gene.setup(TFacts.regulators.tsv(:persist => true).values_at(*self.name), "Associated Gene Name", self.organism)
     end
+    persist :_ary_transcription_regulators
 
-   property :transcription_targets => :array2single do
-     @transcription_targets ||= begin
-                                  Gene.setup(TFacts.targets.tsv(:persist => true).values_at(*self.name), "Associated Gene Name", self.organism)
-                                end
-   end
+    property :transcription_targets => :array2single do
+      Gene.setup(TFacts.targets.tsv(:persist => true).values_at(*self.name), "Associated Gene Name", self.organism)
+    end
+    persist :_ary_transcription_targets
   end
 end

data/lib/rbbt/sources/uniprot.rb

@@ -3,34 +3,32 @@ require 'rbbt/resource'
 require 'rbbt/sources/cath'
 require 'rbbt/sources/uniprot'
 
-module Uniprot
+module UniProt
   extend Resource
-  self.subdir = "share/databases/Uniprot"
+  self.subdir = "share/databases/UniProt"
 
-  Uniprot.claim Uniprot.annotated_variants, :proc do
+  UniProt.claim UniProt.annotated_variants, :proc do
     url = "http://www.uniprot.org/docs/humsavar.txt"
     tsv = TSV.open(CMD.cmd('tail -n +31 | head -n -4|grep "[[:alpha:]]"', :in => Open.open(url), :pipe => true), 
-                   :fix => Proc.new{|line| parts = line.split(/\s+/); (parts[0..5] + [(parts[6..-1] || []) * " "]) * "\t"}, :type => :list,:key_field => "Associated Gene Name", 
-                   :fields => ["Uniprot/SwissProt Accession", "Uniprot Variant ID", "Amino Acid Mutation", "Type of Variant", "SNP ID", "Disease"])
+                   :fix => Proc.new{|line| parts = line.split(/\s+/); (parts[1..5] + [(parts[6..-1] || []) * " "]) * "\t"}, 
+                   :type => :double,
+                   :merge => true,
+                   :key_field => "UniProt/SwissProt Accession",
+                   :fields => ["UniProt Variant ID", "Amino Acid Mutation", "Type of Variant", "SNP ID", "Disease"])
 
     tsv.unnamed = true
-    tsv.process "Amino Acid Mutation" do |mutation|
-      if mutation.match(/p\.(\w{3})(\d+)(\w{3})/)
-        wt = Misc::THREE_TO_ONE_AA_CODE[$1.downcase]
-        mut = Misc::THREE_TO_ONE_AA_CODE[$3.downcase]
-        [wt, $2, mut] * ""
-      else
-        mutation
+    tsv.process "Amino Acid Mutation" do |mutations|
+      mutations.collect do |mutation|
+        if mutation.match(/p\.(\w{3})(\d+)(\w{3})/)
+          wt = Misc::THREE_TO_ONE_AA_CODE[$1.downcase]
+          mut = Misc::THREE_TO_ONE_AA_CODE[$3.downcase]
+          [wt, $2, mut] * ""
+        else
+          mutation
+        end
       end
     end
-
-    uniprot_pos = tsv.identify_field "Uniprot/SwissProt Accession"
-    mutation_pos = tsv.identify_field "Amino Acid Mutation"
-    tsv.add_field "Mutated Isoform" do |key, values|
-      [values[uniprot_pos], values[mutation_pos]] * ":"
-    end
-
-    tsv.reorder("Mutated Isoform").to_s
+    tsv.to_s
   end
 
 
@@ -44,7 +42,12 @@ module Uniprot
     text.split(/\n/).each{|l| 
       next unless l =~ /^DR\s+PDB; (.*)\./
       id, method, resolution, region = $1.split(";").collect{|v| v.strip}
-      chains, start, eend = region.match(/(\w+)=(\d+)-(\d+)/).values_at(1,2,3)
+      begin
+        chains, start, eend = region.match(/(\w+)=(\d+)-(\d+)/).values_at(1,2,3)
+      rescue
+        Log.warn("Error process Uniprot PDB line: #{line}")
+        next
+      end
       pdb[id.downcase] = {:method => method, :resolution => resolution, :region => (start.to_i..eend.to_i), :chains => chains}
     }
     pdb
@@ -96,7 +99,6 @@ module Uniprot
     variants
   end
 
-
   def self.cath(protein)
     url = UNIPROT_TEXT.sub "[PROTEIN]", protein
     text = Open.read(url)
@@ -118,7 +120,7 @@ module Uniprot
   end
 
   def self.pdbs_covering_aa_position(protein, aa_position)
-    Uniprot.pdbs(protein).select do |pdb, info|
+    UniProt.pdbs(protein).select do |pdb, info|
       info[:region].include? aa_position
     end
   end

data/share/Ensembl/release_dates

@@ -0,0 +1,18 @@
+#: :type=:single
+#Release	build
+current	jul2012
+release-68	jul2012
+release-67	may2012
+release-66	feb2012
+release-65	dec2011
+release-64	sep2011
+release-63	jun2011
+release-62	apr2011
+release-61	feb2011
+release-60	nov2010
+release-59	aug2010
+release-58	may2010
+release-57	mar2010
+release-56	sep2009
+release-55	jul2009
+release-54	may2009

data/share/install/Genomes1000/Rakefile

@@ -0,0 +1,15 @@
+
+
+rule /(.+)/ do |t|
+  require 'net/ftp'
+  chromosome = File.basename(t.name)
+
+  ftp = Genomes1000::URL
+  ftp = Net::FTP.new(Genomes1000::FTP_SERVER)
+  ftp.login
+  ftp.chdir(Genomes1000::FTP_PATH)
+  file = ftp.list("*.chr" + chromosome + ".*").collect{|l| l.split(" ").last}.last
+  ddd file
+  exit
+ 
+end

data/share/install/JoChem/Rakefile

@@ -3,7 +3,7 @@ require 'rbbt/util/misc'
 
 def read_chunk(jochem)
   chunk = ""
-  while (not jochem.eof? and not (line = jochem.gets).match(/^--/))
+  while (not jochem.eof? and not (line = Misc.fixutf8(jochem.gets)).match(/^--/))
     chunk << line
   end
   return nil if chunk.empty?
@@ -20,7 +20,7 @@ def process_jochem
   identifiers = File.open('identifiers', 'w')
 
   identifiers.puts("#: :namespace=JoChem")
-  identifiers.puts("#ID\tCompound Name\tPubChem:ID\tDrugBank:ID")
+  identifiers.puts("#ID\tCompound Name\tPubChem:Substance ID\tPubChem:Coumpound ID\tDrugBank:ID\tChemIDplus:ID\tCAS:ID\tMeSH:Term\tChEBI:ID\tHMDB:ID\tKEGG:Coumpound ID\tKEGG:Drug ID")
 
   lexicon = File.open('lexicon', 'w')
   lexicon.puts("#: :namespace=JoChem")
@@ -49,12 +49,20 @@ def process_jochem
     tm = info["TM"] || []
     db = info["DB"] || []
 
+    cheb = db.collect{|code| code.match(/CHEB_(.*)/) ? $1 : nil}.compact
+    chid = db.collect{|code| code.match(/CHID_(.*)/) ? $1 : nil}.compact
     pubc = db.collect{|code| code.match(/PUBC_(.*)/) ? $1 : nil}.compact
+    pubs = db.collect{|code| code.match(/PUBS_(.*)/) ? $1 : nil}.compact
     drug = db.collect{|code| code.match(/DRUG_(.*)/) ? $1 : nil}.compact
+    cas  = db.collect{|code| code.match(/CAS_(.*)/) ? $1 : nil}.compact
+    mesh = db.collect{|code| code.match(/MESH_(.*)/) ? $1 : nil}.compact
+    hmdb = db.collect{|code| code.match(/HMDB_(.*)/) ? $1 : nil}.compact
+    kegg = db.collect{|code| code.match(/KEGG_(.*)/) ? $1 : nil}.compact
+    kegd = db.collect{|code| code.match(/KEGD_(.*)/) ? $1 : nil}.compact
     inch = db.collect{|code| code.match(/INCH_InChI=(.*)/) ? $1 : nil}.compact
 
     lexicon.puts [id, tm.unshift(na) * "|"] * "\t"
-    identifiers.puts [id, na, pubc * "|", drug * "|"] * "\t"
+    identifiers.puts [id, na, pubs * "|", pubc * "|", drug * "|", chid * "|", cas * "|", mesh * "|", cheb * "|", hmdb * "|", kegg * "|", kegd * "|" ] * "\t"
     inchi.puts [id, inch * "|"] * "\t" if inch.any?
     definitions.puts [id, df] * "\t" unless df.nil?
   end

data/share/install/NCI/Rakefile

@@ -1,7 +1,8 @@
 require 'nokogiri'
+require 'rbbt-util'
 
 module NCI
-  def self.get_pathways(xml, format = "UP")
+  def self.get_pathways(xml, format = "UP", get_short_name = false)
     doc = Nokogiri::XML(xml)
     pathways = {}
 
@@ -9,36 +10,60 @@ module NCI
     doc.xpath("//Molecule").each do |molecule|
       id = molecule.attribute('id').value
       type = molecule.attribute('molecule_type').value
-      next unless type == "protein"
       names = molecule.xpath("Name[@name_type='#{format}']").collect{|name| name.attribute("value").value}
-      next if names.empty?
-      molecules[id] = {:xml => molecule, :uniprot => names.first}
+      molecules[id] = {:xml => molecule, :proteins => names}
     end
 
+
     interactions = {}
     doc.xpath("//Interaction").each do |interaction|
       id = interaction.attribute('id').value
-      molecule_ids = interaction.xpath('*/InteractionComponent').collect{|c| c.attribute('molecule_idref').value}
+      type = interaction.attribute('interaction_type').value
+      molecule_ids = interaction.xpath('InteractionComponentList/InteractionComponent').collect{|c| c.attribute('molecule_idref').value}.flatten.compact
+      pathway_ids = interaction.xpath('Abstraction').collect{|c| c.attribute('pathway_idref').value}.flatten.compact
 
-      interactions[id] = {:xml => interaction, :molecule_ids => molecule_ids}
+      interactions[id] = {:xml => interaction, :molecule_ids => molecule_ids, :pathway_ids => pathway_ids}
     end
 
     doc.xpath("//Pathway").each do |pathway|
       id = pathway.attribute('id').value
       subnet = pathway.attribute('subnet').value
       name = pathway.xpath('LongName').first.content
+      short_name = pathway.xpath('ShortName').first.content if get_short_name
 
-      interaction_ids = pathway.xpath("*/PathwayComponent").collect{|component| component.attribute("interaction_idref").value}
+      interaction_ids = pathway.xpath("PathwayComponentList/PathwayComponent").collect{|component| component.attribute("interaction_idref").value}
 
-      pathway_interactions = interaction_ids.collect{|id| interactions[id]}
-      pathway_molecule_ids = pathway_interactions.collect{|info| info[:molecule_ids]}.flatten
+      pathway_interactions = interaction_ids.collect{|i| interactions[i]}
+      pathway_molecule_ids = pathway_interactions.collect{|info| info[:molecule_ids]}.compact.flatten
 
-      pathway_uniprot_ids = pathway_molecule_ids.collect do |id| 
-        next unless molecules.include? id
-        molecules[id][:uniprot]
+      pathway_uniprot_ids = pathway_molecule_ids.collect do |i| 
+        next unless molecules.include? i
+        molecules[i][:proteins]
+      end
+      if get_short_name
+        pathways[id] = [[name], [pathway_uniprot_ids.flatten.compact.uniq], [short_name]]
+      else
+        pathways[id] = [[name], [pathway_uniprot_ids.flatten.compact.uniq]]
       end
-      pathways[id] = [[name], [pathway_uniprot_ids.compact.uniq]]
     end
+    
+    doc.xpath("//Pathway").each do |pathway|
+      id = pathway.attribute('id').value
+      subnet = pathway.attribute('subnet').value
+      name = pathway.xpath('LongName').first.content
+
+      interaction_ids = pathway.xpath("PathwayComponentList/PathwayComponent").collect{|component| component.attribute("interaction_idref").value}
+
+      pathway_interactions = interaction_ids.collect{|i| interactions[i]}
+      pathway_subnet_ids = pathway_interactions.collect{|info| info[:pathway_ids]}.compact.flatten
+
+      pathway_subnet_ids.collect do |nid| 
+        next unless pathways.include? nid
+        new_genes = pathways[id].last
+        pathways[nid][1] = (pathways[nid][1] + new_genes).uniq
+      end
+    end
+
     pathways
   end
 end
@@ -60,11 +85,25 @@ file 'biocarta_pathways' do |t|
 
   xml = Open.read(url)
 
-  pathways = NCI.get_pathways(xml, "LL")
+  pathways = NCI.get_pathways(xml, "LL", true)
 
-  Open.write(t.name, TSV.setup(pathways, :type => :double, :key_field => "NCI BioCarta Pathway ID", :fields => ["Pathway Name","Entrez Gene ID"]).to_s)
+  Open.write(t.name, TSV.setup(pathways, :type => :double, :key_field => "NCI BioCarta Pathway ID", :fields => ["Pathway Name", "Entrez Gene ID", "Pathway Short Name"]).to_s)
 end
 
+file 'biocarta_pathways_fixed_ids' => 'biocarta_pathways' do |t|
+  orig = TSV.open(Open.open(t.prerequisites.first))
+  tsv = TSV.setup({}, :type => :double, :key_field => "BioCarta Pathway ID", :fields => ["Pathway Name", "Entrez Gene ID"])
+
+  orig.through do |key, values|
+    name, genes, short = values
+    code = "h_" + short.first
+    tsv[code] = [name, genes]
+  end
+
+  Open.write(t.name, tsv.to_s)
+end
+
+
 file 'reactome_pathways' do |t|
 
   url = "ftp://ftp1.nci.nih.gov/pub/PID/XML/Reactome.xml.gz"
@@ -76,4 +115,3 @@ file 'reactome_pathways' do |t|
   Open.write(t.name, TSV.setup(pathways, :type => :double, :key_field => "NCI Reactome Pathway ID", :fields => ["Pathway Name","UniProt/SwissProt Accession"]).to_s)
 end
 
-

data/share/install/Organism/Hsa/Rakefile

@@ -43,7 +43,7 @@ $biomart_probe_identifiers = [
   [ 'AFFY HuEx', 'affy_huex_1_0_st_v2', "HuEx" ],
   [ 'AFFY HuGene', 'affy_hugene_1_0_st_v1' ],
   [ 'AFFY U133 X3P', 'affy_u133_x3p' ],
-  [ 'Agilent WholeGenome',"agilent_wholegenome" ],
+  #[ 'Agilent WholeGenome',"agilent_wholegenome" ],
   [ 'Agilent CGH 44b', 'agilent_cgh_44b' ],
   [ 'Codelink ID', 'codelink' ],
   [ 'Illumina HumanWG 6 v2', 'illumina_humanwg_6_v2' ],
@@ -62,6 +62,7 @@ $biomart_identifiers = [
   [ 'UniProt/SwissProt Accession', "uniprot_swissprot_accession"  ],
   [ 'HGNC ID', "hgnc_id", 'HGNC'],
   [ 'EMBL (Genbank) ID' , "embl"] , 
+  [ 'RefSeq mRNA' , "refseq_mrna"] , 
 
   # Probes
   [ 'AFFY HC G110', 'affy_hc_g110' ],
@@ -80,7 +81,7 @@ $biomart_identifiers = [
   [ 'AFFY HuEx', 'affy_huex_1_0_st_v2', "HuEx" ],
   [ 'AFFY HuGene', 'affy_hugene_1_0_st_v1' ],
   [ 'AFFY U133 X3P', 'affy_u133_x3p' ],
-  [ 'Agilent WholeGenome',"agilent_wholegenome" ],
+  #[ 'Agilent WholeGenome',"agilent_wholegenome" ],
   [ 'Agilent CGH 44b', 'agilent_cgh_44b' ],
   [ 'Codelink ID', 'codelink' ],
   [ 'Illumina HumanWG 6 v2', 'illumina_humanwg_6_v2' ],

data/share/install/Organism/Rno/Rakefile

@@ -19,12 +19,12 @@ $biomart_lexicon = [
 ]
 
 $biomart_identifiers = [ 
+  ['Entrez Gene ID', "entrezgene"],
   ['Associated Gene Name' , "external_gene_id"], 
   ['Protein ID' , "protein_id"] , 
   ['UniProt/SwissProt ID' , "uniprot_swissprot"] , 
   ['UniProt/SwissProt Accession' , "uniprot_swissprot_accession"] , 
   ['RefSeq Protein ID' , "refseq_peptide"] , 
-  ['RefSeq DNA ID' , "refseq_dna"] , 
   ['EMBL (Genbank) ID' , "embl"] , 
   ['RGD ID' , "rgd"] , 
   ['RGD Symbol' , "rgd_symbol"] , 
@@ -39,7 +39,6 @@ $biomart_identifiers = [
   ['Affy rg u34c', "affy_rg_u34c"],
   ['Affy rn u34', "affy_rn_u34"],
   ['Affy rt u34', "affy_rt_u34"],
-  ['Agilent WholeGenome',"agilent_wholegenome" ],
   ['Codelink ID ', "codelink"],
 ]
 

data/share/install/Organism/Sce/Rakefile

@@ -4,50 +4,48 @@ require 'rbbt/sources/entrez'
 require File.join(File.dirname(__FILE__), '../../lib/helpers')
 
 $taxs = [559292,4932]
-$native = "SGD ID"
-$url = "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab"
-$biomart_db = 'scerevisiae_gene_ensembl'
-$biomart_main = ['Entrez Gene ID', 'entrezgene']
-$ortholog_key = "yeast_ensembl_gene"
-
-
-file 'scientific_name' do |t|
-  File.open(t.name, 'w') do |f| f.puts "Saccharomyces cerevisiae" end
-end
-
-file 'lexicon' do |t|
-  lexicon = tsv_file($url, [$native, 0], [3, 4, 5], :keep_empty => true)
-
-  lexicon = merge_entrez(lexicon, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tSGD:S0/)})
-
-  lexicon = merge_biomart(lexicon, $biomart_db, $biomart_main, [['Interpro Description' , "interpro_description"]])
-
-  lexicon = lexicon.slice(lexicon.fields - ["Entrez Gene ID"])
+$scientific_name = "Saccharomyces cerevisiae"
+#$ortholog_key = "yeast_ensembl_gene"
 
-  File.open(t.name, 'w') do |f| f.puts lexicon end
-end
-
-file 'identifiers' do |t|
-  identifiers = tsv_file($url, [$native, 0], [["Ensembl Gene ID", 3], ["Associated Gene Name",4], ["Associated Gene Name Alias", 5]], :keep_empty => true)
-
-  identifiers = merge_entrez(identifiers, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tSGD:S0/)})
-
-  identifiers = merge_biomart(identifiers, $biomart_db, $biomart_main,
-                [['Associated Gene Name' , "external_gene_id"], 
-                  ['Ensembl Gene ID', "ensembl_gene_id"  ],
-                  ['Ensembl Protein ID', "ensembl_peptide_id"  ],
-                  ['RefSeq Protein ID' , "refseq_peptide"] , 
-                  ['UniProt/SwissProt ID' , "uniprot_swissprot"] , 
-                  ['UniProt/SwissProt Accession' , "uniprot_swissprot_accession"] , 
-                  ['Protein ID' , "protein_id"] , 
-                  ['EMBL (Genbank) ID' , "embl"] , 
-                  # Affymetrix
-                  ['Affy yeast 2',"affy_yeast_2"],
-                  ['Affy yg s98', "affy_yg_s98"]])
-
-  File.open(t.name, 'w') do |f| f.puts identifiers end
-end
-
-
-task :default => ['name', 'lexicon', 'identifiers']
+$biomart_db = 'scerevisiae_gene_ensembl'
 
+$biomart_lexicon = [ 
+  [ 'Associated Gene Name' , "external_gene_id"], 
+]
+
+$biomart_protein_identifiers = [
+  [ 'Protein ID', "protein_id"  ],
+  [ 'RefSeq Protein ID', "refseq_peptide"  ],
+  [ 'Unigene ID', "unigene"  ],
+  [ 'UniProt/SwissProt ID', "uniprot_swissprot"  ],
+  [ 'UniProt/SwissProt Accession', "uniprot_swissprot_accession"  ],
+]
+
+$biomart_probe_identifiers = [
+]
+
+$biomart_identifiers = [ 
+  [ 'Entrez Gene ID', "entrezgene"],
+  [ 'Ensembl Protein ID', "ensembl_peptide_id"  ],
+  [ 'Associated Gene Name', "external_gene_id"  ],
+  [ 'Protein ID', "protein_id"  ],
+  [ 'RefSeq Protein ID', "refseq_peptide"  ],
+  [ 'UniProt/SwissProt ID', "uniprot_swissprot"  ],
+  [ 'UniProt/SwissProt Accession', "uniprot_swissprot_accession"  ],
+  [ 'EMBL (Genbank) ID' , "embl"] , 
+  [ 'RefSeq mRNA' , "refseq_mrna"] , 
+]
+
+$biomart_go= [
+  ["GO ID", 'go_id'],
+  ["GO Namespace", 'namespace_1003'],
+]
+
+$biomart_go_2009= [
+  ["GO BP ID", 'go_biological_process_id'],
+  ["GO MF ID", 'go_molecular_function_id'],
+  ["GO CC ID", 'go_cellular_component_id'],
+]
+
+$namespace = File.basename(File.dirname(File.expand_path(__FILE__)))
+load File.join(File.dirname(__FILE__), '../organism_helpers.rb')