rbbt-sources 2.1.7 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: daf367338fb6e78d2cb7b76440e67712d27f34ab
-  data.tar.gz: 5b7a7308779ec4441fa2eb997d6f9b7f0dd37e3a
+  metadata.gz: 00cd4a9602b9ea2637a620b30cd3d48a6d63a9fe
+  data.tar.gz: c282f8c86de5148343e5a83ea524cdc09435b9fb
 SHA512:
-  metadata.gz: bb568b0d788284e82d0ac0d9cdbd14db7c0e59b4977ddce57e2701f25ca18bbef93d43424179a188f73daaacc87963d039a17aaf0916872945f2d384e6441552
-  data.tar.gz: b24f422176f10f518f692a7878c2389df0276df27a074feb5918bae1993f860fae4558d330f95de66a7857da712b5c811e487c0b117f553106215d1065f856af
+  metadata.gz: 701a67455ca18d9c705e2c409628cd5463f7449d2ee40ba4d26cce6f203018db21b9c6ee6f233cf8d80e44e28d3ffcfa08e474678b538b8db7cb80c44e5eac5a
+  data.tar.gz: 4bbcf6f222c01c5f3314617ed7c2458b3cebb9d8b3293ac631305ea2c610c935792fe0e5d6a7402f041aab4304e5586a7989f1e2a097b5dc620f0cb7a208250c

data/lib/rbbt/sources/kegg.rb

@@ -0,0 +1,127 @@
+require 'rbbt'
+require 'rbbt/resource'
+
+module KEGG
+  extend Resource
+  self.pkgdir = "phgx"
+  self.subdir = "share/kegg"
+
+
+  KEGG.claim KEGG.root, :rake, Rbbt.share.install.KEGG.Rakefile.find(:lib)
+
+  def self.names
+    @@names ||= KEGG.pathways.tsv :fields => ["Pathway Name"], :persist => true, :type => :single, :unnamed => true
+  end
+
+  def self.descriptions
+    @@descriptions ||= KEGG.pathways.tsv(:fields => ["Pathway Description"], :persist => true, :type => :single, :unnamed => true)
+  end
+
+
+  def self.index2genes
+    @@index2genes ||= KEGG.gene_pathway.tsv(:key_field => "KEGG Pathway ID", :fields => ["KEGG Gene ID"], :persist => true, :type => :flat, :merge => true)
+  end
+
+  def self.index2ens
+    @@index2ens ||= KEGG.identifiers.index(:persist => true)
+  end
+
+  def self.index2kegg
+    @@index2kegg ||= KEGG.identifiers.index(:target => "KEGG Gene ID", :persist => true)
+  end
+
+  def self.id2name(id)
+    names[id]
+  end
+
+  def self.name2id(name)
+    names.select{|id,n| n.downcase.index(name.downcase) == 0}.collect{|id,n| id} rescue []
+  end
+
+
+  def self.description(id)
+    descriptions[id]
+  end
+end
+
+if defined? Entity 
+
+  module KeggPathway
+    extend Entity
+    self.format = "KEGG Pathway ID"
+
+    self.annotation :organism
+
+    def self.filter(query, field = nil, options = nil, entity = nil)
+      return true if query == entity
+
+      return true if KeggPathway.setup(entity.dup, options.merge(:format => field)).name.index query
+
+      false
+    end
+
+    property :name => :single2array do
+      return nil if self.nil?
+      name = KEGG.id2name(self)
+      name.sub(/ - Homo.*/,'') unless name.nil?
+    end
+
+    property :description => :single2array do
+      KEGG.description(self)
+    end
+
+    property :genes => :array2single do |*args|
+      organism = args.first || self.organism
+      KEGG.index2genes.values_at(*self).
+        each{|gene| gene.organism = organism if gene.respond_to? :organism }
+    end
+  end
+
+  if defined? Gene and Entity === Gene
+    module Gene
+      self.format = "KEGG Gene ID"
+
+      def to_kegg
+        return self if format == "KEGG Gene ID"
+        if Array === self
+          Gene.setup(KEGG.index2kegg.values_at(*to("Ensembl Gene ID")), "KEGG Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
+        else
+          Gene.setup(KEGG.index2kegg[to("Ensembl Gene ID")], "KEGG Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
+        end
+      end
+
+      def from_kegg
+        return self unless format == "KEGG Gene ID"
+        if Array === self
+          Gene.setup(KEGG.index2ens.values_at(*self), "Ensembl Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
+        else
+          Gene.setup(KEGG.index2ens[self], "Ensembl Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
+        end
+      end
+
+      def self.gene_kegg_pathway_index
+        @@gene_kegg_pathway_index ||= 
+          KEGG.gene_pathway.tsv(:persist => true, :key_field => "KEGG Gene ID", :fields => ["KEGG Pathway ID"], :type => :flat, :merge => true)
+      end
+
+      property :to => :array2single do |new_format|
+        case
+        when format == new_format
+          self 
+        when format == "KEGG Gene ID"
+          ensembl = from_kegg.clean_annotations
+          Gene.setup(Translation.job(:tsv_translate, "", :organism => organism, :genes => ensembl, :format => new_format).exec.chunked_values_at(ensembl), new_format, organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
+        when new_format == "KEGG Gene ID"
+          to_kegg
+        else
+          Gene.setup(Translation.job(:tsv_translate, "", :organism => organism, :genes => self, :format => new_format).exec.chunked_values_at(self), new_format, organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
+        end
+      end
+
+      property :kegg_pathways => :array2single do
+        @kegg_pathways ||= Gene.gene_kegg_pathway_index.values_at(*self.to_kegg).
+          each{|pth| pth.organism = organism if pth.respond_to? :organism }.tap{|o| KeggPathway.setup(o, organism)}
+      end
+    end
+  end
+end

data/lib/rbbt/sources/matador.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+
+module Matador
+  extend Resource
+  self.pkgdir = "phgx"
+  self.subdir = "share/matador"
+
+  Matador.claim Matador.root, :rake, Rbbt.share.install.Matador.Rakefile.find(:lib)
+end

data/lib/rbbt/sources/pharmagkb.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+
+module PharmaGKB
+  extend Resource
+  self.pkgdir = "phgx"
+  self.subdir = "share/pharmagkb"
+
+  PharmaGKB.claim PharmaGKB.root, :rake, Rbbt.share.install.PharmaGKB.Rakefile.find(:lib)
+end

data/lib/rbbt/sources/pina.rb

@@ -0,0 +1,35 @@
+require 'phgx'
+
+module Pina
+  extend Resource
+  self.pkgdir = "phgx"
+  self.subdir = "share/pina"
+
+  Pina.claim Pina.root, :rake, Rbbt.share.install.Pina.Rakefile.find(:lib)
+end
+
+if defined? Entity and defined? Gene and Entity === Gene
+  require 'rbbt/entity/gene'
+  require 'rbbt/entity/interactor'
+  require 'rbbt/sources/PSI_MI'
+
+  module Gene
+    property :pina_interactors => :array2single do 
+      ens2uniprot = Organism.identifiers(organism).tsv :key_field => "Ensembl Gene ID", :fields => ["UniProt/SwissProt Accession"], :type => :flat, :persist => true, :unnamed => true
+      pina        = Pina.protein_protein.tsv(:persist => true, :fields => ["Interactor UniProt/SwissProt Accession", "Method", "PMID"], :type => :double, :merge => true, :unnamed => true)
+
+      int = self.ensembl.collect do |ens|
+        uniprot = ens2uniprot[ens]
+        list = pina.values_at(*uniprot).compact.collect do |v|
+          Misc.zip_fields(v).collect do |o, method, articles|
+            Interactor.setup(o, PSI_MITerm.setup(method.split(";;")), PMID.setup(articles.split(";;")))
+          end
+        end.flatten.uniq
+        Gene.setup(list, "UniProt/SwissProt Accession", organism).extend(AnnotatedArray)
+      end
+
+      Gene.setup(int, "UniProt/SwissProt Accession", organism).extend(AnnotatedArray)
+    end
+  end
+end
+

data/lib/rbbt/sources/stitch.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+
+module STITCH
+  extend Resource
+  self.pkgdir = "phgx"
+  self.subdir = "share/stitch"
+
+  STITCH.claim STITCH.root, :rake, Rbbt.share.install.STITCH.Rakefile.find(:lib)
+end

data/lib/rbbt/sources/string.rb

@@ -0,0 +1,27 @@
+require 'phgx'
+
+module STRING
+  extend Resource
+  self.pkgdir = "phgx"
+  self.subdir = "share/string"
+
+  STRING.claim STRING.root, :rake, Rbbt.share.install.STRING.Rakefile.find(:lib)
+end
+
+if defined? Entity and defined? Gene and Entity === Gene
+  module Gene
+    property :string_interactors => :array2single do |*args|
+      threshold = args.first || 800
+      string = STRING.protein_protein.tsv(:unnamed => true, :persist => true, :type => :double)
+      all = self.ensembl.collect do |gene|
+        interactors = gene.proteins.collect{|protein| Misc.zip_fields((string[protein] || [[],[]])).select{|i, score| score.to_i > threshold}.collect{|ints,s| ints}}.compact.flatten.uniq
+        Protein.setup(interactors, "Ensembl Protein ID", organism).transcript.gene.compact.uniq
+      end
+
+      all.compact.first.annotate all if Annotated === all.compact.first 
+
+      all
+    end
+  end
+end
+

data/share/install/KEGG/Rakefile

@@ -0,0 +1,114 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks  "h.sapiens" => "ftp://ftp.genome.jp/pub/kegg/genes/organisms/hsa/H.sapiens.ent",
+  "hsa_gene_map.tab" => "ftp://ftp.genome.jp/pub/kegg/pathway/organisms/hsa/hsa_gene_map.tab",
+  "drugs" => "ftp://ftp.genome.jp/pub/kegg/medicus/drug/drug",
+  "pathways" => "ftp://ftp.genome.jp/pub/kegg/pathway/pathway"
+
+
+file :identifiers => 'source/h.sapiens' do |t|
+  pairs = {}
+  entry = nil
+  Open.read(t.prerequisites.first).each do |line|
+    if line =~ /^ENTRY\s+(\d+)/
+      entry = $1
+      next
+    end
+
+    if line =~ /Ensembl: (ENSG\d+)/
+      pairs[entry] = $1
+    end
+  end
+
+  Open.write(t.name, ['#Ensembl Gene ID','KEGG Gene ID'] * "\t" + "\n" + pairs.collect{|entry, ens| [ens, "hsa:" + entry] * "\t"} * "\n")
+end
+
+file :gene_drug => 'source/drugs' do |t|
+  pairs = {}
+  drug = nil
+  Open.read(t.prerequisites.first).
+    scan(/^[A-Z].*?(?:^[A-Z])/sm).select{|line| line =~ /^ENTRY|TARGET/}.collect{|line| line.sub(/\s+/,' ')}.each do |line|
+      if line =~ /^ENTRY\s+(\w+)/
+        drug = $1
+        next
+      end
+
+      if line =~ /TARGET.*?\[HSA:(.*?)\]/
+        genes = $1.split(/\s/)
+        genes.each do |gene|
+          pairs[gene] ||= []
+          pairs[gene] << drug
+        end
+      end
+  end
+
+  Open.write(t.name, ['#KEGG Gene ID', 'KEGG Drug ID'] * "\t" + "\n" + pairs.collect{|gene, drugs| ["hsa:" + gene, drugs * "|" ] * "\t"} * "\n")
+end
+
+file :drugs => 'source/drugs' do |t|
+  info = {}
+  drug = nil
+  Open.read(t.prerequisites.first).
+    scan(/^[A-Z].*?(?:^[A-Z])/sm).select{|line| line =~ /^ENTRY|NAME|DBLINKS/}.collect{|line| line.sub(/\s+/,' ')}.each do |line|
+      if line =~ /^ENTRY\s+(\w+)/
+        drug = $1
+        next
+      end
+
+      if line =~ /^NAME(.*)/
+        names = $1.split(/;/)
+        names.each do |name|
+          info[drug] ||= [[],[]]
+          info[drug][0] << name.chomp.strip
+        end
+      end
+
+      if line =~ /^DBLINKS(.*)/
+        $1.match(/PubChem: (\d*)/)
+        pubchem = $1
+        next unless pubchem
+        info[drug] ||= [[],[]]
+        info[drug][1] << pubchem.chomp.strip
+      end
+  end
+
+  Open.write(t.name, ['#KEGG Drug ID', 'KEGG Drug Name', 'PubChem Drug ID'] * "\t" + "\n" + info.collect{|drug, info| [drug, info.collect{|v| v * "|"} ].flatten * "\t"} * "\n")
+end
+
+file :pathways => 'source/pathways' do |t|
+  descs = {}
+  names = {}
+  klass = {}
+  pathway = nil
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /ENTRY\s+(\w+)/
+      pathway = $1.strip
+    end
+
+    if line =~ /NAME (.*)/
+      names[pathway] = $1.strip
+    end
+
+    if line =~ /DESCRIPTION (.*)/
+      descs[pathway] = $1.strip
+    end
+
+    if line =~ /CLASS (.*)/
+      klass[pathway] = $1.strip
+    end
+  end
+  
+  Open.write(t.name, "#: :type=:list\n" + ['#KEGG Pathway ID', 'Pathway Name', 'Pathway Description', 'Pathway Class'] * "\t" + "\n" + names.keys.collect{|pathway| [pathway, names[pathway], descs[pathway], klass[pathway]] * "\t"} * "\n")
+end
+
+process_tsv :gene_pathway, 'hsa_gene_map.tab',
+  :sep2 => ' ' do 
+  headers ['KEGG Gene ID', 'KEGG Pathway ID']
+  data do |gene, pathway|
+    "hsa:#{ gene }\t#{pathway.flatten.collect{|name| "hsa" + name} * "|"}"
+  end
+end
+
+add_to_defaults [:pathways, :drugs, :gene_drug, :genes]
+
+

data/share/install/PharmaGKB/Rakefile

@@ -0,0 +1,211 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks "genes" => "http://www.pharmgkb.org/commonFileDownload.action?filename=genes.zip",
+  "drugs" => "http://www.pharmgkb.org/commonFileDownload.action?filename=drugs.zip",
+  "diseases" => "http://www.pharmgkb.org/commonFileDownload.action?filename=diseases.zip",
+  "relationships" => "http://www.pharmgkb.org/commonFileDownload.action?filename=relationships.zip",
+  "variants" => "http://www.pharmgkb.org/commonFileDownload.action?filename=variantAnnotations.zip",
+  "pathways" => "http://www.pharmgkb.org/commonFileDownload.action?filename=pathways-tsv.zip"
+ 
+
+process_tsv :diseases, 'diseases', 
+  :header_hash => "",
+  :fix => proc{|l| l.gsub(/","/,'|').gsub(/"/,'').gsub(/,(\t|$)/,'\1')} do
+  headers ['PhGKB Disease ID']
+end
+
+process_tsv :identifiers, 'genes', 
+  :header_hash => "",
+  :fix => proc{|l| l.gsub(/","/,'|').gsub(/"/,'').gsub(/,(\t|$)/,'\1')} do
+  headers ['PhGKB Gene ID', 'Entrez Gene ID', 'Ensembl Gene Id', 'UniProt/SwissProt Accession', 'Long Name', 'Associated Gene Name']
+end
+
+process_tsv :drugs, 'drugs', 
+  :header_hash => "",
+  :fields => ['Name', 'DrugBank Id', 'SMILES', "MeSH IDs"],
+  :fix => proc{|l| l.gsub(/","/,'|').gsub(/"/,'').gsub(/,(\t|$)/,'\1')} do
+  headers ['PhGKB Drug ID', 'Drug Name', 'DrugBank Id', 'SMILES', "MeSH ID"]
+end
+
+process_tsv :relationships, 'relationships',
+  :header_hash => "",
+  :merge => true,
+  :fix => proc{|l| 
+    l.gsub!(/Gene:|Drug:|Disease:/,'')
+    parts = l.split("\t")
+    rels = parts.pop
+    parts = [parts.values_at(0, 2) * ":"]
+    pmids = []
+    pathways = []
+    rsids = []
+    rels.split(',').each do |r|
+      case
+      when r =~ /PMID:(.*)/
+        pmids << $1
+      when r =~ /Pathway:(.*)/
+        pathways << $1
+      when r =~ /RSID:(.*)/
+        rsids << $1
+      end
+    end
+
+    parts << pmids * "|"
+    parts << pathways * "|"
+    parts << rsids * "|"
+
+    parts * "\t"
+  },
+  :keep_empty => true do
+
+  headers ['PhGKB Relationship', "PMID", "PhGKB Pathway ID", "Variant ID"]
+end
+
+
+process_tsv :gene_drug, 'relationships',
+  :select => proc{|l| l =~ /^Gene:/ && l =~ /Drug:/}, 
+  :header_hash => "",
+  :merge => true,
+  :fix => proc{|l| 
+    l.gsub!(/Gene:|Drug:|Disease:/,'')
+    parts = l.split("\t")
+    rels = parts.pop
+    parts = parts.values_at 0, 2
+
+    parts * "\t"
+  },
+  :keep_empty => true do
+
+  headers ['PhGKB Gene ID', 'PhGKB Drug ID']
+end
+
+process_tsv :gene_disease, 'relationships', 
+  :select => proc{|l| l =~ /^Gene:/ && l =~ /Disease:/}, 
+  :key_field => 1, 
+  :fields => 3, 
+  :merge => true,
+  :header_hash => "",
+  :fix => proc{|l| l.gsub(/Gene:|Drug:|Disease/,'')},
+  :keep_empty => true do
+
+  headers ['PhGKB Gene ID', 'PhGKB Disease ID']
+end
+
+process_tsv :variants, 'variants', 
+  :key_field => 1, 
+  :fields => [3,7,8,9,10,4,6,5], 
+  :header_hash => "",
+  :merge => true,
+  :fix => proc{|l| l.gsub(/Gene:|Drug:|Disease/,'')},
+  :keep_empty => true do
+
+  headers ['Variant ID', 'Associated Gene Name', 'Drug', 'Drug_Class', 'Disease', 'Curation', 'Feature', 'Annotation', 'Evidence']
+end
+
+file :pathways => 'source/pathways' do |t|
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + ['PhGKB Pathway ID','Pathway Name','Pathway Annotation Source'] * "\t"
+    Open.read(t.prerequisites.first).split(/\n/).each do |line|
+      case
+      when line =~ /(PA\d+): (.*) - \((.*)\)/
+        f.puts [$1,$2,$3] * "\t"
+      when line =~ /(PA\d+): (.*)/
+        f.puts [$1,$2,""] * "\t"
+      end
+    end
+  end
+end
+
+file :gene_pathway => 'source/pathways' do |t|
+  pathways = {}
+  last_pathway = nil
+
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /(P.*):(.*)/
+      last_pathway = $1
+      pathways[last_pathway] = {:name => $2}
+    else
+      type, code, name = line.split(/\t/)
+      next unless type =='Gene'
+      pathways[last_pathway][:genes] ||= []
+      pathways[last_pathway][:genes] << name
+    end
+  end
+end
+
+file :gene_pathway => 'source/pathways' do |t|
+  pathways = {}
+  last_pathway = nil
+
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /(P.*):(.*)/
+      last_pathway = $1
+      pathways[last_pathway] = {:name => $2}
+    else
+      type, code, name = line.split(/\t/)
+      next unless type =='Gene'
+      pathways[last_pathway][:genes] ||= []
+      pathways[last_pathway][:genes] << name
+    end
+  end
+
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + ['PhGKB Pathway ID',  'Pathway Name',  'Associated Gene Name'] * "\t"
+    pathways.each do |pathway, info|
+      next if info[:genes].nil?
+      f.puts "#{ pathway }\t#{info[:name]}\t#{info[:genes] * "|"}"
+    end
+  end
+end
+
+file :pathway_drugs => 'source/pathways' do |t|
+  pathways = {}
+  last_pathway = nil
+
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /(P.*):(.*)/
+      last_pathway = $1
+      pathways[last_pathway] = {:name => $2}
+    else
+      type, code, name = line.split(/\t/)
+    next unless type =='Drug'
+      pathways[last_pathway][:drugs] ||= []
+      pathways[last_pathway][:drugs] << code
+    end
+  end
+
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + ["PhGKB Pathway ID", "PhGKB Drug ID"]* "\t"
+    pathways.each do |pathway, info|
+      next if info[:drugs].nil?
+      f.puts "#{ pathway }\t#{info[:drugs] * "|"}"
+    end
+  end
+end
+
+
+file :disease_pathway => 'source/pathways' do |t|
+  pathways = {}
+  last_pathway = nil
+
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /(P.*):(.*)/
+      last_pathway = $1
+      pathways[last_pathway] = {:name => $2}
+    else
+      type, code, name = line.split(/\t/)
+    next unless type =='Disease'
+      pathways[last_pathway][:diseases] ||= []
+      pathways[last_pathway][:diseases] << name
+    end
+  end
+
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + %w(ID Name Diseases) * "\t"
+    pathways.each do |pathway, info|
+      next if info[:diseases].nil?
+      f.puts "#{ pathway }\t#{info[:name]}\t#{info[:diseases] * "|"}"
+    end
+  end
+end
+
+add_to_defaults [:gene_pathway, :drug_pathway, :disease_pathway]

data/share/install/Pina/Rakefile

@@ -0,0 +1,16 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks  "Homo sapiens-20110628.txt" => "http://cbg.garvan.unsw.edu.au/pina/download/Homo%20sapiens-20110628.txt"
+
+process_tsv :protein_protein, 'Homo sapiens-20110628.txt',
+  :key         => 0, 
+  :fix         => lambda{|l| l.gsub("uniprotkb:", '').gsub("(gene name)",'').gsub("pubmed:",'').gsub("|", ';;').gsub(/\([^)]+\)/,'')}, 
+  :fields      => [1,6,8], 
+  :header_hash => "#",
+  :merge       => true,
+  :keep_empty  => true do 
+
+  headers ['UniProt/SwissProt Accession', 'Interactor UniProt/SwissProt Accession', 'Method', 'PMID']
+end
+
+

data/share/install/STITCH/Rakefile

@@ -0,0 +1,30 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks "protein_chemicals" => "http://stitch.embl.de:8080/download/protein_chemical.links.v2.0.tsv.gz",
+  "chemicals" => "http://stitch.embl.de:8080/download/chemical.aliases.v2.0.tsv.gz"
+
+process_tsv :protein_chemical, 'protein_chemicals',
+  :key => 1,
+  :grep => "9606\.", 
+  :fix => lambda{|l| l.sub(/9606\./,'')},
+  :keep_empty => true do
+
+  headers ['Ensembl Protein ID', 'STITCH Chemical ID', 'Score']
+end
+
+$grep_re = []
+process_tsv :chemicals, 'chemicals',
+  :grep => $grep_re, 
+  :key  => 0 do
+
+  Rake::Task['protein_chemical'].invoke
+
+  Log.debug "Getting chemicals"
+  chemicals = TSV.open('protein_chemical', :key_field => 1, :fields => []).keys
+  Log.debug "Getting chemicals [done]"
+
+  $grep_re.replace chemicals
+
+  headers ['STITCH Chemical ID', 'Name', 'Source']
+end
+

data/share/install/STRING/Rakefile

@@ -0,0 +1,8 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks "protein_protein" => "http://string-db.org/newstring_download/protein.links.v9.05.txt.gz"
+
+process_tsv :protein_protein, 'protein_protein', :grep => '9606\.ENSP', :fix => lambda{|l| l.gsub(/9606\./,'')}, :merge => true, :sep => "\s" do 
+  headers ['Ensembl Protein ID', 'Interactor Ensembl Protein ID', 'Score']
+end
+

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-sources
 version: !ruby/object:Gem::Version
-  version: 2.1.7
+  version: 3.0.0
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-21 00:00:00.000000000 Z
+date: 2014-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -105,24 +105,34 @@ files:
 - lib/rbbt/sources/go.rb
 - lib/rbbt/sources/gscholar.rb
 - lib/rbbt/sources/jochem.rb
+- lib/rbbt/sources/kegg.rb
+- lib/rbbt/sources/matador.rb
 - lib/rbbt/sources/organism.rb
 - lib/rbbt/sources/pfam.rb
+- lib/rbbt/sources/pharmagkb.rb
+- lib/rbbt/sources/pina.rb
 - lib/rbbt/sources/polysearch.rb
 - lib/rbbt/sources/pubmed.rb
 - lib/rbbt/sources/reactome.rb
+- lib/rbbt/sources/stitch.rb
+- lib/rbbt/sources/string.rb
 - lib/rbbt/sources/tfacts.rb
 - lib/rbbt/sources/uniprot.rb
 - lib/rbbt/sources/wgEncodeBroadHmm.rb
 - share/Ensembl/release_dates
 - share/install/Genomes1000/Rakefile
 - share/install/JoChem/Rakefile
+- share/install/KEGG/Rakefile
 - share/install/NCI/Rakefile
 - share/install/Organism/Hsa/Rakefile
 - share/install/Organism/Mmu/Rakefile
 - share/install/Organism/Rno/Rakefile
 - share/install/Organism/Sce/Rakefile
 - share/install/Organism/organism_helpers.rb
+- share/install/PharmaGKB/Rakefile
+- share/install/Pina/Rakefile
 - share/install/STITCH/Rakefile
+- share/install/STRING/Rakefile
 - share/install/lib/helpers.rb
 - test/rbbt/sources/test_biomart.rb
 - test/rbbt/sources/test_entrez.rb