rbbt-phgx 0.1.0

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010-2011 Miguel Vázquez García
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/lib/phgx.rb

@@ -0,0 +1,16 @@
+require 'rbbt-util'
+require 'rbbt/util/pkg_config'
+require 'rbbt/util/pkg_data'
+require 'rbbt/util/pkg_software'
+require 'rbbt/util/open'
+require 'rbbt/util/tmpfile'
+require 'rbbt/util/filecache'
+
+module PhGx
+  extend PKGConfig
+  extend PKGData
+  extend PKGSoftware
+
+  self.load_cfg(%w(datadir), "datadir: #{File.join(ENV['HOME'], 'phgx', 'data')}\n")
+end
+

data/lib/rbbt/sources/cancer.rb

@@ -0,0 +1,12 @@
+require 'phgx'
+require 'rbbt/util/data_module'
+
+module Cancer
+  PhGx.add_datafiles :anais_annotations => ['Cancer', 'Cancer/anais-annotations.txt'],
+    :anais_interactions => ['Cancer', 'Cancer/anais-interactions.txt']
+
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then NCI.all end

data/lib/rbbt/sources/kegg.rb

@@ -0,0 +1,9 @@
+require 'rbbt/util/data_module'
+require 'phgx'
+
+module KEGG
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then  KEGG.all end

data/lib/rbbt/sources/matador.rb

@@ -0,0 +1,9 @@
+require 'rbbt/util/data_module'
+require 'phgx'
+
+module Matador
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then  Matador.all end

data/lib/rbbt/sources/nci.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+require 'rbbt/util/data_module'
+
+module NCI
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then NCI.all end

data/lib/rbbt/sources/pharmagkb.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+require 'rbbt/util/data_module'
+
+module PharmaGKB
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then PharmaGKB.all end

data/lib/rbbt/sources/stitch.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+require 'rbbt/util/data_module'
+
+module STITCH
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then STITCH.all end

data/lib/rbbt/sources/string.rb

@@ -0,0 +1,9 @@
+require 'phgx'
+require 'rbbt/util/data_module'
+
+module STRING
+  PKG = PhGx
+  extend DataModule
+end
+
+if __FILE__ == $0 then STRING.all end

data/share/install/KEGG/Rakefile

@@ -0,0 +1,109 @@
+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 :genes => '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 = {}
+  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
+  end
+  
+  Open.write(t.name, ['#KEGG Pathway ID', 'Name', 'Description'] * "\t" + "\n" + names.keys.collect{|pathway| [pathway, names[pathway], descs[pathway]] * "\t"} * "\n")
+end
+
+process_tsv :gene_pathway, 'hsa_gene_map.tab',
+  :sep2 => ' ' do 
+  headers ['KEGG Gene ID', 'KEGG Pathways']
+  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/Matador/Rakefile

@@ -0,0 +1,15 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks "matador" => "http://matador.embl.de/media/download/matador.tsv.gz"
+
+
+process_tsv :protein_drug, 'matador',
+  :native  => 3, 
+  :fix     => lambda{|l| l.sub(/9606./,'')}, 
+  :extra   => [1,0,7,8,9,10,11,12], 
+  :header_hash => "",
+  :keep_empty => true do 
+
+  headers ['Ensembl Protein ID', 'Chemical', 'Matador ID', 'Score', 'Annotation', 'Mesh_Score', 'Mesh_Annotation', 'Matador_Score', 'Matador_Annotation']
+end
+

data/share/install/NCI/Rakefile

@@ -0,0 +1,137 @@
+require File.join(File.dirname(__FILE__),'../lib/rake_helper')
+
+define_source_tasks "cancer_gene" => "https://gforge.nci.nih.gov/frs/download.php/6819/NCI_CancerIndex_allphases_disease.zip",
+  "gene_drug" => "https://gforge.nci.nih.gov/frs/download.php/6821/NCI_CancerIndex_allphases_compound.zip"
+
+
+
+file :gene_drug => 'source/gene_drug' do |t|
+  entry      = nil
+  uniprot    = nil
+  drugs      = []
+  concepts   = []
+  statements = []
+  pmids      = []
+ 
+  info = {}
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /<HUGOGeneSymbol>(.*)<\/HUGOGeneSymbol>/
+      if entry != nil
+        drug_info = {}
+        TSV.zip_fields([drugs, concepts, statements, pmids]).each do |drug_fields|
+          drug, concept, statement, pmid = drug_fields
+          drug_info[drug] ||= {:statements => [], :pmids => []}
+          drug_info[drug][:concept] = concept
+          drug_info[drug][:statements] << statement
+          drug_info[drug][:pmids] << pmid
+        end
+        drugs = drug_info.keys
+        concepts   = drug_info.values_at(*drugs).collect{|v| v[:concept]}
+        statements = drug_info.values_at(*drugs).collect{|v| v[:statements] * ";;"}
+        pmids      = drug_info.values_at(*drugs).collect{|v| v[:pmids] * ";;"}
+        info[entry] = [entry, drugs * "|", concepts * "|", statements * "|", pmids * "|"] * "\t"
+      end
+      entry      = $1
+      aliases    = []
+      uniprot    = nil
+      drugs      = []
+      concepts   = []
+      statements = []
+      pmids      = []
+    end
+
+    if line =~ /<UniProtID>(.*)<\/UniProtID>/
+      uniprot = $1
+    end
+
+    if line =~ /<DrugTerm>(.*)<\/DrugTerm>/
+      drugs << $1 || ""
+    end
+
+    if line =~ /<NCIDrugConceptCode>(.*)<\/NCIDrugConceptCode>/
+      concepts << $1 || ""
+    end
+
+    if line =~ /<Statement>(.*)<\/Statement>/
+      statements << $1 || ""
+    end
+
+    if line =~ /<PubMedID>(.*)<\/PubMedID>/
+      pmids << $1 || ""
+    end
+  end
+
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + ['Associated Gene Name', 'Drugs', 'Drug Concepts', 'Statements', 'PMIDS'] * "\t"
+    info.each do |entry, line|
+      f.puts line
+    end
+  end
+end
+
+file :gene_cancer => 'source/cancer_gene' do |t|
+  entry      = nil
+  uniprot    = nil
+  diseases   = []
+  concepts   = []
+  statements = []
+  pmids      = []
+ 
+  info = {}
+  Open.read(t.prerequisites.first).split(/\n/).each do |line|
+    if line =~ /<HUGOGeneSymbol>(.*)<\/HUGOGeneSymbol>/
+      if entry != nil
+        disease_info = {}
+        TSV.zip_fields([diseases, concepts, statements, pmids]).each do |disease_fields|
+          disease, concept, statement, pmid = disease_fields
+          disease_info[disease] ||= {:statements => [], :pmids => []}
+          disease_info[disease][:concept] = concept
+          disease_info[disease][:statements] << statement
+          disease_info[disease][:pmids] << pmid
+        end
+        diseases = disease_info.keys
+        concepts   = disease_info.values_at(*diseases).collect{|v| v[:concept]}
+        statements = disease_info.values_at(*diseases).collect{|v| v[:statements] * ";;"}
+        pmids      = disease_info.values_at(*diseases).collect{|v| v[:pmids] * ";;"}
+        info[entry] = [entry, diseases * "|", concepts * "|", statements * "|", pmids * "|"] * "\t"
+      end
+      entry      = $1
+      aliases    = []
+      uniprot    = nil
+      diseases   = []
+      concepts   = []
+      statements = []
+      pmids      = []
+    end
+
+    if line =~ /<UniProtID>(.*)<\/UniProtID>/
+      uniprot = $1
+    end
+
+    if line =~ /<MatchedDiseaseTerm>(.*)<\/MatchedDiseaseTerm>/
+      diseases << $1 || ""
+    end
+
+    if line =~ /<NCIDiseaseConceptCode>(.*)<\/NCIDiseaseConceptCode>/
+      concepts << $1 || ""
+    end
+
+    if line =~ /<Statement>(.*)<\/Statement>/
+      statements << $1 || ""
+    end
+
+    if line =~ /<PubMedID>(.*)<\/PubMedID>/
+      pmids << $1 || ""
+    end
+  end
+
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + ['Associated Gene Name', 'Diseases', 'Disease Concepts', 'Statements', 'PMIDS'] * "\t"
+    info.each do |entry, line|
+      f.puts line
+    end
+  end
+end
+
+add_to_defaults [:gene_cancer, :gene_drug]
+

data/share/install/PharmaGKB/Rakefile

@@ -0,0 +1,149 @@
+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|$)/,'\1')} do
+  headers ['PhGKB Disease ID']
+end
+
+process_tsv :genes, 'genes', 
+  :header_hash => "",
+  :fix => proc{|l| l.gsub(/","/,'|').gsub(/"/,'').gsub(/,(\t|$)/,'\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 => "",
+  :extra => ['Name', 'DrugBank Id'],
+  :fix => proc{|l| l.gsub(/","/,'|').gsub(/"/,'').gsub(/,(\t|$)/,'\1')} do
+  headers ['PhGKB Drug ID', 'Name', 'DrugBank ID', ]
+end
+
+
+process_tsv :gene_drug, 'relationships',
+  :select => proc{|l| l =~ /Gene:/ && l =~ /Drug:/}, 
+  :native => 'Entity1_id', 
+  :extra => ['Entity2_id','Relationship'], 
+  :header_hash => "",
+  :fix => proc{|l| l.gsub(/Gene:|Drug:|Disease/,'')},
+  :keep_empty => true do
+
+  headers ['PhGKB Gene ID', 'Drug']
+end
+
+process_tsv :gene_disease, 'relationships', 
+  :select => proc{|l| l =~ /Gene:/ && l =~ /Disease:/}, 
+  :native => 1, 
+  :extra => 3, 
+  :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', 
+  :native => 1, 
+  :extra => [3,7,8,9,10,4,5], 
+  :header_hash => "",
+  :fix => proc{|l| l.gsub(/Gene:|Drug:|Disease/,'')},
+  :keep_empty => true do
+
+  headers ['Variant ID', 'Associated Gene Name', 'Drug', 'Drug_Class', 'Disease', 'Curation', 'Feature', 'Evidence']
+end
+
+file :pathways => 'source/pathways' do |t|
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + ['PhGKB Pathway ID','Name','Source'] * "\t"
+    Open.read(t.prerequisites.first).split(/\n/).each do |line|
+      next unless line =~ /(PA\d+): (.*) - \((.*)\)/
+      f.puts [$1,$2,$3] * "\t"
+    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 "#" + ['Pathway ID',  '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 :drug_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 =='Drug'
+      pathways[last_pathway][:drugs] ||= []
+      pathways[last_pathway][:drugs] << name
+    end
+  end
+
+  File.open(t.name, 'w') do |f|
+    f.puts "#" + %w(ID Name Drugs) * "\t"
+    pathways.each do |pathway, info|
+      next if info[:drugs].nil?
+      f.puts "#{ pathway }\t#{info[:name]}\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/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',
+  :native => 1,
+  :grep => "9606\.", 
+  :fix => lambda{|l| l.sub(/9606\./,'')},
+  :keep_empty => true do
+
+  headers ['Ensembl Protein ID', 'Chemical', 'Score']
+end
+
+$grep_re = []
+process_tsv :chemicals, 'chemicals',
+  :grep => $grep_re, 
+  :native => 0 do
+
+  Rake::Task['protein_chemical'].invoke
+
+  Log.debug "Getting chemicals"
+  chemicals = TSV.new('protein_chemical', :native => 1, :other => []).keys
+  Log.debug "Getting chemicals [done]"
+
+  $grep_re.replace chemicals
+
+  headers ['Ensembl Protein ID', 'Chemical', 'Score']
+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:8080/newstring_download/protein.links.v8.3.txt.gz"
+
+process_tsv :protein_protein, 'protein_protein', :grep => '9606\.ENSP', :fix => lambda{|l| l.gsub(/9606\./,'')} do 
+  headers ['Ensembl Protein ID', 'Ensembl Protein ID', 'Score']
+end
+

data/share/install/lib/rake_helper.rb

@@ -0,0 +1,93 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '../../../lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+
+require 'rbbt/util/tsv'
+require 'rbbt/util/open'
+require 'rbbt/util/log'
+
+SOURCE_DIR = 'source'
+def define_source_tasks(sources)
+  sources.each do |name, url|
+    file File.join(SOURCE_DIR, name) do |t|
+      FileUtils.mkdir SOURCE_DIR unless File.exists? SOURCE_DIR
+      Log.log "Retrieving file '#{name}' into '#{t.name}': '#{url}'", Log::LOW
+      Open.write(t.name, Open.open(url, :cache => false, :wget_options => {"--no-check-certificate" => true, "--quiet" => false, :pipe => true}))
+    end
+  end
+end
+
+$__headers = nil
+def headers(values)
+  $__headers = values
+end
+
+$__data = nil
+def data(&block)
+  $__data = block
+end
+
+$__tsv_tasks = []
+def tsv_tasks
+  $__tsv_tasks 
+end
+
+$__files = []
+def add_to_defaults(list)
+  $__files = list
+end
+
+def process_tsv(file, source, options = {}, &block)
+
+  $__tsv_tasks << file
+
+  file file => File.join(SOURCE_DIR, source) do |t|
+    block.call
+
+    d = TSV.new(t.prerequisites.first, options)
+
+    if d.fields != nil
+      data_fields = d.fields.dup.unshift d.key_field
+      if $__headers.nil?
+        $__headers = data_fields
+      else
+       $__headers = data_fields.zip($__headers).collect{|l| l.compact.last}
+      end
+    end
+
+    if d.fields
+      headers = d.fields.dup.unshift d.key_field
+    else
+      headers = nil
+    end
+
+    File.open(t.name.to_s, 'w') do |f|
+      f.puts "#" + $__headers * "\t" if $__headers != nil
+      d.each do |key, values|
+        if $__data.nil?
+          line = values.unshift key
+        else
+          line = $__data.call key, values
+        end
+
+        if Array === line
+          key   = line.shift
+          fields = line.collect{|elem| Array === elem ? elem * "|" : elem }
+          fields.unshift key
+          f.puts fields * "\t" 
+        else
+          f.puts line
+        end
+      end
+    end
+  end
+end
+
+task :default do |t|
+  ($__tsv_tasks + $__files).each do |file| Rake::Task[file].invoke end
+end
+
+task :all => :default 
+
+task :clean do
+  ($__tsv_tasks + $__files).each do |file| FileUtils.rm file.to_s if File.exists?(file.to_s) end
+end

data/test/rbbt/sources/test_cancer.rb

@@ -0,0 +1,11 @@
+require File.expand_path(File.dirname(__FILE__) + '/../../test_helper')
+require 'test/unit'
+require 'rbbt/util/tmpfile'
+require 'rbbt/sources/cancer'
+
+class TestCancer < Test::Unit::TestCase
+  def test_anais_annotations
+    assert TSV.new(Cancer.anais_annotations)['ENSG00000087460']['Tumor Type'].include? 'Adrenocortical'
+  end
+end
+

data/test/rbbt/sources/test_matador.rb

@@ -0,0 +1,11 @@
+require File.expand_path(File.dirname(__FILE__) + '/../../test_helper')
+require 'test/unit'
+require 'rbbt/util/tmpfile'
+require 'rbbt/sources/matador'
+
+class TestMatador < Test::Unit::TestCase
+  def test_matador
+    assert_equal 'procainamide', TSV.new(Matador.protein_drug)['ENSP00000343023']['Chemical'].first
+  end
+end
+

data/test/rbbt/sources/test_pharmagkb.rb

@@ -0,0 +1,11 @@
+require File.expand_path(File.dirname(__FILE__) + '/../../test_helper')
+require 'test/unit'
+require 'rbbt/util/tmpfile'
+require 'rbbt/sources/pharmagkb'
+
+class TestPhGKB < Test::Unit::TestCase
+  def test_phgkb
+    assert TSV.new(PharmaGKB.variants)['rs25487']['Associated Gene Name'].include? 'XRCC1'
+  end
+end
+

data/test/rbbt/sources/test_stitch.rb

@@ -0,0 +1,11 @@
+require File.expand_path(File.dirname(__FILE__) + '/../../test_helper')
+require 'test/unit'
+require 'rbbt/util/tmpfile'
+require 'rbbt/sources/stitch'
+
+class TestSTITCH < Test::Unit::TestCase
+  def test_stitch
+    assert TSV.new(STITCH.chemicals).keys.any?
+  end
+end
+

data/test/test_helper.rb

@@ -0,0 +1,9 @@
+require 'test/unit'
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+
+class Test::Unit::TestCase
+  def test_datafile(file)
+    File.join(File.dirname(__FILE__), 'data', file)
+  end
+end

metadata

@@ -0,0 +1,91 @@
+--- !ruby/object:Gem::Specification 
+name: rbbt-phgx
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Miguel Vazquez
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-12-10 00:00:00 +01:00
+default_executable: 
+dependencies: []
+
+description: Pharmaco-genomics related data sources
+email: miguel.vazquez@fdi.ucm.es
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+files: 
+- LICENSE
+- lib/phgx.rb
+- lib/rbbt/sources/cancer.rb
+- lib/rbbt/sources/kegg.rb
+- lib/rbbt/sources/matador.rb
+- lib/rbbt/sources/nci.rb
+- lib/rbbt/sources/pharmagkb.rb
+- lib/rbbt/sources/stitch.rb
+- lib/rbbt/sources/string.rb
+- share/install/KEGG/Rakefile
+- share/install/Matador/Rakefile
+- share/install/NCI/Rakefile
+- share/install/PharmaGKB/Rakefile
+- share/install/STITCH/Rakefile
+- share/install/STRING/Rakefile
+- share/install/lib/rake_helper.rb
+- test/rbbt/sources/test_cancer.rb
+- test/rbbt/sources/test_matador.rb
+- test/rbbt/sources/test_pharmagkb.rb
+- test/rbbt/sources/test_stitch.rb
+- test/test_helper.rb
+has_rdoc: true
+homepage: http://github.com/mikisvaz/rbbt-phgx
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Pharmaco-genomics for the Ruby Bioinformatics Toolkit (rbbt)
+test_files: 
+- test/rbbt/sources/test_cancer.rb
+- test/rbbt/sources/test_matador.rb
+- test/rbbt/sources/test_pharmagkb.rb
+- test/rbbt/sources/test_stitch.rb
+- test/test_helper.rb