rbbt-sources 0.1.0 → 0.2.0

data/lib/rbbt/sources/biomart.rb

@@ -1,5 +1,5 @@
-require 'rbbt'
-require 'rbbt/util/open'
+require 'rbbt-util'
+require 'rbbt/util/log'
 
 # This module interacts with BioMart. It performs queries to BioMart and
 # synthesises a hash with the results. Note that this module connects to the
@@ -9,6 +9,7 @@ require 'rbbt/util/open'
 module BioMart
   
   class BioMart::QueryError < StandardError; end
+
   private
 
   @@biomart_query_xml = <<-EOT
@@ -25,8 +26,7 @@ module BioMart
 
    
 
-
-  def self.get(database, main, attrs = nil, filters = nil, data = nil, options = {})
+  def self.get(database, main, attrs = nil, filters = nil, data = nil, open_options = {})
     attrs   ||= []
     filters ||= ["with_#{main}"]
     data    ||= {}
@@ -37,7 +37,7 @@ module BioMart
     query.sub!(/<!--MAIN-->/,"<Attribute name = \"#{main}\" />")
     query.sub!(/<!--ATTRIBUTES-->/, attrs.collect{|name| "<Attribute name = \"#{ name }\"/>"}.join("\n") )
 
-    response = Open.read('http://www.biomart.org/biomart/martservice?query=' + query.gsub(/\n/,' '), options)
+    response = Open.read('http://www.biomart.org/biomart/martservice?query=' + query.gsub(/\n/,' '), open_options)
     if response =~ /Query ERROR:/
       raise BioMart::QueryError, response
     end
@@ -51,8 +51,12 @@ module BioMart
       attrs.each{|name|
         value = parts.shift
         data[main][name] ||= []
-        next if value.nil?
-        data[main][name] << value
+        next if value.nil? or value.empty?
+        if data[main][name]
+          data[main][name] = [value]
+        else
+          data[main][name] << value unless data[main][name].include? value
+        end
       }
     }
 
@@ -75,30 +79,48 @@ module BioMart
   # the BioMart query to remove results with the main attribute empty, this may
   # cause an error if the BioMart WS does not allow filtering with that
   # attribute.
-  def self.query(database, main, attrs = nil, filters = nil, data = nil, options = {})
+  def self.query(database, main, attrs = nil, filters = nil, data = nil, open_options = {})
+    open_options = Misc.add_defaults open_options, :nocache => false
     attrs   ||= []
     data    ||= {}
     
+    Log.low "BioMart query: '#{main}' [#{(attrs || []) * ', '}] [#{(filters || []) * ', '}] #{open_options.inspect}"
+
+    max_items = 2
     chunks = []
     chunk = []
     attrs.each{|a|
       chunk << a
-      if chunk.length == 2
+      if chunk.length == max_items
         chunks << chunk
         chunk = []
       end
     }
 
     chunks << chunk if chunk.any?
+    
 
-    chunks.each{|chunk|
-      data = get(database, main, chunk, filters, data, options)
+    Log.low "Chunks: #{chunks.length}"
+    chunks.each_with_index{|chunk,i|
+      Log.low "Chunk #{ i }: [#{chunk * ", "}]"
+      data = get(database, main, chunk, filters, data, open_options)
     }
 
     data
   end
 
-    
+  def self.tsv(database, main, attrs = nil, filters = nil, data = nil, open_options = {})
+    codes = attrs.collect{|attr| attr[1]}
+    data = query(database, main.last, codes, filters, data, open_options)
+    tsv = TSV.new({})
+
+    data.each do |key, info|
+      tsv[key] = info.values_at(*codes)
+    end
 
+    tsv.key_field = main.first
+    tsv.fields    = attrs.collect{|attr| attr.first} 
+    tsv
+  end
 end
 

data/lib/rbbt/sources/entrez.rb

@@ -14,7 +14,10 @@ module Entrez
     taxs = [taxs] unless Array === taxs
     options.merge! :grep => taxs
 
-    TSV.new(Rbbt.find_datafile('gene_info'), options)
+    tsv = TSV.new(Rbbt.find_datafile('gene_info'), options)
+    tsv.key_field = "Entrez Gene ID"
+    tsv.fields    = ["Native ID"]
+    tsv
   end
 
   def self.entrez2pubmed(taxs)

data/lib/rbbt/sources/go.rb

@@ -4,66 +4,67 @@ require 'rbbt-util'
 # now all it does is provide a translation form id to the actual names.
 module GO
 
-  @@info = nil
+  Rbbt.add_datafiles :gene_ontology => ['databases/GO', 'ftp://ftp.geneontology.org/pub/go/ontology/gene_ontology.obo'],
+    :goslim_generic => ['databases/GO', 'http://www.geneontology.org/GO_slims/goslim_generic.obo']
+
+
   MULTIPLE_VALUE_FIELDS = %w(is_a)
+  TSV_GENE_ONTOLOGY = File.join(TSV.cachedir, 'gene_ontology')
 
   # This method needs to be called before any translations can be made, it is
   # called automatically the first time the id2name method is called. It loads
   # the gene_ontology.obo file and extracts all the fields, although right now,
   # only the name field is used.
   def self.init
-    @@info = {}
-    File.open(File.join(Rbbt.datadir, 'dbs/go/gene_ontology.obo')).read.
-      split(/\[Term\]/).
-      each{|term| 
+    info = TCHash.new(TSV_GENE_ONTOLOGY, true)
+    File.open(Rbbt.find_datafile('gene_ontology')).read.split(/\[Term\]/).each{|term| 
         term_info = {}
-        term.split(/\n/).
-          select{|l| l =~ /:/}.
-          each{|l| 
-            key, value = l.chomp.match(/(.*?):(.*)/).values_at(1,2)
-            if MULTIPLE_VALUE_FIELDS.include? key.strip
-              term_info[key.strip] ||= []
-              term_info[key.strip] << value.strip
-            else
-              term_info[key.strip] = value.strip
-            end
-          }
-        @@info[term_info["id"]] = term_info
-    }
+
+        term.split(/\n/). select{|l| l =~ /:/}.each{|l| 
+          key, value = l.chomp.match(/(.*?):(.*)/).values_at(1,2)
+          if MULTIPLE_VALUE_FIELDS.include? key.strip
+            term_info[key.strip] ||= []
+            term_info[key.strip] << value.strip
+          else
+            term_info[key.strip] = value.strip
+          end
+        }
+
+        next if term_info["id"].nil?
+        info[term_info["id"]] = term_info
+      }
+    info.close
   end
 
   def self.info
-    self.init unless @@info
-    @@info
+    self.init unless File.exists? TSV_GENE_ONTOLOGY
+    TCHash.get(TSV_GENE_ONTOLOGY)
   end
 
   def self.goterms
-    self.init unless @@info
-    @@info.keys
+    info.keys
   end
 
   def self.id2name(id)
-    self.init unless @@info
     if id.kind_of? Array
-      @@info.values_at(*id).collect{|i| i['name'] if i}
+      info.values_at(*id).collect{|i| i['name'] if i}
     else
-      return nil if @@info[id].nil?
-      @@info[id]['name']
+      return nil if info[id].nil?
+      info[id]['name']
     end
   end
 
   def self.id2ancestors(id)
-    self.init unless @@info
     if id.kind_of? Array
-      @@info.values_at(*id).
+      info.values_at(*id).
         select{|i| ! i['is_a'].nil?}.
         collect{|i| i['is_a'].collect{|id| 
-          id.match(/(GO:\d+)/)[1] if id.match(/(GO:\d+)/)
-        }.compact
+        id.match(/(GO:\d+)/)[1] if id.match(/(GO:\d+)/)
+      }.compact
       }
     else
-      return [] if @@info[id].nil? || @@info[id]['is_a'].nil?
-      @@info[id]['is_a'].
+      return [] if id.nil? or info[id].nil? or info[id]['is_a'].nil?
+      info[id]['is_a'].
         collect{|id| 
         id.match(/(GO:\d+)/)[1] if id.match(/(GO:\d+)/)
       }.compact
@@ -71,14 +72,12 @@ module GO
   end
 
   def self.id2namespace(id)
-    self.init unless @@info
+    self.init unless info
     if id.kind_of? Array
-      @@info.values_at(*id).collect{|i| i['namespace'] if i}
+      info.values_at(*id).collect{|i| i['namespace'] if i}
     else
-      return nil if @@info[id].nil?
-      @@info[id]['namespace']
+      return nil if info[id].nil?
+      info[id]['namespace']
     end
   end
-
-
 end

data/lib/rbbt/sources/organism.rb

@@ -1,9 +1,15 @@
 require 'rbbt-util'
+require 'rbbt/util/data_module'
+
 module Organism
   class OrganismNotProcessedError < StandardError; end
 
   def self.datadir(org)
     File.join(Rbbt.datadir, 'organisms', org)
   end 
-
+  
+  extend DataModule
+  
+  Hsa = with_key('Hsa')
+  Sce = with_key('Sce')
 end

data/share/install/Organism/Hsa/Rakefile

@@ -0,0 +1,83 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__),'..', '..', '..', '..', 'lib'))
+require 'rbbt/sources/biomart'
+require 'rbbt/sources/entrez'
+require File.join(File.dirname(__FILE__), '../../lib/helpers')
+
+$taxs = [559292,4932]
+$native = "SGD ID"
+$url = "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab"
+$biomart_db = 'hsapiens_gene_ensembl'
+$biomart_main = ['Entrez Gene ID', 'entrezgene']
+$biomart_lexicon = [ 
+  [ 'Associated Gene Name' , "external_gene_id"], 
+  [ 'HGNC symbol', "hgnc_symbol"  ],
+  [ 'HGNC automatic gene name', "hgnc_automatic_gene_name"  ],
+  [ 'HGNC curated gene name ', "hgnc_curated_gene_name"  ],
+]
+
+$biomart_identifiers = [ 
+  [ 'Ensembl Gene ID', "ensembl_gene_id"  ],
+  [ 'Ensembl Protein ID', "ensembl_peptide_id"  ],
+  [ 'Associated Gene Name', "external_gene_id"  ],
+  [ 'CCDS ID', "ccds"  ],
+  [ 'Protein ID', "protein_id"  ],
+  [ 'RefSeq Protein ID', "refseq_peptide"  ],
+  [ 'Unigene ID', "unigene"  ],
+  [ 'UniProt/SwissProt ID', "uniprot_swissprot"  ],
+  [ 'UniProt/SwissProt Accession', "uniprot_swissprot_accession"  ],
+  [ 'HGNC ID', "hgnc_id", 'HGNC'],
+  [ 'EMBL (Genbank) ID' , "embl"] , 
+
+  # Affymetrix
+  [ 'AFFY HC G110', 'affy_hc_g110' ],
+  [ 'AFFY HG FOCUS', 'affy_hg_focus' ],
+  [ 'AFFY HG U133-PLUS-2', 'affy_hg_u133_plus_2' ],
+  [ 'AFFY HG U133A_2', 'affy_hg_u133a_2' ],
+  [ 'AFFY HG U133A', 'affy_hg_u133a' ],
+  [ 'AFFY HG U133B', 'affy_hg_u133b' ],
+  [ 'AFFY HG U95AV2', 'affy_hg_u95av2' ],
+  [ 'AFFY HG U95B', 'affy_hg_u95b' ],
+  [ 'AFFY HG U95C', 'affy_hg_u95c' ],
+  [ 'AFFY HG U95D', 'affy_hg_u95d' ],
+  [ 'AFFY HG U95E', 'affy_hg_u95e' ],
+  [ 'AFFY HG U95A', 'affy_hg_u95a' ],
+  [ 'AFFY HUGENEFL', 'affy_hugenefl' ],
+  [ 'AFFY HuEx', 'affy_huex_1_0_st_v2' ],
+  [ 'AFFY HuGene', 'affy_hugene_1_0_st_v1' ],
+  [ 'AFFY U133 X3P', 'affy_u133_x3p' ],
+  [ 'Agilent WholeGenome',"agilent_wholegenome" ],
+  [ 'Agilent CGH 44b', 'agilent_cgh_44b' ],
+  [ 'Codelink ID', 'codelink' ],
+  [ 'Illumina HumanWG 6 v2', 'illumina_humanwg_6_v2' ],
+  [ 'Illumina HumanWG 6 v3', 'illumina_humanwg_6_v3' ],
+]
+
+
+
+file 'name' do |t|
+  File.open(t.name, 'w') do |f| f.puts "Homo sapiens" end
+end
+
+file 'lexicon' do |t|
+  lexicon = tsv_file('http://www.genenames.org/cgi-bin/hgnc_downloads.cgi?title=HGNC+output+data&hgnc_dbtag=on&col=gd_hgnc_id&col=gd_app_sym&col=gd_app_name&col=gd_prev_sym&col=gd_prev_name&col=gd_aliases&col=gd_name_aliases&col=gd_pub_acc_ids&status=Approved&status_opt=2&level=pri&=on&where=&order_by=gd_app_sym_sort&limit=&format=text&submit=submit&.cgifields=&.cgifields=level&.cgifields=chr&.cgifields=status&.cgifields=hgnc_dbtag',
+                     "HGNC ID", nil, :flatten => true, :header_hash => '')
+  merge_biomart lexicon, $biomart_db, $biomart_main, $biomart_lexicon, "HGNC ID"
+
+  File.open(t.name, 'w') do |f| f.puts lexicon end
+end
+
+file 'identifiers' do |t|
+  identifiers = BioMart.tsv($biomart_db, $biomart_main, $biomart_identifiers)
+  $biomart_identifiers.each do |name, key, prefix|
+    if prefix
+      identifiers.process name do |field, key, values| field.each{|v| v.replace "#{prefix}:#{v}"} end
+    end
+  end
+
+  File.open(t.name, 'w') do |f| f.puts identifiers end
+end
+
+
+task :default => ['name', 'lexicon', 'identifiers']
+
+

data/share/install/Organism/Sce/Rakefile

@@ -0,0 +1,118 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__),'..', '..', '..', '..', 'lib'))
+require 'rbbt/sources/biomart'
+require 'rbbt/sources/entrez'
+require File.join(File.dirname(__FILE__), '../../lib/helpers')
+
+$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']
+
+
+file '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)
+
+  merge_entrez(lexicon, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tS0/)})
+
+  merge_biomart(lexicon, $biomart_db, $biomart_main, [['Interpro Description' , "interpro_description"]])
+
+  lexicon = lexicon.slice(lexicon.fields - ["Entrez Gene ID"])
+
+  File.open(t.name, 'w') do |f| f.puts lexicon end
+end
+
+file 'identifiers' do |t|
+  identifiers = tsv_file($url, [$native, 0], [3, 4, 5], :keep_empty => true)
+
+  merge_entrez(identifiers, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tS0/)})
+
+  merge_biomart(identifiers, $biomart_db, $biomart_main,
+                [['Associated Gene Name' , "external_gene_id"], 
+                  ['Ensembl Gene ID', "ensembl_gene_id"  ],
+                  ['Ensembl Protein ID', "ensembl_peptide_id"  ],
+                  ['RefSeq Protein ID' , "refseq_peptide"] , 
+                  ['UniProt/SwissProt ID' , "uniprot_swissprot"] , 
+                  ['UniProt/SwissProt Accession' , "uniprot_swissprot_accession"] , 
+                  ['Protein ID' , "protein_id"] , 
+                  ['EMBL (Genbank) ID' , "embl"] , 
+                  # Affymetrix
+                  ['Affy yeast 2',"affy_yeast_2"],
+                  ['Affy yg s98', "affy_yg_s98"]])
+
+  File.open(t.name, 'w') do |f| f.puts identifiers end
+end
+
+
+task :default => ['name', 'lexicon', 'identifiers']
+
+#require __FILE__.sub(/[^\/]*$/,'') + '../rake-include'
+#
+#$name = "Saccharomyces cerevisiae"
+#
+#
+#$native_id = "SGD DB Id"
+#
+#$entrez2native = {
+#  :tax => 559292,
+#  :fix => proc{|code| code.sub(/SGD:S0/,'S0') },
+#  :check => proc{|code| code.match(/^S0/)},
+#}
+#
+#$lexicon = {
+#  :file => {
+#    :url => "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab",
+#    :native => 0,
+#    :extra => [4,3,5]
+#  },
+#  :biomart => {
+#    :database => 'scerevisiae_gene_ensembl',
+#    :main => ['Entrez Gene ID', 'entrezgene'],
+#    :extra => [ 
+#      ['Interpro Description' , "interpro_description"], 
+#    ],
+#    :filter => [],
+#  }
+#
+#}
+#
+#$identifiers = {
+#  :file => {
+#    :url => "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab",
+#    :native => 0,
+#    :extra => [],
+#  },
+#  :biomart => {
+#    :database => 'scerevisiae_gene_ensembl',
+#    :main => ['Entrez Gene ID', 'entrezgene'],
+#    :extra => [ 
+#      ['Associated Gene Name' , "external_gene_id"], 
+#      ['Ensembl Gene ID', "ensembl_gene_id"  ],
+#      ['Ensembl Protein ID', "ensembl_peptide_id"  ],
+#      ['RefSeq Protein ID' , "refseq_peptide"] , 
+#      ['UniProt/SwissProt ID' , "uniprot_swissprot"] , 
+#      ['UniProt/SwissProt Accession' , "uniprot_swissprot_accession"] , 
+#      ['Protein ID' , "protein_id"] , 
+#      ['EMBL (Genbank) ID' , "embl"] , 
+#      # Affymetrix
+#      ['Affy yeast 2',"affy_yeast_2"],
+#      ['Affy yg s98', "affy_yg_s98"],
+#    ],
+#    :filter => [],
+#  }
+#}
+#
+#$go = {
+#  :url => "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/literature_curation/gene_association.sgd.gz",
+#  :code => 1,
+#  :go   => 4,
+#  :pmid => 5,
+#}
+#
+#$query = '"saccharomyces cerevisiae"[All Fields] AND ((("proteins"[TIAB] NOT Medline[SB]) OR "proteins"[MeSH Terms] OR protein[Text Word]) OR (("genes"[TIAB] NOT Medline[SB]) OR "genes"[MeSH Terms] OR gene[Text Word]))  AND hasabstract[text] AND English[lang]'
+#
+#

data/share/install/lib/helpers.rb

@@ -0,0 +1,47 @@
+require 'rbbt-util'
+require 'rbbt/sources/biomart'
+require 'rbbt/sources/entrez'
+
+def tsv_file(url, native, extra, options = {})
+  options = Misc.add_defaults options, :persistence => false, :keep_empty => true
+
+  case
+  when Array === native
+    options = Misc.add_defaults options, :native => native.last 
+    key_field = native.first
+  when (String === native or Integer === native)
+    options = Misc.add_defaults options, :native => native
+    key_field = nil
+  else
+    key_field = nil
+  end
+
+  case
+  when (Array === extra and Array === extra.first)
+    options = Misc.add_defaults options, :extra => extra.collect{|e| e.last}
+    fields = extra.collect{|e| e.first}
+  when (Array === extra and not Array === extra.first)
+    options = Misc.add_defaults options, :extra => extra
+    fields = (1..extra.length).to_a.collect{|i| "Field#{i}"}
+  else
+    fields = nil
+  end
+
+  tsv = TSV.new(Open.open(url), options)
+  tsv.key_field ||= key_field
+  tsv.fields ||= fields
+  tsv
+end
+
+def merge_entrez(data, taxs, native, fix = nil, select = nil)
+  entrez =  Entrez.entrez2native(taxs, :fix => fix, :select => select)
+  entrez.fields = [native]
+  entrez
+
+  data.smart_merge entrez, native
+end
+
+def merge_biomart(lexicon, db, native, other, match = nil)
+  match ||= native.first
+  lexicon.smart_merge BioMart.tsv(db, native, other), match
+end

data/test/rbbt/sources/test_biomart.rb

@@ -9,22 +9,27 @@ class TestBioMart < Test::Unit::TestCase
       BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],['with_unknownattr'])
     end
 
-    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],[], nil, :nocache => true, :wget_options => { :quiet => false})
-    assert(data['856452']['protein_id'].include? 'AAB68382')
-
-    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['external_gene_id'],[], data, :nocache => true, :wget_options => { :quiet => false} )
-    assert(data['856452']['protein_id'].include? 'AAB68382')
-    assert(data['856452']['external_gene_id'].include? 'CUP1-2')
+    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],[], nil, :nocache => false, :wget_options => { :quiet => false})
+    assert(data['852236']['protein_id'].include? 'CAA84864')
 
+    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['external_gene_id'],[], data, :nocache => false, :wget_options => { :quiet => false} )
+    assert(data['852236']['protein_id'].include? 'CAA84864')
+    assert(data['852236']['external_gene_id'].include? 'YBL044W')
   end
 
   def test_query
-    data = BioMart.query('scerevisiae_gene_ensembl','entrezgene', ['protein_id','refseq_peptide','external_gene_id','ensembl_gene_id'], [], nil, :nocache => true, :wget_options => { :quiet => false})
+    data = BioMart.query('scerevisiae_gene_ensembl','entrezgene', ['protein_id','refseq_peptide','external_gene_id','ensembl_gene_id'], [], nil, :nocache => false, :wget_options => { :quiet => false})
+
+    assert(data['852236']['external_gene_id'].include? 'YBL044W')
+  end
 
-    assert(data['856452']['protein_id'].include? 'AAB68382')
-    assert(data['856452']['external_gene_id'].include? 'CUP1-2')
- end
+  def test_tsv
+    data = BioMart.tsv('scerevisiae_gene_ensembl',['Entrez Gene', 'entrezgene'], [['Protein ID', 'protein_id'],['RefSeq Peptide','refseq_peptide']], [], nil, :nocache => false, :wget_options => { :quiet => false})
 
+    assert(data['852236']['Protein ID'].include? 'CAA84864')
+    assert_equal 'Entrez Gene', data.key_field
+    assert_equal ['Protein ID', 'RefSeq Peptide'], data.fields
+  end
 end
 
 

data/test/rbbt/sources/test_entrez.rb

@@ -3,12 +3,12 @@ require 'rbbt/sources/entrez'
 require 'test/unit'
 
 class TestEntrez < Test::Unit::TestCase
-  $yeast_tax = 559292
+  $yeast_tax = [559292,4932]
 
   def test_entrez2native
     tax    = $yeast_tax
     fix    = proc{|line| line.sub(/SGD:S0/,'S0') }
-    select = proc{|line| line.match(/\tSGD:S0/)}
+    select = proc{|line| line.match(/\tS0/)}
     lexicon = Entrez.entrez2native(tax, :fix => fix, :select => select)
 
     assert(lexicon['855611'].include? 'S000005056') 

data/test/rbbt/sources/test_go.rb

@@ -4,7 +4,6 @@ require 'rbbt/sources/go'
 require 'test/unit'
 
 class TestGo < Test::Unit::TestCase
-
   def test_go
     assert_match('vacuole inheritance',GO::id2name('GO:0000011'))
     assert_equal(['vacuole inheritance','alpha-glucoside transport'], GO::id2name(['GO:0000011','GO:0000017']))
@@ -17,8 +16,6 @@ class TestGo < Test::Unit::TestCase
   def test_namespace
     assert_equal 'biological_process', GO.id2namespace('GO:0000001')
   end
-
-
 end
 
 

data/test/rbbt/sources/test_organism.rb

@@ -0,0 +1,17 @@
+require File.expand_path(File.dirname(__FILE__) + '/../../test_helper')
+require 'rbbt/sources/organism'
+require 'test/unit'
+
+class TestEntrez < Test::Unit::TestCase
+  def test_identifiers
+    assert TSV.new(Organism.identifiers('Sce'))['S000006120']["Ensembl Gene ID"].include?('YPL199C')
+    assert TSV.new(Organism::Sce.identifiers)['S000006120']["Ensembl Gene ID"].include?('YPL199C')
+    #assert Organism.identifiers('Hsa')['1020']["Associated Gene Name"].include?('CDK5')
+  end
+
+  def test_lexicon
+    assert TSV.new(Organism.lexicon('Sce'))['S000006120'].flatten.include?('YPL199C')
+  end
+end
+
+

data/test/rbbt/sources/test_pubmed.rb

@@ -21,7 +21,7 @@ class TestPubMed < Test::Unit::TestCase
     assert(PubMed.get_article(pmids)[pmid].title == "Discovering semantic features in the literature: a foundation for building functional associations.")
   end
  
-  def test_full_text
+  def _test_full_text
     pmid = '16438716'
     assert(PubMed.get_article(pmid).full_text =~ /Discovering/)
   end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rbbt-sources
 version: !ruby/object:Gem::Version 
-  hash: 27
+  hash: 23
   prerelease: false
   segments: 
   - 0
-  - 1
+  - 2
   - 0
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Miguel Vazquez
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-01 00:00:00 +01:00
+date: 2010-12-10 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -33,7 +33,7 @@ dependencies:
   type: :runtime
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
-  name: mechanize
+  name: rbbt-text
   prerelease: false
   requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
@@ -47,7 +47,7 @@ dependencies:
   type: :runtime
   version_requirements: *id002
 - !ruby/object:Gem::Dependency 
-  name: libxml-ruby
+  name: mechanize
   prerelease: false
   requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
@@ -60,6 +60,20 @@ dependencies:
         version: "0"
   type: :runtime
   version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: libxml-ruby
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id004
 description: Data sources like PubMed, Entrez Gene, or Gene Ontology
 email: miguel.vazquez@fdi.ucm.es
 executables: []
@@ -76,9 +90,13 @@ files:
 - lib/rbbt/sources/gscholar.rb
 - lib/rbbt/sources/organism.rb
 - lib/rbbt/sources/pubmed.rb
+- share/install/Organism/Hsa/Rakefile
+- share/install/Organism/Sce/Rakefile
+- share/install/lib/helpers.rb
 - test/rbbt/sources/test_biomart.rb
 - test/rbbt/sources/test_entrez.rb
 - test/rbbt/sources/test_go.rb
+- test/rbbt/sources/test_organism.rb
 - test/rbbt/sources/test_pubmed.rb
 - test/test_helper.rb
 has_rdoc: true
@@ -119,5 +137,6 @@ test_files:
 - test/rbbt/sources/test_biomart.rb
 - test/rbbt/sources/test_entrez.rb
 - test/rbbt/sources/test_go.rb
+- test/rbbt/sources/test_organism.rb
 - test/rbbt/sources/test_pubmed.rb
 - test/test_helper.rb