rbbt-sources 0.2.1 → 0.2.2

data/lib/rbbt/sources/COSTART.rb

@@ -0,0 +1,16 @@
+require 'rbbt-util'
+
+module COSTART
+
+  Rbbt.claim "COSTART", 
+    Proc.new do
+      terms = ["#COSTART Terms"]
+      Open.open('http://hedwig.mgh.harvard.edu/biostatistics/files/costart.html').lines.each do |line|
+        puts line
+        next unless line =~ /^'(.*)',/
+        terms << $1
+      end
+      
+      terms * "\n"
+    end, 'COSTART'
+end

data/lib/rbbt/sources/CTCAE.rb

@@ -0,0 +1,6 @@
+require 'rbbt-util'
+require 'rbbt/util/excel2tsv'
+
+module CTCAE
+  Rbb.claim "CTCAE", TSV.excel2tsv('http://evs.nci.nih.gov/ftp1/CTCAE/CTCAE_4.03_2010-06-14.xls'), 'CTCAE'
+end

data/lib/rbbt/sources/Reactome.rb

@@ -0,0 +1,16 @@
+require 'rbbt-util'
+
+module Reactome
+
+  Rbbt.claim "Reactome", 
+    Proc.new do
+      headers = ["Uniprot ID#1", "Ensembl Gene ID#2","Entrez Gene ID#1", "Uniprot ID#2", "Ensembl Gene ID#2", "Entrez Gene ID#2" , "Type", "Reaction", "PMID"]
+
+      tsv = TSV.new(Open.open("http://www.reactome.org/download/current/homo_sapiens.interactions.txt.gz"), :fix => Proc.new {|l| l.gsub(/[\w ]+:/, "")})
+      tsv.key_field = headers.shift
+      tsv.fields    = headers
+
+      tsv.to_s
+    end, 'Reactome'
+  ]
+end

data/lib/rbbt/sources/biomart.rb

@@ -10,6 +10,8 @@ module BioMart
   
   class BioMart::QueryError < StandardError; end
 
+  BIOMART_URL = 'http://biomart.org/biomart/martservice?query='
+
   private
 
   @@biomart_query_xml = <<-EOT
@@ -23,8 +25,14 @@ module BioMart
 </Dataset>
 </Query>
   EOT
-
    
+  def self.set_archive(date)
+    @archive_url = BIOMART_URL.sub(/www\.biomar\./, date + '.archive.ensemble')
+  end
+
+  def self.unset_archive
+    @archive_url = nil
+  end
 
   def self.get(database, main, attrs = nil, filters = nil, data = nil, open_options = {})
     attrs   ||= []
@@ -37,8 +45,13 @@ 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/,' '), open_options)
-    if response =~ /Query ERROR:/
+    if @archive_url
+      response = Open.read(@archive_url + query.gsub(/\n/,' '), open_options)
+    else
+      response = Open.read(BIOMART_URL + query.gsub(/\n/,' '), open_options)
+    end
+
+    if response.empty? or response =~ /Query ERROR:/
       raise BioMart::QueryError, response
     end
 

data/lib/rbbt/sources/entrez.rb

@@ -5,29 +5,29 @@ require 'set'
 
 module Entrez
 
-  Rbbt.add_datafiles "gene_info" => ['databases/entrez', 'ftp://ftp.ncbi.nih.gov/gene/DATA/gene_info.gz'],
-    "gene2pubmed" => ["databases/entrez", "ftp://ftp.ncbi.nih.gov/gene/DATA/gene2pubmed.gz" ]
+  Rbbt.claim "gene_info", 'ftp://ftp.ncbi.nih.gov/gene/DATA/gene_info.gz', 'databases/entrez' 
+  Rbbt.claim "gene2pubmed", 'ftp://ftp.ncbi.nih.gov/gene/DATA/gene2pubmed.gz', 'databases/entrez' 
 
   def self.entrez2native(taxs, options = {})
-    options = Misc.add_defaults options, :native => 1, :extra => 5, :flatten => true, :persistence => true
+    options = Misc.add_defaults options, :key => 1, :others => 5, :persistence => true, :merge => true
 
     taxs = [taxs] unless Array === taxs
     options.merge! :grep => taxs
 
-    tsv = TSV.new(Rbbt.find_datafile('gene_info'), options)
+    tsv = TSV.new(Rbbt.files.databases.entrez.gene_info, :flat, options)
     tsv.key_field = "Entrez Gene ID"
     tsv.fields    = ["Native ID"]
     tsv
   end
 
   def self.entrez2pubmed(taxs)
-    options = {:native => 1, :extra => 2, :flatten => true, :persistence => true}
+    options = {:key => 1, :others => 2, :persistence => true, :merge => true}
 
     taxs = [taxs] unless taxs.is_a?(Array)
     taxs = taxs.collect{|t| t.to_s}
     options.merge! :grep => taxs
 
-    TSV.new(Rbbt.find_datafile('gene2pubmed'), options)
+    TSV.new(Rbbt.files.databases.entrez.gene2pubmed, :flat, options)
   end
   
   class Gene

data/lib/rbbt/sources/go.rb

@@ -4,9 +4,8 @@ require 'rbbt-util'
 # now all it does is provide a translation form id to the actual names.
 module GO
 
-  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']
-
+  Rbbt.claim :gene_ontology, 'ftp://ftp.geneontology.org/pub/go/ontology/gene_ontology.obo', 'databases/GO'
+  Rbbt.claim :goslim_generic, 'http://www.geneontology.org/GO_slims/goslim_generic.obo', 'databases/GO'
 
   MULTIPLE_VALUE_FIELDS = %w(is_a)
   TSV_GENE_ONTOLOGY = File.join(TSV.cachedir, 'gene_ontology')

data/lib/rbbt/sources/organism.rb

@@ -1,12 +1,53 @@
 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 
+
+  def self.normalize(org, list, field = nil, others = nil, options = {})
+    return [] if list.nil? or list.empty?
+    options = Misc.add_defaults options, :persistence => true, :case_insensitive => true, :double => false
+    double = Misc.process_options options, :double
+    
+    if Array === list
+      if double
+        index.values_at *list
+      else
+        index.values_at(*list).collect{|e| Misc.first e}
+      end
+    else
+      if double
+        index[list]
+      else
+        index[list].first
+      end
+    end
+  end
+
+  def self.guess_id(org, values)
+    identifiers = TSV.new(Organism.identifiers(org), :persistence => true)
+    field_matches = identifiers.field_matches(values)
+    field_matches.sort_by{|field, matches| matches.uniq.length}.last
+  end
+
+  def self.organisms
+    Dir.glob(File.join(PKGData.sharedir_for_file(__FILE__), 'install/Organism/*/Rakefile')).collect{|f| File.basename(File.dirname(f))}
+  end
+
+  def self.name(organism)
+    Open.read(Organism.scientific_name(organism)).strip
+  end
+
+  def self.organism(name)
+    organisms.select{|organism|
+      organism == name or Organism.name(organism) =~ /#{ name }/i
+    }.first
+  end
   
   extend DataModule
   

data/lib/rbbt/sources/polysearch.rb

@@ -0,0 +1,10 @@
+require 'rbbt'
+
+module Polysearch
+  Rbbt.claim "organ" ,'http://wishart.biology.ualberta.ca/polysearch/include/organ_ID.txt', 'Polysearch'
+  Rbbt.claim "tissue" ,'http://wishart.biology.ualberta.ca/polysearch/include/tissue_ID.txt', 'Polysearch'
+  Rbbt.claim "location" ,'http://wishart.biology.ualberta.ca/polysearch/include/subcellular_localization_ID.txt', 'Polysearch'
+  Rbbt.claim "disease" ,'http://wishart.biology.ualberta.ca/polysearch/include/disease_IDlist.txt', 'Polysearch'
+  Rbbt.claim "drug" ,'http://wishart.biology.ualberta.ca/polysearch/include/drugnames.txt', 'Polysearch'
+end
+  

data/share/install/Organism/Hsa/Rakefile

@@ -52,9 +52,18 @@ $biomart_identifiers = [
   [ 'Illumina HumanWG 6 v3', 'illumina_humanwg_6_v3' ],
 ]
 
+$biomart_positions = [
+  ['Chromosome Name','chromosome_name'],
+  ['Strand','strand'],
+  ['Gene Start','start_position'],
+  ['Gene End','end_position'],
+  ['Transcript Start','transcript_start'],
+  ['Transcript End','transcript_end'],
+]
+
 
 
-file 'name' do |t|
+file 'scientific_name' do |t|
   File.open(t.name, 'w') do |f| f.puts "Homo sapiens" end
 end
 
@@ -77,7 +86,32 @@ file 'identifiers' do |t|
   File.open(t.name, 'w') do |f| f.puts identifiers end
 end
 
+file 'gene_go' do |t|
+  url = "http://cvsweb.geneontology.org/cgi-bin/cvsweb.cgi/go/gene-associations/gene_association.goa_human.gz?rev=HEAD"
+  tsv = TSV.new(Open.open(url, :gzip => true), :native => 2, :extra => 4)
+
+  index = TSV.index(Organism::Hsa.identifiers, :persistence => true)
+  new = TSV.new({})
+  tsv.through do |key, values|
+    next if index[key].nil?
+    new_key = index[key].first
+    new[new_key] = values
+  end
+
+  
+  new.key_field = "Associated Gene Name"
+  new.fields = ["GO Term"]
+  Open.write(t.name, new.to_s)
+end
+
+file 'gene_positions' do |t|
+  BioMart.set_archive('may2009')
+  positions = BioMart.tsv($biomart_db, $biomart_main, $biomart_positions)
+  BioMart.unset_archive
+
+  Open.write(t.name, positions.to_s)
+end
 
-task :default => ['name', 'lexicon', 'identifiers']
+task :default => ['name', 'lexicon', 'identifiers', 'gene_positions']
 
 

data/share/install/Organism/Sce/Rakefile

@@ -10,7 +10,7 @@ $biomart_db = 'scerevisiae_gene_ensembl'
 $biomart_main = ['Entrez Gene ID', 'entrezgene']
 
 
-file 'name' do |t|
+file 'scientific_name' do |t|
   File.open(t.name, 'w') do |f| f.puts "Saccharomyces cerevisiae" end
 end
 
@@ -27,7 +27,7 @@ file 'lexicon' do |t|
 end
 
 file 'identifiers' do |t|
-  identifiers = tsv_file($url, [$native, 0], [3, 4, 5], :keep_empty => true)
+  identifiers = tsv_file($url, [$native, 0], [["Ensembl Gene ID", 3], ["Associated Gene Name",4], ["Associated Gene Name Alias", 5]], :keep_empty => true)
 
   merge_entrez(identifiers, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tS0/)})
 

data/test/rbbt/sources/test_biomart.rb

@@ -4,7 +4,7 @@ require 'test/unit'
 
 class TestBioMart < Test::Unit::TestCase
 
-  def test_get
+  def _test_get
     assert_raise BioMart::QueryError do 
       BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],['with_unknownattr'])
     end
@@ -23,7 +23,7 @@ class TestBioMart < Test::Unit::TestCase
     assert(data['852236']['external_gene_id'].include? 'YBL044W')
   end
 
-  def test_tsv
+  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')

data/test/rbbt/sources/test_entrez.rb

@@ -18,7 +18,7 @@ class TestEntrez < Test::Unit::TestCase
     tax   = $yeast_tax
 
     data = Entrez.entrez2pubmed(tax)
-    assert(data['850320'].include? '15102838') 
+    assert(data['850320'].include? '1574125') 
   end
 
   def test_getonline

data/test/rbbt/sources/test_organism.rb

@@ -6,12 +6,24 @@ 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')
+    assert TSV.new(Organism.identifiers('Hsa'))['1020']["Associated Gene Name"].include?('CDK5')
   end
 
   def test_lexicon
     assert TSV.new(Organism.lexicon('Sce'))['S000006120'].flatten.include?('YPL199C')
   end
+
+  def test_guess_id
+    ensembl = %w(YOL044W YDR289C YAL034C YGR246C ARS519 tH(GUG)E2 YDR218C YLR002C YGL224C)
+    gene_name = %w(SNR64 MIP1 MRPS18 TFB2 JEN1 IVY1 TRS33 GAS3)
+    assert_equal "Ensembl Gene ID", Organism::Sce.guess_id(ensembl).first
+    assert_equal "Associated Gene Name", Organism::Sce.guess_id(gene_name).first
+  end
+
+  def test_organisms
+    assert Organism.organisms.include? "Hsa"
+    assert_equal "Hsa", Organism.organism("Homo sapiens")
+  end
 end
 
 

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rbbt-sources
 version: !ruby/object:Gem::Version 
-  hash: 21
-  prerelease: false
+  hash: 19
+  prerelease: 
   segments: 
   - 0
   - 2
-  - 1
-  version: 0.2.1
+  - 2
+  version: 0.2.2
 platform: ruby
 authors: 
 - Miguel Vazquez
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-14 00:00:00 +01:00
+date: 2011-01-30 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -83,12 +83,16 @@ extensions: []
 extra_rdoc_files: []
 
 files: 
+- lib/rbbt/sources/COSTART.rb
+- lib/rbbt/sources/CTCAE.rb
+- lib/rbbt/sources/Reactome.rb
 - lib/rbbt/sources/bibtex.rb
 - lib/rbbt/sources/biomart.rb
 - lib/rbbt/sources/entrez.rb
 - lib/rbbt/sources/go.rb
 - lib/rbbt/sources/gscholar.rb
 - lib/rbbt/sources/organism.rb
+- lib/rbbt/sources/polysearch.rb
 - lib/rbbt/sources/pubmed.rb
 - share/install/Organism/Hsa/Rakefile
 - share/install/Organism/Sce/Rakefile
@@ -129,7 +133,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.4.2
 signing_key: 
 specification_version: 3
 summary: Data sources for the Ruby Bioinformatics Toolkit (rbbt)