rbbt-sources 3.3.0 → 3.4.1

data/share/install/Organism/organism_helpers.rb

@@ -1,8 +1,11 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__),'..', '..', '..', 'lib'))
+
 require 'net/ftp'
+require 'rbbt/sources/biomart'
+require 'rbbt/sources/entrez'
+require File.join(File.dirname(__FILE__), '../lib/helpers')
 require 'rbbt/sources/ensembl_ftp'
 
-#Thread.current['namespace'] = $namespace
-
 $biomart_ensembl_gene = ['Ensembl Gene ID', 'ensembl_gene_id']
 $biomart_ensembl_protein = ['Ensembl Protein ID', 'ensembl_peptide_id']
 $biomart_ensembl_exon = ['Ensembl Exon ID', 'ensembl_exon_id']
@@ -77,6 +80,17 @@ $biomart_pfam= [
   ["Pfam Domain", 'pfam'],
 ]
 
+$biomart_go= [
+  ["GO ID", 'go_id'],
+  ["GO Namespace", 'namespace_1003'],
+]
+
+$biomart_go_2009= [
+  ["GO BP ID", 'go_biological_process_id'],
+  ["GO MF ID", 'go_molecular_function_id'],
+  ["GO CC ID", 'go_cellular_component_id'],
+]
+
 $biomart_gene_biotype= [
   ["Biotype", 'gene_biotype'],
 ]
@@ -91,7 +105,13 @@ $biomart_exons = [
 #{{{ Rules
 
 file 'entrez_taxids' do |t|
-  Misc.sensiblewrite(t.name, $taxs * "\n")
+  if $tax && $tax.any?
+    Misc.sensiblewrite(t.name, $taxs * "\n")
+  else
+    tsv = Rbbt.share.databases.entrez.tax_ids.tsv(:key_field => "Scientific Name", merge: true, type: :flat)
+    taxs = tsv[$scientific_name] || []
+    Misc.sensiblewrite(t.name, taxs * "\n")
+  end
 end
 
 file 'scientific_name' do |t|
@@ -104,7 +124,8 @@ file 'ortholog_key' do |t|
   Misc.sensiblewrite(t.name, $ortholog_key)
 end
 
-file 'identifiers' do |t|
+file 'identifiers' => 'entrez_taxids' do |t|
+  tax_codes = Open.read(t.prerequisites.first).strip.split("\n")
   identifiers = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_identifiers, [], nil, :namespace => Thread.current['namespace'])
   identifiers.unnamed =  true
 
@@ -116,18 +137,20 @@ file 'identifiers' do |t|
   end
 
   name_pos = identifiers.identify_field "Associated Gene Name"
-  entrez2name = Entrez.entrez2name($taxs)
-  identifiers.process "Entrez Gene ID" do |entrez, ensembl, values|
-    names = values[name_pos]
+  if tax_codes and tax_codes.any?
+    entrez2name = Entrez.entrez2name(tax_codes)
+    identifiers.process "Entrez Gene ID" do |entrez, ensembl, values|
+      names = values[name_pos] || []
 
-    matches = entrez.select do |e|
-      entrez2name.include?(e) && (names & entrez2name[e]).any?
-    end
+      matches = entrez.select do |e|
+        entrez2name.include?(e) && (names & entrez2name[e]).any?
+      end
 
-    if matches.any?
-      matches
-    else
-      entrez
+      if matches.any?
+        matches
+      else
+        entrez
+      end
     end
   end
 
@@ -147,15 +170,18 @@ file 'identifiers' do |t|
     identifiers = identifiers.reorder(:key, ordered_fields)
   end
 
-  entrez_synonyms = Rbbt.share.databases.entrez.gene_info.find.tsv :grep => $taxs.collect{|tax| "^#{tax}"}, :fixed_grep => false, :key_field => 1, :fields => [4]
-  entrez_synonyms.key_field = "Entrez Gene ID"
-  entrez_synonyms.fields = ["Entrez Gene Name Synonyms"]
+  if tax_codes and tax_codes.any?
+    entrez_synonyms = Rbbt.share.databases.entrez.gene_info.find.tsv :grep => tax_codes.collect{|tax| "^#{tax}"}, :fixed_grep => false, :key_field => 1, :fields => [4]
+    entrez_synonyms.key_field = "Entrez Gene ID"
+    entrez_synonyms.fields = ["Entrez Gene Name Synonyms"]
 
-  identifiers.attach entrez_synonyms
+    identifiers.attach entrez_synonyms
+  end
 
   identifiers.with_unnamed do
     identifiers.each do |key, values|
       values.each do |list|
+        list ||= []
         list.reject!{|v| v.nil? or v.empty?}
         list.uniq!
       end
@@ -166,10 +192,11 @@ file 'identifiers' do |t|
   Misc.sensiblewrite(t.name, identifiers.to_s)
 end
 
-file 'lexicon' => 'identifiers' do |t|
+file 'lexicon' => ['identifiers', 'entrez_taxids'] do |t|
   tsv = TSV.open(t.prerequisites.first).slice(["Associated Gene Name", "Entrez Gene Name Synonyms"])
+  tax_codes = Open.read(t.prerequisites.last).strip.split("\n")
 
-  entrez_description = Rbbt.share.databases.entrez.gene_info.tsv :grep => $taxs.collect{|tax| "^#{tax}"}, :fixed_grep => false, :key_field => 1, :fields => 8
+  entrez_description = Rbbt.share.databases.entrez.gene_info.tsv :grep => tax_codes.collect{|tax| "^#{tax}"}, :fixed_grep => false, :key_field => 1, :fields => 8
   entrez_description.key_field = "Entrez Gene ID"
   entrez_description.fields = ["Entrez Gene Description"]
 
@@ -308,8 +335,9 @@ end
 
 # {{{ Other info
 
-file 'gene_pmids' do |t|
-  tsv =  Entrez.entrez2pubmed($taxs)
+file 'gene_pmids' => 'entrez_taxids' do |t|
+  tax_codes = Open.read(t.prerequisites.first).strip.split("\n")
+  tsv =  Entrez.entrez2pubmed(tax_codes)
   text = "#: :namespace=#{Thread.current['namespace']}\n"
   text += "#Entrez Gene ID\tPMID"
   tsv.each do |gene, pmids|
@@ -417,7 +445,7 @@ file 'gene_go_bp' => 'gene_go' do |t|
    
   gene_go.monitor = true
   gene_go.process "GO ID" do |key, go_id, values|
-    clean = values.zip_fields.select do |id, type|
+    clean = NamedArray.zip_fields(values).select do |id, type|
       type == "biological_process"
     end
     clean.collect{|id, type| id}
@@ -487,9 +515,9 @@ file 'gene_pfam' do |t|
 end
 
 file 'chromosomes' do |t|
-  goterms = BioMart.tsv($biomart_db, ['Chromosome Name', "chromosome_name"] , [] , [], nil, :type => :double, :namespace => Thread.current['namespace'])
+  tsv = BioMart.tsv($biomart_db, ['Chromosome Name', "chromosome_name"] , [] , [], nil, :type => :double, :namespace => Thread.current['namespace'])
 
-  Misc.sensiblewrite(t.name, goterms.to_s)
+  Misc.sensiblewrite(t.name, tsv.keys * "\n")
 end
 
 file 'blacklist_chromosomes' => 'chromosomes' do |t|
@@ -511,6 +539,15 @@ end
 
 rule /^chromosome_.*/ do |t|
   chr = t.name.match(/chromosome_(.*)/)[1]
+  path = File.expand_path(t.name)
+  dirname = File.dirname(path)
+
+  organism = File.basename(dirname)
+  if organism =~ /^[a-z]{3}20[0-9]{2}/
+    archive = organism
+    organism = File.basename(File.dirname(dirname))
+    organism = File.join(organism, archive)
+  end
 
   # HACK: Skip LRG chromosomes
   raise "LRG and GL chromosomes not supported: #{ chr }" if chr =~ /^(?:LRG_|GL0)/
@@ -519,28 +556,51 @@ rule /^chromosome_.*/ do |t|
 
   release = Ensembl.releases[archive]
 
-  ftp = Net::FTP.new("ftp.ensembl.org")
+  fasta_url = Ensembl::FTP.ftp_name_for(organism, 'fasta').last
+  server, _, path = fasta_url.partition("/")
+  path = "/" + path
+
+  ftp = Net::FTP.new(server)
   ftp.passive = true
   ftp.login
-  if release.nil? or release == 'current'
-    ftp.chdir("pub/current_fasta/")
-  else
-    ftp.chdir("pub/#{ release }/fasta/")
-  end
-  ftp.chdir($scientific_name.downcase.sub(" ",'_'))
+  ftp.chdir(path)
   ftp.chdir('dna')
-  file = ftp.nlst.select{|file| file =~ /chromosome\.#{ chr }\.fa/}.first
-
-  raise "Fasta file for chromosome not found: '#{ chr }' - #{ archive }, #{ release }" if file.nil?
 
-  Log.debug("Downloading chromosome sequence: #{ file } - #{release} #{t.name}")
+  file = ftp.nlst.select{|file| file =~ /dna_sm\.chromosome\.#{ chr }\.fa/}.first
+  if file
+    Log.debug("Downloading chromosome sequence: #{ file } - #{release} #{t.name}")
 
-  Misc.lock t.name + '.rake' do
-    TmpFile.with_file do |tmpfile|
-      ftp.getbinaryfile(file, tmpfile)
-      Misc.sensiblewrite(t.name, Open.read(tmpfile, :gzip => true).sub(/^>.*\n/,'').gsub(/\s/,''))
-      ftp.close
+    Misc.lock t.name + '.rake' do
+      TmpFile.with_file do |tmpfile|
+        ftp.getbinaryfile(file, tmpfile)
+        Misc.sensiblewrite(t.name, Open.read(tmpfile, :gzip => true).sub(/^>.*\n/,'').gsub(/\s/,''))
+        ftp.close
+      end
     end
+  else
+    file = ftp.nlst.select{|file| file =~ /dna_sm\.toplevel\.fa\.gz/}.first if file.nil?
+    Misc.lock t.name + '.rake' do
+      TmpFile.with_file do |tmpfile|
+        ftp.getbinaryfile(file, tmpfile)
+        txt = Open.read(tmpfile, :gzip => true)
+
+        chr_txt = []
+
+        in_chr = false
+        txt.split("\n").each do |line|
+          if line.start_with?(">#{chr}")
+            in_chr = true
+          elsif line.start_with?(">")
+            in_chr = false
+          else
+            chr_txt << line if in_chr
+          end
+        end
+        Misc.sensiblewrite(t.name, chr_txt * "" )
+        ftp.close
+      end
+    end
+    raise "Fasta file for chromosome not found: '#{ chr }' - #{ archive }, #{ release }" if file.nil?
   end
 end
 
@@ -584,6 +644,16 @@ end
 require 'bio'
 
 file 'transcript_sequence' => ["exons", "transcript_exons", "blacklist_chromosomes"] do |t|
+  path = File.expand_path(t.name)
+  dirname = File.dirname(path)
+
+  organism = File.basename(dirname)
+  if organism =~ /^[a-z]{3}20[0-9]{2}/
+    archive = organism
+    organism = File.basename(File.dirname(dirname))
+    organism = File.join(organism, archive)
+  end
+
   exon_info = TSV.open('exons', :type => :list, :fields => ["Exon Strand", "Exon Chr Start", "Exon Chr End", "Chromosome Name"], :unnamed => true)
 
   chr_transcript_ranges ||= {}
@@ -616,10 +686,10 @@ file 'transcript_sequence' => ["exons", "transcript_exons", "blacklist_chromosom
   chr_transcript_ranges.each do |chr, transcript_ranges|
     begin
       raise "LRG, GL, HG, NT, KI, and HSCHR chromosomes not supported: #{chr}" if blacklist_chromosomes.include? chr
-      p = File.expand_path("./chromosome_#{chr}")
-      Organism.root.annotate p
-      p.sub!(%r{.*/organisms/},'share/organisms/')
-      chr_str = p.produce.read
+      pkgdir = Thread.current["resource"]
+      p = pkgdir[organism]["chromosome_#{chr}"]
+      p.produce or raise "Could not produce #{p}; pkgdir: #{p.pkgdir}"
+      chr_str = p.read
     rescue Exception
       Log.warn("Chr #{ chr } failed (#{transcript_ranges.length} transcripts not covered): #{$!.message}")
       raise $! unless $!.message =~ /not supported/
@@ -656,7 +726,7 @@ file 'transcript_5utr' => ["exons", "transcript_exons", "transcripts"] do |t|
     organism = File.join(organism, archive)
   end
 
-  translation        = Ensembl::FTP.ensembl_tsv(organism, 'translation', 'transcript_id', %w(seq_start start_exon_id seq_end end_exon_id), :type => :list, :unmamed => true)
+  translation        = Ensembl::FTP.ensembl_tsv(organism, 'translation', 'transcript_id', %w(seq_start start_exon_id seq_end end_exon_id), :type => :list, :unnamed => true)
 
   if Ensembl::FTP.has_table?(organism, 'exon_stable_id')
     exon2ensembl       = Ensembl::FTP.ensembl_tsv(organism, 'exon_stable_id', 'exon_id', ['stable_id'], :type => :single, :unnamed => true) 
@@ -670,9 +740,9 @@ file 'transcript_5utr' => ["exons", "transcript_exons", "transcripts"] do |t|
     transcript2ensembl = Ensembl::FTP.ensembl_tsv(organism, 'transcript', 'transcript_id', ['stable_id'], :type => :single, :unnamed => true) 
   end
 
-  transcript_protein = TSV.open("./transcripts", :key_field => "Ensembl Transcript ID", :fields => ["Ensembl Protein ID"], :type => :single,  :unmamed => true)
-  transcript_exons   = TSV.open("./transcript_exons", :unmamed => true)
-  exon_ranges        = TSV.open("./exons",:fields => ["Exon Chr Start", "Exon Chr End"], :cast => :to_i, :unmamed => true)
+  transcript_protein = TSV.open("./transcripts", :key_field => "Ensembl Transcript ID", :fields => ["Ensembl Protein ID"], :type => :single,  :unnamed => true)
+  transcript_exons   = TSV.open("./transcript_exons", :unnamed => true)
+  exon_ranges        = TSV.open("./exons",:fields => ["Exon Chr Start", "Exon Chr End"], :cast => :to_i, :unnamed => true)
 
   transcript_utr5 = TSV.setup({}, :key_field => "Ensembl Transcript ID", :fields => ["5' UTR Length"], :cast => :to_i, :type => :single)
   transcript_utr3 = TSV.setup({}, :key_field => "Ensembl Transcript ID", :fields => ["3' UTR Length"], :cast => :to_i, :type => :single)
@@ -719,12 +789,13 @@ end
 file 'protein_sequence' => ["transcripts", "transcript_5utr", "transcript_3utr", "transcript_phase", "transcript_sequence"] do |t|
   transcript_5utr     = TSV.open(File.expand_path('./transcript_5utr'), :unnamed => true)
   transcript_3utr     = TSV.open(File.expand_path('./transcript_3utr'), :unnamed => true)
-  transcript_phase     = TSV.open(File.expand_path('./transcript_phase'), :unnamed => true)
+  transcript_phase    = TSV.open(File.expand_path('./transcript_phase'), :unnamed => true)
   transcript_sequence = TSV.open(File.expand_path('./transcript_sequence'), :unnamed => true)
   transcript_protein  = TSV.open(File.expand_path('./transcripts'), :fields => ["Ensembl Protein ID"], :type => :single, :unnamed => true)
 
 
   protein_sequence = TSV.setup({}, :key_field => "Ensembl Protein ID", :fields => ["Sequence"], :type => :single)
+  transcript_sequence.monitor = true
   transcript_sequence.through do |transcript, sequence|
     protein = transcript_protein[transcript]
     next if protein.nil? or protein.empty?
@@ -777,6 +848,7 @@ file 'uniprot2ensembl' => ["protein_sequence", "protein_identifiers"] do |t|
     uni_seq = UniProt.get_uniprot_sequence(uni)
     ensps = uni2ensps[uni]
     next if ensps.nil? or ensps.empty?
+
     best_ensp = ensps.sort_by do |ensp|
       ensp_seq = ensp2seq[ensp]
       if ensp_seq
@@ -806,7 +878,7 @@ file 'gene_set' do |t|
   build_code = Organism.GRC_build(organism)
   scientific_name = $scientific_name
   url = "ftp://ftp.ensembl.org/pub/release-#{num}/gtf/#{scientific_name.downcase.sub(" ", '_')}/#{scientific_name.sub(" ", '_')}.#{build_code}.#{num}.gtf.gz"
-  CMD.cmd("wget '#{url}' -O #{t.name}.gz")
+  Open.download(url, "#{t.name}.gz")
   nil
 end
 
@@ -825,7 +897,8 @@ file 'cdna_fasta' do |t|
   num = release.split("-").last
   build_code = Organism.GRC_build(organism)
   scientific_name = Organism.scientific_name(organism)
-  url = "ftp://ftp.ensembl.org/pub/release-#{num}/fasta/#{scientific_name.downcase.sub(" ", '_')}/cdna/#{scientific_name.sub(" ", '_')}.#{build_code}.cdna.all.fa.gz"
-  CMD.cmd("wget '#{url}' -O #{t.name}.gz")
+  url = "ftp://ftp.ensembl.org/pub/release-#{num}/fasta/#{scientific_name.downcase.sub(" ", '_')}/cdna/#{scientific_name.sub(" ", '_')}.#{build_code}.#{num}.cdna.all.fa.gz"
+  Open.download(url, "#{t.name}.gz")
   nil
 end
+

data/share/install/lib/rake_helper.rb

@@ -9,7 +9,7 @@ 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
+      FileUtils.mkdir SOURCE_DIR unless File.exist? 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
@@ -87,5 +87,5 @@ end
 task :all => :default 
 
 task :clean do
-  ($__tsv_tasks + $__files).each do |file| FileUtils.rm file.to_s if File.exists?(file.to_s) end
+  ($__tsv_tasks + $__files).each do |file| FileUtils.rm file.to_s if File.exist?(file.to_s) end
 end

data/test/rbbt/sources/test_biomart.rb

@@ -3,34 +3,44 @@ require File.expand_path(File.dirname(__FILE__) + '/../../test_helper')
 require 'rbbt/sources/pubmed'
 require 'test/unit'
 require 'rbbt/sources/biomart'
+require 'rbbt/sources/organism'
 require 'rbbt/util/tmpfile'
 require 'test/unit'
 
 class TestBioMart < Test::Unit::TestCase
 
   def setup
-    BioMart.set_archive Organism.default_code("Hsa")
+    BioMart.set_archive "feb2014"
   end
 
   def teardown
     BioMart.unset_archive
   end
 
-  def _test_get
+  def test_get_Sce
     assert_raise BioMart::QueryError do 
       BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],['with_unknownattr'])
     end
 
-    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],[], nil, :nocache => false, :merge => true, :wget_options => {:quiet => false})
+    BioMart.set_archive "feb2023-fungi"
+    data = BioMart.get('scerevisiae_eg_gene','entrezgene_id', ['protein_id'],[], nil, :nocache => true, :merge => true, :wget_options => {:quiet => false})
     tsv = TSV.open data, :double, :merge => true
-    assert(tsv['852236'][0].include? 'CAA84864')
+    assert(tsv['852236'][0].include? 'CAA84864.1')
 
-    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['external_gene_id'],[], data, :nocache => false, :wget_options => { :quiet => false} )
+    data = BioMart.get('scerevisiae_eg_gene','entrezgene_id', ['external_gene_id'],[], data, :nocache => false, :wget_options => { :quiet => false} )
     tsv = TSV.open data, :double, :merge => true
     assert(tsv['852236'][1].include? 'YBL044W')
   end
 
-  def _test_query
+  def test_get_Hsa
+    Log.severity = 0
+    data = BioMart.get('hsapiens_gene_ensembl','entrezgene', ['protein_id'],[], nil, :nocache => true, :merge => true, :wget_options => {:quiet => false})
+    tsv = TSV.open data, :double, :merge => true
+    assert(tsv['852236'][0].include? 'CAA84864.1')
+  end
+
+
+  def test_query
     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')
 
@@ -41,6 +51,34 @@ class TestBioMart < Test::Unit::TestCase
     end
   end
 
+  def __test_transcrip_exons
+    Log.with_severity 1 do
+      TmpFile.with_file do |f|
+        fields = ['ensembl_transcript_id','ensembl_exon_id','rank']
+        main = fields[0]
+        attrs = fields.values_at(1, 2)
+        attrs_first = [attrs.first]
+        attrs_last = [attrs.last]
+        database = 'hsapiens_gene_ensembl'
+
+        filename = BioMart.get(database, main, attrs, {"ensembl_transcript_id" => ['ENST00000357654']}, nil, :nocache => false, :wget_options => {:quiet => false}, :filename => f)
+        ppp Open.read(filename)
+
+        filename = BioMart.get(database, main, attrs_first, {"ensembl_transcript_id" => ['ENST00000357654']}, nil, :nocache => false, :wget_options => {:quiet => false}, :filename => f)
+        ppp Open.read(filename)
+
+        filename = BioMart.get(database, main, attrs_last, {"ensembl_transcript_id" => ['ENST00000357654']}, nil, :nocache => false, :wget_options => {:quiet => false}, :filename => f)
+        ppp Open.read(filename)
+
+        filename = BioMart.query(database, main, attrs, {"ensembl_transcript_id" => ['ENST00000357654']}, nil, :nocache => true, :wget_options => {:quiet => false}, :filename => f)
+        ppp Open.read(filename)
+
+        data = TSV.open Open.open(filename)
+        assert(data['852236']['external_gene_id'].include? 'YBL044W')
+      end
+    end
+  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')

data/test/rbbt/sources/test_ensembl_ftp.rb

@@ -0,0 +1,11 @@
+require File.expand_path(__FILE__).sub(%r(/test/.*), '/test/test_helper.rb')
+require File.expand_path(__FILE__).sub(%r(.*/test/), '').sub(/test_(.*)\.rb/,'\1')
+
+class TestEnsemblFTP < Test::Unit::TestCase
+  def test_ftp_for
+    assert_nothing_raised do
+      Ensembl::FTP.ftp_name_for("Hsa/feb2023", 'fasta')
+    end
+  end
+end
+

data/test/rbbt/sources/test_entrez.rb

@@ -14,6 +14,11 @@ class TestEntrez < Test::Unit::TestCase
     assert(lexicon['855611'].include? 'S000005056') 
   end
 
+  def test_entrez2name
+    tax    = $yeast_tax
+    Entrez.entrez2name(tax)
+  end
+
   def test_entrez2pubmed
     tax   = $yeast_tax
 

data/test/rbbt/sources/test_mesh.rb

@@ -0,0 +1,10 @@
+require File.expand_path(__FILE__).sub(%r(/test/.*), '/test/test_helper.rb')
+require File.expand_path(__FILE__).sub(%r(.*/test/), '').sub(/test_(.*)\.rb/,'\1')
+
+class TestMESH < Test::Unit::TestCase
+  def test_vocab
+    tsv = MeSH.vocabulary.tsv
+    assert_equal "3T3 Cells", tsv["D016475"]
+  end
+end
+

data/test/rbbt/sources/test_organism.rb

@@ -5,37 +5,37 @@ require 'rbbt/sources/ensembl_ftp'
 
 class TestOrganism < Test::Unit::TestCase
 
-  def test_known_ids
+  def _test_known_ids
     assert Organism.known_ids("Hsa").include?("Associated Gene Name")
   end
 
-  def test_location
+  def _test_location
     assert_equal "share/organisms/Sce/identifiers", Organism.identifiers('Sce')
   end
 
-  def test_identifiers
+  def _test_identifiers
     assert Organism.identifiers('Hsa/feb2014').tsv(:key_field => "Entrez Gene ID", :persist => true)['1020']["Associated Gene Name"].include?('CDK5')
     assert Organism.identifiers('Sce').tsv(:persist => true)['S000006120']["Ensembl Gene ID"].include?('YPL199C')
     assert Organism.identifiers("Sce").tsv(:persist => true)['S000006120']["Ensembl Gene ID"].include?('YPL199C')
   end
 
-  def test_lexicon
+  def _test_lexicon
     assert TSV.open(Organism.lexicon('Sce'))['S000006120'].flatten.include?('YPL199C')
   end
 
-  def test_guess_id
+  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 "Associated Gene Name", Organism.guess_id("Sce", gene_name).first
     assert_equal "Ensembl Gene ID", Organism.guess_id("Sce", ensembl).first
   end
 
-  def test_organisms
+  def _test_organisms
     assert Organism.organisms.include? "Hsa"
     assert_equal "Hsa", Organism.organism("Homo sapiens")
   end
 
-  def test_attach_translations
+  def _test_attach_translations
     tsv = TSV.setup({"1020" => []}, :type => :list)
     tsv.key_field = "Entrez Gene ID"
     tsv.fields = []
@@ -47,21 +47,21 @@ class TestOrganism < Test::Unit::TestCase
     assert_equal "CDK5", tsv["1020"]["Associated Gene Name"]
   end
 
-  def test_entrez_taxids
+  def _test_entrez_taxids
     assert_equal "Hsa", Organism.entrez_taxid_organism('9606')
   end
 
-  def test_lift_over
+  def _test_lift_over
     mutation_19 = "19:21131664:T"
     mutation_18 = "19:20923504:T"
-    source_build = Organism.default_code("Hsa")
+    source_build = "Hsa/feb2014"
     target_build = "Hsa/may2009"
 
     assert_equal mutation_18, Organism.liftOver([mutation_19], source_build, target_build).first
     assert_equal mutation_19, Organism.liftOver([mutation_18], target_build, source_build).first
   end
 
-  def test_orhtolog
+  def _test_orhtolog
     require 'rbbt/entity/gene'
     assert_equal ["ENSG00000133703"], Gene.setup("Kras", "Associated Gene Name", "Mmu/jun2011").ensembl.ortholog(Organism.default_code("Hsa"))
   end
@@ -70,23 +70,23 @@ class TestOrganism < Test::Unit::TestCase
     assert Organism.chromosome_sizes["2"].to_i > 10_000_000
   end
 
-  def test_build_organism
+  def _test_build_organism
     assert_equal 'Hsa/may2017', Organism.organism_for_build('hg38')
     assert_equal 'Hsa/feb2014', Organism.organism_for_build('b37')
     assert_equal 'Mmu/may2017', Organism.organism_for_build('mm10')
   end
 
-  #def test_genes_at_chromosome
+  #def _test_genes_at_chromosome
   #  pos = [12, 117799500]
   #  assert_equal "ENSG00000089250", Organism::Hsa.genes_at_chromosome_positions(pos.first, pos.last)
   #end
 
-  #def test_genes_at_chromosome_array
+  #def _test_genes_at_chromosome_array
   #  pos = [12, [117799500, 106903900]]
   #  assert_equal ["ENSG00000089250", "ENSG00000013503"], Organism::Hsa.genes_at_chromosome_positions(pos.first, pos.last)
   #end
  
-  #def test_genes_at_genomic_positions
+  #def _test_genes_at_genomic_positions
   #  pos = [[12, 117799500], [12, 106903900], [1, 115259500]]
   #  assert_equal ["ENSG00000089250", "ENSG00000013503", "ENSG00000213281"], Organism::Hsa.genes_at_genomic_positions(pos)
   #end

data/test/rbbt/sources/test_pubmed.rb

@@ -5,7 +5,17 @@ require 'test/unit'
 
 class TestPubMed < Test::Unit::TestCase
 
-  def test_get_article
+  def test_mesh
+    pmid = '10866666'
+    assert_include PubMed.get_article(pmid).mesh, "D016475"
+  end
+
+  def _test_substance
+    pmid = '10866666'
+    assert_include PubMed.get_article(pmid).substance, "C000717247"
+  end
+
+  def _test_get_article
     pmid = '16438716'
     assert(PubMed.get_article(pmid).title == "Discovering semantic features in the literature: a foundation for building functional associations.")
     
@@ -13,38 +23,38 @@ 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_get_multi_abstract
+  def _test_get_multi_abstract
     pmid = "32141403"
 
     assert PubMed.get_article(pmid).abstract.include?("This study shows PCOS patients are at increased risk of incident schizophrenia, and the metformin treatment has a protective effect against incident schizophrenia.")
   end
  
-  def test_full_text
+  def _test_full_text
     pmid = '16438716'
     assert(PubMed.get_article(pmid).full_text =~ /Discovering/)
   end
 
-  def test_pmc_full_xml
+  def _test_pmc_full_xml
     pmid = '4304705'
     assert PubMed.get_article(pmid).pmc_full_xml.include?("HBV antigen")
   end
  
  
-  def test_query
+  def _test_query
     assert(PubMed.query('chagoyen[All Fields] AND ("loattrfull text"[sb] AND hasabstract[text])').include? '16438716')
   end
 
-  def test_year
+  def _test_year
     pmid = '16438716'
     assert_equal "2006", PubMed.get_article(pmid).year
   end
 
-  def test_bibentry
+  def _test_bibentry
     assert("vazquez2008sent", PubMed::Article.make_bibentry('vazquez', 2008, "SENT: Semantic features in text"))
     assert("vazquez2008aes", PubMed::Article.make_bibentry('vazquez', 2008, "An Example System"))
   end
 
-  def test_missing
+  def _test_missing
     pmids = '18627426,014966295'.split(",")
     Log.severity = 0
     assert PubMed.get_article(pmids).include? "014966295"