rbbt 1.1.8 → 1.2.1

data/test/rbbt/ner/test_regexpNER.rb

@@ -0,0 +1,33 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt'
+require 'rbbt/util/tmpfile'
+require 'rbbt/ner/regexpNER'
+require 'test/unit'
+
+class TestRegExpNER < Test::Unit::TestCase
+
+  def test_class
+    text = "a bc d e f g h i j k  l m n o p q one two"
+
+    lexicon =<<-EOF
+C1,a,x,xx,xxx
+C2,bc,y,yy,yyy
+C3,i,z,zz,zzz,m,one two
+    EOF
+
+    file = TmpFile.tmp_file
+    File.open(file, 'w'){|f| f.write lexicon}
+
+    r = RegExpNER.new(file, :sep => ',', :stopwords => false)
+    assert_equal(['a', 'bc', 'i', 'm','one two'].sort,r.match_hash(text).values.flatten.sort)
+
+    r = RegExpNER.new(file, :sep => ',', :stopwords => true)
+    assert_equal(['bc', 'm','one two'].sort,r.match_hash(text).values.flatten.sort)
+
+
+    FileUtils.rm file
+  end
+
+end
+
+

data/test/rbbt/ner/test_rner.rb

@@ -0,0 +1,126 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt'
+require 'rbbt/ner/rner'
+require 'test/unit'
+
+class TestRNer < Test::Unit::TestCase
+
+  def setup
+    @parser = NERFeatures.new do
+      isLetters     /^[A-Z]+$/i 
+      context prefix_3      /^(...)/ 
+      downcase do |w| w.downcase end
+
+      context %w(downcase)
+    end
+  end
+
+  def test_config
+    config = <<-EOC
+  isLetters(/^[A-Z]+$/i)
+  context(prefix_3(/^(...)/))
+  downcase { |w| w.downcase }
+  context(["downcase"])
+    EOC
+
+    assert(@parser.config == config)
+  end
+
+  def test_reverse
+    assert_equal("protein P53", NERFeatures.reverse("P53 protein"))
+    assert_equal(
+       ". LH of assay - radioimmuno serum the with compared was LH urinary for ) GONAVIS - HI ( test hemagglutination direct new A", 
+     NERFeatures.reverse(
+       "A new direct hemagglutination test (HI-GONAVIS) for urinary LH was compared with the serum\n radioimmuno-assay of LH."
+      ))
+  end
+
+  def test_features
+    assert(@parser.features("abCdE"),["abCdE",true,'abc','abcde'])
+  end
+
+  def test_template
+    template =<<-EOT
+UisLetters: %x[0,1]
+Uprefix_3: %x[0,2]
+Uprefix_3#1: %x[1,2]
+Uprefix_3#-1: %x[-1,2]
+Udowncase: %x[0,3]
+Udowncase#1: %x[1,3]
+Udowncase#-1: %x[-1,3]
+B
+    EOT
+    
+    assert(@parser.template == template)
+  end
+
+  def test_tokens
+    assert( NERFeatures.tokens("A new direct hemagglutination test (HI-GONAVIS) for urinary LH was compared with the serum\n radioimmuno-assay of LH.")==
+           ["A", "new", "direct", "hemagglutination", "test", "(", "HI", "-", "GONAVIS", ")", "for", "urinary", "LH", "was", "compared", "with", "the", "serum", "radioimmuno", "-", "assay", "of", "LH", "."])
+
+
+  end
+  def test_text_features
+ 
+    assert(@parser.text_features("abCdE 1234") == [["abCdE",true, "abC", "abcde"], ["1234",false, "123", "1234"]])
+    assert(@parser.text_features("abCdE 1234",true) == [["abCdE",true, "abC", "abcde",1], ["1234",false, "123", "1234",2]])
+    assert(@parser.text_features("abCdE 1234",false) == [["abCdE",true, "abC", "abcde",0], ["1234",false, "123", "1234",0]])
+   
+  end
+
+  def test_tagged_features
+    assert_equal(
+      [["phosphorilation",true, "pho", "phosphorilation", 0], 
+        ["of",true, false, "of", 0], 
+        ["GENE1",false, "GEN", "gene1", 1],
+        [".", false, false, ".", 0]],
+      @parser.tagged_features("phosphorilation of GENE1.",['GENE1']))
+
+      assert_equal(
+        [["GENE1",false, "GEN", "gene1", 1],
+          ["phosphorilation",true, "pho", "phosphorilation", 0]], 
+      @parser.tagged_features("GENE1 phosphorilation",['GENE1']))
+
+ 
+    assert_equal(
+           [["phosphorilation",true, "pho", "phosphorilation", 0], 
+            ["of",true, false, "of", 0], 
+            ["GENE",true, "GEN", "gene", 1],
+            ["1",false, false, "1", 2],
+            [".", false, false, ".", 0]],
+      @parser.tagged_features("phosphorilation of GENE 1.",['GENE 1']))
+  end
+
+  def test_tagged_features_reverse
+    @parser.reverse = true
+    assert_equal(
+      [
+        ["GENE1",false, "GEN", "gene1", 1],
+        ["of",true, false, "of", 0], 
+        ["phosphorilation",true, "pho", "phosphorilation", 0]
+    ],
+    @parser.tagged_features("phosphorilation of GENE1",['GENE1']))
+
+    assert_equal(
+          [
+            [".", false, false, ".", 0],
+            ["1",false, false, "1", 1],
+            ["GENE",true, "GEN", "gene", 2],
+            ["of",true, false, "of", 0], 
+            ["phosphorilation",true, "pho", "phosphorilation", 0]
+        ],
+    @parser.tagged_features("phosphorilation of GENE 1.",['GENE 1']))
+  end
+
+
+  def test_NER_default
+    parser = NERFeatures.new
+
+    assert(parser.template =~ /UisLetter/)
+  end
+
+  def test_CRFPP_install
+    assert(require File.join(Rbbt.datadir, 'third_party/crf++/ruby/CRFPP'))
+  end
+
+end

data/test/rbbt/ner/test_rnorm.rb

@@ -0,0 +1,47 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt/ner/rnorm'
+require 'rbbt/util/open'
+require 'rbbt/util/tmpfile'
+require 'test/unit' 
+ 
+class TestRNORM < Test::Unit::TestCase
+ 
+  def setup 
+    tmp = TmpFile.tmp_file("test-rnorm-")
+    lexicon =<<-EOT
+S000000029	YAL031C	GIP4	FUN21
+S000000030	YAL032C	PRP45	FUN20
+S000000031	YAL033W	POP5	FUN53 
+S000000374	YBR170C	NPL4	HRD4
+S000000375	GENE1	BBB	CCC
+S000000376	AAA	GENE1	DDD
+	EOT
+
+    Open.write(tmp, lexicon)
+
+    @norm = Normalizer.new(tmp) 
+    FileUtils.rm tmp
+  end
+
+  def test_match
+     assert_equal(["S000000029"], @norm.match("FUN21"))
+     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN"))
+     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN 2"))
+     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN 21")) 
+     assert_equal([], @norm.match("GER4"))
+
+     @norm.match("FUN21")
+  end 
+
+  def test_select
+    assert_equal(["S000000029"], @norm.select(["S000000030", "S000000029", "S000000031"],"FUN 21"))
+  end
+
+  def test_resolve
+    assert_equal(["S000000029"], @norm.resolve("FUN 21"))
+  end
+
+  def test_order
+    assert_equal(["S000000375"], @norm.resolve("GENE1"))
+  end
+end

data/test/rbbt/sources/test_biocreative.rb

@@ -0,0 +1,38 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt/sources/biocreative'
+require 'test/unit'
+
+class TestBiocreative < Test::Unit::TestCase
+
+  def test_BC2GM
+    assert(Biocreative.BC2GM(:test)['BC2GM000008491'][:text] == "Phenotypic analysis demonstrates that trio and Abl cooperate in regulating axon outgrowth in the embryonic central nervous system (CNS).")
+    assert(Biocreative.BC2GM(:test)['BC2GM000008491'][:mentions] == ["trio", "Abl"] )
+  end
+
+  def test_position
+    mention   = "IgA"
+    text      = "Early complement components, C1q and C4, and IgA secretory piece were absent."
+    pos       = [[38, 40]]
+    assert(Biocreative.position(text,mention) == pos)
+
+    mention   = "tyrosine-specific phosphatase"
+    text      = "When expressed in Escherichia coli, SH-PTP2 displays tyrosine-specific phosphatase activity."
+    pos       = [[46, 73]]
+    assert(Biocreative.position(text,mention) == pos)
+
+    mention   = "tyrosine - specific phosphatase"
+    text      = "When expressed in Escherichia coli, SH-PTP2 displays tyrosine-specific phosphatase activity."
+    pos       = [[46, 73]]
+    assert(Biocreative.position(text,mention) == pos)
+
+    mention   = "LH"
+    text      = "A new direct hemagglutination test (HI-GONAVIS) for urinary LH was compared with the serum radioimmuno-assay of LH."
+    pos       = [[52, 53],[96, 97]]
+    assert(Biocreative.position(text,mention) == pos)
+
+  end
+
+
+end
+
+

data/test/rbbt/sources/test_biomart.rb

@@ -0,0 +1,31 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt/sources/biomart'
+require 'test/unit'
+
+class TestBioMart < Test::Unit::TestCase
+
+  def test_get
+    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'],[])
+    assert(data['856452']['protein_id'].include? 'AAB68382')
+
+    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['external_gene_id'],[], data )
+    assert(data['856452']['protein_id'].include? 'AAB68382')
+    assert(data['856452']['external_gene_id'].include? 'CUP1-2')
+
+  end
+
+  def test_query
+    data = BioMart.query('scerevisiae_gene_ensembl','entrezgene', ['protein_id','refseq_peptide','external_gene_id','ensembl_gene_id'],[])
+
+    assert(data['856452']['protein_id'].include? 'AAB68382')
+    assert(data['856452']['external_gene_id'].include? 'CUP1-2')
+
+ end
+
+end
+
+

data/test/rbbt/sources/test_entrez.rb

@@ -0,0 +1,49 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt/sources/entrez'
+require 'test/unit'
+
+class TestEntrez < Test::Unit::TestCase
+
+  def test_entrez2native
+    tax   = 4932
+    fix   = proc{|code| code.sub(/SGD:S0/,'S0') }
+    check = proc{|code| code.match(/^S0/)}
+
+    lexicon = Entrez.entrez2native(tax, 5, fix, check)
+    assert(lexicon['855611'].include? 'S000005056') 
+  end
+
+  def test_entrez2pubmed
+    tax = 4932
+
+    data = Entrez.entrez2pubmed(tax)
+    assert(data['850320'].include? '15102838') 
+  end
+
+  def test_getonline
+    geneids = 9129
+
+    assert_match(/PRP3 pre-mRNA processing factor/s, Entrez.get_online(geneids))
+
+    geneids = [9129,9]
+    assert_match(/PRP3 pre-mRNA processing factor/s, Entrez.get_online(geneids)[9129])
+  end
+
+  def test_getgene
+    geneids = 9129
+    assert_equal([["PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)"]], Entrez.get_gene(geneids).description)
+
+    geneids = [9129,728049]
+    assert_equal([["PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)"]], Entrez.get_gene(geneids)[9129].description)
+
+  end
+
+  def test_similarity
+    assert(Entrez.gene_text_similarity(9129, "PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)") > 0)
+    assert_equal(0, Entrez.gene_text_similarity("NON EXISTEN GENEID", "PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)"))
+
+  end
+
+end
+
+

data/test/rbbt/sources/test_go.rb

@@ -0,0 +1,24 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+
+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']))
+  end
+
+  def test_ancestors
+    assert GO.id2ancestors('GO:0000001').include? 'GO:0048308'
+  end
+
+  def test_namespace
+    assert_equal 'biological_process', GO.id2namespace('GO:0000001')
+  end
+
+
+end
+
+

data/test/rbbt/sources/test_organism.rb

@@ -0,0 +1,59 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt/sources/organism'
+require 'test/unit'
+
+class TestOrganism < Test::Unit::TestCase
+
+  def test_all
+    assert Organism.all.include? 'Sce'
+  end
+
+  def test_ner
+    assert(Organism.ner(:Sce, :abner).is_a? Abner)
+  end
+
+  def test_norm
+    assert_equal(["S000003008"], Organism.norm(:Sce).select(['S000029454','S000003008'],'SLU1', 'SLU1 has been used in the literature to refer to both HEM2/YGL040C, which encodes a porphobilinogen synthase and SLU1, which is essential for splicing.'))
+
+  end
+
+  def test_supported_ids
+
+    ids = Organism.supported_ids('Sce', :examples => true)
+    assert(ids.first[0] == 'SGD DB Id' && ids.first[1] =~ /^S00/)
+    
+    ids = Organism.supported_ids('Sce')
+    assert(ids.first == 'SGD DB Id')
+  end
+
+  def test_index
+    index = Organism.id_index('Sce')
+    assert_equal("S000004431", index['851160'])
+  end
+
+  def test_index_partial
+    index = Organism.id_index('Sce',:other => ['Ensembl Gene ID', 'Protein ID'])
+    assert_nil(index['851160'])
+    assert_equal("S000000838", index['YER036C'])
+    
+    index = Organism.id_index('Sce',:other => ['Ensembl Gene ID', 'Protein ID'], :native => "Entrez Gene ID")
+    assert_equal("856758", index['YER036C'])
+
+  end
+
+  def test_go_terms
+
+    begin
+      goterms = Organism.goterms('Sce')
+      assert(goterms["S000000838"].include? "GO:0016887")
+    rescue
+      puts $!
+      puts "No goterms produced, see if it is all installed"
+    end
+
+  end
+
+
+end
+
+

data/test/rbbt/sources/test_polysearch.rb

@@ -0,0 +1,27 @@
+require File.dirname(__FILE__) + '/../../test_helper'
+require 'rbbt'
+require 'rbbt/util/tmpfile'
+require 'rbbt/sources/polysearch'
+require 'test/unit'
+
+class TestPolysearch < Test::Unit::TestCase
+
+  def test_match
+    text =<<-EOT
+
+    Analysis of sorted peripheral blood lymphocytes (CD8 T cells, CD4 T cells,
+    B cells, NK cells) from patients with melanoma. These subpopulations are
+    involved in antitumor responses and negatively impacted by cancer. Results
+    provide insight into molecular mechanisms of immune dysfunction in cancer.
+
+    EOT
+
+    assert_equal(["B cells", "T cells", "blood", "lymphocytes",  "peripheral blood", "peripheral blood lymphocytes"].sort, Polysearch.match(text,nil).values.flatten.uniq.sort) 
+  end
+
+  def test_name
+    assert_equal('ligament', Polysearch.name('organ','OR00039'))
+  end
+end
+
+