rbbt-util 5.14.33 → 5.14.34

data/test/rbbt/test_knowledge_base.rb

@@ -4,72 +4,100 @@ require 'test/unit'
 
 require 'rbbt/workflow'
 require 'rbbt/entity'
+require 'rbbt/entity/identifiers'
 
 require 'rbbt/association'
 require 'rbbt/knowledge_base'
 
-class TestKnowledgeBase < Test::Unit::TestCase
-  def setup
-    if not defined? Genomics
-      Workflow.require_workflow "Genomics"
-      require 'genomics_kb'
-    end
-    KnowledgeBase.knowledge_base_dir = Rbbt.tmp.knowledge_base_test.find
-    @kb = Genomics.knowledge_base
-  end
-
-  def test_register
-    require 'rbbt/sources/pina'
-
-    TmpFile.with_file do |dir|
-      kb = KnowledgeBase.new dir
-
-      kb.register :pina, Pina.protein_protein, :target => "Interactor UniProt/SwissProt Accession=~UniProt/SwissProt Accession"
-      assert_equal [Gene], kb.entity_types
-      assert kb.all_databases.include? :pina
+require 'rbbt/sources/organism'
+require 'rbbt/sources/tfacts'
+require 'rbbt/sources/kegg'
+
+module Gene
+  extend Entity
+  add_identifiers Organism.identifiers("NAMESPACE"), "Ensembl Gene ID", "Associated Gene Name"
+  add_identifiers KEGG.identifiers
+
+  property :follow => :single do |kb,name,annotate=nil|
+    if annotate.nil? or annotate
+      l = kb.children(name, self).target_entity
+      self.annotate l if annotate and kb.source(name) == format
+      l
+    else
+      kb._children(name, self).collect{|v| v.partition("~").last }
     end
   end
 
-  def test_format_Gene
-    TmpFile.with_file do |dir|
-      kb = KnowledgeBase.new dir, "Hsa/jan2013"
-      kb.format["Gene"] = "Ensembl Gene ID"
-
-      kb.register 'nature', NCI.nature_pathways, :merge => true, :target => "UniProt/SwissProt Accession", :key_field => 0
-
-      assert kb.get_database('nature', :persist => false).slice("Ensembl Gene ID").values.flatten.uniq.length > 10
+  property :backtrack => :single do |kb,name,annotate=nil|
+    if annotate.nil? or annotate
+      l = kb.parents(name, self).target_entity
+      self.annotate l if annotate and kb.target(name) == format
+      l
+    else
+      kb._parents(name, self).collect{|v| v.partition("~").last }
     end
   end
 
-  def test_fields
-    TmpFile.with_file do |dir|
-      kb = KnowledgeBase.new dir, "Hsa/jan2013"
-      kb.format["Gene"] = "Ensembl Gene ID"
-
-      kb.register 'nature', NCI.nature_pathways, :merge => true, :fields => [2], :key_field => 0
-      assert kb.get_database('nature', :persist => false).slice("Ensembl Gene ID").values.flatten.uniq.length > 10
+  property :expand => :single do |kb,name,annotate=nil|
+    if annotate.nil? or annotate
+      n = kb.neighbours(name, self)
+      if kb.source(name) == kb.target(name) 
+        self.annotate n.collect{|k,v| v.target}.flatten
+      else
+        n.collect{|k,v| v.target_entity.to_a}.flatten
+      end
+    else
+      n = kb._neighbours(name, self)
+      n.values.flatten.collect{|v| v.partition("~").last}
     end
   end
+end
 
-  def test_global
-    assert @kb.all_databases.include? "pina"
-  end
-
-  def test_subset
-    gene = "TP53"
-    found = Genomics.knowledge_base.identify :pina, gene
-    p53_interactors = Genomics.knowledge_base.children(:pina, found).target_entity 
-
-    assert Genomics.knowledge_base.subset(:pina, {"Gene" => p53_interactors}).target_entity.name.include? "MDM2"
-  end
 
-  def test_syndication
-    kb = KnowledgeBase.new Rbbt.tmp.test.kb2, "Hsa/jan2013"
-    kb.syndicate :genomics, @kb
+class TestKnowledgeBase < Test::Unit::TestCase
 
-    gene = "TP53"
-    found = kb.identify "pina@genomics", gene
-    assert found =~ /ENSG/
+  def test_knowledge_base
+    organism = Organism.default_code("Hsa")
+    TmpFile.with_file do |tmpdir|
+      kb = KnowledgeBase.new tmpdir, Organism.default_code("Hsa")
+      kb.format = {"Gene" => "Ensembl Gene ID"}
+
+      kb.register :tfacts, TFacts.regulators, :source =>"=~Associated Gene Name"
+
+      assert_equal "Ensembl Gene ID", kb.get_database(:tfacts).key_field
+
+      kb.register :kegg, KEGG.gene_pathway, :source_format => "Ensembl Gene ID"
+      assert_match "Ensembl Gene ID", kb.get_database(:kegg).key_field
+
+      gene = Gene.setup("TP53", "Associated Gene Name", organism)
+      assert_equal "TP53", gene.name
+      assert_equal "ENSG00000141510", gene.ensembl
+
+      downstream = gene.follow kb, :tfacts
+      upstream = gene.backtrack kb, :tfacts
+      close = gene.expand kb, :tfacts
+
+      assert downstream.length < downstream.follow(kb, :tfacts,false).flatten.length
+      assert downstream.follow(kb, :tfacts,false).flatten.length < Annotated.flatten(downstream.follow(kb, :tfacts)).follow(kb, :tfacts).flatten.length
+
+      Misc.benchmark(50) do
+        downstream.follow(kb, :tfacts,false)
+        downstream.backtrack(kb, :tfacts,false)
+        downstream.expand(kb, :tfacts,false)
+      end
+
+      Misc.benchmark(50) do
+        downstream.follow(kb, :tfacts)
+        downstream.backtrack(kb, :tfacts)
+        downstream.expand(kb, :tfacts)
+      end
+      
+      Misc.benchmark(50) do
+        downstream.follow(kb, :tfacts, true)
+        downstream.backtrack(kb, :tfacts, true)
+        downstream.expand(kb, :tfacts, true)
+      end
+    end
   end
 end
 

data/test/rbbt/test_monitor.rb

@@ -2,8 +2,6 @@ require File.join(File.expand_path(File.dirname(__FILE__)), '..', 'test_helper.r
 require 'rbbt/monitor'
 
 class TestMonitor < Test::Unit::TestCase
-  def _test_locks
-  end
 end
 
 if __FILE__ == $0

data/test/rbbt/test_packed_index.rb

@@ -2,7 +2,7 @@ require File.join(File.expand_path(File.dirname(__FILE__)), '..', 'test_helper.r
 require 'rbbt/packed_index'
 
 class TestPackedIndex < Test::Unit::TestCase
-  def _test_index
+  def _test_packed_index
 
     TmpFile.with_file do |tmpfile|
       pi = PackedIndex.new tmpfile, true, %w(i i 23s f f f f f)

data/test/rbbt/test_resource.rb

@@ -30,23 +30,23 @@ class TestTSV < Test::Unit::TestCase
       tsv = {"a" => 1, "b" => 2}
       TSV.setup(tsv, :key_field => "Letter", :fields => ["Value"], :type => :single)
     end
-    Log.tsv TestResource.tmp.test.test_tsv.tsv
+    assert TSV === TestResource.tmp.test.test_tsv.tsv
   end
 
-  def _test_rake
+  def test_rake
     TestResource.tmp.test.work.footest.foo.read == "TEST"
     assert TestResource.tmp.test.work.footest.foo.read == "TEST"
   end
 
-  def _test_proc
+  def test_proc
     assert TestResource.tmp.test.proc.read == "PROC TEST"
   end
 
-  def _test_string
+  def test_string
     assert TestResource.tmp.test.string.read == "TEST"
   end
 
-  def _test_url
+  def test_url
     assert TestResource[].tmp.test.google.read =~ /google/
   end
 
@@ -68,7 +68,7 @@ class TestTSV < Test::Unit::TestCase
     assert_equal File.join(ENV['HOME'], '.phgx/etc/foo'), Path.setup('etc/foo', 'phgx').find()
   end
 
-  def _test_libdir
+  def test_libdir
     assert File.exists? TestResource[].share.Rlib["util.R"].find :lib
     assert File.exists? TestResource[].share.Rlib["util.R"].find 
   end

data/test/rbbt/test_tsv.rb

@@ -5,7 +5,7 @@ require 'test/unit'
 
 class TestTSV < Test::Unit::TestCase
 
-  def _test_extend
+  def test_extend
     a = {
       "one" => "1", 
       "two" => "2"
@@ -18,7 +18,7 @@ class TestTSV < Test::Unit::TestCase
     assert_equal "1", a["one"]
   end
   
-  def _test_tsv
+  def test_tsv_1
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -41,7 +41,7 @@ row2    A    B    Id3
     end
   end
 
-  def _test_headerless
+  def test_headerless
     content =<<-EOF
 row1    a|aa|aaa    b    Id1|Id2
 row2    A    B    Id3
@@ -54,7 +54,7 @@ row2    A    B    Id3
     end
   end
 
-  def _test_headerless_fields
+  def test_headerless_fields
     content =<<-EOF
 row1    a|aa|aaa    b    Id1|Id2
 row2    A    B    Id3
@@ -68,7 +68,7 @@ row2    A    B    Id3
     end
   end
 
-  def _test_tsv_persistence
+  def test_tsv_persistence
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -82,19 +82,10 @@ row2    A    B    Id3
       assert_equal :double, tsv.type
       assert_equal "Id", tsv.key_field
       assert TokyoCabinet::HDB === tsv
-
-      FileUtils.rm filename
-      tsv = TSV.open(filename, :sep => /\s+/, :persist =>  true)
-      assert_equal ["a", "aa", "aaa"], tsv["row1"][0]
-      assert_equal ["ValueA", "ValueB", "OtherID"], tsv.fields
-      assert_equal :double, tsv.type
-      assert_equal "Id", tsv.key_field
-      assert TokyoCabinet::HDB === tsv
-
     end
   end
 
-  def _test_tsv_field_selection
+  def test_tsv_field_selection
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -136,7 +127,7 @@ row2    A    B    Id3
     end
   end
 
-  def _test_tsv_cast
+  def test_tsv_cast
     content =<<-EOF
 #Id    Value
 row1    1|2|3
@@ -151,7 +142,7 @@ row2    4
     end
   end
 
-  def _test_tsv_single
+  def test_tsv_single
     content =<<-EOF
 #Id    Value
 row1    1
@@ -168,7 +159,7 @@ row2    4
     end
   end
 
-  def _test_tsv_single_from_flat
+  def test_tsv_single_from_flat
     content =<<-EOF
 #: :type=:flat
 #Id    Value
@@ -183,7 +174,7 @@ row2    4
   end
 
 
-  def _test_tsv_serializer
+  def test_tsv_serializer
     content =<<-EOF
 #Id    Value
 row1    1
@@ -197,7 +188,7 @@ row2    4
     end
   end
 
-  def _test_tsv_header_options
+  def test_tsv_header_options
     content =<<-EOF
 #: :sep=/\\s+/
 #Id Value
@@ -211,7 +202,7 @@ row2    4
     end
   end
 
-  def _test_tsv_fastimport
+  def test_tsv_fastimport
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -228,7 +219,7 @@ row3    AA    B    Id3
     end
   end
 
-  def _test_header_type
+  def test_header_type
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -244,7 +235,7 @@ row3    AA    B    Id3
  
   end
 
-  def _test_single_cast
+  def test_single_cast
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single#:cast=:to_i
 #Id Value
@@ -259,7 +250,7 @@ b 2
     end
   end
 
-  def _test_key_field
+  def test_key_field
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -275,7 +266,7 @@ b 2
     end
   end
 
-  def _test_fix
+  def test_fix
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -289,7 +280,7 @@ b 2
     end
   end
 
-  def _test_select
+  def test_select
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -303,7 +294,7 @@ b 2
     end
   end
 
-  def _test_grep
+  def test_grep
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -317,7 +308,7 @@ b 2
     end
   end
 
-  def _test_grep_invert
+  def test_grep_invert
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -331,7 +322,7 @@ b 2
     end
   end
 
-  def _test_grep_header
+  def test_grep_header
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single#:namespace=Test
 #Id Value
@@ -340,13 +331,13 @@ b 2
     EOF
 
     TmpFile.with_file(content) do |filename|
-      tsv = TSV.open(filename, :key_field => "Value", :grep => "2")
+      tsv = TSV.open(filename, :key_field => "Value", :grep => "#\\|2")
       assert(! tsv.include?("1"))
       assert(tsv.include?("2"))
     end
   end
 
-  def _test_json
+  def test_json
     content =<<-EOF
 #: :sep=/\\s+/#:type=:single
 #Id Value
@@ -361,7 +352,7 @@ b 2
  
   end
 
-  def _test_flat_no_merge
+  def test_flat_no_merge
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -377,7 +368,7 @@ row2    A    B    Id3
     end
   end
 
-  def _test_flat_merge
+  def test_flat_merge
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -404,7 +395,7 @@ row2   b  bbb bbbb bb
     end
   end
 
-  def _test_flat_key
+  def test_flat_key
     content =<<-EOF
 #Id    ValueA 
 row1   a   aa   aaa
@@ -420,7 +411,7 @@ row2   b  bbb bbbb bb aa
 
 
 
-  def _test_zipped
+  def test_zipped
     content =<<-EOF
 #Id    ValueA    ValueB
 row1    a|aa|aaa    b|bb|bbb
@@ -433,7 +424,7 @@ row2    a|aa|aaa    c|cc|ccc
     end
   end
 
-  def _test_named_array_key
+  def test_named_array_key
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -448,7 +439,7 @@ row2    A    B    Id3
  
   end
 
-  def _test_unnamed_key
+  def test_unnamed_key
     content =<<-EOF
 row1    a|aa|aaa    b    Id1|Id2
 row2    A    B    Id3
@@ -461,7 +452,7 @@ row2    A    B    Id3
  
   end
 
-  def _test_float_array
+  def test_float_array
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1   0.2   0.3 0
@@ -476,7 +467,7 @@ row2    0.1  4.5 0
  
   end
 
-  def _test_flat_field_select
+  def test_flat_field_select
     content =<<-EOF
 #: :type=:flat
 #Id    Value
@@ -485,12 +476,11 @@ row2    b  bb bbb
     EOF
 
     TmpFile.with_file(content) do |filename|
-      puts TSV.open(filename, :sep => /\s+/, :key_field => "Value").to_s
       assert TSV.open(filename, :sep => /\s+/, :key_field => "Value").include? "aa"
     end
   end
 
-  def _test_flat2
+  def test_flat2
     content =<<-EOF
 #: :type=:flat
 #Id    Value
@@ -507,7 +497,7 @@ row2    A|AA|AAA
   end
 
 
-  def _test_tsv_flat_double
+  def test_tsv_flat_double
     content =<<-EOF
 #Id    ValueA    ValueB    OtherID
 row1    a|aa|aaa    b    Id1|Id2
@@ -522,7 +512,7 @@ row2    A    B    Id3
     end
   end
 
-  def _test_flat2single
+  def test_flat2single
     content =<<-EOF
 #: :type=:flat
 #Id    Value
@@ -536,7 +526,7 @@ row2    A AA AAA
  
   end
 
-  def _test_shard
+  def test_shard
     shard_function = Proc.new do |key|
       key[-1]
     end

data/test/rbbt/tsv/parallel/test_through.rb

@@ -5,8 +5,7 @@ require 'rbbt/tsv/parallel'
 class TestTSVParallelThrough < Test::Unit::TestCase
 
   def test_pthrough
-    require 'rbbt/sources/organism'
-    tsv = Organism.identifiers("Hsa").tsv :unnamed => true, :persist => false, :fields => ["Associated Gene Name"]
+    tsv = datafile_test('identifiers').tsv :unnamed => true, :persist => false, :fields => ["Associated Gene Name"]
 
     h = {}
     tsv.monitor = true
@@ -21,8 +20,7 @@ class TestTSVParallelThrough < Test::Unit::TestCase
 
 
   def test_ppthrough
-    require 'rbbt/sources/organism'
-    tsv = Organism.identifiers("Hsa").tsv :unnamed => true, :persist => false, :fields => ["Associated Gene Name"]
+    tsv = datafile_test('identifiers').tsv :unnamed => true, :persist => false, :fields => ["Associated Gene Name"]
 
     h = {}