biointerchange 0.2.2 → 1.0.0

data/lib/biointerchange/so.rb

@@ -13114,6 +13114,156 @@ class SO
     if uri == RDF::URI.new('http://purl.obolibrary.org/obo/SEQUENCE_variant_of') then
       return true
     end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/adjacent_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/associated_with') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/complete_evidence_for_feature') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/connects_on') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/contained_by') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/contains') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/derives_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/disconnected_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/edited_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/edited_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/evidence_for_feature') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/exemplar_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/finished_by') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/finishes') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/gained') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/genome_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/guided_by') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/guides') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/has_integral_part') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/has_origin') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/has_part') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/has_quality') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/homologous_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/integral_part_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/is_consecutive_sequence_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/lost') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/maximally_overlaps') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/member_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/non_functional_homolog_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/orthologous_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/overlaps') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/paralogous_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/part_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/partial_evidence_for_feature') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/position_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/processed_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/processed_into') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/recombined_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/recombined_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/sequence_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/similar_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/started_by') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/starts') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/trans_spliced_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/trans_spliced_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/transcribed_from') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/transcribed_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/translates_to') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/translation_of') then
+      return true
+    end
+    if uri == RDF::URI.new('http://purl.obolibrary.org/obo/variant_of') then
+      return true
+    end
     return false
   end
 

data/lib/biointerchange/textmining/pdfx_xml_reader.rb

@@ -5,6 +5,27 @@ require 'rexml/streamlistener'
 
 class PDFxXMLReader < BioInterchange::TextMining::TMReader
   
+  # Register reader:
+  BioInterchange::Registry.register_reader(
+    'uk.ac.man.pdfx',
+    PDFxXMLReader,
+    [
+      'name',
+      'name_id',
+      'date',
+      [ Proc.new { |*args| BioInterchange::TextMining::TMReader::determine_process(*args) }, 'name_id' ],
+      'version'
+    ],
+    false,
+    'PDFx XML reader',
+    [
+      [ 'date <date>', 'date when the GFF3 file was created (optional)' ],
+      [ 'version <version>', 'version number of resource (optional)' ],
+      [ 'name <name>', 'name of the GFF3 file creator (required)' ],
+      [ 'name_id <id>', 'email address of the GFF3 file creator (required)' ]
+    ]
+  )
+
   # Reads input stream and returns associated +BioInterchange::TextMining::Document+ model
   #
   # Presently I assume a single document per xml file,
@@ -14,8 +35,6 @@ class PDFxXMLReader < BioInterchange::TextMining::TMReader
   #
   # +inputstream+:: Input IO stream to deserialize 
   def deserialize(inputstream)
-    #super(inputstream)
-    
     raise BioInterchange::Exceptions::ImplementationReaderError, 'InputStream not of type IO, cannot read.' unless inputstream.kind_of?(IO) or inputstream.kind_of?(String)
     
     @input = inputstream

data/lib/biointerchange/textmining/pubannos_json_reader.rb

@@ -5,13 +5,36 @@ require 'json'
 
 class PubAnnosJSONReader < BioInterchange::TextMining::TMReader
 
+  # Register reader:
+  BioInterchange::Registry.register_reader(
+    'dbcls.catanns.json',
+    PubAnnosJSONReader,
+    [
+      'name',
+      'name_id',
+      'date',
+      [ Proc.new { |*args| BioInterchange::TextMining::TMReader::determine_process(*args) }, 'name_id' ],
+      'version'
+    ],
+    false,
+    'PDFx XML reader',
+    [
+      [ 'date <date>', 'date when the GFF3 file was created (optional)' ],
+      [ 'version <version>', 'version number of resource (optional)' ],
+      [ 'name <name>', 'name of the GFF3 file creator (required)' ],
+      [ 'name_id <id>', 'email address of the GFF3 file creator (required)' ]
+    ]
+  )
+
+  # Deserialize a PubAnnotations JSON object.
+  #
+  # +inputstream+:: Input IO stream to deserialize 
   def deserialize(inputstream)
     if inputstream.kind_of?(IO) then
       pubannos(inputstream.read)
     elsif inputstream.kind_of?(String) then
       pubannos(inputstream)
     else
-      #else raise exception
       super(inputstream)
     end
   end

data/lib/biointerchange/textmining/text_mining_rdf_ntriples.rb

@@ -6,6 +6,15 @@ module BioInterchange::TextMining
 
 class RDFWriter < BioInterchange::Writer
 
+  # Register writers:
+  BioInterchange::Registry.register_writer(
+    'rdf.bh12.sio',
+    RDFWriter,
+    [ 'dbcls.catanns.json', 'uk.ac.man.pdfx' ],
+    false,
+    'Semanticscience Integrated Ontology (SIO) based text-mining RDFization'
+  )
+
   # Creates a new instance of a RDFWriter that will use the provided output stream to serialize RDF.
   #
   # +ostream+:: instance of an IO class or derivative that is used for RDF serialization

data/lib/biointerchange/textmining/text_mining_reader.rb

@@ -5,16 +5,16 @@ class TMReader < BioInterchange::Reader
   # Create a new instance of a text-mining data reader. Sets @process to a new +BioInterchange::TextMining::Process+ object.
   #
   # +name+:: Name of the process which generated this data
-  # +name_uri+:: URI of the resource that generated this data
+  # +name_id+:: URI of the resource that generated this data
   # +date+:: Optional date of data creation
   # +processtype+:: Type of process that created this content
   # +version+:: Optional version number of resource that created this data (nil if manually curated, for example).
-  def initialize(name, name_uri, date = nil, processtype = BioInterchange::TextMining::Process::UNSPECIFIED, version = nil)
-  
+  def initialize(name, name_id, date = nil, processtype = BioInterchange::TextMining::Process::UNSPECIFIED, version = nil)
+    raise ArgumentError, 'Require "name" and "name_id" options to specify source of annotations (e.g., a manual annotators name, or software tool name) and their associated URI (e.g., email address, or webaddress).' unless name and name_id
+
     metadata = {}
     metadata[BioInterchange::TextMining::Process::VERSION] = version
-    @process = BioInterchange::TextMining::Process.new(name, name_uri, processtype, metadata, date)
-    
+    @process = BioInterchange::TextMining::Process.new(name, name_id, processtype, metadata, date)
   end
   
   

data/spec/phylogenetics_spec.rb

@@ -0,0 +1,79 @@
+
+require 'rubygems'
+require 'rspec'
+require 'bio'
+
+# Turn off verbose reporting here, since class definitions may be loaded multiple
+# times here. That reports that constants have been already been initialized, which
+# is true, but they are only "re-initialized" with the very same values.
+v, $VERBOSE = $VERBOSE, nil
+load 'lib/biointerchange/core.rb'
+load 'lib/biointerchange/cdao.rb'
+load 'lib/biointerchange/reader.rb'
+load 'lib/biointerchange/model.rb'
+load 'lib/biointerchange/writer.rb'
+load 'lib/biointerchange/phylogenetics/newick_reader.rb'
+load 'lib/biointerchange/phylogenetics/tree_set.rb'
+load 'lib/biointerchange/phylogenetics/cdao_rdf_ntriples.rb'
+$VERBOSE = v
+
+describe BioInterchange::Phylogenetics::NewickReader do
+  describe 'deserialization of Newick trees' do
+    it 'empty document' do
+      tree_file = Bio::FlatFile.open(Bio::Newick, StringIO.new(''))
+      trees = 0
+      tree_file.each_entry { |tree| trees += 1 }
+      trees.should eq(0)
+    end
+
+    it 'single Newick tree' do
+      tree_file = Bio::FlatFile.open(Bio::Newick, StringIO.new('(,,(,));'))
+      trees = 0
+      tree_file.each_entry { |newick_tree|
+        trees += 1
+        newick_tree.tree.edges.length.should eq(5)
+        newick_tree.tree.nodes.length.should eq(6)
+      }
+      trees.should eq(1)
+    end
+
+    it 'three Newick trees' do
+      tree_file = Bio::FlatFile.open(Bio::Newick, StringIO.new("(,,(,));\n(A,B,(C,D));\n(A,B,(C,D)E)F;"))
+      trees = 0
+      tree_file.each_entry { |newick_tree|
+        trees += 1
+        newick_tree.tree.edges.length.should eq(5)
+        newick_tree.tree.nodes.length.should eq(6)
+      }
+      trees.should eq(3)
+    end
+
+    it 'model consistency' do
+      model = BioInterchange::Phylogenetics::NewickReader.new().deserialize('(A,B,(C,D,E)F)G;')
+      model.should be_an_instance_of BioInterchange::Phylogenetics::TreeSet
+      model.contents.length.should eq(1)
+      model.contents.first.edges.length.should eq(6)
+      model.contents.first.nodes.length.should eq(7)
+    end
+  end
+end
+
+describe BioInterchange::Phylogenetics::CDAORDFWriter do
+  describe 'serialization of tree models' do
+    it 'empty document' do
+      istream, ostream = IO.pipe
+      BioInterchange::Phylogenetics::CDAORDFWriter.new(ostream).serialize(BioInterchange::Phylogenetics::TreeSet.new())
+      ostream.close
+      istream.read.lines.count.should eq(0)
+    end
+
+    it 'single Newick tree' do
+      istream, ostream = IO.pipe
+      model = BioInterchange::Phylogenetics::NewickReader.new().deserialize('(A,B,(C,D,E)F)G;')
+      BioInterchange::Phylogenetics::CDAORDFWriter.new(ostream).serialize(model)
+      ostream.close
+      istream.read.lines.count.should eq(151)
+    end
+  end
+end
+

data/supplemental/java/biointerchange/pom.xml

@@ -4,7 +4,7 @@
 
   <groupId>org.biointerchange</groupId>
   <artifactId>vocabularies</artifactId>
-  <version>0.2.2</version>
+  <version>1.0.0</version>
   <packaging>jar</packaging>
 
   <name>BioInterchange Vocabularies</name>