bio 1.4.0 → 1.4.1

data/lib/bio/db/kegg/pathway.rb

@@ -0,0 +1,254 @@
+#
+# = bio/db/kegg/pathway.rb - KEGG PATHWAY database class
+#
+# Copyright::  Copyright (C) 2010 Kozo Nishida <kozo-ni@is.naist.jp>
+# Copyright::  Copyright (C) 2010 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id:$
+#
+
+require 'bio/db'
+require 'bio/db/kegg/common'
+
+module Bio
+class KEGG
+
+# == Description
+#
+# Bio::KEGG::PATHWAY is a parser class for the KEGG PATHWAY database entry.
+#
+# == References
+#
+# * http://www.genome.jp/kegg/pathway.html
+# * ftp://ftp.genome.jp/pub/kegg/pathway/pathway
+#
+class PATHWAY < KEGGDB
+
+  DELIMITER = RS = "\n///\n"
+  TAGSIZE = 12
+
+  include Common::DblinksAsHash
+  # Returns a Hash of the DB name and an Array of entry IDs in DBLINKS field.
+  def dblinks_as_hash; super; end if false #dummy for RDoc
+  alias dblinks dblinks_as_hash
+
+  include Common::PathwaysAsHash
+  # Returns a Hash of the pathway ID and name in PATHWAY field.
+  def pathways_as_hash; super; end if false #dummy for RDoc
+  alias pathways pathways_as_hash
+
+  include Common::OrthologsAsHash
+  # Returns a Hash of the orthology ID and definition in ORTHOLOGY field.
+  def orthologs_as_hash; super; end if false #dummy for RDoc
+  alias orthologs orthologs_as_hash
+
+  include Common::References
+  # REFERENCE -- Returns contents of the REFERENCE records as an Array of
+  # Bio::Reference objects.
+  # ---
+  # *Returns*:: an Array containing Bio::Reference objects
+  def references; super; end if false #dummy for RDoc
+
+  include Common::ModulesAsHash
+  # Returns MODULE field as a Hash.
+  # Each key of the hash is KEGG MODULE ID,
+  # and each value is the name of the Pathway Module.
+  # ---
+  # *Returns*:: Hash
+  def modules_as_hash; super; end if false #dummy for RDoc
+  alias modules modules_as_hash
+
+  #--
+  # for a private method strings_as_hash.
+  #++
+  include Common::StringsAsHash
+
+  # Creates a new Bio::KEGG::PATHWAY object.
+  # ---
+  # *Arguments*:
+  # * (required) _entry_: (String) single entry as a string
+  # *Returns*:: Bio::KEGG::PATHWAY object
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # Return the ID of the pathway, described in the ENTRY line.
+  # ---
+  # *Returns*:: String
+  def entry_id
+    field_fetch('ENTRY')[/\S+/]
+  end
+
+  # Name of the pathway, described in the NAME line.
+  # ---
+  # *Returns*:: String
+  def name
+    field_fetch('NAME')
+  end
+
+  # Description of the pathway, described in the DESCRIPTION line.
+  # ---
+  # *Returns*:: String
+  def description
+    field_fetch('DESCRIPTION')
+  end
+  alias definition description
+
+  # Return the name of the KEGG class, described in the CLASS line.
+  # ---
+  # *Returns*:: String
+  def keggclass
+    field_fetch('CLASS')
+  end
+
+  # Pathways described in the PATHWAY_MAP lines.
+  # ---
+  # *Returns*:: Array containing String
+  def pathways_as_strings
+    lines_fetch('PATHWAY_MAP')
+  end
+
+  # Returns MODULE field of the entry.
+  # ---
+  # *Returns*:: Array containing String objects
+  def modules_as_strings
+    lines_fetch('MODULE')
+  end
+
+  # Disease described in the DISEASE lines.
+  # ---
+  # *Returns*:: Array containing String
+  def diseases_as_strings
+    lines_fetch('DISEASE')
+  end
+
+  # Diseases described in the DISEASE lines.
+  # ---
+  # *Returns*:: Hash of disease ID and its definition
+  def diseases_as_hash
+    unless @diseases_as_hash
+      @diseases_as_hash = strings_as_hash(diseases_as_strings)
+    end
+    @diseases_as_hash
+  end
+  alias diseases diseases_as_hash
+
+  # Returns an Array of a database name and entry IDs in DBLINKS field.
+  # ---
+  # *Returns*:: Array containing String
+  def dblinks_as_strings
+    lines_fetch('DBLINKS')
+  end
+
+  # Orthologs described in the ORTHOLOGY lines.
+  # ---
+  # *Returns*:: Array containing String
+  def orthologs_as_strings
+    lines_fetch('ORTHOLOGY')
+  end
+
+  # Organism described in the ORGANISM line.
+  # ---
+  # *Returns*:: String
+  def organism
+    field_fetch('ORGANISM')
+  end
+
+  # Genes described in the GENE lines.
+  # ---
+  # *Returns*:: Array containing String
+  def genes_as_strings
+    lines_fetch('GENE')
+  end
+
+  # Genes described in the GENE lines.
+  # ---
+  # *Returns*:: Hash of gene ID and its definition
+  def genes_as_hash
+    unless @genes_as_hash
+      @genes_as_hash = strings_as_hash(genes_as_strings)
+    end
+    @genes_as_hash
+  end
+  alias genes genes_as_hash
+
+  # Enzymes described in the ENZYME lines.
+  # ---
+  # *Returns*:: Array containing String
+  def enzymes_as_strings
+    lines_fetch('ENZYME')
+  end
+  alias enzymes enzymes_as_strings
+
+  # Reactions described in the REACTION lines.
+  # ---
+  # *Returns*:: Array containing String
+  def reactions_as_strings
+    lines_fetch('REACTION')
+  end
+
+  # Reactions described in the REACTION lines.
+  # ---
+  # *Returns*:: Hash of reaction ID and its definition
+  def reactions_as_hash
+    unless @reactions_as_hash
+      @reactions_as_hash = strings_as_hash(reactions_as_strings)
+    end
+    @reactions_as_hash
+  end
+  alias reactions reactions_as_hash
+
+  # Compounds described in the COMPOUND lines.
+  # ---
+  # *Returns*:: Array containing String
+  def compounds_as_strings
+    lines_fetch('COMPOUND')
+  end
+
+  # Compounds described in the COMPOUND lines.
+  # ---
+  # *Returns*:: Hash of compound ID and its definition
+  def compounds_as_hash
+    unless @compounds_as_hash
+      @compounds_as_hash = strings_as_hash(compounds_as_strings)
+    end
+    @compounds_as_hash
+  end
+  alias compounds compounds_as_hash
+
+  # Returns REL_PATHWAY field of the entry.
+  # ---
+  # *Returns*:: Array containing String objects
+  def rel_pathways_as_strings
+    lines_fetch('REL_PATHWAY')
+  end
+
+  # Returns REL_PATHWAY field as a Hash. Each key of the hash is
+  # Pathway ID, and each value is the name of the pathway.
+  # ---
+  # *Returns*:: Hash
+  def rel_pathways_as_hash
+    unless defined? @rel_pathways_as_hash then
+      hash = {}
+      rel_pathways_as_strings.each do |line|
+        entry_id, name = line.split(/\s+/, 2)
+        hash[entry_id] = name
+      end
+      @rel_pathways_as_hash = hash
+    end
+    @rel_pathways_as_hash
+  end
+  alias rel_pathways rel_pathways_as_hash
+
+  # KO pathway described in the KO_PATHWAY line.
+  # ---
+  # *Returns*:: String
+  def ko_pathway
+    field_fetch('KO_PATHWAY')
+  end
+
+end # PATHWAY
+
+end # KEGG
+end # Bio

data/lib/bio/db/medline.rb

@@ -32,8 +32,12 @@ class MEDLINE < NCBIDB
     entry.each_line do |line|
       if line =~ /^\w/
         tag = line[0,4].strip
+      else
+        # continuation from previous lines
+        @pubmed[tag] = @pubmed[tag].sub(/(?:\r|\r\n|\n)\z/, ' ')
       end
-      @pubmed[tag] += line[6..-1] if line.length > 6
+      value = line[6..-1]
+      @pubmed[tag] += value if value
     end
   end
   attr_reader :pubmed
@@ -41,7 +45,7 @@ class MEDLINE < NCBIDB
 
   # returns a Reference object.
   def reference
-    hash = Hash.new('')
+    hash = Hash.new
 
     hash['authors']	= authors
     hash['title']	= title

data/lib/bio/io/flatfile/autodetection.rb

@@ -399,6 +399,10 @@ module Bio
 
           litdb    = RuleRegexp[ 'Bio::LITDB',
             /^CODE        [0-9]+$/ ],
+          pathway_module = RuleRegexp[ 'Bio::KEGG::MODULE',
+            /^ENTRY       .+ Pathway\s+Module\s*/ ],
+          pathway  = RuleRegexp[ 'Bio::KEGG::PATHWAY',
+            /^ENTRY       .+ Pathway\s*/ ],
           brite    = RuleRegexp[ 'Bio::KEGG::BRITE',
             /^Entry           [A-Z0-9]+/ ],
           orthology = RuleRegexp[ 'Bio::KEGG::ORTHOLOGY',
@@ -510,6 +514,8 @@ module Bio
         # KEGG
         #aaindex.is_prior_to litdb
         #litdb.is_prior_to brite
+        pathway_module.is_prior_to pathway
+        pathway.is_prior_to brite
         brite.is_prior_to orthology
         orthology.is_prior_to drug
         drug.is_prior_to glycan

data/lib/bio/location.rb

@@ -179,6 +179,28 @@ class Location
     return 0
   end
 
+  # If _other_ is equal with the self, returns true.
+  # Otherwise, returns false.
+  # ---
+  # *Arguments*:
+  # * (required) _other_: any object
+  # *Returns*:: true or false
+  def ==(other)
+    return true if super(other)
+    return false unless other.instance_of?(self.class)
+    flag = false
+    [ :from, :to, :strand, :sequence, :lt, :gt,
+      :xref_id, :carat ].each do |m|
+      begin
+        flag = (self.__send__(m) == other.__send__(m))
+      rescue NoMethodError, ArgumentError, NameError
+        flag = false
+      end
+      break unless flag
+    end
+    flag
+  end
+
 end # Location
 
 # == Description
@@ -350,6 +372,23 @@ class Locations
     end
   end
 
+  # If _other_ is equal with the self, returns true.
+  # Otherwise, returns false.
+  # ---
+  # *Arguments*:
+  # * (required) _other_: any object
+  # *Returns*:: true or false
+  def ==(other)
+    return true if super(other)
+    return false unless other.instance_of?(self.class)
+    if self.locations == other.locations and
+        self.operator == other.operator then
+      true
+    else
+      false
+    end
+  end
+
   # Iterates on each Bio::Location object.
   def each
     @locations.each do |x|

data/lib/bio/reference.rb

@@ -150,6 +150,30 @@ module Bio
       @affiliations = hash['affiliations'] || []
     end
 
+    # If _other_ is equal with the self, returns true.
+    # Otherwise, returns false.
+    # ---
+    # *Arguments*:
+    # * (required) _other_: any object
+    # *Returns*:: true or false
+    def ==(other)
+      return true if super(other)
+      return false unless other.instance_of?(self.class)
+      flag = false
+      [ :authors, :title, :journal, :volume, :issue, :pages,
+        :year, :pubmed, :medline, :doi, :abstract,
+        :url, :mesh, :embl_gb_record_number,
+        :sequence_position, :comments, :affiliations ].each do |m|
+        begin
+          flag = (self.__send__(m) == other.__send__(m))
+        rescue NoMethodError, ArgumentError, NameError
+          flag = false
+        end
+        break unless flag
+      end
+      flag
+    end
+
     # Formats the reference in a given style.
     #
     # Styles:

data/lib/bio/sequence.rb

@@ -72,8 +72,10 @@ class Sequence
   autoload :Format,  'bio/sequence/format'
   autoload :Adapter, 'bio/sequence/adapter'
   autoload :QualityScore, 'bio/sequence/quality_score'
+  autoload :SequenceMasker, 'bio/sequence/sequence_masker'
 
   include Format
+  include SequenceMasker
 
   # Create a new Bio::Sequence object
   #

data/lib/bio/sequence/adapter.rb

@@ -22,6 +22,7 @@ module Bio::Sequence::Adapter
   autoload :GenBank,     'bio/db/genbank/genbank_to_biosequence'
   autoload :EMBL,        'bio/db/embl/embl_to_biosequence'
   autoload :FastaFormat, 'bio/db/fasta/fasta_to_biosequence'
+  autoload :FastaNumericFormat, 'bio/db/fasta/qual_to_biosequence'
   autoload :BioSQL,      'bio/db/biosql/biosql_to_biosequence'
   autoload :SangerChromatogram,
            'bio/db/sanger_chromatogram/chromatogram_to_biosequence'

data/lib/bio/sequence/format.rb

@@ -183,6 +183,20 @@ module Format
     a
   end
 
+  # The same as output(:fasta, :header=>definition, :width=>width)
+  # This method is intended to replace Bio::Sequence#to_fasta.
+  #
+  #   s = Bio::Sequence.new('atgc')
+  #   puts s.output_fasta                   #=> "> \natgc\n"
+  # ---
+  # *Arguments*: 
+  # * (optional) _definition_: (String) definition line
+  # * (optional) _width_: (Integer) width (default 70)
+  # *Returns*:: String object
+  def output_fasta(definition = nil, width = 70)
+    output(:fasta, :header=> definition, :width => width)
+  end
+
   private
 
   # returns formatter repository modules

data/lib/bio/sequence/sequence_masker.rb

@@ -0,0 +1,95 @@
+#
+# = bio/sequence/sequence_masker.rb - Sequence masking helper methods
+#
+# Copyright::  Copyright (C) 2010
+#              Naohisa Goto <ng@bioruby.org>
+# License::    The Ruby License
+#
+# == Description
+# 
+# Bio::Sequence::SequenceMasker is a mix-in module to provide helpful
+# methods for masking a sequence.
+#
+# For details, see documentation of Bio::Sequence::SequenceMasker.
+#
+
+module Bio
+class Sequence
+
+  # Bio::Sequence::SequenceMasker is a mix-in module to provide helpful
+  # methods for masking a sequence.
+  #
+  # It is only expected to be included in Bio::Sequence.
+  # In the future, methods in this module might be moved to
+  # Bio::Sequence or other module and this module might be removed.
+  # Please do not depend on this module.
+  #
+  module SequenceMasker
+
+    # Masks the sequence with each value in the <em>enum</em>.
+    # The <em>enum<em> should be an array or enumerator.
+    # A block must be given. 
+    # When the block returns true, the sequence is masked with
+    # <em>mask_char</em>.
+    # ---
+    # *Arguments*:
+    # * (required) <em>enum</em> : Enumerator
+    # * (required) <em>mask_char</em> : (String) character used for masking
+    # *Returns*:: Bio::Sequence object
+    def mask_with_enumerator(enum, mask_char)
+      offset = 0
+      unit = mask_char.length - 1
+      s = self.seq.class.new(self.seq)
+      j = 0
+      enum.each_with_index do |item, index|
+        if yield item then
+          j = index + offset
+          if j < s.length then
+            s[j, 1] = mask_char
+            offset += unit
+          end
+        end
+      end
+      newseq = self.dup
+      newseq.seq = s
+      newseq
+    end
+
+    # Masks low quality sequence regions.
+    # For each sequence position, if the quality score is smaller than
+    # the threshold, the sequence in the position is replaced with
+    # <em>mask_char</em>.
+    #
+    # Note: This method does not care quality_score_type.
+    # ---
+    # *Arguments*:
+    # * (required) <em>threshold</em> : (Numeric) threshold
+    # * (required) <em>mask_char</em> : (String) character used for masking
+    # *Returns*:: Bio::Sequence object
+    def mask_with_quality_score(threshold, mask_char)
+      scores = self.quality_scores || []
+      mask_with_enumerator(scores, mask_char) do |item|
+        item < threshold
+      end
+    end
+
+    # Masks high error-probability sequence regions.
+    # For each sequence position, if the error probability is larger than
+    # the threshold, the sequence in the position is replaced with
+    # <em>mask_char</em>.
+    #
+    # ---
+    # *Arguments*:
+    # * (required) <em>threshold</em> : (Numeric) threshold
+    # * (required) <em>mask_char</em> : (String) character used for masking
+    # *Returns*:: Bio::Sequence object
+    def mask_with_error_probability(threshold, mask_char)
+      values = self.error_probabilities || []
+      mask_with_enumerator(values, mask_char) do |item|
+        item > threshold
+      end
+    end
+  end #module SequenceMasker
+end #class Sequence
+end #module Bio
+