wwood-bioruby 1.2.11

data/lib/bio/db/genbank/ddbj.rb

@@ -0,0 +1,22 @@
+#
+# = bio/db/genbank/ddbj.rb - DDBJ database class
+#
+# Copyright::  Copyright (C) 2000-2004 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: ddbj.rb,v 1.9 2007/04/05 23:35:40 trevor Exp $
+#
+
+require 'bio/db/genbank/genbank'
+
+module Bio
+
+class DDBJ < GenBank
+
+  autoload :XML,          'bio/io/ddbjxml'
+
+  # Nothing to do (DDBJ database format is completely same as GenBank)
+
+end # DDBJ
+
+end # Bio

data/lib/bio/db/genbank/format_genbank.rb

@@ -0,0 +1,187 @@
+#
+# = bio/db/genbank/format_genbank.rb - GenBank format generater
+#
+# Copyright::  Copyright (C) 2008 Naohisa Goto <ng@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: format_genbank.rb,v 1.1.2.5 2008/06/17 15:59:24 ngoto Exp $
+#
+
+require 'bio/sequence/format'
+
+module Bio::Sequence::Format::NucFormatter
+
+  # INTERNAL USE ONLY, YOU SHOULD NOT USE THIS CLASS.
+  # GenBank format output class for Bio::Sequence.
+  class Genbank < Bio::Sequence::Format::FormatterBase
+
+    # helper methods
+    include Bio::Sequence::Format::INSDFeatureHelper
+    
+    private
+
+    # string wrapper for GenBank format
+    def genbank_wrap(str)
+      wrap(str.to_s, 67).gsub(/\n/, "\n" + " " * 12)
+    end
+
+    # string wrap with adding a dot at the end of the string
+    def genbank_wrap_dot(str)
+      str = str.to_s
+      str = str + '.' unless /\.\z/ =~ str
+      genbank_wrap(str)
+    end
+
+    # Given words (an Array of String) are wrapping with EMBL style.
+    # Each word is never splitted inside the word.
+    def genbank_wrap_words(array)
+      width = 67
+      result = []
+      str = nil
+      array.each do |x|
+        if str then
+          if str.length + 1 + x.length > width then
+            str = nil
+          else
+            str.concat ' '
+            str.concat x
+          end
+        end
+        unless str then
+          str = "#{x}"
+          result.push str
+        end
+      end
+      result.join("\n" + " " * 12)
+    end
+
+    # formats references
+    def reference_format_genbank(ref, num)
+      pos = ref.sequence_position.to_s.gsub(/\s/, '')
+      pos.gsub!(/(\d+)\-(\d+)/, "\\1 to \\2")
+      pos.gsub!(/\s*\,\s*/, '; ')
+      if pos.empty?
+        pos = ''
+      else
+        pos = " (bases #{pos})"
+      end
+      volissue = "#{ref.volume.to_s}"
+      volissue += " (#{ref.issue})" unless ref.issue.to_s.empty? 
+      journal = "#{ref.journal.to_s}"
+      journal += " #{volissue}" unless volissue.empty? 
+      journal += ", #{ref.pages}" unless ref.pages.to_s.empty?
+      journal += " (#{ref.year})" unless ref.year.to_s.empty?
+
+      alist = ref.authors.collect do |x|
+        y = x.to_s.strip.split(/\, *([^\,]+)\z/)
+        y[1].gsub!(/\. +/, '.') if y[1]
+        y.join(',')
+      end
+      lastauthor = alist.pop
+      last2author = alist.pop
+      alist.each { |x| x.concat ',' }
+      alist.push last2author if last2author
+      alist.push "and" unless alist.empty?
+      alist.push lastauthor.to_s
+      result = <<__END_OF_REFERENCE__
+REFERENCE   #{ genbank_wrap(sprintf('%-2d%s', num, pos))}
+  AUTHORS   #{ genbank_wrap_words(alist) }
+  TITLE     #{ genbank_wrap(ref.title.to_s) }
+  JOURNAL   #{ genbank_wrap(journal) }
+__END_OF_REFERENCE__
+      unless ref.pubmed.to_s.empty? then
+        result.concat "   PUBMED   #{ genbank_wrap(ref.pubmed) }\n"
+      end
+      if ref.comments and !(ref.comments.empty?) then
+        ref.comments.each do |c|
+          result.concat "  REMARK    #{ genbank_wrap(c) }\n"
+        end
+      end
+      result
+    end
+
+    # formats comments lines as GenBank
+    def comments_format_genbank(cmnts)
+      return '' if !cmnts or cmnts.empty?
+      cmnts = [ cmnts ] unless cmnts.kind_of?(Array)
+      a = []
+      cmnts.each do |str|
+        a.push "COMMENT     #{ genbank_wrap(str) }\n"
+      end
+      a.join('')
+    end
+
+    # formats sequence lines as GenBank
+    def seq_format_genbank(str)
+      i = 1
+      result = str.gsub(/.{1,60}/) do |s|
+        s = s.gsub(/.{1,10}/, ' \0')
+        y = sprintf("%9d%s\n", i, s)
+        i += 60
+        y
+      end
+      result
+    end
+
+    # formats date
+    def date_format_genbank
+      date_modified || date_created || null_date
+    end
+
+    # moleculue type
+    def mol_type_genbank
+      if /(DNA|(t|r|m|u|sn|sno)?RNA)/i =~ molecule_type.to_s then
+        $1.sub(/[DR]NA/) { |x| x.upcase }
+      else
+        'NA'
+      end
+    end
+
+    # NCBI GI number
+    def ncbi_gi_number
+      ids = other_seqids
+      if ids and r = ids.find { |x| x.database == 'GI' } then
+        r.id
+      else
+        nil
+      end
+    end
+
+    # strandedness
+    def strandedness_genbank
+      return nil unless strandedness
+      case strandedness
+      when 'single'; 'ss-'; 
+      when 'double'; 'ds-'; 
+      when 'mixed';  'ms-'; 
+      else; nil
+      end
+    end
+
+    # Erb template of GenBank format for Bio::Sequence
+    erb_template <<'__END_OF_TEMPLATE__'
+LOCUS       <%= sprintf("%-16s", entry_id) %> <%= sprintf("%11d", length) %> bp <%= sprintf("%3s", strandedness_genbank) %><%= sprintf("%-6s", mol_type_genbank) %>  <%= sprintf("%-8s", topology) %><%= sprintf("%4s", division) %> <%= date_format_genbank %>
+DEFINITION  <%= genbank_wrap_dot(definition.to_s) %>
+ACCESSION   <%= genbank_wrap(([ primary_accession ] + (secondary_accessions or [])).join(" ")) %>
+VERSION     <%= primary_accession %>.<%= sequence_version %><% if gi = ncbi_gi_number then %>  GI:<%= gi %><% end %>
+KEYWORDS    <%= genbank_wrap_dot((keywords or []).join('; ')) %>
+SOURCE      <%= genbank_wrap(species) %>
+  ORGANISM  <%= genbank_wrap(species) %>
+            <%= genbank_wrap_dot((classification or []).join('; ')) %>
+<% 
+    n = 0
+    (references or []).each do |ref|
+      n += 1
+%><%= reference_format_genbank(ref, n) %><%
+    end
+%><%= comments_format_genbank(comments)
+%>FEATURES             Location/Qualifiers
+<%= format_features_genbank(features || [])
+ %>ORIGIN
+<%= seq_format_genbank(seq)
+ %>//
+__END_OF_TEMPLATE__
+
+  end #class Genbank
+end #module Bio::Sequence::Format::NucFormatter
+

data/lib/bio/db/genbank/genbank.rb

@@ -0,0 +1,250 @@
+#
+# = bio/db/genbank/genbank.rb - GenBank database class
+#
+# Copyright::  Copyright (C) 2000-2005 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: genbank.rb,v 0.40.2.4 2008/06/17 15:56:18 ngoto Exp $
+#
+
+require 'date'
+require 'bio/db'
+require 'bio/db/genbank/common'
+require 'bio/sequence'
+require 'bio/sequence/dblink'
+
+module Bio
+
+# == Description
+#
+# Parses a GenBank formatted database entry
+#
+# == Example
+#
+#   # entry is a string containing only one entry contents
+#   gb = Bio::GenBank.new(entry)
+#
+class GenBank < NCBIDB
+
+  include Bio::NCBIDB::Common
+
+  # Parses the LOCUS line and returns contents of the LOCUS record
+  # as a Bio::GenBank::Locus object.  Locus object is created automatically
+  # when Bio::GenBank#locus, entry_id etc. methods are called.
+  class Locus
+    def initialize(locus_line)
+      if locus_line.empty?
+        # do nothing (just for empty or incomplete entry string)
+      elsif locus_line.length > 75 			# after Rel 126.0
+        @entry_id = locus_line[12..27].strip
+        @length   = locus_line[29..39].to_i
+        @strand   = locus_line[44..46].strip
+        @natype   = locus_line[47..52].strip
+        @circular = locus_line[55..62].strip
+        @division = locus_line[63..66].strip
+        @date     = locus_line[68..78].strip
+      else
+        @entry_id = locus_line[12..21].strip
+        @length   = locus_line[22..29].to_i
+        @strand   = locus_line[33..35].strip
+        @natype   = locus_line[36..39].strip
+        @circular = locus_line[42..51].strip
+        @division = locus_line[52..54].strip
+        @date     = locus_line[62..72].strip
+      end
+    end
+    attr_accessor :entry_id, :length, :strand, :natype, :circular,
+      :division, :date
+  end
+
+  # Accessor methods for the contents of the LOCUS record.
+
+  def locus
+    @data['LOCUS'] ||= Locus.new(get('LOCUS'))
+  end
+
+  def entry_id;  locus.entry_id;  end
+  def length;    locus.length;    end
+  def circular;  locus.circular;  end
+  def division;  locus.division;  end
+  def date;      locus.date;      end
+
+  def strand;    locus.strand;    end
+  def natype;    locus.natype;    end
+
+
+  # FEATURES -- Iterate only for the 'CDS' portion of the Bio::Features.
+  def each_cds
+    features.each do |feature|
+      if feature.feature == 'CDS'
+        yield(feature)
+      end
+    end
+  end
+
+  # FEATURES -- Iterate only for the 'gene' portion of the Bio::Features.
+  def each_gene
+    features.each do |feature|
+      if feature.feature == 'gene'
+        yield(feature)
+      end
+    end
+  end
+
+
+  # BASE COUNT (this field is obsoleted after GenBank release 138.0) --
+  # Returns the BASE COUNT as a Hash.  When the base is specified, returns
+  # count of the base as a Fixnum.  The base can be one of 'a', 't', 'g',
+  # 'c', and 'o' (others).
+  def basecount(base = nil)
+    unless @data['BASE COUNT']
+      hash = Hash.new(0)
+      get('BASE COUNT').scan(/(\d+) (\w)/).each do |c, b|
+        hash[b] = c.to_i
+      end
+      @data['BASE COUNT'] = hash
+    end
+
+    if base
+      base.downcase!
+      @data['BASE COUNT'][base]
+    else
+      @data['BASE COUNT']
+    end
+  end
+
+  # ORIGIN -- Returns DNA sequence in the ORIGIN record as a
+  # Bio::Sequence::NA object.
+  def seq
+    unless @data['SEQUENCE']
+      origin
+    end
+    Bio::Sequence::NA.new(@data['SEQUENCE'])
+  end
+  alias naseq seq
+  alias nalen length
+
+  # (obsolete???) length of the sequence
+  def seq_len
+    seq.length
+  end
+
+  # modified date. Returns Date object, String or nil.
+  def date_modified
+    begin
+      Date.parse(self.date)
+    rescue ArgumentError, TypeError, NoMethodError, NameError
+      self.date
+    end
+  end
+
+  # Taxonomy classfication. Returns an array of strings.
+  def classification
+    self.taxonomy.to_s.sub(/\.\z/, '').split(/\s*\;\s*/)
+  end
+
+  # Strandedness. Returns one of 'single', 'double', 'mixed', or nil.
+  def strandedness
+    case self.strand.to_s.downcase
+    when 'ss-'; 'single'
+    when 'ds-'; 'double'
+    when 'ms-'; 'mixed'
+    else nil; end
+  end
+
+  # converts Bio::GenBank to Bio::Sequence
+  # ---
+  # *Arguments*: 
+  # *Returns*:: Bio::Sequence object
+  def to_biosequence
+    Bio::Sequence.adapter(self, Bio::Sequence::Adapter::GenBank)
+  end
+
+end # GenBank
+end # Bio
+
+
+
+if __FILE__ == $0
+
+  begin
+    require 'pp'
+    alias p pp
+  rescue LoadError
+  end
+
+  puts "### GenBank"
+  if ARGV.size > 0
+    gb = Bio::GenBank.new(ARGF.read)
+  else
+    require 'bio/io/fetch'
+    gb = Bio::GenBank.new(Bio::Fetch.query('gb', 'LPATOVGNS'))
+  end
+
+  puts "## LOCUS"
+  puts "# GenBank.locus"
+  p gb.locus
+  puts "# GenBank.entry_id"
+  p gb.entry_id
+  puts "# GenBank.nalen"
+  p gb.nalen
+  puts "# GenBank.strand"
+  p gb.strand
+  puts "# GenBank.natype"
+  p gb.natype
+  puts "# GenBank.circular"
+  p gb.circular
+  puts "# GenBank.division"
+  p gb.division
+  puts "# GenBank.date"
+  p gb.date
+
+  puts "## DEFINITION"
+  p gb.definition
+
+  puts "## ACCESSION"
+  p gb.accession
+
+  puts "## VERSION"
+  p gb.versions
+  p gb.version
+  p gb.gi
+
+  puts "## NID"
+  p gb.nid
+
+  puts "## KEYWORDS"
+  p gb.keywords
+
+  puts "## SEGMENT"
+  p gb.segment
+
+  puts "## SOURCE"
+  p gb.source
+  p gb.common_name
+  p gb.vernacular_name
+  p gb.organism
+  p gb.taxonomy
+
+  puts "## REFERENCE"
+  p gb.references
+
+  puts "## COMMENT"
+  p gb.comment
+
+  puts "## FEATURES"
+  p gb.features
+
+  puts "## BASE COUNT"
+  p gb.basecount
+  p gb.basecount('a')
+  p gb.basecount('A')
+
+  puts "## ORIGIN"
+  p gb.origin
+  p gb.naseq
+
+end
+
+
+