bio 1.0.0 → 1.1.0

data/lib/bio/util/restriction_enzyme/range/sequence_range/fragment.rb

@@ -0,0 +1,51 @@
+#
+# bio/util/restriction_enzyme/range/sequence_range/fragment.rb - 
+#
+# Author::    Trevor Wennblom  <mailto:trevor@corevx.com>
+# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
+# License::   The Ruby License
+#
+#  $Id: fragment.rb,v 1.6 2007/07/16 19:28:48 k Exp $
+#
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+class SequenceRange
+
+class Fragment
+
+  attr_reader :size
+
+  def initialize( primary_bin, complement_bin )
+    @primary_bin = primary_bin
+    @complement_bin = complement_bin
+  end
+
+  DisplayFragment = Struct.new(:primary, :complement, :p_left, :p_right, :c_left, :c_right)
+
+  def for_display(p_str=nil, c_str=nil)
+    df = DisplayFragment.new
+    df.primary = ''
+    df.complement = ''
+
+    both_bins = (@primary_bin + @complement_bin).sort.uniq
+    both_bins.each do |item|
+      @primary_bin.include?(item) ? df.primary << p_str[item] : df.primary << ' '
+      @complement_bin.include?(item) ? df.complement << c_str[item] : df.complement << ' '
+    end
+    
+    df.p_left  = @primary_bin.first
+    df.p_right = @primary_bin.last
+    df.c_left  = @complement_bin.first
+    df.c_right = @complement_bin.last
+
+    df
+  end
+end # Fragment
+end # SequenceRange
+end # Range
+end # RestrictionEnzyme
+end # Bio

data/lib/bio/util/restriction_enzyme/range/sequence_range/fragments.rb

@@ -0,0 +1,41 @@
+#
+# bio/util/restriction_enzyme/analysis/fragments.rb - 
+#
+# Author::    Trevor Wennblom  <mailto:trevor@corevx.com>
+# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
+# License::   The Ruby License
+#
+#  $Id: fragments.rb,v 1.5 2007/07/16 19:28:48 k Exp $
+#
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+class SequenceRange
+
+class Fragments < Array
+  
+  attr_accessor :primary
+  attr_accessor :complement
+
+  def initialize(primary, complement)
+    @primary = primary
+    @complement = complement
+  end
+
+  DisplayFragment = Struct.new(:primary, :complement)
+
+  def for_display(p_str=nil, c_str=nil)
+    p_str ||= @primary
+    c_str ||= @complement
+    pretty_fragments = []
+    self.each { |fragment| pretty_fragments << fragment.for_display(p_str, c_str) }
+    pretty_fragments
+  end
+end # Fragments
+end # SequenceRange
+end # Range
+end # RestrictionEnzyme
+end # Bio

data/lib/bio/util/restriction_enzyme/range/vertical_cut_range.rb

@@ -0,0 +1,77 @@
+#
+# bio/util/restriction_enzyme/range/vertical_cut_range.rb - 
+#
+# Author::    Trevor Wennblom  <mailto:trevor@corevx.com>
+# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
+# License::   The Ruby License
+#
+#  $Id: vertical_cut_range.rb,v 1.5 2007/07/16 19:28:48 k Exp $
+#
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+
+# FIXME docs are kind of out of date.  Change this to VerticalAndHorizontalCutRange
+class VerticalCutRange < CutRange
+  attr_reader :p_cut_left, :p_cut_right
+  attr_reader :c_cut_left, :c_cut_right
+  attr_reader :min, :max
+  attr_reader :range
+
+  # VerticalCutRange provides an extremely raw, yet precise, method of
+  # defining the location of cuts on primary and complementary sequences.
+  #
+  # Many VerticalCutRange objects are used with HorizontalCutRange objects
+  # to be contained in CutRanges to define the cut pattern that a
+  # specific enzyme may make.
+  #
+  # VerticalCutRange takes up to four possible cuts, two on the primary
+  # strand and two on the complementary strand.  In typical usage
+  # you will want to make a single cut on the primary strand and a single
+  # cut on the complementary strand.
+  #
+  # However, you can construct it with whatever cuts you desire to accomadate
+  # the most eccentric of imaginary restriction enzymes.
+  #
+  # ---
+  # *Arguments*
+  # * +p_cut_left+: (_optional_) Left-most cut on the primary strand.  +nil+ to skip
+  # * +p_cut_right+: (_optional_) Right-most cut on the primary strand.  +nil+ to skip
+  # * +c_cut_left+: (_optional_) Left-most cut on the complementary strand.  +nil+ to skip
+  # * +c_cut_right+: (_optional_) Right-most cut on the complementary strand.  +nil+ to skip
+  # *Returns*:: nothing
+  def initialize( p_cut_left=nil, p_cut_right=nil, c_cut_left=nil, c_cut_right=nil )
+    @p_cut_left = p_cut_left
+    @p_cut_right = p_cut_right
+    @c_cut_left = c_cut_left
+    @c_cut_right = c_cut_right
+
+    a = [@p_cut_left, @c_cut_left, @p_cut_right, @c_cut_right]
+    a.delete(nil)
+    a.sort!
+    @min = a.first
+    @max = a.last
+
+    @range = nil
+    @range = (@min..@max) unless @min == nil or @max == nil
+    return
+  end
+
+  # Check if a location falls within the minimum or maximum values of this
+  # range.
+  #
+  # ---
+  # *Arguments*
+  # * +i+: Location to check if it is included in the range
+  # *Returns*:: +true+ _or_ +false+
+  def include?(i)
+    return false if @range == nil
+    @range.include?(i)
+  end
+end # VerticalCutRange
+end # Range
+end # RestrictionEnzyme
+end # Bio

data/lib/bio/util/restriction_enzyme/single_strand.rb

@@ -0,0 +1,199 @@
+#
+# bio/util/restriction_enzyme/single_strand.rb - Single strand of a restriction enzyme sequence
+#
+# Author::    Trevor Wennblom  <mailto:trevor@corevx.com>
+# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
+# License::   The Ruby License
+#
+#  $Id: single_strand.rb,v 1.7 2007/07/16 19:28:48 k Exp $
+#
+
+require 'bio/util/restriction_enzyme'
+require 'bio/sequence'
+
+module Bio
+class RestrictionEnzyme
+
+# A single strand of restriction enzyme sequence pattern with a 5' to 3' 
+# orientation.
+#  
+# DoubleStranded puts the SingleStrand and SingleStrandComplement together to 
+# create the sequence pattern with cuts on both strands.
+#
+class SingleStrand < Bio::Sequence::NA
+
+  autoload :CutLocationsInEnzymeNotation, 'bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation'
+
+  include CutSymbol
+  include StringFormatting
+
+  # The cut locations in enzyme notation. Contains a 
+  # CutLocationsInEnzymeNotation object set when the SingleStrand
+  # object is initialized.
+  attr_reader :cut_locations_in_enzyme_notation
+
+  # The cut locations transformed from enzyme index notation to 0-based 
+  # array index notation.  Contains an Array.
+  attr_reader :cut_locations
+
+  # Orientation of the strand, 5' to 3'
+  def orientation; [5,3]; end
+
+  # Constructor for a Bio::RestrictionEnzyme::StingleStrand object.
+  #
+  # A single strand of restriction enzyme sequence pattern with a 5' to 3' orientation.
+  #
+  # ---
+  # *Arguments*
+  # * +sequence+: (_required_) The enzyme sequence.
+  # * +c+: (_optional_) Cut locations in enzyme notation.  
+  #   See Bio::RestrictionEnzyme::SingleStrand::CutLocationsInEnzymeNotation
+  #
+  # *Constraints*
+  # * +sequence+ cannot contain immediately adjacent cut symbols (ex. atg^^c).
+  # * +c+ is in enzyme index notation and therefore cannot contain a 0.
+  # * If +c+ is omitted, +sequence+ must contain a cut symbol.
+  # * You cannot provide both a sequence with cut symbols and provide cut locations - ambiguous.
+  #
+  # +sequence+ must be a kind of:
+  # * String
+  # * Bio::Sequence::NA
+  # * Bio::RestrictionEnzyme::SingleStrand
+  #
+  # +c+ must be a kind of:
+  # * Bio::RestrictionEnzyme::SingleStrand::CutLocationsInEnzymeNotation
+  # * Integer, one or more
+  # * Array
+  #
+  # *Returns*:: nothing
+  def initialize( sequence, *c )
+    c.flatten! # if an array was supplied as an argument
+    validate_args(sequence, c)
+    sequence.downcase!
+    
+    if sequence =~ re_cut_symbol
+      @cut_locations_in_enzyme_notation = CutLocationsInEnzymeNotation.new( strip_padding(sequence) )
+    else
+      @cut_locations_in_enzyme_notation = CutLocationsInEnzymeNotation.new( c )
+    end
+
+    @stripped = Bio::Sequence::NA.new( strip_cuts_and_padding( sequence ) )
+    super( pattern )
+    @cut_locations = @cut_locations_in_enzyme_notation.to_array_index
+    return
+  end
+
+  # Returns true if this enzyme is palindromic with its reverse complement.
+  # Does not report if the +cut_locations+ are palindromic or not.
+  #
+  # Examples:
+  # * This would be palindromic: 
+  #     5' - ATGCAT - 3'
+  #          TACGTA
+  #
+  # * This would not be palindromic: 
+  #     5' - ATGCGTA - 3'
+  #          TACGCAT
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +true+ _or_ +false+
+  def palindromic?
+    @stripped.reverse_complement == @stripped
+  end
+
+  # Sequence pattern with no cut symbols and no 'n' padding.
+  # * <code>SingleStrand.new('garraxt', [-2, 1, 7]).stripped  # => "garraxt"</code>
+  attr_reader :stripped
+
+  # The sequence with 'n' padding and cut symbols.
+  # * <code>SingleStrand.new('garraxt', [-2, 1, 7]).with_cut_symbols  # => "n^ng^arraxt^n"</code>
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: The sequence with 'n' padding and cut symbols.
+  def with_cut_symbols
+    s = pattern
+    @cut_locations_in_enzyme_notation.to_array_index.sort.reverse.each { |c| s.insert(c+1, cut_symbol) }
+    s
+  end
+
+  # The sequence with 'n' padding on the left and right for cuts larger than the sequence.
+  # * <code>SingleStrand.new('garraxt', [-2, 1, 7]).pattern  # => "nngarraxtn"</code>
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: The sequence with 'n' padding on the left and right for cuts larger than the sequence.
+  def pattern
+    return stripped if @cut_locations_in_enzyme_notation.min == nil
+    left = (@cut_locations_in_enzyme_notation.min < 0 ? 'n' * @cut_locations_in_enzyme_notation.min.abs : '')
+
+    # Add one more 'n' if a cut is at the last position 
+    right = ( (@cut_locations_in_enzyme_notation.max >= @stripped.length) ? ('n' * (@cut_locations_in_enzyme_notation.max - @stripped.length + 1)) : '')
+    [left, stripped, right].to_s
+  end
+
+  # The sequence with 'n' pads, cut symbols, and spacing for alignment.
+  # * <code>SingleStrand.new('garraxt', [-2, 1, 7]).with_spaces # => "n^n g^a r r a x t^n"</code>
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: The sequence with 'n' pads, cut symbols, and spacing for alignment.
+  def with_spaces
+    add_spacing( with_cut_symbols )
+  end
+
+  #########
+  protected
+  #########
+
+  def validate_args( input_pattern, input_cut_locations )
+    unless input_pattern.kind_of?(String)
+      err = "input_pattern is not a String, Bio::Sequence::NA, or Bio::RestrictionEnzyme::SingleStrand object\n"
+      err += "pattern: #{input_pattern}\n"
+      err += "class: #{input_pattern.class}"
+      raise ArgumentError, err
+    end
+
+    if ( input_pattern =~ re_cut_symbol ) and !input_cut_locations.empty?
+      err = "Cut symbol found in sequence, but cut locations were also supplied.  Ambiguous.\n"
+      err += "pattern: #{input_pattern}\n"
+      err += "symbol: #{cut_symbol}\n"
+      err += "locations: #{input_cut_locations.inspect}"
+      raise ArgumentError, err
+    end
+
+    input_pattern.each_byte do |c| 
+      c = c.chr.downcase
+      unless Bio::NucleicAcid::NAMES.has_key?(c) or c == 'x' or c == 'X' or c == cut_symbol
+        err = "Invalid character in pattern.\n"
+        err += "Not a nucleotide or representation of possible nucleotides.  See Bio::NucleicAcid::NAMES for more information.\n"
+        err += "char: #{c}\n"
+        err += "input_pattern: #{input_pattern}"
+        raise ArgumentError, err
+      end
+    end
+  end
+
+  # Tadayoshi Funaba's method as discussed in Programming Ruby 2ed, p390
+  def self.once(*ids)
+    for id in ids
+      module_eval <<-"end;"
+        alias_method :__#{id.to_i}__, :#{id.to_s}
+        private :__#{id.to_i}__
+        def #{id.to_s}(*args, &block)
+          (@__#{id.to_i}__ ||= [__#{id.to_i}__(*args, &block)])[0]
+        end
+      end;
+    end
+  end
+
+  once :pattern, :with_cut_symbols, :with_spaces, :to_re
+
+end # SingleStrand
+end # RestrictionEnzyme
+end # Bio

data/lib/bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation.rb

@@ -0,0 +1,135 @@
+#
+# bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation.rb - The cut locations, in enzyme notation
+#
+# Author::    Trevor Wennblom  <mailto:trevor@corevx.com>
+# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
+# License::   The Ruby License
+#
+#  $Id: cut_locations_in_enzyme_notation.rb,v 1.7 2007/07/16 19:28:48 k Exp $
+#
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class SingleStrand
+
+# Stores the cut location in thier enzyme index notation
+# 
+# May be initialized with a series of cuts or an enzyme pattern marked
+# with cut symbols.
+# 
+# Enzyme index notation:: 1.._n_, value before 1 is -1
+#
+# example:: [-3][-2][-1][1][2][3][4][5]
+#
+# Negative values are used to indicate when a cut may occur at a specified
+# distance before the sequence begins.  This would be padded with 'n'
+# nucleotides to represent wildcards.
+# 
+# Notes:
+# * <code>0</code> is invalid as it does not refer to any index 
+# * +nil+ is not allowed here as it has no meaning
+# * +nil+ values are kept track of in DoubleStranded::CutLocations as they
+#   need a reference point on the correlating strand.  In 
+#   DoubleStranded::CutLocations +nil+ represents no cut or a partial 
+#   digestion.
+# 
+class CutLocationsInEnzymeNotation < Array
+  include CutSymbol
+  extend CutSymbol
+
+  # First cut, in enzyme-index notation
+  attr_reader :min
+  
+  # Last cut, in enzyme-index notation
+  attr_reader :max
+
+  # Constructor for CutLocationsInEnzymeNotation
+  #
+  # ---
+  # *Arguments*
+  # * +a+: Locations of cuts represented as a string with cuts or an array of values
+  # Examples:
+  # * n^ng^arraxt^n
+  # * 2
+  # * -1, 5
+  # * [-1, 5]
+  # *Returns*:: nothing
+  def initialize(*a)
+    a.flatten! # in case an array was passed as an argument
+
+    if a.size == 1 and a[0].kind_of? String and a[0] =~ re_cut_symbol
+      # Initialize with a cut symbol pattern such as 'n^ng^arraxt^n'
+      s = a[0]
+      a = []
+      i = -( s.tr(cut_symbol, '') =~ %r{[^n]} )  # First character that's not 'n'
+      s.each_byte { |c| (a << i; next) if c.chr == cut_symbol; i += 1 }
+      a.collect! { |n| n <= 0 ? n-1 : n } # 0 is not a valid enzyme index, decrement from 0 and all negative
+    else
+      a.collect! { |n| n.to_i } # Cut locations are always integers
+    end
+
+    validate_cut_locations( a )
+    super(a)
+    self.sort!
+    @min = self.first
+    @max = self.last
+    self.freeze
+  end
+
+  # Transform the cut locations from enzyme index notation to 0-based index
+  # notation.
+  #
+  #   input -> output
+  #   [  1, 2, 3 ] -> [ 0, 1, 2 ]
+  #   [  1, 3, 5 ] -> [ 0, 2, 4 ]
+  #   [ -1, 1, 2 ] -> [ 0, 1, 2 ]
+  #   [ -2, 1, 3 ] -> [ 0, 2, 4 ]
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +Array+ of cuts in 0-based index notation
+  def to_array_index
+    return [] if @min == nil
+    if @min < 0
+      calc = lambda do |n| 
+        n -= 1 unless n < 0
+        n + @min.abs
+      end
+    else
+      calc = lambda { |n| n - 1 }
+    end
+    self.collect(&calc)
+  end
+
+  #########
+  protected
+  #########
+
+  def validate_cut_locations( input_cut_locations )
+    unless input_cut_locations == input_cut_locations.uniq
+      err = "The cut locations supplied contain duplicate values.  Redundant / undefined meaning.\n"
+      err += "cuts: #{input_cut_locations.inspect}\n"
+      err += "unique: #{input_cut_locations.uniq.inspect}"
+      raise ArgumentError, err
+    end
+
+    if input_cut_locations.include?(nil)
+      err = "The cut locations supplied contained a nil.  nil has no index for enzyme notation, alternative meaning is 'no cut'.\n"
+      err += "cuts: #{input_cut_locations.inspect}"
+      raise ArgumentError, err
+    end
+
+    if input_cut_locations.include?(0)
+      err = "The cut locations supplied contained a '0'.  '0' has no index for enzyme notation, alternative meaning is 'no cut'.\n"
+      err += "cuts: #{input_cut_locations.inspect}"
+      raise ArgumentError, err
+    end
+
+  end
+end # CutLocationsInEnzymeNotation
+end # SingleStrand
+end # RestrictionEnzyme
+end # Bio