bio-restriction_enzyme 1.0.0

data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair_in_enzyme_notation.rb

@@ -0,0 +1,30 @@
+# bio/util/restriction_enzyme/double_stranded/cut_location_pair_in_enzyme_notation.rb - Inherits from DoubleStranded::CutLocationPair
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class DoubleStranded
+
+# Inherits from DoubleStranded::CutLocationPair , stores the cut location pair in
+# enzyme notation instead of 0-based.
+#
+class CutLocationPairInEnzymeNotation < CutLocationPair
+
+  #########
+  protected
+  #########
+
+  def validate_2( a, b )
+    if (a == 0) or (b == 0)
+      raise ArgumentError, "Enzyme index notation only.  0 values are illegal."
+    end
+
+    if a == nil and b == nil
+      raise ArgumentError, "Neither strand has a cut.  Ambiguous."
+    end
+  end
+end # CutLocationPair
+end # DoubleStranded
+end # RestrictionEnzyme
+end # Bio

data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations.rb

@@ -0,0 +1,68 @@
+# bio/util/restriction_enzyme/double_stranded/cut_locations.rb - Contains an Array of CutLocationPair objects
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class DoubleStranded
+
+# Contains an +Array+ of CutLocationPair objects.
+#
+class CutLocations < Array
+
+  # CutLocations constructor.
+  #
+  # Contains an +Array+ of CutLocationPair objects.
+  #
+  # Example:
+  #   clp1 = CutLocationPair.new(3,2)
+  #   clp2 = CutLocationPair.new(7,9)
+  #   pairs = CutLocations.new(clp1, clp2)
+  #
+  # ---
+  # *Arguments*
+  # * +args+: Any number of +CutLocationPair+ objects
+  # *Returns*:: nothing
+  def initialize(*args)
+    validate_args(args)
+    super(args)
+  end
+
+  # Returns an +Array+ of locations of cuts on the primary strand
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +Array+ of locations of cuts on the primary strand
+  def primary
+    self.collect {|a| a[0]}
+  end
+
+  # Returns an +Array+ of locations of cuts on the complementary strand
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +Array+ of locations of cuts on the complementary strand
+  def complement
+    self.collect {|a| a[1]}
+  end
+
+  #########
+  protected
+  #########
+
+  def validate_args(args)
+    args.each do |a|
+      unless a.class == Bio::RestrictionEnzyme::DoubleStranded::CutLocationPair
+        err = "Not a CutLocationPair\n"
+        err += "class: #{a.class}\n"
+        err += "inspect: #{a.inspect}"
+        raise ArgumentError, err
+      end
+    end
+  end
+end # CutLocations
+end # DoubleStranded
+end # RestrictionEnzyme
+end # Bio

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

@@ -0,0 +1,99 @@
+# bio/util/restriction_enzyme/double_stranded/cut_locations_in_enzyme_notation.rb - Inherits from DoubleStrand::CutLocations
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class DoubleStranded
+
+# Inherits from DoubleStranded::CutLocations.  Contains CutLocationPairInEnzymeNotation objects.
+# Adds helper methods to convert from enzyme index notation to 0-based array index notation.
+#
+class CutLocationsInEnzymeNotation < CutLocations
+
+  # Returns +Array+ of locations of cuts on the primary
+  # strand in 0-based array index notation.
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +Array+ of locations of cuts on the primary strand in 0-based array index notation.
+  def primary_to_array_index
+    helper_for_to_array_index(self.primary)
+  end
+
+  # Returns +Array+ of locations of cuts on the complementary
+  # strand in 0-based array index notation.
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +Array+ of locations of cuts on the complementary strand in 0-based array index notation.
+  def complement_to_array_index
+    helper_for_to_array_index(self.complement)
+  end
+
+  # Returns the contents of the present CutLocationsInEnzymeNotation object as
+  # a CutLocations object with the contents converted from enzyme notation
+  # to 0-based array index notation.
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: +CutLocations+
+  def to_array_index
+    unless self.primary_to_array_index.size == self.complement_to_array_index.size
+      err = "Primary and complement strand cut locations are not available in equal numbers.\n"
+      err += "primary: #{self.primary_to_array_index.inspect}\n"
+      err += "primary.size: #{self.primary_to_array_index.size}\n"
+      err += "complement: #{self.complement_to_array_index.inspect}\n"
+      err += "complement.size: #{self.complement_to_array_index.size}"
+      raise IndexError, err
+    end
+    a = self.primary_to_array_index.zip(self.complement_to_array_index)
+    CutLocations.new( *a.collect {|cl| CutLocationPair.new(cl)} )
+  end
+
+  #########
+  protected
+  #########
+
+  def helper_for_to_array_index(a)
+    minimum = (self.primary + self.complement).flatten
+    minimum.delete(nil)
+    minimum = minimum.sort.first
+
+    return [] if minimum == nil  # no elements
+
+    if minimum < 0
+      calc = lambda do |n|
+        unless n == nil
+          n -= 1 unless n < 0
+          n += minimum.abs
+        end
+        n
+      end
+    else
+      calc = lambda do |n|
+        n -= 1 unless n == nil
+        n
+      end
+    end
+
+    a.collect(&calc)
+  end
+
+  def validate_args(args)
+    args.each do |a|
+      unless a.class == Bio::RestrictionEnzyme::DoubleStranded::CutLocationPairInEnzymeNotation
+        err = "Not a CutLocationPairInEnzymeNotation\n"
+        err += "class: #{a.class}\n"
+        err += "inspect: #{a.inspect}"
+        raise TypeError, err
+      end
+    end
+  end
+end # CutLocationsInEnzymeNotation
+end # DoubleStranded
+end # RestrictionEnzyme
+end # Bio

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

@@ -0,0 +1,16 @@
+# bio/util/restriction_enzyme/range/cut_range.rb - Abstract base class for HorizontalCutRange and VerticalCutRange
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+
+# Abstract base class for HorizontalCutRange and VerticalCutRange
+#
+class CutRange
+end # CutRange
+
+end # Range
+end # RestrictionEnzyme
+end # Bio

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

@@ -0,0 +1,39 @@
+# bio/util/restriction_enzyme/range/cut_ranges.rb - Container for many CutRange objects or CutRange child objects.
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+
+# Container for many CutRange objects or CutRange child objects.  Inherits from array.
+#
+class CutRanges < Array
+  def min; self.collect{|a| a.min}.flatten.sort.first; end
+  def max; self.collect{|a| a.max}.flatten.sort.last; end
+  def include?(i); self.collect{|a| a.include?(i)}.include?(true); end
+
+  def min_vertical
+    vertical_min_max_helper( :min )
+  end
+
+  def max_vertical
+    vertical_min_max_helper( :max )
+  end
+
+  protected
+
+  def vertical_min_max_helper( sym_which )
+    tmp = []
+    self.each do |a|
+      next unless a.class == Bio::RestrictionEnzyme::Range::VerticalCutRange
+      tmp << a.send( sym_which )
+    end
+    z = (sym_which == :max) ? :last : :first
+    tmp.flatten.sort.send(z)
+  end
+
+end # CutRanges
+end # Range
+end # RestrictionEnzyme
+end # Bio

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

@@ -0,0 +1,59 @@
+# bio/util/restriction_enzyme/range/horizontal_cut_range.rb -
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+
+class HorizontalCutRange < CutRange
+  attr_reader :p_cut_left, :p_cut_right
+  attr_reader :c_cut_left, :c_cut_right
+  attr_reader :min, :max
+  attr_reader :hcuts
+
+  def initialize( left, right=left )
+    raise "left > right" if left > right
+
+    # The 'range' here is actually off by one on the left
+    # side in relation to a normal CutRange, so using the normal
+    # variables from CutRange would result in bad behavior.
+    #
+    # See below - the first horizontal cut is the primary cut plus one.
+    #
+    #    1 2 3 4 5 6 7
+    #    G A|T T A C A
+    #       +-----+
+    #    C T A A T|G T
+    #    1 2 3 4 5 6 7
+    #
+    # Primary cut = 2
+    # Complement cut = 5
+    # Horizontal cuts = 3, 4, 5
+
+    @p_cut_left = nil
+    @p_cut_right = nil
+    @c_cut_left = nil
+    @c_cut_right = nil
+    @min = left  # NOTE this used to be 'nil', make sure all tests work
+    @max = right # NOTE this used to be 'nil', make sure all tests work
+    @range = (@min..@max) unless @min == nil or @max == nil # NOTE this used to be 'nil', make sure all tests work
+
+
+    @hcuts = (left..right)
+  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)
+    @range.include?(i)
+  end
+end # HorizontalCutRange
+end # Range
+end # RestrictionEnzyme
+end # Bio

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

@@ -0,0 +1,249 @@
+# bio/util/restriction_enzyme/range/sequence_range.rb - A defined range over a nucleotide sequence
+
+require 'bio/util/restriction_enzyme'
+
+module Bio
+class RestrictionEnzyme
+class Range
+
+  autoload :CutRange,                'bio/util/restriction_enzyme/range/cut_range'
+  autoload :CutRanges,               'bio/util/restriction_enzyme/range/cut_ranges'
+  autoload :HorizontalCutRange,      'bio/util/restriction_enzyme/range/horizontal_cut_range'
+  autoload :VerticalCutRange,        'bio/util/restriction_enzyme/range/vertical_cut_range'
+
+# A defined range over a nucleotide sequence.
+#
+# This class accomadates having cuts defined on a sequence and returning the
+# fragments made by those cuts.
+class SequenceRange
+
+  autoload :Fragment,                'bio/util/restriction_enzyme/range/sequence_range/fragment'
+  autoload :Fragments,               'bio/util/restriction_enzyme/range/sequence_range/fragments'
+  autoload :CalculatedCuts,          'bio/util/restriction_enzyme/range/sequence_range/calculated_cuts'
+
+  # Left-most index of primary strand
+  attr_reader :p_left
+
+  # Right-most index of primary strand
+  attr_reader :p_right
+
+  # Left-most index of complementary strand
+  attr_reader :c_left
+
+  # Right-most index of complementary strand
+  attr_reader :c_right
+
+  # Left-most index of DNA sequence
+  attr_reader :left
+
+  # Right-most index of DNA sequence
+  attr_reader :right
+
+  # Size of DNA sequence
+  attr_reader :size
+
+  # CutRanges in this SequenceRange
+  attr_reader :cut_ranges
+
+  def initialize( p_left = nil, p_right = nil, c_left = nil, c_right = nil )
+    raise ArgumentError if p_left == nil and c_left == nil
+    raise ArgumentError if p_right == nil and c_right == nil
+    (raise ArgumentError unless p_left <= p_right) unless p_left == nil or p_right == nil
+    (raise ArgumentError unless c_left <= c_right) unless c_left == nil or c_right == nil
+
+    @p_left, @p_right, @c_left, @c_right = p_left, p_right, c_left, c_right
+    @left = [p_left, c_left].compact.sort.first
+    @right = [p_right, c_right].compact.sort.last
+    @size = (@right - @left) + 1 unless @left == nil or @right == nil
+    @cut_ranges = CutRanges.new
+    @__fragments_current = false
+  end
+
+
+  # If the first object is HorizontalCutRange or VerticalCutRange, that is
+  # added to the SequenceRange.  Otherwise this method
+  # builds a VerticalCutRange object and adds it to the SequenceRange.
+  #
+  # Note:
+  # Cut occurs immediately after the index supplied.
+  # For example, a cut at '0' would mean a cut occurs between bases 0 and 1.
+  #
+  # ---
+  # *Arguments*
+  # * +p_cut_left+: (_optional_) Left-most cut on the primary strand *or* a CutRange object.  +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 add_cut_range( p_cut_left=nil, p_cut_right=nil, c_cut_left=nil, c_cut_right=nil )
+    @__fragments_current = false
+    if p_cut_left.kind_of? CutRange # shortcut
+      @cut_ranges << p_cut_left
+    else
+      [p_cut_left, p_cut_right, c_cut_left, c_cut_right].each { |n| (raise IndexError unless n >= @left and n <= @right) unless n == nil }
+      @cut_ranges << VerticalCutRange.new( p_cut_left, p_cut_right, c_cut_left, c_cut_right )
+    end
+  end
+
+  # Add a series of CutRange objects (HorizontalCutRange or VerticalCutRange).
+  #
+  # ---
+  # *Arguments*
+  # * +cut_ranges+: A series of CutRange objects
+  # *Returns*:: nothing
+  def add_cut_ranges(*cut_ranges)
+    cut_ranges.flatten.each do |cut_range|
+      raise TypeError, "Not of type CutRange" unless cut_range.kind_of? CutRange
+      self.add_cut_range( cut_range )
+    end
+  end
+
+  # Builds a HorizontalCutRange object and adds it to the SequenceRange.
+  #
+  # ---
+  # *Arguments*
+  # * +left+: Left-most cut
+  # * +right+: (_optional_) Right side - by default this equals the left side, default is recommended.
+  # *Returns*:: nothing
+  def add_horizontal_cut_range( left, right=left )
+    @__fragments_current = false
+    @cut_ranges << HorizontalCutRange.new( left, right )
+  end
+
+  # A Bio::RestrictionEnzyme::Range::SequenceRange::Bin holds an +Array+ of
+  # indexes for the primary and complement strands (+p+ and +c+ accessors).
+  #
+  # Example hash with Bin values:
+  #   {0=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[0, 1], p=[0]>,
+  #    2=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[], p=[1, 2]>,
+  #    3=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[2, 3], p=[]>,
+  #    4=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[4, 5], p=[3, 4, 5]>}
+  #
+  # Note that the bin cannot be easily stored as a range since there may be
+  # nucleotides excised in the middle of a range.
+  #
+  # TODO: Perhaps store the bins as one-or-many ranges since missing
+  # nucleotides due to enzyme cutting is a special case.
+  Bin = Struct.new(:c, :p)
+
+  # Calculates the fragments over this sequence range as defined after using
+  # the methods add_cut_range, add_cut_ranges, and/or add_horizontal_cut_range
+  #
+  # Example return value:
+  #   [#<Bio::RestrictionEnzyme::Range::SequenceRange::Fragment:0x277bdc
+  #     @complement_bin=[0, 1],
+  #     @primary_bin=[0]>,
+  #    #<Bio::RestrictionEnzyme::Range::SequenceRange::Fragment:0x277bc8
+  #     @complement_bin=[],
+  #     @primary_bin=[1, 2]>,
+  #    #<Bio::RestrictionEnzyme::Range::SequenceRange::Fragment:0x277bb4
+  #     @complement_bin=[2, 3],
+  #     @primary_bin=[]>,
+  #    #<Bio::RestrictionEnzyme::Range::SequenceRange::Fragment:0x277ba0
+  #     @complement_bin=[4, 5],
+  #     @primary_bin=[3, 4, 5]>]
+  #
+  # ---
+  # *Arguments*
+  # * _none_
+  # *Returns*:: Bio::RestrictionEnzyme::Range::SequenceRange::Fragments
+  def fragments
+    return @__fragments if @__fragments_current == true
+    @__fragments_current = true
+
+    num_txt = '0123456789'
+    num_txt_repeat = (num_txt * ( @size / num_txt.size.to_f ).ceil)[0..@size-1]
+    fragments = Fragments.new(num_txt_repeat, num_txt_repeat)
+
+    cc = Bio::RestrictionEnzyme::Range::SequenceRange::CalculatedCuts.new(@size)
+    cc.add_cuts_from_cut_ranges(@cut_ranges)
+    cc.remove_incomplete_cuts
+
+    create_bins(cc).sort.each { |k, bin| fragments << Fragment.new( bin.p, bin.c ) }
+    @__fragments = fragments
+    return fragments
+  end
+
+  #########
+  protected
+  #########
+
+  # Example:
+  #   cc = Bio::RestrictionEnzyme::Range::SequenceRange::CalculatedCuts.new(@size)
+  #   cc.add_cuts_from_cut_ranges(@cut_ranges)
+  #   cc.remove_incomplete_cuts
+  #   bins = create_bins(cc)
+  #
+  # Example return value:
+  #   {0=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[0, 1], p=[0]>,
+  #    2=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[], p=[1, 2]>,
+  #    3=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[2, 3], p=[]>,
+  #    4=>#<struct Bio::RestrictionEnzyme::Range::SequenceRange::Bin c=[4, 5], p=[3, 4, 5]>}
+  #
+  # ---
+  # *Arguments*
+  # * +cc+: Bio::RestrictionEnzyme::Range::SequenceRange::CalculatedCuts
+  # *Returns*:: +Hash+ Keys are unique, values are Bio::RestrictionEnzyme::Range::SequenceRange::Bin objects filled with indexes of the sequence locations they represent.
+  def create_bins(cc)
+    p_cut = cc.vc_primary
+    c_cut = cc.vc_complement
+    h_cut = cc.hc_between_strands
+
+    if @circular
+      # NOTE
+      # if it's circular we should start at the beginning of a cut for orientation
+      # scan for it, hack off the first set of hcuts and move them to the back
+
+      unique_id = 0
+    else
+      p_cut.unshift(-1) unless p_cut.include?(-1)
+      c_cut.unshift(-1) unless c_cut.include?(-1)
+      unique_id = -1
+    end
+
+    p_bin_id = c_bin_id = unique_id
+    bins = {}
+    setup_new_bin(bins, unique_id)
+
+    -1.upto(@size-1) do |idx| # NOTE - circular, for the future - should '-1' be replace with 'unique_id'?
+
+      # if bin_ids are out of sync but the strands are attached
+      if (p_bin_id != c_bin_id) and !h_cut.include?(idx)
+        min_id, max_id = [p_bin_id, c_bin_id].sort
+        bins.delete(max_id)
+        p_bin_id = c_bin_id = min_id
+      end
+
+      bins[ p_bin_id ].p << idx
+      bins[ c_bin_id ].c << idx
+
+      if p_cut.include? idx
+        p_bin_id = (unique_id += 1)
+        setup_new_bin(bins, p_bin_id)
+      end
+
+      if c_cut.include? idx             # repetition
+        c_bin_id = (unique_id += 1)     # repetition
+        setup_new_bin(bins, c_bin_id)   # repetition
+      end                               # repetition
+
+    end
+
+    # Bin "-1" is an easy way to indicate the start of a strand just in case
+    # there is a horizontal cut at position 0
+    bins.delete(-1) unless @circular
+    bins
+  end
+
+  # Modifies bins in place by creating a new element with key bin_id and
+  # initializing the bin.
+  def setup_new_bin(bins, bin_id)
+    bins[ bin_id ] = Bin.new
+    bins[ bin_id ].p = []
+    bins[ bin_id ].c = []
+  end
+
+end # SequenceRange
+end # Range
+end # RestrictionEnzyme
+end # Bio