1 # Copyright (C) 2007-2012 Martin A. Hansen.
3 # This program is free software; you can redistribute it and/or
4 # modify it under the terms of the GNU General Public License
5 # as published by the Free Software Foundation; either version 2
6 # of the License, or (at your option) any later version.
8 # This program is distributed in the hope that it will be useful,
9 # but WITHOUT ANY WARRANTY; without even the implied warranty of
10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11 # GNU General Public License for more details.
13 # You should have received a copy of the GNU General Public License
14 # along with this program; if not, write to the Free Software
15 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
17 # http://www.gnu.org/copyleft/gpl.html
19 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
21 # This software is part of the Biopieces framework (www.biopieces.org).
23 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
25 require 'maasha/align/matches'
26 require 'maasha/math_aux'
28 FACTOR_SCORE_LENGTH = 1.0
29 FACTOR_SCORE_DIAG = -1.41
32 # Module with stuff to create a pairwise aligment.
34 # Class for creating a pairwise alignment.
36 # Class method to create a pairwise alignment of two given Seq objects.
37 def self.align(q_entry, s_entry)
38 self.new(q_entry, s_entry)
41 # Method to inialize a pairwise alignment given two Seq objects.
42 def initialize(q_entry, s_entry)
47 @q_entry.seq.downcase!
48 @s_entry.seq.downcase!
50 space = Space.new(0, 0, @q_entry.length - 1, @s_entry.length - 1)
52 align_recurse(@q_entry.seq, @s_entry.seq, space, KMER)
59 # Method that creates an alignment by chaining matches, which are
60 # subsequences shared between two sequences. This recursive method
61 # functions by considering only matches within a given search space. If no
62 # matches are given these will be located and matches will be included
63 # depending on a calculated score. New search spaces spanning the spaces
64 # between the best scoring matches and the search space boundaries will be
65 # cast and recursed into.
66 def align_recurse(q_seq, s_seq, space, kmer, matches = [])
67 matches = matches_select_by_space(matches, space)
68 matches = matches_select_by_score(matches, space)
70 while (matches.size == 0 and kmer > 0)
71 matches = Matches.find(q_seq, s_seq, space.q_min, space.s_min, space.q_max, space.s_max, kmer)
72 #matches = Mem.find(q_seq, s_seq, kmer, space.q_min, space.s_min, space.q_max, space.s_max)
75 matches.sort_by! { |m| m.length }
77 matches = matches_select_by_score(matches, space)
83 if best_match = matches.pop
84 @matches << best_match
86 space_left = Space.new(space.q_min, space.s_min, best_match.q_beg - 1, best_match.s_beg - 1)
87 space_right = Space.new(best_match.q_end + 1, best_match.s_end + 1, space.q_max, space.s_max)
89 align_recurse(q_seq, s_seq, space_left, kmer, matches) unless space_left.empty?
90 align_recurse(q_seq, s_seq, space_right, kmer, matches) unless space_right.empty?
94 # Method to select matches that lies within the search space.
95 def matches_select_by_space(matches, space)
96 new_matches = matches.select do |match|
97 match.q_beg >= space.q_min and
98 match.s_beg >= space.s_min and
99 match.q_end <= space.q_max and
100 match.s_end <= space.s_max
106 # Method to select matches based on score.
107 def matches_select_by_score(matches, space)
108 matches_score(matches, space)
110 matches.select { |match| match.score > 0 }
113 def matches_score(matches, space)
114 matches.each do |match|
115 score_length = match_score_length(match)
116 score_diag = match_score_diag(match, space)
118 match.score = score_length + score_diag
121 matches.sort_by! { |match| match.score }
124 def match_score_length(match)
125 match.length * FACTOR_SCORE_LENGTH
128 def match_score_diag(match, space)
129 if space.q_dim > space.s_dim # s_dim is the narrow end
130 dist_beg = Math.dist_point2line(match.q_beg,
134 space.q_min + space.s_dim,
135 space.s_min + space.s_dim)
137 dist_end = Math.dist_point2line( match.q_beg,
139 space.q_max - space.s_dim,
140 space.s_max - space.s_dim,
144 dist_beg = Math.dist_point2line( match.q_beg,
148 space.q_min + space.q_dim,
149 space.s_min + space.q_dim)
151 dist_end = Math.dist_point2line( match.q_beg,
153 space.q_max - space.q_dim,
154 space.s_max - space.q_dim,
159 dist_min = dist_beg < dist_end ? dist_beg : dist_end
161 dist_min * FACTOR_SCORE_DIAG
164 # Method for debugging purposes that upcase matching sequence while non-matches
165 # sequence is kept in lower case.
167 @matches.each do |match|
168 @q_entry.seq[match.q_beg .. match.q_end] = @q_entry.seq[match.q_beg .. match.q_end].upcase
169 @s_entry.seq[match.s_beg .. match.s_end] = @s_entry.seq[match.s_beg .. match.s_end].upcase
173 # Method that insert gaps in sequences based on a list of matches and thus
174 # creating an alignment.
176 @matches.sort_by! { |m| m.q_beg }
181 match = @matches.first
182 diff = (q_gaps + match.q_beg) - (s_gaps + match.s_beg)
185 @q_entry.seq.insert(0, "-" * diff.abs)
188 @s_entry.seq.insert(0, "-" * diff.abs)
192 @matches[1 .. -1].each do |m|
193 diff = (q_gaps + m.q_beg) - (s_gaps + m.s_beg)
196 @q_entry.seq.insert(m.q_beg + q_gaps, "-" * diff.abs)
199 @s_entry.seq.insert(m.s_beg + s_gaps, "-" * diff.abs)
204 diff = @q_entry.length - @s_entry.length
207 @q_entry.seq << ("-" * diff.abs)
209 @s_entry.seq << ("-" * diff.abs)
214 # Class for containing a search space between two sequences q and s.
216 attr_reader :q_min, :s_min, :q_max, :s_max
218 def initialize(q_min, s_min, q_max, s_max)
234 if @q_max - @q_min >= 0 and @s_max - @s_min >= 0