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 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
26 def self.find(q_seq, s_seq, q_min, s_min, q_max, s_max, kmer)
28 m.matches_find(q_seq, s_seq, q_min, s_min, q_max, s_max, kmer)
31 # Method that finds all maximally expanded non-redundant matches shared
32 # between two sequences inside a given search space.
33 def matches_find(q_seq, s_seq, q_min, s_min, q_max, s_max, kmer)
35 redundant = Hash.new { |h, k| h[k] = [] }
37 s_index = index_seq(s_seq, s_min, s_max, kmer)
41 while q_pos <= q_max - kmer + 1
42 q_oligo = q_seq[q_pos ... q_pos + kmer]
44 s_index[q_oligo].each do |s_pos|
45 match = Match.new(q_pos, s_pos, kmer)
46 unless match_redundant?(redundant, match)
47 match_expand(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
50 match_redundant_add(redundant, match)
60 # Method that indexes a sequence within a given interval such that the
61 # index contains all oligos of a given kmer size and the positions where
62 # this oligo was located.
63 def index_seq(seq, min, max, kmer, step = 1)
64 index_hash = Hash.new { |h, k| h[k] = [] }
68 while pos <= max - kmer + 1
69 oligo = seq[pos ... pos + kmer]
70 index_hash[oligo] << pos
78 # Method to check if a match is redundant.
79 def match_redundant?(redundant, match)
80 redundant[match.q_beg].each do |s_interval|
81 if s_interval.include? match.s_beg and s_interval.include? match.s_end
89 # Method that adds a match to the redundancy index.
90 def match_redundant_add(redundant, match)
91 (match.q_beg .. match.q_end).each do |q|
92 redundant[q] << (match.s_beg .. match.s_end)
96 # Method that expands a match as far as possible to the left and right.
97 def match_expand(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
98 match_expand_left(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
99 match_expand_right(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
104 # Method that expands a match as far as possible to the left.
105 def match_expand_left(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
106 while match.q_beg > q_min and
107 match.s_beg > s_min and
108 q_seq[match.q_beg - 1] == s_seq[match.s_beg - 1]
117 # Method that expands a match as far as possible to the right.
118 def match_expand_right(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
119 while match.q_end < q_max and
120 match.s_end < s_max and
121 q_seq[match.q_end + 1] == s_seq[match.s_end + 1]
128 # Class for containing a match between two sequences q and s.
130 attr_accessor :q_beg, :s_beg, :length, :score
132 def initialize(q_beg, s_beg, length, score = 0.0)
148 s = "q: #{@q_beg} #{q_end} s: #{@s_beg} #{s_end} l: #{@length} s: #{@score}"
149 s << " seq: #{seq[@q_beg .. q_end]}" if seq