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 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
27 # Class containing methods for located all non-redundant Maximally Extended Matches (MEMs)
28 # between two strings.
30 # Class method to located all non-redudant MEMs bewteen two sequences within a given
31 # search space and seeded with kmers of a given size.
32 def self.find(q_seq, s_seq, q_min, s_min, q_max, s_max, kmer)
34 m.matches_find(q_seq, s_seq, q_min, s_min, q_max, s_max, kmer)
37 # Method that finds all maximally expanded non-redundant matches shared
38 # between two sequences inside a given search space.
39 def matches_find(q_seq, s_seq, q_min, s_min, q_max, s_max, kmer)
41 redundant = Hash.new { |h, k| h[k] = [] }
43 s_index = index_seq(s_seq, s_min, s_max, kmer)
47 while q_pos <= q_max - kmer + 1
48 q_oligo = q_seq[q_pos ... q_pos + kmer]
50 s_index[q_oligo].each do |s_pos|
51 match = Match.new(q_pos, s_pos, kmer)
53 unless match_redundant?(redundant, match)
54 match_expand(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
57 match_redundant_add(redundant, match)
67 # Method that indexes a sequence within a given interval such that the
68 # index contains all oligos of a given kmer size and the positions where
69 # this oligo was located.
70 def index_seq(seq, min, max, kmer, step = 1)
71 index_hash = Hash.new { |h, k| h[k] = [] }
75 while pos <= max - kmer + 1
76 oligo = seq[pos ... pos + kmer]
77 index_hash[oligo] << pos
85 # Method to check if a match is redundant.
86 def match_redundant?(redundant, match)
87 redundant[match.q_beg].each do |s_interval|
88 if s_interval.include? match.s_beg and s_interval.include? match.s_end # TODO test if include? is slow
96 # Method that adds a match to the redundancy index.
97 def match_redundant_add(redundant, match)
98 (match.q_beg .. match.q_end).each do |q|
99 redundant[q] << (match.s_beg .. match.s_end)
103 # Method that expands a match as far as possible to the left and right.
104 def match_expand(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
105 match_expand_left(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
106 match_expand_right(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
111 # Method that expands a match as far as possible to the left.
112 def match_expand_left(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
113 while match.q_beg > q_min and
114 match.s_beg > s_min and
115 q_seq[match.q_beg - 1] == s_seq[match.s_beg - 1]
124 # Method that expands a match as far as possible to the right.
125 def match_expand_right(match, q_seq, s_seq, q_min, s_min, q_max, s_max)
126 while match.q_end < q_max and
127 match.s_end < s_max and
128 q_seq[match.q_end + 1] == s_seq[match.s_end + 1]
135 # Class for containing a match between two sequences q and s.
137 attr_accessor :q_beg, :s_beg, :length, :score
139 def initialize(q_beg, s_beg, length, score = 0.0)
155 s = "q: #{@q_beg} #{q_end} s: #{@s_beg} #{s_end} l: #{@length} s: #{@score}"
156 s << " seq: #{seq[@q_beg .. q_end]}" if seq