1 # Copyright (C) 2007-2011 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 'inline' # RubyInline
27 # Error class for all exceptions to do with BackTrack.
28 class BackTrackError < StandardError; end
30 # Module containing code to locate nucleotide patterns in sequences allowing for
31 # ambiguity codes and a given maximum mismatches, insertions, and deletions. The
32 # pattern match engine is based on a backtrack algorithm.
33 # Insertions are nucleotides found in the pattern but not in the sequence.
34 # Deletions are nucleotides found in the sequence but not in the pattern.
35 # Algorithm based on code kindly provided by j_random_hacker @ Stackoverflow:
36 # http://stackoverflow.com/questions/7557017/approximate-string-matching-using-backtracking/
38 OK_PATTERN = Regexp.new('^[bflsycwphqrimtnkvadegu]+$')
39 MAX_MIS = 5 # Maximum number of mismatches allowed
40 MAX_INS = 5 # Maximum number of insertions allowed
41 MAX_DEL = 5 # Maximum number of deletions allowed
43 # ------------------------------------------------------------------------------
44 # str.scan(pattern[, max_mismatches [, max_insertions [,max_deletions]]])
46 # str.scan(pattern[, max_mismatches [, max_insertions [,max_deletions]]]) { |match|
51 # ------------------------------------------------------------------------------
52 # Method to iterate through a sequence to locate pattern matches starting at a
53 # given offset allowing for a maximum number of mismatches, insertions, and
54 # deletions. Insertions are nucleotides found in the pattern but not in the
55 # sequence. Deletions are nucleotides found in the sequence but not in the
56 # pattern. Matches found in block context return the Match object. Otherwise
57 # matches are returned in an Array of Match objects.
58 def patscan(pattern, offset = 0, max_mismatches = 0, max_insertions = 0, max_deletions = 0)
59 raise BackTrackError, "Bad pattern: #{pattern}" unless pattern.downcase =~ OK_PATTERN
60 raise BackTrackError, "offset: #{offset} out of range (0 ... #{self.length - 1})" unless (0 ... self.length).include? offset
61 raise BackTrackError, "max_mismatches: #{max_mismatches} out of range (0 .. #{MAX_MIS})" unless (0 .. MAX_MIS).include? max_mismatches
62 raise BackTrackError, "max_insertions: #{max_insertions} out of range (0 .. #{MAX_INS})" unless (0 .. MAX_INS).include? max_insertions
63 raise BackTrackError, "max_deletions: #{max_deletions} out of range (0 .. #{MAX_DEL})" unless (0 .. MAX_DEL).include? max_deletions
68 while result = self.track(pattern, offset, max_mismatches, max_insertions, max_deletions)
69 yield Match.new(result.first, result.last, self.seq[result.first ... result.first + result.last])
70 offset = result.first + 1
73 while result = self.track(pattern, offset, max_mismatches, max_insertions, max_deletions)
74 matches << Match.new(result.first, result.last, self.seq[result.first ... result.first + result.last])
75 offset = result.first + 1
79 return matches.empty? ? nil : matches unless block_given?
85 builder.add_static "id_seq", 'rb_intern("@seq")', "ID"
87 # Macro for matching nucleotides including ambiguity codes.
89 #define MATCH(A,B) ((bitmap[(unsigned short) A] & bitmap[(unsigned short) B]) != 0)
92 # Bitmap for matching nucleotides including ambiguity codes.
93 # For each value bits are set from the left: bit pos 1 for A,
94 # bit pos 2 for T, bit pos 3 for C, and bit pos 4 for G.
96 unsigned short bitmap[256] = {
97 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
98 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
99 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
100 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
101 0, 1,14, 4,11, 0, 0, 8, 7, 0, 0,10, 0, 5,15, 0,
102 0, 0, 9,12, 2, 2,13, 3, 0, 6, 0, 0, 0, 0, 0, 0,
103 0, 1,14, 4,11, 0, 0, 8, 7, 0, 0,10, 0, 5,15, 0,
104 0, 0, 9,12, 2, 2,13, 3, 0, 6, 0, 0, 0, 0, 0, 0,
105 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
106 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
107 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
108 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
109 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
110 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
111 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
112 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
116 # Backtrack algorithm for matching a pattern (p) starting in a sequence (s) allowing for mm
117 # mismatches, ins insertions and del deletions. ss is the start of the sequence, used only for
118 # reporting the match endpoints.
120 unsigned int backtrack(char* ss, char* s, char* p, int mm, int ins, int del)
124 while (*s && MATCH(*s, *p)) ++s, ++p; // OK to always match longest segment
127 return (unsigned int) (s - ss);
130 if (mm && *s && *p && (r = backtrack(ss, s + 1, p + 1, mm - 1, ins, del))) return r;
131 if (ins && *p && (r = backtrack(ss, s, p + 1, mm, ins - 1, del))) return r;
132 if (del && *s && (r = backtrack(ss, s + 1, p, mm, ins, del - 1))) return r;
139 # Find pattern (p) in a sequence (@seq) starting at pos, with at most mm mismatches, ins
140 # insertions and del deletions.
142 static VALUE track(char* p, unsigned int pos, int mm, int ins, int del)
144 VALUE seq = rb_ivar_get(self, id_seq);
145 char* s = StringValuePtr(seq);
156 if (e = backtrack(ss, s, p, mm, ins, del))
158 tuple = rb_ary_new();
159 rb_ary_push(tuple, INT2FIX((int) (s - ss)));
160 rb_ary_push(tuple, INT2FIX((int) e - (s - ss)));
173 # Class containing match information.
175 attr_reader :pos, :length, :match
177 def initialize(pos, length, match)
184 "#{pos}:#{length}:#{match}"