3 # Copyright (C) 2007-2011 Martin A. Hansen.
5 # This program is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU General Public License
7 # as published by the Free Software Foundation; either version 2
8 # of the License, or (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
19 # http://www.gnu.org/copyleft/gpl.html
21 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
23 # This program is part of the Biopieces framework (www.biopieces.org).
25 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
27 # Remove adaptors or parts thereof from sequences in the stream.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
35 def disambiguate(adaptor)
36 adaptor_disamb = adaptor.dup
37 adaptor_disamb.gsub!('U', 'T')
38 adaptor_disamb.gsub!('R', '[AG]')
39 adaptor_disamb.gsub!('Y', '[CT]')
40 adaptor_disamb.gsub!('S', '[GC]')
41 adaptor_disamb.gsub!('W', '[AT]')
42 adaptor_disamb.gsub!('M', '[AC]')
43 adaptor_disamb.gsub!('K', '[GT]')
44 adaptor_disamb.gsub!('V', '[ACG]')
45 adaptor_disamb.gsub!('H', '[ACT]')
46 adaptor_disamb.gsub!('D', '[AGT]')
47 adaptor_disamb.gsub!('B', '[CGT]')
48 adaptor_disamb.gsub!('N', '.')
53 # Method that finds an adaptor or part thereof in the sequence of a Seq object.
54 # Returns a Match object if the adaptor was found otherwise nil. The ed_percent
55 # indicates the maximum edit distance allowed in all possible overlaps.
56 def adaptor_find(adaptor, adaptor_disamb, pos = 0, ed_percent = 0)
57 raise SeqError, "Edit distance percent out of range #{ed_percent}" unless (0 .. 100).include? ed_percent
60 pos = self.length - pos # pos offset from the right end
63 if match = adaptor_find_simple(adaptor_disamb, pos)
65 elsif match = adaptor_find_complex(adaptor, pos, ed_percent)
67 elsif match = adaptor_partial_find_complex(adaptor, ed_percent)
74 # Method to find an adaptor in a sequence taking into account ambiguity
75 # codes, but not considering mismatches, insertions, and deletions.
76 def adaptor_find_simple(adaptor, pos)
77 self.seq.upcase.match(adaptor, pos) do |m|
78 return Match.new($`.length, m, m.to_s.length, 0, 0, 0, m.to_s.length)
82 # Method to find an adaptor in a sequence taking into account ambiguity
83 # codes, mismatches, insertions, and deletions.
84 def adaptor_find_complex(adaptor, pos, ed_percent)
85 ed_max = (adaptor.length * ed_percent * 0.01).round
87 match = self.match(adaptor, pos, ed_max)
92 # Method to find part of an adaptor at the right end of a sequence taking
93 # into account ambiguity codes, mismatches, insertions, and deletions.
94 def adaptor_partial_find_complex(adaptor, ed_percent)
95 adaptor = adaptor[0 ... -1]
97 pos = self.len - adaptor.length
99 while adaptor.length > 0
100 ed_max = (adaptor.length * ed_percent * 0.01).round
103 self.seq.upcase.match(adaptor, pos) do |m|
104 return Match.new($`.length, m, m.to_s.length, 0, 0, 0, m.to_s.length)
107 self.scan(adaptor, pos, ed_max).each do |match|
112 adaptor = adaptor[0 ... -1]
114 pos = self.len - adaptor.length
120 casts << {:long=>'adaptor', :short=>'r', :type=>'string', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
121 casts << {:long=>'edit_distance', :short=>'e', :type=>'uint', :mandatory=>false, :default=>20, :allowed=>nil, :disallowed=>nil}
122 casts << {:long=>'pos', :short=>'p', :type=>'int', :mandatory=>false, :default=>1, :allowed=>nil, :disallowed=>"0"}
126 options = bp.parse(ARGV, casts)
128 adaptor = options[:adaptor].to_s.upcase
129 adaptor_disamb = disambiguate(adaptor)
132 pos -= 1 if pos > 0 # pos was 1-based
134 bp.each_record do |record|
135 if record.has_key? :SEQ
136 entry = Seq.new(record[:SEQ_NAME], record[:SEQ], "dna", record[:SCORES])
138 if match = entry.adaptor_find(adaptor, adaptor_disamb, pos, options[:edit_distance])
139 record[:ADAPTOR_POS] = match.pos
140 record[:ADAPTOR_LEN] = match.length
141 record[:ADAPTOR_MATCH] = match.match
149 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<