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 # Shred sequences in the stream into subsequences.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
37 # Method that shreds the sequence of a sequence object into
38 # random subsequences of a specified size. Subsequences are
39 # alternatly picked from the + or - strand (i.e. reverse complemented)
40 # until the specified coverage is reached.
42 # seq.shred { |subseq| } -> Seq
44 def shred(size, max_cov)
49 while (sum / self.seq.length) < max_cov
50 if self.seq.size - size == 0
53 start = rand(self.seq.size - size)
56 stop = start + size - 1
57 seq_name = self.seq_name + "[#{start + 1}-#{stop + 1}:#{strand}]"
58 seq = self.seq[start .. stop]
59 entry = Seq.new(seq_name, seq, 'dna')
61 entry.revcomp if strand == '-'
69 strand = (strand == '+') ? '-' : '+'
79 casts << {:long=>'size', :short=>'s', :type=>'uint', :mandatory=>true, :default=>500, :allowed=>nil, :disallowed=>'0'}
80 casts << {:long=>'coverage', :short=>'c', :type=>'uint', :mandatory=>true, :default=>100, :allowed=>nil, :disallowed=>'0'}
84 options = bp.parse(ARGV, casts)
86 bp.each_record do |record|
87 if record.has_key? :SEQ and record[:SEQ].length >= options[:size]
88 entry = Seq.new(record[:SEQ_NAME], record[:SEQ], record[:SCORES])
90 entry.shred(options[:size], options[:coverage]) do |subentry|
91 bp.puts subentry.to_bp
96 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<