3 # Copyright (C) 2007-2013 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 # Assemble ordered overlapping pair-end sequences in the stream.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 require 'maasha/biopieces'
34 require 'maasha/seq/assemble'
38 casts << {:long=>'mismatches', :short=>'m', :type=>'uint', :mandatory=>false, :default=>5, :allowed=>nil, :disallowed=>nil}
39 casts << {:long=>'overlap_min', :short=>'o', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>"0"}
40 casts << {:long=>'overlap_max', :short=>'p', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>"0"}
42 options = Biopieces.options_parse(ARGV, casts)
47 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
48 input.each_record do |record|
49 if record[:SEQ_NAME] and record[:SEQ] and record[:SCORES]
51 entry1 = Seq.new_bp(record)
53 entry2 = Seq.new_bp(record)
55 entry2.reverse!.complement!
59 merged = Assemble.pair(
62 mismatches_max:options[:mismatches],
63 overlap_min:options[:overlap_min],
64 overlap_max:options[:overlap_max]
68 new_record = merged.to_bp
70 if merged.seq_name =~ /overlap=(\d+):hamming=(\d+)$/
71 new_record[:OVERLAP_LEN] = $1
72 new_record[:HAMMING_DIST] = $2
75 output.puts new_record
88 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<