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 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
33 require 'maasha/seq/assemble'
36 def names_match(entry1, entry2)
37 if entry1.seq_name =~ /^([^ ]+) \d:/
39 elsif entry1.seq_name =~ /^(.+)\/\d$/
42 raise "Could not match sequence name: #{entry1.seq_name}"
45 if entry2.seq_name =~ /^([^ ]+) \d:/
47 elsif entry2.seq_name =~ /^(.+)\/\d$/
50 raise "Could not match sequence name: #{entry2.seq_name}"
57 casts << {long: 'mismatches', short: 'm', type: 'uint', mandatory: false, default: 5, allowed: nil, disallowed: nil}
58 casts << {long: 'overlap_min', short: 'o', type: 'uint', mandatory: false, default: 1, allowed: nil, disallowed: "0"}
59 casts << {long: 'overlap_max', short: 'p', type: 'uint', mandatory: false, default: nil, allowed: nil, disallowed: "0"}
61 options = Biopieces.options_parse(ARGV, casts)
66 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
67 input.each_record do |record|
68 if record[:SEQ_NAME] and record[:SEQ] and record[:SCORES]
70 entry1 = Seq.new_bp(record)
72 entry2 = Seq.new_bp(record)
77 entry1.length >= options[:overlap_min] and
78 entry2.length >= options[:overlap_min]
80 if names_match(entry1, entry2)
82 entry2.reverse!.complement!
84 merged = Assemble.pair(
87 mismatches_max: options[:mismatches],
88 overlap_min: options[:overlap_min],
89 overlap_max: options[:overlap_max]
93 new_record = merged.to_bp
95 if merged.seq_name =~ /overlap=(\d+):hamming=(\d+)$/
96 new_record[:OVERLAP_LEN] = $1
97 new_record[:HAMMING_DIST] = $2
100 output.puts new_record
103 raise "name mismatch: #{entry1.seq_name} != #{entry2.seq_name}"
116 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<