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 # Find homopolymers in sequences in the stream.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 require 'maasha/biopieces'
36 class Seq; include Homopolymer; end
39 casts << {:long=>'min', :short=>'m', :type=>'uint', :mandatory=>false, :default=>1, :allowed=>nil, :disallowed=>"0"}
40 casts << {:long=>'limit', :short=>'l', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>"0"}
41 casts << {:long=>'longest', :short=>'L', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
43 options = Biopieces.options_parse(ARGV, casts)
45 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
46 input.each_record do |record|
48 seq = Seq.new(seq: record[:SEQ])
50 longest = Seq::Homopolymer.new("", 0, 0)
54 seq.each_homopolymer(options[:min]) do |h|
57 record[:HOMOPOL_PAT] = h.pattern
58 record[:HOMOPOL_LEN] = h.length
59 record[:HOMOPOL_POS] = h.pos
62 longest = h.length > longest.length ? h : longest
68 break if options[:limit] and options[:limit] == count
73 if longest.length > options[:min]
74 record[:HOMOPOL_PAT] = longest.pattern
75 record[:HOMOPOL_LEN] = longest.length
76 record[:HOMOPOL_POS] = longest.pos
90 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<