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 # Determine the frequencies for k-mers in sequences in the stream.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 require 'maasha/biopieces'
36 casts << {:long=>'size', :short=>'s', :type=>'uint', :mandatory=>false, :default=>4, :allowed=>nil, :disallowed=>'0'}
37 casts << {:long=>'type', :short=>'t', :type=>'string', :mandatory=>false, :default=>"dna", :allowed=>"dna,rna,protein", :disallowed=>nil}
39 options = Biopieces.options_parse(ARGV, casts)
41 oligos = Seq.generate_oligos(options[:size], options[:type])
43 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
44 input.each_record do |record|
45 if record.has_key? :SEQ
47 oligos.each { |oligo| kmers[oligo.upcase] = 0 }
49 (0 ... record[:SEQ].length - options[:size]).each do |i|
50 kmer = record[:SEQ][i .. i + options[:size] - 1].upcase
51 kmers[kmer] += 1 if kmers[kmer]
62 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<