3 # Copyright (C) 2007-2012 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 sequences in the stream using IDBA-UD.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
32 require 'maasha/fasta'
35 casts << {:long=>'directory', :short=>'d', :type=>'dir', :mandatory=>true, :default=>nil, :allowed=>nil, :disallowed=>nil}
36 casts << {:long=>'kmer_min', :short=>'k', :type=>'uint', :mandatory=>false, :default=>20, :allowed=>nil, :disallowed=>nil}
37 casts << {:long=>'kmer_max', :short=>'K', :type=>'uint', :mandatory=>false, :default=>100, :allowed=>nil, :disallowed=>nil}
38 casts << {:long=>'count_min', :short=>'c', :type=>'uint', :mandatory=>false, :default=>2, :allowed=>nil, :disallowed=>nil}
39 casts << {:long=>'pairs_min', :short=>'p', :type=>'uint', :mandatory=>false, :default=>3, :allowed=>nil, :disallowed=>nil}
40 casts << {:long=>'prefix_len', :short=>'P', :type=>'uint', :mandatory=>false, :default=>3, :allowed=>nil, :disallowed=>nil}
41 casts << {:long=>'cpus', :short=>'C', :type=>'uint', :mandatory=>false, :default=>0, :allowed=>nil, :disallowed=>nil}
42 casts << {:long=>'clean', :short=>'X', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
44 options = Biopieces.options_parse(ARGV, casts)
46 Dir.mkdir(options[:directory]) unless Dir.exists?(options[:directory])
48 file_fasta = File.join(options[:directory], "IDBA-UD") + ".fna"
52 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
53 Fasta.open(file_fasta, "w") do |fasta_io|
54 input.each_record do |record|
55 if record[:SEQ_NAME] and record[:SEQ]
56 seq = Seq.new_bp(record)
58 fasta_io.puts seq.to_fasta
63 unless File.size(file_fasta) == 0
64 prefix = File.join(options[:directory], "IDBA-UD")
67 commands << "nice -n 19"
69 commands << "--read #{file_fasta}"
70 commands << "--out #{prefix}"
71 commands << "--mink #{options[:kmer_min]}"
72 commands << "--maxk #{options[:kmer_max]}"
73 commands << "--min_count #{options[:count_min]}"
74 commands << "--min_pairs #{options[:pairs_min]}"
75 commands << "--prefix #{options[:prefix_len]}"
76 commands << "--num_threads #{options[:cpus]}"
77 commands << "> /dev/null 2>&1" unless options[:verbose]
79 command = commands.join(" ")
82 raise "Command failed: #{command}" unless $?.success?
84 file_contig = File.join(options[:directory], "IDBA-UD", "contig.fa")
86 Fasta.open(file_contig, mode="r") do |fasta_io|
87 fasta_io.each do |entry|
88 output.puts entry.to_bp
94 FileUtils.remove_entry_secure file_fasta
95 FileUtils.remove_entry_secure options[:directory] if options[:clean]
98 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<