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 # Assemble sequences in the stream using IDBA.
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=>'scaffold', :short=>'s', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
37 casts << {:long=>'kmer_min', :short=>'k', :type=>'uint', :mandatory=>false, :default=>25, :allowed=>nil, :disallowed=>nil}
38 casts << {:long=>'kmer_max', :short=>'K', :type=>'uint', :mandatory=>false, :default=>50, :allowed=>nil, :disallowed=>nil}
39 casts << {:long=>'count_min', :short=>'c', :type=>'uint', :mandatory=>false, :default=>2, :allowed=>nil, :disallowed=>nil}
40 casts << {:long=>'cover', :short=>'C', :type=>'uint', :mandatory=>false, :default=>0, :allowed=>nil, :disallowed=>nil}
41 casts << {:long=>'pairs_min', :short=>'p', :type=>'uint', :mandatory=>false, :default=>5, :allowed=>nil, :disallowed=>nil}
42 casts << {:long=>'prefix_len', :short=>'P', :type=>'uint', :mandatory=>false, :default=>3, :allowed=>nil, :disallowed=>nil}
43 casts << {:long=>'clean', :short=>'x', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
45 options = Biopieces.options_parse(ARGV, casts)
47 Dir.mkdir(options[:directory]) unless Dir.exists?(options[:directory])
49 file_fasta = File.join(options[:directory], "IDBA") + ".fna"
53 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
54 Fasta.open(file_fasta, mode="w") do |fasta_io|
55 input.each_record do |record|
56 if options[:scaffold] # we need to fix the sequence name for mate-pair IDBA
57 if records[:SEQ_NAME] =~ /1$/
58 record[:SEQ_NAME] = "read#{count}/1"
60 record[:SEQ_NAME] = "read#{count}/2"
70 unless File.size(file_fasta) == 0
71 prefix = File.join(options[:directory], "IDBA")
74 commands << "nice -n 19"
76 commands << "--read #{file_fasta}"
77 commands << "--output #{prefix}"
78 commands << "--scaffold" if options[:scaffold]
79 commands << "--mink #{options[:kmer_min]}"
80 commands << "--maxk #{options[:kmer_max]}"
81 commands << "--minCount #{options[:count_min]}"
82 commands << "--cover #{options[:cover]}"
83 commands << "--minPairs #{options[:pairs_min]}"
84 commands << "--prefixLength #{options[:prefix_len]}"
85 commands << "> /dev/null 2>&1" unless options[:verbose]
87 command = commands.join(" ")
91 raise "Command failed: #{command}" unless $?.success?
93 $stderr.puts "Command failed: #{command}"
97 file_contig = File.join(options[:directory], "IDBA") + "-contig-mate.fa"
99 file_contig = File.join(options[:directory], "IDBA") + "-contig.fa"
102 Fasta.open(file_contig, mode="r") do |fasta_io|
103 fasta_io.each do |entry|
104 output.puts entry.to_bp
110 FileUtils.remove_entry_secure file_fasta
111 FileUtils.remove_entry_secure options[:directory] if options[:clean]
114 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<