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 Ray.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
32 require 'maasha/fasta'
35 def initialize(directory, sequence_file, options)
36 @directory = directory
37 @sequence_file = sequence_file
42 kmer = @options[:kmer_min]
44 if @options[:type] == "single"
50 while kmer <= @options[:kmer_max]
51 dir_ray = File.join(@directory, "Kmer_#{kmer}")
56 commands << "nice -n 19"
58 commands << "-np #{@options[:cpus]}"
60 commands << "-o " + File.join(dir_ray, "Ray")
61 commands << "-k #{kmer}"
63 commands << @sequence_file
71 def pick_best_assembly
74 Dir.glob("#{@directory}/Kmer_*/*.fasta").each do |file|
79 list.sort_by { |e| e.last }.last.first
85 commands.push "> /dev/null 2>&1" unless @options[:verbose]
87 command = commands.join(" ")
91 raise "Command failed: #{command}" unless $?.success?
93 $stderr.puts "Command failed: #{command}"
103 Fasta.open(file, "r") do |fasta_io|
104 fasta_io.each do |entry|
105 total += entry.length
106 lengths << entry.length
110 lengths.sort.reverse.each do |length|
113 if count >= total * 0.50
124 casts << {:long=>'directory', :short=>'d', :type=>'dir', :mandatory=>true, :default=>nil, :allowed=>nil, :disallowed=>nil}
125 casts << {:long=>'type', :short=>'t', :type=>'string', :mandatory=>true, :default=>'single', :allowed=>'single,paired', :disallowed=>nil}
126 casts << {:long=>'cpus', :short=>'c', :type=>'uint', :mandatory=>true, :default=>1, :allowed=>nil, :disallowed=>'0'}
127 casts << {:long=>'kmer_min', :short=>'k', :type=>'uint', :mandatory=>true, :default=>19, :allowed=>nil, :disallowed=>nil}
128 casts << {:long=>'kmer_max', :short=>'K', :type=>'uint', :mandatory=>true, :default=>31, :allowed=>nil, :disallowed=>nil}
129 casts << {:long=>'clean', :short=>'X', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
131 options = Biopieces.options_parse(ARGV, casts)
133 raise ArgumentError, "kmer_min #{options[:kmer_min]} must be uneven." if options[:kmer_min].even?
134 raise ArgumentError, "kmer_max #{options[:kmer_max]} must be uneven." if options[:kmer_max].even?
135 raise ArgumentError, "kmer_min > kmer_max: #{options[:kmer_min]} > #{options[:kmer_max]}" if options[:kmer_min] > options[:kmer_max]
137 Dir.mkdir(options[:directory]) unless Dir.exists?(options[:directory])
139 file_fasta = File.join(options[:directory], "sequence_in.fasta")
141 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
142 Fasta.open(file_fasta, "w") do |fasta_io|
143 input.each_record do |record|
144 if record[:SEQ_NAME] and record[:SEQ]
145 seq = Seq.new_bp(record)
147 fasta_io.puts seq.to_fasta
152 unless File.size(file_fasta) == 0
153 ray = Ray.new(options[:directory], file_fasta, options)
155 file_contigs = ray.pick_best_assembly
157 Fasta.open(file_contigs, "r") do |fasta_io|
158 fasta_io.each do |entry|
159 output.puts entry.to_bp
165 FileUtils.remove_entry_secure file_fasta
166 FileUtils.remove_entry_secure options[:directory] if options[:clean]
169 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<