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 Velvet.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
32 require 'maasha/fasta'
35 def initialize(directory, sequence_file, verbose)
36 @directory = directory
37 @sequence_file = sequence_file
41 def run_velveth(kmer_min, kmer_max, kmer_step, type)
44 commands << @directory + File::SEPARATOR
45 commands << "#{kmer_min},#{kmer_max + kmer_step},#{kmer_step}" # FIXME - ugly fix for velvet bug
46 commands << "-create_binary"
47 commands << "-#{type}"
49 commands << @sequence_file
54 def run_velvetg(ins_length, paired)
55 dirs = Dir.entries(@directory).select { |d| d.match(/^_/) }
60 commands << File.join(@directory, dir)
61 commands << "-cov_cutoff auto"
62 commands << "-exp_cov auto"
63 commands << "-ins_length #{ins_length}" if paired
64 commands << "-clean yes"
65 commands << "-min_contig_lgth 200"
71 def pick_best_assembly
74 Dir.glob("#{@directory}/_*/contigs.fa").each do |file|
79 list.sort_by { |e| e.last }.last.first
85 commands.push "> /dev/null 2>&1" unless @verbose
87 command = commands.join(" ")
90 $stderr.puts command if @verbose
92 raise "Command failed: #{command}" unless $?.success?
94 $stderr.puts "Command failed: #{command}"
104 Fasta.open(file, "r") do |fasta_io|
105 fasta_io.each do |entry|
106 total += entry.length
107 lengths << entry.length
111 lengths.sort.reverse.each do |length|
114 if count >= total * 0.50
124 types = 'short,shortPaired,long,longPaired'
127 casts << {:long=>'directory', :short=>'d', :type=>'dir', :mandatory=>true, :default=>nil, :allowed=>nil, :disallowed=>nil}
128 casts << {:long=>'type', :short=>'t', :type=>'string', :mandatory=>true, :default=>'short', :allowed=>types, :disallowed=>nil}
129 casts << {:long=>'kmer_min', :short=>'k', :type=>'uint', :mandatory=>true, :default=>19, :allowed=>nil, :disallowed=>nil}
130 casts << {:long=>'kmer_max', :short=>'K', :type=>'uint', :mandatory=>true, :default=>31, :allowed=>nil, :disallowed=>nil}
131 casts << {:long=>'kmer_step', :short=>'s', :type=>'uint', :mandatory=>true, :default=>2, :allowed=>nil, :disallowed=>nil}
132 casts << {:long=>'ins_length', :short=>'i', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
133 casts << {:long=>'clean', :short=>'X', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
135 options = Biopieces.options_parse(ARGV, casts)
137 raise ArgumentError, "kmer_min #{options[:kmer_min]} must be uneven." if options[:kmer_min].even?
138 raise ArgumentError, "kmer_max #{options[:kmer_max]} must be uneven." if options[:kmer_max].even?
139 raise ArgumentError, "kmer_step #{options[:kmer_step]} must be even." unless options[:kmer_step].even?
140 raise ArgumentError, "kmer_min >= kmer_max: #{options[:kmer_min]} >= #{options[:kmer_max]}" unless options[:kmer_max] > options[:kmer_min]
142 Dir.mkdir(options[:directory]) unless Dir.exists?(options[:directory])
144 file_fasta = File.join(options[:directory], "sequence_in.fna")
146 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
147 Fasta.open(file_fasta, "w") do |fasta_io|
148 input.each_record do |record|
149 if record[:SEQ_NAME] and record[:SEQ]
150 seq = Seq.new_bp(record)
151 fasta_io.puts seq.to_fasta
156 unless File.size(file_fasta) == 0
157 velvet = Velvet.new(options[:directory], file_fasta, options[:verbose])
158 velvet.run_velveth(options[:kmer_min], options[:kmer_max], options[:kmer_step], options[:type])
159 velvet.run_velvetg(options[:ins_length], options[:type].match("Paired"))
160 file_contigs = velvet.pick_best_assembly
162 kmer = file_contigs.match(/_\d+/)
164 Fasta.open(file_contigs, "r") do |fasta_io|
165 fasta_io.each do |entry|
166 entry.seq_name << "_kmer#{kmer}"
167 output.puts entry.to_bp
173 FileUtils.remove_entry_secure file_fasta
174 FileUtils.remove_entry_secure options[:directory] if options[:clean]
176 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<