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
45 commands << "#{kmer_min},#{kmer_max},#{kmer_step}"
46 commands << "-#{type}"
48 commands << @sequence_file
53 def run_velvetg(cov_cutoff, exp_cov, paired)
56 commands << @directory
57 commands << "-cov_cutoff #{cov_cutoff}"
58 commands << "-exp_cov #{exp_cov}"
59 commands << "-ins_length #{ins_length}" if paired
60 commands << "-clean yes"
68 commands.push "> /dev/null 2>&1" unless @verbose
70 command = commands.join(" ")
74 raise "Command failed: #{command}" unless $?.success?
76 $stderr.puts "Command failed: #{command}"
81 types = 'short,shortPaired,long,longPaired'
84 casts << {:long=>'directory', :short=>'d', :type=>'dir', :mandatory=>true, :default=>nil, :allowed=>nil, :disallowed=>nil}
85 casts << {:long=>'type', :short=>'t', :type=>'string', :mandatory=>true, :default=>'short', :allowed=>types, :disallowed=>nil}
86 casts << {:long=>'kmer_min', :short=>'k', :type=>'uint', :mandatory=>true, :default=>19, :allowed=>nil, :disallowed=>nil}
87 casts << {:long=>'kmer_max', :short=>'K', :type=>'uint', :mandatory=>true, :default=>31, :allowed=>nil, :disallowed=>nil}
88 casts << {:long=>'kmer_step', :short=>'s', :type=>'uint', :mandatory=>true, :default=>2, :allowed=>nil, :disallowed=>nil}
89 casts << {:long=>'cov_cutoff', :short=>'c', :type=>'float', :mandatory=>true, :default=>'auto', :allowed=>nil, :disallowed=>nil}
90 casts << {:long=>'exp_cov', :short=>'e', :type=>'float', :mandatory=>true, :default=>'auto', :allowed=>nil, :disallowed=>nil}
91 casts << {:long=>'ins_length', :short=>'i', :type=>'uint', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
92 casts << {:long=>'clean', :short=>'X', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
94 options = Biopieces.options_parse(ARGV, casts)
96 raise ArgumentError, "kmer_min #{options[:kmer_min]} must be uneven." if options[:kmer_min].even?
97 raise ArgumentError, "kmer_max #{options[:kmer_max]} must be uneven." if options[:kmer_max].even?
98 raise ArgumentError, "kmer_step #{options[:kmer_step]} must be even." unless options[:kmer_step].even?
99 raise ArgumentError, "kmer_min >= kmer_max: #{options[:kmer_min]} >= #{options[:kmer_max]}" unless options[:kmer_max] > options[:kmer_min]
101 Dir.mkdir(options[:directory]) unless Dir.exists?(options[:directory])
103 file_fasta = File.join(options[:directory], "sequence_in.fna")
105 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
106 Fasta.open(file_fasta, mode="w") do |fasta_io|
107 input.each_record do |record|
108 if record[:SEQ_NAME] and record[:SEQ]
109 seq = Seq.new_bp(record)
110 fasta_io.puts seq.to_fasta
115 unless File.size(file_fasta) == 0
116 velvet = Velvet.new(options[:directory], file_fasta, options[:verbose])
117 velvet.run_velveth(options[:kmer_min], options[:kmer_max], options[:kmer_step], options[:type])
118 velvet.run_velvetg(options[:cov_cutoff], options[:exp_cov], options[:type].match("Paired"))
119 file_contigs = File.join(options[:directory], "contigs.fa")
121 Fasta.open(file_contigs, mode="r") do |fasta_io|
122 fasta_io.each do |entry|
123 output.puts entry.to_bp
129 FileUtils.remove_entry_secure file_fasta
130 FileUtils.remove_entry_secure options[:directory] if options[:clean]
133 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<