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 # Analyze assembled sequences in the stream and output stats.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 require 'maasha/biopieces'
33 require 'maasha/fasta'
34 require 'maasha/prodigal'
38 casts << {:long=>'gene_cov', :short=>'g', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
39 casts << {:long=>'procedure', :short=>'p', :type=>'string', :mandatory=>true, :default=>'single', :allowed=>'single,meta', :disallowed=>nil}
40 casts << {:long=>'no_stream', :short=>'x', :type=>'flag', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
41 casts << {:long=>'data_out', :short=>'o', :type=>'file', :mandatory=>false, :default=>nil, :allowed=>nil, :disallowed=>nil}
43 options = Biopieces.options_parse(ARGV, casts)
45 options[:full] = true;
49 tmpdir = Biopieces.mktmpdir
50 infile = File.join(tmpdir, "in.fna")
51 outfile = File.join(tmpdir, "out.prodigal")
53 Fasta.open(infile, "w") do |fasta_output|
54 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
55 input.each_record do |record|
57 seq = Seq.new_bp(record)
59 total += record[:SEQ].length
60 lengths << record[:SEQ].length
63 output.puts record unless options[:no_stream]
64 fasta_output.puts seq.to_fasta
70 prodigal = Prodigal.new(infile, outfile, options)
72 gene_cov = prodigal.coverage
78 lengths.sort.reverse.each do |length|
81 if count >= total * 0.50
88 new_record[:N50] = n50
89 new_record[:MAX] = lengths.max
90 new_record[:MIN] = lengths.min
91 new_record[:MEAN] = (total.to_f / lengths.size.to_f).to_i
92 new_record[:TOTAL] = total
93 new_record[:COUNT] = lengths.size
94 new_record[:GENE_COV] = gene_cov if options[:gene_cov]
96 Biopieces.open(nil, options[:data_out]) do |input, output|
97 output.puts new_record
101 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<