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 # Usearch sequences in the stream against a specified database.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
32 require 'maasha/fasta'
33 require 'maasha/usearch'
36 casts << {long: 'program', short: 'p', type: 'string', mandatory: false, default: 'global', allowed: "local,global", disallowed: nil}
37 casts << {long: 'database', short: 'd', type: 'file!', mandatory: true, default: nil, allowed: nil, disallowed: nil}
38 casts << {long: 'identity', short: 'i', type: 'float', mandatory: false, default: nil, allowed: nil, disallowed: nil}
39 casts << {long: 'e_val', short: 'e', type: 'float', mandatory: false, default: nil, allowed: nil, disallowed: nil}
40 casts << {long: 'cpus', short: 'c', type: 'uint', mandatory: false, default: 1, allowed: nil, disallowed: "0"}
41 casts << {long: 'maxaccepts', short: 'm', type: 'uint', mandatory: false, default: 0, allowed: nil, disallowed: nil}
43 options = Biopieces.options_parse(ARGV, casts)
45 if options[:program] == 'global'
46 raise ArgumentError, "--identity be specified for global search" unless options[:identity]
47 raise ArgumentError, "--e_val is invalid for global search" if options[:e_val]
49 raise ArgumentError, "--identity or --e_val must be specified" unless options[:identity] or options[:e_val]
52 tmpdir = Biopieces.mktmpdir
53 infile = File.join(tmpdir, "in.fna")
54 outfile = File.join(tmpdir, "out.uc")
56 Biopieces.open(options[:stream_in], options[:stream_out]) do |input, output|
57 Fasta.open(infile, "w") do |fasta_io|
58 input.each_record do |record|
61 if record[:SEQ_NAME] and record[:SEQ]
62 fasta_io.puts Seq.new_bp(record).to_fasta
67 us = Usearch.new(infile, outfile, options)
69 case options[:program]
70 when "local" then us.usearch_local
71 when "global" then us.usearch_global
72 else raise "no such program #{options[:program]}"
75 us.each_hit do |record|
81 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<