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 # Run Uclust on sequences in the stream.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 require 'maasha/biopieces'
32 require 'maasha/fasta'
33 require 'maasha/usearch'
36 casts << {long: 'no_sort', short: 'n', type: 'flag', mandatory: false, default: nil, allowed: nil, disallowed: nil}
37 casts << {long: 'comp', short: 'c', type: 'flag', mandatory: false, default: nil, allowed: nil, disallowed: nil}
38 casts << {long: 'identity', short: 'i', type: 'float', mandatory: true, default: 0.9, allowed: nil, disallowed: nil}
39 casts << {long: 'cpus', short: 'C', type: 'uint', mandatory: false, default: 1, allowed: nil, disallowed: "0"}
41 options = Biopieces.options_parse(ARGV, casts)
43 tmpdir = Biopieces.mktmpdir
44 file_records = File.join(tmpdir, "data.stream")
45 file_fasta = File.join(tmpdir, "in.fna")
46 file_uclust = File.join(tmpdir, "out.uc")
48 Biopieces.open(options[:stream_in], file_records) do |input, output|
49 Fasta.open(file_fasta, 'w') do |fasta_io|
50 input.each_record do |record|
53 if record[:SEQ_NAME] and record[:SEQ]
54 fasta_io.puts Seq.new_bp(record).to_fasta
60 us = Usearch.new(file_fasta, file_uclust, options)
62 us.sortbylength unless options[:no_sort]
67 us.each_cluster do |cluster|
68 hash[cluster[:Q_ID].to_sym] = cluster.dup
71 Biopieces.open(file_records, options[:stream_out]) do |input, output|
72 input.each_record do |record|
73 if record[:SEQ_NAME] and record[:SEQ]
74 if hash[record[:SEQ_NAME].to_sym]
75 us = hash[record[:SEQ_NAME].to_sym]
76 record[:CLUSTER] = us[:CLUSTER].to_i
77 record[:IDENT] = us[:IDENT].to_i
78 record[:IDENT] = '*' if us[:TYPE] == 'S'
87 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<