From: martinahansen Date: Sat, 29 Jan 2011 15:45:25 +0000 (+0000) Subject: added shred_seq biopiece X-Git-Url: https://git.donarmstrong.com/?a=commitdiff_plain;h=d8fb5588758b9d40e562ee66519ee6772ad511a9;p=biopieces.git added shred_seq biopiece git-svn-id: http://biopieces.googlecode.com/svn/trunk@1222 74ccb610-7750-0410-82ae-013aeee3265d --- diff --git a/bp_bin/shred_seq b/bp_bin/shred_seq new file mode 100755 index 0000000..a59b688 --- /dev/null +++ b/bp_bin/shred_seq @@ -0,0 +1,94 @@ +#!/usr/bin/env ruby + +# Copyright (C) 2007-2011 Martin A. Hansen. + +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# as published by the Free Software Foundation; either version 2 +# of the License, or (at your option) any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + +# http://www.gnu.org/copyleft/gpl.html + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + +# This program is part of the Biopieces framework (www.biopieces.org). + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + +# Shred sequences in the stream into subsequences. + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + + +require 'biopieces' +require 'seq' +require 'pp' + +class Seq + # Method that shreds the sequence of a sequence object into + # random subsequences of a specified size. Subsequences are + # alternatly picked from the + or - strand (i.e. reverse complemented) + # until the specified coverage is reached. + # + # seq.shred { |subseq| } -> Seq + # seq.shred -> [] + def shred(size, max_cov) + entries = [] + sum = 0 + strand = '+' + + while (sum / self.seq.length) < max_cov + start = rand(self.seq.size - size) + stop = start + size - 1 + seq_name = self.seq_name + "[#{start + 1}-#{stop + 1}:#{strand}]" + seq = self.seq[start .. stop] + entry = Seq.new(seq_name, seq, 'dna') + + entry.revcomp if strand == '-' + + if block_given? + yield entry + else + entries << entry + end + + strand = (strand == '+') ? '-' : '+' + + sum += size + end + + entries + end +end + +casts = [] +casts << {:long=>'size', :short=>'s', :type=>'uint', :mandatory=>true, :default=>500, :allowed=>nil, :disallowed=>'0'} +casts << {:long=>'coverage', :short=>'c', :type=>'uint', :mandatory=>true, :default=>100, :allowed=>nil, :disallowed=>'0'} + +bp = Biopieces.new + +options = bp.parse(ARGV, casts) + +bp.each_record do |record| + if record.has_key? :SEQ + entry = Seq.new(record[:SEQ_NAME], record[:SEQ], record[:SCORES]) + + entry.shred(options[:size], options[:coverage]) do |subentry| + bp.puts subentry.to_bp + end + end +end + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + + +__END__