1 # Copyright (C) 2007-2011 Martin A. Hansen.
3 # This program is free software; you can redistribute it and/or
4 # modify it under the terms of the GNU General Public License
5 # as published by the Free Software Foundation; either version 2
6 # of the License, or (at your option) any later version.
8 # This program is distributed in the hope that it will be useful,
9 # but WITHOUT ANY WARRANTY; without even the implied warranty of
10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11 # GNU General Public License for more details.
13 # You should have received a copy of the GNU General Public License
14 # along with this program; if not, write to the Free Software
15 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
17 # http://www.gnu.org/copyleft/gpl.html
19 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
21 # This software is part of the Biopieces framework (www.biopieces.org).
23 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
25 require 'maasha/digest'
26 require 'maasha/patternmatcher'
27 #require 'maasha/patscan'
32 PROTEIN = %w[f l s y c w p h q r i m t n k v a d e g]
35 # Quality scores bases
39 # Error class for all exceptions to do with Seq.
40 class SeqError < StandardError; end
44 include PatternMatcher
46 attr_accessor :seq_name, :seq, :type, :qual
48 # Method that generates all possible oligos of a specifed length and type.
49 def self.generate_oligos(length, type)
50 raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
53 when /dna/ then alph = DNA
54 when /rna/ then alph = RNA
55 when /protein/ then alph = PROTEIN
57 raise SeqError, "Unknown sequence type: #{type}"
65 oligos.each do |oligo|
77 # Initialize a sequence object with the following arguments:
78 # - seq_name: Name of the sequence.
79 # - seq: The sequence.
80 # - type: The sequence type - DNA, RNA, or protein
81 # - qual: An Illumina type quality scores string.
82 def initialize(seq_name = nil, seq = nil, type = nil, qual = nil)
89 # Returns the length of a sequence.
91 self.seq.nil? ? 0 : self.seq.length
96 # Return the number indels in a sequence.
98 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
99 self.seq.scan(regex).size
102 # Method that returns true is a given sequence type is DNA.
107 # Method that returns true is a given sequence type is RNA.
112 # Method that returns true is a given sequence type is protein.
114 self.type == 'protein'
117 # Method to transcribe DNA to RNA.
119 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
120 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
122 self.seq.tr!('Tt','Uu')
125 # Method to reverse-transcribe RNA to DNA.
127 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
128 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
131 self.seq.tr!('Uu','Tt')
134 # Method that given a Seq entry returns a Biopieces record (a hash).
136 raise SeqError, "Missing seq_name" if self.seq_name.nil?
137 raise SeqError, "Missing seq" if self.seq.nil?
140 record[:SEQ_NAME] = self.seq_name
141 record[:SEQ] = self.seq
142 record[:SEQ_LEN] = self.length
143 record[:SCORES] = self.qual if self.qual
147 # Method that given a Seq entry returns a FASTA entry (a string).
148 def to_fasta(wrap = nil)
149 raise SeqError, "Missing seq_name" if self.seq_name.nil?
150 raise SeqError, "Missing seq" if self.seq.nil?
152 seq_name = self.seq_name
156 seq.gsub!(/(.{#{wrap}})/) do |match|
163 ">#{seq_name}\n#{seq}\n"
166 # Method that generates a unique key for a
167 # DNA sequence and return this key as a Fixnum.
171 self.seq.upcase.each_char do |char|
175 when 'A' then key |= 0
176 when 'C' then key |= 1
177 when 'G' then key |= 2
178 when 'T' then key |= 3
179 else raise SeqError, "Bad residue: #{char}"
186 # Method to reverse complement sequence.
187 def reverse_complement
192 alias :revcomp :reverse_complement
194 # Method to reverse the sequence.
199 # Method that complements sequence including ambiguity codes.
201 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
204 self.seq.tr!( 'AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn' )
206 self.seq.tr!( 'AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn' )
208 raise SeqError, "Cannot complement sequence type: #{self.type}"
212 # Method that generates a random sequence of a given length and type.
213 def generate(length, type)
214 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
224 raise SeqError, "Unknown sequence type: #{type}"
227 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
229 self.type = type.downcase
233 # Method that returns a subsequence of from a given start position
234 # and of a given length.
235 def subseq(start, length = self.length - start)
236 raise SeqError, "subsequence start: #{start} < 0" if start < 0
237 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
238 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
240 stop = start + length - 1
242 seq = self.seq[start .. stop]
243 qual = self.qual[start .. stop] unless self.qual.nil?
245 Seq.new(self.seq_name, seq, self.type, qual)
248 # Method that replaces a sequence with a subsequence from a given start position
249 # and of a given length.
250 def subseq!(start, length = self.length - start)
251 raise SeqError, "subsequence start: #{start} < 0" if start < 0
252 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
253 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
255 stop = start + length - 1
257 self.seq = self.seq[start .. stop]
258 self.qual = self.qual[start .. stop] unless self.qual.nil?
261 # Method that returns a subsequence of a given length
262 # beginning at a random position.
263 def subseq_rand(length)
264 if self.length - length + 1 == 0
267 start = rand(self.length - length + 1)
270 self.subseq(start, length)
273 # Method that returns the residue compositions of a sequence in
274 # a hash where the key is the residue and the value is the residue
279 self.seq.upcase.each_char do |char|
286 # Method that returns the length of the longest homopolymeric stretch
287 # found in a sequence.
288 def homopol_max(min = 1)
289 return 0 if self.seq.nil? or self.seq.empty?
293 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
295 min = match.size > min ? match.size : min
298 return 0 unless found
303 # Method that returns the percentage of hard masked residues
304 # or N's in a sequence.
306 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
309 # Method that returns the percentage of soft masked residues
310 # or lower cased residues in a sequence.
312 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
315 # Method to convert the quality scores from a specified base
317 def convert_phred2illumina!
318 self.qual.gsub!(/./) do |score|
319 score_phred = score.ord - SCORE_PHRED
320 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 40).include? score_phred
321 score_illumina = score_phred + SCORE_ILLUMINA
322 score = score_illumina.chr
326 # Method to convert the quality scores from Solexa odd/ratio to
328 def convert_solexa2illumina!
329 self.qual.gsub!(/./) do |score|
330 score = solexa_char2illumina_char(score)
336 # Method to convert a Solexa score (odd ratio) to
337 # a phred (probability) integer score.
338 def solexa2phred(score)
339 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
342 # Method to convert a Solexa score encoded using base
343 # 64 ASCII to a Phred score encoded using base 64 ASCII.
344 def solexa_char2illumina_char(char)
345 score_solexa = char.ord - 64
346 score_phred = solexa2phred(score_solexa)
347 (score_phred + 64).chr