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 # Method that guesses and returns the sequence type
90 # by inspecting the first 100 residues.
92 raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
94 case self.seq[0 ... 100].downcase
95 when /[flpqie]/ then return "protein"
96 when /[u]/ then return "rna"
101 # Method that guesses and sets the sequence type
102 # by inspecting the first 100 residues.
104 self.type = self.type_guess
107 # Returns the length of a sequence.
109 self.seq.nil? ? 0 : self.seq.length
114 # Return the number indels in a sequence.
116 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
117 self.seq.scan(regex).size
120 # Method that returns true is a given sequence type is DNA.
125 # Method that returns true is a given sequence type is RNA.
130 # Method that returns true is a given sequence type is protein.
132 self.type == 'protein'
135 # Method to transcribe DNA to RNA.
137 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
138 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
140 self.seq.tr!('Tt','Uu')
143 # Method to reverse-transcribe RNA to DNA.
145 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
146 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
149 self.seq.tr!('Uu','Tt')
152 # Method that given a Seq entry returns a Biopieces record (a hash).
154 raise SeqError, "Missing seq_name" if self.seq_name.nil?
155 raise SeqError, "Missing seq" if self.seq.nil?
158 record[:SEQ_NAME] = self.seq_name
159 record[:SEQ] = self.seq
160 record[:SEQ_LEN] = self.length
161 record[:SCORES] = self.qual if self.qual
165 # Method that given a Seq entry returns a FASTA entry (a string).
166 def to_fasta(wrap = nil)
167 raise SeqError, "Missing seq_name" if self.seq_name.nil?
168 raise SeqError, "Missing seq" if self.seq.nil?
170 seq_name = self.seq_name
174 seq.gsub!(/(.{#{wrap}})/) do |match|
181 ">#{seq_name}\n#{seq}\n"
184 # Method that generates a unique key for a
185 # DNA sequence and return this key as a Fixnum.
189 self.seq.upcase.each_char do |char|
193 when 'A' then key |= 0
194 when 'C' then key |= 1
195 when 'G' then key |= 2
196 when 'T' then key |= 3
197 else raise SeqError, "Bad residue: #{char}"
204 # Method to reverse complement sequence.
205 def reverse_complement
210 alias :revcomp :reverse_complement
212 # Method to reverse the sequence.
217 # Method that complements sequence including ambiguity codes.
219 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
222 self.seq.tr!( 'AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn' )
224 self.seq.tr!( 'AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn' )
226 raise SeqError, "Cannot complement sequence type: #{self.type}"
230 # Method that generates a random sequence of a given length and type.
231 def generate(length, type)
232 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
242 raise SeqError, "Unknown sequence type: #{type}"
245 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
247 self.type = type.downcase
251 # Method that returns a subsequence of from a given start position
252 # and of a given length.
253 def subseq(start, length = self.length - start)
254 raise SeqError, "subsequence start: #{start} < 0" if start < 0
255 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
256 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
258 stop = start + length - 1
260 seq = self.seq[start .. stop]
261 qual = self.qual[start .. stop] unless self.qual.nil?
263 Seq.new(self.seq_name, seq, self.type, qual)
266 # Method that replaces a sequence with a subsequence from a given start position
267 # and of a given length.
268 def subseq!(start, length = self.length - start)
269 raise SeqError, "subsequence start: #{start} < 0" if start < 0
270 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
271 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
273 stop = start + length - 1
275 self.seq = self.seq[start .. stop]
276 self.qual = self.qual[start .. stop] unless self.qual.nil?
279 # Method that returns a subsequence of a given length
280 # beginning at a random position.
281 def subseq_rand(length)
282 if self.length - length + 1 == 0
285 start = rand(self.length - length + 1)
288 self.subseq(start, length)
291 # Method that returns the residue compositions of a sequence in
292 # a hash where the key is the residue and the value is the residue
297 self.seq.upcase.each_char do |char|
304 # Method that returns the length of the longest homopolymeric stretch
305 # found in a sequence.
306 def homopol_max(min = 1)
307 return 0 if self.seq.nil? or self.seq.empty?
311 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
313 min = match.size > min ? match.size : min
316 return 0 unless found
321 # Method that returns the percentage of hard masked residues
322 # or N's in a sequence.
324 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
327 # Method that returns the percentage of soft masked residues
328 # or lower cased residues in a sequence.
330 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
333 # Method to convert the quality scores from a specified base
335 def convert_phred2illumina!
336 self.qual.gsub!(/./) do |score|
337 score_phred = score.ord - SCORE_PHRED
338 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 41).include? score_phred
339 score_illumina = score_phred + SCORE_ILLUMINA
340 score = score_illumina.chr
344 # Method to convert the quality scores from Solexa odd/ratio to
346 def convert_solexa2illumina!
347 self.qual.gsub!(/./) do |score|
348 score = solexa_char2illumina_char(score)
354 # Method to convert a Solexa score (odd ratio) to
355 # a phred (probability) integer score.
356 def solexa2phred(score)
357 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
360 # Method to convert a Solexa score encoded using base
361 # 64 ASCII to a Phred score encoded using base 64 ASCII.
362 def solexa_char2illumina_char(char)
363 score_solexa = char.ord - 64
364 score_phred = solexa2phred(score_solexa)
365 (score_phred + 64).chr