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/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
41 # Error class for all exceptions to do with Seq.
42 class SeqError < StandardError; end
46 include PatternMatcher
48 attr_accessor :seq_name, :seq, :type, :qual
50 # Class method to instantiate a new Sequence object given
52 def self.new_bp(record)
53 seq_name = record[:SEQ_NAME]
55 type = record[:SEQ_TYPE]
56 qual = record[:SCORES]
58 self.new(seq_name, seq, type, qual)
61 # Class method that generates all possible oligos of a specifed length and type.
62 def self.generate_oligos(length, type)
63 raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
66 when /dna/ then alph = DNA
67 when /rna/ then alph = RNA
68 when /protein/ then alph = PROTEIN
70 raise SeqError, "Unknown sequence type: #{type}"
78 oligos.each do |oligo|
90 # Initialize a sequence object with the following arguments:
91 # - seq_name: Name of the sequence.
92 # - seq: The sequence.
93 # - type: The sequence type - DNA, RNA, or protein
94 # - qual: An Illumina type quality scores string.
95 def initialize(seq_name = nil, seq = nil, type = nil, qual = nil)
102 # Method that guesses and returns the sequence type
103 # by inspecting the first 100 residues.
105 raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
107 case self.seq[0 ... 100].downcase
108 when /[flpqie]/ then return "protein"
109 when /[u]/ then return "rna"
114 # Method that guesses and sets the sequence type
115 # by inspecting the first 100 residues.
117 self.type = self.type_guess
120 # Returns the length of a sequence.
122 self.seq.nil? ? 0 : self.seq.length
127 # Return the number indels in a sequence.
129 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
130 self.seq.scan(regex).size
133 # Method that returns true is a given sequence type is DNA.
138 # Method that returns true is a given sequence type is RNA.
143 # Method that returns true is a given sequence type is protein.
145 self.type == 'protein'
148 # Method to transcribe DNA to RNA.
150 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
151 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
153 self.seq.tr!('Tt','Uu')
156 # Method to reverse-transcribe RNA to DNA.
158 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
159 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
162 self.seq.tr!('Uu','Tt')
165 # Method that given a Seq entry returns a Biopieces record (a hash).
167 raise SeqError, "Missing seq_name" if self.seq_name.nil?
168 raise SeqError, "Missing seq" if self.seq.nil?
171 record[:SEQ_NAME] = self.seq_name
172 record[:SEQ] = self.seq
173 record[:SEQ_LEN] = self.length
174 record[:SCORES] = self.qual if self.qual
178 # Method that given a Seq entry returns a FASTA entry (a string).
179 def to_fasta(wrap = nil)
180 raise SeqError, "Missing seq_name" if self.seq_name.nil? or self.seq_name == ''
181 raise SeqError, "Missing seq" if self.seq.nil? or self.seq.empty?
183 seq_name = self.seq_name.to_s
187 seq.gsub!(/(.{#{wrap}})/) do |match|
194 ">" + seq_name + $/ + seq + $/
197 # Method that given a Seq entry returns a FASTQ entry (a string).
199 raise SeqError, "Missing seq_name" if self.seq_name.nil?
200 raise SeqError, "Missing seq" if self.seq.nil?
201 raise SeqError, "Missing qual" if self.qual.nil?
203 seq_name = self.seq_name.to_s
205 qual = self.qual.to_s
207 "@" + seq_name + $/ + seq + $/ + "+" + $/ + qual + $/
210 # Method that generates a unique key for a
211 # DNA sequence and return this key as a Fixnum.
215 self.seq.upcase.each_char do |char|
219 when 'A' then key |= 0
220 when 'C' then key |= 1
221 when 'G' then key |= 2
222 when 'T' then key |= 3
223 else raise SeqError, "Bad residue: #{char}"
230 # Method to reverse complement sequence.
231 def reverse_complement
237 alias :revcomp :reverse_complement
239 # Method to reverse the sequence.
242 self.qual.reverse! if self.qual
246 # Method that complements sequence including ambiguity codes.
248 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
251 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn')
253 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn')
255 raise SeqError, "Cannot complement sequence type: #{self.type}"
259 # Method to determine the Hamming Distance between
260 # two Sequence objects (case insensitive).
261 def hamming_distance(seq)
262 self.seq.upcase.hamming_distance(seq.seq.upcase)
265 # Method that generates a random sequence of a given length and type.
266 def generate(length, type)
267 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
277 raise SeqError, "Unknown sequence type: #{type}"
280 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
282 self.type = type.downcase
286 # Method to shuffle a sequence readomly inline.
288 self.seq = self.seq.split('').shuffle!.join
292 # Method that returns a subsequence of from a given start position
293 # and of a given length.
294 def subseq(start, length = self.length - start)
295 raise SeqError, "subsequence start: #{start} < 0" if start < 0
296 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
297 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
299 stop = start + length - 1
301 seq = self.seq[start .. stop]
302 qual = self.qual[start .. stop] unless self.qual.nil?
304 Seq.new(self.seq_name, seq, self.type, qual)
307 # Method that replaces a sequence with a subsequence from a given start position
308 # and of a given length.
309 def subseq!(start, length = self.length - start)
310 raise SeqError, "subsequence start: #{start} < 0" if start < 0
311 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
312 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
314 stop = start + length - 1
316 self.seq = self.seq[start .. stop]
317 self.qual = self.qual[start .. stop] unless self.qual.nil?
320 # Method that returns a subsequence of a given length
321 # beginning at a random position.
322 def subseq_rand(length)
323 if self.length - length + 1 == 0
326 start = rand(self.length - length + 1)
329 self.subseq(start, length)
332 def quality_trim_right(min)
333 raise SeqError, "no sequence" if self.seq.nil?
334 raise SeqError, "no quality score" if self.qual.nil?
335 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
337 regex_right = Regexp.new("[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+$")
339 self.qual.match(regex_right) do |m|
340 self.subseq!(0, $`.length) if $`.length > 0
346 def quality_trim_left(min)
347 raise SeqError, "no sequence" if self.seq.nil?
348 raise SeqError, "no quality score" if self.qual.nil?
349 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
351 regex_left = Regexp.new("^[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+")
353 self.qual.match(regex_left) do |m|
354 self.subseq!(m.to_s.length, self.length - m.to_s.length) if self.length - m.to_s.length > 0
360 def quality_trim(min)
361 self.quality_trim_right(min)
362 self.quality_trim_left(min)
366 # Method that returns the residue compositions of a sequence in
367 # a hash where the key is the residue and the value is the residue
372 self.seq.upcase.each_char do |char|
379 # Method that returns the length of the longest homopolymeric stretch
380 # found in a sequence.
381 def homopol_max(min = 1)
382 return 0 if self.seq.nil? or self.seq.empty?
386 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
388 min = match.size > min ? match.size : min
391 return 0 unless found
396 # Method that returns the percentage of hard masked residues
397 # or N's in a sequence.
399 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
402 # Method that returns the percentage of soft masked residues
403 # or lower cased residues in a sequence.
405 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
408 # Method to convert the quality scores from a specified base
410 def convert_phred2illumina!
411 self.qual.gsub!(/./) do |score|
412 score_phred = score.ord - SCORE_PHRED
413 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 41).include? score_phred
414 score_illumina = score_phred + SCORE_ILLUMINA
415 score = score_illumina.chr
419 # Method to convert the quality scores from Solexa odd/ratio to
421 def convert_solexa2illumina!
422 self.qual.gsub!(/./) do |score|
423 score = solexa_char2illumina_char(score)
429 # Method to convert a Solexa score (odd ratio) to
430 # a phred (probability) integer score.
431 def solexa2phred(score)
432 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
435 # Method to convert a Solexa score encoded using base
436 # 64 ASCII to a Phred score encoded using base 64 ASCII.
437 def solexa_char2illumina_char(char)
438 score_solexa = char.ord - 64
439 score_phred = solexa2phred(score_solexa)
440 (score_phred + 64).chr