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/backtrack'
28 #require 'maasha/patscan'
33 PROTEIN = %w[f l s y c w p h q r i m t n k v a d e g]
36 # Quality scores bases
42 # Error class for all exceptions to do with Seq.
43 class SeqError < StandardError; end
47 include PatternMatcher
50 attr_accessor :seq_name, :seq, :type, :qual
52 # Class method to instantiate a new Sequence object given
54 def self.new_bp(record)
55 seq_name = record[:SEQ_NAME]
57 type = record[:SEQ_TYPE]
58 qual = record[:SCORES]
60 self.new(seq_name, seq, type, qual)
63 # Class method that generates all possible oligos of a specifed length and type.
64 def self.generate_oligos(length, type)
65 raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
68 when /dna/ then alph = DNA
69 when /rna/ then alph = RNA
70 when /protein/ then alph = PROTEIN
72 raise SeqError, "Unknown sequence type: #{type}"
80 oligos.each do |oligo|
92 # Initialize a sequence object with the following arguments:
93 # - seq_name: Name of the sequence.
94 # - seq: The sequence.
95 # - type: The sequence type - DNA, RNA, or protein
96 # - qual: An Illumina type quality scores string.
97 def initialize(seq_name = nil, seq = nil, type = nil, qual = nil)
104 # Method that guesses and returns the sequence type
105 # by inspecting the first 100 residues.
107 raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
109 case self.seq[0 ... 100].downcase
110 when /[flpqie]/ then return "protein"
111 when /[u]/ then return "rna"
116 # Method that guesses and sets the sequence type
117 # by inspecting the first 100 residues.
119 self.type = self.type_guess
122 # Returns the length of a sequence.
124 self.seq.nil? ? 0 : self.seq.length
129 # Return the number indels in a sequence.
131 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
132 self.seq.scan(regex).size
135 # Method that returns true is a given sequence type is DNA.
140 # Method that returns true is a given sequence type is RNA.
145 # Method that returns true is a given sequence type is protein.
147 self.type == 'protein'
150 # Method to transcribe DNA to RNA.
152 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
153 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
155 self.seq.tr!('Tt','Uu')
158 # Method to reverse-transcribe RNA to DNA.
160 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
161 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
164 self.seq.tr!('Uu','Tt')
167 # Method that given a Seq entry returns a Biopieces record (a hash).
169 raise SeqError, "Missing seq_name" if self.seq_name.nil?
170 raise SeqError, "Missing seq" if self.seq.nil?
173 record[:SEQ_NAME] = self.seq_name
174 record[:SEQ] = self.seq
175 record[:SEQ_LEN] = self.length
176 record[:SCORES] = self.qual if self.qual
180 # Method that given a Seq entry returns a FASTA entry (a string).
181 def to_fasta(wrap = nil)
182 raise SeqError, "Missing seq_name" if self.seq_name.nil? or self.seq_name == ''
183 raise SeqError, "Missing seq" if self.seq.nil? or self.seq.empty?
185 seq_name = self.seq_name.to_s
189 seq.gsub!(/(.{#{wrap}})/) do |match|
196 ">" + seq_name + $/ + seq + $/
199 # Method that given a Seq entry returns a FASTQ entry (a string).
201 raise SeqError, "Missing seq_name" if self.seq_name.nil?
202 raise SeqError, "Missing seq" if self.seq.nil?
203 raise SeqError, "Missing qual" if self.qual.nil?
205 seq_name = self.seq_name.to_s
207 qual = self.qual.to_s
209 "@" + seq_name + $/ + seq + $/ + "+" + $/ + qual + $/
212 # Method that generates a unique key for a
213 # DNA sequence and return this key as a Fixnum.
217 self.seq.upcase.each_char do |char|
221 when 'A' then key |= 0
222 when 'C' then key |= 1
223 when 'G' then key |= 2
224 when 'T' then key |= 3
225 else raise SeqError, "Bad residue: #{char}"
232 # Method to reverse complement sequence.
233 def reverse_complement
239 alias :revcomp :reverse_complement
241 # Method to reverse the sequence.
244 self.qual.reverse! if self.qual
248 # Method that complements sequence including ambiguity codes.
250 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
253 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn')
255 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn')
257 raise SeqError, "Cannot complement sequence type: #{self.type}"
261 # Method to determine the Hamming Distance between
262 # two Sequence objects (case insensitive).
263 def hamming_distance(seq)
264 self.seq.upcase.hamming_distance(seq.seq.upcase)
267 # Method that generates a random sequence of a given length and type.
268 def generate(length, type)
269 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
279 raise SeqError, "Unknown sequence type: #{type}"
282 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
284 self.type = type.downcase
288 # Method to shuffle a sequence readomly inline.
290 self.seq = self.seq.split('').shuffle!.join
294 # Method that returns a subsequence of from a given start position
295 # and of a given length.
296 def subseq(start, length = self.length - start)
297 raise SeqError, "subsequence start: #{start} < 0" if start < 0
298 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
299 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
301 stop = start + length - 1
303 seq = self.seq[start .. stop]
304 qual = self.qual[start .. stop] unless self.qual.nil?
306 Seq.new(self.seq_name, seq, self.type, qual)
309 # Method that replaces a sequence with a subsequence from a given start position
310 # and of a given length.
311 def subseq!(start, length = self.length - start)
312 raise SeqError, "subsequence start: #{start} < 0" if start < 0
313 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
314 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
316 stop = start + length - 1
318 self.seq = self.seq[start .. stop]
319 self.qual = self.qual[start .. stop] unless self.qual.nil?
322 # Method that returns a subsequence of a given length
323 # beginning at a random position.
324 def subseq_rand(length)
325 if self.length - length + 1 == 0
328 start = rand(self.length - length + 1)
331 self.subseq(start, length)
334 def quality_trim_right(min)
335 raise SeqError, "no sequence" if self.seq.nil?
336 raise SeqError, "no quality score" if self.qual.nil?
337 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
339 regex_right = Regexp.new("[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+$")
341 self.qual.match(regex_right) do |m|
342 self.subseq!(0, $`.length) if $`.length > 0
348 def quality_trim_left(min)
349 raise SeqError, "no sequence" if self.seq.nil?
350 raise SeqError, "no quality score" if self.qual.nil?
351 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
353 regex_left = Regexp.new("^[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+")
355 self.qual.match(regex_left) do |m|
356 self.subseq!(m.to_s.length, self.length - m.to_s.length) if self.length - m.to_s.length > 0
362 def quality_trim(min)
363 self.quality_trim_right(min)
364 self.quality_trim_left(min)
368 # Method that returns the residue compositions of a sequence in
369 # a hash where the key is the residue and the value is the residue
374 self.seq.upcase.each_char do |char|
381 # Method that returns the length of the longest homopolymeric stretch
382 # found in a sequence.
383 def homopol_max(min = 1)
384 return 0 if self.seq.nil? or self.seq.empty?
388 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
390 min = match.size > min ? match.size : min
393 return 0 unless found
398 # Method that returns the percentage of hard masked residues
399 # or N's in a sequence.
401 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
404 # Method that returns the percentage of soft masked residues
405 # or lower cased residues in a sequence.
407 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
410 # Method to convert the quality scores from a specified base
412 def convert_phred2illumina!
413 self.qual.gsub!(/./) do |score|
414 score_phred = score.ord - SCORE_PHRED
415 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 41).include? score_phred
416 score_illumina = score_phred + SCORE_ILLUMINA
417 score = score_illumina.chr
421 # Method to convert the quality scores from Solexa odd/ratio to
423 def convert_solexa2illumina!
424 self.qual.gsub!(/./) do |score|
425 score = solexa_char2illumina_char(score)
431 # Method to convert a Solexa score (odd ratio) to
432 # a phred (probability) integer score.
433 def solexa2phred(score)
434 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
437 # Method to convert a Solexa score encoded using base
438 # 64 ASCII to a Phred score encoded using base 64 ASCII.
439 def solexa_char2illumina_char(char)
440 score_solexa = char.ord - 64
441 score_phred = solexa2phred(score_solexa)
442 (score_phred + 64).chr