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/digest'
29 #require 'maasha/patscan'
34 PROTEIN = %w[f l s y c w p h q r i m t n k v a d e g]
37 # Quality scores bases
43 # Error class for all exceptions to do with Seq.
44 class SeqError < StandardError; end
48 include PatternMatcher
52 attr_accessor :seq_name, :seq, :type, :qual
54 # Class method to instantiate a new Sequence object given
56 def self.new_bp(record)
57 seq_name = record[:SEQ_NAME]
59 type = record[:SEQ_TYPE]
60 qual = record[:SCORES]
62 self.new(seq_name, seq, type, qual)
65 # Class method that generates all possible oligos of a specifed length and type.
66 def self.generate_oligos(length, type)
67 raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
70 when /dna/ then alph = DNA
71 when /rna/ then alph = RNA
72 when /protein/ then alph = PROTEIN
74 raise SeqError, "Unknown sequence type: #{type}"
82 oligos.each do |oligo|
94 # Initialize a sequence object with the following arguments:
95 # - seq_name: Name of the sequence.
96 # - seq: The sequence.
97 # - type: The sequence type - DNA, RNA, or protein
98 # - qual: An Illumina type quality scores string.
99 def initialize(seq_name = nil, seq = nil, type = nil, qual = nil)
106 # Method that guesses and returns the sequence type
107 # by inspecting the first 100 residues.
109 raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
111 case self.seq[0 ... 100].downcase
112 when /[flpqie]/ then return "protein"
113 when /[u]/ then return "rna"
118 # Method that guesses and sets the sequence type
119 # by inspecting the first 100 residues.
121 self.type = self.type_guess
124 # Returns the length of a sequence.
126 self.seq.nil? ? 0 : self.seq.length
131 # Return the number indels in a sequence.
133 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
134 self.seq.scan(regex).size
137 # Method that returns true is a given sequence type is DNA.
142 # Method that returns true is a given sequence type is RNA.
147 # Method that returns true is a given sequence type is protein.
149 self.type == 'protein'
152 # Method to transcribe DNA to RNA.
154 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
155 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
157 self.seq.tr!('Tt','Uu')
160 # Method to reverse-transcribe RNA to DNA.
162 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
163 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
166 self.seq.tr!('Uu','Tt')
169 # Method that given a Seq entry returns a Biopieces record (a hash).
171 raise SeqError, "Missing seq_name" if self.seq_name.nil?
172 raise SeqError, "Missing seq" if self.seq.nil?
175 record[:SEQ_NAME] = self.seq_name
176 record[:SEQ] = self.seq
177 record[:SEQ_LEN] = self.length
178 record[:SCORES] = self.qual if self.qual
182 # Method that given a Seq entry returns a FASTA entry (a string).
183 def to_fasta(wrap = nil)
184 raise SeqError, "Missing seq_name" if self.seq_name.nil? or self.seq_name == ''
185 raise SeqError, "Missing seq" if self.seq.nil? or self.seq.empty?
187 seq_name = self.seq_name.to_s
191 seq.gsub!(/(.{#{wrap}})/) do |match|
198 ">" + seq_name + $/ + seq + $/
201 # Method that given a Seq entry returns a FASTQ entry (a string).
203 raise SeqError, "Missing seq_name" if self.seq_name.nil?
204 raise SeqError, "Missing seq" if self.seq.nil?
205 raise SeqError, "Missing qual" if self.qual.nil?
207 seq_name = self.seq_name.to_s
209 qual = self.qual.to_s
211 "@" + seq_name + $/ + seq + $/ + "+" + $/ + qual + $/
214 # Method that generates a unique key for a
215 # DNA sequence and return this key as a Fixnum.
219 self.seq.upcase.each_char do |char|
223 when 'A' then key |= 0
224 when 'C' then key |= 1
225 when 'G' then key |= 2
226 when 'T' then key |= 3
227 else raise SeqError, "Bad residue: #{char}"
234 # Method to reverse complement sequence.
235 def reverse_complement
241 alias :revcomp :reverse_complement
243 # Method to reverse the sequence.
246 self.qual.reverse! if self.qual
250 # Method that complements sequence including ambiguity codes.
252 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
255 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn')
257 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn')
259 raise SeqError, "Cannot complement sequence type: #{self.type}"
263 # Method to determine the Hamming Distance between
264 # two Sequence objects (case insensitive).
265 def hamming_distance(seq)
266 self.seq.upcase.hamming_distance(seq.seq.upcase)
269 # Method that generates a random sequence of a given length and type.
270 def generate(length, type)
271 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
281 raise SeqError, "Unknown sequence type: #{type}"
284 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
286 self.type = type.downcase
290 # Method to shuffle a sequence readomly inline.
292 self.seq = self.seq.split('').shuffle!.join
296 # Method that returns a subsequence of from a given start position
297 # and of a given length.
298 def subseq(start, length = self.length - start)
299 raise SeqError, "subsequence start: #{start} < 0" if start < 0
300 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
301 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
303 stop = start + length - 1
305 seq = self.seq[start .. stop]
306 qual = self.qual[start .. stop] unless self.qual.nil?
308 Seq.new(self.seq_name, seq, self.type, qual)
311 # Method that replaces a sequence with a subsequence from a given start position
312 # and of a given length.
313 def subseq!(start, length = self.length - start)
314 raise SeqError, "subsequence start: #{start} < 0" if start < 0
315 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
316 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
318 stop = start + length - 1
320 self.seq = self.seq[start .. stop]
321 self.qual = self.qual[start .. stop] unless self.qual.nil?
324 # Method that returns a subsequence of a given length
325 # beginning at a random position.
326 def subseq_rand(length)
327 if self.length - length + 1 == 0
330 start = rand(self.length - length + 1)
333 self.subseq(start, length)
336 def quality_trim_right(min)
337 raise SeqError, "no sequence" if self.seq.nil?
338 raise SeqError, "no quality score" if self.qual.nil?
339 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
341 regex_right = Regexp.new("[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+$")
343 self.qual.match(regex_right) do |m|
344 self.subseq!(0, $`.length) if $`.length > 0
350 def quality_trim_left(min)
351 raise SeqError, "no sequence" if self.seq.nil?
352 raise SeqError, "no quality score" if self.qual.nil?
353 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
355 regex_left = Regexp.new("^[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+")
357 self.qual.match(regex_left) do |m|
358 self.subseq!(m.to_s.length, self.length - m.to_s.length) if self.length - m.to_s.length > 0
364 def quality_trim(min)
365 self.quality_trim_right(min)
366 self.quality_trim_left(min)
370 # Method that returns the residue compositions of a sequence in
371 # a hash where the key is the residue and the value is the residue
376 self.seq.upcase.each_char do |char|
383 # Method that returns the length of the longest homopolymeric stretch
384 # found in a sequence.
385 def homopol_max(min = 1)
386 return 0 if self.seq.nil? or self.seq.empty?
390 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
392 min = match.size > min ? match.size : min
395 return 0 unless found
400 # Method that returns the percentage of hard masked residues
401 # or N's in a sequence.
403 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
406 # Method that returns the percentage of soft masked residues
407 # or lower cased residues in a sequence.
409 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
412 # Method to convert the quality scores from a specified base
414 def convert_phred2illumina!
415 self.qual.gsub!(/./) do |score|
416 score_phred = score.ord - SCORE_PHRED
417 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 41).include? score_phred
418 score_illumina = score_phred + SCORE_ILLUMINA
419 score = score_illumina.chr
423 # Method to convert the quality scores from Solexa odd/ratio to
425 def convert_solexa2illumina!
426 self.qual.gsub!(/./) do |score|
427 score = solexa_char2illumina_char(score)
433 # Method to convert a Solexa score (odd ratio) to
434 # a phred (probability) integer score.
435 def solexa2phred(score)
436 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
439 # Method to convert a Solexa score encoded using base
440 # 64 ASCII to a Phred score encoded using base 64 ASCII.
441 def solexa_char2illumina_char(char)
442 score_solexa = char.ord - 64
443 score_phred = solexa2phred(score_solexa)
444 (score_phred + 64).chr