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'
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
49 attr_accessor :seq_name, :seq, :type, :qual
51 # Class method to instantiate a new Sequence object given
53 def self.new_bp(record)
54 seq_name = record[:SEQ_NAME]
56 type = record[:SEQ_TYPE]
57 qual = record[:SCORES]
59 self.new(seq_name, seq, type, qual)
62 # Class method that generates all possible oligos of a specifed length and type.
63 def self.generate_oligos(length, type)
64 raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
67 when /dna/ then alph = DNA
68 when /rna/ then alph = RNA
69 when /protein/ then alph = PROTEIN
71 raise SeqError, "Unknown sequence type: #{type}"
79 oligos.each do |oligo|
91 # Initialize a sequence object with the following arguments:
92 # - seq_name: Name of the sequence.
93 # - seq: The sequence.
94 # - type: The sequence type - DNA, RNA, or protein
95 # - qual: An Illumina type quality scores string.
96 def initialize(seq_name = nil, seq = nil, type = nil, qual = nil)
103 # Method that guesses and returns the sequence type
104 # by inspecting the first 100 residues.
106 raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
108 case self.seq[0 ... 100].downcase
109 when /[flpqie]/ then return "protein"
110 when /[u]/ then return "rna"
115 # Method that guesses and sets the sequence type
116 # by inspecting the first 100 residues.
118 self.type = self.type_guess
121 # Returns the length of a sequence.
123 self.seq.nil? ? 0 : self.seq.length
128 # Return the number indels in a sequence.
130 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
131 self.seq.scan(regex).size
134 # Method that returns true is a given sequence type is DNA.
139 # Method that returns true is a given sequence type is RNA.
144 # Method that returns true is a given sequence type is protein.
146 self.type == 'protein'
149 # Method to transcribe DNA to RNA.
151 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
152 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
154 self.seq.tr!('Tt','Uu')
157 # Method to reverse-transcribe RNA to DNA.
159 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
160 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
163 self.seq.tr!('Uu','Tt')
166 # Method that given a Seq entry returns a Biopieces record (a hash).
168 raise SeqError, "Missing seq_name" if self.seq_name.nil?
169 raise SeqError, "Missing seq" if self.seq.nil?
172 record[:SEQ_NAME] = self.seq_name
173 record[:SEQ] = self.seq
174 record[:SEQ_LEN] = self.length
175 record[:SCORES] = self.qual if self.qual
179 # Method that given a Seq entry returns a FASTA entry (a string).
180 def to_fasta(wrap = nil)
181 raise SeqError, "Missing seq_name" if self.seq_name.nil? or self.seq_name == ''
182 raise SeqError, "Missing seq" if self.seq.nil? or self.seq.empty?
184 seq_name = self.seq_name.to_s
188 seq.gsub!(/(.{#{wrap}})/) do |match|
195 ">" + seq_name + $/ + seq + $/
198 # Method that given a Seq entry returns a FASTQ entry (a string).
200 raise SeqError, "Missing seq_name" if self.seq_name.nil?
201 raise SeqError, "Missing seq" if self.seq.nil?
202 raise SeqError, "Missing qual" if self.qual.nil?
204 seq_name = self.seq_name.to_s
206 qual = self.qual.to_s
208 "@" + seq_name + $/ + seq + $/ + "+" + $/ + qual + $/
211 # Method that generates a unique key for a
212 # DNA sequence and return this key as a Fixnum.
216 self.seq.upcase.each_char do |char|
220 when 'A' then key |= 0
221 when 'C' then key |= 1
222 when 'G' then key |= 2
223 when 'T' then key |= 3
224 else raise SeqError, "Bad residue: #{char}"
231 # Method to reverse complement sequence.
232 def reverse_complement
238 alias :revcomp :reverse_complement
240 # Method to reverse the sequence.
243 self.qual.reverse! if self.qual
247 # Method that complements sequence including ambiguity codes.
249 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
252 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn')
254 self.seq.tr!('AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn')
256 raise SeqError, "Cannot complement sequence type: #{self.type}"
260 # Method to determine the Hamming Distance between
261 # two Sequence objects (case insensitive).
262 def hamming_distance(seq)
263 self.seq.upcase.hamming_distance(seq.seq.upcase)
266 # Method that generates a random sequence of a given length and type.
267 def generate(length, type)
268 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
278 raise SeqError, "Unknown sequence type: #{type}"
281 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
283 self.type = type.downcase
287 # Method to shuffle a sequence readomly inline.
289 self.seq = self.seq.split('').shuffle!.join
293 # Method that returns a subsequence of from a given start position
294 # and of a given length.
295 def subseq(start, length = self.length - start)
296 raise SeqError, "subsequence start: #{start} < 0" if start < 0
297 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
298 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
300 stop = start + length - 1
302 seq = self.seq[start .. stop]
303 qual = self.qual[start .. stop] unless self.qual.nil?
305 Seq.new(self.seq_name, seq, self.type, qual)
308 # Method that replaces a sequence with a subsequence from a given start position
309 # and of a given length.
310 def subseq!(start, length = self.length - start)
311 raise SeqError, "subsequence start: #{start} < 0" if start < 0
312 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
313 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
315 stop = start + length - 1
317 self.seq = self.seq[start .. stop]
318 self.qual = self.qual[start .. stop] unless self.qual.nil?
321 # Method that returns a subsequence of a given length
322 # beginning at a random position.
323 def subseq_rand(length)
324 if self.length - length + 1 == 0
327 start = rand(self.length - length + 1)
330 self.subseq(start, length)
333 def quality_trim_right(min)
334 raise SeqError, "no sequence" if self.seq.nil?
335 raise SeqError, "no quality score" if self.qual.nil?
336 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
338 regex_right = Regexp.new("[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+$")
340 self.qual.match(regex_right) do |m|
341 self.subseq!(0, $`.length) if $`.length > 0
347 def quality_trim_left(min)
348 raise SeqError, "no sequence" if self.seq.nil?
349 raise SeqError, "no quality score" if self.qual.nil?
350 raise SeqError, "minimum value: #{min} out of range #{SCORE_MIN} .. #{SCORE_MAX}" unless (SCORE_MIN .. SCORE_MAX).include? min
352 regex_left = Regexp.new("^[#{(SCORE_ILLUMINA).chr}-#{(SCORE_ILLUMINA + min).chr}]+")
354 self.qual.match(regex_left) do |m|
355 self.subseq!(m.to_s.length, self.length - m.to_s.length) if self.length - m.to_s.length > 0
361 def quality_trim(min)
362 self.quality_trim_right(min)
363 self.quality_trim_left(min)
367 # Method that returns the residue compositions of a sequence in
368 # a hash where the key is the residue and the value is the residue
373 self.seq.upcase.each_char do |char|
380 # Method that returns the length of the longest homopolymeric stretch
381 # found in a sequence.
382 def homopol_max(min = 1)
383 return 0 if self.seq.nil? or self.seq.empty?
387 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
389 min = match.size > min ? match.size : min
392 return 0 unless found
397 # Method that returns the percentage of hard masked residues
398 # or N's in a sequence.
400 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
403 # Method that returns the percentage of soft masked residues
404 # or lower cased residues in a sequence.
406 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
409 # Method to convert the quality scores from a specified base
411 def convert_phred2illumina!
412 self.qual.gsub!(/./) do |score|
413 score_phred = score.ord - SCORE_PHRED
414 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 41).include? score_phred
415 score_illumina = score_phred + SCORE_ILLUMINA
416 score = score_illumina.chr
420 # Method to convert the quality scores from Solexa odd/ratio to
422 def convert_solexa2illumina!
423 self.qual.gsub!(/./) do |score|
424 score = solexa_char2illumina_char(score)
430 # Method to convert a Solexa score (odd ratio) to
431 # a phred (probability) integer score.
432 def solexa2phred(score)
433 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
436 # Method to convert a Solexa score encoded using base
437 # 64 ASCII to a Phred score encoded using base 64 ASCII.
438 def solexa_char2illumina_char(char)
439 score_solexa = char.ord - 64
440 score_phred = solexa2phred(score_solexa)
441 (score_phred + 64).chr