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
40 # Error class for all exceptions to do with Seq.
41 class SeqError < StandardError; end
45 include PatternMatcher
47 attr_accessor :seq_name, :seq, :type, :qual
49 # Method that generates all possible oligos of a specifed length and type.
50 def self.generate_oligos(length, type)
51 raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
54 when /dna/ then alph = DNA
55 when /rna/ then alph = RNA
56 when /protein/ then alph = PROTEIN
58 raise SeqError, "Unknown sequence type: #{type}"
66 oligos.each do |oligo|
78 # Initialize a sequence object with the following arguments:
79 # - seq_name: Name of the sequence.
80 # - seq: The sequence.
81 # - type: The sequence type - DNA, RNA, or protein
82 # - qual: An Illumina type quality scores string.
83 def initialize(seq_name = nil, seq = nil, type = nil, qual = nil)
90 # Method that guesses and returns the sequence type
91 # by inspecting the first 100 residues.
93 raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
95 case self.seq[0 ... 100].downcase
96 when /[flpqie]/ then return "protein"
97 when /[u]/ then return "rna"
102 # Method that guesses and sets the sequence type
103 # by inspecting the first 100 residues.
105 self.type = self.type_guess
108 # Returns the length of a sequence.
110 self.seq.nil? ? 0 : self.seq.length
115 # Return the number indels in a sequence.
117 regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
118 self.seq.scan(regex).size
121 # Method that returns true is a given sequence type is DNA.
126 # Method that returns true is a given sequence type is RNA.
131 # Method that returns true is a given sequence type is protein.
133 self.type == 'protein'
136 # Method to transcribe DNA to RNA.
138 raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
139 raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
141 self.seq.tr!('Tt','Uu')
144 # Method to reverse-transcribe RNA to DNA.
146 raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
147 raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
150 self.seq.tr!('Uu','Tt')
153 # Method that given a Seq entry returns a Biopieces record (a hash).
155 raise SeqError, "Missing seq_name" if self.seq_name.nil?
156 raise SeqError, "Missing seq" if self.seq.nil?
159 record[:SEQ_NAME] = self.seq_name
160 record[:SEQ] = self.seq
161 record[:SEQ_LEN] = self.length
162 record[:SCORES] = self.qual if self.qual
166 # Method that given a Seq entry returns a FASTA entry (a string).
167 def to_fasta(wrap = nil)
168 raise SeqError, "Missing seq_name" if self.seq_name.nil?
169 raise SeqError, "Missing seq" if self.seq.nil?
171 seq_name = self.seq_name
175 seq.gsub!(/(.{#{wrap}})/) do |match|
182 ">#{seq_name}\n#{seq}\n"
185 # Method that generates a unique key for a
186 # DNA sequence and return this key as a Fixnum.
190 self.seq.upcase.each_char do |char|
194 when 'A' then key |= 0
195 when 'C' then key |= 1
196 when 'G' then key |= 2
197 when 'T' then key |= 3
198 else raise SeqError, "Bad residue: #{char}"
205 # Method to reverse complement sequence.
206 def reverse_complement
211 alias :revcomp :reverse_complement
213 # Method to reverse the sequence.
218 # Method that complements sequence including ambiguity codes.
220 raise SeqError, "Cannot complement 0 length sequence" if self.length == 0
223 self.seq.tr!( 'AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'TCGAAYRWSKMDHBVNtcgaayrwskmdhbvn' )
225 self.seq.tr!( 'AGCUTRYWSMKHDVBNagcutrywsmkhdvbn', 'UCGAAYRWSKMDHBVNucgaayrwskmdhbvn' )
227 raise SeqError, "Cannot complement sequence type: #{self.type}"
231 # Method to determine the Hamming Distance between
232 # two Sequence objects (case insensitive).
233 def hamming_distance(seq)
234 self.seq.upcase.hamming_distance(seq.seq.upcase)
237 # Method that generates a random sequence of a given length and type.
238 def generate(length, type)
239 raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
249 raise SeqError, "Unknown sequence type: #{type}"
252 seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
254 self.type = type.downcase
258 # Method that returns a subsequence of from a given start position
259 # and of a given length.
260 def subseq(start, length = self.length - start)
261 raise SeqError, "subsequence start: #{start} < 0" if start < 0
262 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
263 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
265 stop = start + length - 1
267 seq = self.seq[start .. stop]
268 qual = self.qual[start .. stop] unless self.qual.nil?
270 Seq.new(self.seq_name, seq, self.type, qual)
273 # Method that replaces a sequence with a subsequence from a given start position
274 # and of a given length.
275 def subseq!(start, length = self.length - start)
276 raise SeqError, "subsequence start: #{start} < 0" if start < 0
277 raise SeqError, "subsequence length: #{length} < 1" if length <= 0
278 raise SeqError, "subsequence start + length > Seq.length: #{start} + #{length} > #{self.length}" if start + length > self.length
280 stop = start + length - 1
282 self.seq = self.seq[start .. stop]
283 self.qual = self.qual[start .. stop] unless self.qual.nil?
286 # Method that returns a subsequence of a given length
287 # beginning at a random position.
288 def subseq_rand(length)
289 if self.length - length + 1 == 0
292 start = rand(self.length - length + 1)
295 self.subseq(start, length)
298 # Method that returns the residue compositions of a sequence in
299 # a hash where the key is the residue and the value is the residue
304 self.seq.upcase.each_char do |char|
311 # Method that returns the length of the longest homopolymeric stretch
312 # found in a sequence.
313 def homopol_max(min = 1)
314 return 0 if self.seq.nil? or self.seq.empty?
318 self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
320 min = match.size > min ? match.size : min
323 return 0 unless found
328 # Method that returns the percentage of hard masked residues
329 # or N's in a sequence.
331 ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
334 # Method that returns the percentage of soft masked residues
335 # or lower cased residues in a sequence.
337 ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
340 # Method to convert the quality scores from a specified base
342 def convert_phred2illumina!
343 self.qual.gsub!(/./) do |score|
344 score_phred = score.ord - SCORE_PHRED
345 raise SeqError, "Bad Phred score: #{score} (#{score_phred})" unless (0 .. 41).include? score_phred
346 score_illumina = score_phred + SCORE_ILLUMINA
347 score = score_illumina.chr
351 # Method to convert the quality scores from Solexa odd/ratio to
353 def convert_solexa2illumina!
354 self.qual.gsub!(/./) do |score|
355 score = solexa_char2illumina_char(score)
361 # Method to convert a Solexa score (odd ratio) to
362 # a phred (probability) integer score.
363 def solexa2phred(score)
364 (10.0 * Math.log(10.0 ** (score / 10.0) + 1.0, 10)).to_i
367 # Method to convert a Solexa score encoded using base
368 # 64 ASCII to a Phred score encoded using base 64 ASCII.
369 def solexa_char2illumina_char(char)
370 score_solexa = char.ord - 64
371 score_phred = solexa2phred(score_solexa)
372 (score_phred + 64).chr