require 'maasha/seq/trim'
require 'narray'
-autoload :BackTrack, 'maasha/seq/backtrack.rb'
-autoload :Dynamic, 'maasha/seq/dynamic.rb'
+autoload :BackTrack, 'maasha/seq/backtrack.rb'
+autoload :Dynamic, 'maasha/seq/dynamic.rb'
+autoload :Homopolymer, 'maasha/seq/homopolymer.rb'
# Residue alphabets
DNA = %w[a t c g]
def self.new_bp(record)
seq_name = record[:SEQ_NAME]
seq = record[:SEQ]
- type = record[:SEQ_TYPE]
+ type = record[:SEQ_TYPE].to_sym if record[:SEQ_TYPE]
qual = record[:SCORES]
self.new(seq_name, seq, type, qual)
raise SeqError, "Cannot generate negative oligo length: #{length}" if length <= 0
case type.downcase
- when /dna/ then alph = DNA
- when /rna/ then alph = RNA
- when /protein/ then alph = PROTEIN
+ when :dna then alph = DNA
+ when :rna then alph = RNA
+ when :protein then alph = PROTEIN
else
raise SeqError, "Unknown sequence type: #{type}"
end
raise SeqError, "Guess failed: sequence is nil" if self.seq.nil?
case self.seq[0 ... 100].downcase
- when /[flpqie]/ then return "protein"
- when /[u]/ then return "rna"
- else return "dna"
+ when /[flpqie]/ then return :protein
+ when /[u]/ then return :rna
+ else return :dna
end
end
# Method that returns true is a given sequence type is DNA.
def is_dna?
- self.type == 'dna'
+ self.type == :dna
end
# Method that returns true is a given sequence type is RNA.
def is_rna?
- self.type == 'rna'
+ self.type == :rna
end
# Method that returns true is a given sequence type is protein.
def is_protein?
- self.type == 'protein'
+ self.type == :protein
end
# Method to transcribe DNA to RNA.
def to_rna
raise SeqError, "Cannot transcribe 0 length sequence" if self.length == 0
raise SeqError, "Cannot transcribe sequence type: #{self.type}" unless self.is_dna?
- self.type = 'rna'
+ self.type = :rna
self.seq.tr!('Tt','Uu')
end
def to_dna
raise SeqError, "Cannot reverse-transcribe 0 length sequence" if self.length == 0
raise SeqError, "Cannot reverse-transcribe sequence type: #{self.type}" unless self.is_rna?
-
- self.type = 'dna'
+ self.type = :dna
self.seq.tr!('Uu','Tt')
end
# Method to translate a DNA sequence to protein.
def translate!(trans_tab = 11)
- raise SeqError, "Sequence type must be 'dna' - not #{self.type}" unless self.type == 'dna'
+ raise SeqError, "Sequence type must be 'dna' - not #{self.type}" unless self.type == :dna
raise SeqError, "Sequence length must be a multiplum of 3 - was: #{self.length}" unless (self.length % 3) == 0
case trans_tab
self.seq = protein
self.qual = nil
- self.type = "protein"
+ self.type = :protein
self
end
def generate(length, type)
raise SeqError, "Cannot generate sequence length < 1: #{length}" if length <= 0
- case type.downcase
- when "dna"
- alph = DNA
- when "rna"
- alph = RNA
- when "protein"
- alph = PROTEIN
+ case type
+ when :dna then alph = DNA
+ when :rna then alph = RNA
+ when :protein then alph = PROTEIN
else
raise SeqError, "Unknown sequence type: #{type}"
end
seq_new = Array.new(length) { alph[rand(alph.size)] }.join("")
self.seq = seq_new
- self.type = type.downcase
+ self.type = type
seq_new
end
self
end
+ # Method to add two Seq objects.
+ def +(entry)
+ new_entry = Seq.new()
+ new_entry.seq = self.seq + entry.seq
+ new_entry.type = self.type if self.type == entry.type
+ new_entry.qual = self.qual + entry.qual if self.qual and entry.qual
+ new_entry
+ end
+
+ # Method to concatenate sequence entries.
+ def <<(entry)
+ raise SeqError, "sequences of different types" unless self.type == entry.type
+ raise SeqError, "qual is missing in one entry" unless self.qual.class == entry.qual.class
+
+ self.seq << entry.seq
+ self.qual << entry.qual unless entry.qual.nil?
+
+ self
+ end
+
+ # Index method for Seq objects.
+ def [](*args)
+ entry = Seq.new
+ entry.seq_name = self.seq_name
+ entry.seq = self.seq[*args]
+ entry.type = self.type
+ entry.qual = self.qual[*args] unless self.qual.nil?
+
+ entry
+ end
+
+ # Index assignment method for Seq objects.
+ def []=(*args, entry)
+ self.seq[*args] = entry.seq[*args]
+ self.qual[*args] = entry.qual[*args] unless self.qual.nil?
+
+ self
+ end
+
# Method that returns a subsequence of from a given start position
# and of a given length.
def subseq(start, length = self.length - start)
qual = self.qual[start .. stop] unless self.qual.nil?
end
- Seq.new(self.seq_name, seq, self.type, qual) # TODO changed self.seq_name.dup to self.seq_name -> consequence?
+ seq_name = self.seq_name.nil? ? nil : self.seq_name.dup
+
+ Seq.new(seq_name, seq, self.type, qual)
end
# Method that replaces a sequence with a subsequence from a given start position
comp
end
- # Method that returns the length of the longest homopolymeric stretch
- # found in a sequence.
- def homopol_max(min = 1)
- return 0 if self.seq.nil? or self.seq.empty?
-
- found = false
-
- self.seq.upcase.scan(/A{#{min},}|T{#{min},}|G{#{min},}|C{#{min},}|N{#{min},}/) do |match|
- found = true
- min = match.size > min ? match.size : min
- end
-
- return 0 unless found
-
- min
- end
-
# Method that returns the percentage of hard masked residues
# or N's in a sequence.
def hard_mask