The Computer Language
Benchmarks Game

k-nucleotide Ruby program

source code

# The Computer Language Benchmarks Game
# http://benchmarksgame.alioth.debian.org
#
# contributed by jose fco. gonzalez
# modified by Sokolov Yura
# Parallelism by Rick Branson

$seq = String.new

def frequency(seq, length)
  frequencies = Hash.new(0)
  ns          = seq.length + 1 - length
  
  for i in (0 ... ns)
    frequencies[seq[i, length]] += 1
  end
  
  [ns, frequencies]
end

def sort_by_freq(seq, length)
  ret       = ""
  n, table  = frequency(seq, length)

  table.sort{|a,b| b[1] <=> a[1]}.each do |v|
      ret += "%s %.3f\n" % [v[0].upcase,((v[1]*100).to_f/n)]
  end
  
  ret += "\n"
end

def find_seq(seq, s)
  n, table = frequency(seq, s.length)
  "#{table[s].to_s}\t#{s.upcase}\n"
end

line = STDIN.gets while line !~ /^>THREE/
line = STDIN.gets
while (line !~ /^>/) & line do
    $seq << line.chomp
    line = STDIN.gets
end

class Worker
  def initialize(&block)
    if RUBY_PLATFORM == "java"
      @t = Thread.new do
        Thread.current[:result] = yield
      end
    else
      @r, @w = IO.pipe
      @p = Process.fork do
        @r.close
        @w.write yield
        @w.close
      end
      
      @w.close
    end
  end
  
  def result
    if RUBY_PLATFORM == "java"
      @t.join
      @t[:result]
    else
      ret = @r.read
      @r.close
      Process.wait(@p)
      ret
    end
  end
end

FREQS   = [1, 2]
NUCLEOS = %w(ggt ggta ggtatt ggtattttaatt ggtattttaatttatagt)

workers =   FREQS.map   { |i| Worker.new { sort_by_freq($seq, i) } }
workers +=  NUCLEOS.map { |s| Worker.new { find_seq($seq, s) } }
  
results = workers.map { |w| w.result }
print results.join
    

notes, command-line, and program output

NOTES:
64-bit Ubuntu quad core
ruby 2.4.0p0 (2016-12-24 revision 57164) [x86_64-linux]


Sun, 12 Feb 2017 05:58:03 GMT

COMMAND LINE:
/usr/local/src/ruby/bin/ruby -W0 knucleotide.yarv 0 < knucleotide-input25000000.txt

PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754

AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902

1471758	GGT
446535	GGTA
47336	GGTATT
893	GGTATTTTAATT
893	GGTATTTTAATTTATAGT