The Computer Language
Benchmarks Game

k-nucleotide Dart program

source code

/* The Computer Language Benchmarks Game

   http://benchmarksgame.alioth.debian.org/

   Contributed by Philip Rogers
   Based on a javascript implementation by Jesse Millikan and Matt Baker
*/

import 'dart:io';
import 'dart:collection';

String readLine() => stdin.readLineSync();

String readInput() {
  while(readLine().substring(0, 6) != '>THREE');

  List<String> lines = new List();
  String line = readLine();
  while (line != null && line[0] != '>') {
    lines.add(line);
    line = readLine();
  };
  return lines.join('').toUpperCase();
}

HashMap<String, int> frequency(String sequence, int length) {
  HashMap<String, int> freq = new HashMap<String, int>();
  int n = sequence.length - length + 1;
  String sub;
  for (int i = 0; i < n; i++) {
    sub = sequence.substring(i, i + length);
    if (freq.containsKey(sub))
      freq[sub] = freq[sub] + 1;
    else
      freq[sub] = 1;
  }
  return freq;
}

void sort(String sequence, int length) {
  HashMap<String, int> freq = frequency(sequence, length);
  List<String> keys = freq.keys.toList();
  int n = sequence.length - length + 1;
  keys.sort((a, b) => (freq[b] - freq[a]));
  for (String key in keys) {
    String count = (freq[key] * 100 / n).toStringAsFixed(3);
    print('$key $count');
  }
  print('');
}

void find(String sequence, String string) {
  HashMap<String, int> freq = frequency(sequence, string.length);
  print('${(freq[string])}\t$string');
}

void main(args) {
  String sequence = readInput();
  if (sequence == null)
    return;
  sort(sequence, 1);
  sort(sequence, 2);
  find(sequence, 'GGT');
  find(sequence, 'GGTA');
  find(sequence, 'GGTATT');
  find(sequence, 'GGTATTTTAATT');
  find(sequence, 'GGTATTTTAATTTATAGT');
}
    

notes, command-line, and program output

NOTES:
32-bit Ubuntu one core
Dart VM version: 1.20.1 (Wed Oct 12 15:01:12 2016) on "linux_ia32"



Wed, 19 Oct 2016 20:29:46 GMT

COMMAND LINE:
/usr/local/src/dart-sdk/bin/dart  knucleotide.dart 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