source code
/* The Computer Language Benchmarks Game
https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
Naive transliteration from bearophile's program
contributed by Isaac Gouy
*/
const rl = require("node:readline");
async function seq_lines() {
const stdin = rl.createInterface({
input: process.stdin,
});
const lines = [];
let started = false;
for await (const line of stdin) {
if (started) {
if (line.startsWith(">")) break;
lines.push(line);
} else {
started = line.startsWith(">THREE");
}
}
return lines;
}
function base_counts(bases, seq) {
counts = new Map();
size = seq.length + 1 - bases;
for (let i = 0; i < size; i++) {
const nucleo = seq.substring(i,i+bases);
var v; if (v = counts.get(nucleo))
counts.set(nucleo,v+1);
else
counts.set(nucleo,1);
}
return counts;
}
function sorted_freq(bases, seq) {
size = seq.length + 1 - bases;
counts = base_counts(bases, seq);
return Array.from(counts)
.sort((a, b) => b[1] - a[1])
.map((a) => [a[0], 100.0 * a[1] / size]);
}
function specific_count(code, seq) {
counts = base_counts(code.length,seq);
return counts.get(code) ? counts.get(code) : 0;
}
function write_freq(a) {
console.log(`${a[0]} ${a[1].toFixed(3)}`);
}
function main(n) {
seq_lines().then(a => {
const seq = a.map((s) => s.toUpperCase()).join("");
for (const base of [1,2]) {
sorted_freq(base,seq).forEach(write_freq);
console.log();
}
for (const code of ["GGT", "GGTA", "GGTATT",
"GGTATTTTAATT", "GGTATTTTAATTTATAGT"]) {
console.log(`${specific_count(code,seq)}\t${code}`);
}
} );
}
main(+process.argv[2] || 0)
notes, command-line, and program output
NOTES:
64-bit Ubuntu quad core
v23.0.0
Wed, 11 Dec 2024 01:04:14 GMT
MAKE:
cp -L knucleotide.node-8.node knucleotide.js
0.07s to complete and log all make actions
COMMAND LINE:
/opt/src/node-v23.0.0/bin/node knucleotide.js 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