<?php
require __DIR__ . '/../../_common.php';
echo PatternToNumber('AGT');
echo '<hr>';
echo PatternToNumberOptimized('GAATGGAACCATTAATCGTG');
echo '<hr>';
echo NumberToPattern(5437, 8);
echo '<hr>';
echo NumberToPatternOptimized(7551, 7);
function ClumpFindingOptimized($genome, $k, $Length, $times)
{
/*
*
BetterClumpFinding(Genome, k, t, L)
FrequentPatterns ← an empty set
for i ←0 to 4k − 1
Clump(i) ← 0
Text ← Genome(0, L)
FrequencyArray ← ComputingFrequencies(Text, k)
for i ← 0 to 4k − 1
if FrequencyArray(i) ≥ t
Clump(i) ← 1
for i ← 1 to |Genome| − L
FirstPattern ← Genome(i − 1, k)
j ← PatternToNumber(FirstPattern)
FrequencyArray(j) ← FrequencyArray(j) − 1
LastPattern ← Genome(i + L − k, k)
j ← PatternToNumber(LastPattern)
FrequencyArray(j) ← FrequencyArray(j) + 1
if FrequencyArray(j) ≥ t
Clump(j) ← 1
for i ← 0 to 4k − 1
if Clump(i) = 1
Pattern ← NumberToPattern(i, k)
add Pattern to the set FrequentPatterns
return FrequentPatterns
*/
$FrequentPatterns = array();
$Clump = array();
$_limit = pow(4, $k) - 1;
for ($i = 0; $i <= $_limit; $i++) {
$Clump[$i] = 0;
}
$Text = substr($genome, 0, $Length);
$FrequencyArray = ComputingFrequencies($Text, $k);
for ($j = 0; $j <= $_limit; $j++) {
if ($FrequencyArray[$j] >= $times) {
$Clump[$j] = 1;
}
}
$_limit_for_i = strlen($genome) - $Length;
for ($i = 1; $i <= $_limit_for_i; $i++) {
$FirstPattern = substr($genome, $i - 1, $k);
$j = PatternToNumberOptimized($FirstPattern);
$FrequencyArray[$j]--;
$LastPattern = substr($genome, $i + $Length - $k, $k);
$j = PatternToNumberOptimized($LastPattern);
$FrequencyArray[$j]++;
if ($FrequencyArray[$j] >= $times) {
$Clump[$j] = 1;
}
}
for ($i = 0; $i <= $_limit; $i++) {
if ($Clump[$i] == 1) {
$Pattern = NumberToPatternOptimized($i, $k);
$FrequentPatterns[] = $Pattern;
}
}
return $FrequentPatterns;
}