Microsatellite repeats finder

4 // $mismatches_allowed is the porcentaje of errors allowed when searching in the repetitive sequence // so that sequence AACCGGTT-AAGCGGTT-AACCGGAT-AACCGGTT may be considered as a microsatellite repeat // // Return // The function will return an array with the following structure: // $results=Array( // 0=>Array( // start_position => 10, // length => 4, // repeats => 4, // sequence => ACGTACGTACGTACGT, // ), // 0=>Array( // start_position => 50, // length => 3, // repeats => 3, // sequence => ATCATCATC, // ), // ); // // Requeriments: // Functions IncludeN_1, IncludeN_2 and IncludeN_3 function find_microsatellite_repeats($sequence,$min_length,$max_length,$min_repeats,$min_length_of_MR,$mismatches_allowed){ $len_seq=strlen($sequence); $counter=0; for ($i=0;$i<$len_seq-3;$i++){ for ($j=$min_length;$j<$max_length+1;$j++){ if (($i+$j)>$len_seq){break;} $sub_seq=substr($sequence,$i,$j); $len_sub_seq=strlen ($sub_seq); $mismatches=floor($len_sub_seq*$mismatches_allowed/100); if ($mismatches==1){$sub_seq_pattern=includeN_1($sub_seq,0);} elseif ($mismatches==2){$sub_seq_pattern=includeN_2($sub_seq,0);} elseif ($mismatches==3){$sub_seq_pattern=includeN_3($sub_seq,0);} else {$sub_seq_pattern=$sub_seq;} $matches=1; while (preg_match_all("/($sub_seq_pattern)/",substr($sequence,($i+$j*$matches),$j),$out)==1){$matches++;} if ($matches>=$min_repeats and ($j*$matches)>=$min_length_of_MR){ $results[$counter]["start_position"]=$i; $results[$counter]["length"]=$j; $results[$counter]["repeats"]=$matches; $results[$counter]["sequence"]=substr($sequence,$i,$j*$matches); $counter++; $i+=$j*$matches; } } } return ($results); } // Description for Function IncludeN_1 // When a DNA sequence ("$primer") is provided to this function, as for example "acgt", this function will return // a pattern like ".cgt|a.gt|ac.t|acg.". This pattern may be useful to find within a DNA sequence // subsequences matching $primer, but allowing one missmach. The parameter $minus // is a numeric value which indicates number of bases always maching the DNA sequence in 3' end. // For example, when $minus is 1, the pattern for "acgt" will be ".cgt|a.gt|ac.t". // Check also IncludeN_2 and IncludeN_3. // // Parameters // $primer is a DNA sequence (oligonucleotide, primer) // $minus indicates number of bases in 3' which will always much the DNA sequence. // // Return // Returns a pattern (as described in "Description"). function includeN_1($primer,$minus) { $code=".".substr($primer,1); $wpos=1; while ($wpos

Definitions Microsatellite Repeat: A variety of simple di- (DINUCLEOTIDE REPEATS), tri- (TRINUCLEOTIDE REPEATS), tetra-, and pentanucleotide tandem repeats (usually less than 100 bases long). Tandem repeats: Copies of DNA sequences which lie adjacent to each other Related terms: Simple Tandem Repeats (STR), Exact Tandem Repeats (ETRs), Short  Sequence Repeats (SSRs), Repetitive DNA, Simple Sequence Repeats (SSR)