{"id":97,"date":"2017-02-24T00:24:20","date_gmt":"2017-02-24T00:24:20","guid":{"rendered":"http:\/\/uenf.br\/projetos\/biotecveg\/?page_id=97"},"modified":"2017-02-24T15:52:27","modified_gmt":"2017-02-24T15:52:27","slug":"fasta-extractor","status":"publish","type":"page","link":"https:\/\/uenf.br\/projetos\/biotecveg\/fasta-extractor\/","title":{"rendered":"Fasta Extractor"},"content":{"rendered":"
<?php
\n\/\/ FASTA sequence extractor
\n\/\/ This will take a multi-sequence FASTA file and a list of headers as input
\n\/\/ and extract the sequences from the file<\/p>\n

require(‘.\/tools\/seqtools.php’);\/\/ include sequence functions, parsing etc.
\nrequire(‘.\/tools\/formtools.php’);\/\/ include sequence functions, parsing etc.<\/p>\n

\/\/ Form buttons from main form
\n$submit = $_POST[‘submit’];
\n$submit_example = $_POST[‘submit_example’];
\n$search=$_POST[‘search’];<\/p>\n

if (get_magic_quotes_gpc()){
\n$search = stripslashes($search);
\n}<\/p>\n

$search=chop($search);<\/p>\n

function parse_sequences ($inputseqs) {
\n$sequences = parse_fasta($inputseqs, 0, “-“); \/\/ returns array of sequences, each consist of two elements: header and sequence, i.e. $var[0][0] = header of seq 1, $var[0][1] = sequence 1 etc…
\nif (count($sequences) ==0){
\n$error = “Couldn’t parse FASTA input correctly, please submit fasta formatted sequences”;
\nreturn array(1,$error);
\n}
\nreturn array(0,$sequences);
\n}<\/p>\n

function extract_fasta($seqs, $s, $case=””) {
\nif ($case) {$case=”i”;}
\n$s=explode(“\\n”, $s);
\nfor ($i=0; $i’) === 0) {
\n$s[$i]=substr($s[$i], 1); \/\/ remove ‘>’ in the beginning of search text lines
\n}
\n}
\nif (count($s)==1 and $s[0]==””) {
\nreturn array(1,”Nothing to extract”);
\n}
\n$newseqs=array(); \/\/ Init
\nfor ($i=0; $i<count($seqs); $i++) {\/\/ loop through all sequences
\n$current_seqheader=$seqs[$i][0];
\nif ($_POST[‘fuzzy’]) {
\n\/\/
\n\/\/ Do partial match, i.e. match query as only part of header
\n\/\/
\nfor ($j=0; $j”.$current[0].”\\n”;
\n$fullset .= wrap_sequence($current[1], 70, “\\n”);
\n$fullset .= “\\n”;
\n}<\/p>\n

$r[‘text’] = $fullset;
\n$r[‘html’] = ”<\/p>\n

\".$fullset.\"<\/pre>\n
\\n”;<\/p>\n
$r[‘textlabel’]=”Sequences in fasta format”;
\n$r[‘htmllabel’]=”Sequences in fasta format”;<\/p>\n
$r[‘filename’]=”extracted_sequences.fasta”;
\n$r[‘filelabel’]=”Sequences in fasta format”;
\nreturn array(0,$r);
\n}<\/p>\n
if ($submit) {
\n$r= parse_sequences($inputseqs);
\nif ($r[0]==1) { $error=$r[1]; }
\n$sequences=$r[1];
\n$r= extract_fasta($sequences, $search, $_POST[‘case’]);
\nif ($r[0]==1) { $error=$r[1]; }
\n$sequences_new= $r[1];
\nunset($r);
\n}
\n\/\/
\n\/\/ BEGIN HTML OUTPUT!
\n\/\/
\nshow_page_header(“FASTA sequence extractor”, “Analysis finished, results are at bottom (or click here)<\/a>“, $submit, $error);
\n?><\/p>\n
<\/p>\n
\nHeaders of sequences you want to extract (‘>’ are ignored)<\/legend>\n