| "; echo "Assembly ID: "; echo " | "; echo ""; $genopar->input("nomeMtg", "text", $nomeMtg, "", 30, 30); echo " | "; echo "
| "; $genopar->input("tipoArq", "radio", "fasta", "checked"); echo " Assembly file (FASTA): "; echo " | "; echo ""; $genopar->input("fastaFile", "file"); echo " | "; echo "
| "; $genopar->input("tipoArq", "radio", "gbZip"); echo "Annotated assembly file (GenBank): "; echo " | "; echo ""; $genopar->input("gbZipFile", "file"); echo " | "; echo ""; $genopar->submit(); echo " | "; echo "
"; echo "
| "; echo "ORF Finder"; echo " | "; echo "|||||||||
|---|---|---|---|---|---|---|---|---|---|
| "; $genopar->input("orfFinder", "radio", "glimmer", "checked"); echo " | "; echo ""; echo "Glimmer"; echo " | "; echo "||||||||
| "; $genopar->input("orfFinder", "radio", "custom"); echo " | "; echo ""; echo "Mark all"; echo " | "; echo ""; echo "Start Codon"; echo " | "; echo ""; // $genopar->select("startCodon", $codons, $startCodon); $codons = array('ATG', 'GTG', 'TTG', 'CTG', 'ATT'); foreach ($codons as $codon){ $genopar->input("startCodon[".$codon."]", "checkbox", $codon); echo "$codon "; } echo " | "; echo ""; echo "Minimum ORF size"; echo " | "; echo ""; $genopar->input("minSize", "text", $minSize, "", 3, 5); echo "bases"; echo " | "; echo "||||
"; $genopar->mostraListaBact(); echo "
"; $genopar->fechaForm(); }elseif($tipoArq == "fasta"){ $db_name = $genopar->MySQL_Default_DBname; $genopar->abreBanco(); $n = $genopar->queryBanco("SELECT idMontagem FROM contig WHERE idMontagem='$nomeMtg'"); if ($n > 0) $genopar->error("A file $nomeMtg already exist."); if ($runCOG == 1) $orgsToBlast['COG'] = 'COG'; if ($runPFAM == 1) $orgsToBlast['PFAM'] = 'PFAM'; $genopar->insertOrgsToBlast($nomeMtg, $orgsToBlast, $evalue); $size = 1 << 20; // size = 2^20 = 1 MB; $size = $size * 20; // size = 20 MB; $path = "tmp/"; $genomaFasta = $path."/".$_FILES["fastaFile"]["name"]; $fastaFile = $genopar->upload($_FILES["fastaFile"], $path, $size); if ($fastaFile){ if (is_int($id)){ foreach ($orgsToBlast as $id => $name){ $n = $genopar->queryBanco("SELECT idOrg FROM orgsToBlast WHERE idOrg = '$id' AND idMontagem != '$nomeMtg'"); if ($n > 0) continue; $orgDir = "BlastDatabases/$id"; $ext = "faa"; $localFile = "$orgDir/$id.$ext"; if(!is_file($localFile)){ $sql = "SELECT ftpFolder FROM taxonomy WHERE id=$id"; $genopar->queryBanco($sql); $lin = $genopar->getArray(); $orgFolder = $lin['ftpFolder']; getFile($genopar, $id, $orgFolder, $ext); if (!is_file($localFile)) $genopar->error("Nao foi possivel fazer o download do arquivo FASTA"); $blastDB = formatDB($localFile); } } } if ($startCodon){ $startCodon = join("|", $startCodon); } // echo $startCodon; // exit; system("cd autoAnnot && perl autoAnnot.pl $db_name $nomeMtg $fastaFile $orfFinder '$startCodon' $minSize"); } $genopar->fechaBanco(); }else{ $db_name = $genopar->MySQL_Default_DBname; $outAnnotDir = "Fasta/$nomeMtg"; $outContigDir = "Fasta/$nomeMtg/Contigs"; $outOrfDir = "Fasta/$nomeMtg/ORFs"; $genopar->abreBanco(); $n = $genopar->queryBanco("SELECT idMontagem FROM contig WHERE idMontagem='$nomeMtg'"); if ($n > 0) $genopar->error("An assembly $nomeMtg already exist."); $genopar->fechaBanco(); $zipFile = $_FILES['gbZipFile']['name']; $allowedMIME = array("application/x-gzip", "application/x-compressed", "application/x-gtar", "application/x-zip-compressed", "application/zip", "application/gzip"); $size = 1 << 20; // size = 2^20 = 1 MB; $size = $size * 10; // size = 10 MB; $path = "tmp/"; $file = $genopar->upload($_FILES["gbZipFile"], $path, $size, $allowedMIME); $dir = dirname($file); // echo $file; if ($file){ $list = unzip($file); if (is_array($list)){ createTree($outAnnotDir); // createDB($genopar, $dbName, $updateInfoAnnot, $DB_HOST, $DB_USER, $DB_PASS); $outDir = array_shift($list); foreach ($list as $file){ $file = $outDir."/".$file; system("perl gbk2fna.pl $file $outContigDir"); system("perl addAnnot.pl $file $nomeMtg $outOrfDir"); } }elseif ($list === 1){ $genopar->error("The compressed file must contain a root directory."); } }else{ $genopar->error("This file type is not allowed."); } $ctgs = count($list); echo "
fechaPagina(); /** * ******************** * * FUNCOES * * ******************** * **/ # Conecta via FTP ao NCBI e baixa o arquivo "nome.ext" function getFile($genopar, $idOrg, $folder, $ext){ $ncbi = "ftp.ncbi.nih.gov"; $USER = "anonymous"; $PASS = "nada@lugar.algum"; $con = ftp_connect($ncbi) or $genopar->error("NCBI indisponível."); ftp_login($con, $USER, $PASS); ftp_pasv($con, TRUE); ftp_chdir($con, "genomes/Bacteria/$folder") or $genopar->error("Nao foi possivel mudar de diretorio."); $pattern = "/.$ext$/"; foreach(ftp_nlist($con, ".") as $file){ if (preg_match($pattern, $file)){ $rmtFile = $file; break; } } mkdir("BlastDatabases/$idOrg"); $file = "BlastDatabases/$idOrg/$idOrg.$ext"; $handle = fopen($file, "w"); if (!ftp_fget($con, $handle, $rmtFile, FTP_ASCII, 0)) $file = NULL; fclose($handle); ftp_close($con); return $file; } function formatDB($file){ $dbName = substr($file, 0, -4); $formatDB = "/usr/local/blast/bin/formatdb -i $file -p T -n $dbName"; system($formatDB); return $dbName; } function unzip($zipFile){ $cmd = "tar -tf $zipFile"; $outDir = dirname($zipFile); $content= array(); exec($cmd, $content); if (preg_match("/\/$/", $content[0])){ // if (is_dir($outDir."/".$content[0])){ $random = time(); $rootDir = substr($content[0],0,-1); $outDir = $outDir."/".$rootDir.$random; mkdir($outDir); $content[0] = $outDir; // } $cmd = "cd $outDir && tar -xzf $zipFile"; exec($cmd); // array_unshift($content, ); return $content; }else{ return 1; } } function createTree($root){ mkdir($root); mkdir($root."/Contigs"); mkdir($root."/Contigs"."/n"); mkdir($root."/Contigs"."/p"); mkdir($root."/ORFs"); mkdir($root."/ORFs"."/n"); mkdir($root."/ORFs"."/p"); } ?>How to submit a set of contigs for automatic annotation
1. "Assembly ID:" field - Add a name to identify the annotation analysis 2. "Assembly file (FASTA):" field - Generate one file containing all contigs in FASTA format 3. "Annotated assembly file (GenBank):" field + Generate one GenBank file per contig - The contig ID will be extracted from the file name in the format: - The prefix word "Contig" - a number to identify the contig - extensions ".gb" or ".gbk" - Supported GenBank features are: CDS, gene, tRNA, product, and locus_tag + Create a directory and move all contigs inside + Compress the directory using "tar.gz" format 4. Choose the file clicking the "Browse..." button 5. Send informations using "Submit" button