$wsize = mysql_real_escape_string($_POST['wsize']);
$minqHSP = mysql_real_escape_string($_POST['minqHSP']);
$minqHSPc = mysql_real_escape_string($_POST['minqHSPc']);
$minESTc = mysql_real_escape_string($_POST['minESTc']);
$maxnest = mysql_real_escape_string($_POST['maxnest']);
$gsq_job_name = mysql_real_escape_string($_POST['gsq_job_name']);
$job_name_submit = job_name_strip($gsq_job_name);
// jobs_functions.inc.php; strip any user-added illegal chars
// calculate file sizes
$trans_array_est = create_input_list($input_data_path, "est", $dbpass);
# calculate total file size - est (jobs_functions.inc.php)
$trans_array_cdna = create_input_list($input_data_path, "cdna", $dbpass);
# calculate total file size - cdna (jobs_functions.inc.php)
$trans_array_tsa = create_input_list($input_data_path, "tsa", $dbpass);
# calculate total file size - tsa (jobs_functions.inc.php)
$gdna_array = create_input_list($input_data_path, "gdna", $dbpass);
# calculate total file size - genome
$genome_file_size = $gdna_array[2];
// for jobs database as total genome file size
// Get processor info from database based on selected app_id (note: 'nodes' is not required, the app is pre-configured for node count, but we sent it anyway for informational purposes)
$query = "SELECT nodes, proc_per_node, memory_per_node, platform from {$global_DB}.apps where app_id ='{$app_id}'";
$result = mysql_query($query);
$row = mysql_fetch_array($result);
$nodes = $row['nodes'];
$HPC_name = $row['platform'];
$proc_per_node = $row['proc_per_node'];
// should be max
$memory_per_node = $row['memory_per_node'];
// default is '2' currently
$transcript_type = mysql_real_escape_string($_POST['transcript_type']);
//used to assign est, cdna, tsa. See below:
# this is the default
$editable = "";
## GenomeThreader parameters
$input_g = "{$user_input_base}SCFDIR/{$DBid}gdna.fa";
# temp input path for Genome File e.g. /username/hpcGDB002/SCFDIR/GDB002gdna.fa
$input_p = "{$user_input_base}Protein/{$DBid}prot.fa";
# temp input path for Transcript File e.g. /username/hpcGDB002/Protein/GDB002prot.fa
## Set validation style for input files
$valid_est_array = create_input_list($gsq_input_path, "transcript", $dbpass);
// generic; covers est, cdna, tsa
$valid_est = $valid_est_array[0];
$valid_prot_array = create_input_list($gsq_input_path, "protein", $dbpass);
$valid_prot = $valid_prot_array[0];
$valid_gdna_array = create_input_list($gsq_input_path, "gdna", $dbpass);
$valid_gdna = $valid_gdna_array[0];
$valid_out_array = create_input_list($output_data_path, "gsq." . $DBid, $dbpass);
# e.g. gsq.GDB001cdna, test for type in function.
$valid_out = $valid_out_array[0];
## Set return job estimates based on size distribution of gdna:
$scaffolds = calculate_scaffolds($gsq_input_path, $gsq_proc, $gth_proc);
# jobs_functions.inc.php
// return array($large_scaffold_count, $small_scaffold_count, $chunks, $remainder_size, $gsq_split, $gth_split, $scaffold_size_display, $gsq_split_display, $gth_split_display, $gsq_time_display, $gth_time_display);
$large_scaffold_count = $scaffolds[0];
$small_scaffold_count = $scaffolds[1];
$total_scaffold_count = $large_scaffold_count + $small_scaffold_count;
$break_point_count = $scaffolds[2];
$remainder_size = $scaffolds[3];
$gsq_split = $scaffolds[4];
$gth_split = $scaffolds[5];
$scaffold_sizes_display = $scaffolds[6];
$gsq_split_display = $scaffolds[7];