Hello,
I have been having some trouble downloading sequence data via BioMart's
Perl API. I've been trying to obtain sets of coding sequences (maybe on
the order of 35MB or so each), but every time I execute the script, the
following error is returned:
Problems with the web server: 500 read timeout
I seem to be getting exactly 22 sequences every time, instead of the
20,000 or so requested. I certainly would appreciate any help you may be
able to offer. I have included the code I am using below, which I mostly
copied from the Perl button on the Martview website. Below the perl, I
have included the XML contained in the registry file. Perhaps the data
are available from a host receiving less traffic?
Regards and best wishes,
Chris Grassa
S. Tonia Hsieh Lab
University of Florida
#!/usr/bin/perl -w
# An example script demonstrating the use of BioMart API.
# This perl API representation is only available for configuration
versions >= 0.5
use strict;
use BioMart::Initializer;
use BioMart::Query;
use BioMart::QueryRunner;
my $confFile =
"/home/grassa/src/biomart-perl/conf/ensembl_mart_56_registry.xml";
#
# NB: change action to 'clean' if you wish to start a fresh configuration
# and to 'cached' if you want to skip configuration step on subsequent
runs from the same registry
#
my $action='cached';
my $initializer = BioMart::Initializer->new('registryFile'=>$confFile,
'action'=>$action);
my $registry = $initializer->getRegistry;
my $query =
BioMart::Query->new('registry'=>$registry,'virtualSchemaName'=>'default');
$query->setDataset("btaurus_gene_ensembl");
$query->addFilter("ensembl_peptide_id", [large array of Ensembl
protein IDs]);
$query->addAttribute("ensembl_gene_id");
$query->addAttribute("ensembl_transcript_id");
$query->addAttribute("coding");
$query->addAttribute("ensembl_peptide_id");
$query->formatter("FASTA");
my $query_runner = BioMart::QueryRunner->new();
############################## GET COUNT ############################
# $query->count(1);
# $query_runner->execute($query);
# print $query_runner->getCount();
#####################################################################
############################## GET RESULTS ##########################
# to obtain unique rows only
# $query_runner->uniqueRowsOnly(1);
$query_runner->execute($query);
$query_runner->printHeader();
$query_runner->printResults();
$query_runner->printFooter();
#####################################################################
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE MartRegistry>
<MartRegistry>
<MartURLLocation database="ensembl_mart_56" default="1"
displayName="ENSEMBL 56 GENES (SANGER UK)" host="www.biomart.org"
includeDatasets="" martUser="" name="ensembl" path="/biomart/martservice"
port="80" serverVirtualSchema="default" visible="1" />
<MartURLLocation database="snp_mart_56" default="0" displayName="ENSEMBL
56 VARIATION (SANGER UK)" host="www.biomart.org" includeDatasets=""
martUser="" name="snp" path="/biomart/martservice" port="80"
serverVirtualSchema="default" visible="1" />
<MartURLLocation database="functional_genomics_mart_56" default="0"
displayName="ENSEMBL 56 FUNCTIONAL GENOMICS (SANGER UK)"
host="www.biomart.org" includeDatasets="" martUser=""
name="functional_genomics" path="/biomart/martservice" port="80"
serverVirtualSchema="default" visible="1" />
<MartURLLocation database="vega_mart_56" default="0" displayName="VEGA
36 (SANGER UK)" host="www.biomart.org" includeDatasets="" martUser=""
name="vega" path="/biomart/martservice" port="80"
serverVirtualSchema="default" visible="1" />
<MartURLLocation database="genomic_features_mart_56" default="0"
displayName="ENSEMBL 56 GENOMIC FEATURES (SANGER UK)"
host="www.biomart.org" includeDatasets="" martUser=""
name="genomic_features" path="/biomart/martservice" port="80"
serverVirtualSchema="default" visible="0" />
<MartURLLocation database="ontology_mart_56" default="0"
displayName="ENSEMBL 56 ONTOLOGY (SANGER UK)" host="www.biomart.org"
includeDatasets="" martUser="" name="ontology" path="/biomart/martservice"
port="80" serverVirtualSchema="default" visible="0" />
<MartURLLocation database="sequence_mart_56" default="0"
displayName="ENSEMBL 56 SEQUENCE (SANGER UK)" host="www.biomart.org"
includeDatasets="" martUser="" name="sequence" path="/biomart/martservice"
port="80" serverVirtualSchema="default" visible="0" />
</MartRegistry>
--
