Created
October 4, 2013 15:09
-
-
Save awitney/6827524 to your computer and use it in GitHub Desktop.
fetching genes from ensembl
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use strict; | |
use warnings; | |
use Bio::EnsEMBL::LookUp; | |
use Bio::SeqIO; | |
use Bio::Seq; | |
my $string = $ARGV[0] || 'gyrA'; | |
my $strain = $ARGV[1] || 'pseudomonas_aeruginosa*'; | |
my $type = $ARGV[2] || 'dna'; | |
my $seqout = Bio::SeqIO->new( -format => 'Fasta', -fh => \*STDOUT ); | |
# load the lookup from the main Ensembl Bacteria public server | |
my $lookup = Bio::EnsEMBL::LookUp->new( | |
-URL => "http://bacteria.ensembl.org/registry.json", | |
-NO_CACHE => 1 | |
); | |
#my @dbas = @{$lookup->get_all_by_name_pattern('escherichia_coli_%')}; | |
my @dbas; | |
if ( $strain =~ m/\*/ ) { | |
@dbas = @{$lookup->get_all_by_name_pattern($strain)}; | |
} else { | |
@dbas = @{$lookup->get_by_name_exact($strain)}; | |
} | |
print STDERR "Found: ".@dbas." adaptors\n"; | |
foreach my $dba ( @dbas ) { | |
my $genes = $dba->get_GeneAdaptor()->fetch_all_by_external_name($string); | |
print STDERR "\tFound ".@{$genes}." genes for ".$dba->species()."\n"; | |
foreach my $gene ( @{$genes} ) { | |
print STDERR "\t\t".$gene->stable_id." [".$gene->display_id."] [".$gene->external_name."] -- ".($gene->description ? $gene->description : '')."\n"; | |
my $description = ($gene->description ? $gene->description : ''); | |
$description .= ' ['.$dba->species().']'; | |
my $exons = $gene->get_all_Exons(); | |
die "\nError: more than one exon\n" if @{$exons} > 1; | |
my $exon = $exons->[0]; | |
my $transcripts = $gene->get_all_Transcripts(); | |
die "\nError: more than one transcript\n" if @{$transcripts} > 1; | |
my $transcript = $transcripts->[0]; | |
my $seq_string = $type eq 'dna' ? $exon->seq->seq() : $transcript->translate()->seq(); | |
my $seq = Bio::Seq->new( -display_id => $gene->stable_id, -seq => $seq_string, -description => $description ); | |
$seqout->write_seq($seq); | |
# foreach my $exon ( @{$exons} ) { | |
# } | |
} | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment