Last active
December 21, 2015 10:39
-
-
Save danstaines/6293539 to your computer and use it in GitHub Desktop.
Script for dumping genes and "gene" simple features from subset of Ensembl Bacteria databases
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::Seq; | |
use Bio::EnsEMBL::Utils::IO::FASTASerializer; | |
print "Building helper\n"; | |
my $helper = Bio::EnsEMBL::LookUp->new(-URL=>"http://bacteria.ensembl.org/registry.json",-NO_CACHE=>1); | |
my $pattern = 'haemophilus_.*'; | |
print "Getting DBAs for $pattern\n"; | |
my @dbas = @{$helper->get_all_by_name_pattern($pattern)}; | |
for my $dba (@dbas) { | |
print "Working with ".$dba->species()."\n"; | |
open my $filehandle, '>', $dba->species().'.fa' || die "Could not open output file"; | |
my $serializer = Bio::EnsEMBL::Utils::IO::FASTASerializer->new($filehandle); | |
my @genes = @{$dba->get_GeneAdaptor()->fetch_all()}; | |
print "Found ".scalar @genes." genes for ".$dba->species()."\n"; | |
for my $gene (@genes) { | |
my $slice = $gene->feature_Slice(); | |
my $seqobj = Bio::Seq->new( | |
-display_id => $gene->stable_id().' '.$slice->name().' '.($gene->description()||''), | |
-seq => $slice->seq()); | |
$serializer->print_Seq($seqobj); | |
} | |
my @simple_features = grep{$_->analysis()->logic_name() eq 'gene'} @{$dba->get_SimpleFeatureAdaptor()->fetch_all()}; | |
print "Found ".scalar @simple_features." gene simple features for ".$dba->species()."\n"; | |
for my $simple_feature (@simple_features) { | |
my $slice = $simple_feature->feature_Slice(); | |
my $seqobj = Bio::Seq->new( | |
-display_id => 'gene_feature:'.$simple_feature->dbID() . ' ' .$slice->name().' '.($simple_feature->display_label()||''), | |
-seq => $slice->seq()); | |
$serializer->print_Seq($seqobj); | |
} | |
close $filehandle; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Dependent on ensembl/modules and ensemblgenomes-api/modules