Created
March 8, 2012 17:57
-
-
Save anonymous/2002353 to your computer and use it in GitHub Desktop.
EntrezGeneID get sequence
This file contains hidden or 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/perl | |
use Bio::DB::EUtilities; | |
# this needs to be a list of EntrezGene unique IDs | |
my @ids = @ARGV; | |
my $eutil = Bio::DB::EUtilities->new(-eutil => 'esummary', | |
-email => '[email protected]', | |
-db => 'gene', | |
-id => \@ids); | |
my $fetcher = Bio::DB::EUtilities->new(-eutil => 'efetch', | |
-email => '[email protected]', | |
-db => 'nucleotide', | |
-rettype => 'gb'); | |
while (my $docsum = $eutil->next_DocSum) { | |
# to ensure we grab the right ChrStart information, we grab the Item above | |
# it in the Item hierarchy (visible via print_all from the eutil instance) | |
my ($item) = $docsum->get_Items_by_name('GenomicInfoType'); | |
my %item_data = map {$_ => 0} qw(ChrAccVer ChrStart ChrStop); | |
while (my $sub_item = $item->next_subItem) { | |
if (exists $item_data{$sub_item->get_name}) { | |
$item_data{$sub_item->get_name} = $sub_item->get_content; | |
} | |
} | |
# check to make sure everything is set | |
for my $check (qw(ChrAccVer ChrStart ChrStop)) { | |
die "$check not set" unless $item_data{$check}; | |
} | |
my $strand = $item_data{ChrStart} > $item_data{ChrStop} ? 2 : 1; | |
printf("Retrieving %s, from %d-%d, strand %d\n", $item_data{ChrAccVer}, | |
$item_data{ChrStart}, | |
$item_data{ChrStop}, | |
$strand | |
); | |
$fetcher->set_parameters(-id => $item_data{ChrAccVer}, | |
-seq_start => $item_data{ChrStart} -5000 , | |
-seq_stop => $item_data{ChrStop} + 5000 , | |
-strand => $strand); | |
print $fetcher->get_Response->content; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment