File Coverage

blib/lib/NCBIx/eUtils/GeneAliases.pm

Criterion	Covered	Total	%
statement	1	3	33.3
branch			n/a
condition			n/a
subroutine	1	1	100.0
pod			n/a
total	2	4	50.0

package NCBIx::eUtils::GeneAliases;
use Class::Std;
use Class::Std::Utils;
use LWP::Simple;

use warnings;
use strict;
use Carp;

use version; our $VERSION = qv('0.9.0');

our $utils    = "http://www.ncbi.nlm.nih.gov/entrez/eutils";
our $retmax   = 500;
our @keywords = ('Official Symbol:', 'and Name:', 'Name:', 'Other Aliases:', 'Other Designations:', 'Chromosome:', 'Location:', 'Annotation:', 'MIM:', 'Genomic context:', 'Macronuclear:', 'GeneID:');

{
        my %utils_url_of  :ATTR( :get   :set   :default<''>      :init_arg );
        my %retmax_of     :ATTR( :get      :set      :default<'500'>   :init_arg    );

        sub START {
                my ($self, $ident, $arg_ref) = @_;
		$self->set_utils_url( $utils );
                return;
        }

	sub get_aliases {
		my ( $self, $gene_id ) = @_;
		my $gene_names      = {};
		my $gene_data;

		# Get NCBI records for gene
		my $gene_alts = $self->_get_docsums( $gene_id );

		if ( $gene_alts ) {
			# Remove newlines
			$gene_alts =~ s/\n/ /g;

			# Break into lines before keywords
			foreach my $keyword ( @keywords ) { $gene_alts =~ s/$keyword/\n$keyword/g; }
			my @alt_lines = split( /\n/, $gene_alts );

			# Process lines
			foreach my $alt_line ( @alt_lines ) {
				if ( $alt_line =~ m/^Official Symbol:(.*)$/ ) {
					my $match = $1; $match =~ s/[,;]/ /g;
					my @symbols = split( /\s+/, $match );
					foreach my $symbol ( @symbols ) { if ( $symbol && $symbol ne $gene_id ) { $gene_names->{$symbol}++; } }
				}
				elsif ( $alt_line =~ m/^Other Aliases:(.*)$/ ) {
					my $match = $1; $match =~ s/[,;]/ /g;
					my @aliases = split( /\s+/, $match );
					foreach my $alias ( @aliases )  { if ( $alias ) { $gene_names->{$alias}++; } }
				}

			}
			return sort keys %$gene_names;
		} else {
			return ();
		}
	}


	sub _get_docsums {
		my ( $self, $gene_id ) = @_;
		my $gene_data          = '';
		my $retmax             = $self->get_retmax();
		my $utils_url          = $self->get_utils_url();
		my $retstart;

		# Get the query
		my $esearch = $utils_url . "/esearch.fcgi?" .  "db=gene&retmax=1&usehistory=y&term=$gene_id" .
		   		                               '&tool=cpan_ncbix_eutils_genealiases&email=[e-mail]';
		my $esearch_result = get( $esearch );
		sleep(3);

		# Parse the count, query_key, and webenv
		$esearch_result =~ m|(\d+).*(\d+).*(\S+)|s;
		my $Count    = $1 ? $1 : 0;
		my $QueryKey = $2;
		my $WebEnv   = $3;

		#print "  STATUS: Getting $Count results for $gene_id \n";

		for ( my $retstart = 0; $retstart < $Count; $retstart += $retmax ) {
			my $efetch = $utils_url . "/efetch.fcgi?" .
			             "rettype=docsum&retmode=text&retstart=$retstart&retmax=$retmax&" .
			             "db=gene&query_key=$QueryKey&WebEnv=$WebEnv" .
		   		     '&tool=cpan_ncbix_eutils_genealiases&email=[e-mail]';

			$gene_data .= get($efetch);
			sleep(2);
		}

		#print "  STATUS: Done. \n";

		return $gene_data;
	}
}

1; # Magic true value required at end of module
__END__