[Bio] / FigKernelScripts / pubmed_gene2peg.pl Repository:
ViewVC logotype

View of /FigKernelScripts/pubmed_gene2peg.pl

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1.2 - (download) (as text) (annotate)
Mon Sep 4 20:19:26 2006 UTC (13 years, 6 months ago) by redwards
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, rast_rel_2008_06_18, myrast_rel40, rast_rel_2008_06_16, mgrast_dev_05262011, rast_rel_2008_12_18, mgrast_dev_04082011, rast_rel_2008_07_21, rast_rel_2010_0928, rast_2008_0924, mgrast_version_3_2, mgrast_dev_12152011, rast_rel_2008_04_23, mgrast_dev_06072011, rast_rel_2008_09_30, rast_rel_2009_0925, rast_rel_2010_0526, rast_rel_2014_0729, mgrast_dev_02212011, rast_rel_2010_1206, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, mgrast_rel_2008_0924, mgrast_rel_2008_1110_v2, rast_rel_2009_02_05, rast_rel_2011_0119, mgrast_rel_2008_0625, mgrast_release_3_0_4, mgrast_release_3_0_2, mgrast_release_3_0_3, mgrast_release_3_0_1, mgrast_dev_03312011, mgrast_release_3_1_2, mgrast_release_3_1_1, mgrast_release_3_1_0, mgrast_dev_04132011, rast_rel_2008_10_09, mgrast_dev_04012011, rast_release_2008_09_29, mgrast_rel_2008_0806, mgrast_rel_2008_0923, mgrast_rel_2008_0919, rast_rel_2009_07_09, rast_rel_2010_0827, mgrast_rel_2008_1110, myrast_33, rast_rel_2011_0928, rast_rel_2008_09_29, mgrast_rel_2008_0917, rast_rel_2008_10_29, mgrast_dev_04052011, mgrast_dev_02222011, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Changes since 1.1: +3 -1 lines
making sure gene id is right

# convert the list of GeneID/pubmed IDs to a list of the pegs that match.
# Download the file 
#       ftp://ftp.ncbi.nlm.nih.gov/gene/DATA/gene2pubmed.gz
# this has three columns: taxid, geneid, and pubmed id
# We will conver this to peg, geneid, pubmed id

use strict;
use FIG;
my $fig=new FIG;

my $file=shift || die "gene2pubmed file?";

#my %tax;
#foreach my $gen ($fig->genomes) 
#    $gen =~ /^fig\|(\d+)\.\d+/;
#    $tax{$1}=$gen;

if ($file =~ /\.gz$/)
    open(IN, "gunzip -c $file |") || die "Can't open a pipe to gunzip $file";
    open(IN, $file) || die "CAn't open $file";

my $dbh=$fig->db_handle;

while (<IN>)
    my @a=split /\t/;
    my $relational_db_response;
    if (($relational_db_response = $dbh->SQL("SELECT id,aliases FROM features WHERE aliases LIKE \'\%GeneID:$a[1]\%\'")) && (@$relational_db_response > 0))
        foreach my $rdbr (@$relational_db_response)
            $rdbr->[1] =~ /GeneID:(\w+)/;
            next unless ($1 eq $a[1]);
            print join("\t", $rdbr->[0], $a[1], $a[2]), "\n";

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3