diff --git a/misc-scripts/protein_match/get_Xmapping.pl b/misc-scripts/protein_match/get_Xmapping.pl index 09b29f67a3f40e61a8b817e64866b07c59c61e59..8254dbd40733b0ab7c490cb02647a03814d6a6f1 100644 --- a/misc-scripts/protein_match/get_Xmapping.pl +++ b/misc-scripts/protein_match/get_Xmapping.pl @@ -26,7 +26,8 @@ my $refseq_gnp = $conf{'refseq_gnp'}; my $ens1 = $conf{'ens1'}; my $ens4 = $conf{'ens4'}; my $refseq_pred = $conf{'refseq_pred_gnp'}; -my $go = $conf{'go'}; +my $go = $conf{'go'}; +my $gkb = $conf{'gkb'}; #Get specific options for the mouse my $mgi_sp = $conf{'mgi_sp'}; @@ -159,7 +160,19 @@ if ($organism eq "human") { $array[9] =~ s/\'/\\\'/g; print OUT "$array[1]\tSPTR\t$array[4]\tGO\t$array[4]\t$array[9]\tXREF\n"; } + + close (GO); + +#Get the GKB (Genome Knowledge Database) mapping +#Contacts: Imre Vastrik <vastrik@ebi.ac.uk>, Hester <eschmidt@ebi.ac.uk> + open (GKB,"$gkb") || die "Can't open GKB data: $gkb"; + + while (<GKB>) { + chomp; + my ($sp,$id) = split; + print OUT "$sp\tSPTR\t$id\tGKB\t$id\t\tXREF\n"; + } } #Get Xref mapping specifically for mouse. @@ -302,6 +315,7 @@ if($organism eq 'briggsae'){ close(OUT); print STDERR "The output has been written there: $out\n"; + sub parse_sp_file{ my ($file) = @_; #print STDERR "opening file ".$file."\n"; @@ -473,3 +487,4 @@ sub process_parsed_sp{ } } } + diff --git a/misc-scripts/protein_match/mapping_conf.pl b/misc-scripts/protein_match/mapping_conf.pl index 41f00ab97fbb151e490ba0cf1f2de007b5c84ea4..2a3dc067e764009e143373d9833421c77b2b7a28 100644 --- a/misc-scripts/protein_match/mapping_conf.pl +++ b/misc-scripts/protein_match/mapping_conf.pl @@ -104,6 +104,11 @@ package main; #ftp.ebi.ac.uk/pub/databases/GO/goa/HUMAN/gene_association.goa_human.gz #'go' => '', 'go' => '', + + #Location of the file for GKB (Genome Knowledge Base) mapping. + #Contacts: Imre Vastrik <vastrik@ebi.ac.uk>, Hester <eschmidt@ebi.ac.uk> + + 'gkb' => '', ####### #Mouse# diff --git a/misc-scripts/protein_match/maps2db.pl b/misc-scripts/protein_match/maps2db.pl index a6f4693d642954e4b428db981447f71d7b1d930f..67420855636bd92f2dce66bfceff1bdfef56dbcb 100644 --- a/misc-scripts/protein_match/maps2db.pl +++ b/misc-scripts/protein_match/maps2db.pl @@ -355,13 +355,7 @@ if ($organism eq "drosophila") { } -if ($organism eq "drosophila") { - my $query = "select distinct(stable_id) from gene_stable_id"; - my $sth = $db->prepare($query); - - -} if ($organism eq "elegans") { #print STDERR " parsing wormbase information\n";