Generic Model Organism Database Project

Update of /cvsroot/gmod/schema/chado/bin
In directory sc8-pr-cvs1:/tmp/cvs-serv18055/bin

Modified Files:
	ucsc_genes2gff.pl 
Log Message:
adding support for GO annotations, unigene IDs, OMIM IDs, RefSeq descriptions.


Index: ucsc_genes2gff.pl
===================================================================
RCS file: /cvsroot/gmod/schema/chado/bin/ucsc_genes2gff.pl,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** ucsc_genes2gff.pl	22 Dec 2003 17:23:07 -0000	1.8
--- ucsc_genes2gff.pl	27 Dec 2003 00:21:09 -0000	1.9
***************
*** 15,23 ****
  my $executable = basename($0);
  
! my ($SRCDB,$ORIGIN,$ANNOTATIONS,$CENTER);
  GetOptions('srcdb:s'       => \$SRCDB,
             'origin:i'      => \$ORIGIN,
             'annotations:s' => \$ANNOTATIONS,
-            'center:s'      => \$CENTER,
            ) and $ANNOTATIONS or die <<USAGE;
  Usage: $0 -annotations <dir> [options]
--- 15,22 ----
  my $executable = basename($0);
  
! my ($SRCDB,$ORIGIN,$ANNOTATIONS);
  GetOptions('srcdb:s'       => \$SRCDB,
             'origin:i'      => \$ORIGIN,
             'annotations:s' => \$ANNOTATIONS,
            ) and $ANNOTATIONS or die <<USAGE;
  Usage: $0 -annotations <dir> [options]
***************
*** 38,42 ****
  
  $SRCDB           ||= 'UCSC';
- my $CENTER       ||= 'unigene';
  $ORIGIN          ||= 1;
  my $KGXREF         = $ANNOTATIONS.'/kgXref.txt';
--- 37,40 ----
***************
*** 50,55 ****
--- 48,60 ----
  my $GENBANK        = $ANNOTATIONS.'/genbank2accessions.txt';
  my $LOCACC         = $ANNOTATIONS.'/loc2acc';
+ my $LOCGO          = $ANNOTATIONS.'/loc2go';
+ my $LOCUG          = $ANNOTATIONS.'/loc2UG';
+ my $REFLINK        = $ANNOTATIONS.'/refLink.txt';
+ my $REFSEQSUMMARY  = $ANNOTATIONS.'/refSeqSummary.txt';
+ my $CHROMINFO      = $ANNOTATIONS.'/chromInfo.txt';
  
  my %xref;
+ my %loc2mrna;
+ my %ref2mrna;
  
  parseGenbank(\%xref,$GENBANK);
***************
*** 60,67 ****
                                                    # to link Genbank mRNA accession to
                                                    # Genbank protein accession
  parseKnownLocusLink(\%xref,$KNOWNLOCUSLINK);
  parseKnownAffy(\%xref,$KNOWNU133,$KNOWNU95);
  parseKnownPfam(\%xref,$KNOWNPFAM);
! # need to pull in the omim and other annotations too
  
  print "##gff-version 3\n";
--- 65,75 ----
                                                    # to link Genbank mRNA accession to
                                                    # Genbank protein accession
+ parseLocGo(\%xref,$LOCGO);
+ parseLocUG(\%xref,$LOCUG);
  parseKnownLocusLink(\%xref,$KNOWNLOCUSLINK);
  parseKnownAffy(\%xref,$KNOWNU133,$KNOWNU95);
  parseKnownPfam(\%xref,$KNOWNPFAM);
! parseRefLink(\%xref,$REFLINK);
! parseRefSeqSummary(\%xref,$REFSEQSUMMARY);
  
  print "##gff-version 3\n";
***************
*** 264,267 ****
--- 272,277 ----
  	#my $protein = $1;
  
+     my $loc = $line[0];
+ 
      my $gene    = $line[1];
      my $protein = $line[4];
***************
*** 271,274 ****
--- 281,286 ----
      next if $gene eq 'none';
  
+     push @{ $loc2mrna{$loc} }, $gene;
+ 
  	$xref->{$gene}{'db:genbank:protein'}{$protein} = 1 unless($gene eq 'none' || $protein eq '-');
    }
***************
*** 276,279 ****
--- 288,410 ----
  }
  
+ =head2 parseLocGo
+ 
+  Title   : parseLocGo
+  Usage   :
+  Function:
+  Example :
+  Returns :
+  Args    :
+ 
+ =cut
+ 
+ sub parseLocGo {
+   my($xref,$filename) = @_;
+   open  ANNFILE, $filename or die "Can't open file $filename: $!";
+   while(<ANNFILE>) {
+     chomp;
+     next if /^#/;
+ 	my @line = split /\t/;
+ 
+     if($loc2mrna{$line[0]}){
+       foreach my $mrna (@{$loc2mrna{$line[0]}}){
+         $xref->{$mrna}{'cvterm:go'}{$line[1]} = 1;
+       }
+     }
+   }
+   close ANNFILE;
+ }
+ 
+ =head2 parseLocUG
+ 
+  Title   : parseLocUG
+  Usage   :
+  Function:
+  Example :
+  Returns :
+  Args    :
+ 
+ =cut
+ 
+ sub parseLocUG {
+   my($xref,$filename) = @_;
+   open  ANNFILE, $filename or die "Can't open file $filename: $!";
+   while(<ANNFILE>) {
+     chomp;
+     next if /^#/;
+ 	my @line = split /\t/;
+ 
+     if($loc2mrna{$line[0]}){
+       foreach my $mrna (@{$loc2mrna{$line[0]}}){
+         $xref->{$mrna}{'db:unigene'}{$line[1]} = 1;
+       }
+     }
+   }
+   close ANNFILE;
+ }
+ 
+ =head2 parseRefLink
+ 
+  Title   : parseRefLink
+  Usage   :
+  Function:
+  Example :
+  Returns :
+  Args    :
+ 
+ =cut
+ 
+ sub parseRefLink {
+   my($xref,$filename) = @_;
+   open  ANNFILE, $filename or die "Can't open file $filename: $!";
+   while(<ANNFILE>) {
+     chomp;
+     next if /^#/;
+ 	my($symbol,$description,$refmrna,$refprotein,undef,undef,$locus,$omim) = split /\t/;
+     $description = uri_escape($description);
+ 
+     if($ref2mrna{$refmrna}){
+       foreach my $mrna (@{$ref2mrna{$refmrna}}){
+         $xref->{$mrna}{'db:locuslink'}{$locus} = 1;
+         $xref->{$mrna}{'db:omim'}{$omim} = 1;
+         $xref->{$mrna}{'db:refseq:mrna'}{$refmrna} = 1;
+         $xref->{$mrna}{'db:refseq:protein'}{$refprotein} = 1;
+         $xref->{$mrna}{'Alias'}{$symbol} = 1;
+         $xref->{$mrna}{'description'}{$description} = 1;
+       }
+     }
+   }
+   close ANNFILE;
+ }
+ 
+ =head2 parseRefSeqSummary
+ 
+  Title   : parseRefSeqSummary
+  Usage   :
+  Function:
+  Example :
+  Returns :
+  Args    :
+ 
+ =cut
+ 
+ sub parseRefSeqSummary {
+   my($xref,$filename) = @_;
+   open  ANNFILE, $filename or die "Can't open file $filename: $!";
+   while(<ANNFILE>) {
+     chomp;
+     next if /^#/;
+ 	my($refmrna,$completeness,$description) = split /\t/;
+     $description = uri_escape($description);
+ 
+     if($ref2mrna{$refmrna}){
+       foreach my $mrna (@{$ref2mrna{$refmrna}}){
+         $xref->{$mrna}{'completeness'}{$completeness} = 1;
+         $xref->{$mrna}{'description'}{$description} = 1;
+       }
+     }
+   }
+   close ANNFILE;
+ }
  
  =head2 parseKnownLocusLink
***************
*** 457,466 ****
  	# first two are the same (genebank) followed by swissprot etc...
      my ($kgID, $mRNA, $spID, $spDisplayID, $geneSymbol, $refseq, $protAcc, $description) = split /\t/;
!     my $key = "";
!     if($CENTER =~ /unigene/i) { $key = $kgID; }
!     else { $key = $refseq; }
      # escape certain fields
      $key = uri_escape($key);
      $description = uri_escape($description);
  
      $xref->{$key}{'db:genbank:mrna'}{$kgID}             = 1 if $kgID;
--- 588,597 ----
  	# first two are the same (genebank) followed by swissprot etc...
      my ($kgID, $mRNA, $spID, $spDisplayID, $geneSymbol, $refseq, $protAcc, $description) = split /\t/;
!     my $key = $kgID;
      # escape certain fields
      $key = uri_escape($key);
      $description = uri_escape($description);
+ 
+     push @{ $ref2mrna{$refseq} }, $kgID;
  
      $xref->{$key}{'db:genbank:mrna'}{$kgID}             = 1 if $kgID;

2003	Jan	Feb	Mar	Apr	May (19)	Jun (119)	Jul (21)	Aug (7)	Sep (2)	Oct (126)	Nov (85)	Dec (138)
2004	Jan (33)	Feb (11)	Mar (53)	Apr (73)	May (31)	Jun (33)	Jul (81)	Aug (68)	Sep (44)	Oct (21)	Nov (30)	Dec (50)
2005	Jan (9)	Feb (61)	Mar (83)	Apr (81)	May (41)	Jun (40)	Jul (87)	Aug (32)	Sep (22)	Oct (6)	Nov (9)	Dec (63)
2006	Jan (17)	Feb (5)	Mar (19)	Apr (71)	May (10)	Jun (18)	Jul (22)	Aug (18)	Sep (12)	Oct (10)	Nov (14)	Dec (32)
2007	Jan (52)	Feb (82)	Mar (53)	Apr (59)	May (13)	Jun (5)	Jul (8)	Aug (108)	Sep (10)	Oct (17)	Nov (20)	Dec (12)
2008	Jan (16)	Feb (7)	Mar (62)	Apr (6)	May (21)	Jun (10)	Jul (32)	Aug (12)	Sep (16)	Oct (27)	Nov (31)	Dec (37)
2009	Jan (10)	Feb (14)	Mar (13)	Apr (22)	May (52)	Jun (40)	Jul (26)	Aug (20)	Sep (31)	Oct (11)	Nov (7)	Dec (37)
2010	Jan (12)	Feb (6)	Mar (8)	Apr (25)	May (20)	Jun (23)	Jul (4)	Aug (20)	Sep (7)	Oct (11)	Nov (21)	Dec
2011	Jan (1)	Feb (4)	Mar (5)	Apr (4)	May (1)	Jun (10)	Jul (4)	Aug (20)	Sep (20)	Oct (4)	Nov (16)	Dec (1)
2012	Jan (1)	Feb (2)	Mar (7)	Apr (2)	May	Jun	Jul (1)	Aug (1)	Sep	Oct	Nov	Dec (2)
2013	Jan (1)	Feb (3)	Mar (3)	Apr	May (2)	Jun	Jul (2)	Aug	Sep (1)	Oct	Nov	Dec
2014	Jan	Feb	Mar	Apr (1)	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
2015	Jan	Feb	Mar	Apr	May	Jun (1)	Jul	Aug	Sep	Oct	Nov	Dec
2016	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct (3)	Nov	Dec
2017	Jan	Feb	Mar	Apr	May (1)	Jun	Jul	Aug	Sep	Oct	Nov	Dec

S	M	T	W	T	F	S
	1	2 (16)	3 (16)	4 (33)	5 (2)	6 (1)
7	8 (1)	9 (6)	10 (16)	11 (3)	12 (3)	13 (1)
14	15	16	17 (1)	18 (11)	19 (11)	20
21	22 (3)	23 (3)	24 (6)	25 (1)	26 (3)	27 (1)
28	29	30	31

Thanks for helping keep SourceForge clean.

Generic Model Organism Database Project

Brought to you by: daveclements, girlwithglasses, gk_fan, hueyling, and 10 others

gmod-schema-cmts — Commits for schema/Chado