Diff of /Sprout/SproutLoad.pm

-revision 1.40, Thu Jun  8 15:37:32 2006 UTC
+revision 1.47, Fri Jun 30 18:31:34 2006 UTC
 Line 375
                  for my $coupleData (@couplings) {
                      my ($peg2, $score) = @{$coupleData};
                      # Compute the coupling ID.
-                     my $coupleID = Sprout::CouplingID($peg1, $peg2);
+                     my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
                      if (! exists $dupHash{$coupleID}) {
                          $loadCoupling->Add("couplingIn");
                          # Here we have a new coupling to store in the load files.
 Line 634
  The following relations are loaded by this method.
      Subsystem
+     SubsystemClass
      Role
      RoleEC
      SSCell
-Line 696
+Line 697
      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
+     my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
      if ($self->{options}->{loadOnly}) {
          Trace("Loading from existing files.") if T(2);
      } else {
-Line 721
+Line 723
                  my $curator = $sub->get_curator();
                  my $notes = $sub->get_notes();
                  $loadSubsystem->Put($subsysID, $curator, $notes);
+                 my $class = $fig->subsystem_classification($subsysID);
+                 if ($class) {
+                     $loadSubsystemClass->Put($subsysID, $class);
+                 }
                  # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                      # Connect to this role.
-Line 785
+Line 791
                          if ($pegCount > 0) {
                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
-                             # Partition the PEGs found into clusters.
-                             my @clusters = $fig->compute_clusters(\@pegsFound, $sub);
                              # Create a hash mapping PEG IDs to cluster numbers.
                              # We default to -1 for all of them.
                              my %clusterOf = map { $_ => -1 } @pegsFound;
+                             # Partition the PEGs found into clusters.
+                             my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
                              for (my $i = 0; $i <= $#clusters; $i++) {
                                  my $subList = $clusters[$i];
                                  for my $peg (@{$subList}) {
-Line 1042
+Line 1048
                  # Get the annotation tuple.
                  my ($peg, $timestamp, $user, $text) = @{$tuple};
                  # Here we fix up the annotation text. "\r" is removed,
-                 # and "\t" and "\n" are escaped. Note we use the "s"
+                 # and "\t" and "\n" are escaped. Note we use the "gs"
                  # modifier so that new-lines inside the text do not
                  # stop the substitution search.
                  $text =~ s/\r//gs;
-Line 1396
+Line 1402
      return $retVal;
  }
+ =head3 LoadSynonymData
+ C<< my $stats = $spl->LoadSynonymData(); >>
+ Load the synonym groups into Sprout.
+ The following relations are loaded by this method.
+     SynonymGroup
+     IsSynonymGroupFor
+ The source information for these relations is taken from the C<maps_to_id> method
+ of the B<FIG> object. The process starts from the features, so it is possible
+ that there will be duplicates in the SynonymGroup load file, since the relationship
+ is one-to-many toward the features. The automatic sort on primary entity relations
+ will fix this for us.
+ =over 4
+ =item RETURNS
+ Returns a statistics object for the loads.
+ =back
+ =cut
+ #: Return Type $%;
+ sub LoadSynonymData {
+     # Get this object instance.
+     my ($self) = @_;
+     # Get the FIG object.
+     my $fig = $self->{fig};
+     # Get the genome hash.
+     my $genomeHash = $self->{genomes};
+     # Create a load object for the table we're loading.
+     my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
+     my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
+     if ($self->{options}->{loadOnly}) {
+         Trace("Loading from existing files.") if T(2);
+     } else {
+         Trace("Generating synonym group data.") if T(2);
+         # Loop through the genomes.
+         for my $genomeID (sort keys %{$genomeHash}) {
+             Trace("Processing $genomeID.") if T(3);
+             # Get all of the features for this genome. The only method that does this is
+             # all_features_detailed, which returns extra baggage that we discard.
+             my $featureData = $fig->all_features_detailed($genomeID);
+             my @fids = map { $_->[0] } @{$featureData};
+             Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
+             # Loop through the feature IDs.
+             for my $fid (@fids) {
+                 # Get the group for this feature.
+                 my $synonym = $fig->maps_to_id($fid);
+                 # Only proceed if the synonym is a real group.
+                 if ($synonym ne $fid) {
+                     $loadSynonymGroup->Put($synonym);
+                     $loadIsSynonymGroupFor->Put($synonym, $fid);
+                 }
+             }
+         }
+     }
+     # Finish the load.
+     my $retVal = $self->_FinishAll();
+     return $retVal;
+ }
  =head2 Internal Utility Methods
  =head3 TableLoader

 Legend:



Removed from v.1.40
 


changed lines


 
Added in v.1.47
 Legend:



Removed from v.1.40
 


changed lines


 
Added in v.1.47
-Removed from v.1.40
+Added in v.1.47

MCS Webmaster	ViewVC Help
Powered by ViewVC 1.0.3