[Bio] / Sprout / SproutLoad.pm Repository:
ViewVC logotype

Diff of /Sprout/SproutLoad.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.9, Wed Sep 14 11:21:24 2005 UTC revision 1.30, Sun Mar 26 12:35:21 2006 UTC
# Line 10  Line 10 
10      use Sprout;      use Sprout;
11      use Stats;      use Stats;
12      use BasicLocation;      use BasicLocation;
13        use HTML;
14    
15  =head1 Sprout Load Methods  =head1 Sprout Load Methods
16    
# Line 170  Line 171 
171      return $retVal;      return $retVal;
172  }  }
173    
174    =head3 LoadOnly
175    
176    C<< my $flag = $spl->LoadOnly; >>
177    
178    Return TRUE if we are in load-only mode, else FALSE.
179    
180    =cut
181    
182    sub LoadOnly {
183        my ($self) = @_;
184        return $self->{options}->{loadOnly};
185    }
186    
187    =head3 PrimaryOnly
188    
189    C<< my $flag = $spl->PrimaryOnly; >>
190    
191    Return TRUE if only the main entity is to be loaded, else FALSE.
192    
193    =cut
194    
195    sub PrimaryOnly {
196        my ($self) = @_;
197        return $self->{options}->{primaryOnly};
198    }
199    
200  =head3 LoadGenomeData  =head3 LoadGenomeData
201    
202  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 197  Line 224 
224    
225  =back  =back
226    
 B<TO DO>  
   
 Real quality vectors instead of C<unknown> for everything.  
   
 GenomeGroup relation. (The original script took group information from the C<NMPDR> file  
 in each genome's main directory, but no such file exists anywhere in my version of the  
 data store.)  
   
227  =cut  =cut
228  #: Return Type $%;  #: Return Type $%;
229  sub LoadGenomeData {  sub LoadGenomeData {
# Line 215  Line 234 
234      # Get the genome count.      # Get the genome count.
235      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
236      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
237      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
238      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
239      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
240      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
241      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
242      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
243        if ($self->{options}->{loadOnly}) {
244            Trace("Loading from existing files.") if T(2);
245        } else {
246            Trace("Generating genome data.") if T(2);
247      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
248      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
249          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
250          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
251          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
252          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
253          # Get the genus, species, and strain from the scientific name. Note that we append              # Get the genus, species, and strain from the scientific name.
         # the genome ID to the strain. In some cases this is the totality of the strain name.  
254          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
255          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
256          # Get the full taxonomy.          # Get the full taxonomy.
257          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
258          # Output the genome record.          # Output the genome record.
# Line 267  Line 288 
288              }              }
289          }          }
290      }      }
291        }
292      # Finish the loads.      # Finish the loads.
293      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
294      # Return the result.      # Return the result.
# Line 310  Line 332 
332      my $genomeCount = (keys %{$genomeFilter});      my $genomeCount = (keys %{$genomeFilter});
333      my $featureCount = $genomeCount * 4000;      my $featureCount = $genomeCount * 4000;
334      # Start the loads.      # Start the loads.
335      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
336      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
337      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
338      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
339      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
340      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
341            Trace("Loading from existing files.") if T(2);
342        } else {
343            Trace("Generating coupling data.") if T(2);
344      # Loop through the genomes found.      # Loop through the genomes found.
345      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
346          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 367  Line 392 
392                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
393                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
394                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
395                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
396                              # the hash makes it to the output.                              # the hash makes it to the output.
397                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
398                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 382  Line 407 
407                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);
408                          # Connect it to the features.                          # Connect it to the features.
409                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);
410                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 1);                              $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);
411                            }
412                      }                      }
413                  }                  }
414              }              }
# Line 409  Line 435 
435      FeatureTranslation      FeatureTranslation
436      FeatureUpstream      FeatureUpstream
437      IsLocatedIn      IsLocatedIn
438        HasFeature
439    
440  =over 4  =over 4
441    
# Line 425  Line 452 
452      my ($self) = @_;      my ($self) = @_;
453      # Get the FIG object.      # Get the FIG object.
454      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
455      # Get the table of genome IDs.      # Get the table of genome IDs.
456      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
457      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
458      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
459      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
460      my ($loadFeatureAlias, $loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
461      if (! $limited) {      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
462          $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
463          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
464          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature');
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
465      # Get the maximum sequence size. We need this later for splitting up the      # Get the maximum sequence size. We need this later for splitting up the
466      # locations.      # locations.
467      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
468      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
469            Trace("Loading from existing files.") if T(2);
470        } else {
471            Trace("Generating feature data.") if T(2);
472      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
473      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
474          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 455  Line 479 
479          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
480              $loadFeature->Add("featureIn");              $loadFeature->Add("featureIn");
481              # Split the tuple.              # Split the tuple.
482              my ($featureID, $locations, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureData};
483              # Create the feature record.              # Create the feature record.
484              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
485              # The next stuff is for a full load only.                  # Link it to the parent genome.
486              if (! $limited) {                  $loadHasFeature->Put($genomeID, $featureID, $type);
487                  # Create the aliases.                  # Create the aliases.
488                  for my $alias (split /\s*,\s*/, $aliases) {                  for my $alias ($fig->feature_aliases($featureID)) {
489                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
490                  }                  }
491                  # Get the links.                  # Get the links.
# Line 482  Line 506 
506                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
507                      }                      }
508                  }                  }
             }  
509              # This part is the roughest. We need to relate the features to contig              # This part is the roughest. We need to relate the features to contig
510              # locations, and the locations must be split so that none of them exceed              # locations, and the locations must be split so that none of them exceed
511              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
512              # for Sprout.              # for Sprout.
513              my @locationList = map { "$genomeID:$_" } split /\s*,\s*/, $locations;                  my @locationList = split /\s*,\s*/, $locations;
514              # Create the location position indicator.              # Create the location position indicator.
515              my $i = 1;              my $i = 1;
516              # Loop through the locations.              # Loop through the locations.
517              for my $location (@locationList) {              for my $location (@locationList) {
518                  # Parse the location.                  # Parse the location.
519                  my $locObject = BasicLocation->new($location);                      my $locObject = BasicLocation->new("$genomeID:$location");
520                  # Split it into a list of chunks.                  # Split it into a list of chunks.
521                  my @locOList = ();                  my @locOList = ();
522                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 511  Line 534 
534              }              }
535          }          }
536      }      }
537        }
538      # Finish the loads.      # Finish the loads.
539      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
540      return $retVal;      return $retVal;
# Line 547  Line 571 
571      my $fig = $self->{fig};      my $fig = $self->{fig};
572      # Get the table of genome IDs.      # Get the table of genome IDs.
573      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
574      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
575      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
576                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
577      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
578        } else {
579            Trace("Generating BBH data.") if T(2);
580      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
581      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
582          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 578  Line 602 
602              }              }
603          }          }
604      }      }
605        }
606      # Finish the loads.      # Finish the loads.
607      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
608      return $retVal;      return $retVal;
# Line 599  Line 624 
624    
625      Subsystem      Subsystem
626      Role      Role
627        RoleEC
628      SSCell      SSCell
629      ContainsFeature      ContainsFeature
630      IsGenomeOf      IsGenomeOf
# Line 606  Line 632 
632      OccursInSubsystem      OccursInSubsystem
633      ParticipatesIn      ParticipatesIn
634      HasSSCell      HasSSCell
635        ConsistsOfRoles
636        RoleSubset
637        HasRoleSubset
638        ConsistsOfGenomes
639        GenomeSubset
640        HasGenomeSubset
641        Catalyzes
642        Diagram
643        RoleOccursIn
644    
645  =over 4  =over 4
646    
# Line 615  Line 650 
650    
651  =back  =back
652    
 B<TO DO>  
   
 Generate RoleName table?  
   
653  =cut  =cut
654  #: Return Type $%;  #: Return Type $%;
655  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 632  Line 663 
663      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
664      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
665      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
666      my $subsysCount = @subsysIDs;      # Get the map list.
667      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
668      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
669      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
670      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
671      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
672      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
673      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
674      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
675      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
676      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
677      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
678      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
679        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
680        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
681        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
682        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
683        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
684        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
685        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
686        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
687        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
688        if ($self->{options}->{loadOnly}) {
689            Trace("Loading from existing files.") if T(2);
690        } else {
691            Trace("Generating subsystem data.") if T(2);
692            # This hash will contain the role for each EC. When we're done, this
693            # information will be used to generate the Catalyzes table.
694            my %ecToRoles = ();
695      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
696      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
697      # role hash. The hash tracks each role ID so that we don't create      # role hash. The hash tracks each role ID so that we don't create
698      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
699            # and memorize up the reactions.
700            my ($genomeID, $roleID);
701      my %roleData = ();      my %roleData = ();
702      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
703          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
704          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
705                # Get the subsystem object.
706                my $sub = $fig->get_subsystem($subsysID);
707          # Create the subsystem record.          # Create the subsystem record.
708          $loadSubsystem->Put($subsysID);              my $curator = $sub->get_curator();
709          # Get the subsystem's roles.              my $notes = $sub->get_notes();
710          my @roles = $fig->subsystem_to_roles($subsysID);              $loadSubsystem->Put($subsysID, $curator, $notes);
711          # Connect the roles to the subsystem. If a role is new, we create              # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
712          # a role record for it.              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
713          for my $roleID (@roles) {                  # Connect to this role.
714              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
715              $loadOccursInSubsystem->Put($roleID, $subsysID);                  $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
716                    # If it's a new role, add it to the role table.
717              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
718                  $loadRole->Put($roleID);                      # Get the role's abbreviation.
719                        my $abbr = $sub->get_role_abbr($col);
720                        # Add the role.
721                        $loadRole->Put($roleID, $abbr);
722                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
723                        # Check for an EC number.
724                        if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
725                            my $ec = $1;
726                            $loadRoleEC->Put($roleID, $ec);
727                            $ecToRoles{$ec} = $roleID;
728                        }
729              }              }
730          }          }
731          # Now all roles for this subsystem have been filled in. We create the              # Now we create the spreadsheet for the subsystem by matching roles to
732          # spreadsheet by matches roles to genomes. To do this, we need to              # genomes. Each genome is a row and each role is a column. We may need
733          # get the genomes on the sheet.              # to actually create the roles as we find them.
734          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
735          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};              for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
736          for my $genomeID (@genomes) {                  # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
737              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
738                  # Connect the genome to the subsystem.                      # Count the PEGs and cells found for verification purposes.
739                  $loadParticipatesIn->Put($genomeID, $subsysID);                      my $pegCount = 0;
740                        my $cellCount = 0;
741                        # Create a list for the PEGs we find. This list will be used
742                        # to generate cluster numbers.
743                        my @pegsFound = ();
744                        # Create a hash that maps spreadsheet IDs to PEGs. We will
745                        # use this to generate the ContainsFeature data after we have
746                        # the cluster numbers.
747                        my %cellPegs = ();
748                        # Get the genome's variant code for this subsystem.
749                        my $variantCode = $sub->get_variant_code($row);
750                  # Loop through the subsystem's roles. We use an index because it is                  # Loop through the subsystem's roles. We use an index because it is
751                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
752                  for (my $i = 0; $i <= $#roles; $i++) {                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
753                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
754                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                          my @pegs = $sub->get_pegs_from_cell($row, $col);
755                      # Only proceed if features exist.                      # Only proceed if features exist.
756                      if (@pegs > 0) {                      if (@pegs > 0) {
757                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
758                          my $cellID = "$subsysID:$genomeID:$i";                              $cellCount++;
759                                my $cellID = "$subsysID:$genomeID:$col";
760                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
761                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
762                          $loadIsRoleOf->Put($role, $cellID);                              $loadIsRoleOf->Put($roleID, $cellID);
763                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
764                          # Attach the features to it.                              # Remember its features.
765                          for my $pegID (@pegs) {                              push @pegsFound, @pegs;
766                              $loadContainsFeature->Put($cellID, $pegID);                              $cellPegs{$cellID} = \@pegs;
767                                $pegCount += @pegs;
768                            }
769                        }
770                        # If we found some cells for this genome, we need to compute clusters and
771                        # denote it participates in the subsystem.
772                        if ($pegCount > 0) {
773                            Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
774                            $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
775                            # Partition the PEGs found into clusters.
776                            my @clusters = $fig->compute_clusters(\@pegsFound, $sub);
777                            # Create a hash mapping PEG IDs to cluster numbers.
778                            # We default to -1 for all of them.
779                            my %clusterOf = map { $_ => -1 } @pegsFound;
780                            for (my $i = 0; $i <= $#clusters; $i++) {
781                                my $subList = $clusters[$i];
782                                for my $peg (@{$subList}) {
783                                    $clusterOf{$peg} = $i;
784                                }
785                            }
786                            # Create the ContainsFeature data.
787                            for my $cellID (keys %cellPegs) {
788                                my $cellList = $cellPegs{$cellID};
789                                for my $cellPeg (@$cellList) {
790                                    $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
791                          }                          }
792                      }                      }
793                  }                  }
794              }              }
795          }          }
796                # Now we need to generate the subsets. The subset names must be concatenated to
797                # the subsystem name to make them unique keys. There are two types of subsets:
798                # genome subsets and role subsets. We do the role subsets first.
799                my @subsetNames = $sub->get_subset_names();
800                for my $subsetID (@subsetNames) {
801                    # Create the subset record.
802                    my $actualID = "$subsysID:$subsetID";
803                    $loadRoleSubset->Put($actualID);
804                    # Connect the subset to the subsystem.
805                    $loadHasRoleSubset->Put($subsysID, $actualID);
806                    # Connect the subset to its roles.
807                    my @roles = $sub->get_subsetC_roles($subsetID);
808                    for my $roleID (@roles) {
809                        $loadConsistsOfRoles->Put($actualID, $roleID);
810      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
811  }  }
812                # Next the genome subsets.
813  =head3 LoadDiagramData              @subsetNames = $sub->get_subset_namesR();
814                for my $subsetID (@subsetNames) {
815  C<< my $stats = $spl->LoadDiagramData(); >>                  # Create the subset record.
816                    my $actualID = "$subsysID:$subsetID";
817  Load the diagram data from FIG into Sprout.                  $loadGenomeSubset->Put($actualID);
818                    # Connect the subset to the subsystem.
819  Diagrams are used to organize functional roles. The diagram shows the                  $loadHasGenomeSubset->Put($subsysID, $actualID);
820  connections between chemicals that interact with a subsystem.                  # Connect the subset to its genomes.
821                    my @genomes = $sub->get_subsetR($subsetID);
822  The following relations are loaded by this method.                  for my $genomeID (@genomes) {
823                        $loadConsistsOfGenomes->Put($actualID, $genomeID);
824      Diagram                  }
825      RoleOccursIn              }
826            }
827  =over 4          # Now we loop through the diagrams. We need to create the diagram records
828            # and link each diagram to its roles. Note that only roles which occur
829  =item RETURNS          # in subsystems (and therefore appear in the %ecToRoles hash) are
830            # included.
831  Returns a statistics object for the loads.          for my $map (@maps) {
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadDiagramData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the map list.  
     my @maps = $fig->all_maps;  
     my $mapCount = @maps;  
     my $genomeCount = (keys %{$self->{genomes}});  
     my $featureCount = $genomeCount * 4000;  
     # Create load objects for each of the tables we're loading.  
     my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);  
     my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);  
     Trace("Beginning diagram data load.") if T(2);  
     # Loop through the diagrams.  
     for my $map ($fig->all_maps) {  
832          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
833          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
834          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 754  Line 837 
837          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
838          my %roleHash = ();          my %roleHash = ();
839          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
840              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
841                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
842                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
843              }              }
844          }          }
845      }      }
846            # Before we leave, we must create the Catalyzes table. We start with the reactions,
847            # then use the "ecToRoles" table to convert EC numbers to role IDs.
848            my @reactions = $fig->all_reactions();
849            for my $reactionID (@reactions) {
850                # Get this reaction's list of roles. The results will be EC numbers.
851                my @roles = $fig->catalyzed_by($reactionID);
852                # Loop through the roles, creating catalyzation records.
853                for my $thisRole (@roles) {
854                    if (exists $ecToRoles{$thisRole}) {
855                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
856                    }
857                }
858            }
859        }
860      # Finish the load.      # Finish the load.
861      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
862      return $retVal;      return $retVal;
# Line 801  Line 898 
898      my $fig = $self->{fig};      my $fig = $self->{fig};
899      # Get the genome hash.      # Get the genome hash.
900      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
901      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
902      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
903      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
904      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
905            Trace("Loading from existing files.") if T(2);
906        } else {
907            Trace("Generating property data.") if T(2);
908      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
909      my %propertyKeys = ();      my %propertyKeys = ();
910      my $nextID = 1;      my $nextID = 1;
911      # Loop through the genomes.      # Loop through the genomes.
912      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
913          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
914                Trace("Generating properties for $genomeID.") if T(3);
915          # Get the genome's features. The feature ID is the first field in the          # Get the genome's features. The feature ID is the first field in the
916          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
917          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
918          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
919                my $featureCount = 0;
920                my $propertyCount = 0;
921          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
922          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
923              # Get all attributes for this feature. We do this one feature at a time              # Get all attributes for this feature. We do this one feature at a time
924              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
925              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
926                    if (scalar @attributeList) {
927                        $featureCount++;
928                    }
929              # Loop through the attributes.              # Loop through the attributes.
930              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
931                        $propertyCount++;
932                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
933                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
934                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 845  Line 950 
950                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
951              }              }
952          }          }
953                # Update the statistics.
954                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
955                $loadHasProperty->Add("featuresIn", $featureCount);
956                $loadHasProperty->Add("propertiesIn", $propertyCount);
957            }
958      }      }
959      # Finish the load.      # Finish the load.
960      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 885  Line 995 
995      my $fig = $self->{fig};      my $fig = $self->{fig};
996      # Get the genome hash.      # Get the genome hash.
997      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
998      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
999      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1000      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1001      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1002      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1003      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1004      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1005            Trace("Loading from existing files.") if T(2);
1006        } else {
1007            Trace("Generating annotation data.") if T(2);
1008      # Create a hash of user names. We'll use this to prevent us from generating duplicate      # Create a hash of user names. We'll use this to prevent us from generating duplicate
1009      # user records.      # user records.
1010      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 913  Line 1025 
1025              # Create a hash of timestamps. We use this to prevent duplicate time stamps              # Create a hash of timestamps. We use this to prevent duplicate time stamps
1026              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1027              my %seenTimestamps = ();              my %seenTimestamps = ();
1028              # Check for a functional assignment.                  # Loop through the annotations.
             my $func = $fig->function_of($peg);  
             if ($func) {  
                 # If this is NOT a hypothetical assignment, we create an  
                 # assignment annotation for it.  
                 if (! FIG::hypo($peg)) {  
                     # Note that we double the slashes so that what goes into the database is  
                     # a new-line escape sequence rather than an actual new-line.  
                     $loadAnnotation->Put("$peg:$time", $time, "FIG\\nSet function to\\n$func");  
                     $loadIsTargetOfAnnotation->Put($peg, "$peg:$time");  
                     $loadMadeAnnotation->Put("FIG", "$peg:$time");  
                     # Denote we've seen this timestamp.  
                     $seenTimestamps{$time} = 1;  
                 }  
                 # Now loop through the real annotations.  
1029                  for my $tuple ($fig->feature_annotations($peg, "raw")) {                  for my $tuple ($fig->feature_annotations($peg, "raw")) {
1030                      my ($fid, $timestamp, $user, $text) = @{$tuple};                      my ($fid, $timestamp, $user, $text) = @{$tuple};
1031                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
# Line 941  Line 1039 
1039                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1040                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1041                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1042                          # Here it's a number. We need to insure it's unique.                          # Here it's a number. We need to insure the one we use to form
1043                          while ($seenTimestamps{$timestamp}) {                          # the key is unique.
1044                              $timestamp++;                          my $keyStamp = $timestamp;
1045                            while ($seenTimestamps{$keyStamp}) {
1046                                $keyStamp++;
1047                          }                          }
1048                          $seenTimestamps{$timestamp} = 1;                          $seenTimestamps{$keyStamp} = 1;
1049                          my $annotationID = "$peg:$timestamp";                          my $annotationID = "$peg:$keyStamp";
1050                          # Insure the user exists.                          # Insure the user exists.
1051                          if (! $users{$user}) {                          if (! $users{$user}) {
1052                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 954  Line 1054 
1054                              $users{$user} = 1;                              $users{$user} = 1;
1055                          }                          }
1056                          # Generate the annotation.                          # Generate the annotation.
1057                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                          $loadAnnotation->Put($annotationID, $timestamp, $text);
1058                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1059                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1060                      } else {                      } else {
# Line 1005  Line 1105 
1105      my $fig = $self->{fig};      my $fig = $self->{fig};
1106      # Get the genome hash.      # Get the genome hash.
1107      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1108      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1109      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1110      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1111      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1112      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1113            Trace("Loading from existing files.") if T(2);
1114        } else {
1115            Trace("Generating annotation data.") if T(2);
1116      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1117      my %sourceURL = ();      my %sourceURL = ();
1118      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1024  Line 1126 
1126              chomp $line;              chomp $line;
1127              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1128              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1129              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1130                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1131                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1132              }              }
1133              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1134                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1135                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1136                        $sourceDesc{$sourceID} = $sourceID;
1137              }              }
1138          }          }
1139          close TMP;          close TMP;
1140      }      }
1141            # Write the source descriptions.
1142            for my $sourceID (keys %sourceDesc) {
1143                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1144            }
1145        }
1146      # Finish the load.      # Finish the load.
1147      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1148      return $retVal;      return $retVal;
# Line 1074  Line 1182 
1182      my $fig = $self->{fig};      my $fig = $self->{fig};
1183      # Get the genome hash.      # Get the genome hash.
1184      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1185      # Convert the genome hash. We'll get the genus and species for each genome and make      # Convert the genome hash. We'll get the genus and species for each genome and make
1186      # it the key.      # it the key.
1187      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1188      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1189      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1190      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1191      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1192            Trace("Loading from existing files.") if T(2);
1193        } else {
1194            Trace("Generating external data.") if T(2);
1195      # We loop through the files one at a time. First, the organism file.      # We loop through the files one at a time. First, the organism file.
1196      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1197      my $orgLine;      my $orgLine;
# Line 1111  Line 1221 
1221              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1222          }          }
1223      }      }
1224        }
1225        # Finish the load.
1226        my $retVal = $self->_FinishAll();
1227        return $retVal;
1228    }
1229    
1230    
1231    =head3 LoadReactionData
1232    
1233    C<< my $stats = $spl->LoadReactionData(); >>
1234    
1235    Load the reaction data from FIG into Sprout.
1236    
1237    Reaction data connects reactions to the compounds that participate in them.
1238    
1239    The following relations are loaded by this method.
1240    
1241        Reaction
1242        ReactionURL
1243        Compound
1244        CompoundName
1245        CompoundCAS
1246        IsAComponentOf
1247    
1248    This method proceeds reaction by reaction rather than genome by genome.
1249    
1250    =over 4
1251    
1252    =item RETURNS
1253    
1254    Returns a statistics object for the loads.
1255    
1256    =back
1257    
1258    =cut
1259    #: Return Type $%;
1260    sub LoadReactionData {
1261        # Get this object instance.
1262        my ($self) = @_;
1263        # Get the FIG object.
1264        my $fig = $self->{fig};
1265        # Create load objects for each of the tables we're loading.
1266        my $loadReaction = $self->_TableLoader('Reaction');
1267        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1268        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1269        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1270        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1271        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1272        if ($self->{options}->{loadOnly}) {
1273            Trace("Loading from existing files.") if T(2);
1274        } else {
1275            Trace("Generating annotation data.") if T(2);
1276            # First we create the compounds.
1277            my @compounds = $fig->all_compounds();
1278            for my $cid (@compounds) {
1279                # Check for names.
1280                my @names = $fig->names_of_compound($cid);
1281                # Each name will be given a priority number, starting with 1.
1282                my $prio = 1;
1283                for my $name (@names) {
1284                    $loadCompoundName->Put($cid, $name, $prio++);
1285                }
1286                # Create the main compound record. Note that the first name
1287                # becomes the label.
1288                my $label = (@names > 0 ? $names[0] : $cid);
1289                $loadCompound->Put($cid, $label);
1290                # Check for a CAS ID.
1291                my $cas = $fig->cas($cid);
1292                if ($cas) {
1293                    $loadCompoundCAS->Put($cid, $cas);
1294                }
1295            }
1296            # All the compounds are set up, so we need to loop through the reactions next. First,
1297            # we initialize the discriminator index. This is a single integer used to insure
1298            # duplicate elements in a reaction are not accidentally collapsed.
1299            my $discrim = 0;
1300            my @reactions = $fig->all_reactions();
1301            for my $reactionID (@reactions) {
1302                # Create the reaction record.
1303                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1304                # Compute the reaction's URL.
1305                my $url = HTML::reaction_link($reactionID);
1306                # Put it in the ReactionURL table.
1307                $loadReactionURL->Put($reactionID, $url);
1308                # Now we need all of the reaction's compounds. We get these in two phases,
1309                # substrates first and then products.
1310                for my $product (0, 1) {
1311                    # Get the compounds of the current type for the current reaction. FIG will
1312                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1313                    # have location data in SEED, so it defaults to the empty string.
1314                    my @compounds = $fig->reaction2comp($reactionID, $product);
1315                    for my $compData (@compounds) {
1316                        # Extract the compound data from the current tuple.
1317                        my ($cid, $stoich, $main) = @{$compData};
1318                        # Link the compound to the reaction.
1319                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1320                                                 $product, $stoich);
1321                    }
1322                }
1323            }
1324        }
1325      # Finish the load.      # Finish the load.
1326      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1327      return $retVal;      return $retVal;
# Line 1146  Line 1357 
1357      my $fig = $self->{fig};      my $fig = $self->{fig};
1358      # Get the genome hash.      # Get the genome hash.
1359      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1360      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1361      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1362      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1363            Trace("Loading from existing files.") if T(2);
1364        } else {
1365            Trace("Generating group data.") if T(2);
1366      # Loop through the genomes.      # Loop through the genomes.
1367      my $line;      my $line;
1368      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1165  Line 1378 
1378          }          }
1379          close TMP;          close TMP;
1380      }      }
1381        }
1382      # Finish the load.      # Finish the load.
1383      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1384      return $retVal;      return $retVal;
# Line 1186  Line 1400 
1400    
1401  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1402    
1403  =item rowCount (optional)  =item ignore
1404    
1405  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1406    
1407  =item RETURN  =item RETURN
1408    
# Line 1200  Line 1414 
1414    
1415  sub _TableLoader {  sub _TableLoader {
1416      # Get the parameters.      # Get the parameters.
1417      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1418      # Create the load object.      # Create the load object.
1419      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1420                                   $ignore);
1421      # Cache it in the loader list.      # Cache it in the loader list.
1422      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1423      # Return it to the caller.      # Return it to the caller.
# Line 1239  Line 1454 
1454      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1455      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads restartable.
1456      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1457            # Get the relation name.
1458            my $relName = $loader->RelName;
1459            # Check the ignore flag.
1460            if ($loader->Ignore) {
1461                Trace("Relation $relName not loaded.") if T(2);
1462            } else {
1463                # Here we really need to finish.
1464                Trace("Finishing $relName.") if T(2);
1465          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1466                if ($self->{options}->{dbLoad}) {
1467                    # Here we want to use the load file just created to load the database.
1468                    Trace("Loading relation $relName.") if T(2);
1469                    my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1470                    # Accumulate the statistics from the DB load.
1471                    $stats->Accumulate($newStats);
1472                }
1473          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1474          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1475      }      }
1476        }
1477      # Return the load statistics.      # Return the load statistics.
1478      return $retVal;      return $retVal;
1479  }  }

Legend:
Removed from v.1.9  
changed lines
  Added in v.1.30

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3