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

Diff of /Sprout/SproutLoad.pm

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

revision 1.7, Tue Sep 13 19:05:20 2005 UTC revision 1.32, Sun Apr 2 17:34:44 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 51  Line 52 
52    
53  =head3 new  =head3 new
54    
55  C<< my $spl = SproutLoad->new($sprout, $fig, $genomeFile, $subsysFile); >>  C<< my $spl = SproutLoad->new($sprout, $fig, $genomeFile, $subsysFile, $options); >>
56    
57  Construct a new Sprout Loader object, specifying the two participating databases and  Construct a new Sprout Loader object, specifying the two participating databases and
58  the name of the files containing the list of genomes and subsystems to use.  the name of the files containing the list of genomes and subsystems to use.
# Line 82  Line 83 
83  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all known subsystems will be
84  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. Only subsystem data related to the trusted subsystems is loaded.
85    
86    =item options
87    
88    Reference to a hash of command-line options.
89    
90  =back  =back
91    
92  =cut  =cut
93    
94  sub new {  sub new {
95      # Get the parameters.      # Get the parameters.
96      my ($class, $sprout, $fig, $genomeFile, $subsysFile) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
97      # Load the list of genomes into a hash.      # Load the list of genomes into a hash.
98      my %genomes;      my %genomes;
99      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
# Line 158  Line 163 
163                    sprout => $sprout,                    sprout => $sprout,
164                    loadDirectory => $directory,                    loadDirectory => $directory,
165                    erdb => $sprout->{_erdb},                    erdb => $sprout->{_erdb},
166                    loaders => []                    loaders => [],
167                      options => $options
168                   };                   };
169      # Bless and return it.      # Bless and return it.
170      bless $retVal, $class;      bless $retVal, $class;
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 192  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 210  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 262  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 305  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 $genome.") if T(3);
# Line 362  Line 392 
392                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
393                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
394                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
395                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
396                              # the hash makes it to the output.                              # the hash makes it to the output.
397                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
398                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 377  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 404  Line 435 
435      FeatureTranslation      FeatureTranslation
436      FeatureUpstream      FeatureUpstream
437      IsLocatedIn      IsLocatedIn
438        HasFeature
439    
440  =over 4  =over 4
441    
# Line 422  Line 454 
454      my $fig = $self->{fig};      my $fig = $self->{fig};
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 $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
460      my $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
461      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
462      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
463      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
464        my $loadHasFeature = $self->_TableLoader('HasFeature');
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 445  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                    # Link it to the parent genome.
486                    $loadHasFeature->Put($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 475  Line 511 
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 = split /\s*,\s*/, $locations;              my @locationList = split /\s*,\s*/, $locations;
514                    # Create the location position indicator.
515                    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 488  Line 526 
526                  push @locOList, $locObject;                  push @locOList, $locObject;
527                  # Loop through the chunks, creating IsLocatedIn records. The variable                  # Loop through the chunks, creating IsLocatedIn records. The variable
528                  # "$i" will be used to keep the location index.                  # "$i" will be used to keep the location index.
                 my $i = 1;  
529                  for my $locChunk (@locOList) {                  for my $locChunk (@locOList) {
530                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,
531                                            $locChunk->Dir, $locChunk->Length, $i);                                            $locChunk->Dir, $locChunk->Length, $i);
# Line 497  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 533  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 564  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 585  Line 624 
624    
625      Subsystem      Subsystem
626      Role      Role
627        RoleEC
628      SSCell      SSCell
629      ContainsFeature      ContainsFeature
630      IsGenomeOf      IsGenomeOf
# Line 592  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 601  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 618  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                # Get the subsystem object.
704                my $sub = $fig->get_subsystem($subsysID);
705                # Only proceed if the subsystem has a spreadsheet.
706                if (! $sub->{empty_ss}) {
707          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
708          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
709          # Create the subsystem record.          # Create the subsystem record.
710          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
711          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
712          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
713          # 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.
714          # a role record for it.                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
715          for my $roleID (@roles) {                      # Connect to this role.
716              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
717              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
718                        # If it's a new role, add it to the role table.
719              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
720                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
721                            my $abbr = $sub->get_role_abbr($col);
722                            # Add the role.
723                            $loadRole->Put($roleID, $abbr);
724                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
725                            # Check for an EC number.
726                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
727                                my $ec = $1;
728                                $loadRoleEC->Put($roleID, $ec);
729                                $ecToRoles{$ec} = $roleID;
730              }              }
731          }          }
732          # Now all roles for this subsystem have been filled in. We create the                  }
733          # spreadsheet by matches roles to genomes. To do this, we need to                  # Now we create the spreadsheet for the subsystem by matching roles to
734          # get the genomes on the sheet.                  # genomes. Each genome is a row and each role is a column. We may need
735                    # to actually create the roles as we find them.
736          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
737          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
738          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
739              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
740                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
741                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
742                            my $cellCount = 0;
743                            # Create a list for the PEGs we find. This list will be used
744                            # to generate cluster numbers.
745                            my @pegsFound = ();
746                            # Create a hash that maps spreadsheet IDs to PEGs. We will
747                            # use this to generate the ContainsFeature data after we have
748                            # the cluster numbers.
749                            my %cellPegs = ();
750                            # Get the genome's variant code for this subsystem.
751                            my $variantCode = $sub->get_variant_code($row);
752                  # 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
753                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
754                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
755                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
756                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = $sub->get_pegs_from_cell($row, $col);
757                      # Only proceed if features exist.                      # Only proceed if features exist.
758                      if (@pegs > 0) {                      if (@pegs > 0) {
759                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
760                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
761                                    my $cellID = "$subsysID:$genomeID:$col";
762                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
763                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
764                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
765                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
766                          # Attach the features to it.                                  # Remember its features.
767                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
768                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
769                                    $pegCount += @pegs;
770                                }
771                            }
772                            # If we found some cells for this genome, we need to compute clusters and
773                            # denote it participates in the subsystem.
774                            if ($pegCount > 0) {
775                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
776                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
777                                # Partition the PEGs found into clusters.
778                                my @clusters = $fig->compute_clusters(\@pegsFound, $sub);
779                                # Create a hash mapping PEG IDs to cluster numbers.
780                                # We default to -1 for all of them.
781                                my %clusterOf = map { $_ => -1 } @pegsFound;
782                                for (my $i = 0; $i <= $#clusters; $i++) {
783                                    my $subList = $clusters[$i];
784                                    for my $peg (@{$subList}) {
785                                        $clusterOf{$peg} = $i;
786                                    }
787                                }
788                                # Create the ContainsFeature data.
789                                for my $cellID (keys %cellPegs) {
790                                    my $cellList = $cellPegs{$cellID};
791                                    for my $cellPeg (@$cellList) {
792                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
793                          }                          }
794                      }                      }
795                  }                  }
796              }              }
797          }          }
798                    # Now we need to generate the subsets. The subset names must be concatenated to
799                    # the subsystem name to make them unique keys. There are two types of subsets:
800                    # genome subsets and role subsets. We do the role subsets first.
801                    my @subsetNames = $sub->get_subset_names();
802                    for my $subsetID (@subsetNames) {
803                        # Create the subset record.
804                        my $actualID = "$subsysID:$subsetID";
805                        $loadRoleSubset->Put($actualID);
806                        # Connect the subset to the subsystem.
807                        $loadHasRoleSubset->Put($subsysID, $actualID);
808                        # Connect the subset to its roles.
809                        my @roles = $sub->get_subsetC_roles($subsetID);
810                        for my $roleID (@roles) {
811                            $loadConsistsOfRoles->Put($actualID, $roleID);
812      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
813  }  }
814                    # Next the genome subsets.
815  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
816                    for my $subsetID (@subsetNames) {
817  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
818                        my $actualID = "$subsysID:$subsetID";
819  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
820                        # Connect the subset to the subsystem.
821  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
822  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
823                        my @genomes = $sub->get_subsetR($subsetID);
824  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
825                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
826      Diagram                      }
827      RoleOccursIn                  }
828                }
829  =over 4              # Now we loop through the diagrams. We need to create the diagram records
830                # and link each diagram to its roles. Note that only roles which occur
831  =item RETURNS              # in subsystems (and therefore appear in the %ecToRoles hash) are
832                # included.
833  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) {  
834          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
835          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
836          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 740  Line 839 
839          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
840          my %roleHash = ();          my %roleHash = ();
841          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
842              if (! $roleHash{$role}) {                      if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
843                  $loadRoleOccursIn->Put($role, $map);                          $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
844                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
845              }              }
846          }          }
847      }      }
848                # Before we leave, we must create the Catalyzes table. We start with the reactions,
849                # then use the "ecToRoles" table to convert EC numbers to role IDs.
850                my @reactions = $fig->all_reactions();
851                for my $reactionID (@reactions) {
852                    # Get this reaction's list of roles. The results will be EC numbers.
853                    my @roles = $fig->catalyzed_by($reactionID);
854                    # Loop through the roles, creating catalyzation records.
855                    for my $thisRole (@roles) {
856                        if (exists $ecToRoles{$thisRole}) {
857                            $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
858                        }
859                    }
860                }
861            }
862        }
863      # Finish the load.      # Finish the load.
864      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
865      return $retVal;      return $retVal;
# Line 787  Line 901 
901      my $fig = $self->{fig};      my $fig = $self->{fig};
902      # Get the genome hash.      # Get the genome hash.
903      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
904      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
905      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
906      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
907      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
908            Trace("Loading from existing files.") if T(2);
909        } else {
910            Trace("Generating property data.") if T(2);
911      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
912      my %propertyKeys = ();      my %propertyKeys = ();
913      my $nextID = 1;      my $nextID = 1;
914      # Loop through the genomes.      # Loop through the genomes.
915      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
916          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
917                Trace("Generating properties for $genomeID.") if T(3);
918          # 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
919          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
920          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
921          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
922                my $featureCount = 0;
923                my $propertyCount = 0;
924          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
925          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
926              # 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
927              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
928              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
929                    if (scalar @attributeList) {
930                        $featureCount++;
931                    }
932              # Loop through the attributes.              # Loop through the attributes.
933              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
934                        $propertyCount++;
935                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
936                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
937                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 831  Line 953 
953                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
954              }              }
955          }          }
956                # Update the statistics.
957                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
958                $loadHasProperty->Add("featuresIn", $featureCount);
959                $loadHasProperty->Add("propertiesIn", $propertyCount);
960            }
961      }      }
962      # Finish the load.      # Finish the load.
963      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 871  Line 998 
998      my $fig = $self->{fig};      my $fig = $self->{fig};
999      # Get the genome hash.      # Get the genome hash.
1000      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1001      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1002      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1003      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1004      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1005      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1006      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1007      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1008            Trace("Loading from existing files.") if T(2);
1009        } else {
1010            Trace("Generating annotation data.") if T(2);
1011      # 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
1012      # user records.      # user records.
1013      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 899  Line 1028 
1028              # 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
1029              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1030              my %seenTimestamps = ();              my %seenTimestamps = ();
1031              # 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.  
1032                  for my $tuple ($fig->feature_annotations($peg, "raw")) {                  for my $tuple ($fig->feature_annotations($peg, "raw")) {
1033                      my ($fid, $timestamp, $user, $text) = @{$tuple};                      my ($fid, $timestamp, $user, $text) = @{$tuple};
1034                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
# Line 927  Line 1042 
1042                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1043                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1044                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1045                          # Here it's a number. We need to insure it's unique.                          # Here it's a number. We need to insure the one we use to form
1046                          while ($seenTimestamps{$timestamp}) {                          # the key is unique.
1047                              $timestamp++;                          my $keyStamp = $timestamp;
1048                            while ($seenTimestamps{$keyStamp}) {
1049                                $keyStamp++;
1050                          }                          }
1051                          $seenTimestamps{$timestamp} = 1;                          $seenTimestamps{$keyStamp} = 1;
1052                          my $annotationID = "$peg:$timestamp";                          my $annotationID = "$peg:$keyStamp";
1053                          # Insure the user exists.                          # Insure the user exists.
1054                          if (! $users{$user}) {                          if (! $users{$user}) {
1055                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 940  Line 1057 
1057                              $users{$user} = 1;                              $users{$user} = 1;
1058                          }                          }
1059                          # Generate the annotation.                          # Generate the annotation.
1060                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                          $loadAnnotation->Put($annotationID, $timestamp, $text);
1061                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1062                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1063                      } else {                      } else {
# Line 991  Line 1108 
1108      my $fig = $self->{fig};      my $fig = $self->{fig};
1109      # Get the genome hash.      # Get the genome hash.
1110      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1111      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1112      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1113      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1114      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1115      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1116            Trace("Loading from existing files.") if T(2);
1117        } else {
1118            Trace("Generating annotation data.") if T(2);
1119      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1120      my %sourceURL = ();      my %sourceURL = ();
1121      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1010  Line 1129 
1129              chomp $line;              chomp $line;
1130              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1131              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1132              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1133                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1134                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1135              }              }
1136              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1137                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1138                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1139                        $sourceDesc{$sourceID} = $sourceID;
1140              }              }
1141          }          }
1142          close TMP;          close TMP;
1143      }      }
1144            # Write the source descriptions.
1145            for my $sourceID (keys %sourceDesc) {
1146                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1147            }
1148        }
1149      # Finish the load.      # Finish the load.
1150      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1151      return $retVal;      return $retVal;
# Line 1060  Line 1185 
1185      my $fig = $self->{fig};      my $fig = $self->{fig};
1186      # Get the genome hash.      # Get the genome hash.
1187      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1188      # 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
1189      # it the key.      # it the key.
1190      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1191      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1192      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1193      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1194      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1195            Trace("Loading from existing files.") if T(2);
1196        } else {
1197            Trace("Generating external data.") if T(2);
1198      # 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.
1199      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1200      my $orgLine;      my $orgLine;
# Line 1097  Line 1224 
1224              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1225          }          }
1226      }      }
1227        }
1228        # Finish the load.
1229        my $retVal = $self->_FinishAll();
1230        return $retVal;
1231    }
1232    
1233    
1234    =head3 LoadReactionData
1235    
1236    C<< my $stats = $spl->LoadReactionData(); >>
1237    
1238    Load the reaction data from FIG into Sprout.
1239    
1240    Reaction data connects reactions to the compounds that participate in them.
1241    
1242    The following relations are loaded by this method.
1243    
1244        Reaction
1245        ReactionURL
1246        Compound
1247        CompoundName
1248        CompoundCAS
1249        IsAComponentOf
1250    
1251    This method proceeds reaction by reaction rather than genome by genome.
1252    
1253    =over 4
1254    
1255    =item RETURNS
1256    
1257    Returns a statistics object for the loads.
1258    
1259    =back
1260    
1261    =cut
1262    #: Return Type $%;
1263    sub LoadReactionData {
1264        # Get this object instance.
1265        my ($self) = @_;
1266        # Get the FIG object.
1267        my $fig = $self->{fig};
1268        # Create load objects for each of the tables we're loading.
1269        my $loadReaction = $self->_TableLoader('Reaction');
1270        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1271        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1272        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1273        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1274        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1275        if ($self->{options}->{loadOnly}) {
1276            Trace("Loading from existing files.") if T(2);
1277        } else {
1278            Trace("Generating annotation data.") if T(2);
1279            # First we create the compounds.
1280            my @compounds = $fig->all_compounds();
1281            for my $cid (@compounds) {
1282                # Check for names.
1283                my @names = $fig->names_of_compound($cid);
1284                # Each name will be given a priority number, starting with 1.
1285                my $prio = 1;
1286                for my $name (@names) {
1287                    $loadCompoundName->Put($cid, $name, $prio++);
1288                }
1289                # Create the main compound record. Note that the first name
1290                # becomes the label.
1291                my $label = (@names > 0 ? $names[0] : $cid);
1292                $loadCompound->Put($cid, $label);
1293                # Check for a CAS ID.
1294                my $cas = $fig->cas($cid);
1295                if ($cas) {
1296                    $loadCompoundCAS->Put($cid, $cas);
1297                }
1298            }
1299            # All the compounds are set up, so we need to loop through the reactions next. First,
1300            # we initialize the discriminator index. This is a single integer used to insure
1301            # duplicate elements in a reaction are not accidentally collapsed.
1302            my $discrim = 0;
1303            my @reactions = $fig->all_reactions();
1304            for my $reactionID (@reactions) {
1305                # Create the reaction record.
1306                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1307                # Compute the reaction's URL.
1308                my $url = HTML::reaction_link($reactionID);
1309                # Put it in the ReactionURL table.
1310                $loadReactionURL->Put($reactionID, $url);
1311                # Now we need all of the reaction's compounds. We get these in two phases,
1312                # substrates first and then products.
1313                for my $product (0, 1) {
1314                    # Get the compounds of the current type for the current reaction. FIG will
1315                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1316                    # have location data in SEED, so it defaults to the empty string.
1317                    my @compounds = $fig->reaction2comp($reactionID, $product);
1318                    for my $compData (@compounds) {
1319                        # Extract the compound data from the current tuple.
1320                        my ($cid, $stoich, $main) = @{$compData};
1321                        # Link the compound to the reaction.
1322                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1323                                                 $product, $stoich);
1324                    }
1325                }
1326            }
1327        }
1328      # Finish the load.      # Finish the load.
1329      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1330      return $retVal;      return $retVal;
# Line 1132  Line 1360 
1360      my $fig = $self->{fig};      my $fig = $self->{fig};
1361      # Get the genome hash.      # Get the genome hash.
1362      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1363      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1364      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1365      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1366            Trace("Loading from existing files.") if T(2);
1367        } else {
1368            Trace("Generating group data.") if T(2);
1369      # Loop through the genomes.      # Loop through the genomes.
1370      my $line;      my $line;
1371      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1151  Line 1381 
1381          }          }
1382          close TMP;          close TMP;
1383      }      }
1384        }
1385      # Finish the load.      # Finish the load.
1386      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1387      return $retVal;      return $retVal;
# Line 1172  Line 1403 
1403    
1404  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1405    
1406  =item rowCount (optional)  =item ignore
1407    
1408  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1409    
1410  =item RETURN  =item RETURN
1411    
# Line 1186  Line 1417 
1417    
1418  sub _TableLoader {  sub _TableLoader {
1419      # Get the parameters.      # Get the parameters.
1420      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1421      # Create the load object.      # Create the load object.
1422      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1423                                   $ignore);
1424      # Cache it in the loader list.      # Cache it in the loader list.
1425      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1426      # Return it to the caller.      # Return it to the caller.
# Line 1225  Line 1457 
1457      # 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
1458      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads restartable.
1459      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1460            # Get the relation name.
1461            my $relName = $loader->RelName;
1462            # Check the ignore flag.
1463            if ($loader->Ignore) {
1464                Trace("Relation $relName not loaded.") if T(2);
1465            } else {
1466                # Here we really need to finish.
1467                Trace("Finishing $relName.") if T(2);
1468          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1469                if ($self->{options}->{dbLoad}) {
1470                    # Here we want to use the load file just created to load the database.
1471                    Trace("Loading relation $relName.") if T(2);
1472                    my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1473                    # Accumulate the statistics from the DB load.
1474                    $stats->Accumulate($newStats);
1475                }
1476          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1477          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1478      }      }
1479        }
1480      # Return the load statistics.      # Return the load statistics.
1481      return $retVal;      return $retVal;
1482  }  }

Legend:
Removed from v.1.7  
changed lines
  Added in v.1.32

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3