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

Diff of /Sprout/SproutLoad.pm

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

revision 1.19, Thu Oct 20 09:34:09 2005 UTC revision 1.32, Sun Apr 2 17:34:44 2006 UTC
# Line 171  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 198  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 216  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 268  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 311  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 389  Line 413 
413              }              }
414          }          }
415      }      }
416        }
417      # All done. Finish the load.      # All done. Finish the load.
418      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
419      return $retVal;      return $retVal;
# Line 410  Line 435 
435      FeatureTranslation      FeatureTranslation
436      FeatureUpstream      FeatureUpstream
437      IsLocatedIn      IsLocatedIn
438        HasFeature
439    
440  =over 4  =over 4
441    
# Line 426  Line 452 
452      my ($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 = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
461      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
462      if (! $limited) {      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 $genomeID.") if T(3);
# Line 459  Line 482 
482              my ($featureID, $locations, undef, $type) = @{$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 $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
489                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
490              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
491                  # Get the links.                  # Get the links.
492                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
493                  for my $link (@links) {                  for my $link (@links) {
# Line 483  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
# Line 512  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 548  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 579  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 608  Line 632 
632      OccursInSubsystem      OccursInSubsystem
633      ParticipatesIn      ParticipatesIn
634      HasSSCell      HasSSCell
     Catalyzes  
     Reaction  
635      ConsistsOfRoles      ConsistsOfRoles
636      RoleSubset      RoleSubset
637      HasRoleSubset      HasRoleSubset
638      ConsistsOfGenomes      ConsistsOfGenomes
639      GenomeSubset      GenomeSubset
640      HasGenomeSubset      HasGenomeSubset
641        Catalyzes
642        Diagram
643        RoleOccursIn
644    
645  =over 4  =over 4
646    
# Line 638  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 $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadSubsystem = $self->_TableLoader('Subsystem');
672      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
673      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
674      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
675      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
676      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
677      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
678      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
679      my $loadReaction = $self->_TableLoader('Reaction', $featureCount * $genomeCount);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
680      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $featureCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
681      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
682      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
683      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
684      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
685      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
686      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
687      Trace("Beginning subsystem data load.") if T(2);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
688      # The reaction hash will contain a list of reactions for each role. When we're done,      if ($self->{options}->{loadOnly}) {
689      # a complicated sort and merge will be used to generate the Reaction and Catalyzes          Trace("Loading from existing files.") if T(2);
690      # tables.      } else {
691      my %reactionsToRoles = ();          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
# Line 673  Line 700 
700      my ($genomeID, $roleID);      my ($genomeID, $roleID);
701      my %roleData = ();      my %roleData = ();
702      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
703          # Get the subsystem object.          # Get the subsystem object.
704          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
705          # Get its reaction hash.              # Only proceed if the subsystem has a spreadsheet.
706          my $reactionHash = $sub->get_reactions();              if (! $sub->{empty_ss}) {
707                    Trace("Creating subsystem $subsysID.") if T(3);
708                    $loadSubsystem->Add("subsystemIn");
709          # Create the subsystem record.          # Create the subsystem record.
710          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
711          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
# Line 697  Line 724 
724                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
725                  # Check for an EC number.                  # Check for an EC number.
726                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
727                      $loadRoleEC->Put($roleID, $1);                              my $ec = $1;
728                  }                              $loadRoleEC->Put($roleID, $ec);
729                  # Add the role's reactions.                              $ecToRoles{$ec} = $roleID;
                 my $reactions = $reactionHash->{$roleID};  
                 for my $reactionID (@{$reactions}) {  
                     if (! exists $reactionsToRoles{$reactionID}) {  
                         # Here the reaction is brand-new, so we create its reaction  
                         # record.  
                         $loadReaction->Put($reactionID, $fig->reversible($reactionID));  
                         # We also create a blank list for it in the reaction hash.  
                         $reactionsToRoles{$reactionID} = [];  
                     }  
                     # Add the role to the reaction's role list.  
                     push @{$reactionsToRoles{$reactionID}}, $roleID;  
730                  }                  }
731              }              }
732          }          }
# Line 790  Line 806 
806              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
807              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
808              # Connect the subset to its roles.              # Connect the subset to its roles.
809              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
810              for my $roleID (@roles) {              for my $roleID (@roles) {
811                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
812              }              }
# Line 810  Line 826 
826              }              }
827          }          }
828      }      }
829      # Before we leave, we must create the Catalyzes table. The data is all stored in              # Now we loop through the diagrams. We need to create the diagram records
830      # "reactionToRoles" hash.              # and link each diagram to its roles. Note that only roles which occur
831      for my $reactionID (keys %reactionsToRoles) {              # in subsystems (and therefore appear in the %ecToRoles hash) are
832          # Get this reaction's list of roles. We sort it so we can merge out duplicates.              # included.
833          my @roles = sort @{$reactionsToRoles{$reactionID}};              for my $map (@maps) {
         my $lastRole = "";  
         # Loop through the roles, creating catalyzation records.  
         for my $thisRole (@roles) {  
             if ($thisRole ne $lastRole) {  
                 $loadCatalyzes->Put($thisRole, $reactionID);  
             }  
         }  
     }  
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
 =head3 LoadDiagramData  
   
 C<< my $stats = $spl->LoadDiagramData(); >>  
   
 Load the diagram data from FIG into Sprout.  
   
 Diagrams are used to organize functional roles. The diagram shows the  
 connections between chemicals that interact with a subsystem.  
   
 The following relations are loaded by this method.  
   
     Diagram  
     RoleOccursIn  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =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 876  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 923  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 967  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 1007  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 1035  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 1089  Line 1067 
1067              }              }
1068          }          }
1069      }      }
1070        }
1071      # Finish the load.      # Finish the load.
1072      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1073      return $retVal;      return $retVal;
# Line 1129  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 1164  Line 1145 
1145      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1146          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($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 1203  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 1240  Line 1224 
1224              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1225          }          }
1226      }      }
1227        }
1228      # Finish the load.      # Finish the load.
1229      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1230      return $retVal;      return $retVal;
# Line 1256  Line 1241 
1241    
1242  The following relations are loaded by this method.  The following relations are loaded by this method.
1243    
1244        Reaction
1245      ReactionURL      ReactionURL
1246      Compound      Compound
1247      CompoundName      CompoundName
# Line 1279  Line 1265 
1265      my ($self) = @_;      my ($self) = @_;
1266      # Get the FIG object.      # Get the FIG object.
1267      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1268      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1269      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1270      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1271      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1272      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1273      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1274      Trace("Beginning reaction/compound data load.") if T(2);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1275      # Create a hash to remember the compounds we've generated in the compound table.      if ($self->{options}->{loadOnly}) {
1276      my %compoundHash = ();          Trace("Loading from existing files.") if T(2);
1277      # Loop through the reactions.      } 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();      my @reactions = $fig->all_reactions();
1304      for my $reactionID (@reactions) {      for my $reactionID (@reactions) {
1305                # Create the reaction record.
1306                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1307          # Compute the reaction's URL.          # Compute the reaction's URL.
1308          my $url = HTML::reaction_link($reactionID);          my $url = HTML::reaction_link($reactionID);
1309          # Put it in the ReactionURL table.          # Put it in the ReactionURL table.
# Line 1302  Line 1312 
1312          # substrates first and then products.          # substrates first and then products.
1313          for my $product (0, 1) {          for my $product (0, 1) {
1314              # Get the compounds of the current type for the current reaction. FIG will              # Get the compounds of the current type for the current reaction. FIG will
1315              # give us 3-tuples: [ID, Stoichometry, main-flag]. At this time we do not                  # 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.              # have location data in SEED, so it defaults to the empty string.
1317              my @compounds = $fig->reaction2comp($reactionID, $product);              my @compounds = $fig->reaction2comp($reactionID, $product);
1318              for my $compData (@compounds) {              for my $compData (@compounds) {
1319                  # Extract the compound data from the current tuple.                  # Extract the compound data from the current tuple.
1320                  my ($cid, $stoich, $main) = @{$compData};                  my ($cid, $stoich, $main) = @{$compData};
1321                  # Link the compound to the reaction.                  # Link the compound to the reaction.
1322                  $loadIsAComponentOf->Put($cid, $reactionID, "", $main, $product, $stoich);                      $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1323                  # If this is a new compound, we need to create its table entries.                                               $product, $stoich);
                 if (! exists $compoundHash{$cid}) {  
                     $compoundHash{$cid} = 1;  
                     # Create the main compound record and denote we've done it.  
                     $loadCompound->Put($cid);  
                     # Check for a CAS ID.  
                     my $cas = $fig->cas($cid);  
                     if ($cas) {  
                         $loadCompoundCAS->Put($cid, $cas);  
                     }  
                     # Check for names.  
                     my @names = $fig->names_of_compound($cid);  
                     # Each name will be given a priority number, starting with 1.  
                     my $prio = 0;  
                     for my $name (@names) {  
                         $loadCompoundName->Put($cid, $name, $prio++);  
                     }  
1324                  }                  }
1325              }              }
1326          }          }
# Line 1366  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 1385  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 $retVal;
# Line 1406  Line 1403 
1403    
1404  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1405    
1406  =item rowCount (optional)  =item ignore
1407    
1408  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1409    
1410  =item RETURN  =item RETURN
1411    
# Line 1420  Line 1417 
1417    
1418  sub _TableLoader {  sub _TableLoader {
1419      # Get the parameters.      # Get the parameters.
1420      my ($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 1459  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          # Trace the fact that we're cleaning up.          # Get the relation name.
1461          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1462          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1463            if ($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}) {          if ($self->{options}->{dbLoad}) {
1470              # Here we want to use the load file just created to load the database.              # Here we want to use the load file just created to load the database.
# Line 1473  Line 1476 
1476          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
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.1.19  
changed lines
  Added in v.1.32

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3