[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 1.29, Mon Mar 13 19:19:37 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 $retVal;
# Line 426  Line 451 
451      my ($self) = @_;      my ($self) = @_;
452      # Get the FIG object.      # Get the FIG object.
453      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
454      # Get the table of genome IDs.      # Get the table of genome IDs.
455      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
456      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
457      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
458      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
459      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
460      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
461      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
462          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
         $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);  
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
463      # 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
464      # locations.      # locations.
465      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
466      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
467            Trace("Loading from existing files.") if T(2);
468        } else {
469            Trace("Generating feature data.") if T(2);
470      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
471      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
472          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 463  Line 484 
484              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
485                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
486              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
487                  # Get the links.                  # Get the links.
488                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
489                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 502 
502                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
503                      }                      }
504                  }                  }
             }  
505              # 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
506              # 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
507              # 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 530 
530              }              }
531          }          }
532      }      }
533        }
534      # Finish the loads.      # Finish the loads.
535      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
536      return $retVal;      return $retVal;
# Line 548  Line 567 
567      my $fig = $self->{fig};      my $fig = $self->{fig};
568      # Get the table of genome IDs.      # Get the table of genome IDs.
569      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
570      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
571      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
572                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
573      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
574        } else {
575            Trace("Generating BBH data.") if T(2);
576      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
577      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
578          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 579  Line 598 
598              }              }
599          }          }
600      }      }
601        }
602      # Finish the loads.      # Finish the loads.
603      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
604      return $retVal;      return $retVal;
# Line 608  Line 628 
628      OccursInSubsystem      OccursInSubsystem
629      ParticipatesIn      ParticipatesIn
630      HasSSCell      HasSSCell
     Catalyzes  
     Reaction  
631      ConsistsOfRoles      ConsistsOfRoles
632      RoleSubset      RoleSubset
633      HasRoleSubset      HasRoleSubset
634      ConsistsOfGenomes      ConsistsOfGenomes
635      GenomeSubset      GenomeSubset
636      HasGenomeSubset      HasGenomeSubset
637        Catalyzes
638        Diagram
639        RoleOccursIn
640    
641  =over 4  =over 4
642    
# Line 638  Line 659 
659      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
660      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
661      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
662      my $subsysCount = @subsysIDs;      # Get the map list.
663      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
664      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
665      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
666      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
667      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadSubsystem = $self->_TableLoader('Subsystem');
668      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
669      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
670      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
671      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
672      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
673      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
674      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
675      my $loadReaction = $self->_TableLoader('Reaction', $featureCount * $genomeCount);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
676      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $featureCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
677      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
678      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
679      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
680      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
681      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
682      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
683      Trace("Beginning subsystem data load.") if T(2);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
684      # The reaction hash will contain a list of reactions for each role. When we're done,      if ($self->{options}->{loadOnly}) {
685      # a complicated sort and merge will be used to generate the Reaction and Catalyzes          Trace("Loading from existing files.") if T(2);
686      # tables.      } else {
687      my %reactionsToRoles = ();          Trace("Generating subsystem data.") if T(2);
688            # This hash will contain the role for each EC. When we're done, this
689            # information will be used to generate the Catalyzes table.
690            my %ecToRoles = ();
691      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
692      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
693      # 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 677  Line 700 
700          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
701          # Get the subsystem object.          # Get the subsystem object.
702          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
         # Get its reaction hash.  
         my $reactionHash = $sub->get_reactions();  
703          # Create the subsystem record.          # Create the subsystem record.
704          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
705          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
# Line 697  Line 718 
718                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
719                  # Check for an EC number.                  # Check for an EC number.
720                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
721                      $loadRoleEC->Put($roleID, $1);                          my $ec = $1;
722                  }                          $loadRoleEC->Put($roleID, $ec);
723                  # 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;  
724                  }                  }
725              }              }
726          }          }
# Line 790  Line 800 
800              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
801              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
802              # Connect the subset to its roles.              # Connect the subset to its roles.
803              my @roles = $sub->get_subset($subsetID);                  my @roles = $sub->get_subsetC_roles($subsetID);
804              for my $roleID (@roles) {              for my $roleID (@roles) {
805                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
806              }              }
# Line 810  Line 820 
820              }              }
821          }          }
822      }      }
823      # 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
824      # "reactionToRoles" hash.          # and link each diagram to its roles. Note that only roles which occur
825      for my $reactionID (keys %reactionsToRoles) {          # in subsystems (and therefore appear in the %ecToRoles hash) are
826          # Get this reaction's list of roles. We sort it so we can merge out duplicates.          # included.
827          my @roles = sort @{$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) {  
828          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
829          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
830          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 876  Line 833 
833          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
834          my %roleHash = ();          my %roleHash = ();
835          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
836              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
837                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
838                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
839              }              }
840          }          }
841      }      }
842            # Before we leave, we must create the Catalyzes table. We start with the reactions,
843            # then use the "ecToRoles" table to convert EC numbers to role IDs.
844            my @reactions = $fig->all_reactions();
845            for my $reactionID (@reactions) {
846                # Get this reaction's list of roles. The results will be EC numbers.
847                my @roles = $fig->catalyzed_by($reactionID);
848                # Loop through the roles, creating catalyzation records.
849                for my $thisRole (@roles) {
850                    if (exists $ecToRoles{$thisRole}) {
851                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
852                    }
853                }
854            }
855        }
856      # Finish the load.      # Finish the load.
857      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
858      return $retVal;      return $retVal;
# Line 923  Line 894 
894      my $fig = $self->{fig};      my $fig = $self->{fig};
895      # Get the genome hash.      # Get the genome hash.
896      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
897      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
898      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
899      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
900      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
901            Trace("Loading from existing files.") if T(2);
902        } else {
903            Trace("Generating property data.") if T(2);
904      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
905      my %propertyKeys = ();      my %propertyKeys = ();
906      my $nextID = 1;      my $nextID = 1;
907      # Loop through the genomes.      # Loop through the genomes.
908      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
909          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
910                Trace("Generating properties for $genomeID.") if T(3);
911          # 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
912          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
913          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
914          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
915                my $featureCount = 0;
916                my $propertyCount = 0;
917          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
918          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
919              # 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
920              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
921              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
922                    if (scalar @attributeList) {
923                        $featureCount++;
924                    }
925              # Loop through the attributes.              # Loop through the attributes.
926              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
927                        $propertyCount++;
928                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
929                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
930                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 967  Line 946 
946                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
947              }              }
948          }          }
949                # Update the statistics.
950                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
951                $loadHasProperty->Add("featuresIn", $featureCount);
952                $loadHasProperty->Add("propertiesIn", $propertyCount);
953            }
954      }      }
955      # Finish the load.      # Finish the load.
956      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1007  Line 991 
991      my $fig = $self->{fig};      my $fig = $self->{fig};
992      # Get the genome hash.      # Get the genome hash.
993      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
994      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
995      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
996      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
997      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
998      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
999      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1000      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1001            Trace("Loading from existing files.") if T(2);
1002        } else {
1003            Trace("Generating annotation data.") if T(2);
1004      # 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
1005      # user records.      # user records.
1006      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 1035  Line 1021 
1021              # 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
1022              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1023              my %seenTimestamps = ();              my %seenTimestamps = ();
1024              # 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.  
1025              for my $tuple ($fig->feature_annotations($peg, "raw")) {              for my $tuple ($fig->feature_annotations($peg, "raw")) {
1026                  my ($fid, $timestamp, $user, $text) = @{$tuple};                  my ($fid, $timestamp, $user, $text) = @{$tuple};
1027                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
# Line 1089  Line 1060 
1060              }              }
1061          }          }
1062      }      }
1063        }
1064      # Finish the load.      # Finish the load.
1065      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1066      return $retVal;      return $retVal;
# Line 1129  Line 1101 
1101      my $fig = $self->{fig};      my $fig = $self->{fig};
1102      # Get the genome hash.      # Get the genome hash.
1103      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1104      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1105      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1106      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1107      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1108      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1109            Trace("Loading from existing files.") if T(2);
1110        } else {
1111            Trace("Generating annotation data.") if T(2);
1112      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1113      my %sourceURL = ();      my %sourceURL = ();
1114      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1164  Line 1138 
1138      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1139          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1140      }      }
1141        }
1142      # Finish the load.      # Finish the load.
1143      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1144      return $retVal;      return $retVal;
# Line 1203  Line 1178 
1178      my $fig = $self->{fig};      my $fig = $self->{fig};
1179      # Get the genome hash.      # Get the genome hash.
1180      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1181      # 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
1182      # it the key.      # it the key.
1183      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1184      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1185      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1186      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1187      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1188            Trace("Loading from existing files.") if T(2);
1189        } else {
1190            Trace("Generating external data.") if T(2);
1191      # 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.
1192      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1193      my $orgLine;      my $orgLine;
# Line 1240  Line 1217 
1217              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1218          }          }
1219      }      }
1220        }
1221      # Finish the load.      # Finish the load.
1222      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1223      return $retVal;      return $retVal;
# Line 1256  Line 1234 
1234    
1235  The following relations are loaded by this method.  The following relations are loaded by this method.
1236    
1237        Reaction
1238      ReactionURL      ReactionURL
1239      Compound      Compound
1240      CompoundName      CompoundName
# Line 1279  Line 1258 
1258      my ($self) = @_;      my ($self) = @_;
1259      # Get the FIG object.      # Get the FIG object.
1260      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1261      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1262      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1263      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1264      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1265      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1266      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1267      Trace("Beginning reaction/compound data load.") if T(2);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1268      # Create a hash to remember the compounds we've generated in the compound table.      if ($self->{options}->{loadOnly}) {
1269      my %compoundHash = ();          Trace("Loading from existing files.") if T(2);
1270      # Loop through the reactions.      } else {
1271            Trace("Generating annotation data.") if T(2);
1272            # First we create the compounds.
1273            my @compounds = $fig->all_compounds();
1274            for my $cid (@compounds) {
1275                # Check for names.
1276                my @names = $fig->names_of_compound($cid);
1277                # Each name will be given a priority number, starting with 1.
1278                my $prio = 1;
1279                for my $name (@names) {
1280                    $loadCompoundName->Put($cid, $name, $prio++);
1281                }
1282                # Create the main compound record. Note that the first name
1283                # becomes the label.
1284                my $label = (@names > 0 ? $names[0] : $cid);
1285                $loadCompound->Put($cid, $label);
1286                # Check for a CAS ID.
1287                my $cas = $fig->cas($cid);
1288                if ($cas) {
1289                    $loadCompoundCAS->Put($cid, $cas);
1290                }
1291            }
1292            # All the compounds are set up, so we need to loop through the reactions next. First,
1293            # we initialize the discriminator index. This is a single integer used to insure
1294            # duplicate elements in a reaction are not accidentally collapsed.
1295            my $discrim = 0;
1296      my @reactions = $fig->all_reactions();      my @reactions = $fig->all_reactions();
1297      for my $reactionID (@reactions) {      for my $reactionID (@reactions) {
1298                # Create the reaction record.
1299                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1300          # Compute the reaction's URL.          # Compute the reaction's URL.
1301          my $url = HTML::reaction_link($reactionID);          my $url = HTML::reaction_link($reactionID);
1302          # Put it in the ReactionURL table.          # Put it in the ReactionURL table.
# Line 1302  Line 1305 
1305          # substrates first and then products.          # substrates first and then products.
1306          for my $product (0, 1) {          for my $product (0, 1) {
1307              # 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
1308              # 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
1309              # have location data in SEED, so it defaults to the empty string.              # have location data in SEED, so it defaults to the empty string.
1310              my @compounds = $fig->reaction2comp($reactionID, $product);              my @compounds = $fig->reaction2comp($reactionID, $product);
1311              for my $compData (@compounds) {              for my $compData (@compounds) {
1312                  # Extract the compound data from the current tuple.                  # Extract the compound data from the current tuple.
1313                  my ($cid, $stoich, $main) = @{$compData};                  my ($cid, $stoich, $main) = @{$compData};
1314                  # Link the compound to the reaction.                  # Link the compound to the reaction.
1315                  $loadIsAComponentOf->Put($cid, $reactionID, "", $main, $product, $stoich);                      $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1316                  # 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++);  
                     }  
1317                  }                  }
1318              }              }
1319          }          }
# Line 1366  Line 1353 
1353      my $fig = $self->{fig};      my $fig = $self->{fig};
1354      # Get the genome hash.      # Get the genome hash.
1355      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1356      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1357      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1358      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1359            Trace("Loading from existing files.") if T(2);
1360        } else {
1361            Trace("Generating group data.") if T(2);
1362      # Loop through the genomes.      # Loop through the genomes.
1363      my $line;      my $line;
1364      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1385  Line 1374 
1374          }          }
1375          close TMP;          close TMP;
1376      }      }
1377        }
1378      # Finish the load.      # Finish the load.
1379      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1380      return $retVal;      return $retVal;
# Line 1406  Line 1396 
1396    
1397  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1398    
1399  =item rowCount (optional)  =item ignore
1400    
1401  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1402    
1403  =item RETURN  =item RETURN
1404    
# Line 1420  Line 1410 
1410    
1411  sub _TableLoader {  sub _TableLoader {
1412      # Get the parameters.      # Get the parameters.
1413      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1414      # Create the load object.      # Create the load object.
1415      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1416                                   $ignore);
1417      # Cache it in the loader list.      # Cache it in the loader list.
1418      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1419      # Return it to the caller.      # Return it to the caller.
# Line 1459  Line 1450 
1450      # 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
1451      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads restartable.
1452      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1453          # Trace the fact that we're cleaning up.          # Get the relation name.
1454          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1455          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1456            if ($loader->Ignore) {
1457                Trace("Relation $relName not loaded.") if T(2);
1458            } else {
1459                # Here we really need to finish.
1460                Trace("Finishing $relName.") if T(2);
1461          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1462          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1463              # 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 1469 
1469          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
1470          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1471      }      }
1472        }
1473      # Return the load statistics.      # Return the load statistics.
1474      return $retVal;      return $retVal;
1475  }  }

Legend:
Removed from v.1.19  
changed lines
  Added in v.1.29

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3