[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 1.34, Sat May 13 04:13:24 2006 UTC
# Line 80  Line 80 
80  =item subsysFile  =item subsysFile
81    
82  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
83  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
84  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
85    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
86    
87  =item options  =item options
88    
# Line 132  Line 133 
133      # Load the list of trusted subsystems.      # Load the list of trusted subsystems.
134      my %subsystems = ();      my %subsystems = ();
135      if (! defined $subsysFile || $subsysFile eq '') {      if (! defined $subsysFile || $subsysFile eq '') {
136          # Here we want all the subsystems.          # Here we want all the NMPDR subsystems. First we get the whole list.
137          %subsystems = map { $_ => 1 } $fig->all_subsystems();          my @subs = $fig->all_subsystems();
138            # Loop through, checking for the NMPDR file.
139            for my $sub (@subs) {
140                if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {
141                    $subsystems{$sub} = 1;
142                }
143            }
144      } else {      } else {
145          my $type = ref $subsysFile;          my $type = ref $subsysFile;
146          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 171  Line 178 
178      return $retVal;      return $retVal;
179  }  }
180    
181    =head3 LoadOnly
182    
183    C<< my $flag = $spl->LoadOnly; >>
184    
185    Return TRUE if we are in load-only mode, else FALSE.
186    
187    =cut
188    
189    sub LoadOnly {
190        my ($self) = @_;
191        return $self->{options}->{loadOnly};
192    }
193    
194    =head3 PrimaryOnly
195    
196    C<< my $flag = $spl->PrimaryOnly; >>
197    
198    Return TRUE if only the main entity is to be loaded, else FALSE.
199    
200    =cut
201    
202    sub PrimaryOnly {
203        my ($self) = @_;
204        return $self->{options}->{primaryOnly};
205    }
206    
207  =head3 LoadGenomeData  =head3 LoadGenomeData
208    
209  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 198  Line 231 
231    
232  =back  =back
233    
 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.)  
   
234  =cut  =cut
235  #: Return Type $%;  #: Return Type $%;
236  sub LoadGenomeData {  sub LoadGenomeData {
# Line 216  Line 241 
241      # Get the genome count.      # Get the genome count.
242      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
243      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
244      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
245      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
246      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
247      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
248      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
249      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
250        if ($self->{options}->{loadOnly}) {
251            Trace("Loading from existing files.") if T(2);
252        } else {
253            Trace("Generating genome data.") if T(2);
254      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
255      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
256          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
257          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
258          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
259          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
260          # 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.  
261          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
262          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
263          # Get the full taxonomy.          # Get the full taxonomy.
264          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
265          # Output the genome record.          # Output the genome record.
# Line 268  Line 295 
295              }              }
296          }          }
297      }      }
298        }
299      # Finish the loads.      # Finish the loads.
300      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
301      # Return the result.      # Return the result.
# Line 311  Line 339 
339      my $genomeCount = (keys %{$genomeFilter});      my $genomeCount = (keys %{$genomeFilter});
340      my $featureCount = $genomeCount * 4000;      my $featureCount = $genomeCount * 4000;
341      # Start the loads.      # Start the loads.
342      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
343      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
344      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
345      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
346      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
347      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
348            Trace("Loading from existing files.") if T(2);
349        } else {
350            Trace("Generating coupling data.") if T(2);
351      # Loop through the genomes found.      # Loop through the genomes found.
352      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
353          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 389  Line 420 
420              }              }
421          }          }
422      }      }
423        }
424      # All done. Finish the load.      # All done. Finish the load.
425      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
426      return $retVal;      return $retVal;
# Line 410  Line 442 
442      FeatureTranslation      FeatureTranslation
443      FeatureUpstream      FeatureUpstream
444      IsLocatedIn      IsLocatedIn
445        HasFeature
446    
447  =over 4  =over 4
448    
# Line 426  Line 459 
459      my ($self) = @_;      my ($self) = @_;
460      # Get the FIG object.      # Get the FIG object.
461      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
462      # Get the table of genome IDs.      # Get the table of genome IDs.
463      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
464      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
465      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
466      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
467      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
468      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
469      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
470          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
471          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature');
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
472      # 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
473      # locations.      # locations.
474      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
475      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
476            Trace("Loading from existing files.") if T(2);
477        } else {
478            Trace("Generating feature data.") if T(2);
479      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
480      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
481          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 459  Line 489 
489              my ($featureID, $locations, undef, $type) = @{$featureData};              my ($featureID, $locations, undef, $type) = @{$featureData};
490              # Create the feature record.              # Create the feature record.
491              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
492                    # Link it to the parent genome.
493                    $loadHasFeature->Put($genomeID, $featureID, $type);
494              # Create the aliases.              # Create the aliases.
495              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
496                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
497              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
498                  # Get the links.                  # Get the links.
499                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
500                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 513 
513                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
514                      }                      }
515                  }                  }
             }  
516              # 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
517              # 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
518              # 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 541 
541              }              }
542          }          }
543      }      }
544        }
545      # Finish the loads.      # Finish the loads.
546      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
547      return $retVal;      return $retVal;
# Line 548  Line 578 
578      my $fig = $self->{fig};      my $fig = $self->{fig};
579      # Get the table of genome IDs.      # Get the table of genome IDs.
580      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
581      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
582      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
583                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
584      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
585        } else {
586            Trace("Generating BBH data.") if T(2);
587      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
588      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
589          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 579  Line 609 
609              }              }
610          }          }
611      }      }
612        }
613      # Finish the loads.      # Finish the loads.
614      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
615      return $retVal;      return $retVal;
# Line 608  Line 639 
639      OccursInSubsystem      OccursInSubsystem
640      ParticipatesIn      ParticipatesIn
641      HasSSCell      HasSSCell
     Catalyzes  
     Reaction  
642      ConsistsOfRoles      ConsistsOfRoles
643      RoleSubset      RoleSubset
644      HasRoleSubset      HasRoleSubset
645      ConsistsOfGenomes      ConsistsOfGenomes
646      GenomeSubset      GenomeSubset
647      HasGenomeSubset      HasGenomeSubset
648        Catalyzes
649        Diagram
650        RoleOccursIn
651    
652  =over 4  =over 4
653    
# Line 638  Line 670 
670      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
671      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
672      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
673      my $subsysCount = @subsysIDs;      # Get the map list.
674      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
675      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
676      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
677      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
678      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadSubsystem = $self->_TableLoader('Subsystem');
679      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
680      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
681      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
682      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
683      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
684      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
685      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
686      my $loadReaction = $self->_TableLoader('Reaction', $featureCount * $genomeCount);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
687      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $featureCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
688      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
689      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
690      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
691      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
692      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
693      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
694      Trace("Beginning subsystem data load.") if T(2);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
695      # The reaction hash will contain a list of reactions for each role. When we're done,      if ($self->{options}->{loadOnly}) {
696      # a complicated sort and merge will be used to generate the Reaction and Catalyzes          Trace("Loading from existing files.") if T(2);
697      # tables.      } else {
698      my %reactionsToRoles = ();          Trace("Generating subsystem data.") if T(2);
699            # This hash will contain the role for each EC. When we're done, this
700            # information will be used to generate the Catalyzes table.
701            my %ecToRoles = ();
702      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
703      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
704      # 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 707 
707      my ($genomeID, $roleID);      my ($genomeID, $roleID);
708      my %roleData = ();      my %roleData = ();
709      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
710          # Get the subsystem object.          # Get the subsystem object.
711          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
712          # Get its reaction hash.              # Only proceed if the subsystem has a spreadsheet.
713          my $reactionHash = $sub->get_reactions();              if (! $sub->{empty_ss}) {
714                    Trace("Creating subsystem $subsysID.") if T(3);
715                    $loadSubsystem->Add("subsystemIn");
716          # Create the subsystem record.          # Create the subsystem record.
717          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
718          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
# Line 697  Line 731 
731                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
732                  # Check for an EC number.                  # Check for an EC number.
733                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
734                      $loadRoleEC->Put($roleID, $1);                              my $ec = $1;
735                  }                              $loadRoleEC->Put($roleID, $ec);
736                  # 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;  
737                  }                  }
738              }              }
739          }          }
# Line 790  Line 813 
813              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
814              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
815              # Connect the subset to its roles.              # Connect the subset to its roles.
816              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
817              for my $roleID (@roles) {              for my $roleID (@roles) {
818                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
819              }              }
# Line 810  Line 833 
833              }              }
834          }          }
835      }      }
836      # 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
837      # "reactionToRoles" hash.              # and link each diagram to its roles. Note that only roles which occur
838      for my $reactionID (keys %reactionsToRoles) {              # in subsystems (and therefore appear in the %ecToRoles hash) are
839          # Get this reaction's list of roles. We sort it so we can merge out duplicates.              # included.
840          my @roles = sort @{$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) {  
841          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
842          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
843          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 876  Line 846 
846          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
847          my %roleHash = ();          my %roleHash = ();
848          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
849              if (! $roleHash{$role}) {                      if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
850                  $loadRoleOccursIn->Put($role, $map);                          $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
851                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
852              }              }
853          }          }
854      }      }
855                # Before we leave, we must create the Catalyzes table. We start with the reactions,
856                # then use the "ecToRoles" table to convert EC numbers to role IDs.
857                my @reactions = $fig->all_reactions();
858                for my $reactionID (@reactions) {
859                    # Get this reaction's list of roles. The results will be EC numbers.
860                    my @roles = $fig->catalyzed_by($reactionID);
861                    # Loop through the roles, creating catalyzation records.
862                    for my $thisRole (@roles) {
863                        if (exists $ecToRoles{$thisRole}) {
864                            $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
865                        }
866                    }
867                }
868            }
869        }
870      # Finish the load.      # Finish the load.
871      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
872      return $retVal;      return $retVal;
# Line 923  Line 908 
908      my $fig = $self->{fig};      my $fig = $self->{fig};
909      # Get the genome hash.      # Get the genome hash.
910      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
911      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
912      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
913      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
914      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
915            Trace("Loading from existing files.") if T(2);
916        } else {
917            Trace("Generating property data.") if T(2);
918      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
919      my %propertyKeys = ();      my %propertyKeys = ();
920      my $nextID = 1;      my $nextID = 1;
921      # Loop through the genomes.      # Loop through the genomes.
922      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
923          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
924                Trace("Generating properties for $genomeID.") if T(3);
925          # 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
926          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
927          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
928          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
929                my $featureCount = 0;
930                my $propertyCount = 0;
931          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
932          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
933              # 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
934              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
935              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
936                    if (scalar @attributeList) {
937                        $featureCount++;
938                    }
939              # Loop through the attributes.              # Loop through the attributes.
940              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
941                        $propertyCount++;
942                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
943                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
944                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 967  Line 960 
960                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
961              }              }
962          }          }
963                # Update the statistics.
964                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
965                $loadHasProperty->Add("featuresIn", $featureCount);
966                $loadHasProperty->Add("propertiesIn", $propertyCount);
967            }
968      }      }
969      # Finish the load.      # Finish the load.
970      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1007  Line 1005 
1005      my $fig = $self->{fig};      my $fig = $self->{fig};
1006      # Get the genome hash.      # Get the genome hash.
1007      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1008      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1009      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1010      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1011      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1012      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1013      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1014      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1015            Trace("Loading from existing files.") if T(2);
1016        } else {
1017            Trace("Generating annotation data.") if T(2);
1018      # 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
1019      # user records.      # user records.
1020      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 1035  Line 1035 
1035              # 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
1036              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1037              my %seenTimestamps = ();              my %seenTimestamps = ();
1038              # 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.  
1039              for my $tuple ($fig->feature_annotations($peg, "raw")) {              for my $tuple ($fig->feature_annotations($peg, "raw")) {
1040                  my ($fid, $timestamp, $user, $text) = @{$tuple};                  my ($fid, $timestamp, $user, $text) = @{$tuple};
1041                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
# Line 1089  Line 1074 
1074              }              }
1075          }          }
1076      }      }
1077        }
1078      # Finish the load.      # Finish the load.
1079      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1080      return $retVal;      return $retVal;
# Line 1129  Line 1115 
1115      my $fig = $self->{fig};      my $fig = $self->{fig};
1116      # Get the genome hash.      # Get the genome hash.
1117      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1118      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1119      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1120      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1121      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1122      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1123            Trace("Loading from existing files.") if T(2);
1124        } else {
1125            Trace("Generating annotation data.") if T(2);
1126      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1127      my %sourceURL = ();      my %sourceURL = ();
1128      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1164  Line 1152 
1152      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1153          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1154      }      }
1155        }
1156      # Finish the load.      # Finish the load.
1157      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1158      return $retVal;      return $retVal;
# Line 1203  Line 1192 
1192      my $fig = $self->{fig};      my $fig = $self->{fig};
1193      # Get the genome hash.      # Get the genome hash.
1194      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1195      # 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
1196      # it the key.      # it the key.
1197      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1198      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1199      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1200      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1201      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1202            Trace("Loading from existing files.") if T(2);
1203        } else {
1204            Trace("Generating external data.") if T(2);
1205      # 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.
1206      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1207      my $orgLine;      my $orgLine;
# Line 1240  Line 1231 
1231              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1232          }          }
1233      }      }
1234        }
1235      # Finish the load.      # Finish the load.
1236      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1237      return $retVal;      return $retVal;
# Line 1256  Line 1248 
1248    
1249  The following relations are loaded by this method.  The following relations are loaded by this method.
1250    
1251        Reaction
1252      ReactionURL      ReactionURL
1253      Compound      Compound
1254      CompoundName      CompoundName
# Line 1279  Line 1272 
1272      my ($self) = @_;      my ($self) = @_;
1273      # Get the FIG object.      # Get the FIG object.
1274      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1275      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1276      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1277      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1278      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1279      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1280      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1281      Trace("Beginning reaction/compound data load.") if T(2);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1282      # Create a hash to remember the compounds we've generated in the compound table.      if ($self->{options}->{loadOnly}) {
1283      my %compoundHash = ();          Trace("Loading from existing files.") if T(2);
1284      # Loop through the reactions.      } else {
1285            Trace("Generating annotation data.") if T(2);
1286            # First we create the compounds.
1287            my @compounds = $fig->all_compounds();
1288            for my $cid (@compounds) {
1289                # Check for names.
1290                my @names = $fig->names_of_compound($cid);
1291                # Each name will be given a priority number, starting with 1.
1292                my $prio = 1;
1293                for my $name (@names) {
1294                    $loadCompoundName->Put($cid, $name, $prio++);
1295                }
1296                # Create the main compound record. Note that the first name
1297                # becomes the label.
1298                my $label = (@names > 0 ? $names[0] : $cid);
1299                $loadCompound->Put($cid, $label);
1300                # Check for a CAS ID.
1301                my $cas = $fig->cas($cid);
1302                if ($cas) {
1303                    $loadCompoundCAS->Put($cid, $cas);
1304                }
1305            }
1306            # All the compounds are set up, so we need to loop through the reactions next. First,
1307            # we initialize the discriminator index. This is a single integer used to insure
1308            # duplicate elements in a reaction are not accidentally collapsed.
1309            my $discrim = 0;
1310      my @reactions = $fig->all_reactions();      my @reactions = $fig->all_reactions();
1311      for my $reactionID (@reactions) {      for my $reactionID (@reactions) {
1312                # Create the reaction record.
1313                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1314          # Compute the reaction's URL.          # Compute the reaction's URL.
1315          my $url = HTML::reaction_link($reactionID);          my $url = HTML::reaction_link($reactionID);
1316          # Put it in the ReactionURL table.          # Put it in the ReactionURL table.
# Line 1302  Line 1319 
1319          # substrates first and then products.          # substrates first and then products.
1320          for my $product (0, 1) {          for my $product (0, 1) {
1321              # 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
1322              # 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
1323              # have location data in SEED, so it defaults to the empty string.              # have location data in SEED, so it defaults to the empty string.
1324              my @compounds = $fig->reaction2comp($reactionID, $product);              my @compounds = $fig->reaction2comp($reactionID, $product);
1325              for my $compData (@compounds) {              for my $compData (@compounds) {
1326                  # Extract the compound data from the current tuple.                  # Extract the compound data from the current tuple.
1327                  my ($cid, $stoich, $main) = @{$compData};                  my ($cid, $stoich, $main) = @{$compData};
1328                  # Link the compound to the reaction.                  # Link the compound to the reaction.
1329                  $loadIsAComponentOf->Put($cid, $reactionID, "", $main, $product, $stoich);                      $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1330                  # 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++);  
                     }  
1331                  }                  }
1332              }              }
1333          }          }
# Line 1366  Line 1367 
1367      my $fig = $self->{fig};      my $fig = $self->{fig};
1368      # Get the genome hash.      # Get the genome hash.
1369      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1370      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1371      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1372      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1373            Trace("Loading from existing files.") if T(2);
1374        } else {
1375            Trace("Generating group data.") if T(2);
1376      # Loop through the genomes.      # Loop through the genomes.
1377      my $line;      my $line;
1378      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1385  Line 1388 
1388          }          }
1389          close TMP;          close TMP;
1390      }      }
1391        }
1392      # Finish the load.      # Finish the load.
1393      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1394      return $retVal;      return $retVal;
# Line 1406  Line 1410 
1410    
1411  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1412    
1413  =item rowCount (optional)  =item ignore
1414    
1415  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1416    
1417  =item RETURN  =item RETURN
1418    
# Line 1420  Line 1424 
1424    
1425  sub _TableLoader {  sub _TableLoader {
1426      # Get the parameters.      # Get the parameters.
1427      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1428      # Create the load object.      # Create the load object.
1429      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1430                                   $ignore);
1431      # Cache it in the loader list.      # Cache it in the loader list.
1432      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1433      # Return it to the caller.      # Return it to the caller.
# Line 1459  Line 1464 
1464      # 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
1465      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads restartable.
1466      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1467          # Trace the fact that we're cleaning up.          # Get the relation name.
1468          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1469          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1470            if ($loader->Ignore) {
1471                Trace("Relation $relName not loaded.") if T(2);
1472            } else {
1473                # Here we really need to finish.
1474                Trace("Finishing $relName.") if T(2);
1475          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1476          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1477              # 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 1483 
1483          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
1484          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1485      }      }
1486        }
1487      # Return the load statistics.      # Return the load statistics.
1488      return $retVal;      return $retVal;
1489  }  }

Legend:
Removed from v.1.19  
changed lines
  Added in v.1.34

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3