[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 1.64, Sat Aug 12 08:43:37 2006 UTC
# Line 30  Line 30 
30      $stats->Accumulate($spl->LoadFeatureData());      $stats->Accumulate($spl->LoadFeatureData());
31      print $stats->Show();      print $stats->Show();
32    
 This module makes use of the internal Sprout property C<_erdb>.  
   
33  It is worth noting that the FIG object does not need to be a real one. Any object  It is worth noting that the FIG object does not need to be a real one. Any object
34  that implements the FIG methods for data retrieval could be used. So, for example,  that implements the FIG methods for data retrieval could be used. So, for example,
35  this object could be used to copy data from one Sprout database to another, or  this object could be used to copy data from one Sprout database to another, or
# Line 80  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  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
81  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
82  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>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85  =item options  =item options
86    
# Line 94  Line 93 
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
96      # Load the list of genomes into a hash.      # Create the genome hash.
97      my %genomes;      my %genomes = ();
98        # We only need it if load-only is NOT specified.
99        if (! $options->{loadOnly}) {
100      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
101          # Here we want all the complete genomes and an access code of 1.          # Here we want all the complete genomes and an access code of 1.
102          my @genomeList = $fig->genomes(1);          my @genomeList = $fig->genomes(1);
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");
131          }          }
132      }      }
133        }
134      # Load the list of trusted subsystems.      # Load the list of trusted subsystems.
135      my %subsystems = ();      my %subsystems = ();
136        # We only need it if load-only is NOT specified.
137        if (! $options->{loadOnly}) {
138      if (! defined $subsysFile || $subsysFile eq '') {      if (! defined $subsysFile || $subsysFile eq '') {
139          # Here we want all the subsystems.              # Here we want all the usable subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for usability.
142                for my $sub (@subs) {
143                    if ($fig->usable_subsystem($sub)) {
144                        $subsystems{$sub} = 1;
145                    }
146                }
147      } else {      } else {
148          my $type = ref $subsysFile;          my $type = ref $subsysFile;
149          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 153  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 162  Line 173 
173                    subsystems => \%subsystems,                    subsystems => \%subsystems,
174                    sprout => $sprout,                    sprout => $sprout,
175                    loadDirectory => $directory,                    loadDirectory => $directory,
176                    erdb => $sprout->{_erdb},                    erdb => $sprout,
177                    loaders => [],                    loaders => [],
178                    options => $options                    options => $options
179                   };                   };
# Line 171  Line 182 
182      return $retVal;      return $retVal;
183  }  }
184    
185    =head3 LoadOnly
186    
187    C<< my $flag = $spl->LoadOnly; >>
188    
189    Return TRUE if we are in load-only mode, else FALSE.
190    
191    =cut
192    
193    sub LoadOnly {
194        my ($self) = @_;
195        return $self->{options}->{loadOnly};
196    }
197    
198    =head3 PrimaryOnly
199    
200    C<< my $flag = $spl->PrimaryOnly; >>
201    
202    Return TRUE if only the main entity is to be loaded, else FALSE.
203    
204    =cut
205    
206    sub PrimaryOnly {
207        my ($self) = @_;
208        return $self->{options}->{primaryOnly};
209    }
210    
211  =head3 LoadGenomeData  =head3 LoadGenomeData
212    
213  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 198  Line 235 
235    
236  =back  =back
237    
 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.)  
   
238  =cut  =cut
239  #: Return Type $%;  #: Return Type $%;
240  sub LoadGenomeData {  sub LoadGenomeData {
# Line 216  Line 245 
245      # Get the genome count.      # Get the genome count.
246      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
247      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
248      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
249      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
250      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
251      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
252      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
253      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
254        if ($self->{options}->{loadOnly}) {
255            Trace("Loading from existing files.") if T(2);
256        } else {
257            Trace("Generating genome data.") if T(2);
258      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
259      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
260          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
261          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
262          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
263          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
264          # 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.  
265          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
266          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
267          # Get the full taxonomy.          # Get the full taxonomy.
268          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
269          # Output the genome record.          # Output the genome record.
# Line 268  Line 299 
299              }              }
300          }          }
301      }      }
302        }
303      # Finish the loads.      # Finish the loads.
304      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
305      # Return the result.      # Return the result.
# Line 308  Line 340 
340      my $fig = $self->{fig};      my $fig = $self->{fig};
341      # Get the genome hash.      # Get the genome hash.
342      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
343      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
344      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
345      # Start the loads.      # Start the loads.
346      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
347      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
348      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
349      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
350      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
351      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
352            Trace("Loading from existing files.") if T(2);
353        } else {
354            Trace("Generating coupling data.") if T(2);
355      # Loop through the genomes found.      # Loop through the genomes found.
356      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
357          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 340  Line 375 
375              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
376                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
377                  # Compute the coupling ID.                  # Compute the coupling ID.
378                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
379                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
380                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
381                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 376  Line 411 
411                          }                          }
412                      }                      }
413                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
414                                # Get the ID for this evidence.
415                                $pchID++;
416                          # Create the evidence record.                          # Create the evidence record.
417                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
418                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
419                          # Connect it to the coupling.                          # Connect it to the coupling.
420                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
421                          # Connect it to the features.                          # Connect it to the features.
422                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
423                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
424                            }
425                      }                      }
426                  }                  }
427              }              }
# Line 410  Line 448 
448      FeatureTranslation      FeatureTranslation
449      FeatureUpstream      FeatureUpstream
450      IsLocatedIn      IsLocatedIn
451        HasFeature
452    
453  =over 4  =over 4
454    
# Line 426  Line 465 
465      my ($self) = @_;      my ($self) = @_;
466      # Get the FIG object.      # Get the FIG object.
467      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Find out if this is a limited run.  
     my $limited = $self->{options}->{limitedFeatures};  
468      # Get the table of genome IDs.      # Get the table of genome IDs.
469      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
470      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
471      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
472      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
473      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
474      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
475      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
476          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
477          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature');
         $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);  
     }  
478      # 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
479      # locations.      # locations.
480      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
481      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
482            Trace("Loading from existing files.") if T(2);
483        } else {
484            Trace("Generating feature data.") if T(2);
485      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
486      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
487          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
488          $loadFeature->Add("genomeIn");          $loadFeature->Add("genomeIn");
489          # Get the feature list for this genome.          # Get the feature list for this genome.
490          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
491                # Sort and count the list.
492                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
493                my $count = scalar @featureTuples;
494                Trace("$count features found for genome $genomeID.") if T(3);
495                # Set up for our duplicate-feature check.
496                my $oldFeatureID = "";
497          # Loop through the features.          # Loop through the features.
498          for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
             $loadFeature->Add("featureIn");  
499              # Split the tuple.              # Split the tuple.
500              my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
501                    # Check for duplicates.
502                    if ($featureID eq $oldFeatureID) {
503                        Trace("Duplicate feature $featureID found.") if T(1);
504                    } else {
505                        $oldFeatureID = $featureID;
506                        # Count this feature.
507                        $loadFeature->Add("featureIn");
508              # Create the feature record.              # Create the feature record.
509              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
510                        # Link it to the parent genome.
511                        $loadHasFeature->Put($genomeID, $featureID, $type);
512              # Create the aliases.              # Create the aliases.
513              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
514                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
515              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
516                  # Get the links.                  # Get the links.
517                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
518                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 531 
531                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
532                      }                      }
533                  }                  }
             }  
534              # 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
535              # 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
536              # 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 559 
559              }              }
560          }          }
561      }      }
562            }
563        }
564      # Finish the loads.      # Finish the loads.
565      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
566      return $retVal;      return $retVal;
# Line 548  Line 597 
597      my $fig = $self->{fig};      my $fig = $self->{fig};
598      # Get the table of genome IDs.      # Get the table of genome IDs.
599      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
600      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
601      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
602                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
603      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
604        } else {
605            Trace("Generating BBH data.") if T(2);
606      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
607      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
608          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 579  Line 628 
628              }              }
629          }          }
630      }      }
631        }
632      # Finish the loads.      # Finish the loads.
633      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
634      return $retVal;      return $retVal;
# Line 599  Line 649 
649  The following relations are loaded by this method.  The following relations are loaded by this method.
650    
651      Subsystem      Subsystem
652        SubsystemClass
653      Role      Role
654      RoleEC      RoleEC
655      SSCell      SSCell
# Line 608  Line 659 
659      OccursInSubsystem      OccursInSubsystem
660      ParticipatesIn      ParticipatesIn
661      HasSSCell      HasSSCell
     Catalyzes  
     Reaction  
662      ConsistsOfRoles      ConsistsOfRoles
663      RoleSubset      RoleSubset
664      HasRoleSubset      HasRoleSubset
665      ConsistsOfGenomes      ConsistsOfGenomes
666      GenomeSubset      GenomeSubset
667      HasGenomeSubset      HasGenomeSubset
668        Catalyzes
669        Diagram
670        RoleOccursIn
671    
672  =over 4  =over 4
673    
# Line 638  Line 690 
690      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
691      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
692      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
693      my $subsysCount = @subsysIDs;      # Get the map list.
694      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
695      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
696      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
697      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
698      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadSubsystem = $self->_TableLoader('Subsystem');
699      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
700      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
701      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
702      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
703      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
704      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
705      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
706      my $loadReaction = $self->_TableLoader('Reaction', $featureCount * $genomeCount);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
707      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $featureCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
708      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
709      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
710      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
711      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
712      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
713      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
714      Trace("Beginning subsystem data load.") if T(2);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
715      # The reaction hash will contain a list of reactions for each role. When we're done,      my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
716      # a complicated sort and merge will be used to generate the Reaction and Catalyzes      if ($self->{options}->{loadOnly}) {
717      # tables.          Trace("Loading from existing files.") if T(2);
718      my %reactionsToRoles = ();      } else {
719            Trace("Generating subsystem data.") if T(2);
720            # This hash will contain the role for each EC. When we're done, this
721            # information will be used to generate the Catalyzes table.
722            my %ecToRoles = ();
723      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
724      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
725      # 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 728 
728      my ($genomeID, $roleID);      my ($genomeID, $roleID);
729      my %roleData = ();      my %roleData = ();
730      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
731          # Get the subsystem object.          # Get the subsystem object.
732          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
733          # Get its reaction hash.              # Only proceed if the subsystem has a spreadsheet.
734          my $reactionHash = $sub->get_reactions();              if (! $sub->{empty_ss}) {
735                    Trace("Creating subsystem $subsysID.") if T(3);
736                    $loadSubsystem->Add("subsystemIn");
737          # Create the subsystem record.          # Create the subsystem record.
738          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
739          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
740          $loadSubsystem->Put($subsysID, $curator, $notes);          $loadSubsystem->Put($subsysID, $curator, $notes);
741                    my $classList = $fig->subsystem_classification($subsysID);
742                    my @classes = @$classList;
743                    if (@classes) {
744                        for my $class (@classes) {
745                            $loadSubsystemClass->Put($subsysID, $class);
746                        }
747                    }
748          # Connect it to its roles. Each role is a column in the subsystem spreadsheet.          # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
749          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
750              # Connect to this role.              # Connect to this role.
# Line 697  Line 759 
759                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
760                  # Check for an EC number.                  # Check for an EC number.
761                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
762                      $loadRoleEC->Put($roleID, $1);                              my $ec = $1;
763                  }                              $loadRoleEC->Put($roleID, $ec);
764                  # 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;  
765                  }                  }
766              }              }
767          }          }
# Line 737  Line 788 
788                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
789                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
790                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
791                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
792                      # Only proceed if features exist.                      # Only proceed if features exist.
793                      if (@pegs > 0) {                      if (@pegs > 0) {
794                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 758  Line 809 
809                  if ($pegCount > 0) {                  if ($pegCount > 0) {
810                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
811                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                     # Partition the PEGs found into clusters.  
                     my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
812                      # Create a hash mapping PEG IDs to cluster numbers.                      # Create a hash mapping PEG IDs to cluster numbers.
813                      # We default to -1 for all of them.                      # We default to -1 for all of them.
814                      my %clusterOf = map { $_ => -1 } @pegsFound;                      my %clusterOf = map { $_ => -1 } @pegsFound;
815                                # Partition the PEGs found into clusters.
816                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
817                      for (my $i = 0; $i <= $#clusters; $i++) {                      for (my $i = 0; $i <= $#clusters; $i++) {
818                          my $subList = $clusters[$i];                          my $subList = $clusters[$i];
819                          for my $peg (@{$subList}) {                          for my $peg (@{$subList}) {
# Line 790  Line 841 
841              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
842              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
843              # Connect the subset to its roles.              # Connect the subset to its roles.
844              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
845              for my $roleID (@roles) {              for my $roleID (@roles) {
846                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
847              }              }
# Line 810  Line 861 
861              }              }
862          }          }
863      }      }
     # Before we leave, we must create the Catalyzes table. The data is all stored in  
     # "reactionToRoles" hash.  
     for my $reactionID (keys %reactionsToRoles) {  
         # Get this reaction's list of roles. We sort it so we can merge out duplicates.  
         my @roles = sort @{$reactionsToRoles{$reactionID}};  
         my $lastRole = "";  
         # Loop through the roles, creating catalyzation records.  
         for my $thisRole (@roles) {  
             if ($thisRole ne $lastRole) {  
                 $loadCatalyzes->Put($thisRole, $reactionID);  
             }  
         }  
864      }      }
865      # Finish the load.          # Now we loop through the diagrams. We need to create the diagram records
866      my $retVal = $self->_FinishAll();          # and link each diagram to its roles. Note that only roles which occur
867      return $retVal;          # in subsystems (and therefore appear in the %ecToRoles hash) are
868  }          # included.
869            for my $map (@maps) {
 =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) {  
870          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
871          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
872          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 876  Line 875 
875          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
876          my %roleHash = ();          my %roleHash = ();
877          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
878              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
879                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
880                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
881              }              }
882          }          }
883      }      }
884            # Before we leave, we must create the Catalyzes table. We start with the reactions,
885            # then use the "ecToRoles" table to convert EC numbers to role IDs.
886            my @reactions = $fig->all_reactions();
887            for my $reactionID (@reactions) {
888                # Get this reaction's list of roles. The results will be EC numbers.
889                my @roles = $fig->catalyzed_by($reactionID);
890                # Loop through the roles, creating catalyzation records.
891                for my $thisRole (@roles) {
892                    if (exists $ecToRoles{$thisRole}) {
893                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
894                    }
895                }
896            }
897        }
898      # Finish the load.      # Finish the load.
899      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
900      return $retVal;      return $retVal;
# Line 923  Line 936 
936      my $fig = $self->{fig};      my $fig = $self->{fig};
937      # Get the genome hash.      # Get the genome hash.
938      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
939      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
940      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
941      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
942      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
943            Trace("Loading from existing files.") if T(2);
944        } else {
945            Trace("Generating property data.") if T(2);
946      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
947      my %propertyKeys = ();      my %propertyKeys = ();
948      my $nextID = 1;      my $nextID = 1;
949      # Loop through the genomes.      # Loop through the genomes.
950      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
951          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
952                Trace("Generating properties for $genomeID.") if T(3);
953          # 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
954          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
955          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
956          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
957                my $featureCount = 0;
958                my $propertyCount = 0;
959          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
960          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
961              # 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
962              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
963              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
964                    if (scalar @attributeList) {
965                        $featureCount++;
966                    }
967              # Loop through the attributes.              # Loop through the attributes.
968              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
969                        $propertyCount++;
970                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
971                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
972                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 967  Line 988 
988                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
989              }              }
990          }          }
991                # Update the statistics.
992                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
993                $loadHasProperty->Add("featuresIn", $featureCount);
994                $loadHasProperty->Add("propertiesIn", $propertyCount);
995            }
996      }      }
997      # Finish the load.      # Finish the load.
998      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1007  Line 1033 
1033      my $fig = $self->{fig};      my $fig = $self->{fig};
1034      # Get the genome hash.      # Get the genome hash.
1035      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1036      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1037      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1038      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1039      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1040      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1041      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1042      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1043            Trace("Loading from existing files.") if T(2);
1044        } else {
1045            Trace("Generating annotation data.") if T(2);
1046      # 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
1047      # user records.      # user records.
1048      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 1028  Line 1056 
1056      # Loop through the genomes.      # Loop through the genomes.
1057      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1058          Trace("Processing $genomeID.") if T(3);          Trace("Processing $genomeID.") if T(3);
         # Get the genome's PEGs.  
         my @pegs = $fig->pegs_of($genomeID);  
         for my $peg (@pegs) {  
             Trace("Processing $peg.") if T(4);  
1059              # 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
1060              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1061              my %seenTimestamps = ();              my %seenTimestamps = ();
1062              # Check for a functional assignment.              # Get the genome's annotations.
1063              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1064              if ($func) {              Trace("Processing annotations.") if T(2);
1065                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1066                  # assignment annotation for it.                  # Get the annotation tuple.
1067                  if (! FIG::hypo($peg)) {                  my ($peg, $timestamp, $user, $text) = @{$tuple};
                     # 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.  
             for my $tuple ($fig->feature_annotations($peg, "raw")) {  
                 my ($fid, $timestamp, $user, $text) = @{$tuple};  
1068                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1069                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1070                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1071                  # stop the substitution search.                  # stop the substitution search.
1072                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1067  Line 1079 
1079                      # Here it's a number. We need to insure the one we use to form                      # Here it's a number. We need to insure the one we use to form
1080                      # the key is unique.                      # the key is unique.
1081                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1082                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1083                          $keyStamp++;                          $keyStamp++;
1084                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1085                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1086                        $seenTimestamps{$annotationID} = 1;
1087                      # Insure the user exists.                      # Insure the user exists.
1088                      if (! $users{$user}) {                      if (! $users{$user}) {
1089                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1129  Line 1141 
1141      my $fig = $self->{fig};      my $fig = $self->{fig};
1142      # Get the genome hash.      # Get the genome hash.
1143      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1144      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1145      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1146      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1147      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1148      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1149            Trace("Loading from existing files.") if T(2);
1150        } else {
1151            Trace("Generating annotation data.") if T(2);
1152      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1153      my %sourceURL = ();      my %sourceURL = ();
1154      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1164  Line 1178 
1178      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1179          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1180      }      }
1181        }
1182      # Finish the load.      # Finish the load.
1183      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1184      return $retVal;      return $retVal;
# Line 1203  Line 1218 
1218      my $fig = $self->{fig};      my $fig = $self->{fig};
1219      # Get the genome hash.      # Get the genome hash.
1220      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1221      # 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
1222      # it the key.      # it the key.
1223      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1224      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1225      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1226      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1227      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1228            Trace("Loading from existing files.") if T(2);
1229        } else {
1230            Trace("Generating external data.") if T(2);
1231      # 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.
1232      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1233      my $orgLine;      my $orgLine;
1234      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1235          # Clean the input line.          # Clean the input line.
# Line 1224  Line 1241 
1241      close ORGS;      close ORGS;
1242      # Now the function file.      # Now the function file.
1243      my $funcLine;      my $funcLine;
1244      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1245      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1246          # Clean the line ending.          # Clean the line ending.
1247          chomp $funcLine;          chomp $funcLine;
# Line 1240  Line 1257 
1257              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1258          }          }
1259      }      }
1260        }
1261      # Finish the load.      # Finish the load.
1262      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1263      return $retVal;      return $retVal;
# Line 1256  Line 1274 
1274    
1275  The following relations are loaded by this method.  The following relations are loaded by this method.
1276    
1277        Reaction
1278      ReactionURL      ReactionURL
1279      Compound      Compound
1280      CompoundName      CompoundName
# Line 1279  Line 1298 
1298      my ($self) = @_;      my ($self) = @_;
1299      # Get the FIG object.      # Get the FIG object.
1300      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1301      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1302      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1303      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1304      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1305      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1306      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1307      Trace("Beginning reaction/compound data load.") if T(2);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1308      # Create a hash to remember the compounds we've generated in the compound table.      if ($self->{options}->{loadOnly}) {
1309      my %compoundHash = ();          Trace("Loading from existing files.") if T(2);
1310      # Loop through the reactions.      } else {
1311            Trace("Generating annotation data.") if T(2);
1312            # First we create the compounds.
1313            my @compounds = $fig->all_compounds();
1314            for my $cid (@compounds) {
1315                # Check for names.
1316                my @names = $fig->names_of_compound($cid);
1317                # Each name will be given a priority number, starting with 1.
1318                my $prio = 1;
1319                for my $name (@names) {
1320                    $loadCompoundName->Put($cid, $name, $prio++);
1321                }
1322                # Create the main compound record. Note that the first name
1323                # becomes the label.
1324                my $label = (@names > 0 ? $names[0] : $cid);
1325                $loadCompound->Put($cid, $label);
1326                # Check for a CAS ID.
1327                my $cas = $fig->cas($cid);
1328                if ($cas) {
1329                    $loadCompoundCAS->Put($cid, $cas);
1330                }
1331            }
1332            # All the compounds are set up, so we need to loop through the reactions next. First,
1333            # we initialize the discriminator index. This is a single integer used to insure
1334            # duplicate elements in a reaction are not accidentally collapsed.
1335            my $discrim = 0;
1336      my @reactions = $fig->all_reactions();      my @reactions = $fig->all_reactions();
1337      for my $reactionID (@reactions) {      for my $reactionID (@reactions) {
1338                # Create the reaction record.
1339                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1340          # Compute the reaction's URL.          # Compute the reaction's URL.
1341          my $url = HTML::reaction_link($reactionID);          my $url = HTML::reaction_link($reactionID);
1342          # Put it in the ReactionURL table.          # Put it in the ReactionURL table.
# Line 1302  Line 1345 
1345          # substrates first and then products.          # substrates first and then products.
1346          for my $product (0, 1) {          for my $product (0, 1) {
1347              # 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
1348              # 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
1349              # have location data in SEED, so it defaults to the empty string.              # have location data in SEED, so it defaults to the empty string.
1350              my @compounds = $fig->reaction2comp($reactionID, $product);              my @compounds = $fig->reaction2comp($reactionID, $product);
1351              for my $compData (@compounds) {              for my $compData (@compounds) {
1352                  # Extract the compound data from the current tuple.                  # Extract the compound data from the current tuple.
1353                  my ($cid, $stoich, $main) = @{$compData};                  my ($cid, $stoich, $main) = @{$compData};
1354                  # Link the compound to the reaction.                  # Link the compound to the reaction.
1355                  $loadIsAComponentOf->Put($cid, $reactionID, "", $main, $product, $stoich);                      $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1356                  # 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++);  
                     }  
1357                  }                  }
1358              }              }
1359          }          }
# Line 1366  Line 1393 
1393      my $fig = $self->{fig};      my $fig = $self->{fig};
1394      # Get the genome hash.      # Get the genome hash.
1395      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1396      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1397      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1398      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1399            Trace("Loading from existing files.") if T(2);
1400        } else {
1401            Trace("Generating group data.") if T(2);
1402      # Loop through the genomes.      # Loop through the genomes.
1403      my $line;      my $line;
1404      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1385  Line 1414 
1414          }          }
1415          close TMP;          close TMP;
1416      }      }
1417        }
1418        # Finish the load.
1419        my $retVal = $self->_FinishAll();
1420        return $retVal;
1421    }
1422    
1423    =head3 LoadSynonymData
1424    
1425    C<< my $stats = $spl->LoadSynonymData(); >>
1426    
1427    Load the synonym groups into Sprout.
1428    
1429    The following relations are loaded by this method.
1430    
1431        SynonymGroup
1432        IsSynonymGroupFor
1433    
1434    The source information for these relations is taken from the C<maps_to_id> method
1435    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1436    SQL against the FIG database.
1437    
1438    =over 4
1439    
1440    =item RETURNS
1441    
1442    Returns a statistics object for the loads.
1443    
1444    =back
1445    
1446    =cut
1447    #: Return Type $%;
1448    sub LoadSynonymData {
1449        # Get this object instance.
1450        my ($self) = @_;
1451        # Get the FIG object.
1452        my $fig = $self->{fig};
1453        # Get the genome hash.
1454        my $genomeHash = $self->{genomes};
1455        # Create a load object for the table we're loading.
1456        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1457        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1458        if ($self->{options}->{loadOnly}) {
1459            Trace("Loading from existing files.") if T(2);
1460        } else {
1461            Trace("Generating synonym group data.") if T(2);
1462            # Get the database handle.
1463            my $dbh = $fig->db_handle();
1464            # Ask for the synonyms.
1465            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1466            my $result = $sth->execute();
1467            if (! defined($result)) {
1468                Confess("Database error in Synonym load: " . $sth->errstr());
1469            } else {
1470                # Remember the current synonym.
1471                my $current_syn = "";
1472                # Count the features.
1473                my $featureCount = 0;
1474                # Loop through the synonym/peg pairs.
1475                while (my @row = $sth->fetchrow()) {
1476                    # Get the synonym ID and feature ID.
1477                    my ($syn_id, $peg) = @row;
1478                    # Insure it's for one of our genomes.
1479                    my $genomeID = FIG::genome_of($peg);
1480                    if (exists $genomeHash->{$genomeID}) {
1481                        # Verify the synonym.
1482                        if ($syn_id ne $current_syn) {
1483                            # It's new, so put it in the group table.
1484                            $loadSynonymGroup->Put($syn_id);
1485                            $current_syn = $syn_id;
1486                        }
1487                        # Connect the synonym to the peg.
1488                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1489                        # Count this feature.
1490                        $featureCount++;
1491                        if ($featureCount % 1000 == 0) {
1492                            Trace("$featureCount features processed.") if T(3);
1493                        }
1494                    }
1495                }
1496            }
1497        }
1498        # Finish the load.
1499        my $retVal = $self->_FinishAll();
1500        return $retVal;
1501    }
1502    
1503    =head3 LoadFamilyData
1504    
1505    C<< my $stats = $spl->LoadFamilyData(); >>
1506    
1507    Load the protein families into Sprout.
1508    
1509    The following relations are loaded by this method.
1510    
1511        Family
1512        IsFamilyForFeature
1513    
1514    The source information for these relations is taken from the C<families_for_protein>,
1515    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1516    
1517    =over 4
1518    
1519    =item RETURNS
1520    
1521    Returns a statistics object for the loads.
1522    
1523    =back
1524    
1525    =cut
1526    #: Return Type $%;
1527    sub LoadFamilyData {
1528        # Get this object instance.
1529        my ($self) = @_;
1530        # Get the FIG object.
1531        my $fig = $self->{fig};
1532        # Get the genome hash.
1533        my $genomeHash = $self->{genomes};
1534        # Create load objects for the tables we're loading.
1535        my $loadFamily = $self->_TableLoader('Family');
1536        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1537        if ($self->{options}->{loadOnly}) {
1538            Trace("Loading from existing files.") if T(2);
1539        } else {
1540            Trace("Generating family data.") if T(2);
1541            # Create a hash for the family IDs.
1542            my %familyHash = ();
1543            # Loop through the genomes.
1544            for my $genomeID (sort keys %{$genomeHash}) {
1545                Trace("Processing features for $genomeID.") if T(2);
1546                # Loop through this genome's PEGs.
1547                for my $fid ($fig->all_features($genomeID, "peg")) {
1548                    $loadIsFamilyForFeature->Add("features", 1);
1549                    # Get this feature's families.
1550                    my @families = $fig->families_for_protein($fid);
1551                    # Loop through the families, connecting them to the feature.
1552                    for my $family (@families) {
1553                        $loadIsFamilyForFeature->Put($family, $fid);
1554                        # If this is a new family, create a record for it.
1555                        if (! exists $familyHash{$family}) {
1556                            $familyHash{$family} = 1;
1557                            $loadFamily->Add("families", 1);
1558                            my $size = $fig->sz_family($family);
1559                            my $func = $fig->family_function($family);
1560                            $loadFamily->Put($family, $size, $func);
1561                        }
1562                    }
1563                }
1564            }
1565        }
1566      # Finish the load.      # Finish the load.
1567      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1568      return $retVal;      return $retVal;
# Line 1406  Line 1584 
1584    
1585  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1586    
1587  =item rowCount (optional)  =item ignore
1588    
1589  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1590    
1591  =item RETURN  =item RETURN
1592    
# Line 1420  Line 1598 
1598    
1599  sub _TableLoader {  sub _TableLoader {
1600      # Get the parameters.      # Get the parameters.
1601      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1602      # Create the load object.      # Create the load object.
1603      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1604                                   $ignore);
1605      # Cache it in the loader list.      # Cache it in the loader list.
1606      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1607      # Return it to the caller.      # Return it to the caller.
# Line 1456  Line 1635 
1635      my $retVal = Stats->new();      my $retVal = Stats->new();
1636      # Get the loader list.      # Get the loader list.
1637      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1638        # Create a hash to hold the statistics objects, keyed on relation name.
1639        my %loaderHash = ();
1640      # 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
1641      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads more restartable.
1642      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1643          # Trace the fact that we're cleaning up.          # Get the relation name.
1644          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1645          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1646            if ($loader->Ignore) {
1647                Trace("Relation $relName not loaded.") if T(2);
1648            } else {
1649                # Here we really need to finish.
1650                Trace("Finishing $relName.") if T(2);
1651          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1652                $loaderHash{$relName} = $stats;
1653            }
1654        }
1655        # Now we loop through again, actually loading the tables. We want to finish before
1656        # loading so that if something goes wrong at this point, all the load files are usable
1657        # and we don't have to redo all that work.
1658        for my $relName (sort keys %loaderHash) {
1659            # Get the statistics for this relation.
1660            my $stats = $loaderHash{$relName};
1661            # Check for a database load.
1662          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1663              # 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.
1664              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);

Legend:
Removed from v.1.19  
changed lines
  Added in v.1.64

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3