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

Diff of /Sprout/SproutLoad.pm

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

revision 1.21, Sat Nov 12 03:42:48 2005 UTC revision 1.66, Wed Sep 6 19:30:53 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 119  Line 120 
120                  # an omitted access code can be defaulted to 1.                  # an omitted access code can be defaulted to 1.
121                  for my $genomeLine (@genomeList) {                  for my $genomeLine (@genomeList) {
122                      my ($genomeID, $accessCode) = split("\t", $genomeLine);                      my ($genomeID, $accessCode) = split("\t", $genomeLine);
123                      if (undef $accessCode) {                          if (! defined($accessCode)) {
124                          $accessCode = 1;                          $accessCode = 1;
125                      }                      }
126                      $genomes{$genomeID} = $accessCode;                      $genomes{$genomeID} = $accessCode;
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($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");
609          Trace("Processing features for genome $genomeID.") if T(3);          Trace("Processing features for genome $genomeID.") if T(3);
610          # Get the feature list for this genome.          # Get the feature list for this genome.
611          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
612                # Count the BBHs we find.
613                my $bbhCount = 0;
614          # Loop through the features.          # Loop through the features.
615          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
616              # Split the tuple.              # Split the tuple.
# Line 575  Line 626 
626                  if ($genomeHash->{$targetGenomeID}) {                  if ($genomeHash->{$targetGenomeID}) {
627                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
628                                                         $score);                                                         $score);
629                            $bbhCount++;
630                        }
631                  }                  }
632              }              }
633                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
634          }          }
635      }      }
636      # Finish the loads.      # Finish the loads.
# Line 599  Line 653 
653  The following relations are loaded by this method.  The following relations are loaded by this method.
654    
655      Subsystem      Subsystem
656        SubsystemClass
657      Role      Role
658      RoleEC      RoleEC
659      SSCell      SSCell
# Line 639  Line 694 
694      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
695      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
696      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
     my $subsysCount = @subsysIDs;  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
697      # Get the map list.      # Get the map list.
698      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
     my $mapCount = @maps;  
     # Create load objects for each of the tables we're loading.  
     my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);  
     my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);  
     my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);  
     my $loadRole = $self->_TableLoader('Role', $featureCount * 6);  
     my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);  
     my $loadCatalyzes = $self->_TableLoader('Catalyzes', $genomeCount * $featureCount);  
     my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);  
     my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);  
     my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);  
     my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);  
     my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);  
     my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);  
     my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);  
     my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);  
     my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);  
     my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);  
     my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);  
     my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);  
     my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);  
699      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
700      Trace("Beginning subsystem data load.") if T(2);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
701        my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
702        my $loadSubsystem = $self->_TableLoader('Subsystem');
703        my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
704        my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
705        my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
706        my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
707        my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
708        my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
709        my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
710        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
711        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
712        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
713        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
714        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
715        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
716        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
717        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
718        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
719        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
720        if ($self->{options}->{loadOnly}) {
721            Trace("Loading from existing files.") if T(2);
722        } else {
723            Trace("Generating subsystem data.") if T(2);
724      # This hash will contain the role for each EC. When we're done, this      # This hash will contain the role for each EC. When we're done, this
725      # information will be used to generate the Catalyzes table.      # information will be used to generate the Catalyzes table.
726      my %ecToRoles = ();      my %ecToRoles = ();
# Line 678  Line 732 
732      my ($genomeID, $roleID);      my ($genomeID, $roleID);
733      my %roleData = ();      my %roleData = ();
734      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
735          # Get the subsystem object.          # Get the subsystem object.
736          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
737                # Only proceed if the subsystem has a spreadsheet.
738                if (! $sub->{empty_ss}) {
739                    Trace("Creating subsystem $subsysID.") if T(3);
740                    $loadSubsystem->Add("subsystemIn");
741          # Create the subsystem record.          # Create the subsystem record.
742          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
743          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
744          $loadSubsystem->Put($subsysID, $curator, $notes);          $loadSubsystem->Put($subsysID, $curator, $notes);
745                    my $classList = $fig->subsystem_classification($subsysID);
746                    my @classes = @$classList;
747                    if (@classes) {
748                        for my $class (@classes) {
749                            $loadSubsystemClass->Put($subsysID, $class);
750                        }
751                    }
752          # 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.
753          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
754              # Connect to this role.              # Connect to this role.
# Line 729  Line 792 
792                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
793                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
794                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
795                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
796                      # Only proceed if features exist.                      # Only proceed if features exist.
797                      if (@pegs > 0) {                      if (@pegs > 0) {
798                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 750  Line 813 
813                  if ($pegCount > 0) {                  if ($pegCount > 0) {
814                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
815                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                     # Partition the PEGs found into clusters.  
                     my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
816                      # Create a hash mapping PEG IDs to cluster numbers.                      # Create a hash mapping PEG IDs to cluster numbers.
817                      # We default to -1 for all of them.                      # We default to -1 for all of them.
818                      my %clusterOf = map { $_ => -1 } @pegsFound;                      my %clusterOf = map { $_ => -1 } @pegsFound;
819                                # Partition the PEGs found into clusters.
820                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
821                      for (my $i = 0; $i <= $#clusters; $i++) {                      for (my $i = 0; $i <= $#clusters; $i++) {
822                          my $subList = $clusters[$i];                          my $subList = $clusters[$i];
823                          for my $peg (@{$subList}) {                          for my $peg (@{$subList}) {
# Line 782  Line 845 
845              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
846              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
847              # Connect the subset to its roles.              # Connect the subset to its roles.
848              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
849              for my $roleID (@roles) {              for my $roleID (@roles) {
850                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
851              }              }
# Line 802  Line 865 
865              }              }
866          }          }
867      }      }
868            }
869      # Now we loop through the diagrams. We need to create the diagram records      # Now we loop through the diagrams. We need to create the diagram records
870      # and link each diagram to its roles. Note that only roles which occur      # and link each diagram to its roles. Note that only roles which occur
871      # in subsystems (and therefore appear in the %ecToRoles hash) are      # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 834  Line 898 
898              }              }
899          }          }
900      }      }
901        }
902      # Finish the load.      # Finish the load.
903      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
904      return $retVal;      return $retVal;
# Line 875  Line 940 
940      my $fig = $self->{fig};      my $fig = $self->{fig};
941      # Get the genome hash.      # Get the genome hash.
942      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
943      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
944      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
945      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
946      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
947            Trace("Loading from existing files.") if T(2);
948        } else {
949            Trace("Generating property data.") if T(2);
950      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
951      my %propertyKeys = ();      my %propertyKeys = ();
952      my $nextID = 1;      my $nextID = 1;
953      # Loop through the genomes.      # Loop through the genomes.
954      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
955          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
956                Trace("Generating properties for $genomeID.") if T(3);
957          # 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
958          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
959          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
960          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
961                my $featureCount = 0;
962                my $propertyCount = 0;
963          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
964          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
965              # 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
966              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
967              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
968                    if (scalar @attributeList) {
969                        $featureCount++;
970                    }
971              # Loop through the attributes.              # Loop through the attributes.
972              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
973                        $propertyCount++;
974                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
975                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
976                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 919  Line 992 
992                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
993              }              }
994          }          }
995                # Update the statistics.
996                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
997                $loadHasProperty->Add("featuresIn", $featureCount);
998                $loadHasProperty->Add("propertiesIn", $propertyCount);
999            }
1000      }      }
1001      # Finish the load.      # Finish the load.
1002      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 959  Line 1037 
1037      my $fig = $self->{fig};      my $fig = $self->{fig};
1038      # Get the genome hash.      # Get the genome hash.
1039      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1040      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1041      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1042      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1043      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1044      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1045      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1046      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1047            Trace("Loading from existing files.") if T(2);
1048        } else {
1049            Trace("Generating annotation data.") if T(2);
1050      # 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
1051      # user records.      # user records.
1052      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 980  Line 1060 
1060      # Loop through the genomes.      # Loop through the genomes.
1061      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1062          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);  
1063              # 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
1064              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1065              my %seenTimestamps = ();              my %seenTimestamps = ();
1066              # Check for a functional assignment.              # Get the genome's annotations.
1067              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1068              if ($func) {              Trace("Processing annotations.") if T(2);
1069                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1070                  # assignment annotation for it.                  # Get the annotation tuple.
1071                  if (! FIG::hypo($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};  
1072                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1073                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1074                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1075                  # stop the substitution search.                  # stop the substitution search.
1076                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1019  Line 1083 
1083                      # 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
1084                      # the key is unique.                      # the key is unique.
1085                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1086                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1087                          $keyStamp++;                          $keyStamp++;
1088                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1089                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1090                        $seenTimestamps{$annotationID} = 1;
1091                      # Insure the user exists.                      # Insure the user exists.
1092                      if (! $users{$user}) {                      if (! $users{$user}) {
1093                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1081  Line 1145 
1145      my $fig = $self->{fig};      my $fig = $self->{fig};
1146      # Get the genome hash.      # Get the genome hash.
1147      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1148      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1149      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1150      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1151      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1152      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1153            Trace("Loading from existing files.") if T(2);
1154        } else {
1155            Trace("Generating annotation data.") if T(2);
1156      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1157      my %sourceURL = ();      my %sourceURL = ();
1158      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1116  Line 1182 
1182      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1183          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1184      }      }
1185        }
1186      # Finish the load.      # Finish the load.
1187      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1188      return $retVal;      return $retVal;
# Line 1155  Line 1222 
1222      my $fig = $self->{fig};      my $fig = $self->{fig};
1223      # Get the genome hash.      # Get the genome hash.
1224      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1225      # 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
1226      # it the key.      # it the key.
1227      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1228      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1229      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1230      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1231      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1232            Trace("Loading from existing files.") if T(2);
1233        } else {
1234            Trace("Generating external data.") if T(2);
1235      # 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.
1236      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1237      my $orgLine;      my $orgLine;
1238      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1239          # Clean the input line.          # Clean the input line.
# Line 1176  Line 1245 
1245      close ORGS;      close ORGS;
1246      # Now the function file.      # Now the function file.
1247      my $funcLine;      my $funcLine;
1248      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1249      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1250          # Clean the line ending.          # Clean the line ending.
1251          chomp $funcLine;          chomp $funcLine;
# Line 1192  Line 1261 
1261              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1262          }          }
1263      }      }
1264        }
1265      # Finish the load.      # Finish the load.
1266      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1267      return $retVal;      return $retVal;
# Line 1232  Line 1302 
1302      my ($self) = @_;      my ($self) = @_;
1303      # Get the FIG object.      # Get the FIG object.
1304      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1305      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1306      my $loadReaction = $self->_TableLoader('Reaction', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1307      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1308      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1309      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1310      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1311      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1312      Trace("Beginning reaction/compound data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1313            Trace("Loading from existing files.") if T(2);
1314        } else {
1315            Trace("Generating annotation data.") if T(2);
1316      # First we create the compounds.      # First we create the compounds.
1317      my @compounds = $fig->all_compounds();      my @compounds = $fig->all_compounds();
1318      for my $cid (@compounds) {      for my $cid (@compounds) {
# Line 1291  Line 1361 
1361              }              }
1362          }          }
1363      }      }
1364        }
1365      # Finish the load.      # Finish the load.
1366      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1367      return $retVal;      return $retVal;
# Line 1326  Line 1397 
1397      my $fig = $self->{fig};      my $fig = $self->{fig};
1398      # Get the genome hash.      # Get the genome hash.
1399      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1400      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1401      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1402      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1403            Trace("Loading from existing files.") if T(2);
1404        } else {
1405            Trace("Generating group data.") if T(2);
1406      # Loop through the genomes.      # Loop through the genomes.
1407      my $line;      my $line;
1408      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1409          Trace("Processing $genomeID.") if T(3);          Trace("Processing $genomeID.") if T(3);
1410          # Open the NMPDR group file for this genome.          # Open the NMPDR group file for this genome.
1411          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
# Line 1345  Line 1418 
1418          }          }
1419          close TMP;          close TMP;
1420      }      }
1421        }
1422        # Finish the load.
1423        my $retVal = $self->_FinishAll();
1424        return $retVal;
1425    }
1426    
1427    =head3 LoadSynonymData
1428    
1429    C<< my $stats = $spl->LoadSynonymData(); >>
1430    
1431    Load the synonym groups into Sprout.
1432    
1433    The following relations are loaded by this method.
1434    
1435        SynonymGroup
1436        IsSynonymGroupFor
1437    
1438    The source information for these relations is taken from the C<maps_to_id> method
1439    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1440    SQL against the FIG database.
1441    
1442    =over 4
1443    
1444    =item RETURNS
1445    
1446    Returns a statistics object for the loads.
1447    
1448    =back
1449    
1450    =cut
1451    #: Return Type $%;
1452    sub LoadSynonymData {
1453        # Get this object instance.
1454        my ($self) = @_;
1455        # Get the FIG object.
1456        my $fig = $self->{fig};
1457        # Get the genome hash.
1458        my $genomeHash = $self->{genomes};
1459        # Create a load object for the table we're loading.
1460        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1461        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1462        if ($self->{options}->{loadOnly}) {
1463            Trace("Loading from existing files.") if T(2);
1464        } else {
1465            Trace("Generating synonym group data.") if T(2);
1466            # Get the database handle.
1467            my $dbh = $fig->db_handle();
1468            # Ask for the synonyms.
1469            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1470            my $result = $sth->execute();
1471            if (! defined($result)) {
1472                Confess("Database error in Synonym load: " . $sth->errstr());
1473            } else {
1474                # Remember the current synonym.
1475                my $current_syn = "";
1476                # Count the features.
1477                my $featureCount = 0;
1478                # Loop through the synonym/peg pairs.
1479                while (my @row = $sth->fetchrow()) {
1480                    # Get the synonym ID and feature ID.
1481                    my ($syn_id, $peg) = @row;
1482                    # Insure it's for one of our genomes.
1483                    my $genomeID = FIG::genome_of($peg);
1484                    if (exists $genomeHash->{$genomeID}) {
1485                        # Verify the synonym.
1486                        if ($syn_id ne $current_syn) {
1487                            # It's new, so put it in the group table.
1488                            $loadSynonymGroup->Put($syn_id);
1489                            $current_syn = $syn_id;
1490                        }
1491                        # Connect the synonym to the peg.
1492                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1493                        # Count this feature.
1494                        $featureCount++;
1495                        if ($featureCount % 1000 == 0) {
1496                            Trace("$featureCount features processed.") if T(3);
1497                        }
1498                    }
1499                }
1500            }
1501        }
1502        # Finish the load.
1503        my $retVal = $self->_FinishAll();
1504        return $retVal;
1505    }
1506    
1507    =head3 LoadFamilyData
1508    
1509    C<< my $stats = $spl->LoadFamilyData(); >>
1510    
1511    Load the protein families into Sprout.
1512    
1513    The following relations are loaded by this method.
1514    
1515        Family
1516        IsFamilyForFeature
1517    
1518    The source information for these relations is taken from the C<families_for_protein>,
1519    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1520    
1521    =over 4
1522    
1523    =item RETURNS
1524    
1525    Returns a statistics object for the loads.
1526    
1527    =back
1528    
1529    =cut
1530    #: Return Type $%;
1531    sub LoadFamilyData {
1532        # Get this object instance.
1533        my ($self) = @_;
1534        # Get the FIG object.
1535        my $fig = $self->{fig};
1536        # Get the genome hash.
1537        my $genomeHash = $self->{genomes};
1538        # Create load objects for the tables we're loading.
1539        my $loadFamily = $self->_TableLoader('Family');
1540        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1541        if ($self->{options}->{loadOnly}) {
1542            Trace("Loading from existing files.") if T(2);
1543        } else {
1544            Trace("Generating family data.") if T(2);
1545            # Create a hash for the family IDs.
1546            my %familyHash = ();
1547            # Loop through the genomes.
1548            for my $genomeID (sort keys %{$genomeHash}) {
1549                Trace("Processing features for $genomeID.") if T(2);
1550                # Loop through this genome's PEGs.
1551                for my $fid ($fig->all_features($genomeID, "peg")) {
1552                    $loadIsFamilyForFeature->Add("features", 1);
1553                    # Get this feature's families.
1554                    my @families = $fig->families_for_protein($fid);
1555                    # Loop through the families, connecting them to the feature.
1556                    for my $family (@families) {
1557                        $loadIsFamilyForFeature->Put($family, $fid);
1558                        # If this is a new family, create a record for it.
1559                        if (! exists $familyHash{$family}) {
1560                            $familyHash{$family} = 1;
1561                            $loadFamily->Add("families", 1);
1562                            my $size = $fig->sz_family($family);
1563                            my $func = $fig->family_function($family);
1564                            $loadFamily->Put($family, $size, $func);
1565                        }
1566                    }
1567                }
1568            }
1569        }
1570      # Finish the load.      # Finish the load.
1571      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1572      return $retVal;      return $retVal;
# Line 1366  Line 1588 
1588    
1589  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1590    
1591  =item rowCount (optional)  =item ignore
1592    
1593  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1594    
1595  =item RETURN  =item RETURN
1596    
# Line 1380  Line 1602 
1602    
1603  sub _TableLoader {  sub _TableLoader {
1604      # Get the parameters.      # Get the parameters.
1605      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1606      # Create the load object.      # Create the load object.
1607      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1608                                   $ignore);
1609      # Cache it in the loader list.      # Cache it in the loader list.
1610      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1611      # Return it to the caller.      # Return it to the caller.
# Line 1416  Line 1639 
1639      my $retVal = Stats->new();      my $retVal = Stats->new();
1640      # Get the loader list.      # Get the loader list.
1641      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1642        # Create a hash to hold the statistics objects, keyed on relation name.
1643        my %loaderHash = ();
1644      # 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
1645      # 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.
1646      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1647          # Trace the fact that we're cleaning up.          # Get the relation name.
1648          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1649          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1650            if ($loader->Ignore) {
1651                Trace("Relation $relName not loaded.") if T(2);
1652            } else {
1653                # Here we really need to finish.
1654                Trace("Finishing $relName.") if T(2);
1655          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1656                $loaderHash{$relName} = $stats;
1657            }
1658        }
1659        # Now we loop through again, actually loading the tables. We want to finish before
1660        # loading so that if something goes wrong at this point, all the load files are usable
1661        # and we don't have to redo all that work.
1662        for my $relName (sort keys %loaderHash) {
1663            # Get the statistics for this relation.
1664            my $stats = $loaderHash{$relName};
1665            # Check for a database load.
1666          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1667              # 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.
1668              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);

Legend:
Removed from v.1.21  
changed lines
  Added in v.1.66

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3