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

Diff of /Sprout/SproutLoad.pm

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

revision 1.8, Wed Sep 14 09:57:27 2005 UTC revision 1.53, Mon Jul 10 21:55:06 2006 UTC
# Line 10  Line 10 
10      use Sprout;      use Sprout;
11      use Stats;      use Stats;
12      use BasicLocation;      use BasicLocation;
13        use HTML;
14    
15  =head1 Sprout Load Methods  =head1 Sprout Load Methods
16    
# Line 29  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 79  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 93  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 = $fig->genomes(1);
# Line 128  Line 130 
130              Confess("Invalid genome parameter ($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 NMPDR subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for the NMPDR file.
142                for my $sub (@subs) {
143                    if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {
144                        $subsystems{$sub} = 1;
145                    }
146                }
147      } else {      } else {
148          my $type = ref $subsysFile;          my $type = ref $subsysFile;
149          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 152  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 161  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 170  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 197  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 215  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 267  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 307  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 339  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");                      $loadCoupling->Add("couplingIn");
381                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 367  Line 403 
403                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
404                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
405                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
406                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
407                              # the hash makes it to the output.                              # the hash makes it to the output.
408                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
409                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 375  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, 1);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
424                            }
425                      }                      }
426                  }                  }
427              }              }
# Line 409  Line 448 
448      FeatureTranslation      FeatureTranslation
449      FeatureUpstream      FeatureUpstream
450      IsLocatedIn      IsLocatedIn
451        HasFeature
452    
453  =over 4  =over 4
454    
# Line 425  Line 465 
465      my ($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, $loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
474      if (! $limited) {      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
475          $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      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);
# Line 455  Line 492 
492          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
493              $loadFeature->Add("featureIn");              $loadFeature->Add("featureIn");
494              # Split the tuple.              # Split the tuple.
495              my ($featureID, $locations, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureData};
496              # Create the feature record.              # Create the feature record.
497              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
498              # The next stuff is for a full load only.                  # Link it to the parent genome.
499              if (! $limited) {                  $loadHasFeature->Put($genomeID, $featureID, $type);
500                  # Create the aliases.                  # Create the aliases.
501                  for my $alias (split /\s*,\s*/, $aliases) {                  for my $alias ($fig->feature_aliases($featureID)) {
502                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
503                  }                  }
504                  # Get the links.                  # Get the links.
# Line 482  Line 519 
519                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
520                      }                      }
521                  }                  }
             }  
522              # 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
523              # 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
524              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
# Line 493  Line 529 
529              # Loop through the locations.              # Loop through the locations.
530              for my $location (@locationList) {              for my $location (@locationList) {
531                  # Parse the location.                  # Parse the location.
532                  my $locObject = BasicLocation->new($location);                      my $locObject = BasicLocation->new("$genomeID:$location");
533                  # Split it into a list of chunks.                  # Split it into a list of chunks.
534                  my @locOList = ();                  my @locOList = ();
535                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 511  Line 547 
547              }              }
548          }          }
549      }      }
550        }
551      # Finish the loads.      # Finish the loads.
552      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
553      return $retVal;      return $retVal;
# Line 547  Line 584 
584      my $fig = $self->{fig};      my $fig = $self->{fig};
585      # Get the table of genome IDs.      # Get the table of genome IDs.
586      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
587      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
588      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
589                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
590      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
591        } else {
592            Trace("Generating BBH data.") if T(2);
593      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
594      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
595          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 578  Line 615 
615              }              }
616          }          }
617      }      }
618        }
619      # Finish the loads.      # Finish the loads.
620      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
621      return $retVal;      return $retVal;
# Line 598  Line 636 
636  The following relations are loaded by this method.  The following relations are loaded by this method.
637    
638      Subsystem      Subsystem
639        SubsystemClass
640      Role      Role
641        RoleEC
642      SSCell      SSCell
643      ContainsFeature      ContainsFeature
644      IsGenomeOf      IsGenomeOf
# Line 606  Line 646 
646      OccursInSubsystem      OccursInSubsystem
647      ParticipatesIn      ParticipatesIn
648      HasSSCell      HasSSCell
649        ConsistsOfRoles
650        RoleSubset
651        HasRoleSubset
652        ConsistsOfGenomes
653        GenomeSubset
654        HasGenomeSubset
655        Catalyzes
656        Diagram
657        RoleOccursIn
658    
659  =over 4  =over 4
660    
# Line 615  Line 664 
664    
665  =back  =back
666    
 B<TO DO>  
   
 Generate RoleName table?  
   
667  =cut  =cut
668  #: Return Type $%;  #: Return Type $%;
669  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 632  Line 677 
677      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
678      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
679      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
680      my $subsysCount = @subsysIDs;      # Get the map list.
681      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
682      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
683      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
684      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
685      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
686      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
687      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
688      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
689      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
690      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
691      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
692      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
693        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
694        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
695        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
696        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
697        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
698        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
699        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
700        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
701        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
702        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
703        if ($self->{options}->{loadOnly}) {
704            Trace("Loading from existing files.") if T(2);
705        } else {
706            Trace("Generating subsystem data.") if T(2);
707            # This hash will contain the role for each EC. When we're done, this
708            # information will be used to generate the Catalyzes table.
709            my %ecToRoles = ();
710      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
711      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
712      # 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
713      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
714            # and memorize up the reactions.
715            my ($genomeID, $roleID);
716      my %roleData = ();      my %roleData = ();
717      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
718                # Get the subsystem object.
719                my $sub = $fig->get_subsystem($subsysID);
720                # Only proceed if the subsystem has a spreadsheet.
721                if (! $sub->{empty_ss}) {
722          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
723          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
724          # Create the subsystem record.          # Create the subsystem record.
725          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
726          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
727          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
728          # Connect the roles to the subsystem. If a role is new, we create                  my $class = $fig->subsystem_classification($subsysID);
729          # a role record for it.                  if ($class) {
730          for my $roleID (@roles) {                      $loadSubsystemClass->Put($subsysID, $class);
731                    }
732                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
733                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
734                        # Connect to this role.
735              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
736              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
737                        # If it's a new role, add it to the role table.
738              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
739                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
740                            my $abbr = $sub->get_role_abbr($col);
741                            # Add the role.
742                            $loadRole->Put($roleID, $abbr);
743                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
744                            # Check for an EC number.
745                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
746                                my $ec = $1;
747                                $loadRoleEC->Put($roleID, $ec);
748                                $ecToRoles{$ec} = $roleID;
749              }              }
750          }          }
751          # Now all roles for this subsystem have been filled in. We create the                  }
752          # spreadsheet by matches roles to genomes. To do this, we need to                  # Now we create the spreadsheet for the subsystem by matching roles to
753          # get the genomes on the sheet.                  # genomes. Each genome is a row and each role is a column. We may need
754                    # to actually create the roles as we find them.
755          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
756          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
757          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
758              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
759                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
760                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
761                            my $cellCount = 0;
762                            # Create a list for the PEGs we find. This list will be used
763                            # to generate cluster numbers.
764                            my @pegsFound = ();
765                            # Create a hash that maps spreadsheet IDs to PEGs. We will
766                            # use this to generate the ContainsFeature data after we have
767                            # the cluster numbers.
768                            my %cellPegs = ();
769                            # Get the genome's variant code for this subsystem.
770                            my $variantCode = $sub->get_variant_code($row);
771                  # Loop through the subsystem's roles. We use an index because it is                  # Loop through the subsystem's roles. We use an index because it is
772                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
773                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
774                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
775                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
776                      # Only proceed if features exist.                      # Only proceed if features exist.
777                      if (@pegs > 0) {                      if (@pegs > 0) {
778                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
779                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
780                                    my $cellID = "$subsysID:$genomeID:$col";
781                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
782                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
783                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
784                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
785                          # Attach the features to it.                                  # Remember its features.
786                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
787                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
788                                    $pegCount += @pegs;
789                                }
790                            }
791                            # If we found some cells for this genome, we need to compute clusters and
792                            # denote it participates in the subsystem.
793                            if ($pegCount > 0) {
794                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
795                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
796                                # Create a hash mapping PEG IDs to cluster numbers.
797                                # We default to -1 for all of them.
798                                my %clusterOf = map { $_ => -1 } @pegsFound;
799                                # Partition the PEGs found into clusters.
800                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
801                                for (my $i = 0; $i <= $#clusters; $i++) {
802                                    my $subList = $clusters[$i];
803                                    for my $peg (@{$subList}) {
804                                        $clusterOf{$peg} = $i;
805                                    }
806                                }
807                                # Create the ContainsFeature data.
808                                for my $cellID (keys %cellPegs) {
809                                    my $cellList = $cellPegs{$cellID};
810                                    for my $cellPeg (@$cellList) {
811                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
812                          }                          }
813                      }                      }
814                  }                  }
815              }              }
816          }          }
817                    # Now we need to generate the subsets. The subset names must be concatenated to
818                    # the subsystem name to make them unique keys. There are two types of subsets:
819                    # genome subsets and role subsets. We do the role subsets first.
820                    my @subsetNames = $sub->get_subset_names();
821                    for my $subsetID (@subsetNames) {
822                        # Create the subset record.
823                        my $actualID = "$subsysID:$subsetID";
824                        $loadRoleSubset->Put($actualID);
825                        # Connect the subset to the subsystem.
826                        $loadHasRoleSubset->Put($subsysID, $actualID);
827                        # Connect the subset to its roles.
828                        my @roles = $sub->get_subsetC_roles($subsetID);
829                        for my $roleID (@roles) {
830                            $loadConsistsOfRoles->Put($actualID, $roleID);
831      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
832  }  }
833                    # Next the genome subsets.
834  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
835                    for my $subsetID (@subsetNames) {
836  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
837                        my $actualID = "$subsysID:$subsetID";
838  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
839                        # Connect the subset to the subsystem.
840  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
841  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
842                        my @genomes = $sub->get_subsetR($subsetID);
843  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
844                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
845      Diagram                      }
846      RoleOccursIn                  }
847                }
848  =over 4              # Now we loop through the diagrams. We need to create the diagram records
849                # and link each diagram to its roles. Note that only roles which occur
850  =item RETURNS              # in subsystems (and therefore appear in the %ecToRoles hash) are
851                # included.
852  Returns a statistics object for the loads.              for my $map (@maps) {
   
 =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) {  
853          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
854          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
855          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 754  Line 858 
858          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
859          my %roleHash = ();          my %roleHash = ();
860          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
861              if (! $roleHash{$role}) {                      if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
862                  $loadRoleOccursIn->Put($role, $map);                          $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
863                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
864              }              }
865          }          }
866      }      }
867                # Before we leave, we must create the Catalyzes table. We start with the reactions,
868                # then use the "ecToRoles" table to convert EC numbers to role IDs.
869                my @reactions = $fig->all_reactions();
870                for my $reactionID (@reactions) {
871                    # Get this reaction's list of roles. The results will be EC numbers.
872                    my @roles = $fig->catalyzed_by($reactionID);
873                    # Loop through the roles, creating catalyzation records.
874                    for my $thisRole (@roles) {
875                        if (exists $ecToRoles{$thisRole}) {
876                            $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
877                        }
878                    }
879                }
880            }
881        }
882      # Finish the load.      # Finish the load.
883      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
884      return $retVal;      return $retVal;
# Line 801  Line 920 
920      my $fig = $self->{fig};      my $fig = $self->{fig};
921      # Get the genome hash.      # Get the genome hash.
922      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
923      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
924      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
925      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
926      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
927            Trace("Loading from existing files.") if T(2);
928        } else {
929            Trace("Generating property data.") if T(2);
930      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
931      my %propertyKeys = ();      my %propertyKeys = ();
932      my $nextID = 1;      my $nextID = 1;
933      # Loop through the genomes.      # Loop through the genomes.
934      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
935          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
936                Trace("Generating properties for $genomeID.") if T(3);
937          # 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
938          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
939          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
940          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
941                my $featureCount = 0;
942                my $propertyCount = 0;
943          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
944          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
945              # 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
946              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
947              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
948                    if (scalar @attributeList) {
949                        $featureCount++;
950                    }
951              # Loop through the attributes.              # Loop through the attributes.
952              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
953                        $propertyCount++;
954                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
955                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
956                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 845  Line 972 
972                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
973              }              }
974          }          }
975                # Update the statistics.
976                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
977                $loadHasProperty->Add("featuresIn", $featureCount);
978                $loadHasProperty->Add("propertiesIn", $propertyCount);
979            }
980      }      }
981      # Finish the load.      # Finish the load.
982      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 885  Line 1017 
1017      my $fig = $self->{fig};      my $fig = $self->{fig};
1018      # Get the genome hash.      # Get the genome hash.
1019      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1020      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1021      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1022      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1023      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1024      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1025      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1026      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1027            Trace("Loading from existing files.") if T(2);
1028        } else {
1029            Trace("Generating annotation data.") if T(2);
1030      # 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
1031      # user records.      # user records.
1032      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 906  Line 1040 
1040      # Loop through the genomes.      # Loop through the genomes.
1041      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1042          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);  
1043              # 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
1044              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1045              my %seenTimestamps = ();              my %seenTimestamps = ();
1046              # Check for a functional assignment.              # Get the genome's annotations.
1047              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1048              if ($func) {              Trace("Processing annotations.") if T(2);
1049                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1050                  # assignment annotation for it.                  # Get the annotation tuple.
1051                  if (! FIG::hypo($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};  
1052                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1053                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1054                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1055                      # stop the substitution search.                      # stop the substitution search.
1056                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 941  Line 1060 
1060                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1061                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1062                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1063                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1064                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1065                              $timestamp++;                      my $keyStamp = $timestamp;
1066                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1067                            $keyStamp++;
1068                          }                          }
1069                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1070                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1071                          # Insure the user exists.                          # Insure the user exists.
1072                          if (! $users{$user}) {                          if (! $users{$user}) {
1073                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 954  Line 1075 
1075                              $users{$user} = 1;                              $users{$user} = 1;
1076                          }                          }
1077                          # Generate the annotation.                          # Generate the annotation.
1078                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1079                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1080                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1081                      } else {                      } else {
# Line 964  Line 1085 
1085                  }                  }
1086              }              }
1087          }          }
     }  
1088      # Finish the load.      # Finish the load.
1089      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1090      return $retVal;      return $retVal;
# Line 1005  Line 1125 
1125      my $fig = $self->{fig};      my $fig = $self->{fig};
1126      # Get the genome hash.      # Get the genome hash.
1127      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1128      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1129      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1130      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1131      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1132      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1133            Trace("Loading from existing files.") if T(2);
1134        } else {
1135            Trace("Generating annotation data.") if T(2);
1136      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1137      my %sourceURL = ();      my %sourceURL = ();
1138      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1024  Line 1146 
1146              chomp $line;              chomp $line;
1147              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1148              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1149              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1150                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1151                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1152              }              }
1153              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1154                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1155                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1156                        $sourceDesc{$sourceID} = $sourceID;
1157              }              }
1158          }          }
1159          close TMP;          close TMP;
1160      }      }
1161            # Write the source descriptions.
1162            for my $sourceID (keys %sourceDesc) {
1163                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1164            }
1165        }
1166      # Finish the load.      # Finish the load.
1167      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1168      return $retVal;      return $retVal;
# Line 1074  Line 1202 
1202      my $fig = $self->{fig};      my $fig = $self->{fig};
1203      # Get the genome hash.      # Get the genome hash.
1204      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1205      # 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
1206      # it the key.      # it the key.
1207      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1208      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1209      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1210      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1211      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1212            Trace("Loading from existing files.") if T(2);
1213        } else {
1214            Trace("Generating external data.") if T(2);
1215      # 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.
1216      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1217      my $orgLine;      my $orgLine;
# Line 1111  Line 1241 
1241              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1242          }          }
1243      }      }
1244        }
1245        # Finish the load.
1246        my $retVal = $self->_FinishAll();
1247        return $retVal;
1248    }
1249    
1250    
1251    =head3 LoadReactionData
1252    
1253    C<< my $stats = $spl->LoadReactionData(); >>
1254    
1255    Load the reaction data from FIG into Sprout.
1256    
1257    Reaction data connects reactions to the compounds that participate in them.
1258    
1259    The following relations are loaded by this method.
1260    
1261        Reaction
1262        ReactionURL
1263        Compound
1264        CompoundName
1265        CompoundCAS
1266        IsAComponentOf
1267    
1268    This method proceeds reaction by reaction rather than genome by genome.
1269    
1270    =over 4
1271    
1272    =item RETURNS
1273    
1274    Returns a statistics object for the loads.
1275    
1276    =back
1277    
1278    =cut
1279    #: Return Type $%;
1280    sub LoadReactionData {
1281        # Get this object instance.
1282        my ($self) = @_;
1283        # Get the FIG object.
1284        my $fig = $self->{fig};
1285        # Create load objects for each of the tables we're loading.
1286        my $loadReaction = $self->_TableLoader('Reaction');
1287        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1288        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1289        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1290        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1291        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1292        if ($self->{options}->{loadOnly}) {
1293            Trace("Loading from existing files.") if T(2);
1294        } else {
1295            Trace("Generating annotation data.") if T(2);
1296            # First we create the compounds.
1297            my @compounds = $fig->all_compounds();
1298            for my $cid (@compounds) {
1299                # Check for names.
1300                my @names = $fig->names_of_compound($cid);
1301                # Each name will be given a priority number, starting with 1.
1302                my $prio = 1;
1303                for my $name (@names) {
1304                    $loadCompoundName->Put($cid, $name, $prio++);
1305                }
1306                # Create the main compound record. Note that the first name
1307                # becomes the label.
1308                my $label = (@names > 0 ? $names[0] : $cid);
1309                $loadCompound->Put($cid, $label);
1310                # Check for a CAS ID.
1311                my $cas = $fig->cas($cid);
1312                if ($cas) {
1313                    $loadCompoundCAS->Put($cid, $cas);
1314                }
1315            }
1316            # All the compounds are set up, so we need to loop through the reactions next. First,
1317            # we initialize the discriminator index. This is a single integer used to insure
1318            # duplicate elements in a reaction are not accidentally collapsed.
1319            my $discrim = 0;
1320            my @reactions = $fig->all_reactions();
1321            for my $reactionID (@reactions) {
1322                # Create the reaction record.
1323                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1324                # Compute the reaction's URL.
1325                my $url = HTML::reaction_link($reactionID);
1326                # Put it in the ReactionURL table.
1327                $loadReactionURL->Put($reactionID, $url);
1328                # Now we need all of the reaction's compounds. We get these in two phases,
1329                # substrates first and then products.
1330                for my $product (0, 1) {
1331                    # Get the compounds of the current type for the current reaction. FIG will
1332                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1333                    # have location data in SEED, so it defaults to the empty string.
1334                    my @compounds = $fig->reaction2comp($reactionID, $product);
1335                    for my $compData (@compounds) {
1336                        # Extract the compound data from the current tuple.
1337                        my ($cid, $stoich, $main) = @{$compData};
1338                        # Link the compound to the reaction.
1339                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1340                                                 $product, $stoich);
1341                    }
1342                }
1343            }
1344        }
1345      # Finish the load.      # Finish the load.
1346      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1347      return $retVal;      return $retVal;
# Line 1146  Line 1377 
1377      my $fig = $self->{fig};      my $fig = $self->{fig};
1378      # Get the genome hash.      # Get the genome hash.
1379      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1380      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1381      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1382      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1383            Trace("Loading from existing files.") if T(2);
1384        } else {
1385            Trace("Generating group data.") if T(2);
1386      # Loop through the genomes.      # Loop through the genomes.
1387      my $line;      my $line;
1388      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1165  Line 1398 
1398          }          }
1399          close TMP;          close TMP;
1400      }      }
1401        }
1402      # Finish the load.      # Finish the load.
1403      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1404      return $retVal;      return $retVal;
1405  }  }
1406    
1407    =head3 LoadSynonymData
1408    
1409    C<< my $stats = $spl->LoadSynonymData(); >>
1410    
1411    Load the synonym groups into Sprout.
1412    
1413    The following relations are loaded by this method.
1414    
1415        SynonymGroup
1416        IsSynonymGroupFor
1417    
1418    The source information for these relations is taken from the C<maps_to_id> method
1419    of the B<FIG> object. The process starts from the features, so it is possible
1420    that there will be duplicates in the SynonymGroup load file, since the relationship
1421    is one-to-many toward the features. The automatic sort on primary entity relations
1422    will fix this for us.
1423    
1424    =over 4
1425    
1426    =item RETURNS
1427    
1428    Returns a statistics object for the loads.
1429    
1430    =back
1431    
1432    =cut
1433    #: Return Type $%;
1434    sub LoadSynonymData {
1435        # Get this object instance.
1436        my ($self) = @_;
1437        # Get the FIG object.
1438        my $fig = $self->{fig};
1439        # Get the genome hash.
1440        my $genomeHash = $self->{genomes};
1441        # Create a load object for the table we're loading.
1442        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1443        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1444        if ($self->{options}->{loadOnly}) {
1445            Trace("Loading from existing files.") if T(2);
1446        } else {
1447            Trace("Generating synonym group data.") if T(2);
1448            # Loop through the genomes.
1449            for my $genomeID (sort keys %{$genomeHash}) {
1450                Trace("Processing $genomeID.") if T(3);
1451                # Get all of the features for this genome. The only method that does this is
1452                # all_features_detailed, which returns extra baggage that we discard.
1453                my $featureData = $fig->all_features_detailed($genomeID);
1454                my @fids = map { $_->[0] } @{$featureData};
1455                Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
1456                # Loop through the feature IDs.
1457                for my $fid (@fids) {
1458                    # Get the group for this feature.
1459                    my $synonym = $fig->maps_to_id($fid);
1460                    # Only proceed if the synonym is a real group.
1461                    if ($synonym ne $fid) {
1462                        $loadSynonymGroup->Put($synonym);
1463                        $loadIsSynonymGroupFor->Put($synonym, $fid);
1464                    }
1465                }
1466            }
1467        }
1468        # Finish the load.
1469        my $retVal = $self->_FinishAll();
1470        return $retVal;
1471    }
1472    
1473    
1474  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1475    
1476  =head3 TableLoader  =head3 TableLoader
# Line 1186  Line 1487 
1487    
1488  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1489    
1490  =item rowCount (optional)  =item ignore
1491    
1492  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1493    
1494  =item RETURN  =item RETURN
1495    
# Line 1200  Line 1501 
1501    
1502  sub _TableLoader {  sub _TableLoader {
1503      # Get the parameters.      # Get the parameters.
1504      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1505      # Create the load object.      # Create the load object.
1506      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1507                                   $ignore);
1508      # Cache it in the loader list.      # Cache it in the loader list.
1509      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1510      # Return it to the caller.      # Return it to the caller.
# Line 1236  Line 1538 
1538      my $retVal = Stats->new();      my $retVal = Stats->new();
1539      # Get the loader list.      # Get the loader list.
1540      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1541        # Create a hash to hold the statistics objects, keyed on relation name.
1542        my %loaderHash = ();
1543      # 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
1544      # 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.
1545      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1546            # Get the relation name.
1547            my $relName = $loader->RelName;
1548            # Check the ignore flag.
1549            if ($loader->Ignore) {
1550                Trace("Relation $relName not loaded.") if T(2);
1551            } else {
1552                # Here we really need to finish.
1553                Trace("Finishing $relName.") if T(2);
1554          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1555                $loaderHash{$relName} = $stats;
1556            }
1557        }
1558        # Now we loop through again, actually loading the tables. We want to finish before
1559        # loading so that if something goes wrong at this point, all the load files are usable
1560        # and we don't have to redo all that work.
1561        for my $relName (sort keys %loaderHash) {
1562            # Get the statistics for this relation.
1563            my $stats = $loaderHash{$relName};
1564            # Check for a database load.
1565            if ($self->{options}->{dbLoad}) {
1566                # Here we want to use the load file just created to load the database.
1567                Trace("Loading relation $relName.") if T(2);
1568                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1569                # Accumulate the statistics from the DB load.
1570                $stats->Accumulate($newStats);
1571            }
1572          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1573          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1574      }      }
1575      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.8  
changed lines
  Added in v.1.53

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3