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

Diff of /Sprout/SproutLoad.pm

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

revision 1.15, Fri Sep 16 04:12:05 2005 UTC revision 1.67, Tue Sep 19 00:11:12 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 118  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} = $accessCode;
# Line 128  Line 130 
130              Confess("Invalid genome parameter ($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 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 ($type eq 'ARRAY') {
# Line 152  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($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 = $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                        # Get the functional assignment.
509                        my $assignment = $fig->function_of($featureID);
510              # Create the feature record.              # Create the feature record.
511              $loadFeature->Put($featureID, 1, $type);                      $loadFeature->Put($featureID, 1, $type, $assignment);
512                        # Link it to the parent genome.
513                        $loadHasFeature->Put($genomeID, $featureID, $type);
514              # Create the aliases.              # Create the aliases.
515              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
516                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
517              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
518                  # Get the links.                  # Get the links.
519                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
520                  for my $link (@links) {                  for my $link (@links) {
# Line 482  Line 533 
533                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
534                      }                      }
535                  }                  }
             }  
536              # 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
537              # 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
538              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
# Line 511  Line 561 
561              }              }
562          }          }
563      }      }
564            }
565        }
566      # Finish the loads.      # Finish the loads.
567      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
568      return $retVal;      return $retVal;
# Line 547  Line 599 
599      my $fig = $self->{fig};      my $fig = $self->{fig};
600      # Get the table of genome IDs.      # Get the table of genome IDs.
601      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
602      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
603      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
604                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
605      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
606        } else {
607            Trace("Generating BBH data.") if T(2);
608      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
609      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
610          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
611          Trace("Processing features for genome $genomeID.") if T(3);          Trace("Processing features for genome $genomeID.") if T(3);
612          # Get the feature list for this genome.          # Get the feature list for this genome.
613          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
614                # Count the BBHs we find.
615                my $bbhCount = 0;
616          # Loop through the features.          # Loop through the features.
617          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
618              # Split the tuple.              # Split the tuple.
# Line 574  Line 628 
628                  if ($genomeHash->{$targetGenomeID}) {                  if ($genomeHash->{$targetGenomeID}) {
629                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
630                                                         $score);                                                         $score);
631                            $bbhCount++;
632                  }                  }
633              }              }
634          }          }
635                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
636            }
637      }      }
638      # Finish the loads.      # Finish the loads.
639      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 598  Line 655 
655  The following relations are loaded by this method.  The following relations are loaded by this method.
656    
657      Subsystem      Subsystem
658        SubsystemClass
659      Role      Role
660        RoleEC
661      SSCell      SSCell
662      ContainsFeature      ContainsFeature
663      IsGenomeOf      IsGenomeOf
# Line 606  Line 665 
665      OccursInSubsystem      OccursInSubsystem
666      ParticipatesIn      ParticipatesIn
667      HasSSCell      HasSSCell
668        ConsistsOfRoles
669        RoleSubset
670        HasRoleSubset
671        ConsistsOfGenomes
672        GenomeSubset
673        HasGenomeSubset
674        Catalyzes
675        Diagram
676        RoleOccursIn
677    
678  =over 4  =over 4
679    
# Line 615  Line 683 
683    
684  =back  =back
685    
 B<TO DO>  
   
 Generate RoleName table?  
   
686  =cut  =cut
687  #: Return Type $%;  #: Return Type $%;
688  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 632  Line 696 
696      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
697      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
698      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
699      my $subsysCount = @subsysIDs;      # Get the map list.
700      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
701      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
702      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
703      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
704      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
705      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
706      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
707      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
708      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
709      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
710      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
711      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
712        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
713        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
714        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
715        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
716        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
717        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
718        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
719        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
720        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
721        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
722        if ($self->{options}->{loadOnly}) {
723            Trace("Loading from existing files.") if T(2);
724        } else {
725            Trace("Generating subsystem data.") if T(2);
726            # This hash will contain the role for each EC. When we're done, this
727            # information will be used to generate the Catalyzes table.
728            my %ecToRoles = ();
729      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
730      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
731      # 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
732      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
733            # and memorize up the reactions.
734      my ($genomeID, $roleID);      my ($genomeID, $roleID);
735      my %roleData = ();      my %roleData = ();
736      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
737                # Get the subsystem object.
738                my $sub = $fig->get_subsystem($subsysID);
739                # Only proceed if the subsystem has a spreadsheet.
740                if (! $sub->{empty_ss}) {
741          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
742          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
743          # Create the subsystem record.          # Create the subsystem record.
744          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
745          # Get the subsystem object.                  my $notes = $sub->get_notes();
746          my $sub = $fig->get_subsystem($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
747          # Connect it to its roles.                  my $classList = $fig->subsystem_classification($subsysID);
748                    my @classes = @$classList;
749                    if (@classes) {
750                        for my $class (@classes) {
751                            $loadSubsystemClass->Put($subsysID, $class);
752                        }
753                    }
754                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
755          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
756                        # Connect to this role.
757              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
758              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
759                        # If it's a new role, add it to the role table.
760              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
761                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
762                            my $abbr = $sub->get_role_abbr($col);
763                            # Add the role.
764                            $loadRole->Put($roleID, $abbr);
765                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
766                            # Check for an EC number.
767                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
768                                my $ec = $1;
769                                $loadRoleEC->Put($roleID, $ec);
770                                $ecToRoles{$ec} = $roleID;
771                            }
772              }              }
773          }          }
774          # Now we create the spreadsheet for the subsystem by matching roles to          # Now we create the spreadsheet for the subsystem by matching roles to
# Line 678  Line 781 
781                  # Count the PEGs and cells found for verification purposes.                  # Count the PEGs and cells found for verification purposes.
782                  my $pegCount = 0;                  my $pegCount = 0;
783                  my $cellCount = 0;                  my $cellCount = 0;
784                            # Create a list for the PEGs we find. This list will be used
785                            # to generate cluster numbers.
786                            my @pegsFound = ();
787                            # Create a hash that maps spreadsheet IDs to PEGs. We will
788                            # use this to generate the ContainsFeature data after we have
789                            # the cluster numbers.
790                            my %cellPegs = ();
791                            # Get the genome's variant code for this subsystem.
792                            my $variantCode = $sub->get_variant_code($row);
793                  # 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
794                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
795                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
796                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
797                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
798                      # Only proceed if features exist.                      # Only proceed if features exist.
799                      if (@pegs > 0) {                      if (@pegs > 0) {
800                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 692  Line 804 
804                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
805                          $loadIsRoleOf->Put($roleID, $cellID);                          $loadIsRoleOf->Put($roleID, $cellID);
806                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
807                          # Attach the features to it.                                  # Remember its features.
808                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
809                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
810                              $pegCount++;                                  $pegCount += @pegs;
                         }  
811                      }                      }
812                  }                  }
813                  # If we found some cells for this genome, denote it participates in the                          # If we found some cells for this genome, we need to compute clusters and
814                  # subsystem.                          # denote it participates in the subsystem.
815                  if ($pegCount > 0) {                  if ($pegCount > 0) {
816                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
817                      $loadParticipatesIn->Put($genomeID, $subsysID);                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
818                                # Create a hash mapping PEG IDs to cluster numbers.
819                                # We default to -1 for all of them.
820                                my %clusterOf = map { $_ => -1 } @pegsFound;
821                                # Partition the PEGs found into clusters.
822                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
823                                for (my $i = 0; $i <= $#clusters; $i++) {
824                                    my $subList = $clusters[$i];
825                                    for my $peg (@{$subList}) {
826                                        $clusterOf{$peg} = $i;
827                                    }
828                                }
829                                # Create the ContainsFeature data.
830                                for my $cellID (keys %cellPegs) {
831                                    my $cellList = $cellPegs{$cellID};
832                                    for my $cellPeg (@$cellList) {
833                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
834                  }                  }
835              }              }
836          }          }
837      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
838  }  }
839                    # Now we need to generate the subsets. The subset names must be concatenated to
840  =head3 LoadDiagramData                  # the subsystem name to make them unique keys. There are two types of subsets:
841                    # genome subsets and role subsets. We do the role subsets first.
842  C<< my $stats = $spl->LoadDiagramData(); >>                  my @subsetNames = $sub->get_subset_names();
843                    for my $subsetID (@subsetNames) {
844  Load the diagram data from FIG into Sprout.                      # Create the subset record.
845                        my $actualID = "$subsysID:$subsetID";
846  Diagrams are used to organize functional roles. The diagram shows the                      $loadRoleSubset->Put($actualID);
847  connections between chemicals that interact with a subsystem.                      # Connect the subset to the subsystem.
848                        $loadHasRoleSubset->Put($subsysID, $actualID);
849  The following relations are loaded by this method.                      # Connect the subset to its roles.
850                        my @roles = $sub->get_subsetC_roles($subsetID);
851      Diagram                      for my $roleID (@roles) {
852      RoleOccursIn                          $loadConsistsOfRoles->Put($actualID, $roleID);
853                        }
854  =over 4                  }
855                    # Next the genome subsets.
856  =item RETURNS                  @subsetNames = $sub->get_subset_namesR();
857                    for my $subsetID (@subsetNames) {
858  Returns a statistics object for the loads.                      # Create the subset record.
859                        my $actualID = "$subsysID:$subsetID";
860  =back                      $loadGenomeSubset->Put($actualID);
861                        # Connect the subset to the subsystem.
862  =cut                      $loadHasGenomeSubset->Put($subsysID, $actualID);
863  #: Return Type $%;                      # Connect the subset to its genomes.
864  sub LoadDiagramData {                      my @genomes = $sub->get_subsetR($subsetID);
865      # Get this object instance.                      for my $genomeID (@genomes) {
866      my ($self) = @_;                          $loadConsistsOfGenomes->Put($actualID, $genomeID);
867      # Get the FIG object.                      }
868      my $fig = $self->{fig};                  }
869      # Get the map list.              }
870      my @maps = $fig->all_maps;          }
871      my $mapCount = @maps;          # Now we loop through the diagrams. We need to create the diagram records
872      my $genomeCount = (keys %{$self->{genomes}});          # and link each diagram to its roles. Note that only roles which occur
873      my $featureCount = $genomeCount * 4000;          # in subsystems (and therefore appear in the %ecToRoles hash) are
874      # Create load objects for each of the tables we're loading.          # included.
875      my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);          for my $map (@maps) {
     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) {  
876          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
877          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
878          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 761  Line 881 
881          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
882          my %roleHash = ();          my %roleHash = ();
883          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
884              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
885                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
886                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
887              }              }
888          }          }
889      }      }
890            # Before we leave, we must create the Catalyzes table. We start with the reactions,
891            # then use the "ecToRoles" table to convert EC numbers to role IDs.
892            my @reactions = $fig->all_reactions();
893            for my $reactionID (@reactions) {
894                # Get this reaction's list of roles. The results will be EC numbers.
895                my @roles = $fig->catalyzed_by($reactionID);
896                # Loop through the roles, creating catalyzation records.
897                for my $thisRole (@roles) {
898                    if (exists $ecToRoles{$thisRole}) {
899                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
900                    }
901                }
902            }
903        }
904      # Finish the load.      # Finish the load.
905      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
906      return $retVal;      return $retVal;
# Line 808  Line 942 
942      my $fig = $self->{fig};      my $fig = $self->{fig};
943      # Get the genome hash.      # Get the genome hash.
944      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
945      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
946      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
947      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
948      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
949            Trace("Loading from existing files.") if T(2);
950        } else {
951            Trace("Generating property data.") if T(2);
952      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
953      my %propertyKeys = ();      my %propertyKeys = ();
954      my $nextID = 1;      my $nextID = 1;
955      # Loop through the genomes.      # Loop through the genomes.
956      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
957          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
958                Trace("Generating properties for $genomeID.") if T(3);
959          # 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
960          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
961          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
962          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
963                my $featureCount = 0;
964                my $propertyCount = 0;
965          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
966          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
967              # 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
968              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
969              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
970                    if (scalar @attributeList) {
971                        $featureCount++;
972                    }
973              # Loop through the attributes.              # Loop through the attributes.
974              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
975                        $propertyCount++;
976                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
977                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
978                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 852  Line 994 
994                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
995              }              }
996          }          }
997                # Update the statistics.
998                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
999                $loadHasProperty->Add("featuresIn", $featureCount);
1000                $loadHasProperty->Add("propertiesIn", $propertyCount);
1001            }
1002      }      }
1003      # Finish the load.      # Finish the load.
1004      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 892  Line 1039 
1039      my $fig = $self->{fig};      my $fig = $self->{fig};
1040      # Get the genome hash.      # Get the genome hash.
1041      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1042      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1043      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1044      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1045      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1046      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1047      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1048      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1049            Trace("Loading from existing files.") if T(2);
1050        } else {
1051            Trace("Generating annotation data.") if T(2);
1052      # 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
1053      # user records.      # user records.
1054      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 913  Line 1062 
1062      # Loop through the genomes.      # Loop through the genomes.
1063      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1064          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);  
1065              # 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
1066              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1067              my %seenTimestamps = ();              my %seenTimestamps = ();
1068              # Check for a functional assignment.              # Get the genome's annotations.
1069              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1070              if ($func) {              Trace("Processing annotations.") if T(2);
1071                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1072                  # assignment annotation for it.                  # Get the annotation tuple.
1073                  if (! FIG::hypo($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};  
1074                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1075                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1076                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1077                      # stop the substitution search.                      # stop the substitution search.
1078                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 948  Line 1082 
1082                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1083                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1084                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1085                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1086                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1087                              $timestamp++;                      my $keyStamp = $timestamp;
1088                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1089                            $keyStamp++;
1090                          }                          }
1091                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1092                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1093                          # Insure the user exists.                          # Insure the user exists.
1094                          if (! $users{$user}) {                          if (! $users{$user}) {
1095                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 961  Line 1097 
1097                              $users{$user} = 1;                              $users{$user} = 1;
1098                          }                          }
1099                          # Generate the annotation.                          # Generate the annotation.
1100                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1101                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1102                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1103                      } else {                      } else {
# Line 971  Line 1107 
1107                  }                  }
1108              }              }
1109          }          }
     }  
1110      # Finish the load.      # Finish the load.
1111      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1112      return $retVal;      return $retVal;
# Line 1012  Line 1147 
1147      my $fig = $self->{fig};      my $fig = $self->{fig};
1148      # Get the genome hash.      # Get the genome hash.
1149      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1150      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1151      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1152      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1153      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1154      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1155            Trace("Loading from existing files.") if T(2);
1156        } else {
1157            Trace("Generating annotation data.") if T(2);
1158      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1159      my %sourceURL = ();      my %sourceURL = ();
1160      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1031  Line 1168 
1168              chomp $line;              chomp $line;
1169              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1170              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1171              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1172                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1173                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1174              }              }
1175              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1176                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1177                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1178                        $sourceDesc{$sourceID} = $sourceID;
1179              }              }
1180          }          }
1181          close TMP;          close TMP;
1182      }      }
1183            # Write the source descriptions.
1184            for my $sourceID (keys %sourceDesc) {
1185                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1186            }
1187        }
1188      # Finish the load.      # Finish the load.
1189      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1190      return $retVal;      return $retVal;
# Line 1081  Line 1224 
1224      my $fig = $self->{fig};      my $fig = $self->{fig};
1225      # Get the genome hash.      # Get the genome hash.
1226      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1227      # 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
1228      # it the key.      # it the key.
1229      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1230      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1231      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1232      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1233      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1234            Trace("Loading from existing files.") if T(2);
1235        } else {
1236            Trace("Generating external data.") if T(2);
1237      # 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.
1238      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1239      my $orgLine;      my $orgLine;
1240      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1241          # Clean the input line.          # Clean the input line.
# Line 1102  Line 1247 
1247      close ORGS;      close ORGS;
1248      # Now the function file.      # Now the function file.
1249      my $funcLine;      my $funcLine;
1250      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1251      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1252          # Clean the line ending.          # Clean the line ending.
1253          chomp $funcLine;          chomp $funcLine;
# Line 1118  Line 1263 
1263              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1264          }          }
1265      }      }
1266        }
1267        # Finish the load.
1268        my $retVal = $self->_FinishAll();
1269        return $retVal;
1270    }
1271    
1272    
1273    =head3 LoadReactionData
1274    
1275    C<< my $stats = $spl->LoadReactionData(); >>
1276    
1277    Load the reaction data from FIG into Sprout.
1278    
1279    Reaction data connects reactions to the compounds that participate in them.
1280    
1281    The following relations are loaded by this method.
1282    
1283        Reaction
1284        ReactionURL
1285        Compound
1286        CompoundName
1287        CompoundCAS
1288        IsAComponentOf
1289    
1290    This method proceeds reaction by reaction rather than genome by genome.
1291    
1292    =over 4
1293    
1294    =item RETURNS
1295    
1296    Returns a statistics object for the loads.
1297    
1298    =back
1299    
1300    =cut
1301    #: Return Type $%;
1302    sub LoadReactionData {
1303        # Get this object instance.
1304        my ($self) = @_;
1305        # Get the FIG object.
1306        my $fig = $self->{fig};
1307        # Create load objects for each of the tables we're loading.
1308        my $loadReaction = $self->_TableLoader('Reaction');
1309        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1310        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1311        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1312        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1313        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1314        if ($self->{options}->{loadOnly}) {
1315            Trace("Loading from existing files.") if T(2);
1316        } else {
1317            Trace("Generating annotation data.") if T(2);
1318            # First we create the compounds.
1319            my @compounds = $fig->all_compounds();
1320            for my $cid (@compounds) {
1321                # Check for names.
1322                my @names = $fig->names_of_compound($cid);
1323                # Each name will be given a priority number, starting with 1.
1324                my $prio = 1;
1325                for my $name (@names) {
1326                    $loadCompoundName->Put($cid, $name, $prio++);
1327                }
1328                # Create the main compound record. Note that the first name
1329                # becomes the label.
1330                my $label = (@names > 0 ? $names[0] : $cid);
1331                $loadCompound->Put($cid, $label);
1332                # Check for a CAS ID.
1333                my $cas = $fig->cas($cid);
1334                if ($cas) {
1335                    $loadCompoundCAS->Put($cid, $cas);
1336                }
1337            }
1338            # All the compounds are set up, so we need to loop through the reactions next. First,
1339            # we initialize the discriminator index. This is a single integer used to insure
1340            # duplicate elements in a reaction are not accidentally collapsed.
1341            my $discrim = 0;
1342            my @reactions = $fig->all_reactions();
1343            for my $reactionID (@reactions) {
1344                # Create the reaction record.
1345                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1346                # Compute the reaction's URL.
1347                my $url = HTML::reaction_link($reactionID);
1348                # Put it in the ReactionURL table.
1349                $loadReactionURL->Put($reactionID, $url);
1350                # Now we need all of the reaction's compounds. We get these in two phases,
1351                # substrates first and then products.
1352                for my $product (0, 1) {
1353                    # Get the compounds of the current type for the current reaction. FIG will
1354                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1355                    # have location data in SEED, so it defaults to the empty string.
1356                    my @compounds = $fig->reaction2comp($reactionID, $product);
1357                    for my $compData (@compounds) {
1358                        # Extract the compound data from the current tuple.
1359                        my ($cid, $stoich, $main) = @{$compData};
1360                        # Link the compound to the reaction.
1361                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1362                                                 $product, $stoich);
1363                    }
1364                }
1365            }
1366        }
1367      # Finish the load.      # Finish the load.
1368      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1369      return $retVal;      return $retVal;
# Line 1153  Line 1399 
1399      my $fig = $self->{fig};      my $fig = $self->{fig};
1400      # Get the genome hash.      # Get the genome hash.
1401      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1402      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1403      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1404      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1405            Trace("Loading from existing files.") if T(2);
1406        } else {
1407            Trace("Generating group data.") if T(2);
1408      # Loop through the genomes.      # Loop through the genomes.
1409      my $line;      my $line;
1410      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1411          Trace("Processing $genomeID.") if T(3);          Trace("Processing $genomeID.") if T(3);
1412          # Open the NMPDR group file for this genome.          # Open the NMPDR group file for this genome.
1413          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
# Line 1172  Line 1420 
1420          }          }
1421          close TMP;          close TMP;
1422      }      }
1423        }
1424        # Finish the load.
1425        my $retVal = $self->_FinishAll();
1426        return $retVal;
1427    }
1428    
1429    =head3 LoadSynonymData
1430    
1431    C<< my $stats = $spl->LoadSynonymData(); >>
1432    
1433    Load the synonym groups into Sprout.
1434    
1435    The following relations are loaded by this method.
1436    
1437        SynonymGroup
1438        IsSynonymGroupFor
1439    
1440    The source information for these relations is taken from the C<maps_to_id> method
1441    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1442    SQL against the FIG database.
1443    
1444    =over 4
1445    
1446    =item RETURNS
1447    
1448    Returns a statistics object for the loads.
1449    
1450    =back
1451    
1452    =cut
1453    #: Return Type $%;
1454    sub LoadSynonymData {
1455        # Get this object instance.
1456        my ($self) = @_;
1457        # Get the FIG object.
1458        my $fig = $self->{fig};
1459        # Get the genome hash.
1460        my $genomeHash = $self->{genomes};
1461        # Create a load object for the table we're loading.
1462        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1463        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1464        if ($self->{options}->{loadOnly}) {
1465            Trace("Loading from existing files.") if T(2);
1466        } else {
1467            Trace("Generating synonym group data.") if T(2);
1468            # Get the database handle.
1469            my $dbh = $fig->db_handle();
1470            # Ask for the synonyms.
1471            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1472            my $result = $sth->execute();
1473            if (! defined($result)) {
1474                Confess("Database error in Synonym load: " . $sth->errstr());
1475            } else {
1476                # Remember the current synonym.
1477                my $current_syn = "";
1478                # Count the features.
1479                my $featureCount = 0;
1480                # Loop through the synonym/peg pairs.
1481                while (my @row = $sth->fetchrow()) {
1482                    # Get the synonym ID and feature ID.
1483                    my ($syn_id, $peg) = @row;
1484                    # Insure it's for one of our genomes.
1485                    my $genomeID = FIG::genome_of($peg);
1486                    if (exists $genomeHash->{$genomeID}) {
1487                        # Verify the synonym.
1488                        if ($syn_id ne $current_syn) {
1489                            # It's new, so put it in the group table.
1490                            $loadSynonymGroup->Put($syn_id);
1491                            $current_syn = $syn_id;
1492                        }
1493                        # Connect the synonym to the peg.
1494                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1495                        # Count this feature.
1496                        $featureCount++;
1497                        if ($featureCount % 1000 == 0) {
1498                            Trace("$featureCount features processed.") if T(3);
1499                        }
1500                    }
1501                }
1502            }
1503        }
1504        # Finish the load.
1505        my $retVal = $self->_FinishAll();
1506        return $retVal;
1507    }
1508    
1509    =head3 LoadFamilyData
1510    
1511    C<< my $stats = $spl->LoadFamilyData(); >>
1512    
1513    Load the protein families into Sprout.
1514    
1515    The following relations are loaded by this method.
1516    
1517        Family
1518        IsFamilyForFeature
1519    
1520    The source information for these relations is taken from the C<families_for_protein>,
1521    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1522    
1523    =over 4
1524    
1525    =item RETURNS
1526    
1527    Returns a statistics object for the loads.
1528    
1529    =back
1530    
1531    =cut
1532    #: Return Type $%;
1533    sub LoadFamilyData {
1534        # Get this object instance.
1535        my ($self) = @_;
1536        # Get the FIG object.
1537        my $fig = $self->{fig};
1538        # Get the genome hash.
1539        my $genomeHash = $self->{genomes};
1540        # Create load objects for the tables we're loading.
1541        my $loadFamily = $self->_TableLoader('Family');
1542        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1543        if ($self->{options}->{loadOnly}) {
1544            Trace("Loading from existing files.") if T(2);
1545        } else {
1546            Trace("Generating family data.") if T(2);
1547            # Create a hash for the family IDs.
1548            my %familyHash = ();
1549            # Loop through the genomes.
1550            for my $genomeID (sort keys %{$genomeHash}) {
1551                Trace("Processing features for $genomeID.") if T(2);
1552                # Loop through this genome's PEGs.
1553                for my $fid ($fig->all_features($genomeID, "peg")) {
1554                    $loadIsFamilyForFeature->Add("features", 1);
1555                    # Get this feature's families.
1556                    my @families = $fig->families_for_protein($fid);
1557                    # Loop through the families, connecting them to the feature.
1558                    for my $family (@families) {
1559                        $loadIsFamilyForFeature->Put($family, $fid);
1560                        # If this is a new family, create a record for it.
1561                        if (! exists $familyHash{$family}) {
1562                            $familyHash{$family} = 1;
1563                            $loadFamily->Add("families", 1);
1564                            my $size = $fig->sz_family($family);
1565                            my $func = $fig->family_function($family);
1566                            $loadFamily->Put($family, $size, $func);
1567                        }
1568                    }
1569                }
1570            }
1571        }
1572      # Finish the load.      # Finish the load.
1573      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1574      return $retVal;      return $retVal;
# Line 1193  Line 1590 
1590    
1591  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1592    
1593  =item rowCount (optional)  =item ignore
1594    
1595  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1596    
1597  =item RETURN  =item RETURN
1598    
# Line 1207  Line 1604 
1604    
1605  sub _TableLoader {  sub _TableLoader {
1606      # Get the parameters.      # Get the parameters.
1607      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1608      # Create the load object.      # Create the load object.
1609      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1610                                   $ignore);
1611      # Cache it in the loader list.      # Cache it in the loader list.
1612      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1613      # Return it to the caller.      # Return it to the caller.
# Line 1243  Line 1641 
1641      my $retVal = Stats->new();      my $retVal = Stats->new();
1642      # Get the loader list.      # Get the loader list.
1643      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1644        # Create a hash to hold the statistics objects, keyed on relation name.
1645        my %loaderHash = ();
1646      # 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
1647      # 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.
1648      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1649            # Get the relation name.
1650            my $relName = $loader->RelName;
1651            # Check the ignore flag.
1652            if ($loader->Ignore) {
1653                Trace("Relation $relName not loaded.") if T(2);
1654            } else {
1655                # Here we really need to finish.
1656                Trace("Finishing $relName.") if T(2);
1657          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1658                $loaderHash{$relName} = $stats;
1659            }
1660        }
1661        # Now we loop through again, actually loading the tables. We want to finish before
1662        # loading so that if something goes wrong at this point, all the load files are usable
1663        # and we don't have to redo all that work.
1664        for my $relName (sort keys %loaderHash) {
1665            # Get the statistics for this relation.
1666            my $stats = $loaderHash{$relName};
1667            # Check for a database load.
1668            if ($self->{options}->{dbLoad}) {
1669                # Here we want to use the load file just created to load the database.
1670                Trace("Loading relation $relName.") if T(2);
1671                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1672                # Accumulate the statistics from the DB load.
1673                $stats->Accumulate($newStats);
1674            }
1675          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1676          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1677      }      }
1678      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.15  
changed lines
  Added in v.1.67

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3