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

Diff of /Sprout/SproutLoad.pm

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

revision 1.7, Tue Sep 13 19:05:20 2005 UTC revision 1.54, Thu Jul 13 08:47:34 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 51  Line 50 
50    
51  =head3 new  =head3 new
52    
53  C<< my $spl = SproutLoad->new($sprout, $fig, $genomeFile, $subsysFile); >>  C<< my $spl = SproutLoad->new($sprout, $fig, $genomeFile, $subsysFile, $options); >>
54    
55  Construct a new Sprout Loader object, specifying the two participating databases and  Construct a new Sprout Loader object, specifying the two participating databases and
56  the name of the files containing the list of genomes and subsystems to use.  the name of the files containing the list of genomes and subsystems to use.
# Line 79  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
81  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
82  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85    =item options
86    
87    Reference to a hash of command-line options.
88    
89  =back  =back
90    
# Line 88  Line 92 
92    
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile) = @_;      my ($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 = $fig->genomes(1);
# Line 124  Line 130 
130              Confess("Invalid genome parameter ($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 ($type eq 'ARRAY') {
# Line 148  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 157  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
179                   };                   };
180      # Bless and return it.      # Bless and return it.
181      bless $retVal, $class;      bless $retVal, $class;
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 192  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 210  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 262  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 302  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 334  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");                      $loadCoupling->Add("couplingIn");
381                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 362  Line 403 
403                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
404                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
405                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
406                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
407                              # the hash makes it to the output.                              # the hash makes it to the output.
408                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
409                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 370  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 404  Line 448 
448      FeatureTranslation      FeatureTranslation
449      FeatureUpstream      FeatureUpstream
450      IsLocatedIn      IsLocatedIn
451        HasFeature
452    
453  =over 4  =over 4
454    
# Line 422  Line 467 
467      my $fig = $self->{fig};      my $fig = $self->{fig};
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 $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
473      my $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
474      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
475      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
476      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
477        my $loadHasFeature = $self->_TableLoader('HasFeature');
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                my $count = scalar @{$features};
492                Trace("$count features found for genome $genomeID.") if T(3);
493          # Loop through the features.          # Loop through the features.
494          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
495              $loadFeature->Add("featureIn");              $loadFeature->Add("featureIn");
496              # Split the tuple.              # Split the tuple.
497              my ($featureID, $locations, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureData};
498              # Create the feature record.              # Create the feature record.
499              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
500                    # Link it to the parent genome.
501                    $loadHasFeature->Put($genomeID, $featureID, $type);
502              # Create the aliases.              # Create the aliases.
503              for my $alias (split /\s*,\s*/, $aliases) {                  for my $alias ($fig->feature_aliases($featureID)) {
504                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
505              }              }
506              # Get the links.              # Get the links.
# Line 475  Line 526 
526              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
527              # for Sprout.              # for Sprout.
528              my @locationList = split /\s*,\s*/, $locations;              my @locationList = split /\s*,\s*/, $locations;
529                    # Create the location position indicator.
530                    my $i = 1;
531              # Loop through the locations.              # Loop through the locations.
532              for my $location (@locationList) {              for my $location (@locationList) {
533                  # Parse the location.                  # Parse the location.
534                  my $locObject = BasicLocation->new($location);                      my $locObject = BasicLocation->new("$genomeID:$location");
535                  # Split it into a list of chunks.                  # Split it into a list of chunks.
536                  my @locOList = ();                  my @locOList = ();
537                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 488  Line 541 
541                  push @locOList, $locObject;                  push @locOList, $locObject;
542                  # Loop through the chunks, creating IsLocatedIn records. The variable                  # Loop through the chunks, creating IsLocatedIn records. The variable
543                  # "$i" will be used to keep the location index.                  # "$i" will be used to keep the location index.
                 my $i = 1;  
544                  for my $locChunk (@locOList) {                  for my $locChunk (@locOList) {
545                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,
546                                            $locChunk->Dir, $locChunk->Length, $i);                                            $locChunk->Dir, $locChunk->Length, $i);
# Line 497  Line 549 
549              }              }
550          }          }
551      }      }
552        }
553      # Finish the loads.      # Finish the loads.
554      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
555      return $retVal;      return $retVal;
# Line 533  Line 586 
586      my $fig = $self->{fig};      my $fig = $self->{fig};
587      # Get the table of genome IDs.      # Get the table of genome IDs.
588      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
589      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
590      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
591                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
592      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
593        } else {
594            Trace("Generating BBH data.") if T(2);
595      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
596      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
597          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 564  Line 617 
617              }              }
618          }          }
619      }      }
620        }
621      # Finish the loads.      # Finish the loads.
622      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
623      return $retVal;      return $retVal;
# Line 584  Line 638 
638  The following relations are loaded by this method.  The following relations are loaded by this method.
639    
640      Subsystem      Subsystem
641        SubsystemClass
642      Role      Role
643        RoleEC
644      SSCell      SSCell
645      ContainsFeature      ContainsFeature
646      IsGenomeOf      IsGenomeOf
# Line 592  Line 648 
648      OccursInSubsystem      OccursInSubsystem
649      ParticipatesIn      ParticipatesIn
650      HasSSCell      HasSSCell
651        ConsistsOfRoles
652        RoleSubset
653        HasRoleSubset
654        ConsistsOfGenomes
655        GenomeSubset
656        HasGenomeSubset
657        Catalyzes
658        Diagram
659        RoleOccursIn
660    
661  =over 4  =over 4
662    
# Line 601  Line 666 
666    
667  =back  =back
668    
 B<TO DO>  
   
 Generate RoleName table?  
   
669  =cut  =cut
670  #: Return Type $%;  #: Return Type $%;
671  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 618  Line 679 
679      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
680      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
681      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
682      my $subsysCount = @subsysIDs;      # Get the map list.
683      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
684      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
685      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
686      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
687      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
688      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
689      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
690      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
691      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
692      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
693      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
694      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
695        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
696        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
697        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
698        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
699        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
700        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
701        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
702        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
703        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
704        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
705        if ($self->{options}->{loadOnly}) {
706            Trace("Loading from existing files.") if T(2);
707        } else {
708            Trace("Generating subsystem data.") if T(2);
709            # This hash will contain the role for each EC. When we're done, this
710            # information will be used to generate the Catalyzes table.
711            my %ecToRoles = ();
712      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
713      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
714      # 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
715      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
716            # and memorize up the reactions.
717            my ($genomeID, $roleID);
718      my %roleData = ();      my %roleData = ();
719      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
720                # Get the subsystem object.
721                my $sub = $fig->get_subsystem($subsysID);
722                # Only proceed if the subsystem has a spreadsheet.
723                if (! $sub->{empty_ss}) {
724          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
725          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
726          # Create the subsystem record.          # Create the subsystem record.
727          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
728          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
729          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
730          # Connect the roles to the subsystem. If a role is new, we create                  my $class = $fig->subsystem_classification($subsysID);
731          # a role record for it.                  if ($class) {
732          for my $roleID (@roles) {                      $loadSubsystemClass->Put($subsysID, $class);
733                    }
734                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
735                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
736                        # Connect to this role.
737              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
738              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
739                        # If it's a new role, add it to the role table.
740              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
741                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
742                            my $abbr = $sub->get_role_abbr($col);
743                            # Add the role.
744                            $loadRole->Put($roleID, $abbr);
745                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
746                            # Check for an EC number.
747                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
748                                my $ec = $1;
749                                $loadRoleEC->Put($roleID, $ec);
750                                $ecToRoles{$ec} = $roleID;
751                            }
752              }              }
753          }          }
754          # Now all roles for this subsystem have been filled in. We create the                  # Now we create the spreadsheet for the subsystem by matching roles to
755          # spreadsheet by matches roles to genomes. To do this, we need to                  # genomes. Each genome is a row and each role is a column. We may need
756          # get the genomes on the sheet.                  # to actually create the roles as we find them.
757          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
758          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
759          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
760              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
761                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
762                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
763                            my $cellCount = 0;
764                            # Create a list for the PEGs we find. This list will be used
765                            # to generate cluster numbers.
766                            my @pegsFound = ();
767                            # Create a hash that maps spreadsheet IDs to PEGs. We will
768                            # use this to generate the ContainsFeature data after we have
769                            # the cluster numbers.
770                            my %cellPegs = ();
771                            # Get the genome's variant code for this subsystem.
772                            my $variantCode = $sub->get_variant_code($row);
773                  # 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
774                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
775                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
776                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
777                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
778                      # Only proceed if features exist.                      # Only proceed if features exist.
779                      if (@pegs > 0) {                      if (@pegs > 0) {
780                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
781                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
782                                    my $cellID = "$subsysID:$genomeID:$col";
783                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
784                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
785                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
786                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
787                          # Attach the features to it.                                  # Remember its features.
788                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
789                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
790                                    $pegCount += @pegs;
791                                }
792                            }
793                            # If we found some cells for this genome, we need to compute clusters and
794                            # denote it participates in the subsystem.
795                            if ($pegCount > 0) {
796                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
797                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
798                                # Create a hash mapping PEG IDs to cluster numbers.
799                                # We default to -1 for all of them.
800                                my %clusterOf = map { $_ => -1 } @pegsFound;
801                                # Partition the PEGs found into clusters.
802                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
803                                for (my $i = 0; $i <= $#clusters; $i++) {
804                                    my $subList = $clusters[$i];
805                                    for my $peg (@{$subList}) {
806                                        $clusterOf{$peg} = $i;
807                                    }
808                                }
809                                # Create the ContainsFeature data.
810                                for my $cellID (keys %cellPegs) {
811                                    my $cellList = $cellPegs{$cellID};
812                                    for my $cellPeg (@$cellList) {
813                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
814                          }                          }
815                      }                      }
816                  }                  }
817              }              }
818          }          }
819                    # Now we need to generate the subsets. The subset names must be concatenated to
820                    # the subsystem name to make them unique keys. There are two types of subsets:
821                    # genome subsets and role subsets. We do the role subsets first.
822                    my @subsetNames = $sub->get_subset_names();
823                    for my $subsetID (@subsetNames) {
824                        # Create the subset record.
825                        my $actualID = "$subsysID:$subsetID";
826                        $loadRoleSubset->Put($actualID);
827                        # Connect the subset to the subsystem.
828                        $loadHasRoleSubset->Put($subsysID, $actualID);
829                        # Connect the subset to its roles.
830                        my @roles = $sub->get_subsetC_roles($subsetID);
831                        for my $roleID (@roles) {
832                            $loadConsistsOfRoles->Put($actualID, $roleID);
833      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
834  }  }
835                    # Next the genome subsets.
836  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
837                    for my $subsetID (@subsetNames) {
838  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
839                        my $actualID = "$subsysID:$subsetID";
840  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
841                        # Connect the subset to the subsystem.
842  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
843  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
844                        my @genomes = $sub->get_subsetR($subsetID);
845  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
846                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
847      Diagram                      }
848      RoleOccursIn                  }
849                }
850  =over 4              # Now we loop through the diagrams. We need to create the diagram records
851                # and link each diagram to its roles. Note that only roles which occur
852  =item RETURNS              # in subsystems (and therefore appear in the %ecToRoles hash) are
853                # included.
854  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) {  
855          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
856          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
857          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 740  Line 860 
860          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
861          my %roleHash = ();          my %roleHash = ();
862          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
863              if (! $roleHash{$role}) {                      if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
864                  $loadRoleOccursIn->Put($role, $map);                          $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
865                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
866              }              }
867          }          }
868      }      }
869                # Before we leave, we must create the Catalyzes table. We start with the reactions,
870                # then use the "ecToRoles" table to convert EC numbers to role IDs.
871                my @reactions = $fig->all_reactions();
872                for my $reactionID (@reactions) {
873                    # Get this reaction's list of roles. The results will be EC numbers.
874                    my @roles = $fig->catalyzed_by($reactionID);
875                    # Loop through the roles, creating catalyzation records.
876                    for my $thisRole (@roles) {
877                        if (exists $ecToRoles{$thisRole}) {
878                            $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
879                        }
880                    }
881                }
882            }
883        }
884      # Finish the load.      # Finish the load.
885      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
886      return $retVal;      return $retVal;
# Line 787  Line 922 
922      my $fig = $self->{fig};      my $fig = $self->{fig};
923      # Get the genome hash.      # Get the genome hash.
924      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
925      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
926      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
927      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
928      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
929            Trace("Loading from existing files.") if T(2);
930        } else {
931            Trace("Generating property data.") if T(2);
932      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
933      my %propertyKeys = ();      my %propertyKeys = ();
934      my $nextID = 1;      my $nextID = 1;
935      # Loop through the genomes.      # Loop through the genomes.
936      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
937          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
938                Trace("Generating properties for $genomeID.") if T(3);
939          # 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
940          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
941          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
942          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
943                my $featureCount = 0;
944                my $propertyCount = 0;
945          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
946          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
947              # 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
948              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
949              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
950                    if (scalar @attributeList) {
951                        $featureCount++;
952                    }
953              # Loop through the attributes.              # Loop through the attributes.
954              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
955                        $propertyCount++;
956                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
957                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
958                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 831  Line 974 
974                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
975              }              }
976          }          }
977                # Update the statistics.
978                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
979                $loadHasProperty->Add("featuresIn", $featureCount);
980                $loadHasProperty->Add("propertiesIn", $propertyCount);
981            }
982      }      }
983      # Finish the load.      # Finish the load.
984      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 871  Line 1019 
1019      my $fig = $self->{fig};      my $fig = $self->{fig};
1020      # Get the genome hash.      # Get the genome hash.
1021      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1022      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1023      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1024      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1025      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1026      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1027      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1028      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1029            Trace("Loading from existing files.") if T(2);
1030        } else {
1031            Trace("Generating annotation data.") if T(2);
1032      # 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
1033      # user records.      # user records.
1034      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 892  Line 1042 
1042      # Loop through the genomes.      # Loop through the genomes.
1043      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1044          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);  
1045              # 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
1046              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1047              my %seenTimestamps = ();              my %seenTimestamps = ();
1048              # Check for a functional assignment.              # Get the genome's annotations.
1049              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1050              if ($func) {              Trace("Processing annotations.") if T(2);
1051                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1052                  # assignment annotation for it.                  # Get the annotation tuple.
1053                  if (! FIG::hypo($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};  
1054                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1055                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1056                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1057                      # stop the substitution search.                      # stop the substitution search.
1058                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 927  Line 1062 
1062                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1063                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1064                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1065                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1066                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1067                              $timestamp++;                      my $keyStamp = $timestamp;
1068                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1069                            $keyStamp++;
1070                          }                          }
1071                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1072                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1073                          # Insure the user exists.                          # Insure the user exists.
1074                          if (! $users{$user}) {                          if (! $users{$user}) {
1075                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 940  Line 1077 
1077                              $users{$user} = 1;                              $users{$user} = 1;
1078                          }                          }
1079                          # Generate the annotation.                          # Generate the annotation.
1080                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1081                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1082                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1083                      } else {                      } else {
# Line 950  Line 1087 
1087                  }                  }
1088              }              }
1089          }          }
     }  
1090      # Finish the load.      # Finish the load.
1091      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1092      return $retVal;      return $retVal;
# Line 991  Line 1127 
1127      my $fig = $self->{fig};      my $fig = $self->{fig};
1128      # Get the genome hash.      # Get the genome hash.
1129      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1130      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1131      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1132      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1133      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1134      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1135            Trace("Loading from existing files.") if T(2);
1136        } else {
1137            Trace("Generating annotation data.") if T(2);
1138      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1139      my %sourceURL = ();      my %sourceURL = ();
1140      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1010  Line 1148 
1148              chomp $line;              chomp $line;
1149              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1150              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1151              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1152                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1153                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1154              }              }
1155              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1156                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1157                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1158                        $sourceDesc{$sourceID} = $sourceID;
1159              }              }
1160          }          }
1161          close TMP;          close TMP;
1162      }      }
1163            # Write the source descriptions.
1164            for my $sourceID (keys %sourceDesc) {
1165                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1166            }
1167        }
1168      # Finish the load.      # Finish the load.
1169      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1170      return $retVal;      return $retVal;
# Line 1060  Line 1204 
1204      my $fig = $self->{fig};      my $fig = $self->{fig};
1205      # Get the genome hash.      # Get the genome hash.
1206      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1207      # 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
1208      # it the key.      # it the key.
1209      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1210      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1211      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1212      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1213      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1214            Trace("Loading from existing files.") if T(2);
1215        } else {
1216            Trace("Generating external data.") if T(2);
1217      # 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.
1218      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1219      my $orgLine;      my $orgLine;
# Line 1097  Line 1243 
1243              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1244          }          }
1245      }      }
1246        }
1247        # Finish the load.
1248        my $retVal = $self->_FinishAll();
1249        return $retVal;
1250    }
1251    
1252    
1253    =head3 LoadReactionData
1254    
1255    C<< my $stats = $spl->LoadReactionData(); >>
1256    
1257    Load the reaction data from FIG into Sprout.
1258    
1259    Reaction data connects reactions to the compounds that participate in them.
1260    
1261    The following relations are loaded by this method.
1262    
1263        Reaction
1264        ReactionURL
1265        Compound
1266        CompoundName
1267        CompoundCAS
1268        IsAComponentOf
1269    
1270    This method proceeds reaction by reaction rather than genome by genome.
1271    
1272    =over 4
1273    
1274    =item RETURNS
1275    
1276    Returns a statistics object for the loads.
1277    
1278    =back
1279    
1280    =cut
1281    #: Return Type $%;
1282    sub LoadReactionData {
1283        # Get this object instance.
1284        my ($self) = @_;
1285        # Get the FIG object.
1286        my $fig = $self->{fig};
1287        # Create load objects for each of the tables we're loading.
1288        my $loadReaction = $self->_TableLoader('Reaction');
1289        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1290        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1291        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1292        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1293        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1294        if ($self->{options}->{loadOnly}) {
1295            Trace("Loading from existing files.") if T(2);
1296        } else {
1297            Trace("Generating annotation data.") if T(2);
1298            # First we create the compounds.
1299            my @compounds = $fig->all_compounds();
1300            for my $cid (@compounds) {
1301                # Check for names.
1302                my @names = $fig->names_of_compound($cid);
1303                # Each name will be given a priority number, starting with 1.
1304                my $prio = 1;
1305                for my $name (@names) {
1306                    $loadCompoundName->Put($cid, $name, $prio++);
1307                }
1308                # Create the main compound record. Note that the first name
1309                # becomes the label.
1310                my $label = (@names > 0 ? $names[0] : $cid);
1311                $loadCompound->Put($cid, $label);
1312                # Check for a CAS ID.
1313                my $cas = $fig->cas($cid);
1314                if ($cas) {
1315                    $loadCompoundCAS->Put($cid, $cas);
1316                }
1317            }
1318            # All the compounds are set up, so we need to loop through the reactions next. First,
1319            # we initialize the discriminator index. This is a single integer used to insure
1320            # duplicate elements in a reaction are not accidentally collapsed.
1321            my $discrim = 0;
1322            my @reactions = $fig->all_reactions();
1323            for my $reactionID (@reactions) {
1324                # Create the reaction record.
1325                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1326                # Compute the reaction's URL.
1327                my $url = HTML::reaction_link($reactionID);
1328                # Put it in the ReactionURL table.
1329                $loadReactionURL->Put($reactionID, $url);
1330                # Now we need all of the reaction's compounds. We get these in two phases,
1331                # substrates first and then products.
1332                for my $product (0, 1) {
1333                    # Get the compounds of the current type for the current reaction. FIG will
1334                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1335                    # have location data in SEED, so it defaults to the empty string.
1336                    my @compounds = $fig->reaction2comp($reactionID, $product);
1337                    for my $compData (@compounds) {
1338                        # Extract the compound data from the current tuple.
1339                        my ($cid, $stoich, $main) = @{$compData};
1340                        # Link the compound to the reaction.
1341                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1342                                                 $product, $stoich);
1343                    }
1344                }
1345            }
1346        }
1347      # Finish the load.      # Finish the load.
1348      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1349      return $retVal;      return $retVal;
# Line 1132  Line 1379 
1379      my $fig = $self->{fig};      my $fig = $self->{fig};
1380      # Get the genome hash.      # Get the genome hash.
1381      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1382      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1383      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1384      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1385            Trace("Loading from existing files.") if T(2);
1386        } else {
1387            Trace("Generating group data.") if T(2);
1388      # Loop through the genomes.      # Loop through the genomes.
1389      my $line;      my $line;
1390      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1151  Line 1400 
1400          }          }
1401          close TMP;          close TMP;
1402      }      }
1403        }
1404        # Finish the load.
1405        my $retVal = $self->_FinishAll();
1406        return $retVal;
1407    }
1408    
1409    =head3 LoadSynonymData
1410    
1411    C<< my $stats = $spl->LoadSynonymData(); >>
1412    
1413    Load the synonym groups into Sprout.
1414    
1415    The following relations are loaded by this method.
1416    
1417        SynonymGroup
1418        IsSynonymGroupFor
1419    
1420    The source information for these relations is taken from the C<maps_to_id> method
1421    of the B<FIG> object. The process starts from the features, so it is possible
1422    that there will be duplicates in the SynonymGroup load file, since the relationship
1423    is one-to-many toward the features. The automatic sort on primary entity relations
1424    will fix this for us.
1425    
1426    =over 4
1427    
1428    =item RETURNS
1429    
1430    Returns a statistics object for the loads.
1431    
1432    =back
1433    
1434    =cut
1435    #: Return Type $%;
1436    sub LoadSynonymData {
1437        # Get this object instance.
1438        my ($self) = @_;
1439        # Get the FIG object.
1440        my $fig = $self->{fig};
1441        # Get the genome hash.
1442        my $genomeHash = $self->{genomes};
1443        # Create a load object for the table we're loading.
1444        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1445        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1446        if ($self->{options}->{loadOnly}) {
1447            Trace("Loading from existing files.") if T(2);
1448        } else {
1449            Trace("Generating synonym group data.") if T(2);
1450            # Loop through the genomes.
1451            for my $genomeID (sort keys %{$genomeHash}) {
1452                Trace("Processing $genomeID.") if T(3);
1453                # Get all of the features for this genome. The only method that does this is
1454                # all_features_detailed, which returns extra baggage that we discard.
1455                my $featureData = $fig->all_features_detailed($genomeID);
1456                my @fids = map { $_->[0] } @{$featureData};
1457                Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
1458                # Loop through the feature IDs.
1459                for my $fid (@fids) {
1460                    # Get the group for this feature.
1461                    my $synonym = $fig->maps_to_id($fid);
1462                    # Only proceed if the synonym is a real group.
1463                    if ($synonym ne $fid) {
1464                        $loadSynonymGroup->Put($synonym);
1465                        $loadIsSynonymGroupFor->Put($synonym, $fid);
1466                    }
1467                }
1468            }
1469        }
1470      # Finish the load.      # Finish the load.
1471      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1472      return $retVal;      return $retVal;
1473  }  }
1474    
1475    
1476  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1477    
1478  =head3 TableLoader  =head3 TableLoader
# Line 1172  Line 1489 
1489    
1490  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1491    
1492  =item rowCount (optional)  =item ignore
1493    
1494  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1495    
1496  =item RETURN  =item RETURN
1497    
# Line 1186  Line 1503 
1503    
1504  sub _TableLoader {  sub _TableLoader {
1505      # Get the parameters.      # Get the parameters.
1506      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1507      # Create the load object.      # Create the load object.
1508      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1509                                   $ignore);
1510      # Cache it in the loader list.      # Cache it in the loader list.
1511      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1512      # Return it to the caller.      # Return it to the caller.
# Line 1222  Line 1540 
1540      my $retVal = Stats->new();      my $retVal = Stats->new();
1541      # Get the loader list.      # Get the loader list.
1542      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1543        # Create a hash to hold the statistics objects, keyed on relation name.
1544        my %loaderHash = ();
1545      # 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
1546      # 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.
1547      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1548            # Get the relation name.
1549            my $relName = $loader->RelName;
1550            # Check the ignore flag.
1551            if ($loader->Ignore) {
1552                Trace("Relation $relName not loaded.") if T(2);
1553            } else {
1554                # Here we really need to finish.
1555                Trace("Finishing $relName.") if T(2);
1556          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1557                $loaderHash{$relName} = $stats;
1558            }
1559        }
1560        # Now we loop through again, actually loading the tables. We want to finish before
1561        # loading so that if something goes wrong at this point, all the load files are usable
1562        # and we don't have to redo all that work.
1563        for my $relName (sort keys %loaderHash) {
1564            # Get the statistics for this relation.
1565            my $stats = $loaderHash{$relName};
1566            # Check for a database load.
1567            if ($self->{options}->{dbLoad}) {
1568                # Here we want to use the load file just created to load the database.
1569                Trace("Loading relation $relName.") if T(2);
1570                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1571                # Accumulate the statistics from the DB load.
1572                $stats->Accumulate($newStats);
1573            }
1574          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1575          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1576      }      }
1577      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.7  
changed lines
  Added in v.1.54

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3