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

Diff of /Sprout/SproutLoad.pm

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

revision 1.6, Sun Sep 11 17:09:46 2005 UTC revision 1.61, Sun Jul 30 01:41:34 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 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 ($type eq 'ARRAY') {
# Line 148  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($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                # 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, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
501                    # Check for duplicates.
502                    if ($featureID eq $oldFeatureID) {
503                        Trace("Duplicate feature $featureID found.") if T(1);
504                    } else {
505                        $oldFeatureID = $featureID;
506                        # Count this feature.
507                        $loadFeature->Add("featureIn");
508              # Create the feature record.              # Create the feature record.
509              $loadFeature->Put("$genomeID:$featureID", 1, $type);                      $loadFeature->Put($featureID, 1, $type);
510                        # Link it to the parent genome.
511                        $loadHasFeature->Put($genomeID, $featureID, $type);
512              # Create the aliases.              # Create the aliases.
513              for my $alias (split /\s*,\s*/, $aliases) {                      for my $alias ($fig->feature_aliases($featureID)) {
514                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
515              }              }
516              # Get the links.              # Get the links.
# Line 475  Line 536 
536              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
537              # for Sprout.              # for Sprout.
538              my @locationList = split /\s*,\s*/, $locations;              my @locationList = split /\s*,\s*/, $locations;
539                        # Create the location position indicator.
540                        my $i = 1;
541              # Loop through the locations.              # Loop through the locations.
542              for my $location (@locationList) {              for my $location (@locationList) {
543                  # Parse the location.                  # Parse the location.
544                  my $locObject = BasicLocation->new($location);                          my $locObject = BasicLocation->new("$genomeID:$location");
545                  # Split it into a list of chunks.                  # Split it into a list of chunks.
546                  my @locOList = ();                  my @locOList = ();
547                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 488  Line 551 
551                  push @locOList, $locObject;                  push @locOList, $locObject;
552                  # Loop through the chunks, creating IsLocatedIn records. The variable                  # Loop through the chunks, creating IsLocatedIn records. The variable
553                  # "$i" will be used to keep the location index.                  # "$i" will be used to keep the location index.
                 my $i = 1;  
554                  for my $locChunk (@locOList) {                  for my $locChunk (@locOList) {
555                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,
556                                            $locChunk->Dir, $locChunk->Length, $i);                                            $locChunk->Dir, $locChunk->Length, $i);
# Line 497  Line 559 
559              }              }
560          }          }
561      }      }
562            }
563        }
564      # Finish the loads.      # Finish the loads.
565      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
566      return $retVal;      return $retVal;
# Line 533  Line 597 
597      my $fig = $self->{fig};      my $fig = $self->{fig};
598      # Get the table of genome IDs.      # Get the table of genome IDs.
599      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
600      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
601      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
602                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
603      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
604        } else {
605            Trace("Generating BBH data.") if T(2);
606      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
607      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
608          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 564  Line 628 
628              }              }
629          }          }
630      }      }
631        }
632      # Finish the loads.      # Finish the loads.
633      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
634      return $retVal;      return $retVal;
# Line 584  Line 649 
649  The following relations are loaded by this method.  The following relations are loaded by this method.
650    
651      Subsystem      Subsystem
652        SubsystemClass
653      Role      Role
654        RoleEC
655      SSCell      SSCell
656      ContainsFeature      ContainsFeature
657      IsGenomeOf      IsGenomeOf
# Line 592  Line 659 
659      OccursInSubsystem      OccursInSubsystem
660      ParticipatesIn      ParticipatesIn
661      HasSSCell      HasSSCell
662        ConsistsOfRoles
663        RoleSubset
664        HasRoleSubset
665        ConsistsOfGenomes
666        GenomeSubset
667        HasGenomeSubset
668        Catalyzes
669        Diagram
670        RoleOccursIn
671    
672  =over 4  =over 4
673    
# Line 601  Line 677 
677    
678  =back  =back
679    
 B<TO DO>  
   
 Generate RoleName table?  
   
680  =cut  =cut
681  #: Return Type $%;  #: Return Type $%;
682  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 618  Line 690 
690      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
691      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
692      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
693      my $subsysCount = @subsysIDs;      # Get the map list.
694      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
695      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
696      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
697      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
698      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
699      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
700      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
701      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
702      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
703      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
704      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
705      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
706        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
707        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
708        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
709        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
710        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
711        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
712        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
713        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
714        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
715        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
716        if ($self->{options}->{loadOnly}) {
717            Trace("Loading from existing files.") if T(2);
718        } else {
719            Trace("Generating subsystem data.") if T(2);
720            # This hash will contain the role for each EC. When we're done, this
721            # information will be used to generate the Catalyzes table.
722            my %ecToRoles = ();
723      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
724      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
725      # role hash. The hash tracks each role ID so that we don't create      # role hash. The hash tracks each role ID so that we don't create
726      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
727            # and memorize up the reactions.
728            my ($genomeID, $roleID);
729      my %roleData = ();      my %roleData = ();
730      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
731                # Get the subsystem object.
732                my $sub = $fig->get_subsystem($subsysID);
733                # Only proceed if the subsystem has a spreadsheet.
734                if (! $sub->{empty_ss}) {
735          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
736          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
737          # Create the subsystem record.          # Create the subsystem record.
738          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
739          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
740          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
741          # Connect the roles to the subsystem. If a role is new, we create                  my $class = $fig->subsystem_classification($subsysID);
742          # a role record for it.                  if ($class) {
743          for my $roleID (@roles) {                      $loadSubsystemClass->Put($subsysID, $class);
744                    }
745                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
746                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
747                        # Connect to this role.
748              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
749              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
750                        # If it's a new role, add it to the role table.
751              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
752                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
753                            my $abbr = $sub->get_role_abbr($col);
754                            # Add the role.
755                            $loadRole->Put($roleID, $abbr);
756                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
757                            # Check for an EC number.
758                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
759                                my $ec = $1;
760                                $loadRoleEC->Put($roleID, $ec);
761                                $ecToRoles{$ec} = $roleID;
762                            }
763              }              }
764          }          }
765          # 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
766          # 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
767          # get the genomes on the sheet.                  # to actually create the roles as we find them.
768          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
769          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
770          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
771              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
772                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
773                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
774                            my $cellCount = 0;
775                            # Create a list for the PEGs we find. This list will be used
776                            # to generate cluster numbers.
777                            my @pegsFound = ();
778                            # Create a hash that maps spreadsheet IDs to PEGs. We will
779                            # use this to generate the ContainsFeature data after we have
780                            # the cluster numbers.
781                            my %cellPegs = ();
782                            # Get the genome's variant code for this subsystem.
783                            my $variantCode = $sub->get_variant_code($row);
784                  # 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
785                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
786                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
787                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
788                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
789                      # Only proceed if features exist.                      # Only proceed if features exist.
790                      if (@pegs > 0) {                      if (@pegs > 0) {
791                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
792                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
793                                    my $cellID = "$subsysID:$genomeID:$col";
794                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
795                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
796                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
797                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
798                          # Attach the features to it.                                  # Remember its features.
799                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
800                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
801                                    $pegCount += @pegs;
802                                }
803                            }
804                            # If we found some cells for this genome, we need to compute clusters and
805                            # denote it participates in the subsystem.
806                            if ($pegCount > 0) {
807                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
808                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
809                                # Create a hash mapping PEG IDs to cluster numbers.
810                                # We default to -1 for all of them.
811                                my %clusterOf = map { $_ => -1 } @pegsFound;
812                                # Partition the PEGs found into clusters.
813                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
814                                for (my $i = 0; $i <= $#clusters; $i++) {
815                                    my $subList = $clusters[$i];
816                                    for my $peg (@{$subList}) {
817                                        $clusterOf{$peg} = $i;
818                                    }
819                                }
820                                # Create the ContainsFeature data.
821                                for my $cellID (keys %cellPegs) {
822                                    my $cellList = $cellPegs{$cellID};
823                                    for my $cellPeg (@$cellList) {
824                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
825                          }                          }
826                      }                      }
827                  }                  }
828              }              }
829          }          }
830                    # Now we need to generate the subsets. The subset names must be concatenated to
831                    # the subsystem name to make them unique keys. There are two types of subsets:
832                    # genome subsets and role subsets. We do the role subsets first.
833                    my @subsetNames = $sub->get_subset_names();
834                    for my $subsetID (@subsetNames) {
835                        # Create the subset record.
836                        my $actualID = "$subsysID:$subsetID";
837                        $loadRoleSubset->Put($actualID);
838                        # Connect the subset to the subsystem.
839                        $loadHasRoleSubset->Put($subsysID, $actualID);
840                        # Connect the subset to its roles.
841                        my @roles = $sub->get_subsetC_roles($subsetID);
842                        for my $roleID (@roles) {
843                            $loadConsistsOfRoles->Put($actualID, $roleID);
844      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
845  }  }
846                    # Next the genome subsets.
847  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
848                    for my $subsetID (@subsetNames) {
849  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
850                        my $actualID = "$subsysID:$subsetID";
851  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
852                        # Connect the subset to the subsystem.
853  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
854  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
855                        my @genomes = $sub->get_subsetR($subsetID);
856  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
857                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
858      Diagram                      }
859      RoleOccursIn                  }
860                }
861  =over 4          }
862            # Now we loop through the diagrams. We need to create the diagram records
863  =item RETURNS          # and link each diagram to its roles. Note that only roles which occur
864            # in subsystems (and therefore appear in the %ecToRoles hash) are
865  Returns a statistics object for the loads.          # included.
866            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) {  
867          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
868          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
869          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 740  Line 872 
872          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
873          my %roleHash = ();          my %roleHash = ();
874          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
875              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
876                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
877                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
878              }              }
879          }          }
880      }      }
881            # Before we leave, we must create the Catalyzes table. We start with the reactions,
882            # then use the "ecToRoles" table to convert EC numbers to role IDs.
883            my @reactions = $fig->all_reactions();
884            for my $reactionID (@reactions) {
885                # Get this reaction's list of roles. The results will be EC numbers.
886                my @roles = $fig->catalyzed_by($reactionID);
887                # Loop through the roles, creating catalyzation records.
888                for my $thisRole (@roles) {
889                    if (exists $ecToRoles{$thisRole}) {
890                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
891                    }
892                }
893            }
894        }
895      # Finish the load.      # Finish the load.
896      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
897      return $retVal;      return $retVal;
# Line 787  Line 933 
933      my $fig = $self->{fig};      my $fig = $self->{fig};
934      # Get the genome hash.      # Get the genome hash.
935      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
936      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
937      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
938      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
939      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
940            Trace("Loading from existing files.") if T(2);
941        } else {
942            Trace("Generating property data.") if T(2);
943      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
944      my %propertyKeys = ();      my %propertyKeys = ();
945      my $nextID = 1;      my $nextID = 1;
946      # Loop through the genomes.      # Loop through the genomes.
947      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
948          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
949                Trace("Generating properties for $genomeID.") if T(3);
950          # 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
951          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
952          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
953          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
954                my $featureCount = 0;
955                my $propertyCount = 0;
956          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
957          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
958              # 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
959              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
960              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
961                    if (scalar @attributeList) {
962                        $featureCount++;
963                    }
964              # Loop through the attributes.              # Loop through the attributes.
965              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
966                        $propertyCount++;
967                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
968                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
969                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 831  Line 985 
985                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
986              }              }
987          }          }
988                # Update the statistics.
989                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
990                $loadHasProperty->Add("featuresIn", $featureCount);
991                $loadHasProperty->Add("propertiesIn", $propertyCount);
992            }
993      }      }
994      # Finish the load.      # Finish the load.
995      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 871  Line 1030 
1030      my $fig = $self->{fig};      my $fig = $self->{fig};
1031      # Get the genome hash.      # Get the genome hash.
1032      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1033      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1034      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1035      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1036      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1037      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1038      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1039      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1040            Trace("Loading from existing files.") if T(2);
1041        } else {
1042            Trace("Generating annotation data.") if T(2);
1043      # 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
1044      # user records.      # user records.
1045      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 892  Line 1053 
1053      # Loop through the genomes.      # Loop through the genomes.
1054      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1055          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);  
1056              # 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
1057              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1058              my %seenTimestamps = ();              my %seenTimestamps = ();
1059              # Check for a functional assignment.              # Get the genome's annotations.
1060              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1061              if ($func) {              Trace("Processing annotations.") if T(2);
1062                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1063                  # assignment annotation for it.                  # Get the annotation tuple.
1064                  if (! FIG::hypo($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};  
1065                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1066                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1067                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1068                      # stop the substitution search.                      # stop the substitution search.
1069                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 927  Line 1073 
1073                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1074                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1075                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1076                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1077                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1078                              $timestamp++;                      my $keyStamp = $timestamp;
1079                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1080                            $keyStamp++;
1081                          }                          }
1082                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1083                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1084                          # Insure the user exists.                          # Insure the user exists.
1085                          if (! $users{$user}) {                          if (! $users{$user}) {
1086                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 940  Line 1088 
1088                              $users{$user} = 1;                              $users{$user} = 1;
1089                          }                          }
1090                          # Generate the annotation.                          # Generate the annotation.
1091                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1092                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1093                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1094                      } else {                      } else {
# Line 950  Line 1098 
1098                  }                  }
1099              }              }
1100          }          }
     }  
1101      # Finish the load.      # Finish the load.
1102      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1103      return $retVal;      return $retVal;
# Line 991  Line 1138 
1138      my $fig = $self->{fig};      my $fig = $self->{fig};
1139      # Get the genome hash.      # Get the genome hash.
1140      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1141      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1142      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1143      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1144      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1145      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1146            Trace("Loading from existing files.") if T(2);
1147        } else {
1148            Trace("Generating annotation data.") if T(2);
1149      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1150      my %sourceURL = ();      my %sourceURL = ();
1151      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1010  Line 1159 
1159              chomp $line;              chomp $line;
1160              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1161              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1162              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1163                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1164                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1165              }              }
1166              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1167                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1168                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1169                        $sourceDesc{$sourceID} = $sourceID;
1170              }              }
1171          }          }
1172          close TMP;          close TMP;
1173      }      }
1174            # Write the source descriptions.
1175            for my $sourceID (keys %sourceDesc) {
1176                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1177            }
1178        }
1179      # Finish the load.      # Finish the load.
1180      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1181      return $retVal;      return $retVal;
# Line 1060  Line 1215 
1215      my $fig = $self->{fig};      my $fig = $self->{fig};
1216      # Get the genome hash.      # Get the genome hash.
1217      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1218      # 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
1219      # it the key.      # it the key.
1220      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1221      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1222      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1223      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1224      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1225            Trace("Loading from existing files.") if T(2);
1226        } else {
1227            Trace("Generating external data.") if T(2);
1228      # 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.
1229      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1230      my $orgLine;      my $orgLine;
1231      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1232          # Clean the input line.          # Clean the input line.
# Line 1081  Line 1238 
1238      close ORGS;      close ORGS;
1239      # Now the function file.      # Now the function file.
1240      my $funcLine;      my $funcLine;
1241      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1242      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1243          # Clean the line ending.          # Clean the line ending.
1244          chomp $funcLine;          chomp $funcLine;
# Line 1097  Line 1254 
1254              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1255          }          }
1256      }      }
1257        }
1258        # Finish the load.
1259        my $retVal = $self->_FinishAll();
1260        return $retVal;
1261    }
1262    
1263    
1264    =head3 LoadReactionData
1265    
1266    C<< my $stats = $spl->LoadReactionData(); >>
1267    
1268    Load the reaction data from FIG into Sprout.
1269    
1270    Reaction data connects reactions to the compounds that participate in them.
1271    
1272    The following relations are loaded by this method.
1273    
1274        Reaction
1275        ReactionURL
1276        Compound
1277        CompoundName
1278        CompoundCAS
1279        IsAComponentOf
1280    
1281    This method proceeds reaction by reaction rather than genome by genome.
1282    
1283    =over 4
1284    
1285    =item RETURNS
1286    
1287    Returns a statistics object for the loads.
1288    
1289    =back
1290    
1291    =cut
1292    #: Return Type $%;
1293    sub LoadReactionData {
1294        # Get this object instance.
1295        my ($self) = @_;
1296        # Get the FIG object.
1297        my $fig = $self->{fig};
1298        # Create load objects for each of the tables we're loading.
1299        my $loadReaction = $self->_TableLoader('Reaction');
1300        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1301        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1302        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1303        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1304        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1305        if ($self->{options}->{loadOnly}) {
1306            Trace("Loading from existing files.") if T(2);
1307        } else {
1308            Trace("Generating annotation data.") if T(2);
1309            # First we create the compounds.
1310            my @compounds = $fig->all_compounds();
1311            for my $cid (@compounds) {
1312                # Check for names.
1313                my @names = $fig->names_of_compound($cid);
1314                # Each name will be given a priority number, starting with 1.
1315                my $prio = 1;
1316                for my $name (@names) {
1317                    $loadCompoundName->Put($cid, $name, $prio++);
1318                }
1319                # Create the main compound record. Note that the first name
1320                # becomes the label.
1321                my $label = (@names > 0 ? $names[0] : $cid);
1322                $loadCompound->Put($cid, $label);
1323                # Check for a CAS ID.
1324                my $cas = $fig->cas($cid);
1325                if ($cas) {
1326                    $loadCompoundCAS->Put($cid, $cas);
1327                }
1328            }
1329            # All the compounds are set up, so we need to loop through the reactions next. First,
1330            # we initialize the discriminator index. This is a single integer used to insure
1331            # duplicate elements in a reaction are not accidentally collapsed.
1332            my $discrim = 0;
1333            my @reactions = $fig->all_reactions();
1334            for my $reactionID (@reactions) {
1335                # Create the reaction record.
1336                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1337                # Compute the reaction's URL.
1338                my $url = HTML::reaction_link($reactionID);
1339                # Put it in the ReactionURL table.
1340                $loadReactionURL->Put($reactionID, $url);
1341                # Now we need all of the reaction's compounds. We get these in two phases,
1342                # substrates first and then products.
1343                for my $product (0, 1) {
1344                    # Get the compounds of the current type for the current reaction. FIG will
1345                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1346                    # have location data in SEED, so it defaults to the empty string.
1347                    my @compounds = $fig->reaction2comp($reactionID, $product);
1348                    for my $compData (@compounds) {
1349                        # Extract the compound data from the current tuple.
1350                        my ($cid, $stoich, $main) = @{$compData};
1351                        # Link the compound to the reaction.
1352                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1353                                                 $product, $stoich);
1354                    }
1355                }
1356            }
1357        }
1358      # Finish the load.      # Finish the load.
1359      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1360      return $retVal;      return $retVal;
# Line 1132  Line 1390 
1390      my $fig = $self->{fig};      my $fig = $self->{fig};
1391      # Get the genome hash.      # Get the genome hash.
1392      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1393      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1394      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1395      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1396            Trace("Loading from existing files.") if T(2);
1397        } else {
1398            Trace("Generating group data.") if T(2);
1399      # Loop through the genomes.      # Loop through the genomes.
1400      my $line;      my $line;
1401      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1151  Line 1411 
1411          }          }
1412          close TMP;          close TMP;
1413      }      }
1414        }
1415        # Finish the load.
1416        my $retVal = $self->_FinishAll();
1417        return $retVal;
1418    }
1419    
1420    =head3 LoadSynonymData
1421    
1422    C<< my $stats = $spl->LoadSynonymData(); >>
1423    
1424    Load the synonym groups into Sprout.
1425    
1426    The following relations are loaded by this method.
1427    
1428        SynonymGroup
1429        IsSynonymGroupFor
1430    
1431    The source information for these relations is taken from the C<maps_to_id> method
1432    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1433    SQL against the FIG database.
1434    
1435    =over 4
1436    
1437    =item RETURNS
1438    
1439    Returns a statistics object for the loads.
1440    
1441    =back
1442    
1443    =cut
1444    #: Return Type $%;
1445    sub LoadSynonymData {
1446        # Get this object instance.
1447        my ($self) = @_;
1448        # Get the FIG object.
1449        my $fig = $self->{fig};
1450        # Get the genome hash.
1451        my $genomeHash = $self->{genomes};
1452        # Create a load object for the table we're loading.
1453        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1454        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1455        if ($self->{options}->{loadOnly}) {
1456            Trace("Loading from existing files.") if T(2);
1457        } else {
1458            Trace("Generating synonym group data.") if T(2);
1459            # Get the database handle.
1460            my $dbh = $fig->db_handle();
1461            # Ask for the synonyms.
1462            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1463            my $result = $sth->execute();
1464            if (! defined($result)) {
1465                Confess("Database error in Synonym load: " . $sth->errstr());
1466            } else {
1467                # Remember the current synonym.
1468                my $current_syn = "";
1469                # Count the features.
1470                my $featureCount = 0;
1471                # Loop through the synonym/peg pairs.
1472                while (my @row = $sth->fetchrow()) {
1473                    # Get the synonym ID and feature ID.
1474                    my ($syn_id, $peg) = @row;
1475                    # Insure it's for one of our genomes.
1476                    my $genomeID = FIG::genome_of($peg);
1477                    if (exists $genomeHash->{$genomeID}) {
1478                        # Verify the synonym.
1479                        if ($syn_id ne $current_syn) {
1480                            # It's new, so put it in the group table.
1481                            $loadSynonymGroup->Put($syn_id);
1482                            $current_syn = $syn_id;
1483                        }
1484                        # Connect the synonym to the peg.
1485                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1486                        # Count this feature.
1487                        $featureCount++;
1488                        if ($featureCount % 1000 == 0) {
1489                            Trace("$featureCount features processed.") if T(3);
1490                        }
1491                    }
1492                }
1493            }
1494        }
1495        # Finish the load.
1496        my $retVal = $self->_FinishAll();
1497        return $retVal;
1498    }
1499    
1500    =head3 LoadFamilyData
1501    
1502    C<< my $stats = $spl->LoadFamilyData(); >>
1503    
1504    Load the protein families into Sprout.
1505    
1506    The following relations are loaded by this method.
1507    
1508        Family
1509        ContainsFeature
1510    
1511    The source information for these relations is taken from the C<families_for_protein>,
1512    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1513    
1514    =over 4
1515    
1516    =item RETURNS
1517    
1518    Returns a statistics object for the loads.
1519    
1520    =back
1521    
1522    =cut
1523    #: Return Type $%;
1524    sub LoadFamilyData {
1525        # Get this object instance.
1526        my ($self) = @_;
1527        # Get the FIG object.
1528        my $fig = $self->{fig};
1529        # Get the genome hash.
1530        my $genomeHash = $self->{genomes};
1531        # Create load objects for the tables we're loading.
1532        my $loadFamily = $self->_TableLoader('Family');
1533        my $loadContainsFeature = $self->_TableLoader('ContainsFeature');
1534        if ($self->{options}->{loadOnly}) {
1535            Trace("Loading from existing files.") if T(2);
1536        } else {
1537            Trace("Generating family data.") if T(2);
1538            # Create a hash for the family IDs.
1539            my %familyHash = ();
1540            # Loop through the genomes.
1541            for my $genomeID (sort keys %{$genomeHash}) {
1542                Trace("Processing features for $genomeID.") if T(2);
1543                # Loop through this genome's PEGs.
1544                for my $fid ($fig->all_features($genomeID, "peg")) {
1545                    $loadContainsFeature->Add("features", 1);
1546                    # Get this feature's families.
1547                    my @families = $fig->families_for_protein($fid);
1548                    # Loop through the families, connecting them to the feature.
1549                    for my $family (@families) {
1550                        $loadContainsFeature->Put($family, $fid);
1551                        # If this is a new family, create a record for it.
1552                        if (! exists $familyHash{$family}) {
1553                            $loadFamily->Add("families", 1);
1554                            my $size = $fig->sz_family($family);
1555                            my $func = $fig->family_function($family);
1556                            $loadFamily->Put($family, $size, $func);
1557                        }
1558                    }
1559                }
1560            }
1561        }
1562      # Finish the load.      # Finish the load.
1563      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1564      return $retVal;      return $retVal;
# Line 1172  Line 1580 
1580    
1581  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1582    
1583  =item rowCount (optional)  =item ignore
1584    
1585  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1586    
1587  =item RETURN  =item RETURN
1588    
# Line 1186  Line 1594 
1594    
1595  sub _TableLoader {  sub _TableLoader {
1596      # Get the parameters.      # Get the parameters.
1597      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1598      # Create the load object.      # Create the load object.
1599      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1600                                   $ignore);
1601      # Cache it in the loader list.      # Cache it in the loader list.
1602      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1603      # Return it to the caller.      # Return it to the caller.
# Line 1222  Line 1631 
1631      my $retVal = Stats->new();      my $retVal = Stats->new();
1632      # Get the loader list.      # Get the loader list.
1633      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1634        # Create a hash to hold the statistics objects, keyed on relation name.
1635        my %loaderHash = ();
1636      # 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
1637      # 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.
1638      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1639            # Get the relation name.
1640            my $relName = $loader->RelName;
1641            # Check the ignore flag.
1642            if ($loader->Ignore) {
1643                Trace("Relation $relName not loaded.") if T(2);
1644            } else {
1645                # Here we really need to finish.
1646                Trace("Finishing $relName.") if T(2);
1647          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1648                $loaderHash{$relName} = $stats;
1649            }
1650        }
1651        # Now we loop through again, actually loading the tables. We want to finish before
1652        # loading so that if something goes wrong at this point, all the load files are usable
1653        # and we don't have to redo all that work.
1654        for my $relName (sort keys %loaderHash) {
1655            # Get the statistics for this relation.
1656            my $stats = $loaderHash{$relName};
1657            # Check for a database load.
1658            if ($self->{options}->{dbLoad}) {
1659                # Here we want to use the load file just created to load the database.
1660                Trace("Loading relation $relName.") if T(2);
1661                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1662                # Accumulate the statistics from the DB load.
1663                $stats->Accumulate($newStats);
1664            }
1665          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1666          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1667      }      }
1668      # Return the load statistics.      # Return the load statistics.
Legend:
Removed from v.1.6  
changed lines
  Added in v.1.61
MCS Webmaster
 ViewVC Help
Powered by ViewVC 1.0.3