[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 1.51, Mon Jul 10 21:12:51 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 329  Line 370 
370              Trace("Processing PEG $peg1 for $genome.") if T(4);              Trace("Processing PEG $peg1 for $genome.") if T(4);
371              # Get a list of the coupled PEGs.              # Get a list of the coupled PEGs.
372              my @couplings = $fig->coupled_to($peg1);              my @couplings = $fig->coupled_to($peg1);
373                    Trace(scalar(@couplings) . " couplings found for $peg1.") if T(4);
374              # For each coupled PEG, we need to verify that a coupling already              # For each coupled PEG, we need to verify that a coupling already
375              # exists. If not, we have to create one.              # exists. If not, we have to create one.
376              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
377                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
378                  # Compute the coupling ID.                  # Compute the coupling ID.
379                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
380                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
381                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
382                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 362  Line 404 
404                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
405                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
406                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
407                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
408                              # the hash makes it to the output.                              # the hash makes it to the output.
409                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
410                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 370  Line 412 
412                          }                          }
413                      }                      }
414                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
415                                # Get the ID for this evidence.
416                                $pchID++;
417                          # Create the evidence record.                          # Create the evidence record.
418                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
419                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
420                          # Connect it to the coupling.                          # Connect it to the coupling.
421                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
422                          # Connect it to the features.                          # Connect it to the features.
423                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
424                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 1);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
425                            }
426                      }                      }
427                  }                  }
428              }              }
# Line 404  Line 449 
449      FeatureTranslation      FeatureTranslation
450      FeatureUpstream      FeatureUpstream
451      IsLocatedIn      IsLocatedIn
452        HasFeature
453    
454  =over 4  =over 4
455    
# Line 422  Line 468 
468      my $fig = $self->{fig};      my $fig = $self->{fig};
469      # Get the table of genome IDs.      # Get the table of genome IDs.
470      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
471      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
472      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
473      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
474      my $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
475      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
476      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
477      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
478        my $loadHasFeature = $self->_TableLoader('HasFeature');
479      # 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
480      # locations.      # locations.
481      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
482      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
483            Trace("Loading from existing files.") if T(2);
484        } else {
485            Trace("Generating feature data.") if T(2);
486      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
487      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
488          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
# Line 445  Line 493 
493          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
494              $loadFeature->Add("featureIn");              $loadFeature->Add("featureIn");
495              # Split the tuple.              # Split the tuple.
496              my ($featureID, $locations, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureData};
497              # Create the feature record.              # Create the feature record.
498              $loadFeature->Put($featureID, 1, $type);              $loadFeature->Put($featureID, 1, $type);
499                    # Link it to the parent genome.
500                    $loadHasFeature->Put($genomeID, $featureID, $type);
501              # Create the aliases.              # Create the aliases.
502              for my $alias (split /\s*,\s*/, $aliases) {                  for my $alias ($fig->feature_aliases($featureID)) {
503                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
504              }              }
505              # Get the links.              # Get the links.
# Line 475  Line 525 
525              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
526              # for Sprout.              # for Sprout.
527              my @locationList = split /\s*,\s*/, $locations;              my @locationList = split /\s*,\s*/, $locations;
528                    # Create the location position indicator.
529                    my $i = 1;
530              # Loop through the locations.              # Loop through the locations.
531              for my $location (@locationList) {              for my $location (@locationList) {
532                  # Parse the location.                  # Parse the location.
533                  my $locObject = BasicLocation->new($location);                      my $locObject = BasicLocation->new("$genomeID:$location");
534                  # Split it into a list of chunks.                  # Split it into a list of chunks.
535                  my @locOList = ();                  my @locOList = ();
536                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 488  Line 540 
540                  push @locOList, $locObject;                  push @locOList, $locObject;
541                  # Loop through the chunks, creating IsLocatedIn records. The variable                  # Loop through the chunks, creating IsLocatedIn records. The variable
542                  # "$i" will be used to keep the location index.                  # "$i" will be used to keep the location index.
                 my $i = 1;  
543                  for my $locChunk (@locOList) {                  for my $locChunk (@locOList) {
544                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,
545                                            $locChunk->Dir, $locChunk->Length, $i);                                            $locChunk->Dir, $locChunk->Length, $i);
# Line 497  Line 548 
548              }              }
549          }          }
550      }      }
551        }
552      # Finish the loads.      # Finish the loads.
553      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
554      return $retVal;      return $retVal;
# Line 533  Line 585 
585      my $fig = $self->{fig};      my $fig = $self->{fig};
586      # Get the table of genome IDs.      # Get the table of genome IDs.
587      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
588      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
589      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
590                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
591      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
592        } else {
593            Trace("Generating BBH data.") if T(2);
594      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
595      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
596          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
# Line 564  Line 616 
616              }              }
617          }          }
618      }      }
619        }
620      # Finish the loads.      # Finish the loads.
621      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
622      return $retVal;      return $retVal;
# Line 584  Line 637 
637  The following relations are loaded by this method.  The following relations are loaded by this method.
638    
639      Subsystem      Subsystem
640        SubsystemClass
641      Role      Role
642        RoleEC
643      SSCell      SSCell
644      ContainsFeature      ContainsFeature
645      IsGenomeOf      IsGenomeOf
# Line 592  Line 647 
647      OccursInSubsystem      OccursInSubsystem
648      ParticipatesIn      ParticipatesIn
649      HasSSCell      HasSSCell
650        ConsistsOfRoles
651        RoleSubset
652        HasRoleSubset
653        ConsistsOfGenomes
654        GenomeSubset
655        HasGenomeSubset
656        Catalyzes
657        Diagram
658        RoleOccursIn
659    
660  =over 4  =over 4
661    
# Line 601  Line 665 
665    
666  =back  =back
667    
 B<TO DO>  
   
 Generate RoleName table?  
   
668  =cut  =cut
669  #: Return Type $%;  #: Return Type $%;
670  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 618  Line 678 
678      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
679      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
680      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
681      my $subsysCount = @subsysIDs;      # Get the map list.
682      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
683      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
684      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
685      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
686      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
687      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
688      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
689      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
690      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
691      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
692      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
693      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
694        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
695        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
696        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
697        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
698        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
699        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
700        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
701        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
702        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
703        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
704        if ($self->{options}->{loadOnly}) {
705            Trace("Loading from existing files.") if T(2);
706        } else {
707            Trace("Generating subsystem data.") if T(2);
708            # This hash will contain the role for each EC. When we're done, this
709            # information will be used to generate the Catalyzes table.
710            my %ecToRoles = ();
711      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
712      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
713      # 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
714      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
715            # and memorize up the reactions.
716            my ($genomeID, $roleID);
717      my %roleData = ();      my %roleData = ();
718      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
719                # Get the subsystem object.
720                my $sub = $fig->get_subsystem($subsysID);
721                # Only proceed if the subsystem has a spreadsheet.
722                if (! $sub->{empty_ss}) {
723          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
724          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
725          # Create the subsystem record.          # Create the subsystem record.
726          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
727          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
728          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
729          # Connect the roles to the subsystem. If a role is new, we create                  my $class = $fig->subsystem_classification($subsysID);
730          # a role record for it.                  if ($class) {
731          for my $roleID (@roles) {                      $loadSubsystemClass->Put($subsysID, $class);
732                    }
733                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
734                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
735                        # Connect to this role.
736              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
737              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
738                        # If it's a new role, add it to the role table.
739              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
740                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
741                            my $abbr = $sub->get_role_abbr($col);
742                            # Add the role.
743                            $loadRole->Put($roleID, $abbr);
744                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
745                            # Check for an EC number.
746                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
747                                my $ec = $1;
748                                $loadRoleEC->Put($roleID, $ec);
749                                $ecToRoles{$ec} = $roleID;
750                            }
751              }              }
752          }          }
753          # 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
754          # 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
755          # get the genomes on the sheet.                  # to actually create the roles as we find them.
756          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
757          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
758          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
759              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
760                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
761                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
762                            my $cellCount = 0;
763                            # Create a list for the PEGs we find. This list will be used
764                            # to generate cluster numbers.
765                            my @pegsFound = ();
766                            # Create a hash that maps spreadsheet IDs to PEGs. We will
767                            # use this to generate the ContainsFeature data after we have
768                            # the cluster numbers.
769                            my %cellPegs = ();
770                            # Get the genome's variant code for this subsystem.
771                            my $variantCode = $sub->get_variant_code($row);
772                  # 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
773                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
774                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
775                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
776                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
777                      # Only proceed if features exist.                      # Only proceed if features exist.
778                      if (@pegs > 0) {                      if (@pegs > 0) {
779                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
780                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
781                                    my $cellID = "$subsysID:$genomeID:$col";
782                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
783                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
784                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
785                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
786                          # Attach the features to it.                                  # Remember its features.
787                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
788                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
789                                    $pegCount += @pegs;
790                                }
791                            }
792                            # If we found some cells for this genome, we need to compute clusters and
793                            # denote it participates in the subsystem.
794                            if ($pegCount > 0) {
795                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
796                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
797                                # Create a hash mapping PEG IDs to cluster numbers.
798                                # We default to -1 for all of them.
799                                my %clusterOf = map { $_ => -1 } @pegsFound;
800                                # Partition the PEGs found into clusters.
801                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
802                                for (my $i = 0; $i <= $#clusters; $i++) {
803                                    my $subList = $clusters[$i];
804                                    for my $peg (@{$subList}) {
805                                        $clusterOf{$peg} = $i;
806                                    }
807                                }
808                                # Create the ContainsFeature data.
809                                for my $cellID (keys %cellPegs) {
810                                    my $cellList = $cellPegs{$cellID};
811                                    for my $cellPeg (@$cellList) {
812                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
813                          }                          }
814                      }                      }
815                  }                  }
816              }              }
817          }          }
818                    # Now we need to generate the subsets. The subset names must be concatenated to
819                    # the subsystem name to make them unique keys. There are two types of subsets:
820                    # genome subsets and role subsets. We do the role subsets first.
821                    my @subsetNames = $sub->get_subset_names();
822                    for my $subsetID (@subsetNames) {
823                        # Create the subset record.
824                        my $actualID = "$subsysID:$subsetID";
825                        $loadRoleSubset->Put($actualID);
826                        # Connect the subset to the subsystem.
827                        $loadHasRoleSubset->Put($subsysID, $actualID);
828                        # Connect the subset to its roles.
829                        my @roles = $sub->get_subsetC_roles($subsetID);
830                        for my $roleID (@roles) {
831                            $loadConsistsOfRoles->Put($actualID, $roleID);
832      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
833  }  }
834                    # Next the genome subsets.
835  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
836                    for my $subsetID (@subsetNames) {
837  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
838                        my $actualID = "$subsysID:$subsetID";
839  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
840                        # Connect the subset to the subsystem.
841  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
842  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
843                        my @genomes = $sub->get_subsetR($subsetID);
844  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
845                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
846      Diagram                      }
847      RoleOccursIn                  }
848                }
849  =over 4              # Now we loop through the diagrams. We need to create the diagram records
850                # and link each diagram to its roles. Note that only roles which occur
851  =item RETURNS              # in subsystems (and therefore appear in the %ecToRoles hash) are
852                # included.
853  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) {  
854          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
855          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
856          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 740  Line 859 
859          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
860          my %roleHash = ();          my %roleHash = ();
861          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
862              if (! $roleHash{$role}) {                      if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
863                  $loadRoleOccursIn->Put($role, $map);                          $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
864                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
865              }              }
866          }          }
867      }      }
868                # Before we leave, we must create the Catalyzes table. We start with the reactions,
869                # then use the "ecToRoles" table to convert EC numbers to role IDs.
870                my @reactions = $fig->all_reactions();
871                for my $reactionID (@reactions) {
872                    # Get this reaction's list of roles. The results will be EC numbers.
873                    my @roles = $fig->catalyzed_by($reactionID);
874                    # Loop through the roles, creating catalyzation records.
875                    for my $thisRole (@roles) {
876                        if (exists $ecToRoles{$thisRole}) {
877                            $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
878                        }
879                    }
880                }
881            }
882        }
883      # Finish the load.      # Finish the load.
884      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
885      return $retVal;      return $retVal;
# Line 787  Line 921 
921      my $fig = $self->{fig};      my $fig = $self->{fig};
922      # Get the genome hash.      # Get the genome hash.
923      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
924      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
925      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
926      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
927      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
928            Trace("Loading from existing files.") if T(2);
929        } else {
930            Trace("Generating property data.") if T(2);
931      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
932      my %propertyKeys = ();      my %propertyKeys = ();
933      my $nextID = 1;      my $nextID = 1;
934      # Loop through the genomes.      # Loop through the genomes.
935      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
936          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
937                Trace("Generating properties for $genomeID.") if T(3);
938          # 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
939          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
940          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
941          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
942                my $featureCount = 0;
943                my $propertyCount = 0;
944          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
945          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
946              # 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
947              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
948              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
949                    if (scalar @attributeList) {
950                        $featureCount++;
951                    }
952              # Loop through the attributes.              # Loop through the attributes.
953              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
954                        $propertyCount++;
955                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
956                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
957                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 831  Line 973 
973                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
974              }              }
975          }          }
976                # Update the statistics.
977                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
978                $loadHasProperty->Add("featuresIn", $featureCount);
979                $loadHasProperty->Add("propertiesIn", $propertyCount);
980            }
981      }      }
982      # Finish the load.      # Finish the load.
983      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 871  Line 1018 
1018      my $fig = $self->{fig};      my $fig = $self->{fig};
1019      # Get the genome hash.      # Get the genome hash.
1020      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1021      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1022      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1023      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1024      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1025      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1026      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1027      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1028            Trace("Loading from existing files.") if T(2);
1029        } else {
1030            Trace("Generating annotation data.") if T(2);
1031      # 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
1032      # user records.      # user records.
1033      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 892  Line 1041 
1041      # Loop through the genomes.      # Loop through the genomes.
1042      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1043          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);  
1044              # 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
1045              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1046              my %seenTimestamps = ();              my %seenTimestamps = ();
1047              # Check for a functional assignment.              # Get the genome's annotations.
1048              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1049              if ($func) {              Trace("Processing annotations.") if T(2);
1050                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1051                  # assignment annotation for it.                  # Get the annotation tuple.
1052                  if (! FIG::hypo($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};  
1053                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1054                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1055                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1056                      # stop the substitution search.                      # stop the substitution search.
1057                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 927  Line 1061 
1061                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1062                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1063                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1064                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1065                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1066                              $timestamp++;                      my $keyStamp = $timestamp;
1067                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1068                            $keyStamp++;
1069                          }                          }
1070                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1071                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1072                          # Insure the user exists.                          # Insure the user exists.
1073                          if (! $users{$user}) {                          if (! $users{$user}) {
1074                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 940  Line 1076 
1076                              $users{$user} = 1;                              $users{$user} = 1;
1077                          }                          }
1078                          # Generate the annotation.                          # Generate the annotation.
1079                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1080                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1081                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1082                      } else {                      } else {
# Line 950  Line 1086 
1086                  }                  }
1087              }              }
1088          }          }
     }  
1089      # Finish the load.      # Finish the load.
1090      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1091      return $retVal;      return $retVal;
# Line 991  Line 1126 
1126      my $fig = $self->{fig};      my $fig = $self->{fig};
1127      # Get the genome hash.      # Get the genome hash.
1128      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1129      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1130      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1131      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1132      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1133      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1134            Trace("Loading from existing files.") if T(2);
1135        } else {
1136            Trace("Generating annotation data.") if T(2);
1137      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1138      my %sourceURL = ();      my %sourceURL = ();
1139      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1010  Line 1147 
1147              chomp $line;              chomp $line;
1148              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1149              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1150              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1151                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1152                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1153              }              }
1154              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1155                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1156                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1157                        $sourceDesc{$sourceID} = $sourceID;
1158              }              }
1159          }          }
1160          close TMP;          close TMP;
1161      }      }
1162            # Write the source descriptions.
1163            for my $sourceID (keys %sourceDesc) {
1164                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1165            }
1166        }
1167      # Finish the load.      # Finish the load.
1168      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1169      return $retVal;      return $retVal;
# Line 1060  Line 1203 
1203      my $fig = $self->{fig};      my $fig = $self->{fig};
1204      # Get the genome hash.      # Get the genome hash.
1205      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1206      # 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
1207      # it the key.      # it the key.
1208      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1209      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1210      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1211      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1212      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1213            Trace("Loading from existing files.") if T(2);
1214        } else {
1215            Trace("Generating external data.") if T(2);
1216      # 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.
1217      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");
1218      my $orgLine;      my $orgLine;
# Line 1097  Line 1242 
1242              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1243          }          }
1244      }      }
1245        }
1246        # Finish the load.
1247        my $retVal = $self->_FinishAll();
1248        return $retVal;
1249    }
1250    
1251    
1252    =head3 LoadReactionData
1253    
1254    C<< my $stats = $spl->LoadReactionData(); >>
1255    
1256    Load the reaction data from FIG into Sprout.
1257    
1258    Reaction data connects reactions to the compounds that participate in them.
1259    
1260    The following relations are loaded by this method.
1261    
1262        Reaction
1263        ReactionURL
1264        Compound
1265        CompoundName
1266        CompoundCAS
1267        IsAComponentOf
1268    
1269    This method proceeds reaction by reaction rather than genome by genome.
1270    
1271    =over 4
1272    
1273    =item RETURNS
1274    
1275    Returns a statistics object for the loads.
1276    
1277    =back
1278    
1279    =cut
1280    #: Return Type $%;
1281    sub LoadReactionData {
1282        # Get this object instance.
1283        my ($self) = @_;
1284        # Get the FIG object.
1285        my $fig = $self->{fig};
1286        # Create load objects for each of the tables we're loading.
1287        my $loadReaction = $self->_TableLoader('Reaction');
1288        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1289        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1290        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1291        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1292        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1293        if ($self->{options}->{loadOnly}) {
1294            Trace("Loading from existing files.") if T(2);
1295        } else {
1296            Trace("Generating annotation data.") if T(2);
1297            # First we create the compounds.
1298            my @compounds = $fig->all_compounds();
1299            for my $cid (@compounds) {
1300                # Check for names.
1301                my @names = $fig->names_of_compound($cid);
1302                # Each name will be given a priority number, starting with 1.
1303                my $prio = 1;
1304                for my $name (@names) {
1305                    $loadCompoundName->Put($cid, $name, $prio++);
1306                }
1307                # Create the main compound record. Note that the first name
1308                # becomes the label.
1309                my $label = (@names > 0 ? $names[0] : $cid);
1310                $loadCompound->Put($cid, $label);
1311                # Check for a CAS ID.
1312                my $cas = $fig->cas($cid);
1313                if ($cas) {
1314                    $loadCompoundCAS->Put($cid, $cas);
1315                }
1316            }
1317            # All the compounds are set up, so we need to loop through the reactions next. First,
1318            # we initialize the discriminator index. This is a single integer used to insure
1319            # duplicate elements in a reaction are not accidentally collapsed.
1320            my $discrim = 0;
1321            my @reactions = $fig->all_reactions();
1322            for my $reactionID (@reactions) {
1323                # Create the reaction record.
1324                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1325                # Compute the reaction's URL.
1326                my $url = HTML::reaction_link($reactionID);
1327                # Put it in the ReactionURL table.
1328                $loadReactionURL->Put($reactionID, $url);
1329                # Now we need all of the reaction's compounds. We get these in two phases,
1330                # substrates first and then products.
1331                for my $product (0, 1) {
1332                    # Get the compounds of the current type for the current reaction. FIG will
1333                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1334                    # have location data in SEED, so it defaults to the empty string.
1335                    my @compounds = $fig->reaction2comp($reactionID, $product);
1336                    for my $compData (@compounds) {
1337                        # Extract the compound data from the current tuple.
1338                        my ($cid, $stoich, $main) = @{$compData};
1339                        # Link the compound to the reaction.
1340                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1341                                                 $product, $stoich);
1342                    }
1343                }
1344            }
1345        }
1346      # Finish the load.      # Finish the load.
1347      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1348      return $retVal;      return $retVal;
# Line 1132  Line 1378 
1378      my $fig = $self->{fig};      my $fig = $self->{fig};
1379      # Get the genome hash.      # Get the genome hash.
1380      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1381      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1382      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1383      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1384            Trace("Loading from existing files.") if T(2);
1385        } else {
1386            Trace("Generating group data.") if T(2);
1387      # Loop through the genomes.      # Loop through the genomes.
1388      my $line;      my $line;
1389      for my $genomeID (keys %{$genomeHash}) {      for my $genomeID (keys %{$genomeHash}) {
# Line 1151  Line 1399 
1399          }          }
1400          close TMP;          close TMP;
1401      }      }
1402        }
1403        # Finish the load.
1404        my $retVal = $self->_FinishAll();
1405        return $retVal;
1406    }
1407    
1408    =head3 LoadSynonymData
1409    
1410    C<< my $stats = $spl->LoadSynonymData(); >>
1411    
1412    Load the synonym groups into Sprout.
1413    
1414    The following relations are loaded by this method.
1415    
1416        SynonymGroup
1417        IsSynonymGroupFor
1418    
1419    The source information for these relations is taken from the C<maps_to_id> method
1420    of the B<FIG> object. The process starts from the features, so it is possible
1421    that there will be duplicates in the SynonymGroup load file, since the relationship
1422    is one-to-many toward the features. The automatic sort on primary entity relations
1423    will fix this for us.
1424    
1425    =over 4
1426    
1427    =item RETURNS
1428    
1429    Returns a statistics object for the loads.
1430    
1431    =back
1432    
1433    =cut
1434    #: Return Type $%;
1435    sub LoadSynonymData {
1436        # Get this object instance.
1437        my ($self) = @_;
1438        # Get the FIG object.
1439        my $fig = $self->{fig};
1440        # Get the genome hash.
1441        my $genomeHash = $self->{genomes};
1442        # Create a load object for the table we're loading.
1443        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1444        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1445        if ($self->{options}->{loadOnly}) {
1446            Trace("Loading from existing files.") if T(2);
1447        } else {
1448            Trace("Generating synonym group data.") if T(2);
1449            # Loop through the genomes.
1450            for my $genomeID (sort keys %{$genomeHash}) {
1451                Trace("Processing $genomeID.") if T(3);
1452                # Get all of the features for this genome. The only method that does this is
1453                # all_features_detailed, which returns extra baggage that we discard.
1454                my $featureData = $fig->all_features_detailed($genomeID);
1455                my @fids = map { $_->[0] } @{$featureData};
1456                Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
1457                # Loop through the feature IDs.
1458                for my $fid (@fids) {
1459                    # Get the group for this feature.
1460                    my $synonym = $fig->maps_to_id($fid);
1461                    # Only proceed if the synonym is a real group.
1462                    if ($synonym ne $fid) {
1463                        $loadSynonymGroup->Put($synonym);
1464                        $loadIsSynonymGroupFor->Put($synonym, $fid);
1465                    }
1466                }
1467            }
1468        }
1469      # Finish the load.      # Finish the load.
1470      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1471      return $retVal;      return $retVal;
1472  }  }
1473    
1474    
1475  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1476    
1477  =head3 TableLoader  =head3 TableLoader
# Line 1172  Line 1488 
1488    
1489  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1490    
1491  =item rowCount (optional)  =item ignore
1492    
1493  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1494    
1495  =item RETURN  =item RETURN
1496    
# Line 1186  Line 1502 
1502    
1503  sub _TableLoader {  sub _TableLoader {
1504      # Get the parameters.      # Get the parameters.
1505      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1506      # Create the load object.      # Create the load object.
1507      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1508                                   $ignore);
1509      # Cache it in the loader list.      # Cache it in the loader list.
1510      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1511      # Return it to the caller.      # Return it to the caller.
# Line 1222  Line 1539 
1539      my $retVal = Stats->new();      my $retVal = Stats->new();
1540      # Get the loader list.      # Get the loader list.
1541      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1542        # Create a hash to hold the statistics objects, keyed on relation name.
1543        my %loaderHash = ();
1544      # 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
1545      # 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.
1546      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1547            # Get the relation name.
1548            my $relName = $loader->RelName;
1549            # Check the ignore flag.
1550            if ($loader->Ignore) {
1551                Trace("Relation $relName not loaded.") if T(2);
1552            } else {
1553                # Here we really need to finish.
1554                Trace("Finishing $relName.") if T(2);
1555          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1556                $loaderHash{$relName} = $stats;
1557            }
1558        }
1559        # Now we loop through again, actually loading the tables. We want to finish before
1560        # loading so that if something goes wrong at this point, all the load files are usable
1561        # and we don't have to redo all that work.
1562        for my $relName (sort keys %loaderHash) {
1563            # Get the statistics for this relation.
1564            my $stats = $loaderHash{$relName};
1565            # Check for a database load.
1566            if ($self->{options}->{dbLoad}) {
1567                # Here we want to use the load file just created to load the database.
1568                Trace("Loading relation $relName.") if T(2);
1569                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1570                # Accumulate the statistics from the DB load.
1571                $stats->Accumulate($newStats);
1572            }
1573          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1574          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1575      }      }
1576      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.7  
changed lines
  Added in v.1.51

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3