[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 1.66, Wed Sep 6 19:30:53 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 114  Line 120 
120                  # an omitted access code can be defaulted to 1.                  # an omitted access code can be defaulted to 1.
121                  for my $genomeLine (@genomeList) {                  for my $genomeLine (@genomeList) {
122                      my ($genomeID, $accessCode) = split("\t", $genomeLine);                      my ($genomeID, $accessCode) = split("\t", $genomeLine);
123                      if (undef $accessCode) {                          if (! defined($accessCode)) {
124                          $accessCode = 1;                          $accessCode = 1;
125                      }                      }
126                      $genomes{$genomeID} = $accessCode;                      $genomes{$genomeID} = $accessCode;
# Line 124  Line 130 
130              Confess("Invalid genome parameter ($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              $loadFeature->Put($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");
609          Trace("Processing features for genome $genomeID.") if T(3);          Trace("Processing features for genome $genomeID.") if T(3);
610          # Get the feature list for this genome.          # Get the feature list for this genome.
611          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
612                # Count the BBHs we find.
613                my $bbhCount = 0;
614          # Loop through the features.          # Loop through the features.
615          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
616              # Split the tuple.              # Split the tuple.
# Line 560  Line 626 
626                  if ($genomeHash->{$targetGenomeID}) {                  if ($genomeHash->{$targetGenomeID}) {
627                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
628                                                         $score);                                                         $score);
629                            $bbhCount++;
630                        }
631                  }                  }
632              }              }
633                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
634          }          }
635      }      }
636      # Finish the loads.      # Finish the loads.
# Line 584  Line 653 
653  The following relations are loaded by this method.  The following relations are loaded by this method.
654    
655      Subsystem      Subsystem
656        SubsystemClass
657      Role      Role
658        RoleEC
659      SSCell      SSCell
660      ContainsFeature      ContainsFeature
661      IsGenomeOf      IsGenomeOf
# Line 592  Line 663 
663      OccursInSubsystem      OccursInSubsystem
664      ParticipatesIn      ParticipatesIn
665      HasSSCell      HasSSCell
666        ConsistsOfRoles
667        RoleSubset
668        HasRoleSubset
669        ConsistsOfGenomes
670        GenomeSubset
671        HasGenomeSubset
672        Catalyzes
673        Diagram
674        RoleOccursIn
675    
676  =over 4  =over 4
677    
# Line 601  Line 681 
681    
682  =back  =back
683    
 B<TO DO>  
   
 Generate RoleName table?  
   
684  =cut  =cut
685  #: Return Type $%;  #: Return Type $%;
686  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 618  Line 694 
694      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
695      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
696      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
697      my $subsysCount = @subsysIDs;      # Get the map list.
698      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
699      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
700      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
701      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
702      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
703      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
704      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
705      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
706      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
707      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
708      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
709      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
710        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
711        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
712        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
713        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
714        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
715        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
716        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
717        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
718        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
719        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
720        if ($self->{options}->{loadOnly}) {
721            Trace("Loading from existing files.") if T(2);
722        } else {
723            Trace("Generating subsystem data.") if T(2);
724            # This hash will contain the role for each EC. When we're done, this
725            # information will be used to generate the Catalyzes table.
726            my %ecToRoles = ();
727      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
728      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
729      # 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
730      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
731            # and memorize up the reactions.
732            my ($genomeID, $roleID);
733      my %roleData = ();      my %roleData = ();
734      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
735                # Get the subsystem object.
736                my $sub = $fig->get_subsystem($subsysID);
737                # Only proceed if the subsystem has a spreadsheet.
738                if (! $sub->{empty_ss}) {
739          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
740          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
741          # Create the subsystem record.          # Create the subsystem record.
742          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
743          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
744          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
745          # Connect the roles to the subsystem. If a role is new, we create                  my $classList = $fig->subsystem_classification($subsysID);
746          # a role record for it.                  my @classes = @$classList;
747          for my $roleID (@roles) {                  if (@classes) {
748                        for my $class (@classes) {
749                            $loadSubsystemClass->Put($subsysID, $class);
750                        }
751                    }
752                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
753                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
754                        # Connect to this role.
755              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
756              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
757                        # If it's a new role, add it to the role table.
758              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
759                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
760                            my $abbr = $sub->get_role_abbr($col);
761                            # Add the role.
762                            $loadRole->Put($roleID, $abbr);
763                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
764                            # Check for an EC number.
765                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
766                                my $ec = $1;
767                                $loadRoleEC->Put($roleID, $ec);
768                                $ecToRoles{$ec} = $roleID;
769              }              }
770          }          }
771          # Now all roles for this subsystem have been filled in. We create the                  }
772          # spreadsheet by matches roles to genomes. To do this, we need to                  # Now we create the spreadsheet for the subsystem by matching roles to
773          # get the genomes on the sheet.                  # genomes. Each genome is a row and each role is a column. We may need
774                    # to actually create the roles as we find them.
775          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
776          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
777          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
778              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
779                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
780                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
781                            my $cellCount = 0;
782                            # Create a list for the PEGs we find. This list will be used
783                            # to generate cluster numbers.
784                            my @pegsFound = ();
785                            # Create a hash that maps spreadsheet IDs to PEGs. We will
786                            # use this to generate the ContainsFeature data after we have
787                            # the cluster numbers.
788                            my %cellPegs = ();
789                            # Get the genome's variant code for this subsystem.
790                            my $variantCode = $sub->get_variant_code($row);
791                  # 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
792                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
793                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
794                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
795                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
796                      # Only proceed if features exist.                      # Only proceed if features exist.
797                      if (@pegs > 0) {                      if (@pegs > 0) {
798                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
799                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
800                                    my $cellID = "$subsysID:$genomeID:$col";
801                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
802                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
803                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
804                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
805                          # Attach the features to it.                                  # Remember its features.
806                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
807                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
808                                    $pegCount += @pegs;
809                                }
810                            }
811                            # If we found some cells for this genome, we need to compute clusters and
812                            # denote it participates in the subsystem.
813                            if ($pegCount > 0) {
814                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
815                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
816                                # Create a hash mapping PEG IDs to cluster numbers.
817                                # We default to -1 for all of them.
818                                my %clusterOf = map { $_ => -1 } @pegsFound;
819                                # Partition the PEGs found into clusters.
820                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
821                                for (my $i = 0; $i <= $#clusters; $i++) {
822                                    my $subList = $clusters[$i];
823                                    for my $peg (@{$subList}) {
824                                        $clusterOf{$peg} = $i;
825                                    }
826                                }
827                                # Create the ContainsFeature data.
828                                for my $cellID (keys %cellPegs) {
829                                    my $cellList = $cellPegs{$cellID};
830                                    for my $cellPeg (@$cellList) {
831                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
832                          }                          }
833                      }                      }
834                  }                  }
835              }              }
836          }          }
837                    # Now we need to generate the subsets. The subset names must be concatenated to
838                    # the subsystem name to make them unique keys. There are two types of subsets:
839                    # genome subsets and role subsets. We do the role subsets first.
840                    my @subsetNames = $sub->get_subset_names();
841                    for my $subsetID (@subsetNames) {
842                        # Create the subset record.
843                        my $actualID = "$subsysID:$subsetID";
844                        $loadRoleSubset->Put($actualID);
845                        # Connect the subset to the subsystem.
846                        $loadHasRoleSubset->Put($subsysID, $actualID);
847                        # Connect the subset to its roles.
848                        my @roles = $sub->get_subsetC_roles($subsetID);
849                        for my $roleID (@roles) {
850                            $loadConsistsOfRoles->Put($actualID, $roleID);
851      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
852  }  }
853                    # Next the genome subsets.
854  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
855                    for my $subsetID (@subsetNames) {
856  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
857                        my $actualID = "$subsysID:$subsetID";
858  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
859                        # Connect the subset to the subsystem.
860  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
861  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
862                        my @genomes = $sub->get_subsetR($subsetID);
863  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
864                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
865      Diagram                      }
866      RoleOccursIn                  }
867                }
868  =over 4          }
869            # Now we loop through the diagrams. We need to create the diagram records
870  =item RETURNS          # and link each diagram to its roles. Note that only roles which occur
871            # in subsystems (and therefore appear in the %ecToRoles hash) are
872  Returns a statistics object for the loads.          # included.
873            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) {  
874          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
875          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
876          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 740  Line 879 
879          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
880          my %roleHash = ();          my %roleHash = ();
881          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
882              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
883                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
884                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
885              }              }
886          }          }
887      }      }
888            # Before we leave, we must create the Catalyzes table. We start with the reactions,
889            # then use the "ecToRoles" table to convert EC numbers to role IDs.
890            my @reactions = $fig->all_reactions();
891            for my $reactionID (@reactions) {
892                # Get this reaction's list of roles. The results will be EC numbers.
893                my @roles = $fig->catalyzed_by($reactionID);
894                # Loop through the roles, creating catalyzation records.
895                for my $thisRole (@roles) {
896                    if (exists $ecToRoles{$thisRole}) {
897                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
898                    }
899                }
900            }
901        }
902      # Finish the load.      # Finish the load.
903      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
904      return $retVal;      return $retVal;
# Line 787  Line 940 
940      my $fig = $self->{fig};      my $fig = $self->{fig};
941      # Get the genome hash.      # Get the genome hash.
942      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
943      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
944      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
945      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
946      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
947            Trace("Loading from existing files.") if T(2);
948        } else {
949            Trace("Generating property data.") if T(2);
950      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
951      my %propertyKeys = ();      my %propertyKeys = ();
952      my $nextID = 1;      my $nextID = 1;
953      # Loop through the genomes.      # Loop through the genomes.
954      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
955          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
956                Trace("Generating properties for $genomeID.") if T(3);
957          # 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
958          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
959          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
960          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
961                my $featureCount = 0;
962                my $propertyCount = 0;
963          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
964          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
965              # 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
966              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
967              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
968                    if (scalar @attributeList) {
969                        $featureCount++;
970                    }
971              # Loop through the attributes.              # Loop through the attributes.
972              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
973                        $propertyCount++;
974                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
975                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
976                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 831  Line 992 
992                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
993              }              }
994          }          }
995                # Update the statistics.
996                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
997                $loadHasProperty->Add("featuresIn", $featureCount);
998                $loadHasProperty->Add("propertiesIn", $propertyCount);
999            }
1000      }      }
1001      # Finish the load.      # Finish the load.
1002      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 871  Line 1037 
1037      my $fig = $self->{fig};      my $fig = $self->{fig};
1038      # Get the genome hash.      # Get the genome hash.
1039      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1040      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1041      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1042      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1043      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1044      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1045      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1046      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1047            Trace("Loading from existing files.") if T(2);
1048        } else {
1049            Trace("Generating annotation data.") if T(2);
1050      # 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
1051      # user records.      # user records.
1052      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 892  Line 1060 
1060      # Loop through the genomes.      # Loop through the genomes.
1061      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1062          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);  
1063              # 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
1064              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1065              my %seenTimestamps = ();              my %seenTimestamps = ();
1066              # Check for a functional assignment.              # Get the genome's annotations.
1067              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1068              if ($func) {              Trace("Processing annotations.") if T(2);
1069                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1070                  # assignment annotation for it.                  # Get the annotation tuple.
1071                  if (! FIG::hypo($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};  
1072                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1073                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1074                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1075                      # stop the substitution search.                      # stop the substitution search.
1076                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 927  Line 1080 
1080                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1081                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1082                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1083                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1084                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1085                              $timestamp++;                      my $keyStamp = $timestamp;
1086                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1087                            $keyStamp++;
1088                          }                          }
1089                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1090                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1091                          # Insure the user exists.                          # Insure the user exists.
1092                          if (! $users{$user}) {                          if (! $users{$user}) {
1093                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 940  Line 1095 
1095                              $users{$user} = 1;                              $users{$user} = 1;
1096                          }                          }
1097                          # Generate the annotation.                          # Generate the annotation.
1098                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1099                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1100                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1101                      } else {                      } else {
# Line 950  Line 1105 
1105                  }                  }
1106              }              }
1107          }          }
     }  
1108      # Finish the load.      # Finish the load.
1109      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1110      return $retVal;      return $retVal;
# Line 991  Line 1145 
1145      my $fig = $self->{fig};      my $fig = $self->{fig};
1146      # Get the genome hash.      # Get the genome hash.
1147      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1148      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1149      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1150      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1151      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1152      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1153            Trace("Loading from existing files.") if T(2);
1154        } else {
1155            Trace("Generating annotation data.") if T(2);
1156      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1157      my %sourceURL = ();      my %sourceURL = ();
1158      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1010  Line 1166 
1166              chomp $line;              chomp $line;
1167              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1168              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1169              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1170                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1171                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1172              }              }
1173              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1174                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1175                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1176                        $sourceDesc{$sourceID} = $sourceID;
1177              }              }
1178          }          }
1179          close TMP;          close TMP;
1180      }      }
1181            # Write the source descriptions.
1182            for my $sourceID (keys %sourceDesc) {
1183                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1184            }
1185        }
1186      # Finish the load.      # Finish the load.
1187      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1188      return $retVal;      return $retVal;
# Line 1060  Line 1222 
1222      my $fig = $self->{fig};      my $fig = $self->{fig};
1223      # Get the genome hash.      # Get the genome hash.
1224      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1225      # 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
1226      # it the key.      # it the key.
1227      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1228      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1229      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1230      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1231      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1232            Trace("Loading from existing files.") if T(2);
1233        } else {
1234            Trace("Generating external data.") if T(2);
1235      # 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.
1236      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1237      my $orgLine;      my $orgLine;
1238      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1239          # Clean the input line.          # Clean the input line.
# Line 1081  Line 1245 
1245      close ORGS;      close ORGS;
1246      # Now the function file.      # Now the function file.
1247      my $funcLine;      my $funcLine;
1248      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1249      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1250          # Clean the line ending.          # Clean the line ending.
1251          chomp $funcLine;          chomp $funcLine;
# Line 1097  Line 1261 
1261              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1262          }          }
1263      }      }
1264        }
1265        # Finish the load.
1266        my $retVal = $self->_FinishAll();
1267        return $retVal;
1268    }
1269    
1270    
1271    =head3 LoadReactionData
1272    
1273    C<< my $stats = $spl->LoadReactionData(); >>
1274    
1275    Load the reaction data from FIG into Sprout.
1276    
1277    Reaction data connects reactions to the compounds that participate in them.
1278    
1279    The following relations are loaded by this method.
1280    
1281        Reaction
1282        ReactionURL
1283        Compound
1284        CompoundName
1285        CompoundCAS
1286        IsAComponentOf
1287    
1288    This method proceeds reaction by reaction rather than genome by genome.
1289    
1290    =over 4
1291    
1292    =item RETURNS
1293    
1294    Returns a statistics object for the loads.
1295    
1296    =back
1297    
1298    =cut
1299    #: Return Type $%;
1300    sub LoadReactionData {
1301        # Get this object instance.
1302        my ($self) = @_;
1303        # Get the FIG object.
1304        my $fig = $self->{fig};
1305        # Create load objects for each of the tables we're loading.
1306        my $loadReaction = $self->_TableLoader('Reaction');
1307        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1308        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1309        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1310        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1311        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1312        if ($self->{options}->{loadOnly}) {
1313            Trace("Loading from existing files.") if T(2);
1314        } else {
1315            Trace("Generating annotation data.") if T(2);
1316            # First we create the compounds.
1317            my @compounds = $fig->all_compounds();
1318            for my $cid (@compounds) {
1319                # Check for names.
1320                my @names = $fig->names_of_compound($cid);
1321                # Each name will be given a priority number, starting with 1.
1322                my $prio = 1;
1323                for my $name (@names) {
1324                    $loadCompoundName->Put($cid, $name, $prio++);
1325                }
1326                # Create the main compound record. Note that the first name
1327                # becomes the label.
1328                my $label = (@names > 0 ? $names[0] : $cid);
1329                $loadCompound->Put($cid, $label);
1330                # Check for a CAS ID.
1331                my $cas = $fig->cas($cid);
1332                if ($cas) {
1333                    $loadCompoundCAS->Put($cid, $cas);
1334                }
1335            }
1336            # All the compounds are set up, so we need to loop through the reactions next. First,
1337            # we initialize the discriminator index. This is a single integer used to insure
1338            # duplicate elements in a reaction are not accidentally collapsed.
1339            my $discrim = 0;
1340            my @reactions = $fig->all_reactions();
1341            for my $reactionID (@reactions) {
1342                # Create the reaction record.
1343                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1344                # Compute the reaction's URL.
1345                my $url = HTML::reaction_link($reactionID);
1346                # Put it in the ReactionURL table.
1347                $loadReactionURL->Put($reactionID, $url);
1348                # Now we need all of the reaction's compounds. We get these in two phases,
1349                # substrates first and then products.
1350                for my $product (0, 1) {
1351                    # Get the compounds of the current type for the current reaction. FIG will
1352                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1353                    # have location data in SEED, so it defaults to the empty string.
1354                    my @compounds = $fig->reaction2comp($reactionID, $product);
1355                    for my $compData (@compounds) {
1356                        # Extract the compound data from the current tuple.
1357                        my ($cid, $stoich, $main) = @{$compData};
1358                        # Link the compound to the reaction.
1359                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1360                                                 $product, $stoich);
1361                    }
1362                }
1363            }
1364        }
1365      # Finish the load.      # Finish the load.
1366      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1367      return $retVal;      return $retVal;
# Line 1132  Line 1397 
1397      my $fig = $self->{fig};      my $fig = $self->{fig};
1398      # Get the genome hash.      # Get the genome hash.
1399      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1400      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1401      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1402      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1403            Trace("Loading from existing files.") if T(2);
1404        } else {
1405            Trace("Generating group data.") if T(2);
1406      # Loop through the genomes.      # Loop through the genomes.
1407      my $line;      my $line;
1408      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1409          Trace("Processing $genomeID.") if T(3);          Trace("Processing $genomeID.") if T(3);
1410          # Open the NMPDR group file for this genome.          # Open the NMPDR group file for this genome.
1411          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
# Line 1151  Line 1418 
1418          }          }
1419          close TMP;          close TMP;
1420      }      }
1421        }
1422        # Finish the load.
1423        my $retVal = $self->_FinishAll();
1424        return $retVal;
1425    }
1426    
1427    =head3 LoadSynonymData
1428    
1429    C<< my $stats = $spl->LoadSynonymData(); >>
1430    
1431    Load the synonym groups into Sprout.
1432    
1433    The following relations are loaded by this method.
1434    
1435        SynonymGroup
1436        IsSynonymGroupFor
1437    
1438    The source information for these relations is taken from the C<maps_to_id> method
1439    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1440    SQL against the FIG database.
1441    
1442    =over 4
1443    
1444    =item RETURNS
1445    
1446    Returns a statistics object for the loads.
1447    
1448    =back
1449    
1450    =cut
1451    #: Return Type $%;
1452    sub LoadSynonymData {
1453        # Get this object instance.
1454        my ($self) = @_;
1455        # Get the FIG object.
1456        my $fig = $self->{fig};
1457        # Get the genome hash.
1458        my $genomeHash = $self->{genomes};
1459        # Create a load object for the table we're loading.
1460        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1461        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1462        if ($self->{options}->{loadOnly}) {
1463            Trace("Loading from existing files.") if T(2);
1464        } else {
1465            Trace("Generating synonym group data.") if T(2);
1466            # Get the database handle.
1467            my $dbh = $fig->db_handle();
1468            # Ask for the synonyms.
1469            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1470            my $result = $sth->execute();
1471            if (! defined($result)) {
1472                Confess("Database error in Synonym load: " . $sth->errstr());
1473            } else {
1474                # Remember the current synonym.
1475                my $current_syn = "";
1476                # Count the features.
1477                my $featureCount = 0;
1478                # Loop through the synonym/peg pairs.
1479                while (my @row = $sth->fetchrow()) {
1480                    # Get the synonym ID and feature ID.
1481                    my ($syn_id, $peg) = @row;
1482                    # Insure it's for one of our genomes.
1483                    my $genomeID = FIG::genome_of($peg);
1484                    if (exists $genomeHash->{$genomeID}) {
1485                        # Verify the synonym.
1486                        if ($syn_id ne $current_syn) {
1487                            # It's new, so put it in the group table.
1488                            $loadSynonymGroup->Put($syn_id);
1489                            $current_syn = $syn_id;
1490                        }
1491                        # Connect the synonym to the peg.
1492                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1493                        # Count this feature.
1494                        $featureCount++;
1495                        if ($featureCount % 1000 == 0) {
1496                            Trace("$featureCount features processed.") if T(3);
1497                        }
1498                    }
1499                }
1500            }
1501        }
1502        # Finish the load.
1503        my $retVal = $self->_FinishAll();
1504        return $retVal;
1505    }
1506    
1507    =head3 LoadFamilyData
1508    
1509    C<< my $stats = $spl->LoadFamilyData(); >>
1510    
1511    Load the protein families into Sprout.
1512    
1513    The following relations are loaded by this method.
1514    
1515        Family
1516        IsFamilyForFeature
1517    
1518    The source information for these relations is taken from the C<families_for_protein>,
1519    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1520    
1521    =over 4
1522    
1523    =item RETURNS
1524    
1525    Returns a statistics object for the loads.
1526    
1527    =back
1528    
1529    =cut
1530    #: Return Type $%;
1531    sub LoadFamilyData {
1532        # Get this object instance.
1533        my ($self) = @_;
1534        # Get the FIG object.
1535        my $fig = $self->{fig};
1536        # Get the genome hash.
1537        my $genomeHash = $self->{genomes};
1538        # Create load objects for the tables we're loading.
1539        my $loadFamily = $self->_TableLoader('Family');
1540        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1541        if ($self->{options}->{loadOnly}) {
1542            Trace("Loading from existing files.") if T(2);
1543        } else {
1544            Trace("Generating family data.") if T(2);
1545            # Create a hash for the family IDs.
1546            my %familyHash = ();
1547            # Loop through the genomes.
1548            for my $genomeID (sort keys %{$genomeHash}) {
1549                Trace("Processing features for $genomeID.") if T(2);
1550                # Loop through this genome's PEGs.
1551                for my $fid ($fig->all_features($genomeID, "peg")) {
1552                    $loadIsFamilyForFeature->Add("features", 1);
1553                    # Get this feature's families.
1554                    my @families = $fig->families_for_protein($fid);
1555                    # Loop through the families, connecting them to the feature.
1556                    for my $family (@families) {
1557                        $loadIsFamilyForFeature->Put($family, $fid);
1558                        # If this is a new family, create a record for it.
1559                        if (! exists $familyHash{$family}) {
1560                            $familyHash{$family} = 1;
1561                            $loadFamily->Add("families", 1);
1562                            my $size = $fig->sz_family($family);
1563                            my $func = $fig->family_function($family);
1564                            $loadFamily->Put($family, $size, $func);
1565                        }
1566                    }
1567                }
1568            }
1569        }
1570      # Finish the load.      # Finish the load.
1571      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1572      return $retVal;      return $retVal;
# Line 1172  Line 1588 
1588    
1589  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1590    
1591  =item rowCount (optional)  =item ignore
1592    
1593  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1594    
1595  =item RETURN  =item RETURN
1596    
# Line 1186  Line 1602 
1602    
1603  sub _TableLoader {  sub _TableLoader {
1604      # Get the parameters.      # Get the parameters.
1605      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1606      # Create the load object.      # Create the load object.
1607      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1608                                   $ignore);
1609      # Cache it in the loader list.      # Cache it in the loader list.
1610      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1611      # Return it to the caller.      # Return it to the caller.
# Line 1222  Line 1639 
1639      my $retVal = Stats->new();      my $retVal = Stats->new();
1640      # Get the loader list.      # Get the loader list.
1641      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1642        # Create a hash to hold the statistics objects, keyed on relation name.
1643        my %loaderHash = ();
1644      # 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
1645      # 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.
1646      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1647            # Get the relation name.
1648            my $relName = $loader->RelName;
1649            # Check the ignore flag.
1650            if ($loader->Ignore) {
1651                Trace("Relation $relName not loaded.") if T(2);
1652            } else {
1653                # Here we really need to finish.
1654                Trace("Finishing $relName.") if T(2);
1655          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1656                $loaderHash{$relName} = $stats;
1657            }
1658        }
1659        # Now we loop through again, actually loading the tables. We want to finish before
1660        # loading so that if something goes wrong at this point, all the load files are usable
1661        # and we don't have to redo all that work.
1662        for my $relName (sort keys %loaderHash) {
1663            # Get the statistics for this relation.
1664            my $stats = $loaderHash{$relName};
1665            # Check for a database load.
1666            if ($self->{options}->{dbLoad}) {
1667                # Here we want to use the load file just created to load the database.
1668                Trace("Loading relation $relName.") if T(2);
1669                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1670                # Accumulate the statistics from the DB load.
1671                $stats->Accumulate($newStats);
1672            }
1673          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1674          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1675      }      }
1676      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.7  
changed lines
  Added in v.1.66

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3