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

Diff of /Sprout/SproutLoad.pm

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

revision 1.19, Thu Oct 20 09:34:09 2005 UTC revision 1.72, Sat Oct 14 18:12:14 2006 UTC
# Line 30  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 80  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
81  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
82  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85  =item options  =item options
86    
# Line 94  Line 93 
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
96      # Load the list of genomes into a hash.      # Create the genome hash.
97      my %genomes;      my %genomes = ();
98        # We only need it if load-only is NOT specified.
99        if (! $options->{loadOnly}) {
100      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
101          # Here we want all the complete genomes and an access code of 1.          # Here we want all the complete genomes and an access code of 1.
102          my @genomeList = $fig->genomes(1);          my @genomeList = $fig->genomes(1);
# Line 119  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} = $accessCode;
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($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 153  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166            # Go through the subsys hash again, creating the keyword list for each subsystem.
167            for my $subsystem (keys %subsystems) {
168                my $name = $subsystem;
169                $name =~ s/_/ /g;
170                my $classes = $fig->subsystem_classification($subsystem);
171                my @classList = map { " $_" } @{$classes};
172                $name .= join("", @classList);
173                $subsystems{$subsystem} = $name;
174            }
175        }
176      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
177      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
178      # Create the Sprout load object.      # Create the Sprout load object.
# Line 162  Line 182 
182                    subsystems => \%subsystems,                    subsystems => \%subsystems,
183                    sprout => $sprout,                    sprout => $sprout,
184                    loadDirectory => $directory,                    loadDirectory => $directory,
185                    erdb => $sprout->{_erdb},                    erdb => $sprout,
186                    loaders => [],                    loaders => [],
187                    options => $options                    options => $options
188                   };                   };
# Line 171  Line 191 
191      return $retVal;      return $retVal;
192  }  }
193    
194    =head3 LoadOnly
195    
196    C<< my $flag = $spl->LoadOnly; >>
197    
198    Return TRUE if we are in load-only mode, else FALSE.
199    
200    =cut
201    
202    sub LoadOnly {
203        my ($self) = @_;
204        return $self->{options}->{loadOnly};
205    }
206    
207    =head3 PrimaryOnly
208    
209    C<< my $flag = $spl->PrimaryOnly; >>
210    
211    Return TRUE if only the main entity is to be loaded, else FALSE.
212    
213    =cut
214    
215    sub PrimaryOnly {
216        my ($self) = @_;
217        return $self->{options}->{primaryOnly};
218    }
219    
220  =head3 LoadGenomeData  =head3 LoadGenomeData
221    
222  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 198  Line 244 
244    
245  =back  =back
246    
 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.)  
   
247  =cut  =cut
248  #: Return Type $%;  #: Return Type $%;
249  sub LoadGenomeData {  sub LoadGenomeData {
# Line 216  Line 254 
254      # Get the genome count.      # Get the genome count.
255      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
256      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
257      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
258      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
259      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
260      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
261      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
262      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
263        if ($self->{options}->{loadOnly}) {
264            Trace("Loading from existing files.") if T(2);
265        } else {
266            Trace("Generating genome data.") if T(2);
267      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
268      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
269          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
270          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
271          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
272          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
273          # 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.  
274          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
275          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
276          # Get the full taxonomy.          # Get the full taxonomy.
277          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
278                # Open the NMPDR group file for this genome.
279                my $group;
280                if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
281                    defined($group = <TMP>)) {
282                    # Clean the line ending.
283                    chomp $group;
284                } else {
285                    # No group, so use the default.
286                    $group = $FIG_Config::otherGroup;
287                }
288                close TMP;
289          # Output the genome record.          # Output the genome record.
290          $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,          $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,
291                           $species, $extra, $taxonomy);                               $group, $species, $extra, $taxonomy);
292          # Now we loop through each of the genome's contigs.          # Now we loop through each of the genome's contigs.
293          my @contigs = $fig->all_contigs($genomeID);          my @contigs = $fig->all_contigs($genomeID);
294          for my $contigID (@contigs) {          for my $contigID (@contigs) {
# Line 268  Line 319 
319              }              }
320          }          }
321      }      }
322        }
323      # Finish the loads.      # Finish the loads.
324      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
325      # Return the result.      # Return the result.
# Line 308  Line 360 
360      my $fig = $self->{fig};      my $fig = $self->{fig};
361      # Get the genome hash.      # Get the genome hash.
362      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
363      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
364      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
365      # Start the loads.      # Start the loads.
366      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
367      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
368      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
369      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
370      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
371      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
372            Trace("Loading from existing files.") if T(2);
373        } else {
374            Trace("Generating coupling data.") if T(2);
375      # Loop through the genomes found.      # Loop through the genomes found.
376      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
377          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 340  Line 395 
395              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
396                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
397                  # Compute the coupling ID.                  # Compute the coupling ID.
398                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
399                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
400                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
401                      # 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 376  Line 431 
431                          }                          }
432                      }                      }
433                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
434                                # Get the ID for this evidence.
435                                $pchID++;
436                          # Create the evidence record.                          # Create the evidence record.
437                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
438                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
439                          # Connect it to the coupling.                          # Connect it to the coupling.
440                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
441                          # Connect it to the features.                          # Connect it to the features.
442                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
443                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
444                            }
445                      }                      }
446                  }                  }
447              }              }
# Line 410  Line 468 
468      FeatureTranslation      FeatureTranslation
469      FeatureUpstream      FeatureUpstream
470      IsLocatedIn      IsLocatedIn
471        HasFeature
472        HasRoleInSubsystem
473    
474  =over 4  =over 4
475    
# Line 424  Line 484 
484  sub LoadFeatureData {  sub LoadFeatureData {
485      # Get this object instance.      # Get this object instance.
486      my ($self) = @_;      my ($self) = @_;
487      # Get the FIG object.      # Get the FIG and Sprout objects.
488      my $fig = $self->{fig};      my $fig = $self->{fig};
489      # Find out if this is a limited run.      my $sprout = $self->{sprout};
     my $limited = $self->{options}->{limitedFeatures};  
490      # Get the table of genome IDs.      # Get the table of genome IDs.
491      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
492      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
493      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
494      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
495      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
496      my ($loadFeatureLink, $loadFeatureTranslation, $loadFeatureUpstream);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
497      if (! $limited) {      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
498          $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
499          $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadHasFeature = $self->_TableLoader('HasFeature', $self->PrimaryOnly);
500          $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);      my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem', $self->PrimaryOnly);
501      }      # Get the subsystem hash.
502        my $subHash = $self->{subsystems};
503      # 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
504      # locations.      # locations.
505      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
506      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
507            Trace("Loading from existing files.") if T(2);
508        } else {
509            Trace("Generating feature data.") if T(2);
510      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
511      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
512          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
513          $loadFeature->Add("genomeIn");          $loadFeature->Add("genomeIn");
514          # Get the feature list for this genome.          # Get the feature list for this genome.
515          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
516                # Sort and count the list.
517                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
518                my $count = scalar @featureTuples;
519                Trace("$count features found for genome $genomeID.") if T(3);
520                # Set up for our duplicate-feature check.
521                my $oldFeatureID = "";
522          # Loop through the features.          # Loop through the features.
523          for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
             $loadFeature->Add("featureIn");  
524              # Split the tuple.              # Split the tuple.
525              my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
526              # Create the feature record.                  # Check for duplicates.
527              $loadFeature->Put($featureID, 1, $type);                  if ($featureID eq $oldFeatureID) {
528                        Trace("Duplicate feature $featureID found.") if T(1);
529                    } else {
530                        $oldFeatureID = $featureID;
531                        # Count this feature.
532                        $loadFeature->Add("featureIn");
533                        # Get the functional assignment.
534                        my $assignment = $fig->function_of($featureID);
535                        # Begin building the keywords.
536                        my $keywords = "$assignment $genomeID";
537                        # Link this feature to the parent genome.
538                        $loadHasFeature->Put($genomeID, $featureID, $type);
539              # Create the aliases.              # Create the aliases.
540              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
541                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
542                            $keywords .= " $alias";
543              }              }
             # The next stuff is for a full load only.  
             if (! $limited) {  
544                  # Get the links.                  # Get the links.
545                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
546                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 559 
559                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
560                      }                      }
561                  }                  }
562                        # Now we need to find the subsystems this feature participates in.
563                        # We also add the subsystems to the keyword list. Before we do that,
564                        # we must convert underscores to spaces and tack on the classifications.
565                        my @subsystems = $fig->peg_to_subsystems($featureID);
566                        for my $subsystem (@subsystems) {
567                            # Only proceed if we like this subsystem.
568                            if (exists $subHash->{$subsystem}) {
569                                # Store the has-role link.
570                                $loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type);
571                                # Save the subsystem's keyword data.
572                                my $subKeywords = $subHash->{$subsystem};
573                                $keywords .= " $subKeywords";
574                            }
575                        }
576                        # The final task is to add virulence and essentiality attributes.
577                        if ($fig->virulent($featureID)) {
578                            $keywords .= " virulent";
579                        }
580                        if ($fig->essential($featureID)) {
581                            $keywords .= " essential";
582              }              }
583                        # Clean the keyword list.
584                        my $cleanWords = $sprout->CleanKeywords($keywords);
585                        # Create the feature record.
586                        $loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords);
587              # This part is the roughest. We need to relate the features to contig              # This part is the roughest. We need to relate the features to contig
588              # locations, and the locations must be split so that none of them exceed              # locations, and the locations must be split so that none of them exceed
589              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
# Line 512  Line 612 
612              }              }
613          }          }
614      }      }
615            }
616        }
617      # Finish the loads.      # Finish the loads.
618      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
619      return $retVal;      return $retVal;
# Line 548  Line 650 
650      my $fig = $self->{fig};      my $fig = $self->{fig};
651      # Get the table of genome IDs.      # Get the table of genome IDs.
652      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
653      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
654      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
655                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
656      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
657        } else {
658            Trace("Generating BBH data.") if T(2);
659      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
660      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
661          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
662          Trace("Processing features for genome $genomeID.") if T(3);          Trace("Processing features for genome $genomeID.") if T(3);
663          # Get the feature list for this genome.          # Get the feature list for this genome.
664          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
665                # Count the BBHs we find.
666                my $bbhCount = 0;
667          # Loop through the features.          # Loop through the features.
668          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
669              # Split the tuple.              # Split the tuple.
# Line 575  Line 679 
679                  if ($genomeHash->{$targetGenomeID}) {                  if ($genomeHash->{$targetGenomeID}) {
680                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
681                                                         $score);                                                         $score);
682                            $bbhCount++;
683                  }                  }
684              }              }
685          }          }
686                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
687            }
688      }      }
689      # Finish the loads.      # Finish the loads.
690      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 599  Line 706 
706  The following relations are loaded by this method.  The following relations are loaded by this method.
707    
708      Subsystem      Subsystem
709        SubsystemClass
710      Role      Role
711      RoleEC      RoleEC
712      SSCell      SSCell
# Line 608  Line 716 
716      OccursInSubsystem      OccursInSubsystem
717      ParticipatesIn      ParticipatesIn
718      HasSSCell      HasSSCell
     Catalyzes  
     Reaction  
719      ConsistsOfRoles      ConsistsOfRoles
720      RoleSubset      RoleSubset
721      HasRoleSubset      HasRoleSubset
722      ConsistsOfGenomes      ConsistsOfGenomes
723      GenomeSubset      GenomeSubset
724      HasGenomeSubset      HasGenomeSubset
725        Catalyzes
726        Diagram
727        RoleOccursIn
728    
729  =over 4  =over 4
730    
# Line 638  Line 747 
747      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
748      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
749      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
750      my $subsysCount = @subsysIDs;      # Get the map list.
751      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
752      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
753      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
754      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
755      my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);      my $loadSubsystem = $self->_TableLoader('Subsystem');
756      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
757      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
758      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
759      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
760      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
761      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
762      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
763      my $loadReaction = $self->_TableLoader('Reaction', $featureCount * $genomeCount);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
764      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $featureCount * $genomeCount);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
765      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
766      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
767      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
768      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
769      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
770      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
771      Trace("Beginning subsystem data load.") if T(2);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
772      # The reaction hash will contain a list of reactions for each role. When we're done,      my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
773      # a complicated sort and merge will be used to generate the Reaction and Catalyzes      if ($self->{options}->{loadOnly}) {
774      # tables.          Trace("Loading from existing files.") if T(2);
775      my %reactionsToRoles = ();      } else {
776            Trace("Generating subsystem data.") if T(2);
777            # This hash will contain the role for each EC. When we're done, this
778            # information will be used to generate the Catalyzes table.
779            my %ecToRoles = ();
780      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
781      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
782      # 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
# Line 673  Line 785 
785      my ($genomeID, $roleID);      my ($genomeID, $roleID);
786      my %roleData = ();      my %roleData = ();
787      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
788          # Get the subsystem object.          # Get the subsystem object.
789          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
790          # Get its reaction hash.              # Only proceed if the subsystem has a spreadsheet.
791          my $reactionHash = $sub->get_reactions();              if (! $sub->{empty_ss}) {
792                    Trace("Creating subsystem $subsysID.") if T(3);
793                    $loadSubsystem->Add("subsystemIn");
794          # Create the subsystem record.          # Create the subsystem record.
795          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
796          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
797          $loadSubsystem->Put($subsysID, $curator, $notes);          $loadSubsystem->Put($subsysID, $curator, $notes);
798                    # Now for the classification string. This comes back as a list
799                    # reference and we convert it to a space-delimited string.
800                    my $classList = $fig->subsystem_classification($subsysID);
801                    my $classString = join(" ", grep { $_ } @$classList);
802                    $loadSubsystemClass->Put($subsysID, $classString);
803          # Connect it to its roles. Each role is a column in the subsystem spreadsheet.          # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
804          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
805              # Connect to this role.              # Connect to this role.
# Line 697  Line 814 
814                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
815                  # Check for an EC number.                  # Check for an EC number.
816                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {                  if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
817                      $loadRoleEC->Put($roleID, $1);                              my $ec = $1;
818                  }                              $loadRoleEC->Put($roleID, $ec);
819                  # Add the role's reactions.                              $ecToRoles{$ec} = $roleID;
                 my $reactions = $reactionHash->{$roleID};  
                 for my $reactionID (@{$reactions}) {  
                     if (! exists $reactionsToRoles{$reactionID}) {  
                         # Here the reaction is brand-new, so we create its reaction  
                         # record.  
                         $loadReaction->Put($reactionID, $fig->reversible($reactionID));  
                         # We also create a blank list for it in the reaction hash.  
                         $reactionsToRoles{$reactionID} = [];  
                     }  
                     # Add the role to the reaction's role list.  
                     push @{$reactionsToRoles{$reactionID}}, $roleID;  
820                  }                  }
821              }              }
822          }          }
# Line 737  Line 843 
843                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
844                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
845                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
846                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
847                      # Only proceed if features exist.                      # Only proceed if features exist.
848                      if (@pegs > 0) {                      if (@pegs > 0) {
849                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 758  Line 864 
864                  if ($pegCount > 0) {                  if ($pegCount > 0) {
865                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
866                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                     # Partition the PEGs found into clusters.  
                     my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
867                      # Create a hash mapping PEG IDs to cluster numbers.                      # Create a hash mapping PEG IDs to cluster numbers.
868                      # We default to -1 for all of them.                      # We default to -1 for all of them.
869                      my %clusterOf = map { $_ => -1 } @pegsFound;                      my %clusterOf = map { $_ => -1 } @pegsFound;
870                                # Partition the PEGs found into clusters.
871                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
872                      for (my $i = 0; $i <= $#clusters; $i++) {                      for (my $i = 0; $i <= $#clusters; $i++) {
873                          my $subList = $clusters[$i];                          my $subList = $clusters[$i];
874                          for my $peg (@{$subList}) {                          for my $peg (@{$subList}) {
# Line 790  Line 896 
896              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
897              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
898              # Connect the subset to its roles.              # Connect the subset to its roles.
899              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
900              for my $roleID (@roles) {              for my $roleID (@roles) {
901                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
902              }              }
# Line 810  Line 916 
916              }              }
917          }          }
918      }      }
     # Before we leave, we must create the Catalyzes table. The data is all stored in  
     # "reactionToRoles" hash.  
     for my $reactionID (keys %reactionsToRoles) {  
         # Get this reaction's list of roles. We sort it so we can merge out duplicates.  
         my @roles = sort @{$reactionsToRoles{$reactionID}};  
         my $lastRole = "";  
         # Loop through the roles, creating catalyzation records.  
         for my $thisRole (@roles) {  
             if ($thisRole ne $lastRole) {  
                 $loadCatalyzes->Put($thisRole, $reactionID);  
             }  
         }  
     }  
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
919  }  }
920            # Now we loop through the diagrams. We need to create the diagram records
921  =head3 LoadDiagramData          # and link each diagram to its roles. Note that only roles which occur
922            # in subsystems (and therefore appear in the %ecToRoles hash) are
923  C<< my $stats = $spl->LoadDiagramData(); >>          # included.
924            for my $map (@maps) {
 Load the diagram data from FIG into Sprout.  
   
 Diagrams are used to organize functional roles. The diagram shows the  
 connections between chemicals that interact with a subsystem.  
   
 The following relations are loaded by this method.  
   
     Diagram  
     RoleOccursIn  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =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) {  
925          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
926          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
927          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 876  Line 930 
930          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
931          my %roleHash = ();          my %roleHash = ();
932          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
933              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
934                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
935                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
936              }              }
937          }          }
938      }      }
939            # Before we leave, we must create the Catalyzes table. We start with the reactions,
940            # then use the "ecToRoles" table to convert EC numbers to role IDs.
941            my @reactions = $fig->all_reactions();
942            for my $reactionID (@reactions) {
943                # Get this reaction's list of roles. The results will be EC numbers.
944                my @roles = $fig->catalyzed_by($reactionID);
945                # Loop through the roles, creating catalyzation records.
946                for my $thisRole (@roles) {
947                    if (exists $ecToRoles{$thisRole}) {
948                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
949                    }
950                }
951            }
952        }
953      # Finish the load.      # Finish the load.
954      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
955      return $retVal;      return $retVal;
# Line 923  Line 991 
991      my $fig = $self->{fig};      my $fig = $self->{fig};
992      # Get the genome hash.      # Get the genome hash.
993      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
994      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
995      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
996      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
997      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
998            Trace("Loading from existing files.") if T(2);
999        } else {
1000            Trace("Generating property data.") if T(2);
1001      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
1002      my %propertyKeys = ();      my %propertyKeys = ();
1003      my $nextID = 1;      my $nextID = 1;
1004      # Loop through the genomes.      # Loop through the genomes.
1005      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1006          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
1007                Trace("Generating properties for $genomeID.") if T(3);
1008          # 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
1009          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
1010          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
1011          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
1012                my $featureCount = 0;
1013                my $propertyCount = 0;
1014          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
1015          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
1016              # 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
1017              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
1018              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
1019                    # Add essentiality and virulence attributes.
1020                    if ($fig->essential($fid)) {
1021                        push @attributeList, [$fid, 'essential', 1, ''];
1022                    }
1023                    if ($fig->virulent($fid)) {
1024                        push @attributeList, [$fid, 'virulent', 1, ''];
1025                    }
1026                    if (scalar @attributeList) {
1027                        $featureCount++;
1028                    }
1029              # Loop through the attributes.              # Loop through the attributes.
1030              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
1031                        $propertyCount++;
1032                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
1033                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
1034                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 967  Line 1050 
1050                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
1051              }              }
1052          }          }
1053                # Update the statistics.
1054                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
1055                $loadHasProperty->Add("featuresIn", $featureCount);
1056                $loadHasProperty->Add("propertiesIn", $propertyCount);
1057            }
1058      }      }
1059      # Finish the load.      # Finish the load.
1060      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1007  Line 1095 
1095      my $fig = $self->{fig};      my $fig = $self->{fig};
1096      # Get the genome hash.      # Get the genome hash.
1097      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1098      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1099      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1100      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1101      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1102      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1103      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1104      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1105            Trace("Loading from existing files.") if T(2);
1106        } else {
1107            Trace("Generating annotation data.") if T(2);
1108      # 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
1109      # user records.      # user records.
1110      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 1028  Line 1118 
1118      # Loop through the genomes.      # Loop through the genomes.
1119      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1120          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);  
1121              # 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
1122              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1123              my %seenTimestamps = ();              my %seenTimestamps = ();
1124              # Check for a functional assignment.              # Get the genome's annotations.
1125              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1126              if ($func) {              Trace("Processing annotations.") if T(2);
1127                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1128                  # assignment annotation for it.                  # Get the annotation tuple.
1129                  if (! FIG::hypo($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};  
1130                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1131                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1132                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1133                  # stop the substitution search.                  # stop the substitution search.
1134                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1067  Line 1141 
1141                      # Here it's a number. We need to insure the one we use to form                      # Here it's a number. We need to insure the one we use to form
1142                      # the key is unique.                      # the key is unique.
1143                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1144                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1145                          $keyStamp++;                          $keyStamp++;
1146                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1147                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1148                        $seenTimestamps{$annotationID} = 1;
1149                      # Insure the user exists.                      # Insure the user exists.
1150                      if (! $users{$user}) {                      if (! $users{$user}) {
1151                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1129  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      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1207      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1208      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1209      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1210      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1211            Trace("Loading from existing files.") if T(2);
1212        } else {
1213            Trace("Generating annotation data.") if T(2);
1214      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1215      my %sourceURL = ();      my %sourceURL = ();
1216      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1164  Line 1240 
1240      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1241          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1242      }      }
1243        }
1244      # Finish the load.      # Finish the load.
1245      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1246      return $retVal;      return $retVal;
# Line 1203  Line 1280 
1280      my $fig = $self->{fig};      my $fig = $self->{fig};
1281      # Get the genome hash.      # Get the genome hash.
1282      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1283      # 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
1284      # it the key.      # it the key.
1285      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1286      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1287      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1288      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1289      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1290            Trace("Loading from existing files.") if T(2);
1291        } else {
1292            Trace("Generating external data.") if T(2);
1293      # 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.
1294      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1295      my $orgLine;      my $orgLine;
1296      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1297          # Clean the input line.          # Clean the input line.
# Line 1224  Line 1303 
1303      close ORGS;      close ORGS;
1304      # Now the function file.      # Now the function file.
1305      my $funcLine;      my $funcLine;
1306      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1307      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1308          # Clean the line ending.          # Clean the line ending.
1309          chomp $funcLine;          chomp $funcLine;
# Line 1240  Line 1319 
1319              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1320          }          }
1321      }      }
1322        }
1323      # Finish the load.      # Finish the load.
1324      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1325      return $retVal;      return $retVal;
# Line 1256  Line 1336 
1336    
1337  The following relations are loaded by this method.  The following relations are loaded by this method.
1338    
1339        Reaction
1340      ReactionURL      ReactionURL
1341      Compound      Compound
1342      CompoundName      CompoundName
# Line 1279  Line 1360 
1360      my ($self) = @_;      my ($self) = @_;
1361      # Get the FIG object.      # Get the FIG object.
1362      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1363      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1364      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1365      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1366      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1367      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1368      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1369      Trace("Beginning reaction/compound data load.") if T(2);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1370      # Create a hash to remember the compounds we've generated in the compound table.      if ($self->{options}->{loadOnly}) {
1371      my %compoundHash = ();          Trace("Loading from existing files.") if T(2);
1372      # Loop through the reactions.      } else {
1373            Trace("Generating annotation data.") if T(2);
1374            # First we create the compounds.
1375            my @compounds = $fig->all_compounds();
1376            for my $cid (@compounds) {
1377                # Check for names.
1378                my @names = $fig->names_of_compound($cid);
1379                # Each name will be given a priority number, starting with 1.
1380                my $prio = 1;
1381                for my $name (@names) {
1382                    $loadCompoundName->Put($cid, $name, $prio++);
1383                }
1384                # Create the main compound record. Note that the first name
1385                # becomes the label.
1386                my $label = (@names > 0 ? $names[0] : $cid);
1387                $loadCompound->Put($cid, $label);
1388                # Check for a CAS ID.
1389                my $cas = $fig->cas($cid);
1390                if ($cas) {
1391                    $loadCompoundCAS->Put($cid, $cas);
1392                }
1393            }
1394            # All the compounds are set up, so we need to loop through the reactions next. First,
1395            # we initialize the discriminator index. This is a single integer used to insure
1396            # duplicate elements in a reaction are not accidentally collapsed.
1397            my $discrim = 0;
1398      my @reactions = $fig->all_reactions();      my @reactions = $fig->all_reactions();
1399      for my $reactionID (@reactions) {      for my $reactionID (@reactions) {
1400                # Create the reaction record.
1401                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1402          # Compute the reaction's URL.          # Compute the reaction's URL.
1403          my $url = HTML::reaction_link($reactionID);          my $url = HTML::reaction_link($reactionID);
1404          # Put it in the ReactionURL table.          # Put it in the ReactionURL table.
# Line 1302  Line 1407 
1407          # substrates first and then products.          # substrates first and then products.
1408          for my $product (0, 1) {          for my $product (0, 1) {
1409              # Get the compounds of the current type for the current reaction. FIG will              # Get the compounds of the current type for the current reaction. FIG will
1410              # give us 3-tuples: [ID, Stoichometry, main-flag]. At this time we do not                  # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1411              # have location data in SEED, so it defaults to the empty string.              # have location data in SEED, so it defaults to the empty string.
1412              my @compounds = $fig->reaction2comp($reactionID, $product);              my @compounds = $fig->reaction2comp($reactionID, $product);
1413              for my $compData (@compounds) {              for my $compData (@compounds) {
1414                  # Extract the compound data from the current tuple.                  # Extract the compound data from the current tuple.
1415                  my ($cid, $stoich, $main) = @{$compData};                  my ($cid, $stoich, $main) = @{$compData};
1416                  # Link the compound to the reaction.                  # Link the compound to the reaction.
1417                  $loadIsAComponentOf->Put($cid, $reactionID, "", $main, $product, $stoich);                      $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1418                  # If this is a new compound, we need to create its table entries.                                               $product, $stoich);
                 if (! exists $compoundHash{$cid}) {  
                     $compoundHash{$cid} = 1;  
                     # Create the main compound record and denote we've done it.  
                     $loadCompound->Put($cid);  
                     # Check for a CAS ID.  
                     my $cas = $fig->cas($cid);  
                     if ($cas) {  
                         $loadCompoundCAS->Put($cid, $cas);  
                     }  
                     # Check for names.  
                     my @names = $fig->names_of_compound($cid);  
                     # Each name will be given a priority number, starting with 1.  
                     my $prio = 0;  
                     for my $name (@names) {  
                         $loadCompoundName->Put($cid, $name, $prio++);  
                     }  
1419                  }                  }
1420              }              }
1421          }          }
# Line 1346  Line 1435 
1435    
1436      GenomeGroups      GenomeGroups
1437    
1438  There is no direct support for genome groups in FIG, so we access the SEED  Currently, we do not use groups. We used to use them for NMPDR groups,
1439    butThere is no direct support for genome groups in FIG, so we access the SEED
1440  files directly.  files directly.
1441    
1442  =over 4  =over 4
# Line 1366  Line 1456 
1456      my $fig = $self->{fig};      my $fig = $self->{fig};
1457      # Get the genome hash.      # Get the genome hash.
1458      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1459      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1460      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1461      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1462            Trace("Loading from existing files.") if T(2);
1463        } else {
1464            Trace("Generating group data.") if T(2);
1465            # Currently there are no groups.
1466        }
1467        # Finish the load.
1468        my $retVal = $self->_FinishAll();
1469        return $retVal;
1470    }
1471    
1472    =head3 LoadSynonymData
1473    
1474    C<< my $stats = $spl->LoadSynonymData(); >>
1475    
1476    Load the synonym groups into Sprout.
1477    
1478    The following relations are loaded by this method.
1479    
1480        SynonymGroup
1481        IsSynonymGroupFor
1482    
1483    The source information for these relations is taken from the C<maps_to_id> method
1484    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1485    SQL against the FIG database.
1486    
1487    =over 4
1488    
1489    =item RETURNS
1490    
1491    Returns a statistics object for the loads.
1492    
1493    =back
1494    
1495    =cut
1496    #: Return Type $%;
1497    sub LoadSynonymData {
1498        # Get this object instance.
1499        my ($self) = @_;
1500        # Get the FIG object.
1501        my $fig = $self->{fig};
1502        # Get the genome hash.
1503        my $genomeHash = $self->{genomes};
1504        # Create a load object for the table we're loading.
1505        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1506        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1507        if ($self->{options}->{loadOnly}) {
1508            Trace("Loading from existing files.") if T(2);
1509        } else {
1510            Trace("Generating synonym group data.") if T(2);
1511            # Get the database handle.
1512            my $dbh = $fig->db_handle();
1513            # Ask for the synonyms.
1514            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1515            my $result = $sth->execute();
1516            if (! defined($result)) {
1517                Confess("Database error in Synonym load: " . $sth->errstr());
1518            } else {
1519                # Remember the current synonym.
1520                my $current_syn = "";
1521                # Count the features.
1522                my $featureCount = 0;
1523                # Loop through the synonym/peg pairs.
1524                while (my @row = $sth->fetchrow()) {
1525                    # Get the synonym ID and feature ID.
1526                    my ($syn_id, $peg) = @row;
1527                    # Insure it's for one of our genomes.
1528                    my $genomeID = FIG::genome_of($peg);
1529                    if (exists $genomeHash->{$genomeID}) {
1530                        # Verify the synonym.
1531                        if ($syn_id ne $current_syn) {
1532                            # It's new, so put it in the group table.
1533                            $loadSynonymGroup->Put($syn_id);
1534                            $current_syn = $syn_id;
1535                        }
1536                        # Connect the synonym to the peg.
1537                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1538                        # Count this feature.
1539                        $featureCount++;
1540                        if ($featureCount % 1000 == 0) {
1541                            Trace("$featureCount features processed.") if T(3);
1542                        }
1543                    }
1544                }
1545            }
1546        }
1547        # Finish the load.
1548        my $retVal = $self->_FinishAll();
1549        return $retVal;
1550    }
1551    
1552    =head3 LoadFamilyData
1553    
1554    C<< my $stats = $spl->LoadFamilyData(); >>
1555    
1556    Load the protein families into Sprout.
1557    
1558    The following relations are loaded by this method.
1559    
1560        Family
1561        IsFamilyForFeature
1562    
1563    The source information for these relations is taken from the C<families_for_protein>,
1564    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1565    
1566    =over 4
1567    
1568    =item RETURNS
1569    
1570    Returns a statistics object for the loads.
1571    
1572    =back
1573    
1574    =cut
1575    #: Return Type $%;
1576    sub LoadFamilyData {
1577        # Get this object instance.
1578        my ($self) = @_;
1579        # Get the FIG object.
1580        my $fig = $self->{fig};
1581        # Get the genome hash.
1582        my $genomeHash = $self->{genomes};
1583        # Create load objects for the tables we're loading.
1584        my $loadFamily = $self->_TableLoader('Family');
1585        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1586        if ($self->{options}->{loadOnly}) {
1587            Trace("Loading from existing files.") if T(2);
1588        } else {
1589            Trace("Generating family data.") if T(2);
1590            # Create a hash for the family IDs.
1591            my %familyHash = ();
1592      # Loop through the genomes.      # Loop through the genomes.
1593      my $line;          for my $genomeID (sort keys %{$genomeHash}) {
1594      for my $genomeID (keys %{$genomeHash}) {              Trace("Processing features for $genomeID.") if T(2);
1595          Trace("Processing $genomeID.") if T(3);              # Loop through this genome's PEGs.
1596          # Open the NMPDR group file for this genome.              for my $fid ($fig->all_features($genomeID, "peg")) {
1597          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&                  $loadIsFamilyForFeature->Add("features", 1);
1598              defined($line = <TMP>)) {                  # Get this feature's families.
1599              # Clean the line ending.                  my @families = $fig->families_for_protein($fid);
1600              chomp $line;                  # Loop through the families, connecting them to the feature.
1601              # Add the group to the table. Note that there can only be one group                  for my $family (@families) {
1602              # per genome.                      $loadIsFamilyForFeature->Put($family, $fid);
1603              $loadGenomeGroups->Put($genomeID, $line);                      # If this is a new family, create a record for it.
1604                        if (! exists $familyHash{$family}) {
1605                            $familyHash{$family} = 1;
1606                            $loadFamily->Add("families", 1);
1607                            my $size = $fig->sz_family($family);
1608                            my $func = $fig->family_function($family);
1609                            $loadFamily->Put($family, $size, $func);
1610                        }
1611                    }
1612                }
1613          }          }
         close TMP;  
1614      }      }
1615      # Finish the load.      # Finish the load.
1616      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1617      return $retVal;      return $retVal;
1618  }  }
1619    
1620    
1621    
1622  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1623    
1624  =head3 TableLoader  =head3 TableLoader
# Line 1406  Line 1635 
1635    
1636  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1637    
1638  =item rowCount (optional)  =item ignore
1639    
1640  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1641    
1642  =item RETURN  =item RETURN
1643    
# Line 1420  Line 1649 
1649    
1650  sub _TableLoader {  sub _TableLoader {
1651      # Get the parameters.      # Get the parameters.
1652      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1653      # Create the load object.      # Create the load object.
1654      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1655                                   $ignore);
1656      # Cache it in the loader list.      # Cache it in the loader list.
1657      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1658      # Return it to the caller.      # Return it to the caller.
# Line 1456  Line 1686 
1686      my $retVal = Stats->new();      my $retVal = Stats->new();
1687      # Get the loader list.      # Get the loader list.
1688      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1689        # Create a hash to hold the statistics objects, keyed on relation name.
1690        my %loaderHash = ();
1691      # 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
1692      # 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.
1693      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1694          # Trace the fact that we're cleaning up.          # Get the relation name.
1695          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1696          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1697            if ($loader->Ignore) {
1698                Trace("Relation $relName not loaded.") if T(2);
1699            } else {
1700                # Here we really need to finish.
1701                Trace("Finishing $relName.") if T(2);
1702          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1703                $loaderHash{$relName} = $stats;
1704            }
1705        }
1706        # Now we loop through again, actually loading the tables. We want to finish before
1707        # loading so that if something goes wrong at this point, all the load files are usable
1708        # and we don't have to redo all that work.
1709        for my $relName (sort keys %loaderHash) {
1710            # Get the statistics for this relation.
1711            my $stats = $loaderHash{$relName};
1712            # Check for a database load.
1713          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1714              # Here we want to use the load file just created to load the database.              # Here we want to use the load file just created to load the database.
1715              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);

Legend:
Removed from v.1.19  
changed lines
  Added in v.1.72

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3