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

Diff of /Sprout/SproutLoad.pm

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

revision 1.21, Sat Nov 12 03:42:48 2005 UTC revision 1.75, Sun Oct 22 05:17:10 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                        $loadFeature->Add("featureIn");
533                        # Begin building the keywords.
534                        my @keywords = ($genomeID);
535                        # Get the functional assignment and aliases. This
536                        # depends on the feature type.
537                        my $assignment;
538                        if ($type eq "peg") {
539                            $assignment = $fig->function_of($featureID);
540              # Create the aliases.              # Create the aliases.
541              for my $alias ($fig->feature_aliases($featureID)) {              for my $alias ($fig->feature_aliases($featureID)) {
542                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
543                                push @keywords, $alias;
544              }              }
545              # The next stuff is for a full load only.                      } else {
546              if (! $limited) {                          # For other types, the assignment is the first (and ONLY) alias.
547                            ($assignment) = $fig->feature_aliases($featureID);
548                        }
549                        Trace("Assignment for $featureID is: $assignment") if T(4);
550                        # Break the assignment into words and shove it onto the
551                        # keyword list.
552                        push @keywords, split(/\s+/, $assignment);
553                        # Link this feature to the parent genome.
554                        $loadHasFeature->Put($genomeID, $featureID, $type);
555                  # Get the links.                  # Get the links.
556                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
557                  for my $link (@links) {                  for my $link (@links) {
# Line 483  Line 570 
570                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
571                      }                      }
572                  }                  }
573                        # Now we need to find the subsystems this feature participates in.
574                        # We also add the subsystems to the keyword list. Before we do that,
575                        # we must convert underscores to spaces and tack on the classifications.
576                        my @subsystems = $fig->peg_to_subsystems($featureID);
577                        for my $subsystem (@subsystems) {
578                            # Only proceed if we like this subsystem.
579                            if (exists $subHash->{$subsystem}) {
580                                # Store the has-role link.
581                                $loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type);
582                                # Save the subsystem's keyword data.
583                                my $subKeywords = $subHash->{$subsystem};
584                                push @keywords, split /\s+/, $subKeywords;
585                                # Now we need to get this feature's role in the subsystem.
586                                my $subObject = $fig->get_subsystem($subsystem);
587                                my @roleColumns = $subObject->get_peg_roles($featureID);
588                                my @allRoles = $subObject->get_roles();
589                                for my $col (@roleColumns) {
590                                    my $role = $allRoles[$col];
591                                    push @keywords, split /\s+/, $role;
592                                    push @keywords, $subObject->get_role_abbr($col);
593                                }
594              }              }
595                        }
596                        # The final task is to add virulence and essentiality attributes.
597                        if ($fig->virulent($featureID)) {
598                            push @keywords, "virulent";
599                        }
600                        if ($fig->essential($featureID)) {
601                            push @keywords, "essential";
602                        }
603                        # Now we need to bust up hyphenated words in the keyword
604                        # list.
605                        my $keywordString = "";
606                        for my $keyword (@keywords) {
607                            if (length $keyword >= 4) {
608                                $keywordString .= " $keyword";
609                                if ($keyword =~ /-/) {
610                                    my @words = grep { length($_) >= 4 } split /-/, $keyword;
611                                    $keywordString .= join(" ", "", @words);
612                                }
613                            }
614                        }
615                        # Clean the keyword list.
616                        my $cleanWords = $sprout->CleanKeywords($keywordString);
617                        Trace("Keyword string for $featureID: $cleanWords") if T(4);
618                        # Create the feature record.
619                        $loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords);
620              # 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
621              # 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
622              # 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 645 
645              }              }
646          }          }
647      }      }
     # Finish the loads.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
 =head3 LoadBBHData  
   
 C<< my $stats = $spl->LoadBBHData(); >>  
   
 Load the bidirectional best hit data from FIG into Sprout.  
   
 Sprout does not store information on similarities. Instead, it has only the  
 bi-directional best hits. Even so, the BBH table is one of the largest in  
 the database.  
   
 The following relations are loaded by this method.  
   
     IsBidirectionalBestHitOf  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadBBHData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the table of genome IDs.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
     # Create load objects for each of the tables we're loading.  
     my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',  
                                                            $featureCount * $genomeCount);  
     Trace("Beginning BBH load.") if T(2);  
     # Now we loop through the genomes, generating the data for each one.  
     for my $genomeID (sort keys %{$genomeHash}) {  
         $loadIsBidirectionalBestHitOf->Add("genomeIn");  
         Trace("Processing features for genome $genomeID.") if T(3);  
         # Get the feature list for this genome.  
         my $features = $fig->all_features_detailed($genomeID);  
         # Loop through the features.  
         for my $featureData (@{$features}) {  
             # Split the tuple.  
             my ($featureID, $locations, $aliases, $type) = @{$featureData};  
             # Get the bi-directional best hits.  
             my @bbhList = $fig->bbhs($featureID);  
             for my $bbhEntry (@bbhList) {  
                 # Get the target feature ID and the score.  
                 my ($targetID, $score) = @{$bbhEntry};  
                 # Check the target feature's genome.  
                 my $targetGenomeID = $fig->genome_of($targetID);  
                 # Only proceed if it's one of our genomes.  
                 if ($genomeHash->{$targetGenomeID}) {  
                     $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,  
                                                        $score);  
                 }  
             }  
648          }          }
649      }      }
650      # Finish the loads.      # Finish the loads.
# Line 599  Line 667 
667  The following relations are loaded by this method.  The following relations are loaded by this method.
668    
669      Subsystem      Subsystem
670        SubsystemClass
671      Role      Role
672      RoleEC      RoleEC
673      SSCell      SSCell
# Line 639  Line 708 
708      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
709      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
710      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
     my $subsysCount = @subsysIDs;  
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
711      # Get the map list.      # Get the map list.
712      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
     my $mapCount = @maps;  
     # Create load objects for each of the tables we're loading.  
     my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);  
     my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);  
     my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);  
     my $loadRole = $self->_TableLoader('Role', $featureCount * 6);  
     my $loadRoleEC = $self->_TableLoader('RoleEC', $featureCount * 6);  
     my $loadCatalyzes = $self->_TableLoader('Catalyzes', $genomeCount * $featureCount);  
     my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);  
     my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);  
     my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);  
     my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);  
     my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);  
     my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);  
     my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);  
     my $loadRoleSubset = $self->_TableLoader('RoleSubset', $subsysCount * 50);  
     my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $subsysCount * 50);  
     my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $featureCount * $genomeCount);  
     my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $featureCount * $genomeCount);  
     my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $subsysCount * 50);  
     my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $subsysCount * 50);  
713      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
714      Trace("Beginning subsystem data load.") if T(2);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
715        my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
716        my $loadSubsystem = $self->_TableLoader('Subsystem');
717        my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
718        my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
719        my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
720        my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
721        my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
722        my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
723        my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
724        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
725        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
726        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
727        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
728        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
729        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
730        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
731        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
732        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
733        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
734        if ($self->{options}->{loadOnly}) {
735            Trace("Loading from existing files.") if T(2);
736        } else {
737            Trace("Generating subsystem data.") if T(2);
738      # This hash will contain the role for each EC. When we're done, this      # This hash will contain the role for each EC. When we're done, this
739      # information will be used to generate the Catalyzes table.      # information will be used to generate the Catalyzes table.
740      my %ecToRoles = ();      my %ecToRoles = ();
# Line 678  Line 746 
746      my ($genomeID, $roleID);      my ($genomeID, $roleID);
747      my %roleData = ();      my %roleData = ();
748      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
         Trace("Creating subsystem $subsysID.") if T(3);  
         $loadSubsystem->Add("subsystemIn");  
749          # Get the subsystem object.          # Get the subsystem object.
750          my $sub = $fig->get_subsystem($subsysID);          my $sub = $fig->get_subsystem($subsysID);
751                # Only proceed if the subsystem has a spreadsheet.
752                if (! $sub->{empty_ss}) {
753                    Trace("Creating subsystem $subsysID.") if T(3);
754                    $loadSubsystem->Add("subsystemIn");
755          # Create the subsystem record.          # Create the subsystem record.
756          my $curator = $sub->get_curator();          my $curator = $sub->get_curator();
757          my $notes = $sub->get_notes();          my $notes = $sub->get_notes();
758          $loadSubsystem->Put($subsysID, $curator, $notes);          $loadSubsystem->Put($subsysID, $curator, $notes);
759                    # Now for the classification string. This comes back as a list
760                    # reference and we convert it to a space-delimited string.
761                    my $classList = $fig->subsystem_classification($subsysID);
762                    my $classString = join(" : ", grep { $_ } @$classList);
763                    $loadSubsystemClass->Put($subsysID, $classString);
764          # 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.
765          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
766              # Connect to this role.              # Connect to this role.
# Line 729  Line 804 
804                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
805                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
806                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
807                      my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
808                      # Only proceed if features exist.                      # Only proceed if features exist.
809                      if (@pegs > 0) {                      if (@pegs > 0) {
810                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
# Line 750  Line 825 
825                  if ($pegCount > 0) {                  if ($pegCount > 0) {
826                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                      Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
827                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                      $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                     # Partition the PEGs found into clusters.  
                     my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
828                      # Create a hash mapping PEG IDs to cluster numbers.                      # Create a hash mapping PEG IDs to cluster numbers.
829                      # We default to -1 for all of them.                      # We default to -1 for all of them.
830                      my %clusterOf = map { $_ => -1 } @pegsFound;                      my %clusterOf = map { $_ => -1 } @pegsFound;
831                                # Partition the PEGs found into clusters.
832                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
833                      for (my $i = 0; $i <= $#clusters; $i++) {                      for (my $i = 0; $i <= $#clusters; $i++) {
834                          my $subList = $clusters[$i];                          my $subList = $clusters[$i];
835                          for my $peg (@{$subList}) {                          for my $peg (@{$subList}) {
# Line 782  Line 857 
857              # Connect the subset to the subsystem.              # Connect the subset to the subsystem.
858              $loadHasRoleSubset->Put($subsysID, $actualID);              $loadHasRoleSubset->Put($subsysID, $actualID);
859              # Connect the subset to its roles.              # Connect the subset to its roles.
860              my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
861              for my $roleID (@roles) {              for my $roleID (@roles) {
862                  $loadConsistsOfRoles->Put($actualID, $roleID);                  $loadConsistsOfRoles->Put($actualID, $roleID);
863              }              }
# Line 802  Line 877 
877              }              }
878          }          }
879      }      }
880            }
881      # Now we loop through the diagrams. We need to create the diagram records      # Now we loop through the diagrams. We need to create the diagram records
882      # and link each diagram to its roles. Note that only roles which occur      # and link each diagram to its roles. Note that only roles which occur
883      # in subsystems (and therefore appear in the %ecToRoles hash) are      # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 834  Line 910 
910              }              }
911          }          }
912      }      }
913        }
914      # Finish the load.      # Finish the load.
915      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
916      return $retVal;      return $retVal;
# Line 875  Line 952 
952      my $fig = $self->{fig};      my $fig = $self->{fig};
953      # Get the genome hash.      # Get the genome hash.
954      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
955      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
956      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
957      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
958      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
959            Trace("Loading from existing files.") if T(2);
960        } else {
961            Trace("Generating property data.") if T(2);
962      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
963      my %propertyKeys = ();      my %propertyKeys = ();
964      my $nextID = 1;      my $nextID = 1;
965      # Loop through the genomes.      # Loop through the genomes.
966      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
967          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
968                Trace("Generating properties for $genomeID.") if T(3);
969          # 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
970          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
971          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
972          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
973                my $featureCount = 0;
974                my $propertyCount = 0;
975          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
976          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
977              # 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
978              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
979              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
980                    # Add essentiality and virulence attributes.
981                    if ($fig->essential($fid)) {
982                        push @attributeList, [$fid, 'essential', 1, ''];
983                    }
984                    if ($fig->virulent($fid)) {
985                        push @attributeList, [$fid, 'virulent', 1, ''];
986                    }
987                    if (scalar @attributeList) {
988                        $featureCount++;
989                    }
990              # Loop through the attributes.              # Loop through the attributes.
991              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
992                        $propertyCount++;
993                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
994                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
995                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 919  Line 1011 
1011                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
1012              }              }
1013          }          }
1014                # Update the statistics.
1015                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
1016                $loadHasProperty->Add("featuresIn", $featureCount);
1017                $loadHasProperty->Add("propertiesIn", $propertyCount);
1018            }
1019      }      }
1020      # Finish the load.      # Finish the load.
1021      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 959  Line 1056 
1056      my $fig = $self->{fig};      my $fig = $self->{fig};
1057      # Get the genome hash.      # Get the genome hash.
1058      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1059      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1060      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1061      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1062      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1063      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1064      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1065      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1066            Trace("Loading from existing files.") if T(2);
1067        } else {
1068            Trace("Generating annotation data.") if T(2);
1069      # 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
1070      # user records.      # user records.
1071      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 980  Line 1079 
1079      # Loop through the genomes.      # Loop through the genomes.
1080      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1081          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);  
1082              # 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
1083              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1084              my %seenTimestamps = ();              my %seenTimestamps = ();
1085              # Check for a functional assignment.              # Get the genome's annotations.
1086              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1087              if ($func) {              Trace("Processing annotations.") if T(2);
1088                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1089                  # assignment annotation for it.                  # Get the annotation tuple.
1090                  if (! FIG::hypo($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};  
1091                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1092                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1093                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1094                  # stop the substitution search.                  # stop the substitution search.
1095                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1019  Line 1102 
1102                      # 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
1103                      # the key is unique.                      # the key is unique.
1104                      my $keyStamp = $timestamp;                      my $keyStamp = $timestamp;
1105                      while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1106                          $keyStamp++;                          $keyStamp++;
1107                      }                      }
                     $seenTimestamps{$keyStamp} = 1;  
1108                      my $annotationID = "$peg:$keyStamp";                      my $annotationID = "$peg:$keyStamp";
1109                        $seenTimestamps{$annotationID} = 1;
1110                      # Insure the user exists.                      # Insure the user exists.
1111                      if (! $users{$user}) {                      if (! $users{$user}) {
1112                          $loadSproutUser->Put($user, "SEED user");                          $loadSproutUser->Put($user, "SEED user");
# Line 1081  Line 1164 
1164      my $fig = $self->{fig};      my $fig = $self->{fig};
1165      # Get the genome hash.      # Get the genome hash.
1166      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1167      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1168      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1169      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1170      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1171      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1172            Trace("Loading from existing files.") if T(2);
1173        } else {
1174            Trace("Generating annotation data.") if T(2);
1175      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1176      my %sourceURL = ();      my %sourceURL = ();
1177      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1116  Line 1201 
1201      for my $sourceID (keys %sourceDesc) {      for my $sourceID (keys %sourceDesc) {
1202          $loadSource->Put($sourceID, $sourceDesc{$sourceID});          $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1203      }      }
1204        }
1205      # Finish the load.      # Finish the load.
1206      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1207      return $retVal;      return $retVal;
# Line 1155  Line 1241 
1241      my $fig = $self->{fig};      my $fig = $self->{fig};
1242      # Get the genome hash.      # Get the genome hash.
1243      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1244      # 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
1245      # it the key.      # it the key.
1246      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1247      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1248      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1249      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1250      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1251            Trace("Loading from existing files.") if T(2);
1252        } else {
1253            Trace("Generating external data.") if T(2);
1254      # 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.
1255      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1256      my $orgLine;      my $orgLine;
1257      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1258          # Clean the input line.          # Clean the input line.
# Line 1176  Line 1264 
1264      close ORGS;      close ORGS;
1265      # Now the function file.      # Now the function file.
1266      my $funcLine;      my $funcLine;
1267      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1268      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1269          # Clean the line ending.          # Clean the line ending.
1270          chomp $funcLine;          chomp $funcLine;
# Line 1192  Line 1280 
1280              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1281          }          }
1282      }      }
1283        }
1284      # Finish the load.      # Finish the load.
1285      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1286      return $retVal;      return $retVal;
# Line 1232  Line 1321 
1321      my ($self) = @_;      my ($self) = @_;
1322      # Get the FIG object.      # Get the FIG object.
1323      my $fig = $self->{fig};      my $fig = $self->{fig};
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     my $genomeCount = (keys %{$genomeHash});  
1324      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1325      my $loadReaction = $self->_TableLoader('Reaction', $genomeCount * 4000);      my $loadReaction = $self->_TableLoader('Reaction');
1326      my $loadReactionURL = $self->_TableLoader('ReactionURL', $genomeCount * 4000);      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1327      my $loadCompound = $self->_TableLoader('Compound', $genomeCount * 4000);      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1328      my $loadCompoundName = $self->_TableLoader('CompoundName', $genomeCount * 8000);      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1329      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $genomeCount * 4000);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1330      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $genomeCount * 12000);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1331      Trace("Beginning reaction/compound data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1332            Trace("Loading from existing files.") if T(2);
1333        } else {
1334            Trace("Generating annotation data.") if T(2);
1335      # First we create the compounds.      # First we create the compounds.
1336      my @compounds = $fig->all_compounds();      my @compounds = $fig->all_compounds();
1337      for my $cid (@compounds) {      for my $cid (@compounds) {
# Line 1291  Line 1380 
1380              }              }
1381          }          }
1382      }      }
1383        }
1384      # Finish the load.      # Finish the load.
1385      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1386      return $retVal;      return $retVal;
# Line 1306  Line 1396 
1396    
1397      GenomeGroups      GenomeGroups
1398    
1399  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,
1400    butThere is no direct support for genome groups in FIG, so we access the SEED
1401  files directly.  files directly.
1402    
1403  =over 4  =over 4
# Line 1326  Line 1417 
1417      my $fig = $self->{fig};      my $fig = $self->{fig};
1418      # Get the genome hash.      # Get the genome hash.
1419      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1420      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1421      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1422      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1423            Trace("Loading from existing files.") if T(2);
1424        } else {
1425            Trace("Generating group data.") if T(2);
1426            # Currently there are no groups.
1427        }
1428        # Finish the load.
1429        my $retVal = $self->_FinishAll();
1430        return $retVal;
1431    }
1432    
1433    =head3 LoadSynonymData
1434    
1435    C<< my $stats = $spl->LoadSynonymData(); >>
1436    
1437    Load the synonym groups into Sprout.
1438    
1439    The following relations are loaded by this method.
1440    
1441        SynonymGroup
1442        IsSynonymGroupFor
1443    
1444    The source information for these relations is taken from the C<maps_to_id> method
1445    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1446    SQL against the FIG database.
1447    
1448    =over 4
1449    
1450    =item RETURNS
1451    
1452    Returns a statistics object for the loads.
1453    
1454    =back
1455    
1456    =cut
1457    #: Return Type $%;
1458    sub LoadSynonymData {
1459        # Get this object instance.
1460        my ($self) = @_;
1461        # Get the FIG object.
1462        my $fig = $self->{fig};
1463        # Get the genome hash.
1464        my $genomeHash = $self->{genomes};
1465        # Create a load object for the table we're loading.
1466        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1467        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1468        if ($self->{options}->{loadOnly}) {
1469            Trace("Loading from existing files.") if T(2);
1470        } else {
1471            Trace("Generating synonym group data.") if T(2);
1472            # Get the database handle.
1473            my $dbh = $fig->db_handle();
1474            # Ask for the synonyms.
1475            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1476            my $result = $sth->execute();
1477            if (! defined($result)) {
1478                Confess("Database error in Synonym load: " . $sth->errstr());
1479            } else {
1480                # Remember the current synonym.
1481                my $current_syn = "";
1482                # Count the features.
1483                my $featureCount = 0;
1484                # Loop through the synonym/peg pairs.
1485                while (my @row = $sth->fetchrow()) {
1486                    # Get the synonym ID and feature ID.
1487                    my ($syn_id, $peg) = @row;
1488                    # Insure it's for one of our genomes.
1489                    my $genomeID = FIG::genome_of($peg);
1490                    if (exists $genomeHash->{$genomeID}) {
1491                        # Verify the synonym.
1492                        if ($syn_id ne $current_syn) {
1493                            # It's new, so put it in the group table.
1494                            $loadSynonymGroup->Put($syn_id);
1495                            $current_syn = $syn_id;
1496                        }
1497                        # Connect the synonym to the peg.
1498                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1499                        # Count this feature.
1500                        $featureCount++;
1501                        if ($featureCount % 1000 == 0) {
1502                            Trace("$featureCount features processed.") if T(3);
1503                        }
1504                    }
1505                }
1506            }
1507        }
1508        # Finish the load.
1509        my $retVal = $self->_FinishAll();
1510        return $retVal;
1511    }
1512    
1513    =head3 LoadFamilyData
1514    
1515    C<< my $stats = $spl->LoadFamilyData(); >>
1516    
1517    Load the protein families into Sprout.
1518    
1519    The following relations are loaded by this method.
1520    
1521        Family
1522        IsFamilyForFeature
1523    
1524    The source information for these relations is taken from the C<families_for_protein>,
1525    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1526    
1527    =over 4
1528    
1529    =item RETURNS
1530    
1531    Returns a statistics object for the loads.
1532    
1533    =back
1534    
1535    =cut
1536    #: Return Type $%;
1537    sub LoadFamilyData {
1538        # Get this object instance.
1539        my ($self) = @_;
1540        # Get the FIG object.
1541        my $fig = $self->{fig};
1542        # Get the genome hash.
1543        my $genomeHash = $self->{genomes};
1544        # Create load objects for the tables we're loading.
1545        my $loadFamily = $self->_TableLoader('Family');
1546        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1547        if ($self->{options}->{loadOnly}) {
1548            Trace("Loading from existing files.") if T(2);
1549        } else {
1550            Trace("Generating family data.") if T(2);
1551            # Create a hash for the family IDs.
1552            my %familyHash = ();
1553      # Loop through the genomes.      # Loop through the genomes.
1554      my $line;          for my $genomeID (sort keys %{$genomeHash}) {
1555      for my $genomeID (keys %{$genomeHash}) {              Trace("Processing features for $genomeID.") if T(2);
1556          Trace("Processing $genomeID.") if T(3);              # Loop through this genome's PEGs.
1557          # Open the NMPDR group file for this genome.              for my $fid ($fig->all_features($genomeID, "peg")) {
1558          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&                  $loadIsFamilyForFeature->Add("features", 1);
1559              defined($line = <TMP>)) {                  # Get this feature's families.
1560              # Clean the line ending.                  my @families = $fig->families_for_protein($fid);
1561              chomp $line;                  # Loop through the families, connecting them to the feature.
1562              # Add the group to the table. Note that there can only be one group                  for my $family (@families) {
1563              # per genome.                      $loadIsFamilyForFeature->Put($family, $fid);
1564              $loadGenomeGroups->Put($genomeID, $line);                      # If this is a new family, create a record for it.
1565                        if (! exists $familyHash{$family}) {
1566                            $familyHash{$family} = 1;
1567                            $loadFamily->Add("families", 1);
1568                            my $size = $fig->sz_family($family);
1569                            my $func = $fig->family_function($family);
1570                            $loadFamily->Put($family, $size, $func);
1571                        }
1572                    }
1573                }
1574          }          }
         close TMP;  
1575      }      }
1576      # Finish the load.      # Finish the load.
1577      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1578      return $retVal;      return $retVal;
1579  }  }
1580    
1581    
1582    
1583  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1584    
1585  =head3 TableLoader  =head3 TableLoader
# Line 1366  Line 1596 
1596    
1597  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1598    
1599  =item rowCount (optional)  =item ignore
1600    
1601  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1602    
1603  =item RETURN  =item RETURN
1604    
# Line 1380  Line 1610 
1610    
1611  sub _TableLoader {  sub _TableLoader {
1612      # Get the parameters.      # Get the parameters.
1613      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1614      # Create the load object.      # Create the load object.
1615      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1616                                   $ignore);
1617      # Cache it in the loader list.      # Cache it in the loader list.
1618      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1619      # Return it to the caller.      # Return it to the caller.
# Line 1416  Line 1647 
1647      my $retVal = Stats->new();      my $retVal = Stats->new();
1648      # Get the loader list.      # Get the loader list.
1649      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1650        # Create a hash to hold the statistics objects, keyed on relation name.
1651        my %loaderHash = ();
1652      # 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
1653      # 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.
1654      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1655          # Trace the fact that we're cleaning up.          # Get the relation name.
1656          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1657          Trace("Finishing load for $relName.") if T(2);          # Check the ignore flag.
1658            if ($loader->Ignore) {
1659                Trace("Relation $relName not loaded.") if T(2);
1660            } else {
1661                # Here we really need to finish.
1662                Trace("Finishing $relName.") if T(2);
1663          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1664                $loaderHash{$relName} = $stats;
1665            }
1666        }
1667        # Now we loop through again, actually loading the tables. We want to finish before
1668        # loading so that if something goes wrong at this point, all the load files are usable
1669        # and we don't have to redo all that work.
1670        for my $relName (sort keys %loaderHash) {
1671            # Get the statistics for this relation.
1672            my $stats = $loaderHash{$relName};
1673            # Check for a database load.
1674          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1675              # 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.
1676              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);

Legend:
Removed from v.1.21  
changed lines
  Added in v.1.75

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3