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

Diff of /Sprout/SproutLoad.pm

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

revision 1.7, Tue Sep 13 19:05:20 2005 UTC revision 1.68, Sun Sep 24 17:14:16 2006 UTC
# Line 10  Line 10 
10      use Sprout;      use Sprout;
11      use Stats;      use Stats;
12      use BasicLocation;      use BasicLocation;
13        use HTML;
14    
15  =head1 Sprout Load Methods  =head1 Sprout Load Methods
16    
# Line 29  Line 30 
30      $stats->Accumulate($spl->LoadFeatureData());      $stats->Accumulate($spl->LoadFeatureData());
31      print $stats->Show();      print $stats->Show();
32    
 This module makes use of the internal Sprout property C<_erdb>.  
   
33  It is worth noting that the FIG object does not need to be a real one. Any object  It is worth noting that the FIG object does not need to be a real one. Any object
34  that implements the FIG methods for data retrieval could be used. So, for example,  that implements the FIG methods for data retrieval could be used. So, for example,
35  this object could be used to copy data from one Sprout database to another, or  this object could be used to copy data from one Sprout database to another, or
# Line 51  Line 50 
50    
51  =head3 new  =head3 new
52    
53  C<< my $spl = SproutLoad->new($sprout, $fig, $genomeFile, $subsysFile); >>  C<< my $spl = SproutLoad->new($sprout, $fig, $genomeFile, $subsysFile, $options); >>
54    
55  Construct a new Sprout Loader object, specifying the two participating databases and  Construct a new Sprout Loader object, specifying the two participating databases and
56  the name of the files containing the list of genomes and subsystems to use.  the name of the files containing the list of genomes and subsystems to use.
# Line 79  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
81  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
82  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85    =item options
86    
87    Reference to a hash of command-line options.
88    
89  =back  =back
90    
# Line 88  Line 92 
92    
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
96      # Load the list of genomes into a hash.      # Create the genome hash.
97      my %genomes;      my %genomes = ();
98        # We only need it if load-only is NOT specified.
99        if (! $options->{loadOnly}) {
100      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
101          # Here we want all the complete genomes and an access code of 1.          # Here we want all the complete genomes and an access code of 1.
102          my @genomeList = $fig->genomes(1);          my @genomeList = $fig->genomes(1);
# Line 114  Line 120 
120                  # an omitted access code can be defaulted to 1.                  # an omitted access code can be defaulted to 1.
121                  for my $genomeLine (@genomeList) {                  for my $genomeLine (@genomeList) {
122                      my ($genomeID, $accessCode) = split("\t", $genomeLine);                      my ($genomeID, $accessCode) = split("\t", $genomeLine);
123                      if (undef $accessCode) {                          if (! defined($accessCode)) {
124                          $accessCode = 1;                          $accessCode = 1;
125                      }                      }
126                      $genomes{$genomeID} = $accessCode;                      $genomes{$genomeID} = $accessCode;
# Line 124  Line 130 
130              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");
131          }          }
132      }      }
133        }
134      # Load the list of trusted subsystems.      # Load the list of trusted subsystems.
135      my %subsystems = ();      my %subsystems = ();
136        # We only need it if load-only is NOT specified.
137        if (! $options->{loadOnly}) {
138      if (! defined $subsysFile || $subsysFile eq '') {      if (! defined $subsysFile || $subsysFile eq '') {
139          # Here we want all the subsystems.              # Here we want all the usable subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for usability.
142                for my $sub (@subs) {
143                    if ($fig->usable_subsystem($sub)) {
144                        $subsystems{$sub} = 1;
145                    }
146                }
147      } else {      } else {
148          my $type = ref $subsysFile;          my $type = ref $subsysFile;
149          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 148  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 157  Line 173 
173                    subsystems => \%subsystems,                    subsystems => \%subsystems,
174                    sprout => $sprout,                    sprout => $sprout,
175                    loadDirectory => $directory,                    loadDirectory => $directory,
176                    erdb => $sprout->{_erdb},                    erdb => $sprout,
177                    loaders => []                    loaders => [],
178                      options => $options
179                   };                   };
180      # Bless and return it.      # Bless and return it.
181      bless $retVal, $class;      bless $retVal, $class;
182      return $retVal;      return $retVal;
183  }  }
184    
185    =head3 LoadOnly
186    
187    C<< my $flag = $spl->LoadOnly; >>
188    
189    Return TRUE if we are in load-only mode, else FALSE.
190    
191    =cut
192    
193    sub LoadOnly {
194        my ($self) = @_;
195        return $self->{options}->{loadOnly};
196    }
197    
198    =head3 PrimaryOnly
199    
200    C<< my $flag = $spl->PrimaryOnly; >>
201    
202    Return TRUE if only the main entity is to be loaded, else FALSE.
203    
204    =cut
205    
206    sub PrimaryOnly {
207        my ($self) = @_;
208        return $self->{options}->{primaryOnly};
209    }
210    
211  =head3 LoadGenomeData  =head3 LoadGenomeData
212    
213  C<< my $stats = $spl->LoadGenomeData(); >>  C<< my $stats = $spl->LoadGenomeData(); >>
# Line 192  Line 235 
235    
236  =back  =back
237    
 B<TO DO>  
   
 Real quality vectors instead of C<unknown> for everything.  
   
 GenomeGroup relation. (The original script took group information from the C<NMPDR> file  
 in each genome's main directory, but no such file exists anywhere in my version of the  
 data store.)  
   
238  =cut  =cut
239  #: Return Type $%;  #: Return Type $%;
240  sub LoadGenomeData {  sub LoadGenomeData {
# Line 210  Line 245 
245      # Get the genome count.      # Get the genome count.
246      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
247      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
     Trace("Beginning genome data load.") if T(2);  
248      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
249      my $loadGenome = $self->_TableLoader('Genome', $genomeCount);      my $loadGenome = $self->_TableLoader('Genome');
250      my $loadHasContig = $self->_TableLoader('HasContig', $genomeCount * 300);      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
251      my $loadContig = $self->_TableLoader('Contig', $genomeCount * 300);      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
252      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $genomeCount * 60000);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
253      my $loadSequence = $self->_TableLoader('Sequence', $genomeCount * 60000);      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
254        if ($self->{options}->{loadOnly}) {
255            Trace("Loading from existing files.") if T(2);
256        } else {
257            Trace("Generating genome data.") if T(2);
258      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
259      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
260          Trace("Loading data for genome $genomeID.") if T(3);              Trace("Generating data for genome $genomeID.") if T(3);
261          $loadGenome->Add("genomeIn");          $loadGenome->Add("genomeIn");
262          # The access code comes in via the genome hash.          # The access code comes in via the genome hash.
263          my $accessCode = $genomeHash->{$genomeID};          my $accessCode = $genomeHash->{$genomeID};
264          # Get the genus, species, and strain from the scientific name. Note that we append              # Get the genus, species, and strain from the scientific name.
         # the genome ID to the strain. In some cases this is the totality of the strain name.  
265          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);          my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
266          my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
267          # Get the full taxonomy.          # Get the full taxonomy.
268          my $taxonomy = $fig->taxonomy_of($genomeID);          my $taxonomy = $fig->taxonomy_of($genomeID);
269                # Open the NMPDR group file for this genome.
270                my $group;
271                if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
272                    defined($group = <TMP>)) {
273                    # Clean the line ending.
274                    chomp $group;
275                } else {
276                    # No group, so use the default.
277                    $group = $FIG_Config::otherGroup;
278                }
279                close TMP;
280          # Output the genome record.          # Output the genome record.
281          $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,          $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,
282                           $species, $extra, $taxonomy);                               $group, $species, $extra, $taxonomy);
283          # Now we loop through each of the genome's contigs.          # Now we loop through each of the genome's contigs.
284          my @contigs = $fig->all_contigs($genomeID);          my @contigs = $fig->all_contigs($genomeID);
285          for my $contigID (@contigs) {          for my $contigID (@contigs) {
# Line 262  Line 310 
310              }              }
311          }          }
312      }      }
313        }
314      # Finish the loads.      # Finish the loads.
315      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
316      # Return the result.      # Return the result.
# Line 302  Line 351 
351      my $fig = $self->{fig};      my $fig = $self->{fig};
352      # Get the genome hash.      # Get the genome hash.
353      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
354      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
355      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
356      # Start the loads.      # Start the loads.
357      my $loadCoupling = $self->_TableLoader('Coupling', $featureCount * $genomeCount);      my $loadCoupling = $self->_TableLoader('Coupling');
358      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $featureCount * 8000);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
359      my $loadPCH = $self->_TableLoader('PCH', $featureCount * 2000);      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
360      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $featureCount * 2000);      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
361      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $featureCount * 8000);      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
362      Trace("Beginning coupling data load.") if T(2);      if ($self->{options}->{loadOnly}) {
363            Trace("Loading from existing files.") if T(2);
364        } else {
365            Trace("Generating coupling data.") if T(2);
366      # Loop through the genomes found.      # Loop through the genomes found.
367      for my $genome (sort keys %{$genomeFilter}) {      for my $genome (sort keys %{$genomeFilter}) {
368          Trace("Generating coupling data for $genome.") if T(3);          Trace("Generating coupling data for $genome.") if T(3);
# Line 334  Line 386 
386              for my $coupleData (@couplings) {              for my $coupleData (@couplings) {
387                  my ($peg2, $score) = @{$coupleData};                  my ($peg2, $score) = @{$coupleData};
388                  # Compute the coupling ID.                  # Compute the coupling ID.
389                  my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
390                  if (! exists $dupHash{$coupleID}) {                  if (! exists $dupHash{$coupleID}) {
391                      $loadCoupling->Add("couplingIn");                      $loadCoupling->Add("couplingIn");
392                      # Here we have a new coupling to store in the load files.                      # Here we have a new coupling to store in the load files.
# Line 362  Line 414 
414                              # We store this evidence in the hash if the usage                              # We store this evidence in the hash if the usage
415                              # is nonzero or no prior evidence has been found. This                              # is nonzero or no prior evidence has been found. This
416                              # insures that if there is duplicate evidence, we                              # insures that if there is duplicate evidence, we
417                              # at least keep the meaningful ones. Only evidence is                                  # at least keep the meaningful ones. Only evidence in
418                              # the hash makes it to the output.                              # the hash makes it to the output.
419                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {                              if ($usage || ! exists $evidenceMap{$evidenceKey}) {
420                                  $evidenceMap{$evidenceKey} = $evidenceData;                                  $evidenceMap{$evidenceKey} = $evidenceData;
# Line 370  Line 422 
422                          }                          }
423                      }                      }
424                      for my $evidenceID (keys %evidenceMap) {                      for my $evidenceID (keys %evidenceMap) {
425                                # Get the ID for this evidence.
426                                $pchID++;
427                          # Create the evidence record.                          # Create the evidence record.
428                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                          my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
429                          $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
430                          # Connect it to the coupling.                          # Connect it to the coupling.
431                          $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
432                          # Connect it to the features.                          # Connect it to the features.
433                          $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
434                          $loadUsesAsEvidence->Put($evidenceID, $peg4, 1);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
435                            }
436                      }                      }
437                  }                  }
438              }              }
# Line 404  Line 459 
459      FeatureTranslation      FeatureTranslation
460      FeatureUpstream      FeatureUpstream
461      IsLocatedIn      IsLocatedIn
462        HasFeature
463    
464  =over 4  =over 4
465    
# Line 422  Line 478 
478      my $fig = $self->{fig};      my $fig = $self->{fig};
479      # Get the table of genome IDs.      # Get the table of genome IDs.
480      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
481      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
482      my $loadFeature = $self->_TableLoader('Feature', $featureCount);      my $loadFeature = $self->_TableLoader('Feature');
483      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias', $featureCount * 6);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
484      my $loadFeatureLink = $self->_TableLoader('FeatureLink', $featureCount * 10);      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
485      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation', $featureCount);      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
486      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream', $featureCount);      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
487      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $featureCount);      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
488        my $loadHasFeature = $self->_TableLoader('HasFeature');
489      # 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
490      # locations.      # locations.
491      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
492      Trace("Beginning feature data load.") if T(2);      if ($self->{options}->{loadOnly}) {
493            Trace("Loading from existing files.") if T(2);
494        } else {
495            Trace("Generating feature data.") if T(2);
496      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
497      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
498          Trace("Loading features for genome $genomeID.") if T(3);          Trace("Loading features for genome $genomeID.") if T(3);
499          $loadFeature->Add("genomeIn");          $loadFeature->Add("genomeIn");
500          # Get the feature list for this genome.          # Get the feature list for this genome.
501          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
502                # Sort and count the list.
503                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
504                my $count = scalar @featureTuples;
505                Trace("$count features found for genome $genomeID.") if T(3);
506                # Set up for our duplicate-feature check.
507                my $oldFeatureID = "";
508          # Loop through the features.          # Loop through the features.
509          for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
             $loadFeature->Add("featureIn");  
510              # Split the tuple.              # Split the tuple.
511              my ($featureID, $locations, $aliases, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
512                    # Check for duplicates.
513                    if ($featureID eq $oldFeatureID) {
514                        Trace("Duplicate feature $featureID found.") if T(1);
515                    } else {
516                        $oldFeatureID = $featureID;
517                        # Count this feature.
518                        $loadFeature->Add("featureIn");
519                        # Get the functional assignment.
520                        my $assignment = $fig->function_of($featureID);
521              # Create the feature record.              # Create the feature record.
522              $loadFeature->Put($featureID, 1, $type);                      $loadFeature->Put($featureID, 1, $type, $assignment);
523                        # Link it to the parent genome.
524                        $loadHasFeature->Put($genomeID, $featureID, $type);
525              # Create the aliases.              # Create the aliases.
526              for my $alias (split /\s*,\s*/, $aliases) {                      for my $alias ($fig->feature_aliases($featureID)) {
527                  $loadFeatureAlias->Put($featureID, $alias);                  $loadFeatureAlias->Put($featureID, $alias);
528              }              }
529              # Get the links.              # Get the links.
# Line 475  Line 549 
549              # the maximum segment size. This simplifies the genes_in_region processing              # the maximum segment size. This simplifies the genes_in_region processing
550              # for Sprout.              # for Sprout.
551              my @locationList = split /\s*,\s*/, $locations;              my @locationList = split /\s*,\s*/, $locations;
552                        # Create the location position indicator.
553                        my $i = 1;
554              # Loop through the locations.              # Loop through the locations.
555              for my $location (@locationList) {              for my $location (@locationList) {
556                  # Parse the location.                  # Parse the location.
557                  my $locObject = BasicLocation->new($location);                          my $locObject = BasicLocation->new("$genomeID:$location");
558                  # Split it into a list of chunks.                  # Split it into a list of chunks.
559                  my @locOList = ();                  my @locOList = ();
560                  while (my $peeling = $locObject->Peel($chunkSize)) {                  while (my $peeling = $locObject->Peel($chunkSize)) {
# Line 488  Line 564 
564                  push @locOList, $locObject;                  push @locOList, $locObject;
565                  # Loop through the chunks, creating IsLocatedIn records. The variable                  # Loop through the chunks, creating IsLocatedIn records. The variable
566                  # "$i" will be used to keep the location index.                  # "$i" will be used to keep the location index.
                 my $i = 1;  
567                  for my $locChunk (@locOList) {                  for my $locChunk (@locOList) {
568                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,                      $loadIsLocatedIn->Put($featureID, $locChunk->Contig, $locChunk->Left,
569                                            $locChunk->Dir, $locChunk->Length, $i);                                            $locChunk->Dir, $locChunk->Length, $i);
# Line 497  Line 572 
572              }              }
573          }          }
574      }      }
575            }
576        }
577      # Finish the loads.      # Finish the loads.
578      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
579      return $retVal;      return $retVal;
# Line 533  Line 610 
610      my $fig = $self->{fig};      my $fig = $self->{fig};
611      # Get the table of genome IDs.      # Get the table of genome IDs.
612      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
     my $featureCount = $genomeCount * 4000;  
613      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
614      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf',      my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');
615                                                             $featureCount * $genomeCount);      if ($self->{options}->{loadOnly}) {
616      Trace("Beginning BBH load.") if T(2);          Trace("Loading from existing files.") if T(2);
617        } else {
618            Trace("Generating BBH data.") if T(2);
619      # Now we loop through the genomes, generating the data for each one.      # Now we loop through the genomes, generating the data for each one.
620      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
621          $loadIsBidirectionalBestHitOf->Add("genomeIn");          $loadIsBidirectionalBestHitOf->Add("genomeIn");
622          Trace("Processing features for genome $genomeID.") if T(3);          Trace("Processing features for genome $genomeID.") if T(3);
623          # Get the feature list for this genome.          # Get the feature list for this genome.
624          my $features = $fig->all_features_detailed($genomeID);          my $features = $fig->all_features_detailed($genomeID);
625                # Count the BBHs we find.
626                my $bbhCount = 0;
627          # Loop through the features.          # Loop through the features.
628          for my $featureData (@{$features}) {          for my $featureData (@{$features}) {
629              # Split the tuple.              # Split the tuple.
# Line 560  Line 639 
639                  if ($genomeHash->{$targetGenomeID}) {                  if ($genomeHash->{$targetGenomeID}) {
640                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                      $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
641                                                         $score);                                                         $score);
642                            $bbhCount++;
643                  }                  }
644              }              }
645          }          }
646                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
647            }
648      }      }
649      # Finish the loads.      # Finish the loads.
650      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 584  Line 666 
666  The following relations are loaded by this method.  The following relations are loaded by this method.
667    
668      Subsystem      Subsystem
669        SubsystemClass
670      Role      Role
671        RoleEC
672      SSCell      SSCell
673      ContainsFeature      ContainsFeature
674      IsGenomeOf      IsGenomeOf
# Line 592  Line 676 
676      OccursInSubsystem      OccursInSubsystem
677      ParticipatesIn      ParticipatesIn
678      HasSSCell      HasSSCell
679        ConsistsOfRoles
680        RoleSubset
681        HasRoleSubset
682        ConsistsOfGenomes
683        GenomeSubset
684        HasGenomeSubset
685        Catalyzes
686        Diagram
687        RoleOccursIn
688    
689  =over 4  =over 4
690    
# Line 601  Line 694 
694    
695  =back  =back
696    
 B<TO DO>  
   
 Generate RoleName table?  
   
697  =cut  =cut
698  #: Return Type $%;  #: Return Type $%;
699  sub LoadSubsystemData {  sub LoadSubsystemData {
# Line 618  Line 707 
707      # Get the subsystem hash. This lists the subsystems we'll process.      # Get the subsystem hash. This lists the subsystems we'll process.
708      my $subsysHash = $self->{subsystems};      my $subsysHash = $self->{subsystems};
709      my @subsysIDs = sort keys %{$subsysHash};      my @subsysIDs = sort keys %{$subsysHash};
710      my $subsysCount = @subsysIDs;      # Get the map list.
711      my $genomeCount = (keys %{$genomeHash});      my @maps = $fig->all_maps;
     my $featureCount = $genomeCount * 4000;  
712      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
713      my $loadSubsystem = $self->_TableLoader('Subsystem', $subsysCount);      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
714      my $loadRole = $self->_TableLoader('Role', $featureCount * 6);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
715      my $loadSSCell = $self->_TableLoader('SSCell', $featureCount * $genomeCount);      my $loadSubsystem = $self->_TableLoader('Subsystem');
716      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $featureCount * $subsysCount);      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
717      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $featureCount * $genomeCount);      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
718      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $featureCount * $genomeCount);      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
719      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $featureCount * 6);      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
720      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $subsysCount * $genomeCount);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
721      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $featureCount * $genomeCount);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
722      Trace("Beginning subsystem data load.") if T(2);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
723        my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
724        my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
725        my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
726        my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
727        my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
728        my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
729        my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
730        my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
731        my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
732        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
733        if ($self->{options}->{loadOnly}) {
734            Trace("Loading from existing files.") if T(2);
735        } else {
736            Trace("Generating subsystem data.") if T(2);
737            # This hash will contain the role for each EC. When we're done, this
738            # information will be used to generate the Catalyzes table.
739            my %ecToRoles = ();
740      # Loop through the subsystems. Our first task will be to create the      # Loop through the subsystems. Our first task will be to create the
741      # roles. We do this by looping through the subsystems and creating a      # roles. We do this by looping through the subsystems and creating a
742      # 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
743      # duplicates. As we move along, we'll connect the roles and subsystems.          # duplicates. As we move along, we'll connect the roles and subsystems
744            # and memorize up the reactions.
745            my ($genomeID, $roleID);
746      my %roleData = ();      my %roleData = ();
747      for my $subsysID (@subsysIDs) {      for my $subsysID (@subsysIDs) {
748                # Get the subsystem object.
749                my $sub = $fig->get_subsystem($subsysID);
750                # Only proceed if the subsystem has a spreadsheet.
751                if (! $sub->{empty_ss}) {
752          Trace("Creating subsystem $subsysID.") if T(3);          Trace("Creating subsystem $subsysID.") if T(3);
753          $loadSubsystem->Add("subsystemIn");          $loadSubsystem->Add("subsystemIn");
754          # Create the subsystem record.          # Create the subsystem record.
755          $loadSubsystem->Put($subsysID);                  my $curator = $sub->get_curator();
756          # Get the subsystem's roles.                  my $notes = $sub->get_notes();
757          my @roles = $fig->subsystem_to_roles($subsysID);                  $loadSubsystem->Put($subsysID, $curator, $notes);
758          # Connect the roles to the subsystem. If a role is new, we create                  my $classList = $fig->subsystem_classification($subsysID);
759          # a role record for it.                  my @classes = @$classList;
760          for my $roleID (@roles) {                  if (@classes) {
761                        for my $class (@classes) {
762                            $loadSubsystemClass->Put($subsysID, $class);
763                        }
764                    }
765                    # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
766                    for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
767                        # Connect to this role.
768              $loadOccursInSubsystem->Add("roleIn");              $loadOccursInSubsystem->Add("roleIn");
769              $loadOccursInSubsystem->Put($roleID, $subsysID);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);
770                        # If it's a new role, add it to the role table.
771              if (! exists $roleData{$roleID}) {              if (! exists $roleData{$roleID}) {
772                  $loadRole->Put($roleID);                          # Get the role's abbreviation.
773                            my $abbr = $sub->get_role_abbr($col);
774                            # Add the role.
775                            $loadRole->Put($roleID, $abbr);
776                  $roleData{$roleID} = 1;                  $roleData{$roleID} = 1;
777                            # Check for an EC number.
778                            if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {
779                                my $ec = $1;
780                                $loadRoleEC->Put($roleID, $ec);
781                                $ecToRoles{$ec} = $roleID;
782                            }
783              }              }
784          }          }
785          # Now all roles for this subsystem have been filled in. We create the                  # Now we create the spreadsheet for the subsystem by matching roles to
786          # spreadsheet by matches roles to genomes. To do this, we need to                  # genomes. Each genome is a row and each role is a column. We may need
787          # get the genomes on the sheet.                  # to actually create the roles as we find them.
788          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);          Trace("Creating subsystem $subsysID spreadsheet.") if T(3);
789          my @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsysID)};                  for (my $row = 0; defined($genomeID = $sub->get_genome($row)); $row++) {
790          for my $genomeID (@genomes) {                      # Only proceed if this is one of our genomes.
             # Only process this genome if it's one of ours.  
791              if (exists $genomeHash->{$genomeID}) {              if (exists $genomeHash->{$genomeID}) {
792                  # Connect the genome to the subsystem.                          # Count the PEGs and cells found for verification purposes.
793                  $loadParticipatesIn->Put($genomeID, $subsysID);                          my $pegCount = 0;
794                            my $cellCount = 0;
795                            # Create a list for the PEGs we find. This list will be used
796                            # to generate cluster numbers.
797                            my @pegsFound = ();
798                            # Create a hash that maps spreadsheet IDs to PEGs. We will
799                            # use this to generate the ContainsFeature data after we have
800                            # the cluster numbers.
801                            my %cellPegs = ();
802                            # Get the genome's variant code for this subsystem.
803                            my $variantCode = $sub->get_variant_code($row);
804                  # Loop through the subsystem's roles. We use an index because it is                  # Loop through the subsystem's roles. We use an index because it is
805                  # part of the spreadsheet cell ID.                  # part of the spreadsheet cell ID.
806                  for (my $i = 0; $i <= $#roles; $i++) {                          for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
                     my $role = $roles[$i];  
807                      # Get the features in the spreadsheet cell for this genome and role.                      # Get the features in the spreadsheet cell for this genome and role.
808                      my @pegs = $fig->pegs_in_subsystem_cell($subsysID, $genomeID, $i);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
809                      # Only proceed if features exist.                      # Only proceed if features exist.
810                      if (@pegs > 0) {                      if (@pegs > 0) {
811                          # Create the spreadsheet cell.                          # Create the spreadsheet cell.
812                          my $cellID = "$subsysID:$genomeID:$i";                                  $cellCount++;
813                                    my $cellID = "$subsysID:$genomeID:$col";
814                          $loadSSCell->Put($cellID);                          $loadSSCell->Put($cellID);
815                          $loadIsGenomeOf->Put($genomeID, $cellID);                          $loadIsGenomeOf->Put($genomeID, $cellID);
816                          $loadIsRoleOf->Put($role, $cellID);                                  $loadIsRoleOf->Put($roleID, $cellID);
817                          $loadHasSSCell->Put($subsysID, $cellID);                          $loadHasSSCell->Put($subsysID, $cellID);
818                          # Attach the features to it.                                  # Remember its features.
819                          for my $pegID (@pegs) {                                  push @pegsFound, @pegs;
820                              $loadContainsFeature->Put($cellID, $pegID);                                  $cellPegs{$cellID} = \@pegs;
821                                    $pegCount += @pegs;
822                                }
823                            }
824                            # If we found some cells for this genome, we need to compute clusters and
825                            # denote it participates in the subsystem.
826                            if ($pegCount > 0) {
827                                Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
828                                $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
829                                # Create a hash mapping PEG IDs to cluster numbers.
830                                # We default to -1 for all of them.
831                                my %clusterOf = map { $_ => -1 } @pegsFound;
832                                # Partition the PEGs found into clusters.
833                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
834                                for (my $i = 0; $i <= $#clusters; $i++) {
835                                    my $subList = $clusters[$i];
836                                    for my $peg (@{$subList}) {
837                                        $clusterOf{$peg} = $i;
838                                    }
839                                }
840                                # Create the ContainsFeature data.
841                                for my $cellID (keys %cellPegs) {
842                                    my $cellList = $cellPegs{$cellID};
843                                    for my $cellPeg (@$cellList) {
844                                        $loadContainsFeature->Put($cellID, $cellPeg, $clusterOf{$cellPeg});
845                          }                          }
846                      }                      }
847                  }                  }
848              }              }
849          }          }
850                    # Now we need to generate the subsets. The subset names must be concatenated to
851                    # the subsystem name to make them unique keys. There are two types of subsets:
852                    # genome subsets and role subsets. We do the role subsets first.
853                    my @subsetNames = $sub->get_subset_names();
854                    for my $subsetID (@subsetNames) {
855                        # Create the subset record.
856                        my $actualID = "$subsysID:$subsetID";
857                        $loadRoleSubset->Put($actualID);
858                        # Connect the subset to the subsystem.
859                        $loadHasRoleSubset->Put($subsysID, $actualID);
860                        # Connect the subset to its roles.
861                        my @roles = $sub->get_subsetC_roles($subsetID);
862                        for my $roleID (@roles) {
863                            $loadConsistsOfRoles->Put($actualID, $roleID);
864      }      }
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
865  }  }
866                    # Next the genome subsets.
867  =head3 LoadDiagramData                  @subsetNames = $sub->get_subset_namesR();
868                    for my $subsetID (@subsetNames) {
869  C<< my $stats = $spl->LoadDiagramData(); >>                      # Create the subset record.
870                        my $actualID = "$subsysID:$subsetID";
871  Load the diagram data from FIG into Sprout.                      $loadGenomeSubset->Put($actualID);
872                        # Connect the subset to the subsystem.
873  Diagrams are used to organize functional roles. The diagram shows the                      $loadHasGenomeSubset->Put($subsysID, $actualID);
874  connections between chemicals that interact with a subsystem.                      # Connect the subset to its genomes.
875                        my @genomes = $sub->get_subsetR($subsetID);
876  The following relations are loaded by this method.                      for my $genomeID (@genomes) {
877                            $loadConsistsOfGenomes->Put($actualID, $genomeID);
878      Diagram                      }
879      RoleOccursIn                  }
880                }
881  =over 4          }
882            # Now we loop through the diagrams. We need to create the diagram records
883  =item RETURNS          # and link each diagram to its roles. Note that only roles which occur
884            # in subsystems (and therefore appear in the %ecToRoles hash) are
885  Returns a statistics object for the loads.          # included.
886            for my $map (@maps) {
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadDiagramData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the map list.  
     my @maps = $fig->all_maps;  
     my $mapCount = @maps;  
     my $genomeCount = (keys %{$self->{genomes}});  
     my $featureCount = $genomeCount * 4000;  
     # Create load objects for each of the tables we're loading.  
     my $loadDiagram = $self->_TableLoader('Diagram', $mapCount);  
     my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $featureCount * 6);  
     Trace("Beginning diagram data load.") if T(2);  
     # Loop through the diagrams.  
     for my $map ($fig->all_maps) {  
887          Trace("Loading diagram $map.") if T(3);          Trace("Loading diagram $map.") if T(3);
888          # Get the diagram's descriptive name.          # Get the diagram's descriptive name.
889          my $name = $fig->map_name($map);          my $name = $fig->map_name($map);
# Line 740  Line 892 
892          # A hash is used to prevent duplicates.          # A hash is used to prevent duplicates.
893          my %roleHash = ();          my %roleHash = ();
894          for my $role ($fig->map_to_ecs($map)) {          for my $role ($fig->map_to_ecs($map)) {
895              if (! $roleHash{$role}) {                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {
896                  $loadRoleOccursIn->Put($role, $map);                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);
897                  $roleHash{$role} = 1;                  $roleHash{$role} = 1;
898              }              }
899          }          }
900      }      }
901            # Before we leave, we must create the Catalyzes table. We start with the reactions,
902            # then use the "ecToRoles" table to convert EC numbers to role IDs.
903            my @reactions = $fig->all_reactions();
904            for my $reactionID (@reactions) {
905                # Get this reaction's list of roles. The results will be EC numbers.
906                my @roles = $fig->catalyzed_by($reactionID);
907                # Loop through the roles, creating catalyzation records.
908                for my $thisRole (@roles) {
909                    if (exists $ecToRoles{$thisRole}) {
910                        $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);
911                    }
912                }
913            }
914        }
915      # Finish the load.      # Finish the load.
916      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
917      return $retVal;      return $retVal;
# Line 787  Line 953 
953      my $fig = $self->{fig};      my $fig = $self->{fig};
954      # Get the genome hash.      # Get the genome hash.
955      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
956      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
957      my $loadProperty = $self->_TableLoader('Property', $genomeCount * 1500);      my $loadProperty = $self->_TableLoader('Property');
958      my $loadHasProperty = $self->_TableLoader('HasProperty', $genomeCount * 1500);      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
959      Trace("Beginning property data load.") if T(2);      if ($self->{options}->{loadOnly}) {
960            Trace("Loading from existing files.") if T(2);
961        } else {
962            Trace("Generating property data.") if T(2);
963      # Create a hash for storing property IDs.      # Create a hash for storing property IDs.
964      my %propertyKeys = ();      my %propertyKeys = ();
965      my $nextID = 1;      my $nextID = 1;
966      # Loop through the genomes.      # Loop through the genomes.
967      for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
968          $loadProperty->Add("genomeIn");          $loadProperty->Add("genomeIn");
969                Trace("Generating properties for $genomeID.") if T(3);
970          # 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
971          # tuples returned by "all_features_detailed". We use "all_features_detailed"          # tuples returned by "all_features_detailed". We use "all_features_detailed"
972          # rather than "all_features" because we want all features regardless of type.          # rather than "all_features" because we want all features regardless of type.
973          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};          my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
974                my $featureCount = 0;
975                my $propertyCount = 0;
976          # Loop through the features, creating HasProperty records.          # Loop through the features, creating HasProperty records.
977          for my $fid (@features) {          for my $fid (@features) {
             $loadProperty->Add("featureIn");  
978              # 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
979              # to insure we do not get any genome attributes.              # to insure we do not get any genome attributes.
980              my @attributeList = $fig->get_attributes($fid, '', '', '');              my @attributeList = $fig->get_attributes($fid, '', '', '');
981                    if (scalar @attributeList) {
982                        $featureCount++;
983                    }
984              # Loop through the attributes.              # Loop through the attributes.
985              for my $tuple (@attributeList) {              for my $tuple (@attributeList) {
986                        $propertyCount++;
987                  # Get this attribute value's data. Note that we throw away the FID,                  # Get this attribute value's data. Note that we throw away the FID,
988                  # since it will always be the same as the value if "$fid".                  # since it will always be the same as the value if "$fid".
989                  my (undef, $key, $value, $url) = @{$tuple};                  my (undef, $key, $value, $url) = @{$tuple};
# Line 831  Line 1005 
1005                  $loadHasProperty->Put($fid, $propertyID, $url);                  $loadHasProperty->Put($fid, $propertyID, $url);
1006              }              }
1007          }          }
1008                # Update the statistics.
1009                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
1010                $loadHasProperty->Add("featuresIn", $featureCount);
1011                $loadHasProperty->Add("propertiesIn", $propertyCount);
1012            }
1013      }      }
1014      # Finish the load.      # Finish the load.
1015      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 871  Line 1050 
1050      my $fig = $self->{fig};      my $fig = $self->{fig};
1051      # Get the genome hash.      # Get the genome hash.
1052      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1053      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1054      my $loadAnnotation = $self->_TableLoader('Annotation', $genomeCount * 4000);      my $loadAnnotation = $self->_TableLoader('Annotation');
1055      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $genomeCount * 4000);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1056      my $loadSproutUser = $self->_TableLoader('SproutUser', 100);      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1057      my $loadUserAccess = $self->_TableLoader('UserAccess', 1000);      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1058      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $genomeCount * 4000);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1059      Trace("Beginning annotation data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1060            Trace("Loading from existing files.") if T(2);
1061        } else {
1062            Trace("Generating annotation data.") if T(2);
1063      # 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
1064      # user records.      # user records.
1065      my %users = ( FIG => 1, master => 1 );      my %users = ( FIG => 1, master => 1 );
# Line 892  Line 1073 
1073      # Loop through the genomes.      # Loop through the genomes.
1074      for my $genomeID (sort keys %{$genomeHash}) {      for my $genomeID (sort keys %{$genomeHash}) {
1075          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);  
1076              # 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
1077              # from showing up for a single PEG's annotations.              # from showing up for a single PEG's annotations.
1078              my %seenTimestamps = ();              my %seenTimestamps = ();
1079              # Check for a functional assignment.              # Get the genome's annotations.
1080              my $func = $fig->function_of($peg);              my @annotations = $fig->read_all_annotations($genomeID);
1081              if ($func) {              Trace("Processing annotations.") if T(2);
1082                  # If this is NOT a hypothetical assignment, we create an              for my $tuple (@annotations) {
1083                  # assignment annotation for it.                  # Get the annotation tuple.
1084                  if (! FIG::hypo($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};  
1085                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1086                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1087                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1088                      # stop the substitution search.                      # stop the substitution search.
1089                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 927  Line 1093 
1093                      $text =~ s/Set master function/Set FIG function/s;                      $text =~ s/Set master function/Set FIG function/s;
1094                      # Insure the time stamp is valid.                      # Insure the time stamp is valid.
1095                      if ($timestamp =~ /^\d+$/) {                      if ($timestamp =~ /^\d+$/) {
1096                          # Here it's a number. We need to insure it's unique.                      # Here it's a number. We need to insure the one we use to form
1097                          while ($seenTimestamps{$timestamp}) {                      # the key is unique.
1098                              $timestamp++;                      my $keyStamp = $timestamp;
1099                        while ($seenTimestamps{"$peg:$keyStamp"}) {
1100                            $keyStamp++;
1101                          }                          }
1102                          $seenTimestamps{$timestamp} = 1;                      my $annotationID = "$peg:$keyStamp";
1103                          my $annotationID = "$peg:$timestamp";                      $seenTimestamps{$annotationID} = 1;
1104                          # Insure the user exists.                          # Insure the user exists.
1105                          if (! $users{$user}) {                          if (! $users{$user}) {
1106                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 940  Line 1108 
1108                              $users{$user} = 1;                              $users{$user} = 1;
1109                          }                          }
1110                          # Generate the annotation.                          # Generate the annotation.
1111                          $loadAnnotation->Put($annotationID, $timestamp, "$user\\n$text");                      $loadAnnotation->Put($annotationID, $timestamp, $text);
1112                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);                          $loadIsTargetOfAnnotation->Put($peg, $annotationID);
1113                          $loadMadeAnnotation->Put($user, $annotationID);                          $loadMadeAnnotation->Put($user, $annotationID);
1114                      } else {                      } else {
# Line 950  Line 1118 
1118                  }                  }
1119              }              }
1120          }          }
     }  
1121      # Finish the load.      # Finish the load.
1122      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1123      return $retVal;      return $retVal;
# Line 991  Line 1158 
1158      my $fig = $self->{fig};      my $fig = $self->{fig};
1159      # Get the genome hash.      # Get the genome hash.
1160      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1161      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1162      my $loadComesFrom = $self->_TableLoader('ComesFrom', $genomeCount * 4);      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1163      my $loadSource = $self->_TableLoader('Source', $genomeCount * 4);      my $loadSource = $self->_TableLoader('Source');
1164      my $loadSourceURL = $self->_TableLoader('SourceURL', $genomeCount * 8);      my $loadSourceURL = $self->_TableLoader('SourceURL');
1165      Trace("Beginning source data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1166            Trace("Loading from existing files.") if T(2);
1167        } else {
1168            Trace("Generating annotation data.") if T(2);
1169      # Create hashes to collect the Source information.      # Create hashes to collect the Source information.
1170      my %sourceURL = ();      my %sourceURL = ();
1171      my %sourceDesc = ();      my %sourceDesc = ();
# Line 1010  Line 1179 
1179              chomp $line;              chomp $line;
1180              my($sourceID, $desc, $url) = split(/\t/,$line);              my($sourceID, $desc, $url) = split(/\t/,$line);
1181              $loadComesFrom->Put($genomeID, $sourceID);              $loadComesFrom->Put($genomeID, $sourceID);
1182              if ($url && ! exists $sourceURL{$genomeID}) {                  if ($url && ! exists $sourceURL{$sourceID}) {
1183                  $loadSourceURL->Put($sourceID, $url);                  $loadSourceURL->Put($sourceID, $url);
1184                  $sourceURL{$sourceID} = 1;                  $sourceURL{$sourceID} = 1;
1185              }              }
1186              if ($desc && ! exists $sourceDesc{$sourceID}) {                  if ($desc) {
1187                  $loadSource->Put($sourceID, $desc);                      $sourceDesc{$sourceID} = $desc;
1188                  $sourceDesc{$sourceID} = 1;                  } elsif (! exists $sourceDesc{$sourceID}) {
1189                        $sourceDesc{$sourceID} = $sourceID;
1190              }              }
1191          }          }
1192          close TMP;          close TMP;
1193      }      }
1194            # Write the source descriptions.
1195            for my $sourceID (keys %sourceDesc) {
1196                $loadSource->Put($sourceID, $sourceDesc{$sourceID});
1197            }
1198        }
1199      # Finish the load.      # Finish the load.
1200      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1201      return $retVal;      return $retVal;
# Line 1060  Line 1235 
1235      my $fig = $self->{fig};      my $fig = $self->{fig};
1236      # Get the genome hash.      # Get the genome hash.
1237      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1238      # 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
1239      # it the key.      # it the key.
1240      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});      my %speciesHash = map { $fig->genus_species($_) => $_ } (keys %{$genomeHash});
1241      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1242      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc', $genomeCount * 4000);      my $loadExternalAliasFunc = $self->_TableLoader('ExternalAliasFunc');
1243      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg', $genomeCount * 4000);      my $loadExternalAliasOrg = $self->_TableLoader('ExternalAliasOrg');
1244      Trace("Beginning external data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1245            Trace("Loading from existing files.") if T(2);
1246        } else {
1247            Trace("Generating external data.") if T(2);
1248      # 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.
1249      Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1250      my $orgLine;      my $orgLine;
1251      while (defined($orgLine = <ORGS>)) {      while (defined($orgLine = <ORGS>)) {
1252          # Clean the input line.          # Clean the input line.
# Line 1081  Line 1258 
1258      close ORGS;      close ORGS;
1259      # Now the function file.      # Now the function file.
1260      my $funcLine;      my $funcLine;
1261      Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1262      while (defined($funcLine = <FUNCS>)) {      while (defined($funcLine = <FUNCS>)) {
1263          # Clean the line ending.          # Clean the line ending.
1264          chomp $funcLine;          chomp $funcLine;
# Line 1097  Line 1274 
1274              $loadExternalAliasFunc->Put(@funcFields[0,1]);              $loadExternalAliasFunc->Put(@funcFields[0,1]);
1275          }          }
1276      }      }
1277        }
1278        # Finish the load.
1279        my $retVal = $self->_FinishAll();
1280        return $retVal;
1281    }
1282    
1283    
1284    =head3 LoadReactionData
1285    
1286    C<< my $stats = $spl->LoadReactionData(); >>
1287    
1288    Load the reaction data from FIG into Sprout.
1289    
1290    Reaction data connects reactions to the compounds that participate in them.
1291    
1292    The following relations are loaded by this method.
1293    
1294        Reaction
1295        ReactionURL
1296        Compound
1297        CompoundName
1298        CompoundCAS
1299        IsAComponentOf
1300    
1301    This method proceeds reaction by reaction rather than genome by genome.
1302    
1303    =over 4
1304    
1305    =item RETURNS
1306    
1307    Returns a statistics object for the loads.
1308    
1309    =back
1310    
1311    =cut
1312    #: Return Type $%;
1313    sub LoadReactionData {
1314        # Get this object instance.
1315        my ($self) = @_;
1316        # Get the FIG object.
1317        my $fig = $self->{fig};
1318        # Create load objects for each of the tables we're loading.
1319        my $loadReaction = $self->_TableLoader('Reaction');
1320        my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1321        my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1322        my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1323        my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1324        my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1325        if ($self->{options}->{loadOnly}) {
1326            Trace("Loading from existing files.") if T(2);
1327        } else {
1328            Trace("Generating annotation data.") if T(2);
1329            # First we create the compounds.
1330            my @compounds = $fig->all_compounds();
1331            for my $cid (@compounds) {
1332                # Check for names.
1333                my @names = $fig->names_of_compound($cid);
1334                # Each name will be given a priority number, starting with 1.
1335                my $prio = 1;
1336                for my $name (@names) {
1337                    $loadCompoundName->Put($cid, $name, $prio++);
1338                }
1339                # Create the main compound record. Note that the first name
1340                # becomes the label.
1341                my $label = (@names > 0 ? $names[0] : $cid);
1342                $loadCompound->Put($cid, $label);
1343                # Check for a CAS ID.
1344                my $cas = $fig->cas($cid);
1345                if ($cas) {
1346                    $loadCompoundCAS->Put($cid, $cas);
1347                }
1348            }
1349            # All the compounds are set up, so we need to loop through the reactions next. First,
1350            # we initialize the discriminator index. This is a single integer used to insure
1351            # duplicate elements in a reaction are not accidentally collapsed.
1352            my $discrim = 0;
1353            my @reactions = $fig->all_reactions();
1354            for my $reactionID (@reactions) {
1355                # Create the reaction record.
1356                $loadReaction->Put($reactionID, $fig->reversible($reactionID));
1357                # Compute the reaction's URL.
1358                my $url = HTML::reaction_link($reactionID);
1359                # Put it in the ReactionURL table.
1360                $loadReactionURL->Put($reactionID, $url);
1361                # Now we need all of the reaction's compounds. We get these in two phases,
1362                # substrates first and then products.
1363                for my $product (0, 1) {
1364                    # Get the compounds of the current type for the current reaction. FIG will
1365                    # give us 3-tuples: [ID, stoichiometry, main-flag]. At this time we do not
1366                    # have location data in SEED, so it defaults to the empty string.
1367                    my @compounds = $fig->reaction2comp($reactionID, $product);
1368                    for my $compData (@compounds) {
1369                        # Extract the compound data from the current tuple.
1370                        my ($cid, $stoich, $main) = @{$compData};
1371                        # Link the compound to the reaction.
1372                        $loadIsAComponentOf->Put($cid, $reactionID, $discrim++, "", $main,
1373                                                 $product, $stoich);
1374                    }
1375                }
1376            }
1377        }
1378      # Finish the load.      # Finish the load.
1379      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1380      return $retVal;      return $retVal;
# Line 1112  Line 1390 
1390    
1391      GenomeGroups      GenomeGroups
1392    
1393  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,
1394    butThere is no direct support for genome groups in FIG, so we access the SEED
1395  files directly.  files directly.
1396    
1397  =over 4  =over 4
# Line 1132  Line 1411 
1411      my $fig = $self->{fig};      my $fig = $self->{fig};
1412      # Get the genome hash.      # Get the genome hash.
1413      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
     my $genomeCount = (keys %{$genomeHash});  
1414      # Create a load object for the table we're loading.      # Create a load object for the table we're loading.
1415      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups', $genomeCount * 4);      my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');
1416      Trace("Beginning group data load.") if T(2);      if ($self->{options}->{loadOnly}) {
1417            Trace("Loading from existing files.") if T(2);
1418        } else {
1419            Trace("Generating group data.") if T(2);
1420            # Currently there are no groups.
1421        }
1422        # Finish the load.
1423        my $retVal = $self->_FinishAll();
1424        return $retVal;
1425    }
1426    
1427    =head3 LoadSynonymData
1428    
1429    C<< my $stats = $spl->LoadSynonymData(); >>
1430    
1431    Load the synonym groups into Sprout.
1432    
1433    The following relations are loaded by this method.
1434    
1435        SynonymGroup
1436        IsSynonymGroupFor
1437    
1438    The source information for these relations is taken from the C<maps_to_id> method
1439    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1440    SQL against the FIG database.
1441    
1442    =over 4
1443    
1444    =item RETURNS
1445    
1446    Returns a statistics object for the loads.
1447    
1448    =back
1449    
1450    =cut
1451    #: Return Type $%;
1452    sub LoadSynonymData {
1453        # Get this object instance.
1454        my ($self) = @_;
1455        # Get the FIG object.
1456        my $fig = $self->{fig};
1457        # Get the genome hash.
1458        my $genomeHash = $self->{genomes};
1459        # Create a load object for the table we're loading.
1460        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1461        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1462        if ($self->{options}->{loadOnly}) {
1463            Trace("Loading from existing files.") if T(2);
1464        } else {
1465            Trace("Generating synonym group data.") if T(2);
1466            # Get the database handle.
1467            my $dbh = $fig->db_handle();
1468            # Ask for the synonyms.
1469            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1470            my $result = $sth->execute();
1471            if (! defined($result)) {
1472                Confess("Database error in Synonym load: " . $sth->errstr());
1473            } else {
1474                # Remember the current synonym.
1475                my $current_syn = "";
1476                # Count the features.
1477                my $featureCount = 0;
1478                # Loop through the synonym/peg pairs.
1479                while (my @row = $sth->fetchrow()) {
1480                    # Get the synonym ID and feature ID.
1481                    my ($syn_id, $peg) = @row;
1482                    # Insure it's for one of our genomes.
1483                    my $genomeID = FIG::genome_of($peg);
1484                    if (exists $genomeHash->{$genomeID}) {
1485                        # Verify the synonym.
1486                        if ($syn_id ne $current_syn) {
1487                            # It's new, so put it in the group table.
1488                            $loadSynonymGroup->Put($syn_id);
1489                            $current_syn = $syn_id;
1490                        }
1491                        # Connect the synonym to the peg.
1492                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1493                        # Count this feature.
1494                        $featureCount++;
1495                        if ($featureCount % 1000 == 0) {
1496                            Trace("$featureCount features processed.") if T(3);
1497                        }
1498                    }
1499                }
1500            }
1501        }
1502        # Finish the load.
1503        my $retVal = $self->_FinishAll();
1504        return $retVal;
1505    }
1506    
1507    =head3 LoadFamilyData
1508    
1509    C<< my $stats = $spl->LoadFamilyData(); >>
1510    
1511    Load the protein families into Sprout.
1512    
1513    The following relations are loaded by this method.
1514    
1515        Family
1516        IsFamilyForFeature
1517    
1518    The source information for these relations is taken from the C<families_for_protein>,
1519    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1520    
1521    =over 4
1522    
1523    =item RETURNS
1524    
1525    Returns a statistics object for the loads.
1526    
1527    =back
1528    
1529    =cut
1530    #: Return Type $%;
1531    sub LoadFamilyData {
1532        # Get this object instance.
1533        my ($self) = @_;
1534        # Get the FIG object.
1535        my $fig = $self->{fig};
1536        # Get the genome hash.
1537        my $genomeHash = $self->{genomes};
1538        # Create load objects for the tables we're loading.
1539        my $loadFamily = $self->_TableLoader('Family');
1540        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1541        if ($self->{options}->{loadOnly}) {
1542            Trace("Loading from existing files.") if T(2);
1543        } else {
1544            Trace("Generating family data.") if T(2);
1545            # Create a hash for the family IDs.
1546            my %familyHash = ();
1547      # Loop through the genomes.      # Loop through the genomes.
1548      my $line;          for my $genomeID (sort keys %{$genomeHash}) {
1549      for my $genomeID (keys %{$genomeHash}) {              Trace("Processing features for $genomeID.") if T(2);
1550          Trace("Processing $genomeID.") if T(3);              # Loop through this genome's PEGs.
1551          # Open the NMPDR group file for this genome.              for my $fid ($fig->all_features($genomeID, "peg")) {
1552          if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&                  $loadIsFamilyForFeature->Add("features", 1);
1553              defined($line = <TMP>)) {                  # Get this feature's families.
1554              # Clean the line ending.                  my @families = $fig->families_for_protein($fid);
1555              chomp $line;                  # Loop through the families, connecting them to the feature.
1556              # Add the group to the table. Note that there can only be one group                  for my $family (@families) {
1557              # per genome.                      $loadIsFamilyForFeature->Put($family, $fid);
1558              $loadGenomeGroups->Put($genomeID, $line);                      # If this is a new family, create a record for it.
1559                        if (! exists $familyHash{$family}) {
1560                            $familyHash{$family} = 1;
1561                            $loadFamily->Add("families", 1);
1562                            my $size = $fig->sz_family($family);
1563                            my $func = $fig->family_function($family);
1564                            $loadFamily->Put($family, $size, $func);
1565                        }
1566                    }
1567                }
1568          }          }
         close TMP;  
1569      }      }
1570      # Finish the load.      # Finish the load.
1571      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 1172  Line 1588 
1588    
1589  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1590    
1591  =item rowCount (optional)  =item ignore
1592    
1593  Estimated maximum number of rows in the table.  TRUE if the table should be ignored entirely, else FALSE.
1594    
1595  =item RETURN  =item RETURN
1596    
# Line 1186  Line 1602 
1602    
1603  sub _TableLoader {  sub _TableLoader {
1604      # Get the parameters.      # Get the parameters.
1605      my ($self, $tableName, $rowCount) = @_;      my ($self, $tableName, $ignore) = @_;
1606      # Create the load object.      # Create the load object.
1607      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $rowCount);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1608                                   $ignore);
1609      # Cache it in the loader list.      # Cache it in the loader list.
1610      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1611      # Return it to the caller.      # Return it to the caller.
# Line 1222  Line 1639 
1639      my $retVal = Stats->new();      my $retVal = Stats->new();
1640      # Get the loader list.      # Get the loader list.
1641      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1642        # Create a hash to hold the statistics objects, keyed on relation name.
1643        my %loaderHash = ();
1644      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1645      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads more restartable.
1646      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1647            # Get the relation name.
1648            my $relName = $loader->RelName;
1649            # Check the ignore flag.
1650            if ($loader->Ignore) {
1651                Trace("Relation $relName not loaded.") if T(2);
1652            } else {
1653                # Here we really need to finish.
1654                Trace("Finishing $relName.") if T(2);
1655          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1656                $loaderHash{$relName} = $stats;
1657            }
1658        }
1659        # Now we loop through again, actually loading the tables. We want to finish before
1660        # loading so that if something goes wrong at this point, all the load files are usable
1661        # and we don't have to redo all that work.
1662        for my $relName (sort keys %loaderHash) {
1663            # Get the statistics for this relation.
1664            my $stats = $loaderHash{$relName};
1665            # Check for a database load.
1666            if ($self->{options}->{dbLoad}) {
1667                # Here we want to use the load file just created to load the database.
1668                Trace("Loading relation $relName.") if T(2);
1669                my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
1670                # Accumulate the statistics from the DB load.
1671                $stats->Accumulate($newStats);
1672            }
1673          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
         my $relName = $loader->RelName;  
1674          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1675      }      }
1676      # Return the load statistics.      # Return the load statistics.

Legend:
Removed from v.1.7  
changed lines
  Added in v.1.68

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3