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

Diff of /Sprout/SproutLoad.pm

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

revision 1.23, Fri Jan 13 06:59:49 2006 UTC revision 1.61, Sun Jul 30 01:41:34 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 = $fig->genomes(1);
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($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 ($type eq 'ARRAY') {
# Line 153  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166        }
167      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
168      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
169      # Create the Sprout load object.      # Create the Sprout load object.
# Line 162  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                    options => $options
179                   };                   };
# Line 184  Line 195 
195      return $self->{options}->{loadOnly};      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 211  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 231  Line 247 
247      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
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');      my $loadGenome = $self->_TableLoader('Genome');
250      my $loadHasContig = $self->_TableLoader('HasContig');      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);
251      my $loadContig = $self->_TableLoader('Contig');      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);
252      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf');      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);
253      my $loadSequence = $self->_TableLoader('Sequence');      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);
254      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
255          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
256      } else {      } else {
# Line 245  Line 261 
261              $loadGenome->Add("genomeIn");              $loadGenome->Add("genomeIn");
262              # The access code comes in via the genome hash.              # The access code comes in via the genome hash.
263              my $accessCode = $genomeHash->{$genomeID};              my $accessCode = $genomeHash->{$genomeID};
264              # Get the genus, species, and strain from the scientific name. Note that we append              # Get the genus, species, and strain from the scientific name.
             # the genome ID to the strain. In some cases this is the totality of the strain name.  
265              my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);              my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
266              my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
267              # Get the full taxonomy.              # Get the full taxonomy.
268              my $taxonomy = $fig->taxonomy_of($genomeID);              my $taxonomy = $fig->taxonomy_of($genomeID);
269              # Output the genome record.              # Output the genome record.
# Line 325  Line 340 
340      my $fig = $self->{fig};      my $fig = $self->{fig};
341      # Get the genome hash.      # Get the genome hash.
342      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
343      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
344      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
345      # Start the loads.      # Start the loads.
346      my $loadCoupling = $self->_TableLoader('Coupling');      my $loadCoupling = $self->_TableLoader('Coupling');
347      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy');      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
348      my $loadPCH = $self->_TableLoader('PCH');      my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);
349      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling');      my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);
350      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence');      my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);
351      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
352          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
353      } else {      } else {
# Line 360  Line 375 
375                  for my $coupleData (@couplings) {                  for my $coupleData (@couplings) {
376                      my ($peg2, $score) = @{$coupleData};                      my ($peg2, $score) = @{$coupleData};
377                      # Compute the coupling ID.                      # Compute the coupling ID.
378                      my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
379                      if (! exists $dupHash{$coupleID}) {                      if (! exists $dupHash{$coupleID}) {
380                          $loadCoupling->Add("couplingIn");                          $loadCoupling->Add("couplingIn");
381                          # Here we have a new coupling to store in the load files.                          # Here we have a new coupling to store in the load files.
# Line 396  Line 411 
411                              }                              }
412                          }                          }
413                          for my $evidenceID (keys %evidenceMap) {                          for my $evidenceID (keys %evidenceMap) {
414                                # Get the ID for this evidence.
415                                $pchID++;
416                              # Create the evidence record.                              # Create the evidence record.
417                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
418                              $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
419                              # Connect it to the coupling.                              # Connect it to the coupling.
420                              $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
421                              # Connect it to the features.                              # Connect it to the features.
422                              $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
423                              $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
424                          }                          }
425                      }                      }
426                  }                  }
# Line 431  Line 448 
448      FeatureTranslation      FeatureTranslation
449      FeatureUpstream      FeatureUpstream
450      IsLocatedIn      IsLocatedIn
451        HasFeature
452    
453  =over 4  =over 4
454    
# Line 451  Line 469 
469      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
470      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
471      my $loadFeature = $self->_TableLoader('Feature');      my $loadFeature = $self->_TableLoader('Feature');
472      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn');      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
473      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
474      my $loadFeatureLink = $self->_TableLoader('FeatureLink');      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
475      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
476      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
477        my $loadHasFeature = $self->_TableLoader('HasFeature');
478      # Get the maximum sequence size. We need this later for splitting up the      # Get the maximum sequence size. We need this later for splitting up the
479      # locations.      # locations.
480      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
# Line 469  Line 488 
488              $loadFeature->Add("genomeIn");              $loadFeature->Add("genomeIn");
489              # Get the feature list for this genome.              # Get the feature list for this genome.
490              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
491                # Sort and count the list.
492                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
493                my $count = scalar @featureTuples;
494                Trace("$count features found for genome $genomeID.") if T(3);
495                # Set up for our duplicate-feature check.
496                my $oldFeatureID = "";
497              # Loop through the features.              # Loop through the features.
498              for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
                 $loadFeature->Add("featureIn");  
499                  # Split the tuple.                  # Split the tuple.
500                  my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
501                    # Check for duplicates.
502                    if ($featureID eq $oldFeatureID) {
503                        Trace("Duplicate feature $featureID found.") if T(1);
504                    } else {
505                        $oldFeatureID = $featureID;
506                        # Count this feature.
507                        $loadFeature->Add("featureIn");
508                  # Create the feature record.                  # Create the feature record.
509                  $loadFeature->Put($featureID, 1, $type);                  $loadFeature->Put($featureID, 1, $type);
510                        # Link it to the parent genome.
511                        $loadHasFeature->Put($genomeID, $featureID, $type);
512                  # Create the aliases.                  # Create the aliases.
513                  for my $alias ($fig->feature_aliases($featureID)) {                  for my $alias ($fig->feature_aliases($featureID)) {
514                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
# Line 527  Line 560 
560              }              }
561          }          }
562      }      }
563        }
564      # Finish the loads.      # Finish the loads.
565      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
566      return $retVal;      return $retVal;
# Line 615  Line 649 
649  The following relations are loaded by this method.  The following relations are loaded by this method.
650    
651      Subsystem      Subsystem
652        SubsystemClass
653      Role      Role
654      RoleEC      RoleEC
655      SSCell      SSCell
# Line 658  Line 693 
693      # Get the map list.      # Get the map list.
694      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
695      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
696      my $loadDiagram = $self->_TableLoader('Diagram');      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
697      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn');      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
698      my $loadSubsystem = $self->_TableLoader('Subsystem');      my $loadSubsystem = $self->_TableLoader('Subsystem');
699      my $loadRole = $self->_TableLoader('Role');      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
700      my $loadRoleEC = $self->_TableLoader('RoleEC');      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
701      my $loadCatalyzes = $self->_TableLoader('Catalyzes');      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
702      my $loadSSCell = $self->_TableLoader('SSCell');      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
703      my $loadContainsFeature = $self->_TableLoader('ContainsFeature');      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
704      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf');      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
705      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf');      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
706      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem');      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
707      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn');      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
708      my $loadHasSSCell = $self->_TableLoader('HasSSCell');      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
709      my $loadRoleSubset = $self->_TableLoader('RoleSubset');      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
710      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset');      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
711      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles');      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
712      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes');      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
713      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset');      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
714      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset');      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
715        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
716      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
717          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
718      } else {      } else {
# Line 692  Line 728 
728          my ($genomeID, $roleID);          my ($genomeID, $roleID);
729          my %roleData = ();          my %roleData = ();
730          for my $subsysID (@subsysIDs) {          for my $subsysID (@subsysIDs) {
             Trace("Creating subsystem $subsysID.") if T(3);  
             $loadSubsystem->Add("subsystemIn");  
731              # Get the subsystem object.              # Get the subsystem object.
732              my $sub = $fig->get_subsystem($subsysID);              my $sub = $fig->get_subsystem($subsysID);
733                # Only proceed if the subsystem has a spreadsheet.
734                if (! $sub->{empty_ss}) {
735                    Trace("Creating subsystem $subsysID.") if T(3);
736                    $loadSubsystem->Add("subsystemIn");
737              # Create the subsystem record.              # Create the subsystem record.
738              my $curator = $sub->get_curator();              my $curator = $sub->get_curator();
739              my $notes = $sub->get_notes();              my $notes = $sub->get_notes();
740              $loadSubsystem->Put($subsysID, $curator, $notes);              $loadSubsystem->Put($subsysID, $curator, $notes);
741                    my $class = $fig->subsystem_classification($subsysID);
742                    if ($class) {
743                        $loadSubsystemClass->Put($subsysID, $class);
744                    }
745              # 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.
746              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
747                  # Connect to this role.                  # Connect to this role.
# Line 743  Line 785 
785                      # part of the spreadsheet cell ID.                      # part of the spreadsheet cell ID.
786                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
787                          # Get the features in the spreadsheet cell for this genome and role.                          # Get the features in the spreadsheet cell for this genome and role.
788                          my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
789                          # Only proceed if features exist.                          # Only proceed if features exist.
790                          if (@pegs > 0) {                          if (@pegs > 0) {
791                              # Create the spreadsheet cell.                              # Create the spreadsheet cell.
# Line 764  Line 806 
806                      if ($pegCount > 0) {                      if ($pegCount > 0) {
807                          Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                          Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
808                          $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                          $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                         # Partition the PEGs found into clusters.  
                         my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
809                          # Create a hash mapping PEG IDs to cluster numbers.                          # Create a hash mapping PEG IDs to cluster numbers.
810                          # We default to -1 for all of them.                          # We default to -1 for all of them.
811                          my %clusterOf = map { $_ => -1 } @pegsFound;                          my %clusterOf = map { $_ => -1 } @pegsFound;
812                                # Partition the PEGs found into clusters.
813                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
814                          for (my $i = 0; $i <= $#clusters; $i++) {                          for (my $i = 0; $i <= $#clusters; $i++) {
815                              my $subList = $clusters[$i];                              my $subList = $clusters[$i];
816                              for my $peg (@{$subList}) {                              for my $peg (@{$subList}) {
# Line 796  Line 838 
838                  # Connect the subset to the subsystem.                  # Connect the subset to the subsystem.
839                  $loadHasRoleSubset->Put($subsysID, $actualID);                  $loadHasRoleSubset->Put($subsysID, $actualID);
840                  # Connect the subset to its roles.                  # Connect the subset to its roles.
841                  my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
842                  for my $roleID (@roles) {                  for my $roleID (@roles) {
843                      $loadConsistsOfRoles->Put($actualID, $roleID);                      $loadConsistsOfRoles->Put($actualID, $roleID);
844                  }                  }
# Line 816  Line 858 
858                  }                  }
859              }              }
860          }          }
861            }
862          # 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
863          # 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
864          # in subsystems (and therefore appear in the %ecToRoles hash) are          # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 892  Line 935 
935      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
936      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
937      my $loadProperty = $self->_TableLoader('Property');      my $loadProperty = $self->_TableLoader('Property');
938      my $loadHasProperty = $self->_TableLoader('HasProperty');      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
939      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
940          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
941      } else {      } else {
# Line 903  Line 946 
946          # Loop through the genomes.          # Loop through the genomes.
947          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (keys %{$genomeHash}) {
948              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
949                Trace("Generating properties for $genomeID.") if T(3);
950              # 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
951              # tuples returned by "all_features_detailed". We use "all_features_detailed"              # tuples returned by "all_features_detailed". We use "all_features_detailed"
952              # rather than "all_features" because we want all features regardless of type.              # rather than "all_features" because we want all features regardless of type.
953              my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};              my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
954                my $featureCount = 0;
955                my $propertyCount = 0;
956              # Loop through the features, creating HasProperty records.              # Loop through the features, creating HasProperty records.
957              for my $fid (@features) {              for my $fid (@features) {
                 $loadProperty->Add("featureIn");  
958                  # 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
959                  # to insure we do not get any genome attributes.                  # to insure we do not get any genome attributes.
960                  my @attributeList = $fig->get_attributes($fid, '', '', '');                  my @attributeList = $fig->get_attributes($fid, '', '', '');
961                    if (scalar @attributeList) {
962                        $featureCount++;
963                    }
964                  # Loop through the attributes.                  # Loop through the attributes.
965                  for my $tuple (@attributeList) {                  for my $tuple (@attributeList) {
966                        $propertyCount++;
967                      # Get this attribute value's data. Note that we throw away the FID,                      # Get this attribute value's data. Note that we throw away the FID,
968                      # since it will always be the same as the value if "$fid".                      # since it will always be the same as the value if "$fid".
969                      my (undef, $key, $value, $url) = @{$tuple};                      my (undef, $key, $value, $url) = @{$tuple};
# Line 936  Line 985 
985                      $loadHasProperty->Put($fid, $propertyID, $url);                      $loadHasProperty->Put($fid, $propertyID, $url);
986                  }                  }
987              }              }
988                # Update the statistics.
989                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
990                $loadHasProperty->Add("featuresIn", $featureCount);
991                $loadHasProperty->Add("propertiesIn", $propertyCount);
992          }          }
993      }      }
994      # Finish the load.      # Finish the load.
# Line 979  Line 1032 
1032      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1033      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1034      my $loadAnnotation = $self->_TableLoader('Annotation');      my $loadAnnotation = $self->_TableLoader('Annotation');
1035      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation');      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1036      my $loadSproutUser = $self->_TableLoader('SproutUser');      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1037      my $loadUserAccess = $self->_TableLoader('UserAccess');      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1038      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation');      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1039      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1040          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1041      } else {      } else {
# Line 1000  Line 1053 
1053          # Loop through the genomes.          # Loop through the genomes.
1054          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1055              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);  
1056                  # 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
1057                  # from showing up for a single PEG's annotations.                  # from showing up for a single PEG's annotations.
1058                  my %seenTimestamps = ();                  my %seenTimestamps = ();
1059                  # Loop through the annotations.              # Get the genome's annotations.
1060                  for my $tuple ($fig->feature_annotations($peg, "raw")) {              my @annotations = $fig->read_all_annotations($genomeID);
1061                      my ($fid, $timestamp, $user, $text) = @{$tuple};              Trace("Processing annotations.") if T(2);
1062                for my $tuple (@annotations) {
1063                    # Get the annotation tuple.
1064                    my ($peg, $timestamp, $user, $text) = @{$tuple};
1065                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1066                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1067                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1068                      # stop the substitution search.                      # stop the substitution search.
1069                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 1024  Line 1076 
1076                          # 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
1077                          # the key is unique.                          # the key is unique.
1078                          my $keyStamp = $timestamp;                          my $keyStamp = $timestamp;
1079                          while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1080                              $keyStamp++;                              $keyStamp++;
1081                          }                          }
                         $seenTimestamps{$keyStamp} = 1;  
1082                          my $annotationID = "$peg:$keyStamp";                          my $annotationID = "$peg:$keyStamp";
1083                        $seenTimestamps{$annotationID} = 1;
1084                          # Insure the user exists.                          # Insure the user exists.
1085                          if (! $users{$user}) {                          if (! $users{$user}) {
1086                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 1046  Line 1098 
1098                  }                  }
1099              }              }
1100          }          }
     }  
1101      # Finish the load.      # Finish the load.
1102      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1103      return $retVal;      return $retVal;
# Line 1088  Line 1139 
1139      # Get the genome hash.      # Get the genome hash.
1140      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1141      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1142      my $loadComesFrom = $self->_TableLoader('ComesFrom');      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1143      my $loadSource = $self->_TableLoader('Source');      my $loadSource = $self->_TableLoader('Source');
1144      my $loadSourceURL = $self->_TableLoader('SourceURL');      my $loadSourceURL = $self->_TableLoader('SourceURL');
1145      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
# Line 1175  Line 1226 
1226      } else {      } else {
1227          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1228          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1229          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1230          my $orgLine;          my $orgLine;
1231          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1232              # Clean the input line.              # Clean the input line.
# Line 1187  Line 1238 
1238          close ORGS;          close ORGS;
1239          # Now the function file.          # Now the function file.
1240          my $funcLine;          my $funcLine;
1241          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1242          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1243              # Clean the line ending.              # Clean the line ending.
1244              chomp $funcLine;              chomp $funcLine;
# Line 1246  Line 1297 
1297      my $fig = $self->{fig};      my $fig = $self->{fig};
1298      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1299      my $loadReaction = $self->_TableLoader('Reaction');      my $loadReaction = $self->_TableLoader('Reaction');
1300      my $loadReactionURL = $self->_TableLoader('ReactionURL');      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1301      my $loadCompound = $self->_TableLoader('Compound');      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1302      my $loadCompoundName = $self->_TableLoader('CompoundName');      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1303      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS');      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1304      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf');      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1305      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1306          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1307      } else {      } else {
# Line 1366  Line 1417 
1417      return $retVal;      return $retVal;
1418  }  }
1419    
1420    =head3 LoadSynonymData
1421    
1422    C<< my $stats = $spl->LoadSynonymData(); >>
1423    
1424    Load the synonym groups into Sprout.
1425    
1426    The following relations are loaded by this method.
1427    
1428        SynonymGroup
1429        IsSynonymGroupFor
1430    
1431    The source information for these relations is taken from the C<maps_to_id> method
1432    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1433    SQL against the FIG database.
1434    
1435    =over 4
1436    
1437    =item RETURNS
1438    
1439    Returns a statistics object for the loads.
1440    
1441    =back
1442    
1443    =cut
1444    #: Return Type $%;
1445    sub LoadSynonymData {
1446        # Get this object instance.
1447        my ($self) = @_;
1448        # Get the FIG object.
1449        my $fig = $self->{fig};
1450        # Get the genome hash.
1451        my $genomeHash = $self->{genomes};
1452        # Create a load object for the table we're loading.
1453        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1454        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1455        if ($self->{options}->{loadOnly}) {
1456            Trace("Loading from existing files.") if T(2);
1457        } else {
1458            Trace("Generating synonym group data.") if T(2);
1459            # Get the database handle.
1460            my $dbh = $fig->db_handle();
1461            # Ask for the synonyms.
1462            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1463            my $result = $sth->execute();
1464            if (! defined($result)) {
1465                Confess("Database error in Synonym load: " . $sth->errstr());
1466            } else {
1467                # Remember the current synonym.
1468                my $current_syn = "";
1469                # Count the features.
1470                my $featureCount = 0;
1471                # Loop through the synonym/peg pairs.
1472                while (my @row = $sth->fetchrow()) {
1473                    # Get the synonym ID and feature ID.
1474                    my ($syn_id, $peg) = @row;
1475                    # Insure it's for one of our genomes.
1476                    my $genomeID = FIG::genome_of($peg);
1477                    if (exists $genomeHash->{$genomeID}) {
1478                        # Verify the synonym.
1479                        if ($syn_id ne $current_syn) {
1480                            # It's new, so put it in the group table.
1481                            $loadSynonymGroup->Put($syn_id);
1482                            $current_syn = $syn_id;
1483                        }
1484                        # Connect the synonym to the peg.
1485                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1486                        # Count this feature.
1487                        $featureCount++;
1488                        if ($featureCount % 1000 == 0) {
1489                            Trace("$featureCount features processed.") if T(3);
1490                        }
1491                    }
1492                }
1493            }
1494        }
1495        # Finish the load.
1496        my $retVal = $self->_FinishAll();
1497        return $retVal;
1498    }
1499    
1500    =head3 LoadFamilyData
1501    
1502    C<< my $stats = $spl->LoadFamilyData(); >>
1503    
1504    Load the protein families into Sprout.
1505    
1506    The following relations are loaded by this method.
1507    
1508        Family
1509        ContainsFeature
1510    
1511    The source information for these relations is taken from the C<families_for_protein>,
1512    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1513    
1514    =over 4
1515    
1516    =item RETURNS
1517    
1518    Returns a statistics object for the loads.
1519    
1520    =back
1521    
1522    =cut
1523    #: Return Type $%;
1524    sub LoadFamilyData {
1525        # Get this object instance.
1526        my ($self) = @_;
1527        # Get the FIG object.
1528        my $fig = $self->{fig};
1529        # Get the genome hash.
1530        my $genomeHash = $self->{genomes};
1531        # Create load objects for the tables we're loading.
1532        my $loadFamily = $self->_TableLoader('Family');
1533        my $loadContainsFeature = $self->_TableLoader('ContainsFeature');
1534        if ($self->{options}->{loadOnly}) {
1535            Trace("Loading from existing files.") if T(2);
1536        } else {
1537            Trace("Generating family data.") if T(2);
1538            # Create a hash for the family IDs.
1539            my %familyHash = ();
1540            # Loop through the genomes.
1541            for my $genomeID (sort keys %{$genomeHash}) {
1542                Trace("Processing features for $genomeID.") if T(2);
1543                # Loop through this genome's PEGs.
1544                for my $fid ($fig->all_features($genomeID, "peg")) {
1545                    $loadContainsFeature->Add("features", 1);
1546                    # Get this feature's families.
1547                    my @families = $fig->families_for_protein($fid);
1548                    # Loop through the families, connecting them to the feature.
1549                    for my $family (@families) {
1550                        $loadContainsFeature->Put($family, $fid);
1551                        # If this is a new family, create a record for it.
1552                        if (! exists $familyHash{$family}) {
1553                            $loadFamily->Add("families", 1);
1554                            my $size = $fig->sz_family($family);
1555                            my $func = $fig->family_function($family);
1556                            $loadFamily->Put($family, $size, $func);
1557                        }
1558                    }
1559                }
1560            }
1561        }
1562        # Finish the load.
1563        my $retVal = $self->_FinishAll();
1564        return $retVal;
1565    }
1566    
1567  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1568    
1569  =head3 TableLoader  =head3 TableLoader
# Line 1382  Line 1580 
1580    
1581  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1582    
1583    =item ignore
1584    
1585    TRUE if the table should be ignored entirely, else FALSE.
1586    
1587  =item RETURN  =item RETURN
1588    
1589  Returns an ERDBLoad object for loading the specified table.  Returns an ERDBLoad object for loading the specified table.
# Line 1392  Line 1594 
1594    
1595  sub _TableLoader {  sub _TableLoader {
1596      # Get the parameters.      # Get the parameters.
1597      my ($self, $tableName, $loadOnly) = @_;      my ($self, $tableName, $ignore) = @_;
1598      # Create the load object.      # Create the load object.
1599      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1600                                   $ignore);
1601      # Cache it in the loader list.      # Cache it in the loader list.
1602      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1603      # Return it to the caller.      # Return it to the caller.
# Line 1428  Line 1631 
1631      my $retVal = Stats->new();      my $retVal = Stats->new();
1632      # Get the loader list.      # Get the loader list.
1633      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1634        # Create a hash to hold the statistics objects, keyed on relation name.
1635        my %loaderHash = ();
1636      # 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
1637      # 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.
1638      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1639          # Trace the fact that we're cleaning up.          # Get the relation name.
1640          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1641            # Check the ignore flag.
1642            if ($loader->Ignore) {
1643                Trace("Relation $relName not loaded.") if T(2);
1644            } else {
1645                # Here we really need to finish.
1646          Trace("Finishing $relName.") if T(2);          Trace("Finishing $relName.") if T(2);
1647          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1648                $loaderHash{$relName} = $stats;
1649            }
1650        }
1651        # Now we loop through again, actually loading the tables. We want to finish before
1652        # loading so that if something goes wrong at this point, all the load files are usable
1653        # and we don't have to redo all that work.
1654        for my $relName (sort keys %loaderHash) {
1655            # Get the statistics for this relation.
1656            my $stats = $loaderHash{$relName};
1657            # Check for a database load.
1658          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1659              # 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.
1660              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);

Legend:
Removed from v.1.23  
changed lines
  Added in v.1.61

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3