[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 1.48, Fri Jul 7 00:24:16 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 NMPDR subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for the NMPDR file.
142                for my $sub (@subs) {
143                    if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {
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 329  Line 344 
344      my $featureCount = $genomeCount * 4000;      my $featureCount = $genomeCount * 4000;
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 431  Line 446 
446      FeatureTranslation      FeatureTranslation
447      FeatureUpstream      FeatureUpstream
448      IsLocatedIn      IsLocatedIn
449        HasFeature
450    
451  =over 4  =over 4
452    
# Line 451  Line 467 
467      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
468      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
469      my $loadFeature = $self->_TableLoader('Feature');      my $loadFeature = $self->_TableLoader('Feature');
470      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn');      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);
471      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
472      my $loadFeatureLink = $self->_TableLoader('FeatureLink');      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
473      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
474      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
475        my $loadHasFeature = $self->_TableLoader('HasFeature');
476      # 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
477      # locations.      # locations.
478      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
# Line 476  Line 493 
493                  my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureData};
494                  # Create the feature record.                  # Create the feature record.
495                  $loadFeature->Put($featureID, 1, $type);                  $loadFeature->Put($featureID, 1, $type);
496                    # Link it to the parent genome.
497                    $loadHasFeature->Put($genomeID, $featureID, $type);
498                  # Create the aliases.                  # Create the aliases.
499                  for my $alias ($fig->feature_aliases($featureID)) {                  for my $alias ($fig->feature_aliases($featureID)) {
500                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
# Line 615  Line 634 
634  The following relations are loaded by this method.  The following relations are loaded by this method.
635    
636      Subsystem      Subsystem
637        SubsystemClass
638      Role      Role
639      RoleEC      RoleEC
640      SSCell      SSCell
# Line 658  Line 678 
678      # Get the map list.      # Get the map list.
679      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
680      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
681      my $loadDiagram = $self->_TableLoader('Diagram');      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);
682      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn');      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);
683      my $loadSubsystem = $self->_TableLoader('Subsystem');      my $loadSubsystem = $self->_TableLoader('Subsystem');
684      my $loadRole = $self->_TableLoader('Role');      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);
685      my $loadRoleEC = $self->_TableLoader('RoleEC');      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);
686      my $loadCatalyzes = $self->_TableLoader('Catalyzes');      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);
687      my $loadSSCell = $self->_TableLoader('SSCell');      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);
688      my $loadContainsFeature = $self->_TableLoader('ContainsFeature');      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);
689      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf');      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);
690      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf');      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);
691      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem');      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);
692      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn');      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);
693      my $loadHasSSCell = $self->_TableLoader('HasSSCell');      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);
694      my $loadRoleSubset = $self->_TableLoader('RoleSubset');      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);
695      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset');      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);
696      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles');      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);
697      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes');      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
698      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset');      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
699      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset');      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
700        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
701      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
702          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
703      } else {      } else {
# Line 692  Line 713 
713          my ($genomeID, $roleID);          my ($genomeID, $roleID);
714          my %roleData = ();          my %roleData = ();
715          for my $subsysID (@subsysIDs) {          for my $subsysID (@subsysIDs) {
             Trace("Creating subsystem $subsysID.") if T(3);  
             $loadSubsystem->Add("subsystemIn");  
716              # Get the subsystem object.              # Get the subsystem object.
717              my $sub = $fig->get_subsystem($subsysID);              my $sub = $fig->get_subsystem($subsysID);
718                # Only proceed if the subsystem has a spreadsheet.
719                if (! $sub->{empty_ss}) {
720                    Trace("Creating subsystem $subsysID.") if T(3);
721                    $loadSubsystem->Add("subsystemIn");
722              # Create the subsystem record.              # Create the subsystem record.
723              my $curator = $sub->get_curator();              my $curator = $sub->get_curator();
724              my $notes = $sub->get_notes();              my $notes = $sub->get_notes();
725              $loadSubsystem->Put($subsysID, $curator, $notes);              $loadSubsystem->Put($subsysID, $curator, $notes);
726                    my $class = $fig->subsystem_classification($subsysID);
727                    if ($class) {
728                        $loadSubsystemClass->Put($subsysID, $class);
729                    }
730              # 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.
731              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
732                  # Connect to this role.                  # Connect to this role.
# Line 743  Line 770 
770                      # part of the spreadsheet cell ID.                      # part of the spreadsheet cell ID.
771                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
772                          # Get the features in the spreadsheet cell for this genome and role.                          # Get the features in the spreadsheet cell for this genome and role.
773                          my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
774                          # Only proceed if features exist.                          # Only proceed if features exist.
775                          if (@pegs > 0) {                          if (@pegs > 0) {
776                              # Create the spreadsheet cell.                              # Create the spreadsheet cell.
# Line 764  Line 791 
791                      if ($pegCount > 0) {                      if ($pegCount > 0) {
792                          Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                          Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
793                          $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                          $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                         # Partition the PEGs found into clusters.  
                         my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
794                          # Create a hash mapping PEG IDs to cluster numbers.                          # Create a hash mapping PEG IDs to cluster numbers.
795                          # We default to -1 for all of them.                          # We default to -1 for all of them.
796                          my %clusterOf = map { $_ => -1 } @pegsFound;                          my %clusterOf = map { $_ => -1 } @pegsFound;
797                                # Partition the PEGs found into clusters.
798                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
799                          for (my $i = 0; $i <= $#clusters; $i++) {                          for (my $i = 0; $i <= $#clusters; $i++) {
800                              my $subList = $clusters[$i];                              my $subList = $clusters[$i];
801                              for my $peg (@{$subList}) {                              for my $peg (@{$subList}) {
# Line 796  Line 823 
823                  # Connect the subset to the subsystem.                  # Connect the subset to the subsystem.
824                  $loadHasRoleSubset->Put($subsysID, $actualID);                  $loadHasRoleSubset->Put($subsysID, $actualID);
825                  # Connect the subset to its roles.                  # Connect the subset to its roles.
826                  my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
827                  for my $roleID (@roles) {                  for my $roleID (@roles) {
828                      $loadConsistsOfRoles->Put($actualID, $roleID);                      $loadConsistsOfRoles->Put($actualID, $roleID);
829                  }                  }
# Line 849  Line 876 
876              }              }
877          }          }
878      }      }
879        }
880      # Finish the load.      # Finish the load.
881      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
882      return $retVal;      return $retVal;
# Line 892  Line 920 
920      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
921      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
922      my $loadProperty = $self->_TableLoader('Property');      my $loadProperty = $self->_TableLoader('Property');
923      my $loadHasProperty = $self->_TableLoader('HasProperty');      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);
924      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
925          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
926      } else {      } else {
# Line 903  Line 931 
931          # Loop through the genomes.          # Loop through the genomes.
932          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (keys %{$genomeHash}) {
933              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
934                Trace("Generating properties for $genomeID.") if T(3);
935              # 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
936              # tuples returned by "all_features_detailed". We use "all_features_detailed"              # tuples returned by "all_features_detailed". We use "all_features_detailed"
937              # rather than "all_features" because we want all features regardless of type.              # rather than "all_features" because we want all features regardless of type.
938              my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};              my @features = map { $_->[0] } @{$fig->all_features_detailed($genomeID)};
939                my $featureCount = 0;
940                my $propertyCount = 0;
941              # Loop through the features, creating HasProperty records.              # Loop through the features, creating HasProperty records.
942              for my $fid (@features) {              for my $fid (@features) {
                 $loadProperty->Add("featureIn");  
943                  # 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
944                  # to insure we do not get any genome attributes.                  # to insure we do not get any genome attributes.
945                  my @attributeList = $fig->get_attributes($fid, '', '', '');                  my @attributeList = $fig->get_attributes($fid, '', '', '');
946                    if (scalar @attributeList) {
947                        $featureCount++;
948                    }
949                  # Loop through the attributes.                  # Loop through the attributes.
950                  for my $tuple (@attributeList) {                  for my $tuple (@attributeList) {
951                        $propertyCount++;
952                      # Get this attribute value's data. Note that we throw away the FID,                      # Get this attribute value's data. Note that we throw away the FID,
953                      # since it will always be the same as the value if "$fid".                      # since it will always be the same as the value if "$fid".
954                      my (undef, $key, $value, $url) = @{$tuple};                      my (undef, $key, $value, $url) = @{$tuple};
# Line 936  Line 970 
970                      $loadHasProperty->Put($fid, $propertyID, $url);                      $loadHasProperty->Put($fid, $propertyID, $url);
971                  }                  }
972              }              }
973                # Update the statistics.
974                Trace("$propertyCount attributes processed for $featureCount features.") if T(3);
975                $loadHasProperty->Add("featuresIn", $featureCount);
976                $loadHasProperty->Add("propertiesIn", $propertyCount);
977          }          }
978      }      }
979      # Finish the load.      # Finish the load.
# Line 979  Line 1017 
1017      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1018      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1019      my $loadAnnotation = $self->_TableLoader('Annotation');      my $loadAnnotation = $self->_TableLoader('Annotation');
1020      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation');      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);
1021      my $loadSproutUser = $self->_TableLoader('SproutUser');      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);
1022      my $loadUserAccess = $self->_TableLoader('UserAccess');      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);
1023      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation');      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);
1024      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1025          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1026      } else {      } else {
# Line 1000  Line 1038 
1038          # Loop through the genomes.          # Loop through the genomes.
1039          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1040              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);  
1041                  # 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
1042                  # from showing up for a single PEG's annotations.                  # from showing up for a single PEG's annotations.
1043                  my %seenTimestamps = ();                  my %seenTimestamps = ();
1044                  # Loop through the annotations.              # Get the genome's annotations.
1045                  for my $tuple ($fig->feature_annotations($peg, "raw")) {              my @annotations = $fig->read_all_annotations($genomeID);
1046                      my ($fid, $timestamp, $user, $text) = @{$tuple};              Trace("Processing annotations.") if T(2);
1047                for my $tuple (@annotations) {
1048                    # Get the annotation tuple.
1049                    my ($peg, $timestamp, $user, $text) = @{$tuple};
1050                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1051                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1052                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1053                      # stop the substitution search.                      # stop the substitution search.
1054                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 1024  Line 1061 
1061                          # 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
1062                          # the key is unique.                          # the key is unique.
1063                          my $keyStamp = $timestamp;                          my $keyStamp = $timestamp;
1064                          while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1065                              $keyStamp++;                              $keyStamp++;
1066                          }                          }
                         $seenTimestamps{$keyStamp} = 1;  
1067                          my $annotationID = "$peg:$keyStamp";                          my $annotationID = "$peg:$keyStamp";
1068                        $seenTimestamps{$annotationID} = 1;
1069                          # Insure the user exists.                          # Insure the user exists.
1070                          if (! $users{$user}) {                          if (! $users{$user}) {
1071                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 1046  Line 1083 
1083                  }                  }
1084              }              }
1085          }          }
     }  
1086      # Finish the load.      # Finish the load.
1087      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1088      return $retVal;      return $retVal;
# Line 1088  Line 1124 
1124      # Get the genome hash.      # Get the genome hash.
1125      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1126      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1127      my $loadComesFrom = $self->_TableLoader('ComesFrom');      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);
1128      my $loadSource = $self->_TableLoader('Source');      my $loadSource = $self->_TableLoader('Source');
1129      my $loadSourceURL = $self->_TableLoader('SourceURL');      my $loadSourceURL = $self->_TableLoader('SourceURL');
1130      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
# Line 1246  Line 1282 
1282      my $fig = $self->{fig};      my $fig = $self->{fig};
1283      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1284      my $loadReaction = $self->_TableLoader('Reaction');      my $loadReaction = $self->_TableLoader('Reaction');
1285      my $loadReactionURL = $self->_TableLoader('ReactionURL');      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);
1286      my $loadCompound = $self->_TableLoader('Compound');      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);
1287      my $loadCompoundName = $self->_TableLoader('CompoundName');      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);
1288      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS');      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);
1289      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf');      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);
1290      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1291          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1292      } else {      } else {
# Line 1366  Line 1402 
1402      return $retVal;      return $retVal;
1403  }  }
1404    
1405    =head3 LoadSynonymData
1406    
1407    C<< my $stats = $spl->LoadSynonymData(); >>
1408    
1409    Load the synonym groups into Sprout.
1410    
1411    The following relations are loaded by this method.
1412    
1413        SynonymGroup
1414        IsSynonymGroupFor
1415    
1416    The source information for these relations is taken from the C<maps_to_id> method
1417    of the B<FIG> object. The process starts from the features, so it is possible
1418    that there will be duplicates in the SynonymGroup load file, since the relationship
1419    is one-to-many toward the features. The automatic sort on primary entity relations
1420    will fix this for us.
1421    
1422    =over 4
1423    
1424    =item RETURNS
1425    
1426    Returns a statistics object for the loads.
1427    
1428    =back
1429    
1430    =cut
1431    #: Return Type $%;
1432    sub LoadSynonymData {
1433        # Get this object instance.
1434        my ($self) = @_;
1435        # Get the FIG object.
1436        my $fig = $self->{fig};
1437        # Get the genome hash.
1438        my $genomeHash = $self->{genomes};
1439        # Create a load object for the table we're loading.
1440        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1441        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1442        if ($self->{options}->{loadOnly}) {
1443            Trace("Loading from existing files.") if T(2);
1444        } else {
1445            Trace("Generating synonym group data.") if T(2);
1446            # Loop through the genomes.
1447            for my $genomeID (sort keys %{$genomeHash}) {
1448                Trace("Processing $genomeID.") if T(3);
1449                # Get all of the features for this genome. The only method that does this is
1450                # all_features_detailed, which returns extra baggage that we discard.
1451                my $featureData = $fig->all_features_detailed($genomeID);
1452                my @fids = map { $_->[0] } @{$featureData};
1453                Trace(scalar(@fids) . " features found for genome $genomeID.") if T(3);
1454                # Loop through the feature IDs.
1455                for my $fid (@fids) {
1456                    # Get the group for this feature.
1457                    my $synonym = $fig->maps_to_id($fid);
1458                    # Only proceed if the synonym is a real group.
1459                    if ($synonym ne $fid) {
1460                        $loadSynonymGroup->Put($synonym);
1461                        $loadIsSynonymGroupFor->Put($synonym, $fid);
1462                    }
1463                }
1464            }
1465        }
1466        # Finish the load.
1467        my $retVal = $self->_FinishAll();
1468        return $retVal;
1469    }
1470    
1471    
1472  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1473    
1474  =head3 TableLoader  =head3 TableLoader
# Line 1382  Line 1485 
1485    
1486  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1487    
1488    =item ignore
1489    
1490    TRUE if the table should be ignored entirely, else FALSE.
1491    
1492  =item RETURN  =item RETURN
1493    
1494  Returns an ERDBLoad object for loading the specified table.  Returns an ERDBLoad object for loading the specified table.
# Line 1392  Line 1499 
1499    
1500  sub _TableLoader {  sub _TableLoader {
1501      # Get the parameters.      # Get the parameters.
1502      my ($self, $tableName, $loadOnly) = @_;      my ($self, $tableName, $ignore) = @_;
1503      # Create the load object.      # Create the load object.
1504      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly);      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,
1505                                   $ignore);
1506      # Cache it in the loader list.      # Cache it in the loader list.
1507      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1508      # Return it to the caller.      # Return it to the caller.
# Line 1428  Line 1536 
1536      my $retVal = Stats->new();      my $retVal = Stats->new();
1537      # Get the loader list.      # Get the loader list.
1538      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1539        # Create a hash to hold the statistics objects, keyed on relation name.
1540        my %loaderHash = ();
1541      # 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
1542      # 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.
1543      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1544          # Trace the fact that we're cleaning up.          # Get the relation name.
1545          my $relName = $loader->RelName;          my $relName = $loader->RelName;
1546            # Check the ignore flag.
1547            if ($loader->Ignore) {
1548                Trace("Relation $relName not loaded.") if T(2);
1549            } else {
1550                # Here we really need to finish.
1551          Trace("Finishing $relName.") if T(2);          Trace("Finishing $relName.") if T(2);
1552          my $stats = $loader->Finish();          my $stats = $loader->Finish();
1553                $loaderHash{$relName} = $stats;
1554            }
1555        }
1556        # Now we loop through again, actually loading the tables. We want to finish before
1557        # loading so that if something goes wrong at this point, all the load files are usable
1558        # and we don't have to redo all that work.
1559        for my $relName (sort keys %loaderHash) {
1560            # Get the statistics for this relation.
1561            my $stats = $loaderHash{$relName};
1562            # Check for a database load.
1563          if ($self->{options}->{dbLoad}) {          if ($self->{options}->{dbLoad}) {
1564              # 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.
1565              Trace("Loading relation $relName.") if T(2);              Trace("Loading relation $relName.") if T(2);
# Line 1445  Line 1570 
1570          $retVal->Accumulate($stats);          $retVal->Accumulate($stats);
1571          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);          Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1572      }      }
1573        }
1574      # Return the load statistics.      # Return the load statistics.
1575      return $retVal;      return $retVal;
1576  }  }

Legend:
Removed from v.1.23  
changed lines
  Added in v.1.48

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3