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

Diff of /Sprout/SproutLoad.pm

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

revision 1.26, Mon Jan 30 21:57:02 2006 UTC revision 1.72, Sat Oct 14 18:12:14 2006 UTC
# Line 30  Line 30 
30      $stats->Accumulate($spl->LoadFeatureData());      $stats->Accumulate($spl->LoadFeatureData());
31      print $stats->Show();      print $stats->Show();
32    
 This module makes use of the internal Sprout property C<_erdb>.  
   
33  It is worth noting that the FIG object does not need to be a real one. Any object  It is worth noting that the FIG object does not need to be a real one. Any object
34  that implements the FIG methods for data retrieval could be used. So, for example,  that implements the FIG methods for data retrieval could be used. So, for example,
35  this object could be used to copy data from one Sprout database to another, or  this object could be used to copy data from one Sprout database to another, or
# Line 80  Line 78 
78  =item subsysFile  =item subsysFile
79    
80  Either the name of the file containing the list of trusted subsystems or a reference  Either the name of the file containing the list of trusted subsystems or a reference
81  to a list of subsystem names. If nothing is specified, all known subsystems will be  to a list of subsystem names. If nothing is specified, all NMPDR subsystems will be
82  considered trusted. Only subsystem data related to the trusted subsystems is loaded.  considered trusted. (A subsystem is considered NMPDR if it has a file named C<NMPDR>
83    in its data directory.) Only subsystem data related to the trusted subsystems is loaded.
84    
85  =item options  =item options
86    
# Line 94  Line 93 
93  sub new {  sub new {
94      # Get the parameters.      # Get the parameters.
95      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;      my ($class, $sprout, $fig, $genomeFile, $subsysFile, $options) = @_;
96      # Load the list of genomes into a hash.      # Create the genome hash.
97      my %genomes;      my %genomes = ();
98        # We only need it if load-only is NOT specified.
99        if (! $options->{loadOnly}) {
100      if (! defined($genomeFile) || $genomeFile eq '') {      if (! defined($genomeFile) || $genomeFile eq '') {
101          # Here we want all the complete genomes and an access code of 1.          # Here we want all the complete genomes and an access code of 1.
102          my @genomeList = $fig->genomes(1);          my @genomeList = $fig->genomes(1);
# Line 119  Line 120 
120                  # an omitted access code can be defaulted to 1.                  # an omitted access code can be defaulted to 1.
121                  for my $genomeLine (@genomeList) {                  for my $genomeLine (@genomeList) {
122                      my ($genomeID, $accessCode) = split("\t", $genomeLine);                      my ($genomeID, $accessCode) = split("\t", $genomeLine);
123                      if (undef $accessCode) {                          if (! defined($accessCode)) {
124                          $accessCode = 1;                          $accessCode = 1;
125                      }                      }
126                      $genomes{$genomeID} = $accessCode;                      $genomes{$genomeID} = $accessCode;
# Line 129  Line 130 
130              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");              Confess("Invalid genome parameter ($type) in SproutLoad constructor.");
131          }          }
132      }      }
133        }
134      # Load the list of trusted subsystems.      # Load the list of trusted subsystems.
135      my %subsystems = ();      my %subsystems = ();
136        # We only need it if load-only is NOT specified.
137        if (! $options->{loadOnly}) {
138      if (! defined $subsysFile || $subsysFile eq '') {      if (! defined $subsysFile || $subsysFile eq '') {
139          # Here we want all the subsystems.              # Here we want all the usable subsystems. First we get the whole list.
140          %subsystems = map { $_ => 1 } $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141                # Loop through, checking for usability.
142                for my $sub (@subs) {
143                    if ($fig->usable_subsystem($sub)) {
144                        $subsystems{$sub} = 1;
145                    }
146                }
147      } else {      } else {
148          my $type = ref $subsysFile;          my $type = ref $subsysFile;
149          if ($type eq 'ARRAY') {          if ($type eq 'ARRAY') {
# Line 153  Line 163 
163              Confess("Invalid subsystem parameter in SproutLoad constructor.");              Confess("Invalid subsystem parameter in SproutLoad constructor.");
164          }          }
165      }      }
166            # Go through the subsys hash again, creating the keyword list for each subsystem.
167            for my $subsystem (keys %subsystems) {
168                my $name = $subsystem;
169                $name =~ s/_/ /g;
170                my $classes = $fig->subsystem_classification($subsystem);
171                my @classList = map { " $_" } @{$classes};
172                $name .= join("", @classList);
173                $subsystems{$subsystem} = $name;
174            }
175        }
176      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
177      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
178      # Create the Sprout load object.      # Create the Sprout load object.
# Line 162  Line 182 
182                    subsystems => \%subsystems,                    subsystems => \%subsystems,
183                    sprout => $sprout,                    sprout => $sprout,
184                    loadDirectory => $directory,                    loadDirectory => $directory,
185                    erdb => $sprout->{_erdb},                    erdb => $sprout,
186                    loaders => [],                    loaders => [],
187                    options => $options                    options => $options
188                   };                   };
# Line 250  Line 270 
270              $loadGenome->Add("genomeIn");              $loadGenome->Add("genomeIn");
271              # The access code comes in via the genome hash.              # The access code comes in via the genome hash.
272              my $accessCode = $genomeHash->{$genomeID};              my $accessCode = $genomeHash->{$genomeID};
273              # Get the genus, species, and strain from the scientific name. Note that we append              # Get the genus, species, and strain from the scientific name.
             # the genome ID to the strain. In some cases this is the totality of the strain name.  
274              my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);              my ($genus, $species, @extraData) = split / /, $self->{fig}->genus_species($genomeID);
275              my $extra = join " ", @extraData, "[$genomeID]";              my $extra = join " ", @extraData;
276              # Get the full taxonomy.              # Get the full taxonomy.
277              my $taxonomy = $fig->taxonomy_of($genomeID);              my $taxonomy = $fig->taxonomy_of($genomeID);
278                # Open the NMPDR group file for this genome.
279                my $group;
280                if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&
281                    defined($group = <TMP>)) {
282                    # Clean the line ending.
283                    chomp $group;
284                } else {
285                    # No group, so use the default.
286                    $group = $FIG_Config::otherGroup;
287                }
288                close TMP;
289              # Output the genome record.              # Output the genome record.
290              $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,              $loadGenome->Put($genomeID, $accessCode, $fig->is_complete($genomeID), $genus,
291                               $species, $extra, $taxonomy);                               $group, $species, $extra, $taxonomy);
292              # Now we loop through each of the genome's contigs.              # Now we loop through each of the genome's contigs.
293              my @contigs = $fig->all_contigs($genomeID);              my @contigs = $fig->all_contigs($genomeID);
294              for my $contigID (@contigs) {              for my $contigID (@contigs) {
# Line 330  Line 360 
360      my $fig = $self->{fig};      my $fig = $self->{fig};
361      # Get the genome hash.      # Get the genome hash.
362      my $genomeFilter = $self->{genomes};      my $genomeFilter = $self->{genomes};
363      my $genomeCount = (keys %{$genomeFilter});      # Set up an ID counter for the PCHs.
364      my $featureCount = $genomeCount * 4000;      my $pchID = 0;
365      # Start the loads.      # Start the loads.
366      my $loadCoupling = $self->_TableLoader('Coupling');      my $loadCoupling = $self->_TableLoader('Coupling');
367      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);      my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);
# Line 365  Line 395 
395                  for my $coupleData (@couplings) {                  for my $coupleData (@couplings) {
396                      my ($peg2, $score) = @{$coupleData};                      my ($peg2, $score) = @{$coupleData};
397                      # Compute the coupling ID.                      # Compute the coupling ID.
398                      my $coupleID = Sprout::CouplingID($peg1, $peg2);                      my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);
399                      if (! exists $dupHash{$coupleID}) {                      if (! exists $dupHash{$coupleID}) {
400                          $loadCoupling->Add("couplingIn");                          $loadCoupling->Add("couplingIn");
401                          # Here we have a new coupling to store in the load files.                          # Here we have a new coupling to store in the load files.
# Line 401  Line 431 
431                              }                              }
432                          }                          }
433                          for my $evidenceID (keys %evidenceMap) {                          for my $evidenceID (keys %evidenceMap) {
434                                # Get the ID for this evidence.
435                                $pchID++;
436                              # Create the evidence record.                              # Create the evidence record.
437                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};                              my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};
438                              $loadPCH->Put($evidenceID, $usage);                              $loadPCH->Put($pchID, $usage);
439                              # Connect it to the coupling.                              # Connect it to the coupling.
440                              $loadIsEvidencedBy->Put($coupleID, $evidenceID);                              $loadIsEvidencedBy->Put($coupleID, $pchID);
441                              # Connect it to the features.                              # Connect it to the features.
442                              $loadUsesAsEvidence->Put($evidenceID, $peg3, 1);                              $loadUsesAsEvidence->Put($pchID, $peg3, 1);
443                              $loadUsesAsEvidence->Put($evidenceID, $peg4, 2);                              $loadUsesAsEvidence->Put($pchID, $peg4, 2);
444                          }                          }
445                      }                      }
446                  }                  }
# Line 436  Line 468 
468      FeatureTranslation      FeatureTranslation
469      FeatureUpstream      FeatureUpstream
470      IsLocatedIn      IsLocatedIn
471        HasFeature
472        HasRoleInSubsystem
473    
474  =over 4  =over 4
475    
# Line 450  Line 484 
484  sub LoadFeatureData {  sub LoadFeatureData {
485      # Get this object instance.      # Get this object instance.
486      my ($self) = @_;      my ($self) = @_;
487      # Get the FIG object.      # Get the FIG and Sprout objects.
488      my $fig = $self->{fig};      my $fig = $self->{fig};
489        my $sprout = $self->{sprout};
490      # Get the table of genome IDs.      # Get the table of genome IDs.
491      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
492      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
# Line 461  Line 496 
496      my $loadFeatureLink = $self->_TableLoader('FeatureLink');      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
497      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
498      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
499        my $loadHasFeature = $self->_TableLoader('HasFeature', $self->PrimaryOnly);
500        my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem', $self->PrimaryOnly);
501        # Get the subsystem hash.
502        my $subHash = $self->{subsystems};
503      # Get the maximum sequence size. We need this later for splitting up the      # Get the maximum sequence size. We need this later for splitting up the
504      # locations.      # locations.
505      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
# Line 474  Line 513 
513              $loadFeature->Add("genomeIn");              $loadFeature->Add("genomeIn");
514              # Get the feature list for this genome.              # Get the feature list for this genome.
515              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
516                # Sort and count the list.
517                my @featureTuples = sort { $a->[0] cmp $b->[0] } @{$features};
518                my $count = scalar @featureTuples;
519                Trace("$count features found for genome $genomeID.") if T(3);
520                # Set up for our duplicate-feature check.
521                my $oldFeatureID = "";
522              # Loop through the features.              # Loop through the features.
523              for my $featureData (@{$features}) {              for my $featureTuple (@featureTuples) {
                 $loadFeature->Add("featureIn");  
524                  # Split the tuple.                  # Split the tuple.
525                  my ($featureID, $locations, undef, $type) = @{$featureData};                  my ($featureID, $locations, undef, $type) = @{$featureTuple};
526                  # Create the feature record.                  # Check for duplicates.
527                  $loadFeature->Put($featureID, 1, $type);                  if ($featureID eq $oldFeatureID) {
528                        Trace("Duplicate feature $featureID found.") if T(1);
529                    } else {
530                        $oldFeatureID = $featureID;
531                        # Count this feature.
532                        $loadFeature->Add("featureIn");
533                        # Get the functional assignment.
534                        my $assignment = $fig->function_of($featureID);
535                        # Begin building the keywords.
536                        my $keywords = "$assignment $genomeID";
537                        # Link this feature to the parent genome.
538                        $loadHasFeature->Put($genomeID, $featureID, $type);
539                  # Create the aliases.                  # Create the aliases.
540                  for my $alias ($fig->feature_aliases($featureID)) {                  for my $alias ($fig->feature_aliases($featureID)) {
541                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
542                            $keywords .= " $alias";
543                  }                  }
544                  # Get the links.                  # Get the links.
545                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
# Line 503  Line 559 
559                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
560                      }                      }
561                  }                  }
562                        # Now we need to find the subsystems this feature participates in.
563                        # We also add the subsystems to the keyword list. Before we do that,
564                        # we must convert underscores to spaces and tack on the classifications.
565                        my @subsystems = $fig->peg_to_subsystems($featureID);
566                        for my $subsystem (@subsystems) {
567                            # Only proceed if we like this subsystem.
568                            if (exists $subHash->{$subsystem}) {
569                                # Store the has-role link.
570                                $loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type);
571                                # Save the subsystem's keyword data.
572                                my $subKeywords = $subHash->{$subsystem};
573                                $keywords .= " $subKeywords";
574                            }
575                        }
576                        # The final task is to add virulence and essentiality attributes.
577                        if ($fig->virulent($featureID)) {
578                            $keywords .= " virulent";
579                        }
580                        if ($fig->essential($featureID)) {
581                            $keywords .= " essential";
582                        }
583                        # Clean the keyword list.
584                        my $cleanWords = $sprout->CleanKeywords($keywords);
585                        # Create the feature record.
586                        $loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords);
587                  # This part is the roughest. We need to relate the features to contig                  # This part is the roughest. We need to relate the features to contig
588                  # locations, and the locations must be split so that none of them exceed                  # locations, and the locations must be split so that none of them exceed
589                  # the maximum segment size. This simplifies the genes_in_region processing                  # the maximum segment size. This simplifies the genes_in_region processing
# Line 532  Line 613 
613              }              }
614          }          }
615      }      }
616        }
617      # Finish the loads.      # Finish the loads.
618      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
619      return $retVal;      return $retVal;
# Line 580  Line 662 
662              Trace("Processing features for genome $genomeID.") if T(3);              Trace("Processing features for genome $genomeID.") if T(3);
663              # Get the feature list for this genome.              # Get the feature list for this genome.
664              my $features = $fig->all_features_detailed($genomeID);              my $features = $fig->all_features_detailed($genomeID);
665                # Count the BBHs we find.
666                my $bbhCount = 0;
667              # Loop through the features.              # Loop through the features.
668              for my $featureData (@{$features}) {              for my $featureData (@{$features}) {
669                  # Split the tuple.                  # Split the tuple.
# Line 595  Line 679 
679                      if ($genomeHash->{$targetGenomeID}) {                      if ($genomeHash->{$targetGenomeID}) {
680                          $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,                          $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,
681                                                             $score);                                                             $score);
682                            $bbhCount++;
683                      }                      }
684                  }                  }
685              }              }
686                Trace("$bbhCount BBHs found for $genomeID.") if T(3);
687          }          }
688      }      }
689      # Finish the loads.      # Finish the loads.
# Line 620  Line 706 
706  The following relations are loaded by this method.  The following relations are loaded by this method.
707    
708      Subsystem      Subsystem
709        SubsystemClass
710      Role      Role
711      RoleEC      RoleEC
712      SSCell      SSCell
# Line 682  Line 769 
769      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
770      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
771      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
772        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
773      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
774          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
775      } else {      } else {
# Line 697  Line 785 
785          my ($genomeID, $roleID);          my ($genomeID, $roleID);
786          my %roleData = ();          my %roleData = ();
787          for my $subsysID (@subsysIDs) {          for my $subsysID (@subsysIDs) {
             Trace("Creating subsystem $subsysID.") if T(3);  
             $loadSubsystem->Add("subsystemIn");  
788              # Get the subsystem object.              # Get the subsystem object.
789              my $sub = $fig->get_subsystem($subsysID);              my $sub = $fig->get_subsystem($subsysID);
790                # Only proceed if the subsystem has a spreadsheet.
791                if (! $sub->{empty_ss}) {
792                    Trace("Creating subsystem $subsysID.") if T(3);
793                    $loadSubsystem->Add("subsystemIn");
794              # Create the subsystem record.              # Create the subsystem record.
795              my $curator = $sub->get_curator();              my $curator = $sub->get_curator();
796              my $notes = $sub->get_notes();              my $notes = $sub->get_notes();
797              $loadSubsystem->Put($subsysID, $curator, $notes);              $loadSubsystem->Put($subsysID, $curator, $notes);
798                    # Now for the classification string. This comes back as a list
799                    # reference and we convert it to a space-delimited string.
800                    my $classList = $fig->subsystem_classification($subsysID);
801                    my $classString = join(" ", grep { $_ } @$classList);
802                    $loadSubsystemClass->Put($subsysID, $classString);
803              # Connect it to its roles. Each role is a column in the subsystem spreadsheet.              # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
804              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {              for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
805                  # Connect to this role.                  # Connect to this role.
# Line 748  Line 843 
843                      # part of the spreadsheet cell ID.                      # part of the spreadsheet cell ID.
844                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                      for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
845                          # Get the features in the spreadsheet cell for this genome and role.                          # Get the features in the spreadsheet cell for this genome and role.
846                          my @pegs = $sub->get_pegs_from_cell($row, $col);                              my @pegs = grep { !$fig->is_deleted_fid($_) } $sub->get_pegs_from_cell($row, $col);
847                          # Only proceed if features exist.                          # Only proceed if features exist.
848                          if (@pegs > 0) {                          if (@pegs > 0) {
849                              # Create the spreadsheet cell.                              # Create the spreadsheet cell.
# Line 769  Line 864 
864                      if ($pegCount > 0) {                      if ($pegCount > 0) {
865                          Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                          Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
866                          $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                          $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                         # Partition the PEGs found into clusters.  
                         my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
867                          # Create a hash mapping PEG IDs to cluster numbers.                          # Create a hash mapping PEG IDs to cluster numbers.
868                          # We default to -1 for all of them.                          # We default to -1 for all of them.
869                          my %clusterOf = map { $_ => -1 } @pegsFound;                          my %clusterOf = map { $_ => -1 } @pegsFound;
870                                # Partition the PEGs found into clusters.
871                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
872                          for (my $i = 0; $i <= $#clusters; $i++) {                          for (my $i = 0; $i <= $#clusters; $i++) {
873                              my $subList = $clusters[$i];                              my $subList = $clusters[$i];
874                              for my $peg (@{$subList}) {                              for my $peg (@{$subList}) {
# Line 801  Line 896 
896                  # Connect the subset to the subsystem.                  # Connect the subset to the subsystem.
897                  $loadHasRoleSubset->Put($subsysID, $actualID);                  $loadHasRoleSubset->Put($subsysID, $actualID);
898                  # Connect the subset to its roles.                  # Connect the subset to its roles.
899                  my @roles = $sub->get_subset($subsetID);                      my @roles = $sub->get_subsetC_roles($subsetID);
900                  for my $roleID (@roles) {                  for my $roleID (@roles) {
901                      $loadConsistsOfRoles->Put($actualID, $roleID);                      $loadConsistsOfRoles->Put($actualID, $roleID);
902                  }                  }
# Line 821  Line 916 
916                  }                  }
917              }              }
918          }          }
919            }
920          # 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
921          # 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
922          # in subsystems (and therefore appear in the %ecToRoles hash) are          # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 906  Line 1002 
1002          my %propertyKeys = ();          my %propertyKeys = ();
1003          my $nextID = 1;          my $nextID = 1;
1004          # Loop through the genomes.          # Loop through the genomes.
1005          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1006              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
1007              Trace("Generating properties for $genomeID.") if T(3);              Trace("Generating properties for $genomeID.") if T(3);
1008              # Get the genome's features. The feature ID is the first field in the              # Get the genome's features. The feature ID is the first field in the
# Line 920  Line 1016 
1016                  # Get all attributes for this feature. We do this one feature at a time                  # Get all attributes for this feature. We do this one feature at a time
1017                  # to insure we do not get any genome attributes.                  # to insure we do not get any genome attributes.
1018                  my @attributeList = $fig->get_attributes($fid, '', '', '');                  my @attributeList = $fig->get_attributes($fid, '', '', '');
1019                    # Add essentiality and virulence attributes.
1020                    if ($fig->essential($fid)) {
1021                        push @attributeList, [$fid, 'essential', 1, ''];
1022                    }
1023                    if ($fig->virulent($fid)) {
1024                        push @attributeList, [$fid, 'virulent', 1, ''];
1025                    }
1026                  if (scalar @attributeList) {                  if (scalar @attributeList) {
1027                      $featureCount++;                      $featureCount++;
1028                  }                  }
# Line 1015  Line 1118 
1118          # Loop through the genomes.          # Loop through the genomes.
1119          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
1120              Trace("Processing $genomeID.") if T(3);              Trace("Processing $genomeID.") if T(3);
             # Get the genome's PEGs.  
             my @pegs = $fig->pegs_of($genomeID);  
             for my $peg (@pegs) {  
                 Trace("Processing $peg.") if T(4);  
1121                  # Create a hash of timestamps. We use this to prevent duplicate time stamps                  # Create a hash of timestamps. We use this to prevent duplicate time stamps
1122                  # from showing up for a single PEG's annotations.                  # from showing up for a single PEG's annotations.
1123                  my %seenTimestamps = ();                  my %seenTimestamps = ();
1124                  # Loop through the annotations.              # Get the genome's annotations.
1125                  for my $tuple ($fig->feature_annotations($peg, "raw")) {              my @annotations = $fig->read_all_annotations($genomeID);
1126                      my ($fid, $timestamp, $user, $text) = @{$tuple};              Trace("Processing annotations.") if T(2);
1127                for my $tuple (@annotations) {
1128                    # Get the annotation tuple.
1129                    my ($peg, $timestamp, $user, $text) = @{$tuple};
1130                      # Here we fix up the annotation text. "\r" is removed,                      # Here we fix up the annotation text. "\r" is removed,
1131                      # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1132                      # modifier so that new-lines inside the text do not                      # modifier so that new-lines inside the text do not
1133                      # stop the substitution search.                      # stop the substitution search.
1134                      $text =~ s/\r//gs;                      $text =~ s/\r//gs;
# Line 1039  Line 1141 
1141                          # Here it's a number. We need to insure the one we use to form                          # Here it's a number. We need to insure the one we use to form
1142                          # the key is unique.                          # the key is unique.
1143                          my $keyStamp = $timestamp;                          my $keyStamp = $timestamp;
1144                          while ($seenTimestamps{$keyStamp}) {                      while ($seenTimestamps{"$peg:$keyStamp"}) {
1145                              $keyStamp++;                              $keyStamp++;
1146                          }                          }
                         $seenTimestamps{$keyStamp} = 1;  
1147                          my $annotationID = "$peg:$keyStamp";                          my $annotationID = "$peg:$keyStamp";
1148                        $seenTimestamps{$annotationID} = 1;
1149                          # Insure the user exists.                          # Insure the user exists.
1150                          if (! $users{$user}) {                          if (! $users{$user}) {
1151                              $loadSproutUser->Put($user, "SEED user");                              $loadSproutUser->Put($user, "SEED user");
# Line 1061  Line 1163 
1163                  }                  }
1164              }              }
1165          }          }
     }  
1166      # Finish the load.      # Finish the load.
1167      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
1168      return $retVal;      return $retVal;
# Line 1190  Line 1291 
1291      } else {      } else {
1292          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1293          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1294          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1295          my $orgLine;          my $orgLine;
1296          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1297              # Clean the input line.              # Clean the input line.
# Line 1202  Line 1303 
1303          close ORGS;          close ORGS;
1304          # Now the function file.          # Now the function file.
1305          my $funcLine;          my $funcLine;
1306          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1307          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1308              # Clean the line ending.              # Clean the line ending.
1309              chomp $funcLine;              chomp $funcLine;
# Line 1334  Line 1435 
1435    
1436      GenomeGroups      GenomeGroups
1437    
1438  There is no direct support for genome groups in FIG, so we access the SEED  Currently, we do not use groups. We used to use them for NMPDR groups,
1439    butThere is no direct support for genome groups in FIG, so we access the SEED
1440  files directly.  files directly.
1441    
1442  =over 4  =over 4
# Line 1360  Line 1462 
1462          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1463      } else {      } else {
1464          Trace("Generating group data.") if T(2);          Trace("Generating group data.") if T(2);
1465            # Currently there are no groups.
1466        }
1467        # Finish the load.
1468        my $retVal = $self->_FinishAll();
1469        return $retVal;
1470    }
1471    
1472    =head3 LoadSynonymData
1473    
1474    C<< my $stats = $spl->LoadSynonymData(); >>
1475    
1476    Load the synonym groups into Sprout.
1477    
1478    The following relations are loaded by this method.
1479    
1480        SynonymGroup
1481        IsSynonymGroupFor
1482    
1483    The source information for these relations is taken from the C<maps_to_id> method
1484    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1485    SQL against the FIG database.
1486    
1487    =over 4
1488    
1489    =item RETURNS
1490    
1491    Returns a statistics object for the loads.
1492    
1493    =back
1494    
1495    =cut
1496    #: Return Type $%;
1497    sub LoadSynonymData {
1498        # Get this object instance.
1499        my ($self) = @_;
1500        # Get the FIG object.
1501        my $fig = $self->{fig};
1502        # Get the genome hash.
1503        my $genomeHash = $self->{genomes};
1504        # Create a load object for the table we're loading.
1505        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1506        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1507        if ($self->{options}->{loadOnly}) {
1508            Trace("Loading from existing files.") if T(2);
1509        } else {
1510            Trace("Generating synonym group data.") if T(2);
1511            # Get the database handle.
1512            my $dbh = $fig->db_handle();
1513            # Ask for the synonyms.
1514            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1515            my $result = $sth->execute();
1516            if (! defined($result)) {
1517                Confess("Database error in Synonym load: " . $sth->errstr());
1518            } else {
1519                # Remember the current synonym.
1520                my $current_syn = "";
1521                # Count the features.
1522                my $featureCount = 0;
1523                # Loop through the synonym/peg pairs.
1524                while (my @row = $sth->fetchrow()) {
1525                    # Get the synonym ID and feature ID.
1526                    my ($syn_id, $peg) = @row;
1527                    # Insure it's for one of our genomes.
1528                    my $genomeID = FIG::genome_of($peg);
1529                    if (exists $genomeHash->{$genomeID}) {
1530                        # Verify the synonym.
1531                        if ($syn_id ne $current_syn) {
1532                            # It's new, so put it in the group table.
1533                            $loadSynonymGroup->Put($syn_id);
1534                            $current_syn = $syn_id;
1535                        }
1536                        # Connect the synonym to the peg.
1537                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1538                        # Count this feature.
1539                        $featureCount++;
1540                        if ($featureCount % 1000 == 0) {
1541                            Trace("$featureCount features processed.") if T(3);
1542                        }
1543                    }
1544                }
1545            }
1546        }
1547        # Finish the load.
1548        my $retVal = $self->_FinishAll();
1549        return $retVal;
1550    }
1551    
1552    =head3 LoadFamilyData
1553    
1554    C<< my $stats = $spl->LoadFamilyData(); >>
1555    
1556    Load the protein families into Sprout.
1557    
1558    The following relations are loaded by this method.
1559    
1560        Family
1561        IsFamilyForFeature
1562    
1563    The source information for these relations is taken from the C<families_for_protein>,
1564    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1565    
1566    =over 4
1567    
1568    =item RETURNS
1569    
1570    Returns a statistics object for the loads.
1571    
1572    =back
1573    
1574    =cut
1575    #: Return Type $%;
1576    sub LoadFamilyData {
1577        # Get this object instance.
1578        my ($self) = @_;
1579        # Get the FIG object.
1580        my $fig = $self->{fig};
1581        # Get the genome hash.
1582        my $genomeHash = $self->{genomes};
1583        # Create load objects for the tables we're loading.
1584        my $loadFamily = $self->_TableLoader('Family');
1585        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1586        if ($self->{options}->{loadOnly}) {
1587            Trace("Loading from existing files.") if T(2);
1588        } else {
1589            Trace("Generating family data.") if T(2);
1590            # Create a hash for the family IDs.
1591            my %familyHash = ();
1592          # Loop through the genomes.          # Loop through the genomes.
1593          my $line;          for my $genomeID (sort keys %{$genomeHash}) {
1594          for my $genomeID (keys %{$genomeHash}) {              Trace("Processing features for $genomeID.") if T(2);
1595              Trace("Processing $genomeID.") if T(3);              # Loop through this genome's PEGs.
1596              # Open the NMPDR group file for this genome.              for my $fid ($fig->all_features($genomeID, "peg")) {
1597              if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&                  $loadIsFamilyForFeature->Add("features", 1);
1598                  defined($line = <TMP>)) {                  # Get this feature's families.
1599                  # Clean the line ending.                  my @families = $fig->families_for_protein($fid);
1600                  chomp $line;                  # Loop through the families, connecting them to the feature.
1601                  # Add the group to the table. Note that there can only be one group                  for my $family (@families) {
1602                  # per genome.                      $loadIsFamilyForFeature->Put($family, $fid);
1603                  $loadGenomeGroups->Put($genomeID, $line);                      # If this is a new family, create a record for it.
1604                        if (! exists $familyHash{$family}) {
1605                            $familyHash{$family} = 1;
1606                            $loadFamily->Add("families", 1);
1607                            my $size = $fig->sz_family($family);
1608                            my $func = $fig->family_function($family);
1609                            $loadFamily->Put($family, $size, $func);
1610                        }
1611                    }
1612              }              }
             close TMP;  
1613          }          }
1614      }      }
1615      # Finish the load.      # Finish the load.
# Line 1381  Line 1617 
1617      return $retVal;      return $retVal;
1618  }  }
1619    
1620    
1621    
1622  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1623    
1624  =head3 TableLoader  =head3 TableLoader
# Line 1448  Line 1686 
1686      my $retVal = Stats->new();      my $retVal = Stats->new();
1687      # Get the loader list.      # Get the loader list.
1688      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1689        # Create a hash to hold the statistics objects, keyed on relation name.
1690        my %loaderHash = ();
1691      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1692      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads more restartable.
1693      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1694          # Get the relation name.          # Get the relation name.
1695          my $relName = $loader->RelName;          my $relName = $loader->RelName;
# Line 1460  Line 1700 
1700              # Here we really need to finish.              # Here we really need to finish.
1701              Trace("Finishing $relName.") if T(2);              Trace("Finishing $relName.") if T(2);
1702              my $stats = $loader->Finish();              my $stats = $loader->Finish();
1703              if ($self->{options}->{dbLoad} && ! $loader->Ignore) {              $loaderHash{$relName} = $stats;
1704            }
1705        }
1706        # Now we loop through again, actually loading the tables. We want to finish before
1707        # loading so that if something goes wrong at this point, all the load files are usable
1708        # and we don't have to redo all that work.
1709        for my $relName (sort keys %loaderHash) {
1710            # Get the statistics for this relation.
1711            my $stats = $loaderHash{$relName};
1712            # Check for a database load.
1713            if ($self->{options}->{dbLoad}) {
1714                  # Here we want to use the load file just created to load the database.                  # Here we want to use the load file just created to load the database.
1715                  Trace("Loading relation $relName.") if T(2);                  Trace("Loading relation $relName.") if T(2);
1716                  my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);                  my $newStats = $self->{sprout}->LoadUpdate(1, [$relName]);
# Line 1470  Line 1720 
1720              $retVal->Accumulate($stats);              $retVal->Accumulate($stats);
1721              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1722          }          }
     }  
1723      # Return the load statistics.      # Return the load statistics.
1724      return $retVal;      return $retVal;
1725  }  }

Legend:
Removed from v.1.26  
changed lines
  Added in v.1.72

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3