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

Diff of /Sprout/SproutLoad.pm

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

revision 1.40, Thu Jun 8 15:37:32 2006 UTC revision 1.75, Sun Oct 22 05:17:10 2006 UTC
# Line 120  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 136  Line 136 
136      # We only need it if load-only is NOT specified.      # We only need it if load-only is NOT specified.
137      if (! $options->{loadOnly}) {      if (! $options->{loadOnly}) {
138          if (! defined $subsysFile || $subsysFile eq '') {          if (! defined $subsysFile || $subsysFile eq '') {
139              # Here we want all the NMPDR subsystems. First we get the whole list.              # Here we want all the usable subsystems. First we get the whole list.
140              my @subs = $fig->all_subsystems();              my @subs = $fig->all_subsystems();
141              # Loop through, checking for the NMPDR file.              # Loop through, checking for usability.
142              for my $sub (@subs) {              for my $sub (@subs) {
143                  if (-e "$FIG_Config::data/Subsystems/$sub/NMPDR") {                  if ($fig->usable_subsystem($sub)) {
144                      $subsystems{$sub} = 1;                      $subsystems{$sub} = 1;
145                  }                  }
146              }              }
# Line 163  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();
# Line 266  Line 275 
275              my $extra = join " ", @extraData;              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 340  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 375  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 411  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, $peg4, 2);
444                          }                          }
445                      }                      }
446                  }                  }
# Line 447  Line 469 
469      FeatureUpstream      FeatureUpstream
470      IsLocatedIn      IsLocatedIn
471      HasFeature      HasFeature
472        HasRoleInSubsystem
473    
474  =over 4  =over 4
475    
# Line 461  Line 484 
484  sub LoadFeatureData {  sub LoadFeatureData {
485      # Get this object instance.      # Get this object instance.
486      my ($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 472  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');      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 486  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                  # Link it to the parent genome.                      Trace("Duplicate feature $featureID found.") if T(1);
529                  $loadHasFeature->Put($genomeID, $featureID, $type);                  } else {
530                        $oldFeatureID = $featureID;
531                        # Count this feature.
532                        $loadFeature->Add("featureIn");
533                        # Begin building the keywords.
534                        my @keywords = ($genomeID);
535                        # Get the functional assignment and aliases. This
536                        # depends on the feature type.
537                        my $assignment;
538                        if ($type eq "peg") {
539                            $assignment = $fig->function_of($featureID);
540                  # Create the aliases.                  # Create the aliases.
541                  for my $alias ($fig->feature_aliases($featureID)) {                  for my $alias ($fig->feature_aliases($featureID)) {
542                      $loadFeatureAlias->Put($featureID, $alias);                      $loadFeatureAlias->Put($featureID, $alias);
543                                push @keywords, $alias;
544                  }                  }
545                        } else {
546                            # For other types, the assignment is the first (and ONLY) alias.
547                            ($assignment) = $fig->feature_aliases($featureID);
548                        }
549                        Trace("Assignment for $featureID is: $assignment") if T(4);
550                        # Break the assignment into words and shove it onto the
551                        # keyword list.
552                        push @keywords, split(/\s+/, $assignment);
553                        # Link this feature to the parent genome.
554                        $loadHasFeature->Put($genomeID, $featureID, $type);
555                  # Get the links.                  # Get the links.
556                  my @links = $fig->fid_links($featureID);                  my @links = $fig->fid_links($featureID);
557                  for my $link (@links) {                  for my $link (@links) {
# Line 517  Line 570 
570                          $loadFeatureUpstream->Put($featureID, $upstream);                          $loadFeatureUpstream->Put($featureID, $upstream);
571                      }                      }
572                  }                  }
573                        # Now we need to find the subsystems this feature participates in.
574                        # We also add the subsystems to the keyword list. Before we do that,
575                        # we must convert underscores to spaces and tack on the classifications.
576                        my @subsystems = $fig->peg_to_subsystems($featureID);
577                        for my $subsystem (@subsystems) {
578                            # Only proceed if we like this subsystem.
579                            if (exists $subHash->{$subsystem}) {
580                                # Store the has-role link.
581                                $loadHasRoleInSubsystem->Put($featureID, $subsystem, $genomeID, $type);
582                                # Save the subsystem's keyword data.
583                                my $subKeywords = $subHash->{$subsystem};
584                                push @keywords, split /\s+/, $subKeywords;
585                                # Now we need to get this feature's role in the subsystem.
586                                my $subObject = $fig->get_subsystem($subsystem);
587                                my @roleColumns = $subObject->get_peg_roles($featureID);
588                                my @allRoles = $subObject->get_roles();
589                                for my $col (@roleColumns) {
590                                    my $role = $allRoles[$col];
591                                    push @keywords, split /\s+/, $role;
592                                    push @keywords, $subObject->get_role_abbr($col);
593                                }
594                            }
595                        }
596                        # The final task is to add virulence and essentiality attributes.
597                        if ($fig->virulent($featureID)) {
598                            push @keywords, "virulent";
599                        }
600                        if ($fig->essential($featureID)) {
601                            push @keywords, "essential";
602                        }
603                        # Now we need to bust up hyphenated words in the keyword
604                        # list.
605                        my $keywordString = "";
606                        for my $keyword (@keywords) {
607                            if (length $keyword >= 4) {
608                                $keywordString .= " $keyword";
609                                if ($keyword =~ /-/) {
610                                    my @words = grep { length($_) >= 4 } split /-/, $keyword;
611                                    $keywordString .= join(" ", "", @words);
612                                }
613                            }
614                        }
615                        # Clean the keyword list.
616                        my $cleanWords = $sprout->CleanKeywords($keywordString);
617                        Trace("Keyword string for $featureID: $cleanWords") if T(4);
618                        # Create the feature record.
619                        $loadFeature->Put($featureID, 1, $type, $assignment, $cleanWords);
620                  # This part is the roughest. We need to relate the features to contig                  # This part is the roughest. We need to relate the features to contig
621                  # locations, and the locations must be split so that none of them exceed                  # locations, and the locations must be split so that none of them exceed
622                  # the maximum segment size. This simplifies the genes_in_region processing                  # the maximum segment size. This simplifies the genes_in_region processing
# Line 546  Line 646 
646              }              }
647          }          }
648      }      }
     # Finish the loads.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
 =head3 LoadBBHData  
   
 C<< my $stats = $spl->LoadBBHData(); >>  
   
 Load the bidirectional best hit data from FIG into Sprout.  
   
 Sprout does not store information on similarities. Instead, it has only the  
 bi-directional best hits. Even so, the BBH table is one of the largest in  
 the database.  
   
 The following relations are loaded by this method.  
   
     IsBidirectionalBestHitOf  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadBBHData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the table of genome IDs.  
     my $genomeHash = $self->{genomes};  
     # Create load objects for each of the tables we're loading.  
     my $loadIsBidirectionalBestHitOf = $self->_TableLoader('IsBidirectionalBestHitOf');  
     if ($self->{options}->{loadOnly}) {  
         Trace("Loading from existing files.") if T(2);  
     } else {  
         Trace("Generating BBH data.") if T(2);  
         # Now we loop through the genomes, generating the data for each one.  
         for my $genomeID (sort keys %{$genomeHash}) {  
             $loadIsBidirectionalBestHitOf->Add("genomeIn");  
             Trace("Processing features for genome $genomeID.") if T(3);  
             # Get the feature list for this genome.  
             my $features = $fig->all_features_detailed($genomeID);  
             # Loop through the features.  
             for my $featureData (@{$features}) {  
                 # Split the tuple.  
                 my ($featureID, $locations, $aliases, $type) = @{$featureData};  
                 # Get the bi-directional best hits.  
                 my @bbhList = $fig->bbhs($featureID);  
                 for my $bbhEntry (@bbhList) {  
                     # Get the target feature ID and the score.  
                     my ($targetID, $score) = @{$bbhEntry};  
                     # Check the target feature's genome.  
                     my $targetGenomeID = $fig->genome_of($targetID);  
                     # Only proceed if it's one of our genomes.  
                     if ($genomeHash->{$targetGenomeID}) {  
                         $loadIsBidirectionalBestHitOf->Put($featureID, $targetID, $targetGenomeID,  
                                                            $score);  
                     }  
                 }  
             }  
         }  
649      }      }
650      # Finish the loads.      # Finish the loads.
651      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
# Line 634  Line 667 
667  The following relations are loaded by this method.  The following relations are loaded by this method.
668    
669      Subsystem      Subsystem
670        SubsystemClass
671      Role      Role
672      RoleEC      RoleEC
673      SSCell      SSCell
# Line 696  Line 730 
730      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);
731      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);
732      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);
733        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);
734      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
735          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
736      } else {      } else {
# Line 721  Line 756 
756                  my $curator = $sub->get_curator();                  my $curator = $sub->get_curator();
757                  my $notes = $sub->get_notes();                  my $notes = $sub->get_notes();
758                  $loadSubsystem->Put($subsysID, $curator, $notes);                  $loadSubsystem->Put($subsysID, $curator, $notes);
759                    # Now for the classification string. This comes back as a list
760                    # reference and we convert it to a space-delimited string.
761                    my $classList = $fig->subsystem_classification($subsysID);
762                    my $classString = join(" : ", grep { $_ } @$classList);
763                    $loadSubsystemClass->Put($subsysID, $classString);
764                  # Connect it to its roles. Each role is a column in the subsystem spreadsheet.                  # Connect it to its roles. Each role is a column in the subsystem spreadsheet.
765                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
766                      # Connect to this role.                      # Connect to this role.
# Line 785  Line 825 
825                          if ($pegCount > 0) {                          if ($pegCount > 0) {
826                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);                              Trace("$pegCount PEGs in $cellCount cells for $genomeID.") if T(3);
827                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);                              $loadParticipatesIn->Put($genomeID, $subsysID, $variantCode);
                             # Partition the PEGs found into clusters.  
                             my @clusters = $fig->compute_clusters(\@pegsFound, $sub);  
828                              # Create a hash mapping PEG IDs to cluster numbers.                              # Create a hash mapping PEG IDs to cluster numbers.
829                              # We default to -1 for all of them.                              # We default to -1 for all of them.
830                              my %clusterOf = map { $_ => -1 } @pegsFound;                              my %clusterOf = map { $_ => -1 } @pegsFound;
831                                # Partition the PEGs found into clusters.
832                                my @clusters = $fig->compute_clusters([keys %clusterOf], $sub);
833                              for (my $i = 0; $i <= $#clusters; $i++) {                              for (my $i = 0; $i <= $#clusters; $i++) {
834                                  my $subList = $clusters[$i];                                  my $subList = $clusters[$i];
835                                  for my $peg (@{$subList}) {                                  for my $peg (@{$subList}) {
# Line 837  Line 877 
877                      }                      }
878                  }                  }
879              }              }
880            }
881              # Now we loop through the diagrams. We need to create the diagram records              # Now we loop through the diagrams. We need to create the diagram records
882              # and link each diagram to its roles. Note that only roles which occur              # and link each diagram to its roles. Note that only roles which occur
883              # in subsystems (and therefore appear in the %ecToRoles hash) are              # in subsystems (and therefore appear in the %ecToRoles hash) are
# Line 870  Line 911 
911                  }                  }
912              }              }
913          }          }
     }  
914      # Finish the load.      # Finish the load.
915      my $retVal = $self->_FinishAll();      my $retVal = $self->_FinishAll();
916      return $retVal;      return $retVal;
# Line 923  Line 963 
963          my %propertyKeys = ();          my %propertyKeys = ();
964          my $nextID = 1;          my $nextID = 1;
965          # Loop through the genomes.          # Loop through the genomes.
966          for my $genomeID (keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
967              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
968              Trace("Generating properties for $genomeID.") if T(3);              Trace("Generating properties for $genomeID.") if T(3);
969              # Get the genome's features. The feature ID is the first field in the              # Get the genome's features. The feature ID is the first field in the
# Line 937  Line 977 
977                  # Get all attributes for this feature. We do this one feature at a time                  # Get all attributes for this feature. We do this one feature at a time
978                  # to insure we do not get any genome attributes.                  # to insure we do not get any genome attributes.
979                  my @attributeList = $fig->get_attributes($fid, '', '', '');                  my @attributeList = $fig->get_attributes($fid, '', '', '');
980                    # Add essentiality and virulence attributes.
981                    if ($fig->essential($fid)) {
982                        push @attributeList, [$fid, 'essential', 1, ''];
983                    }
984                    if ($fig->virulent($fid)) {
985                        push @attributeList, [$fid, 'virulent', 1, ''];
986                    }
987                  if (scalar @attributeList) {                  if (scalar @attributeList) {
988                      $featureCount++;                      $featureCount++;
989                  }                  }
# Line 1042  Line 1089 
1089                  # Get the annotation tuple.                  # Get the annotation tuple.
1090                  my ($peg, $timestamp, $user, $text) = @{$tuple};                  my ($peg, $timestamp, $user, $text) = @{$tuple};
1091                  # Here we fix up the annotation text. "\r" is removed,                  # Here we fix up the annotation text. "\r" is removed,
1092                  # and "\t" and "\n" are escaped. Note we use the "s"                  # and "\t" and "\n" are escaped. Note we use the "gs"
1093                  # modifier so that new-lines inside the text do not                  # modifier so that new-lines inside the text do not
1094                  # stop the substitution search.                  # stop the substitution search.
1095                  $text =~ s/\r//gs;                  $text =~ s/\r//gs;
# Line 1205  Line 1252 
1252      } else {      } else {
1253          Trace("Generating external data.") if T(2);          Trace("Generating external data.") if T(2);
1254          # We loop through the files one at a time. First, the organism file.          # We loop through the files one at a time. First, the organism file.
1255          Open(\*ORGS, "<$FIG_Config::global/ext_org.table");          Open(\*ORGS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_org.table |");
1256          my $orgLine;          my $orgLine;
1257          while (defined($orgLine = <ORGS>)) {          while (defined($orgLine = <ORGS>)) {
1258              # Clean the input line.              # Clean the input line.
# Line 1217  Line 1264 
1264          close ORGS;          close ORGS;
1265          # Now the function file.          # Now the function file.
1266          my $funcLine;          my $funcLine;
1267          Open(\*FUNCS, "<$FIG_Config::global/ext_func.table");          Open(\*FUNCS, "sort +0 -1 -u -t\"\t\" $FIG_Config::global/ext_func.table |");
1268          while (defined($funcLine = <FUNCS>)) {          while (defined($funcLine = <FUNCS>)) {
1269              # Clean the line ending.              # Clean the line ending.
1270              chomp $funcLine;              chomp $funcLine;
# Line 1349  Line 1396 
1396    
1397      GenomeGroups      GenomeGroups
1398    
1399  There is no direct support for genome groups in FIG, so we access the SEED  Currently, we do not use groups. We used to use them for NMPDR groups,
1400    butThere is no direct support for genome groups in FIG, so we access the SEED
1401  files directly.  files directly.
1402    
1403  =over 4  =over 4
# Line 1375  Line 1423 
1423          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1424      } else {      } else {
1425          Trace("Generating group data.") if T(2);          Trace("Generating group data.") if T(2);
1426            # Currently there are no groups.
1427        }
1428        # Finish the load.
1429        my $retVal = $self->_FinishAll();
1430        return $retVal;
1431    }
1432    
1433    =head3 LoadSynonymData
1434    
1435    C<< my $stats = $spl->LoadSynonymData(); >>
1436    
1437    Load the synonym groups into Sprout.
1438    
1439    The following relations are loaded by this method.
1440    
1441        SynonymGroup
1442        IsSynonymGroupFor
1443    
1444    The source information for these relations is taken from the C<maps_to_id> method
1445    of the B<FIG> object. Unfortunately, to make this work, we need to use direct
1446    SQL against the FIG database.
1447    
1448    =over 4
1449    
1450    =item RETURNS
1451    
1452    Returns a statistics object for the loads.
1453    
1454    =back
1455    
1456    =cut
1457    #: Return Type $%;
1458    sub LoadSynonymData {
1459        # Get this object instance.
1460        my ($self) = @_;
1461        # Get the FIG object.
1462        my $fig = $self->{fig};
1463        # Get the genome hash.
1464        my $genomeHash = $self->{genomes};
1465        # Create a load object for the table we're loading.
1466        my $loadSynonymGroup = $self->_TableLoader('SynonymGroup');
1467        my $loadIsSynonymGroupFor = $self->_TableLoader('IsSynonymGroupFor');
1468        if ($self->{options}->{loadOnly}) {
1469            Trace("Loading from existing files.") if T(2);
1470        } else {
1471            Trace("Generating synonym group data.") if T(2);
1472            # Get the database handle.
1473            my $dbh = $fig->db_handle();
1474            # Ask for the synonyms.
1475            my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1476            my $result = $sth->execute();
1477            if (! defined($result)) {
1478                Confess("Database error in Synonym load: " . $sth->errstr());
1479            } else {
1480                # Remember the current synonym.
1481                my $current_syn = "";
1482                # Count the features.
1483                my $featureCount = 0;
1484                # Loop through the synonym/peg pairs.
1485                while (my @row = $sth->fetchrow()) {
1486                    # Get the synonym ID and feature ID.
1487                    my ($syn_id, $peg) = @row;
1488                    # Insure it's for one of our genomes.
1489                    my $genomeID = FIG::genome_of($peg);
1490                    if (exists $genomeHash->{$genomeID}) {
1491                        # Verify the synonym.
1492                        if ($syn_id ne $current_syn) {
1493                            # It's new, so put it in the group table.
1494                            $loadSynonymGroup->Put($syn_id);
1495                            $current_syn = $syn_id;
1496                        }
1497                        # Connect the synonym to the peg.
1498                        $loadIsSynonymGroupFor->Put($syn_id, $peg);
1499                        # Count this feature.
1500                        $featureCount++;
1501                        if ($featureCount % 1000 == 0) {
1502                            Trace("$featureCount features processed.") if T(3);
1503                        }
1504                    }
1505                }
1506            }
1507        }
1508        # Finish the load.
1509        my $retVal = $self->_FinishAll();
1510        return $retVal;
1511    }
1512    
1513    =head3 LoadFamilyData
1514    
1515    C<< my $stats = $spl->LoadFamilyData(); >>
1516    
1517    Load the protein families into Sprout.
1518    
1519    The following relations are loaded by this method.
1520    
1521        Family
1522        IsFamilyForFeature
1523    
1524    The source information for these relations is taken from the C<families_for_protein>,
1525    C<family_function>, and C<sz_family> methods of the B<FIG> object.
1526    
1527    =over 4
1528    
1529    =item RETURNS
1530    
1531    Returns a statistics object for the loads.
1532    
1533    =back
1534    
1535    =cut
1536    #: Return Type $%;
1537    sub LoadFamilyData {
1538        # Get this object instance.
1539        my ($self) = @_;
1540        # Get the FIG object.
1541        my $fig = $self->{fig};
1542        # Get the genome hash.
1543        my $genomeHash = $self->{genomes};
1544        # Create load objects for the tables we're loading.
1545        my $loadFamily = $self->_TableLoader('Family');
1546        my $loadIsFamilyForFeature = $self->_TableLoader('IsFamilyForFeature');
1547        if ($self->{options}->{loadOnly}) {
1548            Trace("Loading from existing files.") if T(2);
1549        } else {
1550            Trace("Generating family data.") if T(2);
1551            # Create a hash for the family IDs.
1552            my %familyHash = ();
1553          # Loop through the genomes.          # Loop through the genomes.
1554          my $line;          for my $genomeID (sort keys %{$genomeHash}) {
1555          for my $genomeID (keys %{$genomeHash}) {              Trace("Processing features for $genomeID.") if T(2);
1556              Trace("Processing $genomeID.") if T(3);              # Loop through this genome's PEGs.
1557              # Open the NMPDR group file for this genome.              for my $fid ($fig->all_features($genomeID, "peg")) {
1558              if (open(TMP, "<$FIG_Config::organisms/$genomeID/NMPDR") &&                  $loadIsFamilyForFeature->Add("features", 1);
1559                  defined($line = <TMP>)) {                  # Get this feature's families.
1560                  # Clean the line ending.                  my @families = $fig->families_for_protein($fid);
1561                  chomp $line;                  # Loop through the families, connecting them to the feature.
1562                  # Add the group to the table. Note that there can only be one group                  for my $family (@families) {
1563                  # per genome.                      $loadIsFamilyForFeature->Put($family, $fid);
1564                  $loadGenomeGroups->Put($genomeID, $line);                      # If this is a new family, create a record for it.
1565                        if (! exists $familyHash{$family}) {
1566                            $familyHash{$family} = 1;
1567                            $loadFamily->Add("families", 1);
1568                            my $size = $fig->sz_family($family);
1569                            my $func = $fig->family_function($family);
1570                            $loadFamily->Put($family, $size, $func);
1571                        }
1572                    }
1573              }              }
             close TMP;  
1574          }          }
1575      }      }
1576      # Finish the load.      # Finish the load.
# Line 1396  Line 1578 
1578      return $retVal;      return $retVal;
1579  }  }
1580    
1581    
1582    
1583  =head2 Internal Utility Methods  =head2 Internal Utility Methods
1584    
1585  =head3 TableLoader  =head3 TableLoader
# Line 1463  Line 1647 
1647      my $retVal = Stats->new();      my $retVal = Stats->new();
1648      # Get the loader list.      # Get the loader list.
1649      my $loadList = $self->{loaders};      my $loadList = $self->{loaders};
1650        # Create a hash to hold the statistics objects, keyed on relation name.
1651        my %loaderHash = ();
1652      # Loop through the list, finishing the loads. Note that if the finish fails, we die      # Loop through the list, finishing the loads. Note that if the finish fails, we die
1653      # ignominiously. At some future point, we want to make the loads restartable.      # ignominiously. At some future point, we want to make the loads more restartable.
1654      while (my $loader = pop @{$loadList}) {      while (my $loader = pop @{$loadList}) {
1655          # Get the relation name.          # Get the relation name.
1656          my $relName = $loader->RelName;          my $relName = $loader->RelName;
# Line 1475  Line 1661 
1661              # Here we really need to finish.              # Here we really need to finish.
1662              Trace("Finishing $relName.") if T(2);              Trace("Finishing $relName.") if T(2);
1663              my $stats = $loader->Finish();              my $stats = $loader->Finish();
1664                $loaderHash{$relName} = $stats;
1665            }
1666        }
1667        # Now we loop through again, actually loading the tables. We want to finish before
1668        # loading so that if something goes wrong at this point, all the load files are usable
1669        # and we don't have to redo all that work.
1670        for my $relName (sort keys %loaderHash) {
1671            # Get the statistics for this relation.
1672            my $stats = $loaderHash{$relName};
1673            # Check for a database load.
1674              if ($self->{options}->{dbLoad}) {              if ($self->{options}->{dbLoad}) {
1675                  # Here we want to use the load file just created to load the database.                  # Here we want to use the load file just created to load the database.
1676                  Trace("Loading relation $relName.") if T(2);                  Trace("Loading relation $relName.") if T(2);
# Line 1485  Line 1681 
1681              $retVal->Accumulate($stats);              $retVal->Accumulate($stats);
1682              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);              Trace("Statistics for $relName:\n" . $stats->Show()) if T(2);
1683          }          }
     }  
1684      # Return the load statistics.      # Return the load statistics.
1685      return $retVal;      return $retVal;
1686  }  }

Legend:
Removed from v.1.40  
changed lines
  Added in v.1.75

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3