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

Diff of /Sprout/SproutLoad.pm

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

revision 1.84, Thu May 17 23:44:51 2007 UTC revision 1.89, Mon Nov 5 23:43:57 2007 UTC
# Line 7  Line 7 
7      use PageBuilder;      use PageBuilder;
8      use ERDBLoad;      use ERDBLoad;
9      use FIG;      use FIG;
10        use FIGRules;
11      use Sprout;      use Sprout;
12      use Stats;      use Stats;
13      use BasicLocation;      use BasicLocation;
14      use HTML;      use HTML;
15        use AliasAnalysis;
16    
17  =head1 Sprout Load Methods  =head1 Sprout Load Methods
18    
# Line 101  Line 103 
103              # 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.
104              my @genomeList = $fig->genomes(1);              my @genomeList = $fig->genomes(1);
105              %genomes = map { $_ => 1 } @genomeList;              %genomes = map { $_ => 1 } @genomeList;
106                Trace(scalar(keys %genomes) . " genomes found.") if T(3);
107          } else {          } else {
108              my $type = ref $genomeFile;              my $type = ref $genomeFile;
109              Trace("Genome file parameter type is \"$type\".") if T(3);              Trace("Genome file parameter type is \"$type\".") if T(3);
# Line 167  Line 170 
170          for my $subsystem (keys %subsystems) {          for my $subsystem (keys %subsystems) {
171              my $name = $subsystem;              my $name = $subsystem;
172              $name =~ s/_/ /g;              $name =~ s/_/ /g;
173              my $classes = $fig->subsystem_classification($subsystem);  #            my $classes = $fig->subsystem_classification($subsystem);
174              $name .= " " . join(" ", @{$classes});  #            $name .= " " . join(" ", @{$classes});
175              $subsystems{$subsystem} = $name;              $subsystems{$subsystem} = $name;
176          }          }
177      }      }
178        # Get the list of NMPDR-oriented attribute keys.
179        my @propKeys = $fig->get_group_keys("NMPDR");
180      # Get the data directory from the Sprout object.      # Get the data directory from the Sprout object.
181      my ($directory) = $sprout->LoadInfo();      my ($directory) = $sprout->LoadInfo();
182      # Create the Sprout load object.      # Create the Sprout load object.
# Line 183  Line 188 
188                    loadDirectory => $directory,                    loadDirectory => $directory,
189                    erdb => $sprout,                    erdb => $sprout,
190                    loaders => [],                    loaders => [],
191                    options => $options                    options => $options,
192                      propKeys => \@propKeys,
193                   };                   };
194      # Bless and return it.      # Bless and return it.
195      bless $retVal, $class;      bless $retVal, $class;
# Line 203  Line 209 
209      return $self->{options}->{loadOnly};      return $self->{options}->{loadOnly};
210  }  }
211    
 =head3 PrimaryOnly  
   
 C<< my $flag = $spl->PrimaryOnly; >>  
   
 Return TRUE if only the main entity is to be loaded, else FALSE.  
   
 =cut  
   
 sub PrimaryOnly {  
     my ($self) = @_;  
     return $self->{options}->{primaryOnly};  
 }  
212    
213  =head3 LoadGenomeData  =head3 LoadGenomeData
214    
# Line 255  Line 249 
249      my $genomeCount = (keys %{$genomeHash});      my $genomeCount = (keys %{$genomeHash});
250      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
251      my $loadGenome = $self->_TableLoader('Genome');      my $loadGenome = $self->_TableLoader('Genome');
252      my $loadHasContig = $self->_TableLoader('HasContig', $self->PrimaryOnly);      my $loadHasContig = $self->_TableLoader('HasContig');
253      my $loadContig = $self->_TableLoader('Contig', $self->PrimaryOnly);      my $loadContig = $self->_TableLoader('Contig');
254      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf', $self->PrimaryOnly);      my $loadIsMadeUpOf = $self->_TableLoader('IsMadeUpOf');
255      my $loadSequence = $self->_TableLoader('Sequence', $self->PrimaryOnly);      my $loadSequence = $self->_TableLoader('Sequence');
256      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
257          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
258      } else {      } else {
# Line 332  Line 326 
326      return $retVal;      return $retVal;
327  }  }
328    
 =head3 LoadCouplingData  
   
 C<< my $stats = $spl->LoadCouplingData(); >>  
   
 Load the coupling and evidence data from FIG into Sprout.  
   
 The coupling data specifies which genome features are functionally coupled. The  
 evidence data explains why the coupling is functional.  
   
 The following relations are loaded by this method.  
   
     Coupling  
     IsEvidencedBy  
     PCH  
     ParticipatesInCoupling  
     UsesAsEvidence  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadCouplingData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the genome hash.  
     my $genomeFilter = $self->{genomes};  
     # Set up an ID counter for the PCHs.  
     my $pchID = 0;  
     # Start the loads.  
     my $loadCoupling = $self->_TableLoader('Coupling');  
     my $loadIsEvidencedBy = $self->_TableLoader('IsEvidencedBy', $self->PrimaryOnly);  
     my $loadPCH = $self->_TableLoader('PCH', $self->PrimaryOnly);  
     my $loadParticipatesInCoupling = $self->_TableLoader('ParticipatesInCoupling', $self->PrimaryOnly);  
     my $loadUsesAsEvidence = $self->_TableLoader('UsesAsEvidence', $self->PrimaryOnly);  
     if ($self->{options}->{loadOnly}) {  
         Trace("Loading from existing files.") if T(2);  
     } else {  
         Trace("Generating coupling data.") if T(2);  
         # Loop through the genomes found.  
         for my $genome (sort keys %{$genomeFilter}) {  
             Trace("Generating coupling data for $genome.") if T(3);  
             $loadCoupling->Add("genomeIn");  
             # Create a hash table for holding coupled pairs. We use this to prevent  
             # duplicates. For example, if A is coupled to B, we don't want to also  
             # assert that B is coupled to A, because we already know it. Fortunately,  
             # all couplings occur within a genome, so we can keep the hash table  
             # size reasonably small.  
             my %dupHash = ();  
             # Get all of the genome's PEGs.  
             my @pegs = $fig->pegs_of($genome);  
             # Loop through the PEGs.  
             for my $peg1 (@pegs) {  
                 $loadCoupling->Add("pegIn");  
                 Trace("Processing PEG $peg1 for $genome.") if T(4);  
                 # Get a list of the coupled PEGs.  
                 my @couplings = $fig->coupled_to($peg1);  
                 # For each coupled PEG, we need to verify that a coupling already  
                 # exists. If not, we have to create one.  
                 for my $coupleData (@couplings) {  
                     my ($peg2, $score) = @{$coupleData};  
                     # Compute the coupling ID.  
                     my $coupleID = $self->{erdb}->CouplingID($peg1, $peg2);  
                     if (! exists $dupHash{$coupleID}) {  
                         $loadCoupling->Add("couplingIn");  
                         # Here we have a new coupling to store in the load files.  
                         Trace("Storing coupling ($coupleID) with score $score.") if T(4);  
                         # Ensure we don't do this again.  
                         $dupHash{$coupleID} = $score;  
                         # Write the coupling record.  
                         $loadCoupling->Put($coupleID, $score);  
                         # Connect it to the coupled PEGs.  
                         $loadParticipatesInCoupling->Put($peg1, $coupleID, 1);  
                         $loadParticipatesInCoupling->Put($peg2, $coupleID, 2);  
                         # Get the evidence for this coupling.  
                         my @evidence = $fig->coupling_evidence($peg1, $peg2);  
                         # Organize the evidence into a hash table.  
                         my %evidenceMap = ();  
                         # Process each evidence item.  
                         for my $evidenceData (@evidence) {  
                             $loadPCH->Add("evidenceIn");  
                             my ($peg3, $peg4, $usage) = @{$evidenceData};  
                             # Only proceed if the evidence is from a Sprout  
                             # genome.  
                             if ($genomeFilter->{$fig->genome_of($peg3)}) {  
                                 $loadUsesAsEvidence->Add("evidenceChosen");  
                                 my $evidenceKey = "$coupleID $peg3 $peg4";  
                                 # We store this evidence in the hash if the usage  
                                 # is nonzero or no prior evidence has been found. This  
                                 # insures that if there is duplicate evidence, we  
                                 # at least keep the meaningful ones. Only evidence in  
                                 # the hash makes it to the output.  
                                 if ($usage || ! exists $evidenceMap{$evidenceKey}) {  
                                     $evidenceMap{$evidenceKey} = $evidenceData;  
                                 }  
                             }  
                         }  
                         for my $evidenceID (keys %evidenceMap) {  
                             # Get the ID for this evidence.  
                             $pchID++;  
                             # Create the evidence record.  
                             my ($peg3, $peg4, $usage) = @{$evidenceMap{$evidenceID}};  
                             $loadPCH->Put($pchID, $usage);  
                             # Connect it to the coupling.  
                             $loadIsEvidencedBy->Put($coupleID, $pchID);  
                             # Connect it to the features.  
                             $loadUsesAsEvidence->Put($pchID, $peg3, 1);  
                             $loadUsesAsEvidence->Put($pchID, $peg4, 2);  
                         }  
                     }  
                 }  
             }  
         }  
     }  
     # All done. Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
329  =head3 LoadFeatureData  =head3 LoadFeatureData
330    
331  C<< my $stats = $spl->LoadFeatureData(); >>  C<< my $stats = $spl->LoadFeatureData(); >>
# Line 470  Line 338 
338    
339      Feature      Feature
340      FeatureAlias      FeatureAlias
341        IsAliasOf
342      FeatureLink      FeatureLink
343      FeatureTranslation      FeatureTranslation
344      FeatureUpstream      FeatureUpstream
# Line 479  Line 348 
348      FeatureEssential      FeatureEssential
349      FeatureVirulent      FeatureVirulent
350      FeatureIEDB      FeatureIEDB
351        CDD
352        IsPresentOnProteinOf
353    
354  =over 4  =over 4
355    
# Line 500  Line 371 
371      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
372      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
373      my $loadFeature = $self->_TableLoader('Feature');      my $loadFeature = $self->_TableLoader('Feature');
374      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn', $self->PrimaryOnly);      my $loadIsLocatedIn = $self->_TableLoader('IsLocatedIn');
375      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');      my $loadFeatureAlias = $self->_TableLoader('FeatureAlias');
376        my $loadIsAliasOf = $self->_TableLoader('IsAliasOf');
377      my $loadFeatureLink = $self->_TableLoader('FeatureLink');      my $loadFeatureLink = $self->_TableLoader('FeatureLink');
378      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');      my $loadFeatureTranslation = $self->_TableLoader('FeatureTranslation');
379      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');      my $loadFeatureUpstream = $self->_TableLoader('FeatureUpstream');
380      my $loadHasFeature = $self->_TableLoader('HasFeature', $self->PrimaryOnly);      my $loadHasFeature = $self->_TableLoader('HasFeature');
381      my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem', $self->PrimaryOnly);      my $loadHasRoleInSubsystem = $self->_TableLoader('HasRoleInSubsystem');
382      my $loadFeatureEssential = $self->_TableLoader('FeatureEssential');      my $loadFeatureEssential = $self->_TableLoader('FeatureEssential');
383      my $loadFeatureVirulent = $self->_TableLoader('FeatureVirulent');      my $loadFeatureVirulent = $self->_TableLoader('FeatureVirulent');
384      my $loadFeatureIEDB = $self->_TableLoader('FeatureIEDB');      my $loadFeatureIEDB = $self->_TableLoader('FeatureIEDB');
385        my $loadCDD = $self->_TableLoader('CDD');
386        my $loadIsPresentOnProteinOf = $self->_TableLoader('IsPresentOnProteinOf');
387      # Get the subsystem hash.      # Get the subsystem hash.
388      my $subHash = $self->{subsystems};      my $subHash = $self->{subsystems};
389        # Get the property keys.
390        my $propKeys = $self->{propKeys};
391        # Create a hashes to hold CDD and alias values.
392        my %CDD = ();
393        my %alias = ();
394      # 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
395      # locations.      # locations.
396      my $chunkSize = $self->{sprout}->MaxSegment();      my $chunkSize = $self->{sprout}->MaxSegment();
# Line 520  Line 399 
399      } else {      } else {
400          Trace("Generating feature data.") if T(2);          Trace("Generating feature data.") if T(2);
401          # Now we loop through the genomes, generating the data for each one.          # Now we loop through the genomes, generating the data for each one.
402          for my $genomeID (sort keys %{$genomeHash}) {          my @allGenomes = sort keys %{$genomeHash};
403            Trace(scalar(@allGenomes) . " genomes found in list.") if T(3);
404            for my $genomeID (@allGenomes) {
405              Trace("Loading features for genome $genomeID.") if T(3);              Trace("Loading features for genome $genomeID.") if T(3);
406              $loadFeature->Add("genomeIn");              $loadFeature->Add("genomeIn");
407              # Get the feature list for this genome.              # Get the feature list for this genome.
# Line 531  Line 412 
412              my @fids = map { $_->[0] } @featureTuples;              my @fids = map { $_->[0] } @featureTuples;
413              Trace("$count features found for genome $genomeID.") if T(3);              Trace("$count features found for genome $genomeID.") if T(3);
414              # Get the attributes for this genome and put them in a hash by feature ID.              # Get the attributes for this genome and put them in a hash by feature ID.
415              my $attributes = GetGenomeAttributes($fig, $genomeID, \@fids);              my $attributes = GetGenomeAttributes($fig, $genomeID, \@fids, $propKeys);
416                Trace("Looping through features for $genomeID.") if T(3);
417              # Set up for our duplicate-feature check.              # Set up for our duplicate-feature check.
418              my $oldFeatureID = "";              my $oldFeatureID = "";
419              # Loop through the features.              # Loop through the features.
# Line 556  Line 438 
438                                      $fig->taxonomy_of($genomeID));                                      $fig->taxonomy_of($genomeID));
439                      # Create the aliases.                      # Create the aliases.
440                      for my $alias ($fig->feature_aliases($featureID)) {                      for my $alias ($fig->feature_aliases($featureID)) {
441                          $loadFeatureAlias->Put($featureID, $alias);                          #Connect this alias to this feature.
442                            $loadIsAliasOf->Put($alias, $featureID);
443                          push @keywords, $alias;                          push @keywords, $alias;
444                            # If this is a locus tag, also add its natural form as a keyword.
445                            my $naturalName = AliasAnalysis::Type(LocusTag => $alias);
446                            if ($naturalName) {
447                                push @keywords, $naturalName;
448                            }
449                            # If this is the first time for the specified alias, create its
450                            # alias record.
451                            if (! exists $alias{$alias}) {
452                                $loadFeatureAlias->Put($alias);
453                                $alias{$alias} = 1;
454                            }
455                      }                      }
456                      Trace("Assignment for $featureID is: $assignment") if T(4);                      Trace("Assignment for $featureID is: $assignment") if T(4);
457                      # Break the assignment into words and shove it onto the                      # Break the assignment into words and shove it onto the
# Line 585  Line 479 
479                      }                      }
480                      # Now we need to find the subsystems this feature participates in.                      # Now we need to find the subsystems this feature participates in.
481                      # We also add the subsystems to the keyword list. Before we do that,                      # We also add the subsystems to the keyword list. Before we do that,
482                      # we must convert underscores to spaces and tack on the classifications.                      # we must convert underscores to spaces.
483                      my @subsystems = $fig->peg_to_subsystems($featureID);                      my @subsystems = $fig->peg_to_subsystems($featureID);
484                      for my $subsystem (@subsystems) {                      for my $subsystem (@subsystems) {
485                          # Only proceed if we like this subsystem.                          # Only proceed if we like this subsystem.
# Line 634  Line 528 
528                          push @keywords, 'iedb';                          push @keywords, 'iedb';
529                          $loadFeature->Add('iedb');                          $loadFeature->Add('iedb');
530                      }                      }
531                        # Now we have some other attributes we need to process. Currently,
532                        # this is CDD and CELLO, but we expect the number to increase.
533                        my %attributeHash = ();
534                        for my $attrRow (@{$attributes->{$featureID}}) {
535                            my (undef, $key, @values) = @{$attrRow};
536                            $key =~ /^([^:]+)::(.+)/;
537                            if (exists $attributeHash{$1}) {
538                                $attributeHash{$1}->{$2} = \@values;
539                            } else {
540                                $attributeHash{$1} = {$2 => \@values};
541                            }
542                        }
543                        my $celloValue = "unknown";
544                        # Pull in the CELLO attribute. There will never be more than one.
545                        # If we have one, it's a feature attribute AND a keyword.
546                        my @celloData = keys %{$attributeHash{CELLO}};
547                        if (@celloData) {
548                            $celloValue = $celloData[0];
549                            push @keywords, $celloValue;
550                        }
551                        # Now we handle CDD. This is a bit more complicated, because
552                        # there are multiple CDDs per protein.
553                        if (exists $attributeHash{CDD}) {
554                            # Get the hash of CDD IDs to scores for this feature. We
555                            # already know it exists because of the above IF.
556                            my $cddHash = $attributeHash{CDD};
557                            my @cddData = sort keys %{$cddHash};
558                            for my $cdd (@cddData) {
559                                # Extract the score for this CDD and decode it.
560                                my ($codeScore) = split(/\s*,\s*/, $cddHash->{$cdd}->[1]);
561                                my $realScore = FIGRules::DecodeScore($codeScore);
562                                # We can't afford to crash because of a bad attribute
563                                # value, hence the IF below.
564                                if (! defined($realScore)) {
565                                    # Bad score, so count it.
566                                    $loadFeature->Add('badCDDscore');
567                                } else {
568                                    # Create the connection.
569                                    $loadIsPresentOnProteinOf->Put($cdd, $featureID, $realScore);
570                                    # If this CDD does not yet exist, create its record.
571                                    if (! exists $CDD{$cdd}) {
572                                        $CDD{$cdd} = 1;
573                                        $loadCDD->Put($cdd);
574                                    }
575                                }
576                            }
577                        }
578                      # Now we need to bust up hyphenated words in the keyword                      # Now we need to bust up hyphenated words in the keyword
579                      # list. We keep them separate and put them at the end so                      # list. We keep them separate and put them at the end so
580                      # the original word order is available.                      # the original word order is available.
# Line 654  Line 595 
595                      # Clean the keyword list.                      # Clean the keyword list.
596                      my $cleanWords = $sprout->CleanKeywords($keywordString);                      my $cleanWords = $sprout->CleanKeywords($keywordString);
597                      Trace("Keyword string for $featureID: $cleanWords") if T(4);                      Trace("Keyword string for $featureID: $cleanWords") if T(4);
598                      # Create the feature record.                      # Now we need to process the feature's locations. First, we split them up.
599                      $loadFeature->Put($featureID, 1, $user, $quality, $type, $assignment, $cleanWords);                      my @locationList = split /\s*,\s*/, $locations;
600                        # Next, we convert them to Sprout location objects.
601                        my @locObjectList = map { BasicLocation->new("$genomeID:$_") } @locationList;
602                      # 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
603                      # 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
604                      # the maximum segment size. This simplifies the genes_in_region processing                      # the maximum segment size. This simplifies the genes_in_region processing
605                      # for Sprout.                      # for Sprout. To start, we create the location position indicator.
                     my @locationList = split /\s*,\s*/, $locations;  
                     # Create the location position indicator.  
606                      my $i = 1;                      my $i = 1;
607                      # Loop through the locations.                      # Loop through the locations.
608                      for my $location (@locationList) {                      for my $locObject (@locObjectList) {
609                          # Parse the location.                          # Split this location into a list of chunks.
                         my $locObject = BasicLocation->new("$genomeID:$location");  
                         # Split it into a list of chunks.  
610                          my @locOList = ();                          my @locOList = ();
611                          while (my $peeling = $locObject->Peel($chunkSize)) {                          while (my $peeling = $locObject->Peel($chunkSize)) {
612                              $loadIsLocatedIn->Add("peeling");                              $loadIsLocatedIn->Add("peeling");
# Line 682  Line 621 
621                              $i++;                              $i++;
622                          }                          }
623                      }                      }
624                        # Finally, reassemble the location objects into a list of Sprout location strings.
625                        $locations = join(", ", map { $_->String } @locObjectList);
626                        # Create the feature record.
627                        $loadFeature->Put($featureID, 1, $user, $quality, $celloValue, $type, $assignment, $cleanWords, $locations);
628                  }                  }
629              }              }
630                Trace("Genome $genomeID processed.") if T(3);
631          }          }
632      }      }
633      # Finish the loads.      # Finish the loads.
# Line 709  Line 653 
653      SubsystemClass      SubsystemClass
654      Role      Role
655      RoleEC      RoleEC
656        IsIdentifiedByEC
657      SSCell      SSCell
658      ContainsFeature      ContainsFeature
659      IsGenomeOf      IsGenomeOf
# Line 750  Line 695 
695      # Get the map list.      # Get the map list.
696      my @maps = $fig->all_maps;      my @maps = $fig->all_maps;
697      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
698      my $loadDiagram = $self->_TableLoader('Diagram', $self->PrimaryOnly);      my $loadDiagram = $self->_TableLoader('Diagram');
699      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn', $self->PrimaryOnly);      my $loadRoleOccursIn = $self->_TableLoader('RoleOccursIn');
700      my $loadSubsystem = $self->_TableLoader('Subsystem');      my $loadSubsystem = $self->_TableLoader('Subsystem');
701      my $loadRole = $self->_TableLoader('Role', $self->PrimaryOnly);      my $loadRole = $self->_TableLoader('Role');
702      my $loadRoleEC = $self->_TableLoader('RoleEC', $self->PrimaryOnly);      my $loadRoleEC = $self->_TableLoader('RoleEC');
703      my $loadCatalyzes = $self->_TableLoader('Catalyzes', $self->PrimaryOnly);      my $loadIsIdentifiedByEC = $self->_TableLoader('IsIdentifiedByEC');
704      my $loadSSCell = $self->_TableLoader('SSCell', $self->PrimaryOnly);      my $loadCatalyzes = $self->_TableLoader('Catalyzes');
705      my $loadContainsFeature = $self->_TableLoader('ContainsFeature', $self->PrimaryOnly);      my $loadSSCell = $self->_TableLoader('SSCell');
706      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf', $self->PrimaryOnly);      my $loadContainsFeature = $self->_TableLoader('ContainsFeature');
707      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf', $self->PrimaryOnly);      my $loadIsGenomeOf = $self->_TableLoader('IsGenomeOf');
708      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem', $self->PrimaryOnly);      my $loadIsRoleOf = $self->_TableLoader('IsRoleOf');
709      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn', $self->PrimaryOnly);      my $loadOccursInSubsystem = $self->_TableLoader('OccursInSubsystem');
710      my $loadHasSSCell = $self->_TableLoader('HasSSCell', $self->PrimaryOnly);      my $loadParticipatesIn = $self->_TableLoader('ParticipatesIn');
711      my $loadRoleSubset = $self->_TableLoader('RoleSubset', $self->PrimaryOnly);      my $loadHasSSCell = $self->_TableLoader('HasSSCell');
712      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset', $self->PrimaryOnly);      my $loadRoleSubset = $self->_TableLoader('RoleSubset');
713      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles', $self->PrimaryOnly);      my $loadGenomeSubset = $self->_TableLoader('GenomeSubset');
714      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes', $self->PrimaryOnly);      my $loadConsistsOfRoles = $self->_TableLoader('ConsistsOfRoles');
715      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset', $self->PrimaryOnly);      my $loadConsistsOfGenomes = $self->_TableLoader('ConsistsOfGenomes');
716      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset', $self->PrimaryOnly);      my $loadHasRoleSubset = $self->_TableLoader('HasRoleSubset');
717      my $loadSubsystemClass = $self->_TableLoader('SubsystemClass', $self->PrimaryOnly);      my $loadHasGenomeSubset = $self->_TableLoader('HasGenomeSubset');
718        my $loadSubsystemClass = $self->_TableLoader('SubsystemClass');
719      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
720          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
721      } else {      } else {
722          Trace("Generating subsystem data.") if T(2);          Trace("Generating subsystem data.") if T(2);
723          # This hash will contain the role for each EC. When we're done, this          # This hash will contain the roles for each EC. When we're done, this
724          # information will be used to generate the Catalyzes table.          # information will be used to generate the Catalyzes table.
725          my %ecToRoles = ();          my %ecToRoles = ();
726          # Loop through the subsystems. Our first task will be to create the          # Loop through the subsystems. Our first task will be to create the
# Line 802  Line 748 
748                  $loadSubsystemClass->Put($subsysID, $classString);                  $loadSubsystemClass->Put($subsysID, $classString);
749                  # 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.
750                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {                  for (my $col = 0; defined($roleID = $sub->get_role($col)); $col++) {
751                        # Get the role's abbreviation.
752                        my $abbr = $sub->get_role_abbr($col);
753                      # Connect to this role.                      # Connect to this role.
754                      $loadOccursInSubsystem->Add("roleIn");                      $loadOccursInSubsystem->Add("roleIn");
755                      $loadOccursInSubsystem->Put($roleID, $subsysID, $col);                      $loadOccursInSubsystem->Put($roleID, $subsysID, $abbr, $col);
756                      # If it's a new role, add it to the role table.                      # If it's a new role, add it to the role table.
757                      if (! exists $roleData{$roleID}) {                      if (! exists $roleData{$roleID}) {
758                          # Get the role's abbreviation.                          # Get the role's abbreviation.
                         my $abbr = $sub->get_role_abbr($col);  
759                          # Add the role.                          # Add the role.
760                          $loadRole->Put($roleID, $abbr);                          $loadRole->Put($roleID);
761                          $roleData{$roleID} = 1;                          $roleData{$roleID} = 1;
762                          # Check for an EC number.                          # Check for an EC number.
763                          if ($roleID =~ /\(EC ([^.]+\.[^.]+\.[^.]+\.[^)]+)\)\s*$/) {                          if ($roleID =~ /\(EC (\d+\.\d+\.\d+\.\d+)\s*\)\s*$/) {
764                              my $ec = $1;                              my $ec = $1;
765                              $loadRoleEC->Put($roleID, $ec);                              $loadIsIdentifiedByEC->Put($roleID, $ec);
766                              $ecToRoles{$ec} = $roleID;                              # Check to see if this is our first encounter with this EC.
767                                if (exists $ecToRoles{$ec}) {
768                                    # No, so just add this role to the EC list.
769                                    push @{$ecToRoles{$ec}}, $roleID;
770                                } else {
771                                    # Output this EC.
772                                    $loadRoleEC->Put($ec);
773                                    # Create its role list.
774                                    $ecToRoles{$ec} = [$roleID];
775                                }
776                          }                          }
777                      }                      }
778                  }                  }
# Line 929  Line 885 
885              # Now we need to link all the map's roles to it.              # Now we need to link all the map's roles to it.
886              # A hash is used to prevent duplicates.              # A hash is used to prevent duplicates.
887              my %roleHash = ();              my %roleHash = ();
888              for my $role ($fig->map_to_ecs($map)) {              for my $ec ($fig->map_to_ecs($map)) {
889                  if (exists $ecToRoles{$role} && ! $roleHash{$role}) {                  if (exists $ecToRoles{$ec}) {
890                      $loadRoleOccursIn->Put($ecToRoles{$role}, $map);                      for my $role (@{$ecToRoles{$ec}}) {
891                            if (! $roleHash{$role}) {
892                                $loadRoleOccursIn->Put($role, $map);
893                      $roleHash{$role} = 1;                      $roleHash{$role} = 1;
894                  }                  }
895              }              }
896          }          }
897                }
898            }
899          # Before we leave, we must create the Catalyzes table. We start with the reactions,          # Before we leave, we must create the Catalyzes table. We start with the reactions,
900          # then use the "ecToRoles" table to convert EC numbers to role IDs.          # then use the "ecToRoles" table to convert EC numbers to role IDs.
901          my @reactions = $fig->all_reactions();          my @reactions = $fig->all_reactions();
902          for my $reactionID (@reactions) {          for my $reactionID (@reactions) {
903              # Get this reaction's list of roles. The results will be EC numbers.              # Get this reaction's list of roles. The results will be EC numbers.
904              my @roles = $fig->catalyzed_by($reactionID);              my @ecs = $fig->catalyzed_by($reactionID);
905              # Loop through the roles, creating catalyzation records.              # Loop through the roles, creating catalyzation records.
906              for my $thisRole (@roles) {              for my $thisEC (@ecs) {
907                  if (exists $ecToRoles{$thisRole}) {                  if (exists $ecToRoles{$thisEC}) {
908                      $loadCatalyzes->Put($ecToRoles{$thisRole}, $reactionID);                      for my $thisRole (@{$ecToRoles{$thisEC}}) {
909                            $loadCatalyzes->Put($thisRole, $reactionID);
910                        }
911                  }                  }
912              }              }
913          }          }
# Line 993  Line 955 
955      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
956      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
957      my $loadProperty = $self->_TableLoader('Property');      my $loadProperty = $self->_TableLoader('Property');
958      my $loadHasProperty = $self->_TableLoader('HasProperty', $self->PrimaryOnly);      my $loadHasProperty = $self->_TableLoader('HasProperty');
959      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
960          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
961      } else {      } else {
# Line 1002  Line 964 
964          my %propertyKeys = ();          my %propertyKeys = ();
965          my $nextID = 1;          my $nextID = 1;
966          # Get the attributes we intend to store in the property table.          # Get the attributes we intend to store in the property table.
967          my @propKeys = $fig->get_group_keys("NMPDR");          my $propKeys = $self->{propKeys};
968          # Loop through the genomes.          # Loop through the genomes.
969          for my $genomeID (sort keys %{$genomeHash}) {          for my $genomeID (sort keys %{$genomeHash}) {
970              $loadProperty->Add("genomeIn");              $loadProperty->Add("genomeIn");
# Line 1010  Line 972 
972              # Initialize a counter.              # Initialize a counter.
973              my $propertyCount = 0;              my $propertyCount = 0;
974              # Get the properties for this genome's features.              # Get the properties for this genome's features.
975              my @attributes = $fig->get_attributes("fig|$genomeID%", \@propKeys);              my @attributes = $fig->get_attributes("fig|$genomeID%", $propKeys);
976              Trace("Property list built for $genomeID.") if T(3);              Trace("Property list built for $genomeID.") if T(3);
977              # Loop through the results, creating HasProperty records.              # Loop through the results, creating HasProperty records.
978              for my $attributeData (@attributes) {              for my $attributeData (@attributes) {
# Line 1079  Line 1041 
1041      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1042      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1043      my $loadAnnotation = $self->_TableLoader('Annotation');      my $loadAnnotation = $self->_TableLoader('Annotation');
1044      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation', $self->PrimaryOnly);      my $loadIsTargetOfAnnotation = $self->_TableLoader('IsTargetOfAnnotation');
1045      my $loadSproutUser = $self->_TableLoader('SproutUser', $self->PrimaryOnly);      my $loadSproutUser = $self->_TableLoader('SproutUser');
1046      my $loadUserAccess = $self->_TableLoader('UserAccess', $self->PrimaryOnly);      my $loadUserAccess = $self->_TableLoader('UserAccess');
1047      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation', $self->PrimaryOnly);      my $loadMadeAnnotation = $self->_TableLoader('MadeAnnotation');
1048      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1049          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1050      } else {      } else {
# Line 1186  Line 1148 
1148      # Get the genome hash.      # Get the genome hash.
1149      my $genomeHash = $self->{genomes};      my $genomeHash = $self->{genomes};
1150      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1151      my $loadComesFrom = $self->_TableLoader('ComesFrom', $self->PrimaryOnly);      my $loadComesFrom = $self->_TableLoader('ComesFrom');
1152      my $loadSource = $self->_TableLoader('Source');      my $loadSource = $self->_TableLoader('Source');
1153      my $loadSourceURL = $self->_TableLoader('SourceURL');      my $loadSourceURL = $self->_TableLoader('SourceURL');
1154      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
# Line 1323  Line 1285 
1285      Compound      Compound
1286      CompoundName      CompoundName
1287      CompoundCAS      CompoundCAS
1288        IsIdentifiedByCAS
1289        HasCompoundName
1290      IsAComponentOf      IsAComponentOf
1291    
1292  This method proceeds reaction by reaction rather than genome by genome.  This method proceeds reaction by reaction rather than genome by genome.
# Line 1344  Line 1308 
1308      my $fig = $self->{fig};      my $fig = $self->{fig};
1309      # Create load objects for each of the tables we're loading.      # Create load objects for each of the tables we're loading.
1310      my $loadReaction = $self->_TableLoader('Reaction');      my $loadReaction = $self->_TableLoader('Reaction');
1311      my $loadReactionURL = $self->_TableLoader('ReactionURL', $self->PrimaryOnly);      my $loadReactionURL = $self->_TableLoader('ReactionURL');
1312      my $loadCompound = $self->_TableLoader('Compound', $self->PrimaryOnly);      my $loadCompound = $self->_TableLoader('Compound');
1313      my $loadCompoundName = $self->_TableLoader('CompoundName', $self->PrimaryOnly);      my $loadCompoundName = $self->_TableLoader('CompoundName');
1314      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS', $self->PrimaryOnly);      my $loadCompoundCAS = $self->_TableLoader('CompoundCAS');
1315      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf', $self->PrimaryOnly);      my $loadIsAComponentOf = $self->_TableLoader('IsAComponentOf');
1316        my $loadIsIdentifiedByCAS = $self->_TableLoader('IsIdentifiedByCAS');
1317        my $loadHasCompoundName = $self->_TableLoader('HasCompoundName');
1318      if ($self->{options}->{loadOnly}) {      if ($self->{options}->{loadOnly}) {
1319          Trace("Loading from existing files.") if T(2);          Trace("Loading from existing files.") if T(2);
1320      } else {      } else {
1321          Trace("Generating annotation data.") if T(2);          Trace("Generating reaction data.") if T(2);
1322            # We need some hashes to prevent duplicates.
1323            my %compoundNames = ();
1324            my %compoundCASes = ();
1325          # First we create the compounds.          # First we create the compounds.
1326          my @compounds = $fig->all_compounds();          my @compounds = $fig->all_compounds();
1327          for my $cid (@compounds) {          for my $cid (@compounds) {
# Line 1361  Line 1330 
1330              # Each name will be given a priority number, starting with 1.              # Each name will be given a priority number, starting with 1.
1331              my $prio = 1;              my $prio = 1;
1332              for my $name (@names) {              for my $name (@names) {
1333                  $loadCompoundName->Put($cid, $name, $prio++);                  if (! exists $compoundNames{$name}) {
1334                        $loadCompoundName->Put($name);
1335                        $compoundNames{$name} = 1;
1336                    }
1337                    $loadHasCompoundName->Put($cid, $name, $prio++);
1338              }              }
1339              # Create the main compound record. Note that the first name              # Create the main compound record. Note that the first name
1340              # becomes the label.              # becomes the label.
# Line 1370  Line 1343 
1343              # Check for a CAS ID.              # Check for a CAS ID.
1344              my $cas = $fig->cas($cid);              my $cas = $fig->cas($cid);
1345              if ($cas) {              if ($cas) {
1346                  $loadCompoundCAS->Put($cid, $cas);                  $loadIsIdentifiedByCAS->Put($cid, $cas);
1347                    if (! exists $compoundCASes{$cas}) {
1348                        $loadCompoundCAS->Put($cas);
1349                        $compoundCASes{$cas} = 1;
1350                    }
1351              }              }
1352          }          }
1353          # All the compounds are set up, so we need to loop through the reactions next. First,          # All the compounds are set up, so we need to loop through the reactions next. First,
# Line 1407  Line 1384 
1384      return $retVal;      return $retVal;
1385  }  }
1386    
 =head3 LoadGroupData  
   
 C<< my $stats = $spl->LoadGroupData(); >>  
   
 Load the genome Groups into Sprout.  
   
 The following relations are loaded by this method.  
   
     GenomeGroups  
   
 Currently, we do not use groups. We used to use them for NMPDR groups,  
 butThere is no direct support for genome groups in FIG, so we access the SEED  
 files directly.  
   
 =over 4  
   
 =item RETURNS  
   
 Returns a statistics object for the loads.  
   
 =back  
   
 =cut  
 #: Return Type $%;  
 sub LoadGroupData {  
     # Get this object instance.  
     my ($self) = @_;  
     # Get the FIG object.  
     my $fig = $self->{fig};  
     # Get the genome hash.  
     my $genomeHash = $self->{genomes};  
     # Create a load object for the table we're loading.  
     my $loadGenomeGroups = $self->_TableLoader('GenomeGroups');  
     if ($self->{options}->{loadOnly}) {  
         Trace("Loading from existing files.") if T(2);  
     } else {  
         Trace("Generating group data.") if T(2);  
         # Currently there are no groups.  
     }  
     # Finish the load.  
     my $retVal = $self->_FinishAll();  
     return $retVal;  
 }  
   
1387  =head3 LoadSynonymData  =head3 LoadSynonymData
1388    
1389  C<< my $stats = $spl->LoadSynonymData(); >>  C<< my $stats = $spl->LoadSynonymData(); >>
# Line 1492  Line 1425 
1425          Trace("Generating synonym group data.") if T(2);          Trace("Generating synonym group data.") if T(2);
1426          # Get the database handle.          # Get the database handle.
1427          my $dbh = $fig->db_handle();          my $dbh = $fig->db_handle();
1428          # Ask for the synonyms.          # Ask for the synonyms. Note that "maps_to" is a group name, and "syn_id" is a PEG ID or alias.
1429          my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");          my $sth = $dbh->prepare_command("SELECT maps_to, syn_id FROM peg_synonyms ORDER BY maps_to");
1430          my $result = $sth->execute();          my $result = $sth->execute();
1431          if (! defined($result)) {          if (! defined($result)) {
# Line 1504  Line 1437 
1437              my $featureCount = 0;              my $featureCount = 0;
1438              # Loop through the synonym/peg pairs.              # Loop through the synonym/peg pairs.
1439              while (my @row = $sth->fetchrow()) {              while (my @row = $sth->fetchrow()) {
1440                  # Get the synonym ID and feature ID.                  # Get the synonym group ID and feature ID.
1441                  my ($syn_id, $peg) = @row;                  my ($syn_id, $peg) = @row;
1442                  # Insure it's for one of our genomes.                  # Insure it's for one of our genomes.
1443                  my $genomeID = FIG::genome_of($peg);                  my $genomeID = FIG::genome_of($peg);
# Line 1890  Line 1823 
1823    
1824  Name of the table (relation) being loaded.  Name of the table (relation) being loaded.
1825    
 =item ignore  
   
 TRUE if the table should be ignored entirely, else FALSE.  
   
1826  =item RETURN  =item RETURN
1827    
1828  Returns an ERDBLoad object for loading the specified table.  Returns an ERDBLoad object for loading the specified table.
# Line 1904  Line 1833 
1833    
1834  sub _TableLoader {  sub _TableLoader {
1835      # Get the parameters.      # Get the parameters.
1836      my ($self, $tableName, $ignore) = @_;      my ($self, $tableName) = @_;
1837      # Create the load object.      # Create the load object.
1838      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly,      my $retVal = ERDBLoad->new($self->{erdb}, $tableName, $self->{loadDirectory}, $self->LoadOnly);
                                $ignore);  
1839      # Cache it in the loader list.      # Cache it in the loader list.
1840      push @{$self->{loaders}}, $retVal;      push @{$self->{loaders}}, $retVal;
1841      # Return it to the caller.      # Return it to the caller.
# Line 1981  Line 1909 
1909    
1910  =head3 GetGenomeAttributes  =head3 GetGenomeAttributes
1911    
1912  C<< my $aHashRef = GetGenomeAttributes($fig, $genomeID, \@fids); >>  C<< my $aHashRef = GetGenomeAttributes($fig, $genomeID, \@fids, \@propKeys); >>
1913    
1914  Return a hash of attributes keyed on feature ID. This method gets all the NMPDR-related  Return a hash of attributes keyed on feature ID. This method gets all the NMPDR-related
1915  attributes for all the features of a genome in a single call, then organizes them into  attributes for all the features of a genome in a single call, then organizes them into
# Line 2001  Line 1929 
1929    
1930  Reference to a list of the feature IDs whose attributes are to be kept.  Reference to a list of the feature IDs whose attributes are to be kept.
1931    
1932    =item propKeys
1933    
1934    A list of the keys to retrieve.
1935    
1936  =item RETURN  =item RETURN
1937    
1938  Returns a reference to a hash. The key of the hash is the feature ID. The value is the  Returns a reference to a hash. The key of the hash is the feature ID. The value is the
# Line 2013  Line 1945 
1945    
1946  sub GetGenomeAttributes {  sub GetGenomeAttributes {
1947      # Get the parameters.      # Get the parameters.
1948      my ($fig, $genomeID, $fids) = @_;      my ($fig, $genomeID, $fids, $propKeys) = @_;
1949      # Declare the return variable.      # Declare the return variable.
1950      my $retVal = {};      my $retVal = {};
     # Get a list of the attributes we care about.  
     my @propKeys = $fig->get_group_keys("NMPDR");  
     # Get the attributes.  
     my @aList = $fig->get_attributes("fig|$genomeID%", \@propKeys);  
1951      # Initialize the hash. This not only enables us to easily determine which FIDs to      # Initialize the hash. This not only enables us to easily determine which FIDs to
1952      # keep, it insures that the caller sees a list reference for every known fid,      # keep, it insures that the caller sees a list reference for every known fid,
1953      # simplifying the logic.      # simplifying the logic.
1954      for my $fid (@{$fids}) {      for my $fid (@{$fids}) {
1955          $retVal->{$fid} = [];          $retVal->{$fid} = [];
1956      }      }
1957      # Populate the hash.      # Get the attributes. If ev_code_cron is running, we may get a timeout error, so
1958        # an eval is used.
1959        my @aList = ();
1960        eval {
1961            @aList = $fig->get_attributes("fig|$genomeID%", $propKeys);
1962            Trace(scalar(@aList) . " attributes returned for genome $genomeID.") if T(3);
1963        };
1964        # Check for a problem.
1965        if ($@) {
1966            Trace("Retrying attributes for $genomeID due to error: $@") if T(1);
1967            # Our fallback plan is to process the attributes in blocks of 100. This is much slower,
1968            # but allows us to continue processing.
1969            my $nFids = scalar @{$fids};
1970            for (my $i = 0; $i < $nFids; $i += 100) {
1971                # Determine the index of the last feature ID we'll be specifying on this pass.
1972                # Normally it's $i + 99, but if we're close to the end it may be less.
1973                my $end = ($i + 100 > $nFids ? $nFids - 1 : $i + 99);
1974                # Get a slice of the fid list.
1975                my @slice = @{$fids}[$i .. $end];
1976                # Get the relevant attributes.
1977                Trace("Retrieving attributes for fids $i to $end.") if T(3);
1978                my @aShort = $fig->get_attributes(\@slice, $propKeys);
1979                Trace(scalar(@aShort) . " attributes returned for fids $i to $end.") if T(3);
1980                push @aList, @aShort;
1981            }
1982        }
1983        # Now we should have all the interesting attributes in @aList. Populate the hash with
1984        # them.
1985      for my $aListEntry (@aList) {      for my $aListEntry (@aList) {
1986          my $fid = $aListEntry->[0];          my $fid = $aListEntry->[0];
1987          if (exists $retVal->{$fid}) {          if (exists $retVal->{$fid}) {
# Line 2037  Line 1992 
1992      return $retVal;      return $retVal;
1993  }  }
1994    
1995    
1996  1;  1;

Legend:
Removed from v.1.84  
changed lines
  Added in v.1.89

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3