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

Diff of /Sprout/Sprout.pm

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

revision 1.8, Thu Jan 27 00:30:20 2005 UTC revision 1.30, Wed Sep 14 13:13:25 2005 UTC
# Line 70  Line 70 
70    
71  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
72    
73    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
74    
75  =back  =back
76    
77  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
# Line 86  Line 88 
88          # Compute the options. We do this by starting with a table of defaults and overwriting with          # Compute the options. We do this by starting with a table of defaults and overwriting with
89          # the incoming data.          # the incoming data.
90          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
91                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
92                                             dataDir              => 'Data',                      # data file directory                                                          # database type
93                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
94                                             userData             => 'root/',                     # user name and password                                                          # data file directory
95                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
96                                                            # database definition file name
97                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
98                                                            # user name and password
99                           port         => $FIG_Config::dbport,
100                                                            # database connection port
101                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
102                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
103                           noDBOpen     => 0,               # 1 to suppress the database open
104                                            }, $options);                                            }, $options);
105          # Get the data directory.          # Get the data directory.
106          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 100  Line 108 
108          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
109          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
110          # Connect to the database.          # Connect to the database.
111          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
112        if (! $optionTable->{noDBOpen}) {
113            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
114                                    $password, $optionTable->{port});
115        }
116          # Create the ERDB object.          # Create the ERDB object.
117          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
118          my $erdb = ERDB->new($dbh, $xmlFileName);          my $erdb = ERDB->new($dbh, $xmlFileName);
# Line 124  Line 136 
136  =cut  =cut
137  #: Return Type $;  #: Return Type $;
138  sub MaxSegment {  sub MaxSegment {
139          my $self = shift @_;      my ($self) = @_;
140          return $self->{_options}->{maxSegmentLength};          return $self->{_options}->{maxSegmentLength};
141  }  }
142    
# Line 139  Line 151 
151  =cut  =cut
152  #: Return Type $;  #: Return Type $;
153  sub MaxSequence {  sub MaxSequence {
154          my $self = shift @_;      my ($self) = @_;
155          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
156  }  }
157    
# Line 232  Line 244 
244    
245  sub Get {  sub Get {
246          # Get the parameters.          # Get the parameters.
247          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList) = @_;
         my ($objectNames, $filterClause, $parameterList) = @_;  
248          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference
249          # rather than a list of parameters. The next step is to convert the parameters from a reference          # rather than a list of parameters. The next step is to convert the parameters from a reference
250          # to a real list. We can only do this if the parameters have been specified.          # to a real list. We can only do this if the parameters have been specified.
# Line 269  Line 280 
280    
281  sub GetEntity {  sub GetEntity {
282          # Get the parameters.          # Get the parameters.
283          my $self = shift @_;      my ($self, $entityType, $ID) = @_;
284          my ($entityType, $ID) = @_;      # Call the ERDB method.
285          # Create a query.      return $self->{_erdb}->GetEntity($entityType, $ID);
         my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);  
         # Get the first (and only) object.  
         my $retVal = $query->Fetch();  
         # Return the result.  
         return $retVal;  
286  }  }
287    
288  =head3 GetEntityValues  =head3 GetEntityValues
# Line 309  Line 315 
315  #: Return Type @;  #: Return Type @;
316  sub GetEntityValues {  sub GetEntityValues {
317          # Get the parameters.          # Get the parameters.
318          my $self = shift @_;      my ($self, $entityType, $ID, $fields) = @_;
319          my ($entityType, $ID, $fields) = @_;      # Call the ERDB method.
320          # Get the specified entity.      return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);
         my $entity = $self->GetEntity($entityType, $ID);  
         # Declare the return list.  
         my @retVal = ();  
         # If we found the entity, push the values into the return list.  
         if ($entity) {  
                 push @retVal, $entity->Values($fields);  
         }  
         # Return the result.  
         return @retVal;  
321  }  }
322    
323  =head3 ShowMetaData  =head3 ShowMetaData
# Line 341  Line 338 
338    
339  sub ShowMetaData {  sub ShowMetaData {
340          # Get the parameters.          # Get the parameters.
341          my $self = shift @_;      my ($self, $fileName) = @_;
         my ($fileName) = @_;  
342          # Compute the file name.          # Compute the file name.
343          my $options = $self->{_options};          my $options = $self->{_options};
344          # Call the show method on the underlying ERDB object.          # Call the show method on the underlying ERDB object.
# Line 382  Line 378 
378  #: Return Type %;  #: Return Type %;
379  sub Load {  sub Load {
380          # Get the parameters.          # Get the parameters.
381          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
382          # Get the database object.          # Get the database object.
383          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
384          # Load the tables from the data directory.          # Load the tables from the data directory.
# Line 426  Line 421 
421  #: Return Type $%;  #: Return Type $%;
422  sub LoadUpdate {  sub LoadUpdate {
423          # Get the parameters.          # Get the parameters.
424          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
425          # Get the database object.          # Get the database object.
426          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
427          # Declare the return value.          # Declare the return value.
# Line 438  Line 432 
432          # Loop through the incoming table names.          # Loop through the incoming table names.
433          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
434                  # Find the table's file.                  # Find the table's file.
435                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
436                  if (! -e $fileName) {          if (! $fileName) {
437                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
438                  }          } else {
439                  # Attempt to load this table.                  # Attempt to load this table.
440                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
442                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
443          }          }
444        }
445          # Return the statistics.          # Return the statistics.
446          return $retVal;          return $retVal;
447  }  }
# Line 463  Line 458 
458  #: Return Type ;  #: Return Type ;
459  sub Build {  sub Build {
460          # Get the parameters.          # Get the parameters.
461          my $self = shift @_;      my ($self) = @_;
462          # Create the tables.          # Create the tables.
463          $self->{_erdb}->CreateTables;          $self->{_erdb}->CreateTables;
464  }  }
# Line 478  Line 473 
473  #: Return Type @;  #: Return Type @;
474  sub Genomes {  sub Genomes {
475          # Get the parameters.          # Get the parameters.
476          my $self = shift @_;      my ($self) = @_;
477          # Get all the genomes.          # Get all the genomes.
478          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
479          # Return the list of IDs.          # Return the list of IDs.
# Line 508  Line 503 
503  #: Return Type $;  #: Return Type $;
504  sub GenusSpecies {  sub GenusSpecies {
505          # Get the parameters.          # Get the parameters.
506          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
507          # Get the data for the specified genome.          # Get the data for the specified genome.
508          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
509                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 545  Line 539 
539  #: Return Type @;  #: Return Type @;
540  sub FeaturesOf {  sub FeaturesOf {
541          # Get the parameters.          # Get the parameters.
542          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
543          # Get the features we want.          # Get the features we want.
544          my @features;          my @features;
545          if (!$ftype) {          if (!$ftype) {
# Line 590  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 599  Line 592 
592  #: Return Type $;  #: Return Type $;
593  sub FeatureLocation {  sub FeatureLocation {
594          # Get the parameters.          # Get the parameters.
595          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
596          # Create a query for the feature locations.          # Create a query for the feature locations.
597          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",
598                                                     [$featureID]);                                                     [$featureID]);
# Line 634  Line 626 
626                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
627          }          }
628          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
629          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
630  }  }
631    
632  =head3 ParseLocation  =head3 ParseLocation
# Line 660  Line 652 
652  =cut  =cut
653  #: Return Type @;  #: Return Type @;
654  sub ParseLocation {  sub ParseLocation {
655          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
656        # the first parameter.
657        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
658          my ($location) = @_;          my ($location) = @_;
659          # Parse it into segments.          # Parse it into segments.
660          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;
# Line 679  Line 673 
673          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
674  }  }
675    
676    =head3 PointLocation
677    
678    C<< my $found = Sprout::PointLocation($location, $point); >>
679    
680    Return the offset into the specified location of the specified point on the contig. If
681    the specified point is before the location, a negative value will be returned. If it is
682    beyond the location, an undefined value will be returned. It is assumed that the offset
683    is for the location's contig. The location can either be new-style (using a C<+> or C<->
684    and a length) or old-style (using C<_> and start and end positions.
685    
686    =over 4
687    
688    =item location
689    
690    A location specifier (see L</FeatureLocation> for a description).
691    
692    =item point
693    
694    The offset into the contig of the point in which we're interested.
695    
696    =item RETURN
697    
698    Returns the offset inside the specified location of the specified point, a negative
699    number if the point is before the location, or an undefined value if the point is past
700    the location. If the length of the location is 0, this method will B<always> denote
701    that it is outside the location. The offset will always be relative to the left-most
702    position in the location.
703    
704    =back
705    
706    =cut
707    #: Return Type $;
708    sub PointLocation {
709        # Get the parameter. Note that if we're called as an instance method, we ignore
710        # the first parameter.
711        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
712        my ($location, $point) = @_;
713        # Parse out the location elements. Note that this works on both old-style and new-style
714        # locations.
715        my ($contigID, $start, $dir, $len) = ParseLocation($location);
716        # Declare the return variable.
717        my $retVal;
718        # Compute the offset. The computation is dependent on the direction of the location.
719        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
720        # Return the offset if it's valid.
721        if ($offset < $len) {
722            $retVal = $offset;
723        }
724        # Return the offset found.
725        return $retVal;
726    }
727    
728  =head3 DNASeq  =head3 DNASeq
729    
730  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
# Line 704  Line 750 
750  #: Return Type $;  #: Return Type $;
751  sub DNASeq {  sub DNASeq {
752          # Get the parameters.          # Get the parameters.
753          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
754          # Create the return string.          # Create the return string.
755          my $retVal = "";          my $retVal = "";
756          # Loop through the locations.          # Loop through the locations.
# Line 720  Line 765 
765                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
766                  # before putting it in the return value.                  # before putting it in the return value.
767                  my ($start, $stop);                  my ($start, $stop);
768            Tracer("Parsed location is $beg$dir$len.") if T(SDNA => 4);
769                  if ($dir eq "+") {                  if ($dir eq "+") {
770                          $start = $beg;                          $start = $beg;
771                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
772                  } else {                  } else {
773                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
774                          $stop = $beg;                          $stop = $beg;
775                  }                  }
776            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
777                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
778                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
779                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 738  Line 785 
785                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
786                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
787                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
788                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
789                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
790                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
791                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;
792                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
793                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
794                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
795                  }                  }
796                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
797                  if ($dir eq '+') {                  if ($dir eq '+') {
798                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
799                  } else {                  } else {
800                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
801                  }                  }
802          }          }
803          # Return the result.          # Return the result.
# Line 778  Line 826 
826  #: Return Type @;  #: Return Type @;
827  sub AllContigs {  sub AllContigs {
828          # Get the parameters.          # Get the parameters.
829          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
830          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
831          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
832                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 809  Line 856 
856  #: Return Type $;  #: Return Type $;
857  sub ContigLength {  sub ContigLength {
858          # Get the parameters.          # Get the parameters.
859          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
860          # Get the contig's last sequence.          # Get the contig's last sequence.
861          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
862                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 852  Line 898 
898  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns a three-element list. The first element is a list of feature IDs for the features that
899  overlap the region of interest. The second and third elements are the minimum and maximum  overlap the region of interest. The second and third elements are the minimum and maximum
900  locations of the features provided on the specified contig. These may extend outside  locations of the features provided on the specified contig. These may extend outside
901  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
902    roughly by location.
903    
904  =back  =back
905    
906  =cut  =cut
907  #: Return Type @;  #: Return Type @@;
908  sub GenesInRegion {  sub GenesInRegion {
909          # Get the parameters.          # Get the parameters.
910          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
911          # Get the maximum segment length.          # Get the maximum segment length.
912          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
913          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
914          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
915        # containing the minimum and maximum offsets. We will use the offsets to sort the results
916        # when we're building the result set.
917          my %featuresFound = ();          my %featuresFound = ();
918          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
919          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
920        my ($min, $max) = @initialMinMax;
921          # Create a table of parameters for each query. Each query looks for features travelling in          # Create a table of parameters for each query. Each query looks for features travelling in
922          # a particular direction. The query parameters include the contig ID, the feature direction,          # a particular direction. The query parameters include the contig ID, the feature direction,
923          # the lowest possible start position, and the highest possible start position. This works          # the lowest possible start position, and the highest possible start position. This works
# Line 898  Line 947 
947                                          $found = 1;                                          $found = 1;
948                                  }                                  }
949                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
950                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
951                                  if ($end <= $stop) {                  # ending.
952                    ($beg, $end) = ($beg - $len, $beg);
953                    if ($beg <= $stop) {
954                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
955                                          $found = 1;                                          $found = 1;
956                                  }                                  }
957                          }                          }
958                          if ($found) {                          if ($found) {
959                                  # Here we need to record the feature and update the minimum and maximum.                  # Here we need to record the feature and update the minima and maxima. First,
960                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
961                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
962                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
963                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
964                                  if ($end > $max) { $max = $end; }                  # global min and max.
965                    if ($beg < $loc1) {
966                        $loc1 = $beg;
967                        $min = $beg if $beg < $min;
968                    }
969                    if ($end > $loc2) {
970                        $loc2 = $end;
971                        $max = $end if $end > $max;
972                    }
973                    # Store the entry back into the hash table.
974                    $featuresFound{$featureID} = [$loc1, $loc2];
975                          }                          }
976                  }                  }
977          }          }
978          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
979          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
980        # but the result of the sort will be the same.)
981        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
982        # Now we sort by midpoint and yank out the feature IDs.
983        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
984          # Return it along with the min and max.          # Return it along with the min and max.
985          return (\@list, $min, $max);      return (\@retVal, $min, $max);
986  }  }
987    
988  =head3 FType  =head3 FType
# Line 943  Line 1008 
1008  #: Return Type $;  #: Return Type $;
1009  sub FType {  sub FType {
1010          # Get the parameters.          # Get the parameters.
1011          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1012          # Get the specified feature's type.          # Get the specified feature's type.
1013          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1014          # Return the result.          # Return the result.
# Line 981  Line 1045 
1045  #: Return Type @%;  #: Return Type @%;
1046  sub FeatureAnnotations {  sub FeatureAnnotations {
1047          # Get the parameters.          # Get the parameters.
1048          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1049          # Create a query to get the feature's annotations and the associated users.          # Create a query to get the feature's annotations and the associated users.
1050          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1051                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1011  Line 1074 
1074  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1075    
1076  Return all of the functional assignments for a particular feature. The data is returned as a  Return all of the functional assignments for a particular feature. The data is returned as a
1077  hash of functional assignments to user IDs. A functional assignment is a type of annotation.  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
1078  It has the format "XXXX\nset XXXX function to\nYYYYY". In this instance, XXXX is the user ID  Functional assignments are described in the L</ParseAssignment> function. Its worth noting that
1079  and YYYYY is the functional assignment text. Its worth noting that we cannot filter on the content  we cannot filter on the content of the annotation itself because it's a text field; however,
1080  of the annotation itself because it's a text field; however, this is not a big problem because most  this is not a big problem because most features only have a small number of annotations.
1081  features only have a small number of annotations. Finally, if a single user has multiple  Finally, if a single user has multiple functional assignments, we will only keep the most
1082  functional assignments, we will only keep the most recent one.  recent one.
1083    
1084  =over 4  =over 4
1085    
# Line 1034  Line 1097 
1097  #: Return Type %;  #: Return Type %;
1098  sub AllFunctionsOf {  sub AllFunctionsOf {
1099          # Get the parameters.          # Get the parameters.
1100          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1101          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1102      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1103                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
# Line 1051  Line 1113 
1113          # Get the annotation fields.          # Get the annotation fields.
1114          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text) = @{$annotation};
1115                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1116                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1117          if ($user && ! exists $timeHash{$user}) {          if ($user && ! exists $timeHash{$user}) {
1118              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1119              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
# Line 1073  Line 1135 
1135    
1136  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1137  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1138  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is a type of annotation. The format of an assignment is described in
1139  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1140  we cannot filter on the content of the annotation itself because it's a text field; however, this  annotation itself because it's a text field; however, this is not a big problem because
1141  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1142    
1143  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1144  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1108  Line 1170 
1170  #: Return Type $;  #: Return Type $;
1171  sub FunctionOf {  sub FunctionOf {
1172          # Get the parameters.          # Get the parameters.
1173          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1174      # Declare the return value.      # Declare the return value.
1175      my $retVal;      my $retVal;
1176      # Determine the ID type.      # Determine the ID type.
# Line 1146  Line 1207 
1207              # Get the annotation text.              # Get the annotation text.
1208              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1209              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1210              my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1211              if ($type =~ m/^set $user function to$/i) {              if ($user) {
1212                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1213                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1214                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1185  Line 1246 
1246    
1247  =item RETURN  =item RETURN
1248    
1249  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1250  their best hits.  on the target genome.
1251    
1252  =back  =back
1253    
# Line 1194  Line 1255 
1255  #: Return Type %;  #: Return Type %;
1256  sub BBHList {  sub BBHList {
1257          # Get the parameters.          # Get the parameters.
1258          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1259          # Create the return structure.          # Create the return structure.
1260          my %retVal = ();          my %retVal = ();
1261          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1215  Line 1275 
1275          return \%retVal;          return \%retVal;
1276  }  }
1277    
1278    =head3 SimList
1279    
1280    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1281    
1282    Return a list of the similarities to the specified feature.
1283    
1284    Sprout does not support real similarities, so this method just returns the bidirectional
1285    best hits.
1286    
1287    =over 4
1288    
1289    =item featureID
1290    
1291    ID of the feature whose similarities are desired.
1292    
1293    =item count
1294    
1295    Maximum number of similar features to be returned, or C<0> to return them all.
1296    
1297    =back
1298    
1299    =cut
1300    #: Return Type %;
1301    sub SimList {
1302        # Get the parameters.
1303        my ($self, $featureID, $count) = @_;
1304        # Ask for the best hits.
1305        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1306                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1307                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1308                                  $count);
1309        # Create the return value.
1310        my %retVal = ();
1311        for my $tuple (@lists) {
1312            $retVal{$tuple->[0]} = $tuple->[1];
1313        }
1314        # Return the result.
1315        return %retVal;
1316    }
1317    
1318    
1319    
1320    =head3 IsComplete
1321    
1322    C<< my $flag = $sprout->IsComplete($genomeID); >>
1323    
1324    Return TRUE if the specified genome is complete, else FALSE.
1325    
1326    =over 4
1327    
1328    =item genomeID
1329    
1330    ID of the genome whose completeness status is desired.
1331    
1332    =item RETURN
1333    
1334    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1335    not found.
1336    
1337    =back
1338    
1339    =cut
1340    #: Return Type $;
1341    sub IsComplete {
1342        # Get the parameters.
1343        my ($self, $genomeID) = @_;
1344        # Declare the return variable.
1345        my $retVal;
1346        # Get the genome's data.
1347        my $genomeData = $self->GetEntity('Genome', $genomeID);
1348        if ($genomeData) {
1349            # The genome exists, so get the completeness flag.
1350            ($retVal) = $genomeData->Value('complete');
1351        }
1352        # Return the result.
1353        return $retVal;
1354    }
1355    
1356  =head3 FeatureAliases  =head3 FeatureAliases
1357    
1358  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1238  Line 1376 
1376  #: Return Type @;  #: Return Type @;
1377  sub FeatureAliases {  sub FeatureAliases {
1378          # Get the parameters.          # Get the parameters.
1379          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1380          # Get the desired feature's aliases          # Get the desired feature's aliases
1381          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1382          # Return the result.          # Return the result.
# Line 1269  Line 1406 
1406  #: Return Type $;  #: Return Type $;
1407  sub GenomeOf {  sub GenomeOf {
1408          # Get the parameters.          # Get the parameters.
1409          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1410          # Create a query to find the genome associated with the feature.          # Create a query to find the genome associated with the feature.
1411          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1412          # Declare the return value.          # Declare the return value.
# Line 1306  Line 1442 
1442  #: Return Type %;  #: Return Type %;
1443  sub CoupledFeatures {  sub CoupledFeatures {
1444          # Get the parameters.          # Get the parameters.
1445          my $self = shift @_;      my ($self, $featureID) = @_;
1446          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1447          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1448          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1449          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1450          my $found = 0;          my $found = 0;
1451          # Create the return hash.          # Create the return hash.
1452          my %retVal = ();          my %retVal = ();
1453          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1454          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1455                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1456                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1457                                                            'Coupling(score)']);
1458            # The coupling ID contains the two feature IDs separated by a space. We use
1459            # this information to find the ID of the other feature.
1460            my ($fid1, $fid2) = split / /, $couplingID;
1461            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1462            # Attach the other feature's score to its ID.
1463                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1464                  $found = 1;                  $found = 1;
1465          }          }
# Line 1333  Line 1472 
1472          return %retVal;          return %retVal;
1473  }  }
1474    
1475    =head3 CouplingEvidence
1476    
1477    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1478    
1479    Return the evidence for a functional coupling.
1480    
1481    A pair of features is considered evidence of a coupling between two other
1482    features if they occur close together on a contig and both are similar to
1483    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1484    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1485    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1486    similar to B<A2>.
1487    
1488    The score of a coupling is determined by the number of pieces of evidence
1489    that are considered I<representative>. If several evidence items belong to
1490    a group of genomes that are close to each other, only one of those items
1491    is considered representative. The other evidence items are presumed to be
1492    there because of the relationship between the genomes rather than because
1493    the two proteins generated by the features have a related functionality.
1494    
1495    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1496    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1497    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1498    and FALSE otherwise.
1499    
1500    =over 4
1501    
1502    =item peg1
1503    
1504    ID of the feature of interest.
1505    
1506    =item peg2
1507    
1508    ID of a feature functionally coupled to the feature of interest.
1509    
1510    =item RETURN
1511    
1512    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1513    of interest, a feature similar to the functionally coupled feature, and a flag
1514    that is TRUE for a representative piece of evidence and FALSE otherwise.
1515    
1516    =back
1517    
1518    =cut
1519    #: Return Type @@;
1520    sub CouplingEvidence {
1521        # Get the parameters.
1522        my ($self, $peg1, $peg2) = @_;
1523        # Declare the return variable.
1524        my @retVal = ();
1525        # Our first task is to find out the nature of the coupling: whether or not
1526        # it exists, its score, and whether the features are stored in the same
1527        # order as the ones coming in.
1528        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1529        # Only proceed if a coupling exists.
1530        if ($couplingID) {
1531            # Determine the ordering to place on the evidence items. If we're
1532            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1533            # we want feature 1 before feature 2 (normal).
1534            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1535            my $ordering = ($inverted ? "DESC" : "");
1536            # Get the coupling evidence.
1537            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1538                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1539                                              [$couplingID],
1540                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1541            # Loop through the evidence items. Each piece of evidence is represented by two
1542            # positions in the evidence list, one for each feature on the other side of the
1543            # evidence link. If at some point we want to generalize to couplings with
1544            # more than two positions, this section of code will need to be re-done.
1545            while (@evidenceList > 0) {
1546                my $peg1Data = shift @evidenceList;
1547                my $peg2Data = shift @evidenceList;
1548                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1549                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1550            }
1551            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1552        }
1553        # Return the result.
1554        return @retVal;
1555    }
1556    
1557    =head3 GetCoupling
1558    
1559    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1560    
1561    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1562    exists, we return the coupling ID along with an indicator of whether the
1563    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1564    In the second case, we say the coupling is I<inverted>. The importance of an
1565    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1566    
1567    =over 4
1568    
1569    =item peg1
1570    
1571    ID of the feature of interest.
1572    
1573    =item peg2
1574    
1575    ID of the potentially coupled feature.
1576    
1577    =item RETURN
1578    
1579    Returns a three-element list. The first element contains the database ID of
1580    the coupling. The second element is FALSE if the coupling is stored in the
1581    database in the caller specified order and TRUE if it is stored in the
1582    inverted order. The third element is the coupling's score. If the coupling
1583    does not exist, all three list elements will be C<undef>.
1584    
1585    =back
1586    
1587    =cut
1588    #: Return Type $%@;
1589    sub GetCoupling {
1590        # Get the parameters.
1591        my ($self, $peg1, $peg2) = @_;
1592        # Declare the return values. We'll start with the coupling ID and undefine the
1593        # flag and score until we have more information.
1594        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1595        # Find the coupling data.
1596        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1597                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1598                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1599        # Check to see if we found anything.
1600        if (!@pegs) {
1601            Trace("No coupling found.") if T(Coupling => 4);
1602            # No coupling, so undefine the return value.
1603            $retVal = undef;
1604        } else {
1605            # We have a coupling! Get the score and check for inversion.
1606            $score = $pegs[0]->[1];
1607            my $firstFound = $pegs[0]->[0];
1608            $inverted = ($firstFound ne $peg1);
1609            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1610        }
1611        # Return the result.
1612        return ($retVal, $inverted, $score);
1613    }
1614    
1615    =head3 CouplingID
1616    
1617    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1618    
1619    Return the coupling ID for a pair of feature IDs.
1620    
1621    The coupling ID is currently computed by joining the feature IDs in
1622    sorted order with a space. Client modules (that is, modules which
1623    use Sprout) should not, however, count on this always being the
1624    case. This method provides a way for abstracting the concept of a
1625    coupling ID. All that we know for sure about it is that it can be
1626    generated easily from the feature IDs and the order of the IDs
1627    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1628    will have the same value as C<CouplingID("b1", "a1")>.
1629    
1630    =over 4
1631    
1632    =item peg1
1633    
1634    First feature of interest.
1635    
1636    =item peg2
1637    
1638    Second feature of interest.
1639    
1640    =item RETURN
1641    
1642    Returns the ID that would be used to represent a functional coupling of
1643    the two specified PEGs.
1644    
1645    =back
1646    
1647    =cut
1648    #: Return Type $;
1649    sub CouplingID {
1650        return join " ", sort @_;
1651    }
1652    
1653  =head3 GetEntityTypes  =head3 GetEntityTypes
1654    
1655  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1343  Line 1660 
1660  #: Return Type @;  #: Return Type @;
1661  sub GetEntityTypes {  sub GetEntityTypes {
1662          # Get the parameters.          # Get the parameters.
1663          my $self = shift @_;      my ($self) = @_;
1664          # Get the underlying database object.          # Get the underlying database object.
1665          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1666          # Get its entity type list.          # Get its entity type list.
# Line 1394  Line 1711 
1711                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1712                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1713                          if ($id) {                          if ($id) {
1714                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1715                          }                          }
1716                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1717                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1718                  } else {                  } else {
1719                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
1720                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1721                # case.
1722                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1723                          $sequence .= $1;                          $sequence .= $1;
1724                  }                  }
1725          }          }
1726          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1727          if ($sequence) {          if ($sequence) {
1728                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1729          }          }
1730        # Close the file.
1731        close FASTAFILE;
1732          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1733          return %retVal;          return %retVal;
1734  }  }
# Line 1419  Line 1739 
1739    
1740  Insure that a list of feature locations is in the Sprout format. The Sprout feature location  Insure that a list of feature locations is in the Sprout format. The Sprout feature location
1741  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
1742  gene. The old format is I<contig>_I<beg>_I<end>.  gene. The old format is I<contig>_I<beg>_I<end>. If a feature is in the new format already,
1743    it will not be changed; otherwise, it will be converted. This method can also be used to
1744    perform the reverse task-- insuring that all the locations are in the old format.
1745    
1746  =over 4  =over 4
1747    
# Line 1446  Line 1768 
1768  #: Return Type @;  #: Return Type @;
1769  sub FormatLocations {  sub FormatLocations {
1770          # Get the parameters.          # Get the parameters.
1771          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1772          # Create the return list.          # Create the return list.
1773          my @retVal = ();          my @retVal = ();
1774          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1775          if ($locations eq '') {          if ($locations eq '') {
1776              confess "No locations specified.";          Confess("No locations specified.");
1777          } else {          } else {
1778                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1779                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1487  Line 1808 
1808    
1809  sub DumpData {  sub DumpData {
1810          # Get the parameters.          # Get the parameters.
1811          my $self = shift @_;      my ($self) = @_;
1812          # Get the data directory name.          # Get the data directory name.
1813          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1814          # Dump the relations.          # Dump the relations.
# Line 1503  Line 1824 
1824  =cut  =cut
1825  #: Return Type $;  #: Return Type $;
1826  sub XMLFileName {  sub XMLFileName {
1827          my $self = shift @_;      my ($self) = @_;
1828          return $self->{_xmlName};          return $self->{_xmlName};
1829  }  }
1830    
# Line 1523  Line 1844 
1844  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1845  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1846    
1847  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1848    
1849  =over 4  =over 4
1850    
# Line 1541  Line 1862 
1862  #: Return Type ;  #: Return Type ;
1863  sub Insert {  sub Insert {
1864          # Get the parameters.          # Get the parameters.
1865          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1866          # Call the underlying method.          # Call the underlying method.
1867          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1868  }  }
# Line 1583  Line 1903 
1903  #: Return Type $;  #: Return Type $;
1904  sub Annotate {  sub Annotate {
1905          # Get the parameters.          # Get the parameters.
1906          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1907          # Create the annotation ID.          # Create the annotation ID.
1908          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1909          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1604  Line 1923 
1923    
1924  =head3 AssignFunction  =head3 AssignFunction
1925    
1926  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1927    
1928  This method assigns a function to a feature. Functions are a special type of annotation. The general  This method assigns a function to a feature. Functions are a special type of annotation. The general
1929  format is "XXXX\nset XXXX function to\nYYYYY" where XXXX is the feature type and YYYY is the functional  format is described in L</ParseAssignment>.
 assignment text.  
1930    
1931  =over 4  =over 4
1932    
# Line 1618  Line 1936 
1936    
1937  =item user  =item user
1938    
1939  Name of the user making the assignment. This is frequently a group name, like C<kegg> or C<fig>.  Name of the user group making the assignment, such as C<kegg> or C<fig>.
1940    
1941  =item function  =item function
1942    
1943  Text of the function being assigned.  Text of the function being assigned.
1944    
1945    =item assigningUser (optional)
1946    
1947    Name of the individual user making the assignment. If omitted, defaults to the user group.
1948    
1949  =item RETURN  =item RETURN
1950    
1951  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1634  Line 1956 
1956  #: Return Type $;  #: Return Type $;
1957  sub AssignFunction {  sub AssignFunction {
1958          # Get the parameters.          # Get the parameters.
1959          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1960          my ($featureID, $user, $function) = @_;      # Default the assigning user.
1961        if (! $assigningUser) {
1962            $assigningUser = $user;
1963        }
1964          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1965          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1966          # Get the current time.          # Get the current time.
1967          my $now = time;          my $now = time;
1968          # Declare the return variable.          # Declare the return variable.
# Line 1682  Line 2007 
2007  #: Return Type @;  #: Return Type @;
2008  sub FeaturesByAlias {  sub FeaturesByAlias {
2009          # Get the parameters.          # Get the parameters.
2010          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2011          # Declare the return variable.          # Declare the return variable.
2012          my @retVal = ();          my @retVal = ();
2013          # Parse the alias.          # Parse the alias.
# Line 1725  Line 2049 
2049  #: Return Type $;  #: Return Type $;
2050  sub Exists {  sub Exists {
2051          # Get the parameters.          # Get the parameters.
2052          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2053          # Check for the entity instance.          # Check for the entity instance.
2054        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2055          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2056          # Return an existence indicator.          # Return an existence indicator.
2057          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1756  Line 2080 
2080  #: Return Type $;  #: Return Type $;
2081  sub FeatureTranslation {  sub FeatureTranslation {
2082          # Get the parameters.          # Get the parameters.
2083          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2084          # Get the specified feature's translation.          # Get the specified feature's translation.
2085          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2086          return $retVal;          return $retVal;
# Line 1789  Line 2112 
2112  #: Return Type @;  #: Return Type @;
2113  sub Taxonomy {  sub Taxonomy {
2114          # Get the parameters.          # Get the parameters.
2115          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2116          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2117          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2118          # Declare the return variable.          # Declare the return variable.
# Line 1833  Line 2155 
2155  #: Return Type $;  #: Return Type $;
2156  sub CrudeDistance {  sub CrudeDistance {
2157          # Get the parameters.          # Get the parameters.
2158          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2159          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2160          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2161          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1881  Line 2202 
2202  #: Return Type $;  #: Return Type $;
2203  sub RoleName {  sub RoleName {
2204          # Get the parameters.          # Get the parameters.
2205          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2206          # Get the specified role's name.          # Get the specified role's name.
2207          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2208          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1915  Line 2235 
2235  #: Return Type @;  #: Return Type @;
2236  sub RoleDiagrams {  sub RoleDiagrams {
2237          # Get the parameters.          # Get the parameters.
2238          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2239          # Query for the diagrams.          # Query for the diagrams.
2240          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2241                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1924  Line 2243 
2243          return @retVal;          return @retVal;
2244  }  }
2245    
2246    =head3 GetProperties
2247    
2248    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2249    
2250    Return a list of the properties with the specified characteristics.
2251    
2252    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2253    will also be associated with genomes.) A property value is represented by a 4-tuple of
2254    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2255    
2256    =over 4
2257    
2258    =item fid
2259    
2260    ID of the feature possessing the property.
2261    
2262    =item key
2263    
2264    Name or key of the property.
2265    
2266    =item value
2267    
2268    Value of the property.
2269    
2270    =item url
2271    
2272    URL of the document that indicated the property should have this particular value, or an
2273    empty string if no such document exists.
2274    
2275    =back
2276    
2277    The parameters act as a filter for the desired data. Any non-null parameter will
2278    automatically match all the tuples returned. So, specifying just the I<$fid> will
2279    return all the properties of the specified feature; similarly, specifying the I<$key>
2280    and I<$value> parameters will return all the features having the specified property
2281    value.
2282    
2283    A single property key can have many values, representing different ideas about the
2284    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2285    virulent, and another may declare that it is not virulent. A query about the virulence of
2286    C<fig|83333.1.peg.10> would be coded as
2287    
2288        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2289    
2290    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2291    not to be filtered. The tuples returned would be
2292    
2293        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2294        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2295    
2296    =cut
2297    #: Return Type @@;
2298    sub GetProperties {
2299        # Get the parameters.
2300        my ($self, @parms) = @_;
2301        # Declare the return variable.
2302        my @retVal = ();
2303        # Now we need to create a WHERE clause that will get us the data we want. First,
2304        # we create a list of the columns containing the data for each parameter.
2305        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2306                        'Property(property-value)', 'HasProperty(evidence)');
2307        # Now we build the WHERE clause and the list of parameter values.
2308        my @where = ();
2309        my @values = ();
2310        for (my $i = 0; $i <= $#colNames; $i++) {
2311            my $parm = $parms[$i];
2312            if (defined $parm && ($parm ne '')) {
2313                push @where, "$colNames[$i] = ?";
2314                push @values, $parm;
2315            }
2316        }
2317        # Format the WHERE clause.
2318        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2319        # Ask for all the propertie values with the desired characteristics.
2320        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2321        while (my $valueObject = $query->Fetch()) {
2322            my @tuple = $valueObject->Values(\@colNames);
2323            push @retVal, \@tuple;
2324        }
2325        # Return the result.
2326        return @retVal;
2327    }
2328    
2329  =head3 FeatureProperties  =head3 FeatureProperties
2330    
2331  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1953  Line 2355 
2355  #: Return Type @@;  #: Return Type @@;
2356  sub FeatureProperties {  sub FeatureProperties {
2357          # Get the parameters.          # Get the parameters.
2358          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2359          # Get the properties.          # Get the properties.
2360          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2361                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1985  Line 2386 
2386  #: Return Type $;  #: Return Type $;
2387  sub DiagramName {  sub DiagramName {
2388          # Get the parameters.          # Get the parameters.
2389          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2390          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2391          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2392          return $retVal;          return $retVal;
# Line 2018  Line 2418 
2418  #: Return Type @;  #: Return Type @;
2419  sub MergedAnnotations {  sub MergedAnnotations {
2420          # Get the parameters.          # Get the parameters.
2421          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2422          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2423          my @tuples = ();          my @tuples = ();
2424          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2067  Line 2466 
2466  #: Return Type @;  #: Return Type @;
2467  sub RoleNeighbors {  sub RoleNeighbors {
2468          # Get the parameters.          # Get the parameters.
2469          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2470          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2471          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2472                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2110  Line 2508 
2508  #: Return Type @;  #: Return Type @;
2509  sub FeatureLinks {  sub FeatureLinks {
2510          # Get the parameters.          # Get the parameters.
2511          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2512          # Get the feature's links.          # Get the feature's links.
2513          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2514          # Return the feature's links.          # Return the feature's links.
# Line 2123  Line 2520 
2520  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2521    
2522  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
2523  to the role the feature performs.  to the roles the feature performs.
2524    
2525  =over 4  =over 4
2526    
# Line 2133  Line 2530 
2530    
2531  =item RETURN  =item RETURN
2532    
2533  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
2534    
2535  =back  =back
2536    
2537  =cut  =cut
2538  #: Return Type %;  #: Return Type %@;
2539  sub SubsystemsOf {  sub SubsystemsOf {
2540          # Get the parameters.          # Get the parameters.
2541          my $self = shift @_;      my ($self, $featureID) = @_;
2542          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2543          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2544                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2545                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2151  Line 2547 
2547          my %retVal = ();          my %retVal = ();
2548          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2549          for my $record (@subsystems) {          for my $record (@subsystems) {
2550                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2551            if (exists $retVal{$subsys}) {
2552                push @{$retVal{$subsys}}, $role;
2553            } else {
2554                $retVal{$subsys} = [$role];
2555            }
2556          }          }
2557          # Return the hash.          # Return the hash.
2558          return %retVal;          return %retVal;
2559  }  }
2560    
2561    =head3 SubsystemList
2562    
2563    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2564    
2565    Return a list containing the names of the subsystems in which the specified
2566    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2567    subsystem names, not the roles.
2568    
2569    =over 4
2570    
2571    =item featureID
2572    
2573    ID of the feature whose subsystem names are desired.
2574    
2575    =item RETURN
2576    
2577    Returns a list of the names of the subsystems in which the feature participates.
2578    
2579    =back
2580    
2581    =cut
2582    #: Return Type @;
2583    sub SubsystemList {
2584        # Get the parameters.
2585        my ($self, $featureID) = @_;
2586        # Get the list of names.
2587        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2588                                    [$featureID], 'HasSSCell(from-link)');
2589        # Return the result.
2590        return @retVal;
2591    }
2592    
2593  =head3 RelatedFeatures  =head3 RelatedFeatures
2594    
2595  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2190  Line 2623 
2623  #: Return Type @;  #: Return Type @;
2624  sub RelatedFeatures {  sub RelatedFeatures {
2625          # Get the parameters.          # Get the parameters.
2626          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2627          # Get a list of the features that are BBHs of the incoming feature.          # Get a list of the features that are BBHs of the incoming feature.
2628          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2629                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2239  Line 2671 
2671  #: Return Type @;  #: Return Type @;
2672  sub TaxonomySort {  sub TaxonomySort {
2673          # Get the parameters.          # Get the parameters.
2674          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2675          # Create the working hash table.          # Create the working hash table.
2676          my %hashBuffer = ();          my %hashBuffer = ();
2677          # Loop through the features.          # Loop through the features.
# Line 2249  Line 2680 
2680                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2681                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2682                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2683                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2684          }          }
2685          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2686          my @retVal = ();          my @retVal = ();
# Line 2322  Line 2749 
2749  #: Return Type @@;  #: Return Type @@;
2750  sub GetAll {  sub GetAll {
2751          # Get the parameters.          # Get the parameters.
2752          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2753          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2754          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2755          my $query = $self->Get($objectNames, $filterClause, $parameterList);                                          $fields, $count);
         # Set up a counter of the number of records read.  
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
2756          # Return the resulting list.          # Return the resulting list.
2757          return @retVal;          return @retVal;
2758  }  }
# Line 2384  Line 2797 
2797  #: Return Type @;  #: Return Type @;
2798  sub GetFlat {  sub GetFlat {
2799          # Get the parameters.          # Get the parameters.
2800          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2801          # Construct the query.          # Construct the query.
2802          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2803          # Create the result list.          # Create the result list.
# Line 2495  Line 2907 
2907  #: Return Type @;  #: Return Type @;
2908  sub LoadInfo {  sub LoadInfo {
2909          # Get the parameters.          # Get the parameters.
2910          my $self = shift @_;      my ($self) = @_;
2911          # Create the return list, priming it with the name of the data directory.          # Create the return list, priming it with the name of the data directory.
2912          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2913          # Concatenate the table names.          # Concatenate the table names.
# Line 2532  Line 2944 
2944  #: Return Type %;  #: Return Type %;
2945  sub LowBBHs {  sub LowBBHs {
2946          # Get the parsameters.          # Get the parsameters.
2947          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
2948          # Create the return hash.          # Create the return hash.
2949          my %retVal = ();          my %retVal = ();
2950          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2562  Line 2973 
2973  #: Return Type %@;  #: Return Type %@;
2974  sub GetGroups {  sub GetGroups {
2975      # Get the parameters.      # Get the parameters.
2976      my $self = shift @_;      my ($self, $groupList) = @_;
     my ($groupList) = @_;  
2977      # Declare the return value.      # Declare the return value.
2978      my %retVal = ();      my %retVal = ();
2979      # Determine whether we are getting all the groups or just some.      # Determine whether we are getting all the groups or just some.
# Line 2590  Line 3000 
3000              # Loop through the groups, adding the genome ID to each group's              # Loop through the groups, adding the genome ID to each group's
3001              # list.              # list.
3002              for my $group (@groups) {              for my $group (@groups) {
3003                  if (exists $retVal{$group}) {                  Tracer::AddToListMap(\%retVal, $group, $genomeID);
                     push @{$retVal{$group}}, $genomeID;  
                 } else {  
                     $retVal{$group} = [$genomeID];  
                 }  
3004              }              }
3005          }          }
3006      }      }
# Line 2602  Line 3008 
3008      return %retVal;      return %retVal;
3009  }  }
3010    
3011    =head3 MyGenomes
3012    
3013    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3014    
3015    Return a list of the genomes to be included in the Sprout.
3016    
3017    This method is provided for use during the Sprout load. It presumes the Genome load file has
3018    already been created. (It will be in the Sprout data directory and called either C<Genome>
3019    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3020    IDs.
3021    
3022    =over 4
3023    
3024    =item dataDir
3025    
3026    Directory containing the Sprout load files.
3027    
3028    =back
3029    
3030    =cut
3031    #: Return Type @;
3032    sub MyGenomes {
3033        # Get the parameters.
3034        my ($dataDir) = @_;
3035        # Compute the genome file name.
3036        my $genomeFileName = LoadFileName($dataDir, "Genome");
3037        # Extract the genome IDs from the files.
3038        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3039        # Return the result.
3040        return @retVal;
3041    }
3042    
3043    =head3 LoadFileName
3044    
3045    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3046    
3047    Return the name of the load file for the specified table in the specified data
3048    directory.
3049    
3050    =over 4
3051    
3052    =item dataDir
3053    
3054    Directory containing the Sprout load files.
3055    
3056    =item tableName
3057    
3058    Name of the table whose load file is desired.
3059    
3060    =item RETURN
3061    
3062    Returns the name of the file containing the load data for the specified table, or
3063    C<undef> if no load file is present.
3064    
3065    =back
3066    
3067    =cut
3068    #: Return Type $;
3069    sub LoadFileName {
3070        # Get the parameters.
3071        my ($dataDir, $tableName) = @_;
3072        # Declare the return variable.
3073        my $retVal;
3074        # Check for the various file names.
3075        if (-e "$dataDir/$tableName") {
3076            $retVal = "$dataDir/$tableName";
3077        } elsif (-e "$dataDir/$tableName.dtx") {
3078            $retVal = "$dataDir/$tableName.dtx";
3079        }
3080        # Return the result.
3081        return $retVal;
3082    }
3083    
3084  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3085    
3086  =head3 ParseAssignment  =head3 ParseAssignment
3087    
3088  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3089  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3090  will be returned.  isn't, an empty list will be returned.
3091    
3092    A functional assignment is always of the form
3093    
3094        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3095    
3096    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3097    actual functional role. In most cases, the user and the assigning user will be the
3098    same, but that is not always the case.
3099    
3100  This is a static method.  This is a static method.
3101    
# Line 2627  Line 3114 
3114    
3115  =cut  =cut
3116    
3117  sub ParseAssignment {  sub _ParseAssignment {
3118          # Get the parameters.          # Get the parameters.
3119          my ($text) = @_;          my ($text) = @_;
3120          # Declare the return value.          # Declare the return value.
3121          my @retVal = ();          my @retVal = ();
3122          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3123          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3124          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3125                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3126                  @retVal = ($user, $function);          # and the assigning user.
3127            @retVal = ($1, $function, $user);
3128          }          }
3129          # Return the result list.          # Return the result list.
3130          return @retVal;          return @retVal;
# Line 2668  Line 3156 
3156      return $retVal;      return $retVal;
3157  }  }
3158    
3159    =head3 AddProperty
3160    
3161    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3162    
3163    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3164    be added to almost any object. In Sprout, they can only be added to features. In
3165    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3166    pair. If the particular key/value pair coming in is not already in the database, a new
3167    B<Property> record is created to hold it.
3168    
3169    =over 4
3170    
3171    =item peg
3172    
3173    ID of the feature to which the attribute is to be replied.
3174    
3175    =item key
3176    
3177    Name of the attribute (key).
3178    
3179    =item value
3180    
3181    Value of the attribute.
3182    
3183    =item url
3184    
3185    URL or text citation from which the property was obtained.
3186    
3187    =back
3188    
3189    =cut
3190    #: Return Type ;
3191    sub AddProperty {
3192        # Get the parameters.
3193        my ($self, $featureID, $key, $value, $url) = @_;
3194        # Declare the variable to hold the desired property ID.
3195        my $propID;
3196        # Attempt to find a property record for this key/value pair.
3197        my @properties = $self->GetFlat(['Property'],
3198                                       "Property(property-name) = ? AND Property(property-value) = ?",
3199                                       [$key, $value], 'Property(id)');
3200        if (@properties) {
3201            # Here the property is already in the database. We save its ID.
3202            $propID = $properties[0];
3203            # Here the property value does not exist. We need to generate an ID. It will be set
3204            # to a number one greater than the maximum value in the database. This call to
3205            # GetAll will stop after one record.
3206            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3207                                            1);
3208            $propID = $maxProperty[0]->[0] + 1;
3209            # Insert the new property value.
3210            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3211        }
3212        # Now we connect the incoming feature to the property.
3213        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3214    }
3215    
3216    
3217    
3218  1;  1;

Legend:
Removed from v.1.8  
changed lines
  Added in v.1.30

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3