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

Diff of /Sprout/Sprout.pm

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

revision 1.1, Sun Jan 23 16:12:29 2005 UTC revision 1.43, Tue Oct 18 18:36:26 2005 UTC
# Line 11  Line 11 
11          use Tracer;          use Tracer;
12          use FIGRules;          use FIGRules;
13          use Stats;          use Stats;
14        use POSIX qw(strftime);
15    
16    
17  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
# Line 33  Line 34 
34    
35  =cut  =cut
36    
37  #  #: Constructor SFXlate->new_sprout_only();
38    
39  =head2 Public Methods  =head2 Public Methods
40    
# Line 69  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 85  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 99  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 121  Line 134 
134  and 10999.  and 10999.
135    
136  =cut  =cut
137    #: 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 136  Line 149 
149  we generally only need a few sequences in memory rather than the entire contig.  we generally only need a few sequences in memory rather than the entire contig.
150    
151  =cut  =cut
152    #: 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 231  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 268  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 305  Line 312 
312  =back  =back
313    
314  =cut  =cut
315    #: 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 340  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 378  Line 375 
375  =back  =back
376    
377  =cut  =cut
378    #: 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 422  Line 418 
418  =back  =back
419    
420  =cut  =cut
421    #: 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 437  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 459  Line 455 
455  changed.  changed.
456    
457  =cut  =cut
458    #: 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 474  Line 470 
470  Return a list of all the genome IDs.  Return a list of all the genome IDs.
471    
472  =cut  =cut
473    #: 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 504  Line 500 
500  =back  =back
501    
502  =cut  =cut
503    #: 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 541  Line 536 
536  =back  =back
537    
538  =cut  =cut
539    #: 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 589  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    
590  =cut  =cut
591    #: Return Type @;
592    #: 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]);                                                     [$featureID]);
# Line 616  Line 610 
610                  if ($prevContig eq $contigID && $dir eq $prevDir) {                  if ($prevContig eq $contigID && $dir eq $prevDir) {
611                          # Here the new segment is in the same direction on the same contig. Insure the                          # Here the new segment is in the same direction on the same contig. Insure the
612                          # new segment's beginning is next to the old segment's end.                          # new segment's beginning is next to the old segment's end.
613                          if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
614                                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
615                                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
616                                  # to include both segments.                  $len += $prevLen;
617                    # Pop the old segment off. The new one will replace it later.
618                    pop @retVal;
619                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
620                    # Here we need to merge two forward blocks. Adjust the beginning and
621                    # length values to include both segments.
622                                  $beg = $prevBeg;                                  $beg = $prevBeg;
623                                  $len += $prevLen;                                  $len += $prevLen;
624                                  # Pop the old segment off. The new one will replace it later.                                  # Pop the old segment off. The new one will replace it later.
# Line 628  Line 627 
627                  }                  }
628                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
629                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
630            # Compute the initial base pair.
631            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
632                  # Add the specifier to the list.                  # Add the specifier to the list.
633                  push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
634          }          }
635          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
636          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
637  }  }
638    
639  =head3 ParseLocation  =head3 ParseLocation
# Line 656  Line 657 
657  =back  =back
658    
659  =cut  =cut
660    #: Return Type @;
661  sub ParseLocation {  sub ParseLocation {
662          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
663        # the first parameter.
664        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
665          my ($location) = @_;          my ($location) = @_;
666          # Parse it into segments.          # Parse it into segments.
667          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
668          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
669          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
670          if ($dir eq "_") {          if ($dir eq "_") {
# Line 677  Line 680 
680          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
681  }  }
682    
683    =head3 PointLocation
684    
685    C<< my $found = Sprout::PointLocation($location, $point); >>
686    
687    Return the offset into the specified location of the specified point on the contig. If
688    the specified point is before the location, a negative value will be returned. If it is
689    beyond the location, an undefined value will be returned. It is assumed that the offset
690    is for the location's contig. The location can either be new-style (using a C<+> or C<->
691    and a length) or old-style (using C<_> and start and end positions.
692    
693    =over 4
694    
695    =item location
696    
697    A location specifier (see L</FeatureLocation> for a description).
698    
699    =item point
700    
701    The offset into the contig of the point in which we're interested.
702    
703    =item RETURN
704    
705    Returns the offset inside the specified location of the specified point, a negative
706    number if the point is before the location, or an undefined value if the point is past
707    the location. If the length of the location is 0, this method will B<always> denote
708    that it is outside the location. The offset will always be relative to the left-most
709    position in the location.
710    
711    =back
712    
713    =cut
714    #: Return Type $;
715    sub PointLocation {
716        # Get the parameter. Note that if we're called as an instance method, we ignore
717        # the first parameter.
718        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
719        my ($location, $point) = @_;
720        # Parse out the location elements. Note that this works on both old-style and new-style
721        # locations.
722        my ($contigID, $start, $dir, $len) = ParseLocation($location);
723        # Declare the return variable.
724        my $retVal;
725        # Compute the offset. The computation is dependent on the direction of the location.
726        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
727        # Return the offset if it's valid.
728        if ($offset < $len) {
729            $retVal = $offset;
730        }
731        # Return the offset found.
732        return $retVal;
733    }
734    
735  =head3 DNASeq  =head3 DNASeq
736    
737  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
738    
739  This method returns the DNA sequence represented by a list of locations. The list of locations  This method returns the DNA sequence represented by a list of locations. The list of locations
740  should be of the form returned by L</feature_location> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
741  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
742    
743  =over 4  =over 4
# Line 699  Line 754 
754  =back  =back
755    
756  =cut  =cut
757    #: Return Type $;
758  sub DNASeq {  sub DNASeq {
759          # Get the parameters.          # Get the parameters.
760          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
761          # Create the return string.          # Create the return string.
762          my $retVal = "";          my $retVal = "";
763          # Loop through the locations.          # Loop through the locations.
# Line 718  Line 772 
772                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
773                  # before putting it in the return value.                  # before putting it in the return value.
774                  my ($start, $stop);                  my ($start, $stop);
775            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
776                  if ($dir eq "+") {                  if ($dir eq "+") {
777                          $start = $beg;                          $start = $beg;
778                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
779                  } else {                  } else {
780                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
781                          $stop = $beg;                          $stop = $beg;
782                  }                  }
783            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
784                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
785                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
786                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 736  Line 792 
792                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
793                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
794                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
795                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
796                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
797                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
798                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
799                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
800                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
801                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
802                  }                  }
803                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
804                  if ($dir eq '+') {                  if ($dir eq '+') {
805                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
806                  } else {                  } else {
807                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
808                  }                  }
809          }          }
810          # Return the result.          # Return the result.
# Line 773  Line 830 
830  =back  =back
831    
832  =cut  =cut
833    #: Return Type @;
834  sub AllContigs {  sub AllContigs {
835          # Get the parameters.          # Get the parameters.
836          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
837          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
838          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
839                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 797  Line 853 
853    
854  ID of the contig whose length is desired.  ID of the contig whose length is desired.
855    
856    =item RETURN
857    
858    Returns the number of positions in the contig.
859    
860  =back  =back
861    
862  =cut  =cut
863    #: Return Type $;
864  sub ContigLength {  sub ContigLength {
865          # Get the parameters.          # Get the parameters.
866          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
867          # Get the contig's last sequence.          # Get the contig's last sequence.
868          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
869                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 815  Line 874 
874          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
875          if ($sequence) {          if ($sequence) {
876                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
877                  $retVal = $start + $len;          $retVal = $start + $len - 1;
878        }
879        # Return the result.
880        return $retVal;
881    }
882    
883    =head3 ClusterPEGs
884    
885    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
886    
887    Cluster the PEGs in a list according to the cluster coding scheme of the specified
888    subsystem. In order for this to work properly, the subsystem object must have
889    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
890    This causes the cluster numbers to be pulled into the subsystem's color hash.
891    If a PEG is not found in the color hash, it will not appear in the output
892    sequence.
893    
894    =over 4
895    
896    =item sub
897    
898    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
899    method.
900    
901    =item pegs
902    
903    Reference to the list of PEGs to be clustered.
904    
905    =item RETURN
906    
907    Returns a list of the PEGs, grouped into smaller lists by cluster number.
908    
909    =back
910    
911    =cut
912    #: Return Type $@@;
913    sub ClusterPEGs {
914        # Get the parameters.
915        my ($self, $sub, $pegs) = @_;
916        # Declare the return variable.
917        my $retVal = [];
918        # Loop through the PEGs, creating arrays for each cluster.
919        for my $pegID (@{$pegs}) {
920            my $clusterNumber = $sub->get_cluster_number($pegID);
921            # Only proceed if the PEG is in a cluster.
922            if ($clusterNumber >= 0) {
923                # Push this PEG onto the sub-list for the specified cluster number.
924                push @{$retVal->[$clusterNumber]}, $pegID;
925            }
926          }          }
927          # Return the result.          # Return the result.
928          return $retVal;          return $retVal;
# Line 846  Line 953 
953  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
954  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
955  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
956  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
957    roughly by location.
958    
959  =back  =back
960    
961  =cut  =cut
962    #: Return Type @@;
963  sub GenesInRegion {  sub GenesInRegion {
964          # Get the parameters.          # Get the parameters.
965          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
966          # Get the maximum segment length.          # Get the maximum segment length.
967          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
968          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
969          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
970        # containing the minimum and maximum offsets. We will use the offsets to sort the results
971        # when we're building the result set.
972          my %featuresFound = ();          my %featuresFound = ();
973          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
974          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
975        my ($min, $max) = @initialMinMax;
976          # 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
977          # 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,
978          # 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 892  Line 1002 
1002                                          $found = 1;                                          $found = 1;
1003                                  }                                  }
1004                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
1005                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
1006                                  if ($end <= $stop) {                  # ending.
1007                    ($beg, $end) = ($beg - $len, $beg);
1008                    if ($beg <= $stop) {
1009                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
1010                                          $found = 1;                                          $found = 1;
1011                                  }                                  }
1012                          }                          }
1013                          if ($found) {                          if ($found) {
1014                                  # 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,
1015                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
1016                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
1017                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
1018                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
1019                                  if ($end > $max) { $max = $end; }                  # global min and max.
1020                    if ($beg < $loc1) {
1021                        $loc1 = $beg;
1022                        $min = $beg if $beg < $min;
1023                    }
1024                    if ($end > $loc2) {
1025                        $loc2 = $end;
1026                        $max = $end if $end > $max;
1027                    }
1028                    # Store the entry back into the hash table.
1029                    $featuresFound{$featureID} = [$loc1, $loc2];
1030                          }                          }
1031                  }                  }
1032          }          }
1033          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
1034          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1035        # but the result of the sort will be the same.)
1036        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
1037        # Now we sort by midpoint and yank out the feature IDs.
1038        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1039          # Return it along with the min and max.          # Return it along with the min and max.
1040          return (\@list, $min, $max);      return (\@retVal, $min, $max);
1041  }  }
1042    
1043  =head3 FType  =head3 FType
# Line 934  Line 1060 
1060  =back  =back
1061    
1062  =cut  =cut
1063    #: Return Type $;
1064  sub FType {  sub FType {
1065          # Get the parameters.          # Get the parameters.
1066          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1067          # Get the specified feature's type.          # Get the specified feature's type.
1068          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1069          # Return the result.          # Return the result.
# Line 947  Line 1072 
1072    
1073  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1074    
1075  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1076    
1077  Return the annotations of a feature.  Return the annotations of a feature.
1078    
# Line 957  Line 1082 
1082    
1083  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1084    
1085    =item rawFlag
1086    
1087    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1088    will be returned in human-readable form.
1089    
1090  =item RETURN  =item RETURN
1091    
1092  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
# Line 972  Line 1102 
1102  =back  =back
1103    
1104  =cut  =cut
1105    #: Return Type @%;
1106  sub FeatureAnnotations {  sub FeatureAnnotations {
1107          # Get the parameters.          # Get the parameters.
1108          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1109          # 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.
1110          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1111                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 989  Line 1118 
1118                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1119                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1120                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1121            # Convert the time, if necessary.
1122            if (! $rawFlag) {
1123                $timeStamp = FriendlyTimestamp($timeStamp);
1124            }
1125                  # Assemble them into a hash.                  # Assemble them into a hash.
1126                  my $annotationHash = { featureID => $featureID, timeStamp => $timeStamp,          my $annotationHash = { featureID => $featureID,
1127                                   timeStamp => $timeStamp,
1128                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1129                  # Add it to the return list.                  # Add it to the return list.
1130                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1004  Line 1138 
1138  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1139    
1140  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
1141  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,
1142  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
1143  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,
1144  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.
1145  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1146    recent one.
1147    
1148  =over 4  =over 4
1149    
# Line 1016  Line 1151 
1151    
1152  ID of the feature whose functional assignments are desired.  ID of the feature whose functional assignments are desired.
1153    
1154    =item RETURN
1155    
1156    Returns a hash mapping the functional assignment IDs to user IDs.
1157    
1158  =back  =back
1159    
1160  =cut  =cut
1161    #: Return Type %;
1162  sub AllFunctionsOf {  sub AllFunctionsOf {
1163          # Get the parameters.          # Get the parameters.
1164          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1165          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1166          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1167                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1168                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);
1169          # Declare the return hash.          # Declare the return hash.
1170          my %retVal;          my %retVal;
1171        # Declare a hash for insuring we only make one assignment per user.
1172        my %timeHash = ();
1173        # Now we sort the assignments by timestamp in reverse.
1174        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1175          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1176          for my $text (@query) {      for my $annotation (@sortedQuery) {
1177            # Get the annotation fields.
1178            my ($timeStamp, $text) = @{$annotation};
1179                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1180                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1181                  if ($user) {          if ($user && ! exists $timeHash{$user}) {
1182                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1183                # previous assignment for this user, so we stuff it in the
1184                # return hash.
1185                          $retVal{$function} = $user;                          $retVal{$function} = $user;
1186                # Insure we don't assign to this user again.
1187                $timeHash{$user} = 1;
1188                  }                  }
1189          }          }
1190          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1047  Line 1195 
1195    
1196  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>
1197    
1198  Return the most recently-determined functional assignment of a particular feature. A functional  Return the most recently-determined functional assignment of a particular feature.
1199  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  
1200  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  The functional assignment is handled differently depending on the type of feature. If
1201  we cannot filter on the content of the annotation itself because it's a text field; however, this  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1202  is not a big problem because most features only have a small number of annotations.  assignment is a type of annotation. The format of an assignment is described in
1203    L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1204    annotation itself because it's a text field; however, this is not a big problem because
1205    most features only have a small number of annotations.
1206    
1207    Each user has an associated list of trusted users. The assignment returned will be the most
1208    recent one by at least one of the trusted users. If no trusted user list is available, then
1209    the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1210    is trusted.
1211    
1212    If the feature is B<not> identified by a FIG ID, then the functional assignment
1213    information is taken from the B<ExternalAliasFunc> table. If the table does
1214    not contain an entry for the feature, an undefined value is returned.
1215    
1216  =over 4  =over 4
1217    
# Line 1061  Line 1221 
1221    
1222  =item userID (optional)  =item userID (optional)
1223    
1224  ID of the user whose function determination is desired. If omitted, C<FIG> is assumed.  ID of the user whose function determination is desired. If omitted, only the latest
1225    C<FIG> assignment will be returned.
1226    
1227  =item RETURN  =item RETURN
1228    
# Line 1070  Line 1231 
1231  =back  =back
1232    
1233  =cut  =cut
1234    #: Return Type $;
1235  sub FunctionOf {  sub FunctionOf {
1236          # Get the parameters.          # Get the parameters.
1237          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
1238          my ($featureID, $userID) = @_;      # Declare the return value.
         if (!$userID) { $userID = 'FIG'; }  
         # Build a query for all of the feature's annotation, sorted by date.  
         my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],  
                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);  
         # Declare the return value. We'll set this to the most recent annotation for the  
         # specified user.  
1239          my $retVal;          my $retVal;
1240        # Determine the ID type.
1241        if ($featureID =~ m/^fig\|/) {
1242            # Here we have a FIG feature ID. We must build the list of trusted
1243            # users.
1244            my %trusteeTable = ();
1245            # Check the user ID.
1246            if (!$userID) {
1247                # No user ID, so only FIG is trusted.
1248                $trusteeTable{FIG} = 1;
1249            } else {
1250                # Add this user's ID.
1251                $trusteeTable{$userID} = 1;
1252                # Look for the trusted users in the database.
1253                my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)');
1254                if (! @trustees) {
1255                    # None were found, so build a default list.
1256                    $trusteeTable{FIG} = 1;
1257                } else {
1258                    # Otherwise, put all the trustees in.
1259                    for my $trustee (@trustees) {
1260                        $trusteeTable{$trustee} = 1;
1261                    }
1262                }
1263            }
1264            # Build a query for all of the feature's annotations, sorted by date.
1265            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],
1266                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1267                                   [$featureID]);
1268          my $timeSelected = 0;          my $timeSelected = 0;
1269          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1270          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1271                  # Get the annotation text.                  # Get the annotation text.
1272                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1273                  # Check to see if this is a functional assignment for the desired user.              # Check to see if this is a functional assignment for a trusted user.
1274                  my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1275                  if ($type =~ m/^set $userID function to$/i) {              if ($user) {
1276                          # Here it is, so we check the time and save the assignment value.                  # Here it is a functional assignment. Check the time and the user
1277                          if ($time > $timeSelected) {                  # name. The time must be recent and the user must be trusted.
1278                    if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
1279                                  $retVal = $function;                                  $retVal = $function;
1280                                  $timeSelected = $time;                                  $timeSelected = $time;
1281                          }                          }
1282                  }                  }
1283          }          }
1284        } else {
1285            # Here we have a non-FIG feature ID. In this case the user ID does not
1286            # matter. We simply get the information from the External Alias Function
1287            # table.
1288            ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);
1289        }
1290          # Return the assignment found.          # Return the assignment found.
1291          return $retVal;          return $retVal;
1292  }  }
# Line 1120  Line 1310 
1310    
1311  =item RETURN  =item RETURN
1312    
1313  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
1314  their best hits.  on the target genome.
1315    
1316  =back  =back
1317    
1318  =cut  =cut
1319    #: Return Type %;
1320  sub BBHList {  sub BBHList {
1321          # Get the parameters.          # Get the parameters.
1322          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1323          # Create the return structure.          # Create the return structure.
1324          my %retVal = ();          my %retVal = ();
1325          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1139  Line 1328 
1328                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1329                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1330                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1331                  # Look for the best hit.          # Peel off the BBHs found.
1332                  my $bbh = $query->Fetch;          my @found = ();
1333                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1334                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1335                  }                  }
1336            $retVal{$featureID} = \@found;
1337          }          }
1338          # Return the mapping.          # Return the mapping.
1339          return \%retVal;          return \%retVal;
1340  }  }
1341    
1342    =head3 SimList
1343    
1344    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1345    
1346    Return a list of the similarities to the specified feature.
1347    
1348    Sprout does not support real similarities, so this method just returns the bidirectional
1349    best hits.
1350    
1351    =over 4
1352    
1353    =item featureID
1354    
1355    ID of the feature whose similarities are desired.
1356    
1357    =item count
1358    
1359    Maximum number of similar features to be returned, or C<0> to return them all.
1360    
1361    =back
1362    
1363    =cut
1364    #: Return Type %;
1365    sub SimList {
1366        # Get the parameters.
1367        my ($self, $featureID, $count) = @_;
1368        # Ask for the best hits.
1369        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1370                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1371                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1372                                  $count);
1373        # Create the return value.
1374        my %retVal = ();
1375        for my $tuple (@lists) {
1376            $retVal{$tuple->[0]} = $tuple->[1];
1377        }
1378        # Return the result.
1379        return %retVal;
1380    }
1381    
1382    
1383    
1384    =head3 IsComplete
1385    
1386    C<< my $flag = $sprout->IsComplete($genomeID); >>
1387    
1388    Return TRUE if the specified genome is complete, else FALSE.
1389    
1390    =over 4
1391    
1392    =item genomeID
1393    
1394    ID of the genome whose completeness status is desired.
1395    
1396    =item RETURN
1397    
1398    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1399    not found.
1400    
1401    =back
1402    
1403    =cut
1404    #: Return Type $;
1405    sub IsComplete {
1406        # Get the parameters.
1407        my ($self, $genomeID) = @_;
1408        # Declare the return variable.
1409        my $retVal;
1410        # Get the genome's data.
1411        my $genomeData = $self->GetEntity('Genome', $genomeID);
1412        if ($genomeData) {
1413            # The genome exists, so get the completeness flag.
1414            ($retVal) = $genomeData->Value('complete');
1415        }
1416        # Return the result.
1417        return $retVal;
1418    }
1419    
1420  =head3 FeatureAliases  =head3 FeatureAliases
1421    
1422  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1170  Line 1437 
1437  =back  =back
1438    
1439  =cut  =cut
1440    #: Return Type @;
1441  sub FeatureAliases {  sub FeatureAliases {
1442          # Get the parameters.          # Get the parameters.
1443          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1444          # Get the desired feature's aliases          # Get the desired feature's aliases
1445          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1446          # Return the result.          # Return the result.
# Line 1201  Line 1467 
1467  =back  =back
1468    
1469  =cut  =cut
1470    #: Return Type $;
1471  sub GenomeOf {  sub GenomeOf {
1472          # Get the parameters.          # Get the parameters.
1473          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1474          # Create a query to find the genome associated with the feature.          # Create a query to find the genome associated with the feature.
1475          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1476          # Declare the return value.          # Declare the return value.
# Line 1238  Line 1503 
1503  =back  =back
1504    
1505  =cut  =cut
1506    #: Return Type %;
1507  sub CoupledFeatures {  sub CoupledFeatures {
1508          # Get the parameters.          # Get the parameters.
1509          my $self = shift @_;      my ($self, $featureID) = @_;
1510          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1511          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1512          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1513          # 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.
1514          my $found = 0;          my $found = 0;
1515          # Create the return hash.          # Create the return hash.
1516          my %retVal = ();          my %retVal = ();
1517          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1518          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1519                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1520                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1521                                                            'Coupling(score)']);
1522            # The coupling ID contains the two feature IDs separated by a space. We use
1523            # this information to find the ID of the other feature.
1524            my ($fid1, $fid2) = split / /, $couplingID;
1525            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1526            # Attach the other feature's score to its ID.
1527                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1528                  $found = 1;                  $found = 1;
1529          }          }
# Line 1268  Line 1536 
1536          return %retVal;          return %retVal;
1537  }  }
1538    
1539    =head3 CouplingEvidence
1540    
1541    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1542    
1543    Return the evidence for a functional coupling.
1544    
1545    A pair of features is considered evidence of a coupling between two other
1546    features if they occur close together on a contig and both are similar to
1547    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1548    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1549    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1550    similar to B<A2>.
1551    
1552    The score of a coupling is determined by the number of pieces of evidence
1553    that are considered I<representative>. If several evidence items belong to
1554    a group of genomes that are close to each other, only one of those items
1555    is considered representative. The other evidence items are presumed to be
1556    there because of the relationship between the genomes rather than because
1557    the two proteins generated by the features have a related functionality.
1558    
1559    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1560    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1561    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1562    and FALSE otherwise.
1563    
1564    =over 4
1565    
1566    =item peg1
1567    
1568    ID of the feature of interest.
1569    
1570    =item peg2
1571    
1572    ID of a feature functionally coupled to the feature of interest.
1573    
1574    =item RETURN
1575    
1576    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1577    of interest, a feature similar to the functionally coupled feature, and a flag
1578    that is TRUE for a representative piece of evidence and FALSE otherwise.
1579    
1580    =back
1581    
1582    =cut
1583    #: Return Type @@;
1584    sub CouplingEvidence {
1585        # Get the parameters.
1586        my ($self, $peg1, $peg2) = @_;
1587        # Declare the return variable.
1588        my @retVal = ();
1589        # Our first task is to find out the nature of the coupling: whether or not
1590        # it exists, its score, and whether the features are stored in the same
1591        # order as the ones coming in.
1592        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1593        # Only proceed if a coupling exists.
1594        if ($couplingID) {
1595            # Determine the ordering to place on the evidence items. If we're
1596            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1597            # we want feature 1 before feature 2 (normal).
1598            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1599            my $ordering = ($inverted ? "DESC" : "");
1600            # Get the coupling evidence.
1601            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1602                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1603                                              [$couplingID],
1604                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1605            # Loop through the evidence items. Each piece of evidence is represented by two
1606            # positions in the evidence list, one for each feature on the other side of the
1607            # evidence link. If at some point we want to generalize to couplings with
1608            # more than two positions, this section of code will need to be re-done.
1609            while (@evidenceList > 0) {
1610                my $peg1Data = shift @evidenceList;
1611                my $peg2Data = shift @evidenceList;
1612                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1613                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1614            }
1615            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1616        }
1617        # Return the result.
1618        return @retVal;
1619    }
1620    
1621    =head3 GetCoupling
1622    
1623    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1624    
1625    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1626    exists, we return the coupling ID along with an indicator of whether the
1627    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1628    In the second case, we say the coupling is I<inverted>. The importance of an
1629    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1630    
1631    =over 4
1632    
1633    =item peg1
1634    
1635    ID of the feature of interest.
1636    
1637    =item peg2
1638    
1639    ID of the potentially coupled feature.
1640    
1641    =item RETURN
1642    
1643    Returns a three-element list. The first element contains the database ID of
1644    the coupling. The second element is FALSE if the coupling is stored in the
1645    database in the caller specified order and TRUE if it is stored in the
1646    inverted order. The third element is the coupling's score. If the coupling
1647    does not exist, all three list elements will be C<undef>.
1648    
1649    =back
1650    
1651    =cut
1652    #: Return Type $%@;
1653    sub GetCoupling {
1654        # Get the parameters.
1655        my ($self, $peg1, $peg2) = @_;
1656        # Declare the return values. We'll start with the coupling ID and undefine the
1657        # flag and score until we have more information.
1658        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1659        # Find the coupling data.
1660        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1661                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1662                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1663        # Check to see if we found anything.
1664        if (!@pegs) {
1665            Trace("No coupling found.") if T(Coupling => 4);
1666            # No coupling, so undefine the return value.
1667            $retVal = undef;
1668        } else {
1669            # We have a coupling! Get the score and check for inversion.
1670            $score = $pegs[0]->[1];
1671            my $firstFound = $pegs[0]->[0];
1672            $inverted = ($firstFound ne $peg1);
1673            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1674        }
1675        # Return the result.
1676        return ($retVal, $inverted, $score);
1677    }
1678    
1679    =head3 CouplingID
1680    
1681    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1682    
1683    Return the coupling ID for a pair of feature IDs.
1684    
1685    The coupling ID is currently computed by joining the feature IDs in
1686    sorted order with a space. Client modules (that is, modules which
1687    use Sprout) should not, however, count on this always being the
1688    case. This method provides a way for abstracting the concept of a
1689    coupling ID. All that we know for sure about it is that it can be
1690    generated easily from the feature IDs and the order of the IDs
1691    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1692    will have the same value as C<CouplingID("b1", "a1")>.
1693    
1694    =over 4
1695    
1696    =item peg1
1697    
1698    First feature of interest.
1699    
1700    =item peg2
1701    
1702    Second feature of interest.
1703    
1704    =item RETURN
1705    
1706    Returns the ID that would be used to represent a functional coupling of
1707    the two specified PEGs.
1708    
1709    =back
1710    
1711    =cut
1712    #: Return Type $;
1713    sub CouplingID {
1714        return join " ", sort @_;
1715    }
1716    
1717  =head3 GetEntityTypes  =head3 GetEntityTypes
1718    
1719  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1275  Line 1721 
1721  Return the list of supported entity types.  Return the list of supported entity types.
1722    
1723  =cut  =cut
1724    #: Return Type @;
1725  sub GetEntityTypes {  sub GetEntityTypes {
1726          # Get the parameters.          # Get the parameters.
1727          my $self = shift @_;      my ($self) = @_;
1728          # Get the underlying database object.          # Get the underlying database object.
1729          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1730          # Get its entity type list.          # Get its entity type list.
# Line 1310  Line 1756 
1756  =back  =back
1757    
1758  =cut  =cut
1759    #: Return Type %;
1760  sub ReadFasta {  sub ReadFasta {
1761          # Get the parameters.          # Get the parameters.
1762          my ($fileName, $prefix) = @_;          my ($fileName, $prefix) = @_;
# Line 1329  Line 1775 
1775                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1776                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1777                          if ($id) {                          if ($id) {
1778                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1779                          }                          }
1780                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1781                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1782                  } else {                  } else {
1783                          # 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.
1784                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1785                # case.
1786                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1787                          $sequence .= $1;                          $sequence .= $1;
1788                  }                  }
1789          }          }
1790          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1791          if ($sequence) {          if ($sequence) {
1792                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1793          }          }
1794        # Close the file.
1795        close FASTAFILE;
1796          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1797          return %retVal;          return %retVal;
1798  }  }
# Line 1354  Line 1803 
1803    
1804  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
1805  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
1806  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,
1807    it will not be changed; otherwise, it will be converted. This method can also be used to
1808    perform the reverse task-- insuring that all the locations are in the old format.
1809    
1810  =over 4  =over 4
1811    
# Line 1378  Line 1829 
1829  =back  =back
1830    
1831  =cut  =cut
1832    #: Return Type @;
1833  sub FormatLocations {  sub FormatLocations {
1834          # Get the parameters.          # Get the parameters.
1835          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1836          # Create the return list.          # Create the return list.
1837          my @retVal = ();          my @retVal = ();
1838          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1839          if ($locations eq '') {          if ($locations eq '') {
1840              confess "No locations specified.";          Confess("No locations specified.");
1841          } else {          } else {
1842                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1843                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1422  Line 1872 
1872    
1873  sub DumpData {  sub DumpData {
1874          # Get the parameters.          # Get the parameters.
1875          my $self = shift @_;      my ($self) = @_;
1876          # Get the data directory name.          # Get the data directory name.
1877          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1878          # Dump the relations.          # Dump the relations.
# Line 1436  Line 1886 
1886  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
1887    
1888  =cut  =cut
1889    #: Return Type $;
1890  sub XMLFileName {  sub XMLFileName {
1891          my $self = shift @_;      my ($self) = @_;
1892          return $self->{_xmlName};          return $self->{_xmlName};
1893  }  }
1894    
# Line 1458  Line 1908 
1908  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
1909  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>.
1910    
1911  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'}); >>
1912    
1913  =over 4  =over 4
1914    
# Line 1473  Line 1923 
1923  =back  =back
1924    
1925  =cut  =cut
1926    #: Return Type ;
1927  sub Insert {  sub Insert {
1928          # Get the parameters.          # Get the parameters.
1929          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1930          # Call the underlying method.          # Call the underlying method.
1931          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1932  }  }
# Line 1515  Line 1964 
1964  =back  =back
1965    
1966  =cut  =cut
1967    #: Return Type $;
1968  sub Annotate {  sub Annotate {
1969          # Get the parameters.          # Get the parameters.
1970          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1971          # Create the annotation ID.          # Create the annotation ID.
1972          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1973          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1539  Line 1987 
1987    
1988  =head3 AssignFunction  =head3 AssignFunction
1989    
1990  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1991    
1992  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
1993  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.  
1994    
1995  =over 4  =over 4
1996    
# Line 1553  Line 2000 
2000    
2001  =item user  =item user
2002    
2003  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>.
2004    
2005  =item function  =item function
2006    
2007  Text of the function being assigned.  Text of the function being assigned.
2008    
2009    =item assigningUser (optional)
2010    
2011    Name of the individual user making the assignment. If omitted, defaults to the user group.
2012    
2013  =item RETURN  =item RETURN
2014    
2015  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1566  Line 2017 
2017  =back  =back
2018    
2019  =cut  =cut
2020    #: Return Type $;
2021  sub AssignFunction {  sub AssignFunction {
2022          # Get the parameters.          # Get the parameters.
2023          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2024          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2025        if (! $assigningUser) {
2026            $assigningUser = $user;
2027        }
2028          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2029          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2030          # Get the current time.          # Get the current time.
2031          my $now = time;          my $now = time;
2032          # Declare the return variable.          # Declare the return variable.
# Line 1614  Line 2068 
2068  =back  =back
2069    
2070  =cut  =cut
2071    #: Return Type @;
2072  sub FeaturesByAlias {  sub FeaturesByAlias {
2073          # Get the parameters.          # Get the parameters.
2074          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2075          # Declare the return variable.          # Declare the return variable.
2076          my @retVal = ();          my @retVal = ();
2077          # Parse the alias.          # Parse the alias.
# Line 1657  Line 2110 
2110  =back  =back
2111    
2112  =cut  =cut
2113    #: Return Type $;
2114  sub Exists {  sub Exists {
2115          # Get the parameters.          # Get the parameters.
2116          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2117          # Check for the entity instance.          # Check for the entity instance.
2118        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2119          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2120          # Return an existence indicator.          # Return an existence indicator.
2121          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1688  Line 2141 
2141  =back  =back
2142    
2143  =cut  =cut
2144    #: Return Type $;
2145  sub FeatureTranslation {  sub FeatureTranslation {
2146          # Get the parameters.          # Get the parameters.
2147          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2148          # Get the specified feature's translation.          # Get the specified feature's translation.
2149          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2150          return $retVal;          return $retVal;
# Line 1721  Line 2173 
2173  =back  =back
2174    
2175  =cut  =cut
2176    #: Return Type @;
2177  sub Taxonomy {  sub Taxonomy {
2178          # Get the parameters.          # Get the parameters.
2179          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2180          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2181          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2182          # Declare the return variable.          # Declare the return variable.
# Line 1765  Line 2216 
2216  =back  =back
2217    
2218  =cut  =cut
2219    #: Return Type $;
2220  sub CrudeDistance {  sub CrudeDistance {
2221          # Get the parameters.          # Get the parameters.
2222          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2223          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2224          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2225          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1813  Line 2263 
2263  =back  =back
2264    
2265  =cut  =cut
2266    #: Return Type $;
2267  sub RoleName {  sub RoleName {
2268          # Get the parameters.          # Get the parameters.
2269          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2270          # Get the specified role's name.          # Get the specified role's name.
2271          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2272          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1847  Line 2296 
2296  =back  =back
2297    
2298  =cut  =cut
2299    #: Return Type @;
2300  sub RoleDiagrams {  sub RoleDiagrams {
2301          # Get the parameters.          # Get the parameters.
2302          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2303          # Query for the diagrams.          # Query for the diagrams.
2304          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2305                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1859  Line 2307 
2307          return @retVal;          return @retVal;
2308  }  }
2309    
2310    =head3 GetProperties
2311    
2312    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2313    
2314    Return a list of the properties with the specified characteristics.
2315    
2316    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2317    will also be associated with genomes.) A property value is represented by a 4-tuple of
2318    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2319    
2320    =over 4
2321    
2322    =item fid
2323    
2324    ID of the feature possessing the property.
2325    
2326    =item key
2327    
2328    Name or key of the property.
2329    
2330    =item value
2331    
2332    Value of the property.
2333    
2334    =item url
2335    
2336    URL of the document that indicated the property should have this particular value, or an
2337    empty string if no such document exists.
2338    
2339    =back
2340    
2341    The parameters act as a filter for the desired data. Any non-null parameter will
2342    automatically match all the tuples returned. So, specifying just the I<$fid> will
2343    return all the properties of the specified feature; similarly, specifying the I<$key>
2344    and I<$value> parameters will return all the features having the specified property
2345    value.
2346    
2347    A single property key can have many values, representing different ideas about the
2348    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2349    virulent, and another may declare that it is not virulent. A query about the virulence of
2350    C<fig|83333.1.peg.10> would be coded as
2351    
2352        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2353    
2354    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2355    not to be filtered. The tuples returned would be
2356    
2357        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2358        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2359    
2360    =cut
2361    #: Return Type @@;
2362    sub GetProperties {
2363        # Get the parameters.
2364        my ($self, @parms) = @_;
2365        # Declare the return variable.
2366        my @retVal = ();
2367        # Now we need to create a WHERE clause that will get us the data we want. First,
2368        # we create a list of the columns containing the data for each parameter.
2369        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2370                        'Property(property-value)', 'HasProperty(evidence)');
2371        # Now we build the WHERE clause and the list of parameter values.
2372        my @where = ();
2373        my @values = ();
2374        for (my $i = 0; $i <= $#colNames; $i++) {
2375            my $parm = $parms[$i];
2376            if (defined $parm && ($parm ne '')) {
2377                push @where, "$colNames[$i] = ?";
2378                push @values, $parm;
2379            }
2380        }
2381        # Format the WHERE clause.
2382        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2383        # Ask for all the propertie values with the desired characteristics.
2384        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2385        while (my $valueObject = $query->Fetch()) {
2386            my @tuple = $valueObject->Values(\@colNames);
2387            push @retVal, \@tuple;
2388        }
2389        # Return the result.
2390        return @retVal;
2391    }
2392    
2393  =head3 FeatureProperties  =head3 FeatureProperties
2394    
2395  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1885  Line 2416 
2416  =back  =back
2417    
2418  =cut  =cut
2419    #: Return Type @@;
2420  sub FeatureProperties {  sub FeatureProperties {
2421          # Get the parameters.          # Get the parameters.
2422          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2423          # Get the properties.          # Get the properties.
2424          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2425                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1917  Line 2447 
2447  =back  =back
2448    
2449  =cut  =cut
2450    #: Return Type $;
2451  sub DiagramName {  sub DiagramName {
2452          # Get the parameters.          # Get the parameters.
2453          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2454          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2455          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2456          return $retVal;          return $retVal;
# Line 1950  Line 2479 
2479  =back  =back
2480    
2481  =cut  =cut
2482    #: Return Type @;
2483  sub MergedAnnotations {  sub MergedAnnotations {
2484          # Get the parameters.          # Get the parameters.
2485          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2486          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2487          my @tuples = ();          my @tuples = ();
2488          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 1969  Line 2497 
2497          }          }
2498          # Sort the result list by timestamp.          # Sort the result list by timestamp.
2499          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;
2500        # Loop through and make the time stamps friendly.
2501        for my $tuple (@retVal) {
2502            $tuple->[1] = FriendlyTimestamp($tuple->[1]);
2503        }
2504          # Return the sorted list.          # Return the sorted list.
2505          return @retVal;          return @retVal;
2506  }  }
# Line 1995  Line 2527 
2527  =back  =back
2528    
2529  =cut  =cut
2530    #: Return Type @;
2531  sub RoleNeighbors {  sub RoleNeighbors {
2532          # Get the parameters.          # Get the parameters.
2533          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2534          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2535          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2536                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2038  Line 2569 
2569  =back  =back
2570    
2571  =cut  =cut
2572    #: Return Type @;
2573  sub FeatureLinks {  sub FeatureLinks {
2574          # Get the parameters.          # Get the parameters.
2575          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2576          # Get the feature's links.          # Get the feature's links.
2577          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2578          # Return the feature's links.          # Return the feature's links.
# Line 2054  Line 2584 
2584  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2585    
2586  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
2587  to the role the feature performs.  to the roles the feature performs.
2588    
2589  =over 4  =over 4
2590    
# Line 2064  Line 2594 
2594    
2595  =item RETURN  =item RETURN
2596    
2597  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.
2598    
2599  =back  =back
2600    
2601  =cut  =cut
2602    #: Return Type %@;
2603  sub SubsystemsOf {  sub SubsystemsOf {
2604          # Get the parameters.          # Get the parameters.
2605          my $self = shift @_;      my ($self, $featureID) = @_;
2606          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2607          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2608                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2609                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2610          # Create the return value.          # Create the return value.
2611          my %retVal = ();          my %retVal = ();
2612        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2613        # in two spreadsheet cells.
2614        my %dupHash = ();
2615          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2616          for my $record (@subsystems) {          for my $record (@subsystems) {
2617                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2618            my ($subsys, $role) = @{$record};
2619            # Insure it's the first time for both.
2620            my $dupKey = "$subsys\n$role";
2621            if (! exists $dupHash{"$subsys\n$role"}) {
2622                $dupHash{$dupKey} = 1;
2623                push @{$retVal{$subsys}}, $role;
2624            }
2625          }          }
2626          # Return the hash.          # Return the hash.
2627          return %retVal;          return %retVal;
2628  }  }
2629    
2630    =head3 SubsystemList
2631    
2632    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2633    
2634    Return a list containing the names of the subsystems in which the specified
2635    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2636    subsystem names, not the roles.
2637    
2638    =over 4
2639    
2640    =item featureID
2641    
2642    ID of the feature whose subsystem names are desired.
2643    
2644    =item RETURN
2645    
2646    Returns a list of the names of the subsystems in which the feature participates.
2647    
2648    =back
2649    
2650    =cut
2651    #: Return Type @;
2652    sub SubsystemList {
2653        # Get the parameters.
2654        my ($self, $featureID) = @_;
2655        # Get the list of names.
2656        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2657                                    [$featureID], 'HasSSCell(from-link)');
2658        # Return the result.
2659        return @retVal;
2660    }
2661    
2662  =head3 RelatedFeatures  =head3 RelatedFeatures
2663    
2664  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2118  Line 2689 
2689  =back  =back
2690    
2691  =cut  =cut
2692    #: Return Type @;
2693  sub RelatedFeatures {  sub RelatedFeatures {
2694          # Get the parameters.          # Get the parameters.
2695          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2696          # 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.
2697          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2698                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2167  Line 2737 
2737  =back  =back
2738    
2739  =cut  =cut
2740    #: Return Type @;
2741  sub TaxonomySort {  sub TaxonomySort {
2742          # Get the parameters.          # Get the parameters.
2743          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2744          # Create the working hash table.          # Create the working hash table.
2745          my %hashBuffer = ();          my %hashBuffer = ();
2746          # Loop through the features.          # Loop through the features.
# Line 2180  Line 2749 
2749                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2750                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2751                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2752                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2753          }          }
2754          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2755          my @retVal = ();          my @retVal = ();
# Line 2250  Line 2815 
2815  =back  =back
2816    
2817  =cut  =cut
2818    #: Return Type @@;
2819  sub GetAll {  sub GetAll {
2820          # Get the parameters.          # Get the parameters.
2821          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2822          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2823          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2824          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++;  
         }  
2825          # Return the resulting list.          # Return the resulting list.
2826          return @retVal;          return @retVal;
2827  }  }
# Line 2312  Line 2863 
2863  =back  =back
2864    
2865  =cut  =cut
2866    #: Return Type @;
2867  sub GetFlat {  sub GetFlat {
2868          # Get the parameters.          # Get the parameters.
2869          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2870          # Construct the query.          # Construct the query.
2871          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2872          # Create the result list.          # Create the result list.
# Line 2423  Line 2973 
2973  to load the entire database.  to load the entire database.
2974    
2975  =cut  =cut
2976    #: Return Type @;
2977  sub LoadInfo {  sub LoadInfo {
2978          # Get the parameters.          # Get the parameters.
2979          my $self = shift @_;      my ($self) = @_;
2980          # 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.
2981          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2982          # Concatenate the table names.          # Concatenate the table names.
# Line 2460  Line 3010 
3010  =back  =back
3011    
3012  =cut  =cut
3013    #: Return Type %;
3014  sub LowBBHs {  sub LowBBHs {
3015          # Get the parsameters.          # Get the parsameters.
3016          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3017          # Create the return hash.          # Create the return hash.
3018          my %retVal = ();          my %retVal = ();
3019          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2480  Line 3029 
3029          return %retVal;          return %retVal;
3030  }  }
3031    
3032    =head3 GetGroups
3033    
3034    C<< my %groups = $sprout->GetGroups(\@groupList); >>
3035    
3036    Return a hash mapping each group to the IDs of the genomes in the group.
3037    A list of groups may be specified, in which case only those groups will be
3038    shown. Alternatively, if no parameter is supplied, all groups will be
3039    included. Genomes that are not in any group are omitted.
3040    
3041    =cut
3042    #: Return Type %@;
3043    sub GetGroups {
3044        # Get the parameters.
3045        my ($self, $groupList) = @_;
3046        # Declare the return value.
3047        my %retVal = ();
3048        # Determine whether we are getting all the groups or just some.
3049        if (defined $groupList) {
3050            # Here we have a group list. Loop through them individually,
3051            # getting a list of the relevant genomes.
3052            for my $group (@{$groupList}) {
3053                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",
3054                    [$group], "Genome(id)");
3055                $retVal{$group} = \@genomeIDs;
3056            }
3057        } else {
3058            # Here we need all of the groups. In this case, we run through all
3059            # of the genome records, putting each one found into the appropriate
3060            # group. Note that we use a filter clause to insure that only genomes
3061            # in groups are included in the return set.
3062            my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],
3063                                        ['Genome(id)', 'Genome(group-name)']);
3064            # Loop through the genomes found.
3065            for my $genome (@genomes) {
3066                # Pop this genome's ID off the current list.
3067                my @groups = @{$genome};
3068                my $genomeID = shift @groups;
3069                # Loop through the groups, adding the genome ID to each group's
3070                # list.
3071                for my $group (@groups) {
3072                    Tracer::AddToListMap(\%retVal, $group, $genomeID);
3073                }
3074            }
3075        }
3076        # Return the hash we just built.
3077        return %retVal;
3078    }
3079    
3080    =head3 MyGenomes
3081    
3082    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3083    
3084    Return a list of the genomes to be included in the Sprout.
3085    
3086    This method is provided for use during the Sprout load. It presumes the Genome load file has
3087    already been created. (It will be in the Sprout data directory and called either C<Genome>
3088    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3089    IDs.
3090    
3091    =over 4
3092    
3093    =item dataDir
3094    
3095    Directory containing the Sprout load files.
3096    
3097    =back
3098    
3099    =cut
3100    #: Return Type @;
3101    sub MyGenomes {
3102        # Get the parameters.
3103        my ($dataDir) = @_;
3104        # Compute the genome file name.
3105        my $genomeFileName = LoadFileName($dataDir, "Genome");
3106        # Extract the genome IDs from the files.
3107        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3108        # Return the result.
3109        return @retVal;
3110    }
3111    
3112    =head3 LoadFileName
3113    
3114    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3115    
3116    Return the name of the load file for the specified table in the specified data
3117    directory.
3118    
3119    =over 4
3120    
3121    =item dataDir
3122    
3123    Directory containing the Sprout load files.
3124    
3125    =item tableName
3126    
3127    Name of the table whose load file is desired.
3128    
3129    =item RETURN
3130    
3131    Returns the name of the file containing the load data for the specified table, or
3132    C<undef> if no load file is present.
3133    
3134    =back
3135    
3136    =cut
3137    #: Return Type $;
3138    sub LoadFileName {
3139        # Get the parameters.
3140        my ($dataDir, $tableName) = @_;
3141        # Declare the return variable.
3142        my $retVal;
3143        # Check for the various file names.
3144        if (-e "$dataDir/$tableName") {
3145            $retVal = "$dataDir/$tableName";
3146        } elsif (-e "$dataDir/$tableName.dtx") {
3147            $retVal = "$dataDir/$tableName.dtx";
3148        }
3149        # Return the result.
3150        return $retVal;
3151    }
3152    
3153  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3154    
3155  =head3 ParseAssignment  =head3 ParseAssignment
3156    
3157  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3158  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3159  will be returned.  isn't, an empty list will be returned.
3160    
3161    A functional assignment is always of the form
3162    
3163        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3164    
3165    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3166    actual functional role. In most cases, the user and the assigning user will be the
3167    same, but that is not always the case.
3168    
3169  This is a static method.  This is a static method.
3170    
# Line 2505  Line 3183 
3183    
3184  =cut  =cut
3185    
3186  sub ParseAssignment {  sub _ParseAssignment {
3187          # Get the parameters.          # Get the parameters.
3188          my ($text) = @_;          my ($text) = @_;
3189          # Declare the return value.          # Declare the return value.
3190          my @retVal = ();          my @retVal = ();
3191          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3192          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3193          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3194                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3195                  @retVal = ($user, $function);          # and the assigning user.
3196            @retVal = ($1, $function);
3197          }          }
3198          # Return the result list.          # Return the result list.
3199          return @retVal;          return @retVal;
3200  }  }
3201    
3202    =head3 FriendlyTimestamp
3203    
3204    Convert a time number to a user-friendly time stamp for display.
3205    
3206    This is a static method.
3207    
3208    =over 4
3209    
3210    =item timeValue
3211    
3212    Numeric time value.
3213    
3214    =item RETURN
3215    
3216    Returns a string containing the same time in user-readable format.
3217    
3218    =back
3219    
3220    =cut
3221    
3222    sub FriendlyTimestamp {
3223        my ($timeValue) = @_;
3224        my $retVal = localtime($timeValue);
3225        return $retVal;
3226    }
3227    
3228    =head3 AddProperty
3229    
3230    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3231    
3232    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3233    be added to almost any object. In Sprout, they can only be added to features. In
3234    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3235    pair. If the particular key/value pair coming in is not already in the database, a new
3236    B<Property> record is created to hold it.
3237    
3238    =over 4
3239    
3240    =item peg
3241    
3242    ID of the feature to which the attribute is to be replied.
3243    
3244    =item key
3245    
3246    Name of the attribute (key).
3247    
3248    =item value
3249    
3250    Value of the attribute.
3251    
3252    =item url
3253    
3254    URL or text citation from which the property was obtained.
3255    
3256    =back
3257    
3258    =cut
3259    #: Return Type ;
3260    sub AddProperty {
3261        # Get the parameters.
3262        my ($self, $featureID, $key, $value, $url) = @_;
3263        # Declare the variable to hold the desired property ID.
3264        my $propID;
3265        # Attempt to find a property record for this key/value pair.
3266        my @properties = $self->GetFlat(['Property'],
3267                                       "Property(property-name) = ? AND Property(property-value) = ?",
3268                                       [$key, $value], 'Property(id)');
3269        if (@properties) {
3270            # Here the property is already in the database. We save its ID.
3271            $propID = $properties[0];
3272            # Here the property value does not exist. We need to generate an ID. It will be set
3273            # to a number one greater than the maximum value in the database. This call to
3274            # GetAll will stop after one record.
3275            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3276                                            1);
3277            $propID = $maxProperty[0]->[0] + 1;
3278            # Insert the new property value.
3279            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3280        }
3281        # Now we connect the incoming feature to the property.
3282        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3283    }
3284    
3285    
3286    
3287  1;  1;

Legend:
Removed from v.1.1  
changed lines
  Added in v.1.43

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3