[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 1.40, Wed Oct 12 03:12:24 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]);                                                     [$featureID]);
# Line 628  Line 622 
622                  }                  }
623                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
624                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
625            # Compute the initial base pair.
626            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
627                  # Add the specifier to the list.                  # Add the specifier to the list.
628                  push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
629          }          }
630          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
631          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
632  }  }
633    
634  =head3 ParseLocation  =head3 ParseLocation
# Line 656  Line 652 
652  =back  =back
653    
654  =cut  =cut
655    #: Return Type @;
656  sub ParseLocation {  sub ParseLocation {
657          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
658        # the first parameter.
659        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
660          my ($location) = @_;          my ($location) = @_;
661          # Parse it into segments.          # Parse it into segments.
662          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
663          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
664          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
665          if ($dir eq "_") {          if ($dir eq "_") {
# Line 677  Line 675 
675          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
676  }  }
677    
678    =head3 PointLocation
679    
680    C<< my $found = Sprout::PointLocation($location, $point); >>
681    
682    Return the offset into the specified location of the specified point on the contig. If
683    the specified point is before the location, a negative value will be returned. If it is
684    beyond the location, an undefined value will be returned. It is assumed that the offset
685    is for the location's contig. The location can either be new-style (using a C<+> or C<->
686    and a length) or old-style (using C<_> and start and end positions.
687    
688    =over 4
689    
690    =item location
691    
692    A location specifier (see L</FeatureLocation> for a description).
693    
694    =item point
695    
696    The offset into the contig of the point in which we're interested.
697    
698    =item RETURN
699    
700    Returns the offset inside the specified location of the specified point, a negative
701    number if the point is before the location, or an undefined value if the point is past
702    the location. If the length of the location is 0, this method will B<always> denote
703    that it is outside the location. The offset will always be relative to the left-most
704    position in the location.
705    
706    =back
707    
708    =cut
709    #: Return Type $;
710    sub PointLocation {
711        # Get the parameter. Note that if we're called as an instance method, we ignore
712        # the first parameter.
713        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
714        my ($location, $point) = @_;
715        # Parse out the location elements. Note that this works on both old-style and new-style
716        # locations.
717        my ($contigID, $start, $dir, $len) = ParseLocation($location);
718        # Declare the return variable.
719        my $retVal;
720        # Compute the offset. The computation is dependent on the direction of the location.
721        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
722        # Return the offset if it's valid.
723        if ($offset < $len) {
724            $retVal = $offset;
725        }
726        # Return the offset found.
727        return $retVal;
728    }
729    
730  =head3 DNASeq  =head3 DNASeq
731    
732  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
733    
734  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
735  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,
736  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>.
737    
738  =over 4  =over 4
# Line 699  Line 749 
749  =back  =back
750    
751  =cut  =cut
752    #: Return Type $;
753  sub DNASeq {  sub DNASeq {
754          # Get the parameters.          # Get the parameters.
755          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
756          # Create the return string.          # Create the return string.
757          my $retVal = "";          my $retVal = "";
758          # Loop through the locations.          # Loop through the locations.
# Line 718  Line 767 
767                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
768                  # before putting it in the return value.                  # before putting it in the return value.
769                  my ($start, $stop);                  my ($start, $stop);
770            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
771                  if ($dir eq "+") {                  if ($dir eq "+") {
772                          $start = $beg;                          $start = $beg;
773                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
774                  } else {                  } else {
775                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
776                          $stop = $beg;                          $stop = $beg;
777                  }                  }
778            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
779                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
780                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
781                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 736  Line 787 
787                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
788                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
789                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
790                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
791                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
792                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
793                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
794                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
795                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
796                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
797                  }                  }
798                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
799                  if ($dir eq '+') {                  if ($dir eq '+') {
800                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
801                  } else {                  } else {
802                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
803                  }                  }
804          }          }
805          # Return the result.          # Return the result.
# Line 773  Line 825 
825  =back  =back
826    
827  =cut  =cut
828    #: Return Type @;
829  sub AllContigs {  sub AllContigs {
830          # Get the parameters.          # Get the parameters.
831          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
832          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
833          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
834                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 797  Line 848 
848    
849  ID of the contig whose length is desired.  ID of the contig whose length is desired.
850    
851    =item RETURN
852    
853    Returns the number of positions in the contig.
854    
855  =back  =back
856    
857  =cut  =cut
858    #: Return Type $;
859  sub ContigLength {  sub ContigLength {
860          # Get the parameters.          # Get the parameters.
861          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
862          # Get the contig's last sequence.          # Get the contig's last sequence.
863          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
864                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 815  Line 869 
869          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
870          if ($sequence) {          if ($sequence) {
871                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
872                  $retVal = $start + $len;          $retVal = $start + $len - 1;
873        }
874        # Return the result.
875        return $retVal;
876    }
877    
878    =head3 ClusterPEGs
879    
880    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
881    
882    Cluster the PEGs in a list according to the cluster coding scheme of the specified
883    subsystem. In order for this to work properly, the subsystem object must have
884    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
885    This causes the cluster numbers to be pulled into the subsystem's color hash.
886    If a PEG is not found in the color hash, it will not appear in the output
887    sequence.
888    
889    =over 4
890    
891    =item sub
892    
893    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
894    method.
895    
896    =item pegs
897    
898    Reference to the list of PEGs to be clustered.
899    
900    =item RETURN
901    
902    Returns a list of the PEGs, grouped into smaller lists by cluster number.
903    
904    =back
905    
906    =cut
907    #: Return Type $@@;
908    sub ClusterPEGs {
909        # Get the parameters.
910        my ($self, $sub, $pegs) = @_;
911        # Declare the return variable.
912        my $retVal = [];
913        # Loop through the PEGs, creating arrays for each cluster.
914        for my $pegID (@{$pegs}) {
915            my $clusterNumber = $sub->get_cluster_number($pegID);
916            # Only proceed if the PEG is in a cluster.
917            if ($clusterNumber >= 0) {
918                # Push this PEG onto the sub-list for the specified cluster number.
919                push @{$retVal->[$clusterNumber]}, $pegID;
920            }
921          }          }
922          # Return the result.          # Return the result.
923          return $retVal;          return $retVal;
# Line 846  Line 948 
948  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
949  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
950  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
951  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
952    roughly by location.
953    
954  =back  =back
955    
956  =cut  =cut
957    #: Return Type @@;
958  sub GenesInRegion {  sub GenesInRegion {
959          # Get the parameters.          # Get the parameters.
960          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
961          # Get the maximum segment length.          # Get the maximum segment length.
962          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
963          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
964          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
965        # containing the minimum and maximum offsets. We will use the offsets to sort the results
966        # when we're building the result set.
967          my %featuresFound = ();          my %featuresFound = ();
968          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
969          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
970        my ($min, $max) = @initialMinMax;
971          # 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
972          # 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,
973          # 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 997 
997                                          $found = 1;                                          $found = 1;
998                                  }                                  }
999                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
1000                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
1001                                  if ($end <= $stop) {                  # ending.
1002                    ($beg, $end) = ($beg - $len, $beg);
1003                    if ($beg <= $stop) {
1004                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
1005                                          $found = 1;                                          $found = 1;
1006                                  }                                  }
1007                          }                          }
1008                          if ($found) {                          if ($found) {
1009                                  # 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,
1010                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
1011                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
1012                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
1013                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
1014                                  if ($end > $max) { $max = $end; }                  # global min and max.
1015                    if ($beg < $loc1) {
1016                        $loc1 = $beg;
1017                        $min = $beg if $beg < $min;
1018                    }
1019                    if ($end > $loc2) {
1020                        $loc2 = $end;
1021                        $max = $end if $end > $max;
1022                    }
1023                    # Store the entry back into the hash table.
1024                    $featuresFound{$featureID} = [$loc1, $loc2];
1025                          }                          }
1026                  }                  }
1027          }          }
1028          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
1029          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1030        # but the result of the sort will be the same.)
1031        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
1032        # Now we sort by midpoint and yank out the feature IDs.
1033        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1034          # Return it along with the min and max.          # Return it along with the min and max.
1035          return (\@list, $min, $max);      return (\@retVal, $min, $max);
1036  }  }
1037    
1038  =head3 FType  =head3 FType
# Line 934  Line 1055 
1055  =back  =back
1056    
1057  =cut  =cut
1058    #: Return Type $;
1059  sub FType {  sub FType {
1060          # Get the parameters.          # Get the parameters.
1061          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1062          # Get the specified feature's type.          # Get the specified feature's type.
1063          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1064          # Return the result.          # Return the result.
# Line 947  Line 1067 
1067    
1068  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1069    
1070  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1071    
1072  Return the annotations of a feature.  Return the annotations of a feature.
1073    
# Line 957  Line 1077 
1077    
1078  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1079    
1080    =item rawFlag
1081    
1082    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1083    will be returned in human-readable form.
1084    
1085  =item RETURN  =item RETURN
1086    
1087  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 1097 
1097  =back  =back
1098    
1099  =cut  =cut
1100    #: Return Type @%;
1101  sub FeatureAnnotations {  sub FeatureAnnotations {
1102          # Get the parameters.          # Get the parameters.
1103          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1104          # 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.
1105          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1106                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 989  Line 1113 
1113                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1114                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1115                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1116            # Convert the time, if necessary.
1117            if (! $rawFlag) {
1118                $timeStamp = FriendlyTimestamp($timeStamp);
1119            }
1120                  # Assemble them into a hash.                  # Assemble them into a hash.
1121                  my $annotationHash = { featureID => $featureID, timeStamp => $timeStamp,          my $annotationHash = { featureID => $featureID,
1122                                   timeStamp => $timeStamp,
1123                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1124                  # Add it to the return list.                  # Add it to the return list.
1125                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1004  Line 1133 
1133  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1134    
1135  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
1136  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,
1137  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
1138  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,
1139  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.
1140  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1141    recent one.
1142    
1143  =over 4  =over 4
1144    
# Line 1016  Line 1146 
1146    
1147  ID of the feature whose functional assignments are desired.  ID of the feature whose functional assignments are desired.
1148    
1149    =item RETURN
1150    
1151    Returns a hash mapping the functional assignment IDs to user IDs.
1152    
1153  =back  =back
1154    
1155  =cut  =cut
1156    #: Return Type %;
1157  sub AllFunctionsOf {  sub AllFunctionsOf {
1158          # Get the parameters.          # Get the parameters.
1159          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1160          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1161          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1162                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1163                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);
1164          # Declare the return hash.          # Declare the return hash.
1165          my %retVal;          my %retVal;
1166        # Declare a hash for insuring we only make one assignment per user.
1167        my %timeHash = ();
1168        # Now we sort the assignments by timestamp in reverse.
1169        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1170          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1171          for my $text (@query) {      for my $annotation (@sortedQuery) {
1172            # Get the annotation fields.
1173            my ($timeStamp, $text) = @{$annotation};
1174                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1175                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1176                  if ($user) {          if ($user && ! exists $timeHash{$user}) {
1177                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1178                # previous assignment for this user, so we stuff it in the
1179                # return hash.
1180                          $retVal{$function} = $user;                          $retVal{$function} = $user;
1181                # Insure we don't assign to this user again.
1182                $timeHash{$user} = 1;
1183                  }                  }
1184          }          }
1185          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1047  Line 1190 
1190    
1191  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>
1192    
1193  Return the most recently-determined functional assignment of a particular feature. A functional  Return the most recently-determined functional assignment of a particular feature.
1194  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  
1195  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
1196  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
1197  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
1198    L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1199    annotation itself because it's a text field; however, this is not a big problem because
1200    most features only have a small number of annotations.
1201    
1202    Each user has an associated list of trusted users. The assignment returned will be the most
1203    recent one by at least one of the trusted users. If no trusted user list is available, then
1204    the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1205    is trusted.
1206    
1207    If the feature is B<not> identified by a FIG ID, then the functional assignment
1208    information is taken from the B<ExternalAliasFunc> table. If the table does
1209    not contain an entry for the feature, an undefined value is returned.
1210    
1211  =over 4  =over 4
1212    
# Line 1061  Line 1216 
1216    
1217  =item userID (optional)  =item userID (optional)
1218    
1219  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
1220    C<FIG> assignment will be returned.
1221    
1222  =item RETURN  =item RETURN
1223    
# Line 1070  Line 1226 
1226  =back  =back
1227    
1228  =cut  =cut
1229    #: Return Type $;
1230  sub FunctionOf {  sub FunctionOf {
1231          # Get the parameters.          # Get the parameters.
1232          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
1233          my ($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.  
1234          my $retVal;          my $retVal;
1235        # Determine the ID type.
1236        if ($featureID =~ m/^fig\|/) {
1237            # Here we have a FIG feature ID. We must build the list of trusted
1238            # users.
1239            my %trusteeTable = ();
1240            # Check the user ID.
1241            if (!$userID) {
1242                # No user ID, so only FIG is trusted.
1243                $trusteeTable{FIG} = 1;
1244            } else {
1245                # Add this user's ID.
1246                $trusteeTable{$userID} = 1;
1247                # Look for the trusted users in the database.
1248                my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)');
1249                if (! @trustees) {
1250                    # None were found, so build a default list.
1251                    $trusteeTable{FIG} = 1;
1252                } else {
1253                    # Otherwise, put all the trustees in.
1254                    for my $trustee (@trustees) {
1255                        $trusteeTable{$trustee} = 1;
1256                    }
1257                }
1258            }
1259            # Build a query for all of the feature's annotations, sorted by date.
1260            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],
1261                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1262                                   [$featureID]);
1263          my $timeSelected = 0;          my $timeSelected = 0;
1264          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1265          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1266                  # Get the annotation text.                  # Get the annotation text.
1267                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1268                  # Check to see if this is a functional assignment for the desired user.              # Check to see if this is a functional assignment for a trusted user.
1269                  my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1270                  if ($type =~ m/^set $userID function to$/i) {              if ($user) {
1271                          # Here it is, so we check the time and save the assignment value.                  # Here it is a functional assignment. Check the time and the user
1272                          if ($time > $timeSelected) {                  # name. The time must be recent and the user must be trusted.
1273                    if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
1274                                  $retVal = $function;                                  $retVal = $function;
1275                                  $timeSelected = $time;                                  $timeSelected = $time;
1276                          }                          }
1277                  }                  }
1278          }          }
1279        } else {
1280            # Here we have a non-FIG feature ID. In this case the user ID does not
1281            # matter. We simply get the information from the External Alias Function
1282            # table.
1283            ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);
1284        }
1285          # Return the assignment found.          # Return the assignment found.
1286          return $retVal;          return $retVal;
1287  }  }
# Line 1120  Line 1305 
1305    
1306  =item RETURN  =item RETURN
1307    
1308  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
1309  their best hits.  on the target genome.
1310    
1311  =back  =back
1312    
1313  =cut  =cut
1314    #: Return Type %;
1315  sub BBHList {  sub BBHList {
1316          # Get the parameters.          # Get the parameters.
1317          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1318          # Create the return structure.          # Create the return structure.
1319          my %retVal = ();          my %retVal = ();
1320          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1139  Line 1323 
1323                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1324                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1325                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1326                  # Look for the best hit.          # Peel off the BBHs found.
1327                  my $bbh = $query->Fetch;          my @found = ();
1328                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1329                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1330                  }                  }
1331            $retVal{$featureID} = \@found;
1332          }          }
1333          # Return the mapping.          # Return the mapping.
1334          return \%retVal;          return \%retVal;
1335  }  }
1336    
1337    =head3 SimList
1338    
1339    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1340    
1341    Return a list of the similarities to the specified feature.
1342    
1343    Sprout does not support real similarities, so this method just returns the bidirectional
1344    best hits.
1345    
1346    =over 4
1347    
1348    =item featureID
1349    
1350    ID of the feature whose similarities are desired.
1351    
1352    =item count
1353    
1354    Maximum number of similar features to be returned, or C<0> to return them all.
1355    
1356    =back
1357    
1358    =cut
1359    #: Return Type %;
1360    sub SimList {
1361        # Get the parameters.
1362        my ($self, $featureID, $count) = @_;
1363        # Ask for the best hits.
1364        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1365                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1366                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1367                                  $count);
1368        # Create the return value.
1369        my %retVal = ();
1370        for my $tuple (@lists) {
1371            $retVal{$tuple->[0]} = $tuple->[1];
1372        }
1373        # Return the result.
1374        return %retVal;
1375    }
1376    
1377    
1378    
1379    =head3 IsComplete
1380    
1381    C<< my $flag = $sprout->IsComplete($genomeID); >>
1382    
1383    Return TRUE if the specified genome is complete, else FALSE.
1384    
1385    =over 4
1386    
1387    =item genomeID
1388    
1389    ID of the genome whose completeness status is desired.
1390    
1391    =item RETURN
1392    
1393    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1394    not found.
1395    
1396    =back
1397    
1398    =cut
1399    #: Return Type $;
1400    sub IsComplete {
1401        # Get the parameters.
1402        my ($self, $genomeID) = @_;
1403        # Declare the return variable.
1404        my $retVal;
1405        # Get the genome's data.
1406        my $genomeData = $self->GetEntity('Genome', $genomeID);
1407        if ($genomeData) {
1408            # The genome exists, so get the completeness flag.
1409            ($retVal) = $genomeData->Value('complete');
1410        }
1411        # Return the result.
1412        return $retVal;
1413    }
1414    
1415  =head3 FeatureAliases  =head3 FeatureAliases
1416    
1417  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1170  Line 1432 
1432  =back  =back
1433    
1434  =cut  =cut
1435    #: Return Type @;
1436  sub FeatureAliases {  sub FeatureAliases {
1437          # Get the parameters.          # Get the parameters.
1438          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1439          # Get the desired feature's aliases          # Get the desired feature's aliases
1440          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1441          # Return the result.          # Return the result.
# Line 1201  Line 1462 
1462  =back  =back
1463    
1464  =cut  =cut
1465    #: Return Type $;
1466  sub GenomeOf {  sub GenomeOf {
1467          # Get the parameters.          # Get the parameters.
1468          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1469          # Create a query to find the genome associated with the feature.          # Create a query to find the genome associated with the feature.
1470          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1471          # Declare the return value.          # Declare the return value.
# Line 1238  Line 1498 
1498  =back  =back
1499    
1500  =cut  =cut
1501    #: Return Type %;
1502  sub CoupledFeatures {  sub CoupledFeatures {
1503          # Get the parameters.          # Get the parameters.
1504          my $self = shift @_;      my ($self, $featureID) = @_;
1505          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1506          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1507          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1508          # 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.
1509          my $found = 0;          my $found = 0;
1510          # Create the return hash.          # Create the return hash.
1511          my %retVal = ();          my %retVal = ();
1512          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1513          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1514                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1515                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1516                                                            'Coupling(score)']);
1517            # The coupling ID contains the two feature IDs separated by a space. We use
1518            # this information to find the ID of the other feature.
1519            my ($fid1, $fid2) = split / /, $couplingID;
1520            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1521            # Attach the other feature's score to its ID.
1522                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1523                  $found = 1;                  $found = 1;
1524          }          }
# Line 1268  Line 1531 
1531          return %retVal;          return %retVal;
1532  }  }
1533    
1534    =head3 CouplingEvidence
1535    
1536    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1537    
1538    Return the evidence for a functional coupling.
1539    
1540    A pair of features is considered evidence of a coupling between two other
1541    features if they occur close together on a contig and both are similar to
1542    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1543    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1544    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1545    similar to B<A2>.
1546    
1547    The score of a coupling is determined by the number of pieces of evidence
1548    that are considered I<representative>. If several evidence items belong to
1549    a group of genomes that are close to each other, only one of those items
1550    is considered representative. The other evidence items are presumed to be
1551    there because of the relationship between the genomes rather than because
1552    the two proteins generated by the features have a related functionality.
1553    
1554    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1555    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1556    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1557    and FALSE otherwise.
1558    
1559    =over 4
1560    
1561    =item peg1
1562    
1563    ID of the feature of interest.
1564    
1565    =item peg2
1566    
1567    ID of a feature functionally coupled to the feature of interest.
1568    
1569    =item RETURN
1570    
1571    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1572    of interest, a feature similar to the functionally coupled feature, and a flag
1573    that is TRUE for a representative piece of evidence and FALSE otherwise.
1574    
1575    =back
1576    
1577    =cut
1578    #: Return Type @@;
1579    sub CouplingEvidence {
1580        # Get the parameters.
1581        my ($self, $peg1, $peg2) = @_;
1582        # Declare the return variable.
1583        my @retVal = ();
1584        # Our first task is to find out the nature of the coupling: whether or not
1585        # it exists, its score, and whether the features are stored in the same
1586        # order as the ones coming in.
1587        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1588        # Only proceed if a coupling exists.
1589        if ($couplingID) {
1590            # Determine the ordering to place on the evidence items. If we're
1591            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1592            # we want feature 1 before feature 2 (normal).
1593            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1594            my $ordering = ($inverted ? "DESC" : "");
1595            # Get the coupling evidence.
1596            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1597                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1598                                              [$couplingID],
1599                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1600            # Loop through the evidence items. Each piece of evidence is represented by two
1601            # positions in the evidence list, one for each feature on the other side of the
1602            # evidence link. If at some point we want to generalize to couplings with
1603            # more than two positions, this section of code will need to be re-done.
1604            while (@evidenceList > 0) {
1605                my $peg1Data = shift @evidenceList;
1606                my $peg2Data = shift @evidenceList;
1607                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1608                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1609            }
1610            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1611        }
1612        # Return the result.
1613        return @retVal;
1614    }
1615    
1616    =head3 GetCoupling
1617    
1618    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1619    
1620    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1621    exists, we return the coupling ID along with an indicator of whether the
1622    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1623    In the second case, we say the coupling is I<inverted>. The importance of an
1624    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1625    
1626    =over 4
1627    
1628    =item peg1
1629    
1630    ID of the feature of interest.
1631    
1632    =item peg2
1633    
1634    ID of the potentially coupled feature.
1635    
1636    =item RETURN
1637    
1638    Returns a three-element list. The first element contains the database ID of
1639    the coupling. The second element is FALSE if the coupling is stored in the
1640    database in the caller specified order and TRUE if it is stored in the
1641    inverted order. The third element is the coupling's score. If the coupling
1642    does not exist, all three list elements will be C<undef>.
1643    
1644    =back
1645    
1646    =cut
1647    #: Return Type $%@;
1648    sub GetCoupling {
1649        # Get the parameters.
1650        my ($self, $peg1, $peg2) = @_;
1651        # Declare the return values. We'll start with the coupling ID and undefine the
1652        # flag and score until we have more information.
1653        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1654        # Find the coupling data.
1655        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1656                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1657                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1658        # Check to see if we found anything.
1659        if (!@pegs) {
1660            Trace("No coupling found.") if T(Coupling => 4);
1661            # No coupling, so undefine the return value.
1662            $retVal = undef;
1663        } else {
1664            # We have a coupling! Get the score and check for inversion.
1665            $score = $pegs[0]->[1];
1666            my $firstFound = $pegs[0]->[0];
1667            $inverted = ($firstFound ne $peg1);
1668            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1669        }
1670        # Return the result.
1671        return ($retVal, $inverted, $score);
1672    }
1673    
1674    =head3 CouplingID
1675    
1676    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1677    
1678    Return the coupling ID for a pair of feature IDs.
1679    
1680    The coupling ID is currently computed by joining the feature IDs in
1681    sorted order with a space. Client modules (that is, modules which
1682    use Sprout) should not, however, count on this always being the
1683    case. This method provides a way for abstracting the concept of a
1684    coupling ID. All that we know for sure about it is that it can be
1685    generated easily from the feature IDs and the order of the IDs
1686    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1687    will have the same value as C<CouplingID("b1", "a1")>.
1688    
1689    =over 4
1690    
1691    =item peg1
1692    
1693    First feature of interest.
1694    
1695    =item peg2
1696    
1697    Second feature of interest.
1698    
1699    =item RETURN
1700    
1701    Returns the ID that would be used to represent a functional coupling of
1702    the two specified PEGs.
1703    
1704    =back
1705    
1706    =cut
1707    #: Return Type $;
1708    sub CouplingID {
1709        return join " ", sort @_;
1710    }
1711    
1712  =head3 GetEntityTypes  =head3 GetEntityTypes
1713    
1714  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1275  Line 1716 
1716  Return the list of supported entity types.  Return the list of supported entity types.
1717    
1718  =cut  =cut
1719    #: Return Type @;
1720  sub GetEntityTypes {  sub GetEntityTypes {
1721          # Get the parameters.          # Get the parameters.
1722          my $self = shift @_;      my ($self) = @_;
1723          # Get the underlying database object.          # Get the underlying database object.
1724          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1725          # Get its entity type list.          # Get its entity type list.
# Line 1310  Line 1751 
1751  =back  =back
1752    
1753  =cut  =cut
1754    #: Return Type %;
1755  sub ReadFasta {  sub ReadFasta {
1756          # Get the parameters.          # Get the parameters.
1757          my ($fileName, $prefix) = @_;          my ($fileName, $prefix) = @_;
# Line 1329  Line 1770 
1770                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1771                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1772                          if ($id) {                          if ($id) {
1773                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1774                          }                          }
1775                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1776                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1777                  } else {                  } else {
1778                          # 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.
1779                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1780                # case.
1781                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1782                          $sequence .= $1;                          $sequence .= $1;
1783                  }                  }
1784          }          }
1785          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1786          if ($sequence) {          if ($sequence) {
1787                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1788          }          }
1789        # Close the file.
1790        close FASTAFILE;
1791          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1792          return %retVal;          return %retVal;
1793  }  }
# Line 1354  Line 1798 
1798    
1799  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
1800  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
1801  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,
1802    it will not be changed; otherwise, it will be converted. This method can also be used to
1803    perform the reverse task-- insuring that all the locations are in the old format.
1804    
1805  =over 4  =over 4
1806    
# Line 1378  Line 1824 
1824  =back  =back
1825    
1826  =cut  =cut
1827    #: Return Type @;
1828  sub FormatLocations {  sub FormatLocations {
1829          # Get the parameters.          # Get the parameters.
1830          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1831          # Create the return list.          # Create the return list.
1832          my @retVal = ();          my @retVal = ();
1833          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1834          if ($locations eq '') {          if ($locations eq '') {
1835              confess "No locations specified.";          Confess("No locations specified.");
1836          } else {          } else {
1837                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1838                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1422  Line 1867 
1867    
1868  sub DumpData {  sub DumpData {
1869          # Get the parameters.          # Get the parameters.
1870          my $self = shift @_;      my ($self) = @_;
1871          # Get the data directory name.          # Get the data directory name.
1872          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1873          # Dump the relations.          # Dump the relations.
# Line 1436  Line 1881 
1881  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
1882    
1883  =cut  =cut
1884    #: Return Type $;
1885  sub XMLFileName {  sub XMLFileName {
1886          my $self = shift @_;      my ($self) = @_;
1887          return $self->{_xmlName};          return $self->{_xmlName};
1888  }  }
1889    
# Line 1458  Line 1903 
1903  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
1904  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>.
1905    
1906  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'}); >>
1907    
1908  =over 4  =over 4
1909    
# Line 1473  Line 1918 
1918  =back  =back
1919    
1920  =cut  =cut
1921    #: Return Type ;
1922  sub Insert {  sub Insert {
1923          # Get the parameters.          # Get the parameters.
1924          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1925          # Call the underlying method.          # Call the underlying method.
1926          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1927  }  }
# Line 1515  Line 1959 
1959  =back  =back
1960    
1961  =cut  =cut
1962    #: Return Type $;
1963  sub Annotate {  sub Annotate {
1964          # Get the parameters.          # Get the parameters.
1965          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1966          # Create the annotation ID.          # Create the annotation ID.
1967          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1968          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1539  Line 1982 
1982    
1983  =head3 AssignFunction  =head3 AssignFunction
1984    
1985  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1986    
1987  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
1988  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.  
1989    
1990  =over 4  =over 4
1991    
# Line 1553  Line 1995 
1995    
1996  =item user  =item user
1997    
1998  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>.
1999    
2000  =item function  =item function
2001    
2002  Text of the function being assigned.  Text of the function being assigned.
2003    
2004    =item assigningUser (optional)
2005    
2006    Name of the individual user making the assignment. If omitted, defaults to the user group.
2007    
2008  =item RETURN  =item RETURN
2009    
2010  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1566  Line 2012 
2012  =back  =back
2013    
2014  =cut  =cut
2015    #: Return Type $;
2016  sub AssignFunction {  sub AssignFunction {
2017          # Get the parameters.          # Get the parameters.
2018          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2019          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2020        if (! $assigningUser) {
2021            $assigningUser = $user;
2022        }
2023          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2024          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2025          # Get the current time.          # Get the current time.
2026          my $now = time;          my $now = time;
2027          # Declare the return variable.          # Declare the return variable.
# Line 1614  Line 2063 
2063  =back  =back
2064    
2065  =cut  =cut
2066    #: Return Type @;
2067  sub FeaturesByAlias {  sub FeaturesByAlias {
2068          # Get the parameters.          # Get the parameters.
2069          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2070          # Declare the return variable.          # Declare the return variable.
2071          my @retVal = ();          my @retVal = ();
2072          # Parse the alias.          # Parse the alias.
# Line 1657  Line 2105 
2105  =back  =back
2106    
2107  =cut  =cut
2108    #: Return Type $;
2109  sub Exists {  sub Exists {
2110          # Get the parameters.          # Get the parameters.
2111          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2112          # Check for the entity instance.          # Check for the entity instance.
2113        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2114          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2115          # Return an existence indicator.          # Return an existence indicator.
2116          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1688  Line 2136 
2136  =back  =back
2137    
2138  =cut  =cut
2139    #: Return Type $;
2140  sub FeatureTranslation {  sub FeatureTranslation {
2141          # Get the parameters.          # Get the parameters.
2142          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2143          # Get the specified feature's translation.          # Get the specified feature's translation.
2144          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2145          return $retVal;          return $retVal;
# Line 1721  Line 2168 
2168  =back  =back
2169    
2170  =cut  =cut
2171    #: Return Type @;
2172  sub Taxonomy {  sub Taxonomy {
2173          # Get the parameters.          # Get the parameters.
2174          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2175          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2176          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2177          # Declare the return variable.          # Declare the return variable.
# Line 1765  Line 2211 
2211  =back  =back
2212    
2213  =cut  =cut
2214    #: Return Type $;
2215  sub CrudeDistance {  sub CrudeDistance {
2216          # Get the parameters.          # Get the parameters.
2217          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2218          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2219          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2220          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1813  Line 2258 
2258  =back  =back
2259    
2260  =cut  =cut
2261    #: Return Type $;
2262  sub RoleName {  sub RoleName {
2263          # Get the parameters.          # Get the parameters.
2264          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2265          # Get the specified role's name.          # Get the specified role's name.
2266          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2267          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1847  Line 2291 
2291  =back  =back
2292    
2293  =cut  =cut
2294    #: Return Type @;
2295  sub RoleDiagrams {  sub RoleDiagrams {
2296          # Get the parameters.          # Get the parameters.
2297          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2298          # Query for the diagrams.          # Query for the diagrams.
2299          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2300                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1859  Line 2302 
2302          return @retVal;          return @retVal;
2303  }  }
2304    
2305    =head3 GetProperties
2306    
2307    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2308    
2309    Return a list of the properties with the specified characteristics.
2310    
2311    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2312    will also be associated with genomes.) A property value is represented by a 4-tuple of
2313    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2314    
2315    =over 4
2316    
2317    =item fid
2318    
2319    ID of the feature possessing the property.
2320    
2321    =item key
2322    
2323    Name or key of the property.
2324    
2325    =item value
2326    
2327    Value of the property.
2328    
2329    =item url
2330    
2331    URL of the document that indicated the property should have this particular value, or an
2332    empty string if no such document exists.
2333    
2334    =back
2335    
2336    The parameters act as a filter for the desired data. Any non-null parameter will
2337    automatically match all the tuples returned. So, specifying just the I<$fid> will
2338    return all the properties of the specified feature; similarly, specifying the I<$key>
2339    and I<$value> parameters will return all the features having the specified property
2340    value.
2341    
2342    A single property key can have many values, representing different ideas about the
2343    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2344    virulent, and another may declare that it is not virulent. A query about the virulence of
2345    C<fig|83333.1.peg.10> would be coded as
2346    
2347        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2348    
2349    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2350    not to be filtered. The tuples returned would be
2351    
2352        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2353        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2354    
2355    =cut
2356    #: Return Type @@;
2357    sub GetProperties {
2358        # Get the parameters.
2359        my ($self, @parms) = @_;
2360        # Declare the return variable.
2361        my @retVal = ();
2362        # Now we need to create a WHERE clause that will get us the data we want. First,
2363        # we create a list of the columns containing the data for each parameter.
2364        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2365                        'Property(property-value)', 'HasProperty(evidence)');
2366        # Now we build the WHERE clause and the list of parameter values.
2367        my @where = ();
2368        my @values = ();
2369        for (my $i = 0; $i <= $#colNames; $i++) {
2370            my $parm = $parms[$i];
2371            if (defined $parm && ($parm ne '')) {
2372                push @where, "$colNames[$i] = ?";
2373                push @values, $parm;
2374            }
2375        }
2376        # Format the WHERE clause.
2377        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2378        # Ask for all the propertie values with the desired characteristics.
2379        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2380        while (my $valueObject = $query->Fetch()) {
2381            my @tuple = $valueObject->Values(\@colNames);
2382            push @retVal, \@tuple;
2383        }
2384        # Return the result.
2385        return @retVal;
2386    }
2387    
2388  =head3 FeatureProperties  =head3 FeatureProperties
2389    
2390  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1885  Line 2411 
2411  =back  =back
2412    
2413  =cut  =cut
2414    #: Return Type @@;
2415  sub FeatureProperties {  sub FeatureProperties {
2416          # Get the parameters.          # Get the parameters.
2417          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2418          # Get the properties.          # Get the properties.
2419          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2420                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1917  Line 2442 
2442  =back  =back
2443    
2444  =cut  =cut
2445    #: Return Type $;
2446  sub DiagramName {  sub DiagramName {
2447          # Get the parameters.          # Get the parameters.
2448          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2449          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2450          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2451          return $retVal;          return $retVal;
# Line 1950  Line 2474 
2474  =back  =back
2475    
2476  =cut  =cut
2477    #: Return Type @;
2478  sub MergedAnnotations {  sub MergedAnnotations {
2479          # Get the parameters.          # Get the parameters.
2480          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2481          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2482          my @tuples = ();          my @tuples = ();
2483          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 1969  Line 2492 
2492          }          }
2493          # Sort the result list by timestamp.          # Sort the result list by timestamp.
2494          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;
2495        # Loop through and make the time stamps friendly.
2496        for my $tuple (@retVal) {
2497            $tuple->[1] = FriendlyTimestamp($tuple->[1]);
2498        }
2499          # Return the sorted list.          # Return the sorted list.
2500          return @retVal;          return @retVal;
2501  }  }
# Line 1995  Line 2522 
2522  =back  =back
2523    
2524  =cut  =cut
2525    #: Return Type @;
2526  sub RoleNeighbors {  sub RoleNeighbors {
2527          # Get the parameters.          # Get the parameters.
2528          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2529          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2530          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2531                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2038  Line 2564 
2564  =back  =back
2565    
2566  =cut  =cut
2567    #: Return Type @;
2568  sub FeatureLinks {  sub FeatureLinks {
2569          # Get the parameters.          # Get the parameters.
2570          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2571          # Get the feature's links.          # Get the feature's links.
2572          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2573          # Return the feature's links.          # Return the feature's links.
# Line 2054  Line 2579 
2579  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2580    
2581  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
2582  to the role the feature performs.  to the roles the feature performs.
2583    
2584  =over 4  =over 4
2585    
# Line 2064  Line 2589 
2589    
2590  =item RETURN  =item RETURN
2591    
2592  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.
2593    
2594  =back  =back
2595    
2596  =cut  =cut
2597    #: Return Type %@;
2598  sub SubsystemsOf {  sub SubsystemsOf {
2599          # Get the parameters.          # Get the parameters.
2600          my $self = shift @_;      my ($self, $featureID) = @_;
2601          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2602          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2603                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2604                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2082  Line 2606 
2606          my %retVal = ();          my %retVal = ();
2607          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2608          for my $record (@subsystems) {          for my $record (@subsystems) {
2609                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2610            if (exists $retVal{$subsys}) {
2611                push @{$retVal{$subsys}}, $role;
2612            } else {
2613                $retVal{$subsys} = [$role];
2614            }
2615          }          }
2616          # Return the hash.          # Return the hash.
2617          return %retVal;          return %retVal;
2618  }  }
2619    
2620    =head3 SubsystemList
2621    
2622    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2623    
2624    Return a list containing the names of the subsystems in which the specified
2625    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2626    subsystem names, not the roles.
2627    
2628    =over 4
2629    
2630    =item featureID
2631    
2632    ID of the feature whose subsystem names are desired.
2633    
2634    =item RETURN
2635    
2636    Returns a list of the names of the subsystems in which the feature participates.
2637    
2638    =back
2639    
2640    =cut
2641    #: Return Type @;
2642    sub SubsystemList {
2643        # Get the parameters.
2644        my ($self, $featureID) = @_;
2645        # Get the list of names.
2646        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2647                                    [$featureID], 'HasSSCell(from-link)');
2648        # Return the result.
2649        return @retVal;
2650    }
2651    
2652  =head3 RelatedFeatures  =head3 RelatedFeatures
2653    
2654  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2118  Line 2679 
2679  =back  =back
2680    
2681  =cut  =cut
2682    #: Return Type @;
2683  sub RelatedFeatures {  sub RelatedFeatures {
2684          # Get the parameters.          # Get the parameters.
2685          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2686          # 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.
2687          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2688                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2167  Line 2727 
2727  =back  =back
2728    
2729  =cut  =cut
2730    #: Return Type @;
2731  sub TaxonomySort {  sub TaxonomySort {
2732          # Get the parameters.          # Get the parameters.
2733          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2734          # Create the working hash table.          # Create the working hash table.
2735          my %hashBuffer = ();          my %hashBuffer = ();
2736          # Loop through the features.          # Loop through the features.
# Line 2180  Line 2739 
2739                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2740                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2741                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2742                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2743          }          }
2744          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2745          my @retVal = ();          my @retVal = ();
# Line 2250  Line 2805 
2805  =back  =back
2806    
2807  =cut  =cut
2808    #: Return Type @@;
2809  sub GetAll {  sub GetAll {
2810          # Get the parameters.          # Get the parameters.
2811          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2812          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2813          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2814          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++;  
         }  
2815          # Return the resulting list.          # Return the resulting list.
2816          return @retVal;          return @retVal;
2817  }  }
# Line 2312  Line 2853 
2853  =back  =back
2854    
2855  =cut  =cut
2856    #: Return Type @;
2857  sub GetFlat {  sub GetFlat {
2858          # Get the parameters.          # Get the parameters.
2859          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2860          # Construct the query.          # Construct the query.
2861          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2862          # Create the result list.          # Create the result list.
# Line 2423  Line 2963 
2963  to load the entire database.  to load the entire database.
2964    
2965  =cut  =cut
2966    #: Return Type @;
2967  sub LoadInfo {  sub LoadInfo {
2968          # Get the parameters.          # Get the parameters.
2969          my $self = shift @_;      my ($self) = @_;
2970          # 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.
2971          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2972          # Concatenate the table names.          # Concatenate the table names.
# Line 2460  Line 3000 
3000  =back  =back
3001    
3002  =cut  =cut
3003    #: Return Type %;
3004  sub LowBBHs {  sub LowBBHs {
3005          # Get the parsameters.          # Get the parsameters.
3006          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3007          # Create the return hash.          # Create the return hash.
3008          my %retVal = ();          my %retVal = ();
3009          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2480  Line 3019 
3019          return %retVal;          return %retVal;
3020  }  }
3021    
3022    =head3 GetGroups
3023    
3024    C<< my %groups = $sprout->GetGroups(\@groupList); >>
3025    
3026    Return a hash mapping each group to the IDs of the genomes in the group.
3027    A list of groups may be specified, in which case only those groups will be
3028    shown. Alternatively, if no parameter is supplied, all groups will be
3029    included. Genomes that are not in any group are omitted.
3030    
3031    =cut
3032    #: Return Type %@;
3033    sub GetGroups {
3034        # Get the parameters.
3035        my ($self, $groupList) = @_;
3036        # Declare the return value.
3037        my %retVal = ();
3038        # Determine whether we are getting all the groups or just some.
3039        if (defined $groupList) {
3040            # Here we have a group list. Loop through them individually,
3041            # getting a list of the relevant genomes.
3042            for my $group (@{$groupList}) {
3043                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",
3044                    [$group], "Genome(id)");
3045                $retVal{$group} = \@genomeIDs;
3046            }
3047        } else {
3048            # Here we need all of the groups. In this case, we run through all
3049            # of the genome records, putting each one found into the appropriate
3050            # group. Note that we use a filter clause to insure that only genomes
3051            # in groups are included in the return set.
3052            my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],
3053                                        ['Genome(id)', 'Genome(group-name)']);
3054            # Loop through the genomes found.
3055            for my $genome (@genomes) {
3056                # Pop this genome's ID off the current list.
3057                my @groups = @{$genome};
3058                my $genomeID = shift @groups;
3059                # Loop through the groups, adding the genome ID to each group's
3060                # list.
3061                for my $group (@groups) {
3062                    Tracer::AddToListMap(\%retVal, $group, $genomeID);
3063                }
3064            }
3065        }
3066        # Return the hash we just built.
3067        return %retVal;
3068    }
3069    
3070    =head3 MyGenomes
3071    
3072    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3073    
3074    Return a list of the genomes to be included in the Sprout.
3075    
3076    This method is provided for use during the Sprout load. It presumes the Genome load file has
3077    already been created. (It will be in the Sprout data directory and called either C<Genome>
3078    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3079    IDs.
3080    
3081    =over 4
3082    
3083    =item dataDir
3084    
3085    Directory containing the Sprout load files.
3086    
3087    =back
3088    
3089    =cut
3090    #: Return Type @;
3091    sub MyGenomes {
3092        # Get the parameters.
3093        my ($dataDir) = @_;
3094        # Compute the genome file name.
3095        my $genomeFileName = LoadFileName($dataDir, "Genome");
3096        # Extract the genome IDs from the files.
3097        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3098        # Return the result.
3099        return @retVal;
3100    }
3101    
3102    =head3 LoadFileName
3103    
3104    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3105    
3106    Return the name of the load file for the specified table in the specified data
3107    directory.
3108    
3109    =over 4
3110    
3111    =item dataDir
3112    
3113    Directory containing the Sprout load files.
3114    
3115    =item tableName
3116    
3117    Name of the table whose load file is desired.
3118    
3119    =item RETURN
3120    
3121    Returns the name of the file containing the load data for the specified table, or
3122    C<undef> if no load file is present.
3123    
3124    =back
3125    
3126    =cut
3127    #: Return Type $;
3128    sub LoadFileName {
3129        # Get the parameters.
3130        my ($dataDir, $tableName) = @_;
3131        # Declare the return variable.
3132        my $retVal;
3133        # Check for the various file names.
3134        if (-e "$dataDir/$tableName") {
3135            $retVal = "$dataDir/$tableName";
3136        } elsif (-e "$dataDir/$tableName.dtx") {
3137            $retVal = "$dataDir/$tableName.dtx";
3138        }
3139        # Return the result.
3140        return $retVal;
3141    }
3142    
3143  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3144    
3145  =head3 ParseAssignment  =head3 ParseAssignment
3146    
3147  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3148  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3149  will be returned.  isn't, an empty list will be returned.
3150    
3151    A functional assignment is always of the form
3152    
3153        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3154    
3155    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3156    actual functional role. In most cases, the user and the assigning user will be the
3157    same, but that is not always the case.
3158    
3159  This is a static method.  This is a static method.
3160    
# Line 2505  Line 3173 
3173    
3174  =cut  =cut
3175    
3176  sub ParseAssignment {  sub _ParseAssignment {
3177          # Get the parameters.          # Get the parameters.
3178          my ($text) = @_;          my ($text) = @_;
3179          # Declare the return value.          # Declare the return value.
3180          my @retVal = ();          my @retVal = ();
3181          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3182          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3183          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3184                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3185                  @retVal = ($user, $function);          # and the assigning user.
3186            @retVal = ($1, $function, $user);
3187          }          }
3188          # Return the result list.          # Return the result list.
3189          return @retVal;          return @retVal;
3190  }  }
3191    
3192    =head3 FriendlyTimestamp
3193    
3194    Convert a time number to a user-friendly time stamp for display.
3195    
3196    This is a static method.
3197    
3198    =over 4
3199    
3200    =item timeValue
3201    
3202    Numeric time value.
3203    
3204    =item RETURN
3205    
3206    Returns a string containing the same time in user-readable format.
3207    
3208    =back
3209    
3210    =cut
3211    
3212    sub FriendlyTimestamp {
3213        my ($timeValue) = @_;
3214        my $retVal = localtime($timeValue);
3215        return $retVal;
3216    }
3217    
3218    =head3 AddProperty
3219    
3220    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3221    
3222    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3223    be added to almost any object. In Sprout, they can only be added to features. In
3224    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3225    pair. If the particular key/value pair coming in is not already in the database, a new
3226    B<Property> record is created to hold it.
3227    
3228    =over 4
3229    
3230    =item peg
3231    
3232    ID of the feature to which the attribute is to be replied.
3233    
3234    =item key
3235    
3236    Name of the attribute (key).
3237    
3238    =item value
3239    
3240    Value of the attribute.
3241    
3242    =item url
3243    
3244    URL or text citation from which the property was obtained.
3245    
3246    =back
3247    
3248    =cut
3249    #: Return Type ;
3250    sub AddProperty {
3251        # Get the parameters.
3252        my ($self, $featureID, $key, $value, $url) = @_;
3253        # Declare the variable to hold the desired property ID.
3254        my $propID;
3255        # Attempt to find a property record for this key/value pair.
3256        my @properties = $self->GetFlat(['Property'],
3257                                       "Property(property-name) = ? AND Property(property-value) = ?",
3258                                       [$key, $value], 'Property(id)');
3259        if (@properties) {
3260            # Here the property is already in the database. We save its ID.
3261            $propID = $properties[0];
3262            # Here the property value does not exist. We need to generate an ID. It will be set
3263            # to a number one greater than the maximum value in the database. This call to
3264            # GetAll will stop after one record.
3265            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3266                                            1);
3267            $propID = $maxProperty[0]->[0] + 1;
3268            # Insert the new property value.
3269            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3270        }
3271        # Now we connect the incoming feature to the property.
3272        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3273    }
3274    
3275    
3276    
3277  1;  1;

Legend:
Removed from v.1.1  
changed lines
  Added in v.1.40

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3