[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 1.26, Tue Sep 13 18:33:20 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]);                                                     [$featureID]);
# Line 632  Line 626 
626                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
627          }          }
628          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
629          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
630  }  }
631    
632  =head3 ParseLocation  =head3 ParseLocation
# Line 656  Line 650 
650  =back  =back
651    
652  =cut  =cut
653    #: Return Type @;
654  sub ParseLocation {  sub ParseLocation {
655          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
656        # the first parameter.
657        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
658          my ($location) = @_;          my ($location) = @_;
659          # Parse it into segments.          # Parse it into segments.
660          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;
# Line 677  Line 673 
673          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
674  }  }
675    
676    =head3 PointLocation
677    
678    C<< my $found = Sprout::PointLocation($location, $point); >>
679    
680    Return the offset into the specified location of the specified point on the contig. If
681    the specified point is before the location, a negative value will be returned. If it is
682    beyond the location, an undefined value will be returned. It is assumed that the offset
683    is for the location's contig. The location can either be new-style (using a C<+> or C<->
684    and a length) or old-style (using C<_> and start and end positions.
685    
686    =over 4
687    
688    =item location
689    
690    A location specifier (see L</FeatureLocation> for a description).
691    
692    =item point
693    
694    The offset into the contig of the point in which we're interested.
695    
696    =item RETURN
697    
698    Returns the offset inside the specified location of the specified point, a negative
699    number if the point is before the location, or an undefined value if the point is past
700    the location. If the length of the location is 0, this method will B<always> denote
701    that it is outside the location. The offset will always be relative to the left-most
702    position in the location.
703    
704    =back
705    
706    =cut
707    #: Return Type $;
708    sub PointLocation {
709        # Get the parameter. Note that if we're called as an instance method, we ignore
710        # the first parameter.
711        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
712        my ($location, $point) = @_;
713        # Parse out the location elements. Note that this works on both old-style and new-style
714        # locations.
715        my ($contigID, $start, $dir, $len) = ParseLocation($location);
716        # Declare the return variable.
717        my $retVal;
718        # Compute the offset. The computation is dependent on the direction of the location.
719        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
720        # Return the offset if it's valid.
721        if ($offset < $len) {
722            $retVal = $offset;
723        }
724        # Return the offset found.
725        return $retVal;
726    }
727    
728  =head3 DNASeq  =head3 DNASeq
729    
730  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
731    
732  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
733  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,
734  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>.
735    
736  =over 4  =over 4
# Line 699  Line 747 
747  =back  =back
748    
749  =cut  =cut
750    #: Return Type $;
751  sub DNASeq {  sub DNASeq {
752          # Get the parameters.          # Get the parameters.
753          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
754          # Create the return string.          # Create the return string.
755          my $retVal = "";          my $retVal = "";
756          # Loop through the locations.          # Loop through the locations.
# Line 773  Line 820 
820  =back  =back
821    
822  =cut  =cut
823    #: Return Type @;
824  sub AllContigs {  sub AllContigs {
825          # Get the parameters.          # Get the parameters.
826          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
827          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
828          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
829                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 797  Line 843 
843    
844  ID of the contig whose length is desired.  ID of the contig whose length is desired.
845    
846    =item RETURN
847    
848    Returns the number of positions in the contig.
849    
850  =back  =back
851    
852  =cut  =cut
853    #: Return Type $;
854  sub ContigLength {  sub ContigLength {
855          # Get the parameters.          # Get the parameters.
856          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
857          # Get the contig's last sequence.          # Get the contig's last sequence.
858          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
859                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 846  Line 895 
895  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
896  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
897  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
898  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
899    roughly by location.
900    
901  =back  =back
902    
903  =cut  =cut
904    #: Return Type @@;
905  sub GenesInRegion {  sub GenesInRegion {
906          # Get the parameters.          # Get the parameters.
907          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
908          # Get the maximum segment length.          # Get the maximum segment length.
909          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
910          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
911          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
912        # containing the minimum and maximum offsets. We will use the offsets to sort the results
913        # when we're building the result set.
914          my %featuresFound = ();          my %featuresFound = ();
915          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
916          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
917        my ($min, $max) = @initialMinMax;
918          # 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
919          # 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,
920          # 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 944 
944                                          $found = 1;                                          $found = 1;
945                                  }                                  }
946                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
947                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
948                                  if ($end <= $stop) {                  # ending.
949                    ($beg, $end) = ($beg - $len, $beg);
950                    if ($beg <= $stop) {
951                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
952                                          $found = 1;                                          $found = 1;
953                                  }                                  }
954                          }                          }
955                          if ($found) {                          if ($found) {
956                                  # 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,
957                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
958                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
959                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
960                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
961                                  if ($end > $max) { $max = $end; }                  # global min and max.
962                    if ($beg < $loc1) {
963                        $loc1 = $beg;
964                        $min = $beg if $beg < $min;
965                    }
966                    if ($end > $loc2) {
967                        $loc2 = $end;
968                        $max = $end if $end > $max;
969                    }
970                    # Store the entry back into the hash table.
971                    $featuresFound{$featureID} = [$loc1, $loc2];
972                          }                          }
973                  }                  }
974          }          }
975          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
976          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
977        # but the result of the sort will be the same.)
978        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
979        # Now we sort by midpoint and yank out the feature IDs.
980        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
981          # Return it along with the min and max.          # Return it along with the min and max.
982          return (\@list, $min, $max);      return (\@retVal, $min, $max);
983  }  }
984    
985  =head3 FType  =head3 FType
# Line 934  Line 1002 
1002  =back  =back
1003    
1004  =cut  =cut
1005    #: Return Type $;
1006  sub FType {  sub FType {
1007          # Get the parameters.          # Get the parameters.
1008          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1009          # Get the specified feature's type.          # Get the specified feature's type.
1010          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1011          # Return the result.          # Return the result.
# Line 963  Line 1030 
1030    
1031  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1032    
1033  * B<timeStamp> time the annotation was made.  * B<timeStamp> time the annotation was made, in user-friendly format.
1034    
1035  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1036    
# Line 972  Line 1039 
1039  =back  =back
1040    
1041  =cut  =cut
1042    #: Return Type @%;
1043  sub FeatureAnnotations {  sub FeatureAnnotations {
1044          # Get the parameters.          # Get the parameters.
1045          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1046          # 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.
1047          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1048                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 990  Line 1056 
1056                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1057                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1058                  # Assemble them into a hash.                  # Assemble them into a hash.
1059                  my $annotationHash = { featureID => $featureID, timeStamp => $timeStamp,          my $annotationHash = { featureID => $featureID,
1060                                   timeStamp => FriendlyTimestamp($timeStamp),
1061                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1062                  # Add it to the return list.                  # Add it to the return list.
1063                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1004  Line 1071 
1071  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1072    
1073  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
1074  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,
1075  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
1076  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,
1077  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.
1078  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1079    recent one.
1080    
1081  =over 4  =over 4
1082    
# Line 1016  Line 1084 
1084    
1085  ID of the feature whose functional assignments are desired.  ID of the feature whose functional assignments are desired.
1086    
1087    =item RETURN
1088    
1089    Returns a hash mapping the functional assignment IDs to user IDs.
1090    
1091  =back  =back
1092    
1093  =cut  =cut
1094    #: Return Type %;
1095  sub AllFunctionsOf {  sub AllFunctionsOf {
1096          # Get the parameters.          # Get the parameters.
1097          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1098          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1099          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1100                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1101                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);
1102          # Declare the return hash.          # Declare the return hash.
1103          my %retVal;          my %retVal;
1104        # Declare a hash for insuring we only make one assignment per user.
1105        my %timeHash = ();
1106        # Now we sort the assignments by timestamp in reverse.
1107        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1108          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1109          for my $text (@query) {      for my $annotation (@sortedQuery) {
1110            # Get the annotation fields.
1111            my ($timeStamp, $text) = @{$annotation};
1112                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1113                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1114                  if ($user) {          if ($user && ! exists $timeHash{$user}) {
1115                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1116                # previous assignment for this user, so we stuff it in the
1117                # return hash.
1118                          $retVal{$function} = $user;                          $retVal{$function} = $user;
1119                # Insure we don't assign to this user again.
1120                $timeHash{$user} = 1;
1121                  }                  }
1122          }          }
1123          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1047  Line 1128 
1128    
1129  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>
1130    
1131  Return the most recently-determined functional assignment of a particular feature. A functional  Return the most recently-determined functional assignment of a particular feature.
1132  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  
1133  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
1134  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
1135  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
1136    L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1137    annotation itself because it's a text field; however, this is not a big problem because
1138    most features only have a small number of annotations.
1139    
1140    Each user has an associated list of trusted users. The assignment returned will be the most
1141    recent one by at least one of the trusted users. If no trusted user list is available, then
1142    the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1143    is trusted.
1144    
1145    If the feature is B<not> identified by a FIG ID, then the functional assignment
1146    information is taken from the B<ExternalAliasFunc> table. If the table does
1147    not contain an entry for the feature, an undefined value is returned.
1148    
1149  =over 4  =over 4
1150    
# Line 1061  Line 1154 
1154    
1155  =item userID (optional)  =item userID (optional)
1156    
1157  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
1158    C<FIG> assignment will be returned.
1159    
1160  =item RETURN  =item RETURN
1161    
# Line 1070  Line 1164 
1164  =back  =back
1165    
1166  =cut  =cut
1167    #: Return Type $;
1168  sub FunctionOf {  sub FunctionOf {
1169          # Get the parameters.          # Get the parameters.
1170          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
1171          my ($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.  
1172          my $retVal;          my $retVal;
1173        # Determine the ID type.
1174        if ($featureID =~ m/^fig\|/) {
1175            # Here we have a FIG feature ID. We must build the list of trusted
1176            # users.
1177            my %trusteeTable = ();
1178            # Check the user ID.
1179            if (!$userID) {
1180                # No user ID, so only FIG is trusted.
1181                $trusteeTable{FIG} = 1;
1182            } else {
1183                # Add this user's ID.
1184                $trusteeTable{$userID} = 1;
1185                # Look for the trusted users in the database.
1186                my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)');
1187                if (! @trustees) {
1188                    # None were found, so build a default list.
1189                    $trusteeTable{FIG} = 1;
1190                } else {
1191                    # Otherwise, put all the trustees in.
1192                    for my $trustee (@trustees) {
1193                        $trusteeTable{$trustee} = 1;
1194                    }
1195                }
1196            }
1197            # Build a query for all of the feature's annotations, sorted by date.
1198            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],
1199                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1200                                   [$featureID]);
1201          my $timeSelected = 0;          my $timeSelected = 0;
1202          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1203          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1204                  # Get the annotation text.                  # Get the annotation text.
1205                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1206                  # Check to see if this is a functional assignment for the desired user.              # Check to see if this is a functional assignment for a trusted user.
1207                  my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1208                  if ($type =~ m/^set $userID function to$/i) {              if ($user) {
1209                          # Here it is, so we check the time and save the assignment value.                  # Here it is a functional assignment. Check the time and the user
1210                          if ($time > $timeSelected) {                  # name. The time must be recent and the user must be trusted.
1211                    if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
1212                                  $retVal = $function;                                  $retVal = $function;
1213                                  $timeSelected = $time;                                  $timeSelected = $time;
1214                          }                          }
1215                  }                  }
1216          }          }
1217        } else {
1218            # Here we have a non-FIG feature ID. In this case the user ID does not
1219            # matter. We simply get the information from the External Alias Function
1220            # table.
1221            ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);
1222        }
1223          # Return the assignment found.          # Return the assignment found.
1224          return $retVal;          return $retVal;
1225  }  }
# Line 1120  Line 1243 
1243    
1244  =item RETURN  =item RETURN
1245    
1246  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
1247  their best hits.  on the target genome.
1248    
1249  =back  =back
1250    
1251  =cut  =cut
1252    #: Return Type %;
1253  sub BBHList {  sub BBHList {
1254          # Get the parameters.          # Get the parameters.
1255          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1256          # Create the return structure.          # Create the return structure.
1257          my %retVal = ();          my %retVal = ();
1258          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1150  Line 1272 
1272          return \%retVal;          return \%retVal;
1273  }  }
1274    
1275    =head3 SimList
1276    
1277    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1278    
1279    Return a list of the similarities to the specified feature.
1280    
1281    Sprout does not support real similarities, so this method just returns the bidirectional
1282    best hits.
1283    
1284    =over 4
1285    
1286    =item featureID
1287    
1288    ID of the feature whose similarities are desired.
1289    
1290    =item count
1291    
1292    Maximum number of similar features to be returned, or C<0> to return them all.
1293    
1294    =back
1295    
1296    =cut
1297    #: Return Type %;
1298    sub SimList {
1299        # Get the parameters.
1300        my ($self, $featureID, $count) = @_;
1301        # Ask for the best hits.
1302        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1303                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1304                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1305                                  $count);
1306        # Create the return value.
1307        my %retVal = ();
1308        for my $tuple (@lists) {
1309            $retVal{$tuple->[0]} = $tuple->[1];
1310        }
1311        # Return the result.
1312        return %retVal;
1313    }
1314    
1315    
1316    
1317    =head3 IsComplete
1318    
1319    C<< my $flag = $sprout->IsComplete($genomeID); >>
1320    
1321    Return TRUE if the specified genome is complete, else FALSE.
1322    
1323    =over 4
1324    
1325    =item genomeID
1326    
1327    ID of the genome whose completeness status is desired.
1328    
1329    =item RETURN
1330    
1331    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1332    not found.
1333    
1334    =back
1335    
1336    =cut
1337    #: Return Type $;
1338    sub IsComplete {
1339        # Get the parameters.
1340        my ($self, $genomeID) = @_;
1341        # Declare the return variable.
1342        my $retVal;
1343        # Get the genome's data.
1344        my $genomeData = $self->GetEntity('Genome', $genomeID);
1345        if ($genomeData) {
1346            # The genome exists, so get the completeness flag.
1347            ($retVal) = $genomeData->Value('complete');
1348        }
1349        # Return the result.
1350        return $retVal;
1351    }
1352    
1353  =head3 FeatureAliases  =head3 FeatureAliases
1354    
1355  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1170  Line 1370 
1370  =back  =back
1371    
1372  =cut  =cut
1373    #: Return Type @;
1374  sub FeatureAliases {  sub FeatureAliases {
1375          # Get the parameters.          # Get the parameters.
1376          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1377          # Get the desired feature's aliases          # Get the desired feature's aliases
1378          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1379          # Return the result.          # Return the result.
# Line 1201  Line 1400 
1400  =back  =back
1401    
1402  =cut  =cut
1403    #: Return Type $;
1404  sub GenomeOf {  sub GenomeOf {
1405          # Get the parameters.          # Get the parameters.
1406          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1407          # Create a query to find the genome associated with the feature.          # Create a query to find the genome associated with the feature.
1408          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1409          # Declare the return value.          # Declare the return value.
# Line 1238  Line 1436 
1436  =back  =back
1437    
1438  =cut  =cut
1439    #: Return Type %;
1440  sub CoupledFeatures {  sub CoupledFeatures {
1441          # Get the parameters.          # Get the parameters.
1442          my $self = shift @_;      my ($self, $featureID) = @_;
1443          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1444          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1445          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1446          # 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.
1447          my $found = 0;          my $found = 0;
1448          # Create the return hash.          # Create the return hash.
1449          my %retVal = ();          my %retVal = ();
1450          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1451          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1452                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1453                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1454                                                            'Coupling(score)']);
1455            # The coupling ID contains the two feature IDs separated by a space. We use
1456            # this information to find the ID of the other feature.
1457            my ($fid1, $fid2) = split / /, $couplingID;
1458            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1459            # Attach the other feature's score to its ID.
1460                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1461                  $found = 1;                  $found = 1;
1462          }          }
# Line 1268  Line 1469 
1469          return %retVal;          return %retVal;
1470  }  }
1471    
1472    =head3 CouplingEvidence
1473    
1474    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1475    
1476    Return the evidence for a functional coupling.
1477    
1478    A pair of features is considered evidence of a coupling between two other
1479    features if they occur close together on a contig and both are similar to
1480    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1481    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1482    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1483    similar to B<A2>.
1484    
1485    The score of a coupling is determined by the number of pieces of evidence
1486    that are considered I<representative>. If several evidence items belong to
1487    a group of genomes that are close to each other, only one of those items
1488    is considered representative. The other evidence items are presumed to be
1489    there because of the relationship between the genomes rather than because
1490    the two proteins generated by the features have a related functionality.
1491    
1492    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1493    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1494    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1495    and FALSE otherwise.
1496    
1497    =over 4
1498    
1499    =item peg1
1500    
1501    ID of the feature of interest.
1502    
1503    =item peg2
1504    
1505    ID of a feature functionally coupled to the feature of interest.
1506    
1507    =item RETURN
1508    
1509    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1510    of interest, a feature similar to the functionally coupled feature, and a flag
1511    that is TRUE for a representative piece of evidence and FALSE otherwise.
1512    
1513    =back
1514    
1515    =cut
1516    #: Return Type @@;
1517    sub CouplingEvidence {
1518        # Get the parameters.
1519        my ($self, $peg1, $peg2) = @_;
1520        # Declare the return variable.
1521        my @retVal = ();
1522        # Our first task is to find out the nature of the coupling: whether or not
1523        # it exists, its score, and whether the features are stored in the same
1524        # order as the ones coming in.
1525        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1526        # Only proceed if a coupling exists.
1527        if ($couplingID) {
1528            # Determine the ordering to place on the evidence items. If we're
1529            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1530            # we want feature 1 before feature 2 (normal).
1531            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1532            my $ordering = ($inverted ? "DESC" : "");
1533            # Get the coupling evidence.
1534            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1535                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1536                                              [$couplingID],
1537                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1538            # Loop through the evidence items. Each piece of evidence is represented by two
1539            # positions in the evidence list, one for each feature on the other side of the
1540            # evidence link. If at some point we want to generalize to couplings with
1541            # more than two positions, this section of code will need to be re-done.
1542            while (@evidenceList > 0) {
1543                my $peg1Data = shift @evidenceList;
1544                my $peg2Data = shift @evidenceList;
1545                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1546                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1547            }
1548            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1549        }
1550        # Return the result.
1551        return @retVal;
1552    }
1553    
1554    =head3 GetCoupling
1555    
1556    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1557    
1558    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1559    exists, we return the coupling ID along with an indicator of whether the
1560    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1561    In the second case, we say the coupling is I<inverted>. The importance of an
1562    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1563    
1564    =over 4
1565    
1566    =item peg1
1567    
1568    ID of the feature of interest.
1569    
1570    =item peg2
1571    
1572    ID of the potentially coupled feature.
1573    
1574    =item RETURN
1575    
1576    Returns a three-element list. The first element contains the database ID of
1577    the coupling. The second element is FALSE if the coupling is stored in the
1578    database in the caller specified order and TRUE if it is stored in the
1579    inverted order. The third element is the coupling's score. If the coupling
1580    does not exist, all three list elements will be C<undef>.
1581    
1582    =back
1583    
1584    =cut
1585    #: Return Type $%@;
1586    sub GetCoupling {
1587        # Get the parameters.
1588        my ($self, $peg1, $peg2) = @_;
1589        # Declare the return values. We'll start with the coupling ID and undefine the
1590        # flag and score until we have more information.
1591        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1592        # Find the coupling data.
1593        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1594                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1595                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1596        # Check to see if we found anything.
1597        if (!@pegs) {
1598            Trace("No coupling found.") if T(Coupling => 4);
1599            # No coupling, so undefine the return value.
1600            $retVal = undef;
1601        } else {
1602            # We have a coupling! Get the score and check for inversion.
1603            $score = $pegs[0]->[1];
1604            my $firstFound = $pegs[0]->[0];
1605            $inverted = ($firstFound ne $peg1);
1606            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1607        }
1608        # Return the result.
1609        return ($retVal, $inverted, $score);
1610    }
1611    
1612    =head3 CouplingID
1613    
1614    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1615    
1616    Return the coupling ID for a pair of feature IDs.
1617    
1618    The coupling ID is currently computed by joining the feature IDs in
1619    sorted order with a space. Client modules (that is, modules which
1620    use Sprout) should not, however, count on this always being the
1621    case. This method provides a way for abstracting the concept of a
1622    coupling ID. All that we know for sure about it is that it can be
1623    generated easily from the feature IDs and the order of the IDs
1624    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1625    will have the same value as C<CouplingID("b1", "a1")>.
1626    
1627    =over 4
1628    
1629    =item peg1
1630    
1631    First feature of interest.
1632    
1633    =item peg2
1634    
1635    Second feature of interest.
1636    
1637    =item RETURN
1638    
1639    Returns the ID that would be used to represent a functional coupling of
1640    the two specified PEGs.
1641    
1642    =back
1643    
1644    =cut
1645    #: Return Type $;
1646    sub CouplingID {
1647        return join " ", sort @_;
1648    }
1649    
1650  =head3 GetEntityTypes  =head3 GetEntityTypes
1651    
1652  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1275  Line 1654 
1654  Return the list of supported entity types.  Return the list of supported entity types.
1655    
1656  =cut  =cut
1657    #: Return Type @;
1658  sub GetEntityTypes {  sub GetEntityTypes {
1659          # Get the parameters.          # Get the parameters.
1660          my $self = shift @_;      my ($self) = @_;
1661          # Get the underlying database object.          # Get the underlying database object.
1662          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1663          # Get its entity type list.          # Get its entity type list.
# Line 1310  Line 1689 
1689  =back  =back
1690    
1691  =cut  =cut
1692    #: Return Type %;
1693  sub ReadFasta {  sub ReadFasta {
1694          # Get the parameters.          # Get the parameters.
1695          my ($fileName, $prefix) = @_;          my ($fileName, $prefix) = @_;
# Line 1329  Line 1708 
1708                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1709                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1710                          if ($id) {                          if ($id) {
1711                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1712                          }                          }
1713                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1714                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1715                  } else {                  } else {
1716                          # 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.
1717                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1718                # case.
1719                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1720                          $sequence .= $1;                          $sequence .= $1;
1721                  }                  }
1722          }          }
1723          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1724          if ($sequence) {          if ($sequence) {
1725                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1726          }          }
1727        # Close the file.
1728        close FASTAFILE;
1729          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1730          return %retVal;          return %retVal;
1731  }  }
# Line 1354  Line 1736 
1736    
1737  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
1738  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
1739  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,
1740    it will not be changed; otherwise, it will be converted. This method can also be used to
1741    perform the reverse task-- insuring that all the locations are in the old format.
1742    
1743  =over 4  =over 4
1744    
# Line 1378  Line 1762 
1762  =back  =back
1763    
1764  =cut  =cut
1765    #: Return Type @;
1766  sub FormatLocations {  sub FormatLocations {
1767          # Get the parameters.          # Get the parameters.
1768          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1769          # Create the return list.          # Create the return list.
1770          my @retVal = ();          my @retVal = ();
1771          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1772          if ($locations eq '') {          if ($locations eq '') {
1773              confess "No locations specified.";          Confess("No locations specified.");
1774          } else {          } else {
1775                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1776                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1422  Line 1805 
1805    
1806  sub DumpData {  sub DumpData {
1807          # Get the parameters.          # Get the parameters.
1808          my $self = shift @_;      my ($self) = @_;
1809          # Get the data directory name.          # Get the data directory name.
1810          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1811          # Dump the relations.          # Dump the relations.
# Line 1436  Line 1819 
1819  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
1820    
1821  =cut  =cut
1822    #: Return Type $;
1823  sub XMLFileName {  sub XMLFileName {
1824          my $self = shift @_;      my ($self) = @_;
1825          return $self->{_xmlName};          return $self->{_xmlName};
1826  }  }
1827    
# Line 1458  Line 1841 
1841  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
1842  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>.
1843    
1844  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'}); >>
1845    
1846  =over 4  =over 4
1847    
# Line 1473  Line 1856 
1856  =back  =back
1857    
1858  =cut  =cut
1859    #: Return Type ;
1860  sub Insert {  sub Insert {
1861          # Get the parameters.          # Get the parameters.
1862          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1863          # Call the underlying method.          # Call the underlying method.
1864          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1865  }  }
# Line 1515  Line 1897 
1897  =back  =back
1898    
1899  =cut  =cut
1900    #: Return Type $;
1901  sub Annotate {  sub Annotate {
1902          # Get the parameters.          # Get the parameters.
1903          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1904          # Create the annotation ID.          # Create the annotation ID.
1905          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1906          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1539  Line 1920 
1920    
1921  =head3 AssignFunction  =head3 AssignFunction
1922    
1923  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1924    
1925  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
1926  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.  
1927    
1928  =over 4  =over 4
1929    
# Line 1553  Line 1933 
1933    
1934  =item user  =item user
1935    
1936  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>.
1937    
1938  =item function  =item function
1939    
1940  Text of the function being assigned.  Text of the function being assigned.
1941    
1942    =item assigningUser (optional)
1943    
1944    Name of the individual user making the assignment. If omitted, defaults to the user group.
1945    
1946  =item RETURN  =item RETURN
1947    
1948  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1566  Line 1950 
1950  =back  =back
1951    
1952  =cut  =cut
1953    #: Return Type $;
1954  sub AssignFunction {  sub AssignFunction {
1955          # Get the parameters.          # Get the parameters.
1956          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1957          my ($featureID, $user, $function) = @_;      # Default the assigning user.
1958        if (! $assigningUser) {
1959            $assigningUser = $user;
1960        }
1961          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1962          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1963          # Get the current time.          # Get the current time.
1964          my $now = time;          my $now = time;
1965          # Declare the return variable.          # Declare the return variable.
# Line 1614  Line 2001 
2001  =back  =back
2002    
2003  =cut  =cut
2004    #: Return Type @;
2005  sub FeaturesByAlias {  sub FeaturesByAlias {
2006          # Get the parameters.          # Get the parameters.
2007          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2008          # Declare the return variable.          # Declare the return variable.
2009          my @retVal = ();          my @retVal = ();
2010          # Parse the alias.          # Parse the alias.
# Line 1657  Line 2043 
2043  =back  =back
2044    
2045  =cut  =cut
2046    #: Return Type $;
2047  sub Exists {  sub Exists {
2048          # Get the parameters.          # Get the parameters.
2049          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2050          # Check for the entity instance.          # Check for the entity instance.
2051        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2052          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2053          # Return an existence indicator.          # Return an existence indicator.
2054          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1688  Line 2074 
2074  =back  =back
2075    
2076  =cut  =cut
2077    #: Return Type $;
2078  sub FeatureTranslation {  sub FeatureTranslation {
2079          # Get the parameters.          # Get the parameters.
2080          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2081          # Get the specified feature's translation.          # Get the specified feature's translation.
2082          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2083          return $retVal;          return $retVal;
# Line 1721  Line 2106 
2106  =back  =back
2107    
2108  =cut  =cut
2109    #: Return Type @;
2110  sub Taxonomy {  sub Taxonomy {
2111          # Get the parameters.          # Get the parameters.
2112          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2113          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2114          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2115          # Declare the return variable.          # Declare the return variable.
# Line 1765  Line 2149 
2149  =back  =back
2150    
2151  =cut  =cut
2152    #: Return Type $;
2153  sub CrudeDistance {  sub CrudeDistance {
2154          # Get the parameters.          # Get the parameters.
2155          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2156          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2157          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2158          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1813  Line 2196 
2196  =back  =back
2197    
2198  =cut  =cut
2199    #: Return Type $;
2200  sub RoleName {  sub RoleName {
2201          # Get the parameters.          # Get the parameters.
2202          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2203          # Get the specified role's name.          # Get the specified role's name.
2204          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2205          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1847  Line 2229 
2229  =back  =back
2230    
2231  =cut  =cut
2232    #: Return Type @;
2233  sub RoleDiagrams {  sub RoleDiagrams {
2234          # Get the parameters.          # Get the parameters.
2235          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2236          # Query for the diagrams.          # Query for the diagrams.
2237          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2238                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1859  Line 2240 
2240          return @retVal;          return @retVal;
2241  }  }
2242    
2243    =head3 GetProperties
2244    
2245    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2246    
2247    Return a list of the properties with the specified characteristics.
2248    
2249    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2250    will also be associated with genomes.) A property value is represented by a 4-tuple of
2251    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2252    
2253    =over 4
2254    
2255    =item fid
2256    
2257    ID of the feature possessing the property.
2258    
2259    =item key
2260    
2261    Name or key of the property.
2262    
2263    =item value
2264    
2265    Value of the property.
2266    
2267    =item url
2268    
2269    URL of the document that indicated the property should have this particular value, or an
2270    empty string if no such document exists.
2271    
2272    =back
2273    
2274    The parameters act as a filter for the desired data. Any non-null parameter will
2275    automatically match all the tuples returned. So, specifying just the I<$fid> will
2276    return all the properties of the specified feature; similarly, specifying the I<$key>
2277    and I<$value> parameters will return all the features having the specified property
2278    value.
2279    
2280    A single property key can have many values, representing different ideas about the
2281    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2282    virulent, and another may declare that it is not virulent. A query about the virulence of
2283    C<fig|83333.1.peg.10> would be coded as
2284    
2285        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2286    
2287    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2288    not to be filtered. The tuples returned would be
2289    
2290        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2291        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2292    
2293    =cut
2294    #: Return Type @@;
2295    sub GetProperties {
2296        # Get the parameters.
2297        my ($self, @parms) = @_;
2298        # Declare the return variable.
2299        my @retVal = ();
2300        # Now we need to create a WHERE clause that will get us the data we want. First,
2301        # we create a list of the columns containing the data for each parameter.
2302        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2303                        'Property(property-value)', 'HasProperty(evidence)');
2304        # Now we build the WHERE clause and the list of parameter values.
2305        my @where = ();
2306        my @values = ();
2307        for (my $i = 0; $i <= $#colNames; $i++) {
2308            my $parm = $parms[$i];
2309            if (defined $parm && ($parm ne '')) {
2310                push @where, "$colNames[$i] = ?";
2311                push @values, $parm;
2312            }
2313        }
2314        # Format the WHERE clause.
2315        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2316        # Ask for all the propertie values with the desired characteristics.
2317        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2318        while (my $valueObject = $query->Fetch()) {
2319            my @tuple = $valueObject->Values(\@colNames);
2320            push @retVal, \@tuple;
2321        }
2322        # Return the result.
2323        return @retVal;
2324    }
2325    
2326  =head3 FeatureProperties  =head3 FeatureProperties
2327    
2328  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1885  Line 2349 
2349  =back  =back
2350    
2351  =cut  =cut
2352    #: Return Type @@;
2353  sub FeatureProperties {  sub FeatureProperties {
2354          # Get the parameters.          # Get the parameters.
2355          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2356          # Get the properties.          # Get the properties.
2357          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2358                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1917  Line 2380 
2380  =back  =back
2381    
2382  =cut  =cut
2383    #: Return Type $;
2384  sub DiagramName {  sub DiagramName {
2385          # Get the parameters.          # Get the parameters.
2386          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2387          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2388          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2389          return $retVal;          return $retVal;
# Line 1950  Line 2412 
2412  =back  =back
2413    
2414  =cut  =cut
2415    #: Return Type @;
2416  sub MergedAnnotations {  sub MergedAnnotations {
2417          # Get the parameters.          # Get the parameters.
2418          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2419          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2420          my @tuples = ();          my @tuples = ();
2421          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 1969  Line 2430 
2430          }          }
2431          # Sort the result list by timestamp.          # Sort the result list by timestamp.
2432          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;
2433        # Loop through and make the time stamps friendly.
2434        for my $tuple (@retVal) {
2435            $tuple->[1] = FriendlyTimestamp($tuple->[1]);
2436        }
2437          # Return the sorted list.          # Return the sorted list.
2438          return @retVal;          return @retVal;
2439  }  }
# Line 1995  Line 2460 
2460  =back  =back
2461    
2462  =cut  =cut
2463    #: Return Type @;
2464  sub RoleNeighbors {  sub RoleNeighbors {
2465          # Get the parameters.          # Get the parameters.
2466          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2467          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2468          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2469                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2038  Line 2502 
2502  =back  =back
2503    
2504  =cut  =cut
2505    #: Return Type @;
2506  sub FeatureLinks {  sub FeatureLinks {
2507          # Get the parameters.          # Get the parameters.
2508          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2509          # Get the feature's links.          # Get the feature's links.
2510          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2511          # Return the feature's links.          # Return the feature's links.
# Line 2054  Line 2517 
2517  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2518    
2519  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
2520  to the role the feature performs.  to the roles the feature performs.
2521    
2522  =over 4  =over 4
2523    
# Line 2064  Line 2527 
2527    
2528  =item RETURN  =item RETURN
2529    
2530  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.
2531    
2532  =back  =back
2533    
2534  =cut  =cut
2535    #: Return Type %@;
2536  sub SubsystemsOf {  sub SubsystemsOf {
2537          # Get the parameters.          # Get the parameters.
2538          my $self = shift @_;      my ($self, $featureID) = @_;
2539          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2540          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2541                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2542                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2082  Line 2544 
2544          my %retVal = ();          my %retVal = ();
2545          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2546          for my $record (@subsystems) {          for my $record (@subsystems) {
2547                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2548            if (exists $retVal{$subsys}) {
2549                push @{$retVal{$subsys}}, $role;
2550            } else {
2551                $retVal{$subsys} = [$role];
2552            }
2553          }          }
2554          # Return the hash.          # Return the hash.
2555          return %retVal;          return %retVal;
2556  }  }
2557    
2558    =head3 SubsystemList
2559    
2560    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2561    
2562    Return a list containing the names of the subsystems in which the specified
2563    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2564    subsystem names, not the roles.
2565    
2566    =over 4
2567    
2568    =item featureID
2569    
2570    ID of the feature whose subsystem names are desired.
2571    
2572    =item RETURN
2573    
2574    Returns a list of the names of the subsystems in which the feature participates.
2575    
2576    =back
2577    
2578    =cut
2579    #: Return Type @;
2580    sub SubsystemList {
2581        # Get the parameters.
2582        my ($self, $featureID) = @_;
2583        # Get the list of names.
2584        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2585                                    [$featureID], 'HasSSCell(from-link)');
2586        # Return the result.
2587        return @retVal;
2588    }
2589    
2590  =head3 RelatedFeatures  =head3 RelatedFeatures
2591    
2592  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2118  Line 2617 
2617  =back  =back
2618    
2619  =cut  =cut
2620    #: Return Type @;
2621  sub RelatedFeatures {  sub RelatedFeatures {
2622          # Get the parameters.          # Get the parameters.
2623          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2624          # 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.
2625          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2626                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2167  Line 2665 
2665  =back  =back
2666    
2667  =cut  =cut
2668    #: Return Type @;
2669  sub TaxonomySort {  sub TaxonomySort {
2670          # Get the parameters.          # Get the parameters.
2671          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2672          # Create the working hash table.          # Create the working hash table.
2673          my %hashBuffer = ();          my %hashBuffer = ();
2674          # Loop through the features.          # Loop through the features.
# Line 2180  Line 2677 
2677                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2678                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2679                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2680                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2681          }          }
2682          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2683          my @retVal = ();          my @retVal = ();
# Line 2250  Line 2743 
2743  =back  =back
2744    
2745  =cut  =cut
2746    #: Return Type @@;
2747  sub GetAll {  sub GetAll {
2748          # Get the parameters.          # Get the parameters.
2749          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2750          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2751          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2752          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++;  
         }  
2753          # Return the resulting list.          # Return the resulting list.
2754          return @retVal;          return @retVal;
2755  }  }
# Line 2312  Line 2791 
2791  =back  =back
2792    
2793  =cut  =cut
2794    #: Return Type @;
2795  sub GetFlat {  sub GetFlat {
2796          # Get the parameters.          # Get the parameters.
2797          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2798          # Construct the query.          # Construct the query.
2799          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2800          # Create the result list.          # Create the result list.
# Line 2423  Line 2901 
2901  to load the entire database.  to load the entire database.
2902    
2903  =cut  =cut
2904    #: Return Type @;
2905  sub LoadInfo {  sub LoadInfo {
2906          # Get the parameters.          # Get the parameters.
2907          my $self = shift @_;      my ($self) = @_;
2908          # 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.
2909          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2910          # Concatenate the table names.          # Concatenate the table names.
# Line 2460  Line 2938 
2938  =back  =back
2939    
2940  =cut  =cut
2941    #: Return Type %;
2942  sub LowBBHs {  sub LowBBHs {
2943          # Get the parsameters.          # Get the parsameters.
2944          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
2945          # Create the return hash.          # Create the return hash.
2946          my %retVal = ();          my %retVal = ();
2947          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2480  Line 2957 
2957          return %retVal;          return %retVal;
2958  }  }
2959    
2960    =head3 GetGroups
2961    
2962    C<< my %groups = $sprout->GetGroups(\@groupList); >>
2963    
2964    Return a hash mapping each group to the IDs of the genomes in the group.
2965    A list of groups may be specified, in which case only those groups will be
2966    shown. Alternatively, if no parameter is supplied, all groups will be
2967    included. Genomes that are not in any group are omitted.
2968    
2969    =cut
2970    #: Return Type %@;
2971    sub GetGroups {
2972        # Get the parameters.
2973        my ($self, $groupList) = @_;
2974        # Declare the return value.
2975        my %retVal = ();
2976        # Determine whether we are getting all the groups or just some.
2977        if (defined $groupList) {
2978            # Here we have a group list. Loop through them individually,
2979            # getting a list of the relevant genomes.
2980            for my $group (@{$groupList}) {
2981                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",
2982                    [$group], "Genome(id)");
2983                $retVal{$group} = \@genomeIDs;
2984            }
2985        } else {
2986            # Here we need all of the groups. In this case, we run through all
2987            # of the genome records, putting each one found into the appropriate
2988            # group. Note that we use a filter clause to insure that only genomes
2989            # in groups are included in the return set.
2990            my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],
2991                                        ['Genome(id)', 'Genome(group-name)']);
2992            # Loop through the genomes found.
2993            for my $genome (@genomes) {
2994                # Pop this genome's ID off the current list.
2995                my @groups = @{$genome};
2996                my $genomeID = shift @groups;
2997                # Loop through the groups, adding the genome ID to each group's
2998                # list.
2999                for my $group (@groups) {
3000                    Tracer::AddToListMap(\%retVal, $group, $genomeID);
3001                }
3002            }
3003        }
3004        # Return the hash we just built.
3005        return %retVal;
3006    }
3007    
3008    =head3 MyGenomes
3009    
3010    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3011    
3012    Return a list of the genomes to be included in the Sprout.
3013    
3014    This method is provided for use during the Sprout load. It presumes the Genome load file has
3015    already been created. (It will be in the Sprout data directory and called either C<Genome>
3016    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3017    IDs.
3018    
3019    =over 4
3020    
3021    =item dataDir
3022    
3023    Directory containing the Sprout load files.
3024    
3025    =back
3026    
3027    =cut
3028    #: Return Type @;
3029    sub MyGenomes {
3030        # Get the parameters.
3031        my ($dataDir) = @_;
3032        # Compute the genome file name.
3033        my $genomeFileName = LoadFileName($dataDir, "Genome");
3034        # Extract the genome IDs from the files.
3035        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3036        # Return the result.
3037        return @retVal;
3038    }
3039    
3040    =head3 LoadFileName
3041    
3042    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3043    
3044    Return the name of the load file for the specified table in the specified data
3045    directory.
3046    
3047    =over 4
3048    
3049    =item dataDir
3050    
3051    Directory containing the Sprout load files.
3052    
3053    =item tableName
3054    
3055    Name of the table whose load file is desired.
3056    
3057    =item RETURN
3058    
3059    Returns the name of the file containing the load data for the specified table, or
3060    C<undef> if no load file is present.
3061    
3062    =back
3063    
3064    =cut
3065    #: Return Type $;
3066    sub LoadFileName {
3067        # Get the parameters.
3068        my ($dataDir, $tableName) = @_;
3069        # Declare the return variable.
3070        my $retVal;
3071        # Check for the various file names.
3072        if (-e "$dataDir/$tableName") {
3073            $retVal = "$dataDir/$tableName";
3074        } elsif (-e "$dataDir/$tableName.dtx") {
3075            $retVal = "$dataDir/$tableName.dtx";
3076        }
3077        # Return the result.
3078        return $retVal;
3079    }
3080    
3081  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3082    
3083  =head3 ParseAssignment  =head3 ParseAssignment
3084    
3085  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3086  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3087  will be returned.  isn't, an empty list will be returned.
3088    
3089    A functional assignment is always of the form
3090    
3091        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3092    
3093    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3094    actual functional role. In most cases, the user and the assigning user will be the
3095    same, but that is not always the case.
3096    
3097  This is a static method.  This is a static method.
3098    
# Line 2505  Line 3111 
3111    
3112  =cut  =cut
3113    
3114  sub ParseAssignment {  sub _ParseAssignment {
3115          # Get the parameters.          # Get the parameters.
3116          my ($text) = @_;          my ($text) = @_;
3117          # Declare the return value.          # Declare the return value.
3118          my @retVal = ();          my @retVal = ();
3119          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3120          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3121          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3122                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3123                  @retVal = ($user, $function);          # and the assigning user.
3124            @retVal = ($1, $function, $user);
3125          }          }
3126          # Return the result list.          # Return the result list.
3127          return @retVal;          return @retVal;
3128  }  }
3129    
3130    =head3 FriendlyTimestamp
3131    
3132    Convert a time number to a user-friendly time stamp for display.
3133    
3134    This is a static method.
3135    
3136    =over 4
3137    
3138    =item timeValue
3139    
3140    Numeric time value.
3141    
3142    =item RETURN
3143    
3144    Returns a string containing the same time in user-readable format.
3145    
3146    =back
3147    
3148    =cut
3149    
3150    sub FriendlyTimestamp {
3151        my ($timeValue) = @_;
3152        my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));
3153        return $retVal;
3154    }
3155    
3156    =head3 AddProperty
3157    
3158    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3159    
3160    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3161    be added to almost any object. In Sprout, they can only be added to features. In
3162    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3163    pair. If the particular key/value pair coming in is not already in the database, a new
3164    B<Property> record is created to hold it.
3165    
3166    =over 4
3167    
3168    =item peg
3169    
3170    ID of the feature to which the attribute is to be replied.
3171    
3172    =item key
3173    
3174    Name of the attribute (key).
3175    
3176    =item value
3177    
3178    Value of the attribute.
3179    
3180    =item url
3181    
3182    URL or text citation from which the property was obtained.
3183    
3184    =back
3185    
3186    =cut
3187    #: Return Type ;
3188    sub AddProperty {
3189        # Get the parameters.
3190        my ($self, $featureID, $key, $value, $url) = @_;
3191        # Declare the variable to hold the desired property ID.
3192        my $propID;
3193        # Attempt to find a property record for this key/value pair.
3194        my @properties = $self->GetFlat(['Property'],
3195                                       "Property(property-name) = ? AND Property(property-value) = ?",
3196                                       [$key, $value], 'Property(id)');
3197        if (@properties) {
3198            # Here the property is already in the database. We save its ID.
3199            $propID = $properties[0];
3200            # Here the property value does not exist. We need to generate an ID. It will be set
3201            # to a number one greater than the maximum value in the database. This call to
3202            # GetAll will stop after one record.
3203            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3204                                            1);
3205            $propID = $maxProperty[0]->[0] + 1;
3206            # Insert the new property value.
3207            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3208        }
3209        # Now we connect the incoming feature to the property.
3210        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3211    }
3212    
3213    
3214    
3215  1;  1;

Legend:
Removed from v.1.1  
changed lines
  Added in v.1.26

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3