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

Diff of /Sprout/Sprout.pm

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

revision 1.8, Thu Jan 27 00:30:20 2005 UTC revision 1.18, Tue Jun 28 21:34:15 2005 UTC
# Line 86  Line 86 
86          # 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
87          # the incoming data.          # the incoming data.
88          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
89                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
90                                             dataDir              => 'Data',                      # data file directory                                                          # database type
91                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
92                                             userData             => 'root/',                     # user name and password                                                          # data file directory
93                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
94                                                            # database definition file name
95                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
96                                                            # user name and password
97                           port         => $FIG_Config::dbport,
98                                                            # database connection port
99                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
100                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
101                                            }, $options);                                            }, $options);
# Line 124  Line 129 
129  =cut  =cut
130  #: Return Type $;  #: Return Type $;
131  sub MaxSegment {  sub MaxSegment {
132          my $self = shift @_;      my ($self) = @_;
133          return $self->{_options}->{maxSegmentLength};          return $self->{_options}->{maxSegmentLength};
134  }  }
135    
# Line 139  Line 144 
144  =cut  =cut
145  #: Return Type $;  #: Return Type $;
146  sub MaxSequence {  sub MaxSequence {
147          my $self = shift @_;      my ($self) = @_;
148          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
149  }  }
150    
# Line 232  Line 237 
237    
238  sub Get {  sub Get {
239          # Get the parameters.          # Get the parameters.
240          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList) = @_;
         my ($objectNames, $filterClause, $parameterList) = @_;  
241          # 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
242          # 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
243          # to a real list. We can only do this if the parameters have been specified.          # to a real list. We can only do this if the parameters have been specified.
# Line 269  Line 273 
273    
274  sub GetEntity {  sub GetEntity {
275          # Get the parameters.          # Get the parameters.
276          my $self = shift @_;      my ($self, $entityType, $ID) = @_;
277          my ($entityType, $ID) = @_;      # Call the ERDB method.
278          # 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;  
279  }  }
280    
281  =head3 GetEntityValues  =head3 GetEntityValues
# Line 309  Line 308 
308  #: Return Type @;  #: Return Type @;
309  sub GetEntityValues {  sub GetEntityValues {
310          # Get the parameters.          # Get the parameters.
311          my $self = shift @_;      my ($self, $entityType, $ID, $fields) = @_;
312          my ($entityType, $ID, $fields) = @_;      # Call the ERDB method.
313          # 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;  
314  }  }
315    
316  =head3 ShowMetaData  =head3 ShowMetaData
# Line 341  Line 331 
331    
332  sub ShowMetaData {  sub ShowMetaData {
333          # Get the parameters.          # Get the parameters.
334          my $self = shift @_;      my ($self, $fileName) = @_;
         my ($fileName) = @_;  
335          # Compute the file name.          # Compute the file name.
336          my $options = $self->{_options};          my $options = $self->{_options};
337          # Call the show method on the underlying ERDB object.          # Call the show method on the underlying ERDB object.
# Line 382  Line 371 
371  #: Return Type %;  #: Return Type %;
372  sub Load {  sub Load {
373          # Get the parameters.          # Get the parameters.
374          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
375          # Get the database object.          # Get the database object.
376          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
377          # Load the tables from the data directory.          # Load the tables from the data directory.
# Line 426  Line 414 
414  #: Return Type $%;  #: Return Type $%;
415  sub LoadUpdate {  sub LoadUpdate {
416          # Get the parameters.          # Get the parameters.
417          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
418          # Get the database object.          # Get the database object.
419          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
420          # Declare the return value.          # Declare the return value.
# Line 438  Line 425 
425          # Loop through the incoming table names.          # Loop through the incoming table names.
426          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
427                  # Find the table's file.                  # Find the table's file.
428                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
429                  if (! -e $fileName) {          if (! $fileName) {
430                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
431                  }          } else {
432                  # Attempt to load this table.                  # Attempt to load this table.
433                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
434                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
435                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
436          }          }
437        }
438          # Return the statistics.          # Return the statistics.
439          return $retVal;          return $retVal;
440  }  }
# Line 463  Line 451 
451  #: Return Type ;  #: Return Type ;
452  sub Build {  sub Build {
453          # Get the parameters.          # Get the parameters.
454          my $self = shift @_;      my ($self) = @_;
455          # Create the tables.          # Create the tables.
456          $self->{_erdb}->CreateTables;          $self->{_erdb}->CreateTables;
457  }  }
# Line 478  Line 466 
466  #: Return Type @;  #: Return Type @;
467  sub Genomes {  sub Genomes {
468          # Get the parameters.          # Get the parameters.
469          my $self = shift @_;      my ($self) = @_;
470          # Get all the genomes.          # Get all the genomes.
471          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
472          # Return the list of IDs.          # Return the list of IDs.
# Line 508  Line 496 
496  #: Return Type $;  #: Return Type $;
497  sub GenusSpecies {  sub GenusSpecies {
498          # Get the parameters.          # Get the parameters.
499          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
500          # Get the data for the specified genome.          # Get the data for the specified genome.
501          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
502                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 545  Line 532 
532  #: Return Type @;  #: Return Type @;
533  sub FeaturesOf {  sub FeaturesOf {
534          # Get the parameters.          # Get the parameters.
535          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
536          # Get the features we want.          # Get the features we want.
537          my @features;          my @features;
538          if (!$ftype) {          if (!$ftype) {
# Line 599  Line 585 
585  #: Return Type $;  #: Return Type $;
586  sub FeatureLocation {  sub FeatureLocation {
587          # Get the parameters.          # Get the parameters.
588          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
589          # Create a query for the feature locations.          # Create a query for the feature locations.
590          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",
591                                                     [$featureID]);                                                     [$featureID]);
# Line 660  Line 645 
645  =cut  =cut
646  #: Return Type @;  #: Return Type @;
647  sub ParseLocation {  sub ParseLocation {
648          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
649        # the first parameter.
650        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
651          my ($location) = @_;          my ($location) = @_;
652          # Parse it into segments.          # Parse it into segments.
653          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;
# Line 679  Line 666 
666          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
667  }  }
668    
669    =head3 PointLocation
670    
671    C<< my $found = Sprout::PointLocation($location, $point); >>
672    
673    Return the offset into the specified location of the specified point on the contig. If
674    the specified point is before the location, a negative value will be returned. If it is
675    beyond the location, an undefined value will be returned. It is assumed that the offset
676    is for the location's contig. The location can either be new-style (using a C<+> or C<->
677    and a length) or old-style (using C<_> and start and end positions.
678    
679    =over 4
680    
681    =item location
682    
683    A location specifier (see L</FeatureLocation> for a description).
684    
685    =item point
686    
687    The offset into the contig of the point in which we're interested.
688    
689    =item RETURN
690    
691    Returns the offset inside the specified location of the specified point, a negative
692    number if the point is before the location, or an undefined value if the point is past
693    the location. If the length of the location is 0, this method will B<always> denote
694    that it is outside the location. The offset will always be relative to the left-most
695    position in the location.
696    
697    =back
698    
699    =cut
700    #: Return Type $;
701    sub PointLocation {
702        # Get the parameter. Note that if we're called as an instance method, we ignore
703        # the first parameter.
704        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
705        my ($location, $point) = @_;
706        # Parse out the location elements. Note that this works on both old-style and new-style
707        # locations.
708        my ($contigID, $start, $dir, $len) = ParseLocation($location);
709        # Declare the return variable.
710        my $retVal;
711        # Compute the offset. The computation is dependent on the direction of the location.
712        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
713        # Return the offset if it's valid.
714        if ($offset < $len) {
715            $retVal = $offset;
716        }
717        # Return the offset found.
718        return $retVal;
719    }
720    
721  =head3 DNASeq  =head3 DNASeq
722    
723  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  C<< my $sequence = $sprout->DNASeq(\@locationList); >>
# Line 704  Line 743 
743  #: Return Type $;  #: Return Type $;
744  sub DNASeq {  sub DNASeq {
745          # Get the parameters.          # Get the parameters.
746          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
747          # Create the return string.          # Create the return string.
748          my $retVal = "";          my $retVal = "";
749          # Loop through the locations.          # Loop through the locations.
# Line 778  Line 816 
816  #: Return Type @;  #: Return Type @;
817  sub AllContigs {  sub AllContigs {
818          # Get the parameters.          # Get the parameters.
819          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
820          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
821          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
822                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 809  Line 846 
846  #: Return Type $;  #: Return Type $;
847  sub ContigLength {  sub ContigLength {
848          # Get the parameters.          # Get the parameters.
849          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
850          # Get the contig's last sequence.          # Get the contig's last sequence.
851          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
852                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 852  Line 888 
888  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
889  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
890  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
891  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
892    roughly by location.
893    
894  =back  =back
895    
896  =cut  =cut
897  #: Return Type @;  #: Return Type @@;
898  sub GenesInRegion {  sub GenesInRegion {
899          # Get the parameters.          # Get the parameters.
900          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
         my ($contigID, $start, $stop) = @_;  
901          # Get the maximum segment length.          # Get the maximum segment length.
902          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
903          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
904          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be a two-element
905        # containing the minimum and maximum offsets. We will use the offsets to sort the results
906        # when we're building the result set.
907          my %featuresFound = ();          my %featuresFound = ();
908          # Prime the values we'll use for the returned beginning and end.          # Prime the values we'll use for the returned beginning and end.
909          my ($min, $max) = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
910        my ($min, $max) = @initialMinMax;
911          # 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
912          # 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,
913          # the lowest possible start position, and the highest possible start position. This works          # the lowest possible start position, and the highest possible start position. This works
# Line 898  Line 937 
937                                          $found = 1;                                          $found = 1;
938                                  }                                  }
939                          } elsif ($dir eq '-') {                          } elsif ($dir eq '-') {
940                                  $end = $beg - $len;                  # Note we switch things around so that the beginning is to the left of the
941                                  if ($end <= $stop) {                  # ending.
942                    ($beg, $end) = ($beg - $len, $beg);
943                    if ($beg <= $stop) {
944                                          # Denote we found a useful feature.                                          # Denote we found a useful feature.
945                                          $found = 1;                                          $found = 1;
946                                  }                                  }
947                          }                          }
948                          if ($found) {                          if ($found) {
949                                  # 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,
950                                  $featuresFound{$featureID} = 1;                  # get the current entry for the specified feature.
951                                  if ($beg < $min) { $min = $beg; }                  my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :
952                                  if ($end < $min) { $min = $end; }                                       @initialMinMax);
953                                  if ($beg > $max) { $max = $beg; }                  # Merge the current segment's begin and end into the feature begin and end and the
954                                  if ($end > $max) { $max = $end; }                  # global min and max.
955                    if ($beg < $loc1) {
956                        $loc1 = $beg;
957                        $min = $beg if $beg < $min;
958                    }
959                    if ($end > $loc2) {
960                        $loc2 = $end;
961                        $max = $end if $end > $max;
962                    }
963                    # Store the entry back into the hash table.
964                    $featuresFound{$featureID} = [$loc1, $loc2];
965                          }                          }
966                  }                  }
967          }          }
968          # Compute a list of the IDs for the features found.      # Now we must compute the list of the IDs for the features found. We start with a list
969          my @list = (sort (keys %featuresFound));      # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
970        # but the result of the sort will be the same.)
971        my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;
972        # Now we sort by midpoint and yank out the feature IDs.
973        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
974          # Return it along with the min and max.          # Return it along with the min and max.
975          return (\@list, $min, $max);      return (\@retVal, $min, $max);
976  }  }
977    
978  =head3 FType  =head3 FType
# Line 943  Line 998 
998  #: Return Type $;  #: Return Type $;
999  sub FType {  sub FType {
1000          # Get the parameters.          # Get the parameters.
1001          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1002          # Get the specified feature's type.          # Get the specified feature's type.
1003          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1004          # Return the result.          # Return the result.
# Line 981  Line 1035 
1035  #: Return Type @%;  #: Return Type @%;
1036  sub FeatureAnnotations {  sub FeatureAnnotations {
1037          # Get the parameters.          # Get the parameters.
1038          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1039          # 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.
1040          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1041                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1011  Line 1064 
1064  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1065    
1066  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
1067  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,
1068  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
1069  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,
1070  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.
1071  features only have a small number of annotations. Finally, if a single user has multiple  Finally, if a single user has multiple functional assignments, we will only keep the most
1072  functional assignments, we will only keep the most recent one.  recent one.
1073    
1074  =over 4  =over 4
1075    
# Line 1034  Line 1087 
1087  #: Return Type %;  #: Return Type %;
1088  sub AllFunctionsOf {  sub AllFunctionsOf {
1089          # Get the parameters.          # Get the parameters.
1090          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1091          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1092      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1093                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
# Line 1051  Line 1103 
1103          # Get the annotation fields.          # Get the annotation fields.
1104          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text) = @{$annotation};
1105                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1106                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1107          if ($user && ! exists $timeHash{$user}) {          if ($user && ! exists $timeHash{$user}) {
1108              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1109              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
# Line 1073  Line 1125 
1125    
1126  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1127  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1128  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is a type of annotation. The format of an assignment is described in
1129  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1130  we cannot filter on the content of the annotation itself because it's a text field; however, this  annotation itself because it's a text field; however, this is not a big problem because
1131  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1132    
1133  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1134  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1108  Line 1160 
1160  #: Return Type $;  #: Return Type $;
1161  sub FunctionOf {  sub FunctionOf {
1162          # Get the parameters.          # Get the parameters.
1163          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1164      # Declare the return value.      # Declare the return value.
1165      my $retVal;      my $retVal;
1166      # Determine the ID type.      # Determine the ID type.
# Line 1146  Line 1197 
1197              # Get the annotation text.              # Get the annotation text.
1198              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1199              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1200              my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1201              if ($type =~ m/^set $user function to$/i) {              if ($user) {
1202                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1203                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1204                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1185  Line 1236 
1236    
1237  =item RETURN  =item RETURN
1238    
1239  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
1240  their best hits.  on the target genome.
1241    
1242  =back  =back
1243    
# Line 1194  Line 1245 
1245  #: Return Type %;  #: Return Type %;
1246  sub BBHList {  sub BBHList {
1247          # Get the parameters.          # Get the parameters.
1248          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1249          # Create the return structure.          # Create the return structure.
1250          my %retVal = ();          my %retVal = ();
1251          # Loop through the incoming features.          # Loop through the incoming features.
# Line 1215  Line 1265 
1265          return \%retVal;          return \%retVal;
1266  }  }
1267    
1268    =head3 SimList
1269    
1270    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1271    
1272    Return a list of the similarities to the specified feature.
1273    
1274    Sprout does not support real similarities, so this method just returns the bidirectional
1275    best hits.
1276    
1277    =over 4
1278    
1279    =item featureID
1280    
1281    ID of the feature whose similarities are desired.
1282    
1283    =item count
1284    
1285    Maximum number of similar features to be returned, or C<0> to return them all.
1286    
1287    =back
1288    
1289    =cut
1290    #: Return Type %;
1291    sub SimList {
1292        # Get the parameters.
1293        my ($self, $featureID, $count) = @_;
1294        # Ask for the best hits.
1295        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1296                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1297                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1298                                  $count);
1299        # Create the return value.
1300        my %retVal = ();
1301        for my $tuple (@lists) {
1302            $retVal{$tuple->[0]} = $tuple->[1];
1303        }
1304        # Return the result.
1305        return %retVal;
1306    }
1307    
1308    
1309    
1310    =head3 IsComplete
1311    
1312    C<< my $flag = $sprout->IsComplete($genomeID); >>
1313    
1314    Return TRUE if the specified genome is complete, else FALSE.
1315    
1316    =over 4
1317    
1318    =item genomeID
1319    
1320    ID of the genome whose completeness status is desired.
1321    
1322    =item RETURN
1323    
1324    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1325    not found.
1326    
1327    =back
1328    
1329    =cut
1330    #: Return Type $;
1331    sub IsComplete {
1332        # Get the parameters.
1333        my ($self, $genomeID) = @_;
1334        # Declare the return variable.
1335        my $retVal;
1336        # Get the genome's data.
1337        my $genomeData = $self->GetEntity('Genome', $genomeID);
1338        if ($genomeData) {
1339            # The genome exists, so get the completeness flag.
1340            ($retVal) = $genomeData->Value('complete');
1341        }
1342        # Return the result.
1343        return $retVal;
1344    }
1345    
1346  =head3 FeatureAliases  =head3 FeatureAliases
1347    
1348  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1238  Line 1366 
1366  #: Return Type @;  #: Return Type @;
1367  sub FeatureAliases {  sub FeatureAliases {
1368          # Get the parameters.          # Get the parameters.
1369          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1370          # Get the desired feature's aliases          # Get the desired feature's aliases
1371          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);
1372          # Return the result.          # Return the result.
# Line 1269  Line 1396 
1396  #: Return Type $;  #: Return Type $;
1397  sub GenomeOf {  sub GenomeOf {
1398          # Get the parameters.          # Get the parameters.
1399          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1400          # Create a query to find the genome associated with the feature.          # Create a query to find the genome associated with the feature.
1401          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);          my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);
1402          # Declare the return value.          # Declare the return value.
# Line 1306  Line 1432 
1432  #: Return Type %;  #: Return Type %;
1433  sub CoupledFeatures {  sub CoupledFeatures {
1434          # Get the parameters.          # Get the parameters.
1435          my $self = shift @_;      my ($self, $featureID) = @_;
1436          my ($featureID) = @_;      # Create a query to retrieve the functionally-coupled features.
1437          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1438          # fact that the functional coupling is physically paired. If (A,B) is in the database, then                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         # (B,A) will also be found.  
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1439          # 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.
1440          my $found = 0;          my $found = 0;
1441          # Create the return hash.          # Create the return hash.
1442          my %retVal = ();          my %retVal = ();
1443          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1444          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1445                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1446                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1447                                                            'Coupling(score)']);
1448            # The coupling ID contains the two feature IDs separated by a space. We use
1449            # this information to find the ID of the other feature.
1450            my ($fid1, $fid2) = split / /, $couplingID;
1451            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1452            # Attach the other feature's score to its ID.
1453                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1454                  $found = 1;                  $found = 1;
1455          }          }
# Line 1333  Line 1462 
1462          return %retVal;          return %retVal;
1463  }  }
1464    
1465    =head3 CouplingEvidence
1466    
1467    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1468    
1469    Return the evidence for a functional coupling.
1470    
1471    A pair of features is considered evidence of a coupling between two other
1472    features if they occur close together on a contig and both are similar to
1473    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1474    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1475    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1476    similar to B<A2>.
1477    
1478    The score of a coupling is determined by the number of pieces of evidence
1479    that are considered I<representative>. If several evidence items belong to
1480    a group of genomes that are close to each other, only one of those items
1481    is considered representative. The other evidence items are presumed to be
1482    there because of the relationship between the genomes rather than because
1483    the two proteins generated by the features have a related functionality.
1484    
1485    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1486    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1487    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1488    and FALSE otherwise.
1489    
1490    =over 4
1491    
1492    =item peg1
1493    
1494    ID of the feature of interest.
1495    
1496    =item peg2
1497    
1498    ID of a feature functionally coupled to the feature of interest.
1499    
1500    =item RETURN
1501    
1502    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1503    of interest, a feature similar to the functionally coupled feature, and a flag
1504    that is TRUE for a representative piece of evidence and FALSE otherwise.
1505    
1506    =back
1507    
1508    =cut
1509    #: Return Type @@;
1510    sub CouplingEvidence {
1511        # Get the parameters.
1512        my ($self, $peg1, $peg2) = @_;
1513        # Declare the return variable.
1514        my @retVal = ();
1515        # Our first task is to find out the nature of the coupling: whether or not
1516        # it exists, its score, and whether the features are stored in the same
1517        # order as the ones coming in.
1518        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1519        # Only proceed if a coupling exists.
1520        if ($couplingID) {
1521            # Determine the ordering to place on the evidence items. If we're
1522            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1523            # we want feature 1 before feature 2 (normal).
1524            my $ordering = ($inverted ? "DESC" : "");
1525            # Get the coupling evidence.
1526            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1527                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1528                                              [$couplingID],
1529                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1530            # Loop through the evidence items. Each piece of evidence is represented by two
1531            # positions in the evidence list, one for each feature on the other side of the
1532            # evidence link. If at some point we want to generalize to couplings with
1533            # more than two positions, this section of code will need to be re-done.
1534            while (@evidenceList > 0) {
1535                my $peg1Data = shift @evidenceList;
1536                my $peg2Data = shift @evidenceList;
1537                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1538            }
1539        }
1540        # Return the result.
1541        return @retVal;
1542    }
1543    
1544    =head3 GetCoupling
1545    
1546    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1547    
1548    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1549    exists, we return the coupling ID along with an indicator of whether the
1550    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1551    In the second case, we say the coupling is I<inverted>. The importance of an
1552    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1553    
1554    =over 4
1555    
1556    =item peg1
1557    
1558    ID of the feature of interest.
1559    
1560    =item peg2
1561    
1562    ID of the potentially coupled feature.
1563    
1564    =item RETURN
1565    
1566    Returns a three-element list. The first element contains the database ID of
1567    the coupling. The second element is FALSE if the coupling is stored in the
1568    database in the caller specified order and TRUE if it is stored in the
1569    inverted order. The third element is the coupling's score. If the coupling
1570    does not exist, all three list elements will be C<undef>.
1571    
1572    =back
1573    
1574    =cut
1575    #: Return Type $%@;
1576    sub GetCoupling {
1577        # Get the parameters.
1578        my ($self, $peg1, $peg2) = @_;
1579        # Declare the return values. We'll start with the coupling ID and undefine the
1580        # flag and score until we have more information.
1581        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1582        # Find the coupling data.
1583        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1584                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1585                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1586        # Check to see if we found anything.
1587        if (!@pegs) {
1588            # No coupling, so undefine the return value.
1589            $retVal = undef;
1590        } else {
1591            # We have a coupling! Get the score and check for inversion.
1592            $score = $pegs[0]->[1];
1593            $inverted = ($pegs[0]->[0] eq $peg1);
1594        }
1595        # Return the result.
1596        return ($retVal, $inverted, $score);
1597    }
1598    
1599    =head3 CouplingID
1600    
1601    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1602    
1603    Return the coupling ID for a pair of feature IDs.
1604    
1605    The coupling ID is currently computed by joining the feature IDs in
1606    sorted order with a space. Client modules (that is, modules which
1607    use Sprout) should not, however, count on this always being the
1608    case. This method provides a way for abstracting the concept of a
1609    coupling ID. All that we know for sure about it is that it can be
1610    generated easily from the feature IDs and the order of the IDs
1611    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1612    will have the same value as C<CouplingID("b1", "a1")>.
1613    
1614    =over 4
1615    
1616    =item peg1
1617    
1618    First feature of interest.
1619    
1620    =item peg2
1621    
1622    Second feature of interest.
1623    
1624    =item RETURN
1625    
1626    Returns the ID that would be used to represent a functional coupling of
1627    the two specified PEGs.
1628    
1629    =back
1630    
1631    =cut
1632    #: Return Type $;
1633    sub CouplingID {
1634        return join " ", sort @_;
1635    }
1636    
1637  =head3 GetEntityTypes  =head3 GetEntityTypes
1638    
1639  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1343  Line 1644 
1644  #: Return Type @;  #: Return Type @;
1645  sub GetEntityTypes {  sub GetEntityTypes {
1646          # Get the parameters.          # Get the parameters.
1647          my $self = shift @_;      my ($self) = @_;
1648          # Get the underlying database object.          # Get the underlying database object.
1649          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1650          # Get its entity type list.          # Get its entity type list.
# Line 1394  Line 1695 
1695                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1696                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1697                          if ($id) {                          if ($id) {
1698                                  $retVal{$id} = $sequence;                  $retVal{$id} = uc $sequence;
1699                          }                          }
1700                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1701                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1702                  } else {                  } else {
1703                          # 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.
1704                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to upper
1705                # case.
1706                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1707                          $sequence .= $1;                          $sequence .= $1;
1708                  }                  }
1709          }          }
1710          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1711          if ($sequence) {          if ($sequence) {
1712                  $retVal {$id} = $sequence;          $retVal{$id} = uc $sequence;
1713          }          }
1714        # Close the file.
1715        close FASTAFILE;
1716          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1717          return %retVal;          return %retVal;
1718  }  }
# Line 1419  Line 1723 
1723    
1724  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
1725  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
1726  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,
1727    it will not be changed; otherwise, it will be converted. This method can also be used to
1728    perform the reverse task-- insuring that all the locations are in the old format.
1729    
1730  =over 4  =over 4
1731    
# Line 1446  Line 1752 
1752  #: Return Type @;  #: Return Type @;
1753  sub FormatLocations {  sub FormatLocations {
1754          # Get the parameters.          # Get the parameters.
1755          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1756          # Create the return list.          # Create the return list.
1757          my @retVal = ();          my @retVal = ();
1758          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1759          if ($locations eq '') {          if ($locations eq '') {
1760              confess "No locations specified.";          Confess("No locations specified.");
1761          } else {          } else {
1762                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1763                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1487  Line 1792 
1792    
1793  sub DumpData {  sub DumpData {
1794          # Get the parameters.          # Get the parameters.
1795          my $self = shift @_;      my ($self) = @_;
1796          # Get the data directory name.          # Get the data directory name.
1797          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1798          # Dump the relations.          # Dump the relations.
# Line 1503  Line 1808 
1808  =cut  =cut
1809  #: Return Type $;  #: Return Type $;
1810  sub XMLFileName {  sub XMLFileName {
1811          my $self = shift @_;      my ($self) = @_;
1812          return $self->{_xmlName};          return $self->{_xmlName};
1813  }  }
1814    
# Line 1523  Line 1828 
1828  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
1829  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>.
1830    
1831  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'}); >>
1832    
1833  =over 4  =over 4
1834    
# Line 1541  Line 1846 
1846  #: Return Type ;  #: Return Type ;
1847  sub Insert {  sub Insert {
1848          # Get the parameters.          # Get the parameters.
1849          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1850          # Call the underlying method.          # Call the underlying method.
1851          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1852  }  }
# Line 1583  Line 1887 
1887  #: Return Type $;  #: Return Type $;
1888  sub Annotate {  sub Annotate {
1889          # Get the parameters.          # Get the parameters.
1890          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1891          # Create the annotation ID.          # Create the annotation ID.
1892          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1893          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1604  Line 1907 
1907    
1908  =head3 AssignFunction  =head3 AssignFunction
1909    
1910  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1911    
1912  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
1913  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.  
1914    
1915  =over 4  =over 4
1916    
# Line 1618  Line 1920 
1920    
1921  =item user  =item user
1922    
1923  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>.
1924    
1925  =item function  =item function
1926    
1927  Text of the function being assigned.  Text of the function being assigned.
1928    
1929    =item assigningUser (optional)
1930    
1931    Name of the individual user making the assignment. If omitted, defaults to the user group.
1932    
1933  =item RETURN  =item RETURN
1934    
1935  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1634  Line 1940 
1940  #: Return Type $;  #: Return Type $;
1941  sub AssignFunction {  sub AssignFunction {
1942          # Get the parameters.          # Get the parameters.
1943          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1944          my ($featureID, $user, $function) = @_;      # Default the assigning user.
1945        if (! $assigningUser) {
1946            $assigningUser = $user;
1947        }
1948          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1949          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1950          # Get the current time.          # Get the current time.
1951          my $now = time;          my $now = time;
1952          # Declare the return variable.          # Declare the return variable.
# Line 1682  Line 1991 
1991  #: Return Type @;  #: Return Type @;
1992  sub FeaturesByAlias {  sub FeaturesByAlias {
1993          # Get the parameters.          # Get the parameters.
1994          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
1995          # Declare the return variable.          # Declare the return variable.
1996          my @retVal = ();          my @retVal = ();
1997          # Parse the alias.          # Parse the alias.
# Line 1725  Line 2033 
2033  #: Return Type $;  #: Return Type $;
2034  sub Exists {  sub Exists {
2035          # Get the parameters.          # Get the parameters.
2036          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2037          # Check for the entity instance.          # Check for the entity instance.
2038          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2039          # Return an existence indicator.          # Return an existence indicator.
# Line 1756  Line 2063 
2063  #: Return Type $;  #: Return Type $;
2064  sub FeatureTranslation {  sub FeatureTranslation {
2065          # Get the parameters.          # Get the parameters.
2066          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2067          # Get the specified feature's translation.          # Get the specified feature's translation.
2068          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2069          return $retVal;          return $retVal;
# Line 1789  Line 2095 
2095  #: Return Type @;  #: Return Type @;
2096  sub Taxonomy {  sub Taxonomy {
2097          # Get the parameters.          # Get the parameters.
2098          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2099          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2100          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2101          # Declare the return variable.          # Declare the return variable.
# Line 1833  Line 2138 
2138  #: Return Type $;  #: Return Type $;
2139  sub CrudeDistance {  sub CrudeDistance {
2140          # Get the parameters.          # Get the parameters.
2141          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2142          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2143          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2144          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1881  Line 2185 
2185  #: Return Type $;  #: Return Type $;
2186  sub RoleName {  sub RoleName {
2187          # Get the parameters.          # Get the parameters.
2188          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2189          # Get the specified role's name.          # Get the specified role's name.
2190          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2191          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1915  Line 2218 
2218  #: Return Type @;  #: Return Type @;
2219  sub RoleDiagrams {  sub RoleDiagrams {
2220          # Get the parameters.          # Get the parameters.
2221          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2222          # Query for the diagrams.          # Query for the diagrams.
2223          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2224                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1953  Line 2255 
2255  #: Return Type @@;  #: Return Type @@;
2256  sub FeatureProperties {  sub FeatureProperties {
2257          # Get the parameters.          # Get the parameters.
2258          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2259          # Get the properties.          # Get the properties.
2260          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2261                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 1985  Line 2286 
2286  #: Return Type $;  #: Return Type $;
2287  sub DiagramName {  sub DiagramName {
2288          # Get the parameters.          # Get the parameters.
2289          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2290          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2291          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2292          return $retVal;          return $retVal;
# Line 2018  Line 2318 
2318  #: Return Type @;  #: Return Type @;
2319  sub MergedAnnotations {  sub MergedAnnotations {
2320          # Get the parameters.          # Get the parameters.
2321          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2322          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2323          my @tuples = ();          my @tuples = ();
2324          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2067  Line 2366 
2366  #: Return Type @;  #: Return Type @;
2367  sub RoleNeighbors {  sub RoleNeighbors {
2368          # Get the parameters.          # Get the parameters.
2369          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2370          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2371          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2372                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2110  Line 2408 
2408  #: Return Type @;  #: Return Type @;
2409  sub FeatureLinks {  sub FeatureLinks {
2410          # Get the parameters.          # Get the parameters.
2411          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2412          # Get the feature's links.          # Get the feature's links.
2413          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2414          # Return the feature's links.          # Return the feature's links.
# Line 2141  Line 2438 
2438  #: Return Type %;  #: Return Type %;
2439  sub SubsystemsOf {  sub SubsystemsOf {
2440          # Get the parameters.          # Get the parameters.
2441          my $self = shift @_;      my ($self, $featureID) = @_;
2442          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2443          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2444                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2445                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2157  Line 2453 
2453          return %retVal;          return %retVal;
2454  }  }
2455    
2456    =head3 SubsystemList
2457    
2458    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2459    
2460    Return a list containing the names of the subsystems in which the specified
2461    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2462    subsystem names, not the roles.
2463    
2464    =over 4
2465    
2466    =item featureID
2467    
2468    ID of the feature whose subsystem names are desired.
2469    
2470    =item RETURN
2471    
2472    Returns a list of the names of the subsystems in which the feature participates.
2473    
2474    =back
2475    
2476    =cut
2477    #: Return Type @;
2478    sub SubsystemList {
2479        # Get the parameters.
2480        my ($self, $featureID) = @_;
2481        # Get the list of names.
2482        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2483                                    [$featureID], 'HasSSCell(from-link)');
2484        # Return the result.
2485        return @retVal;
2486    }
2487    
2488  =head3 RelatedFeatures  =head3 RelatedFeatures
2489    
2490  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2190  Line 2518 
2518  #: Return Type @;  #: Return Type @;
2519  sub RelatedFeatures {  sub RelatedFeatures {
2520          # Get the parameters.          # Get the parameters.
2521          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2522          # 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.
2523          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2524                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2239  Line 2566 
2566  #: Return Type @;  #: Return Type @;
2567  sub TaxonomySort {  sub TaxonomySort {
2568          # Get the parameters.          # Get the parameters.
2569          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2570          # Create the working hash table.          # Create the working hash table.
2571          my %hashBuffer = ();          my %hashBuffer = ();
2572          # Loop through the features.          # Loop through the features.
# Line 2249  Line 2575 
2575                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2576                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2577                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2578                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2579          }          }
2580          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2581          my @retVal = ();          my @retVal = ();
# Line 2322  Line 2644 
2644  #: Return Type @@;  #: Return Type @@;
2645  sub GetAll {  sub GetAll {
2646          # Get the parameters.          # Get the parameters.
2647          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2648          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2649          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2650          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++;  
         }  
2651          # Return the resulting list.          # Return the resulting list.
2652          return @retVal;          return @retVal;
2653  }  }
# Line 2384  Line 2692 
2692  #: Return Type @;  #: Return Type @;
2693  sub GetFlat {  sub GetFlat {
2694          # Get the parameters.          # Get the parameters.
2695          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2696          # Construct the query.          # Construct the query.
2697          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2698          # Create the result list.          # Create the result list.
# Line 2495  Line 2802 
2802  #: Return Type @;  #: Return Type @;
2803  sub LoadInfo {  sub LoadInfo {
2804          # Get the parameters.          # Get the parameters.
2805          my $self = shift @_;      my ($self) = @_;
2806          # 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.
2807          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2808          # Concatenate the table names.          # Concatenate the table names.
# Line 2532  Line 2839 
2839  #: Return Type %;  #: Return Type %;
2840  sub LowBBHs {  sub LowBBHs {
2841          # Get the parsameters.          # Get the parsameters.
2842          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
2843          # Create the return hash.          # Create the return hash.
2844          my %retVal = ();          my %retVal = ();
2845          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2562  Line 2868 
2868  #: Return Type %@;  #: Return Type %@;
2869  sub GetGroups {  sub GetGroups {
2870      # Get the parameters.      # Get the parameters.
2871      my $self = shift @_;      my ($self, $groupList) = @_;
     my ($groupList) = @_;  
2872      # Declare the return value.      # Declare the return value.
2873      my %retVal = ();      my %retVal = ();
2874      # Determine whether we are getting all the groups or just some.      # Determine whether we are getting all the groups or just some.
# Line 2590  Line 2895 
2895              # Loop through the groups, adding the genome ID to each group's              # Loop through the groups, adding the genome ID to each group's
2896              # list.              # list.
2897              for my $group (@groups) {              for my $group (@groups) {
2898                  if (exists $retVal{$group}) {                  Tracer::AddToListMap(\%retVal, $group, $genomeID);
                     push @{$retVal{$group}}, $genomeID;  
                 } else {  
                     $retVal{$group} = [$genomeID];  
                 }  
2899              }              }
2900          }          }
2901      }      }
# Line 2602  Line 2903 
2903      return %retVal;      return %retVal;
2904  }  }
2905    
2906    =head3 MyGenomes
2907    
2908    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
2909    
2910    Return a list of the genomes to be included in the Sprout.
2911    
2912    This method is provided for use during the Sprout load. It presumes the Genome load file has
2913    already been created. (It will be in the Sprout data directory and called either C<Genome>
2914    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
2915    IDs.
2916    
2917    =over 4
2918    
2919    =item dataDir
2920    
2921    Directory containing the Sprout load files.
2922    
2923    =back
2924    
2925    =cut
2926    #: Return Type @;
2927    sub MyGenomes {
2928        # Get the parameters.
2929        my ($dataDir) = @_;
2930        # Compute the genome file name.
2931        my $genomeFileName = LoadFileName($dataDir, "Genome");
2932        # Extract the genome IDs from the files.
2933        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
2934        # Return the result.
2935        return @retVal;
2936    }
2937    
2938    =head3 LoadFileName
2939    
2940    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
2941    
2942    Return the name of the load file for the specified table in the specified data
2943    directory.
2944    
2945    =over 4
2946    
2947    =item dataDir
2948    
2949    Directory containing the Sprout load files.
2950    
2951    =item tableName
2952    
2953    Name of the table whose load file is desired.
2954    
2955    =item RETURN
2956    
2957    Returns the name of the file containing the load data for the specified table, or
2958    C<undef> if no load file is present.
2959    
2960    =back
2961    
2962    =cut
2963    #: Return Type $;
2964    sub LoadFileName {
2965        # Get the parameters.
2966        my ($dataDir, $tableName) = @_;
2967        # Declare the return variable.
2968        my $retVal;
2969        # Check for the various file names.
2970        if (-e "$dataDir/$tableName") {
2971            $retVal = "$dataDir/$tableName";
2972        } elsif (-e "$dataDir/$tableName.dtx") {
2973            $retVal = "$dataDir/$tableName.dtx";
2974        }
2975        # Return the result.
2976        return $retVal;
2977    }
2978    
2979  =head2 Internal Utility Methods  =head2 Internal Utility Methods
2980    
2981  =head3 ParseAssignment  =head3 ParseAssignment
2982    
2983  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
2984  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
2985  will be returned.  isn't, an empty list will be returned.
2986    
2987    A functional assignment is always of the form
2988    
2989        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
2990    
2991    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
2992    actual functional role. In most cases, the user and the assigning user will be the
2993    same, but that is not always the case.
2994    
2995  This is a static method.  This is a static method.
2996    
# Line 2627  Line 3009 
3009    
3010  =cut  =cut
3011    
3012  sub ParseAssignment {  sub _ParseAssignment {
3013          # Get the parameters.          # Get the parameters.
3014          my ($text) = @_;          my ($text) = @_;
3015          # Declare the return value.          # Declare the return value.
3016          my @retVal = ();          my @retVal = ();
3017          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3018          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3019          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3020                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3021                  @retVal = ($user, $function);          # and the assigning user.
3022            @retVal = ($1, $function, $user);
3023          }          }
3024          # Return the result list.          # Return the result list.
3025          return @retVal;          return @retVal;
# Line 2668  Line 3051 
3051      return $retVal;      return $retVal;
3052  }  }
3053    
3054    =head3 AddProperty
3055    
3056    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3057    
3058    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3059    be added to almost any object. In Sprout, they can only be added to features. In
3060    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3061    pair. If the particular key/value pair coming in is not already in the database, a new
3062    B<Property> record is created to hold it.
3063    
3064    =over 4
3065    
3066    =item peg
3067    
3068    ID of the feature to which the attribute is to be replied.
3069    
3070    =item key
3071    
3072    Name of the attribute (key).
3073    
3074    =item value
3075    
3076    Value of the attribute.
3077    
3078    =item url
3079    
3080    URL or text citation from which the property was obtained.
3081    
3082    =back
3083    
3084    =cut
3085    #: Return Type ;
3086    sub AddProperty {
3087        # Get the parameters.
3088        my ($self, $featureID, $key, $value, $url) = @_;
3089        # Declare the variable to hold the desired property ID.
3090        my $propID;
3091        # Attempt to find a property record for this key/value pair.
3092        my @properties = $self->GetFlat(['Property'],
3093                                       "Property(property-name) = ? AND Property(property-value) = ?",
3094                                       [$key, $value], 'Property(id)');
3095        if (@properties) {
3096            # Here the property is already in the database. We save its ID.
3097            $propID = $properties[0];
3098            # Here the property value does not exist. We need to generate an ID. It will be set
3099            # to a number one greater than the maximum value in the database. This call to
3100            # GetAll will stop after one record.
3101            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3102                                            1);
3103            $propID = $maxProperty[0]->[0] + 1;
3104            # Insert the new property value.
3105            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3106        }
3107        # Now we connect the incoming feature to the property.
3108        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3109    }
3110    
3111  1;  1;

Legend:
Removed from v.1.8  
changed lines
  Added in v.1.18

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3