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

Diff of /Sprout/Sprout.pm

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

revision 1.9, Mon Feb 7 00:32:07 2005 UTC revision 1.22, Fri Sep 9 21:10:46 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 590  Line 576 
576  =item RETURN  =item RETURN
577    
578  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
579  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
580    
581  =back  =back
582    
# 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]);                                                     [$featureID]);
# Line 634  Line 619 
619                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
620          }          }
621          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
622          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
623  }  }
624    
625  =head3 ParseLocation  =head3 ParseLocation
# Line 660  Line 645 
645  =cut  =cut
646  #: Return Type @;  #: Return Type @;
647  sub ParseLocation {  sub ParseLocation {
648          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
649        # the first parameter.
650        shift if UNIVERSAL::isa($_[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 861  Line 897 
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
# Line 963  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 1001  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 1031  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 1054  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 = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],
1093                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
# Line 1071  Line 1103 
1103          # Get the annotation fields.          # Get the annotation fields.
1104          my ($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 1093  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 1128  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 $retVal;
1166      # Determine the ID type.      # Determine the ID type.
# Line 1166  Line 1197 
1197              # Get the annotation text.              # Get the annotation text.
1198              my ($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 1205  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 1214  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 1235  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 1258  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 1289  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 1326  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 1353  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            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1525            my $ordering = ($inverted ? "DESC" : "");
1526            # Get the coupling evidence.
1527            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1528                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1529                                              [$couplingID],
1530                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1531            # Loop through the evidence items. Each piece of evidence is represented by two
1532            # positions in the evidence list, one for each feature on the other side of the
1533            # evidence link. If at some point we want to generalize to couplings with
1534            # more than two positions, this section of code will need to be re-done.
1535            while (@evidenceList > 0) {
1536                my $peg1Data = shift @evidenceList;
1537                my $peg2Data = shift @evidenceList;
1538                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1539                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1540            }
1541            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1542        }
1543        # Return the result.
1544        return @retVal;
1545    }
1546    
1547    =head3 GetCoupling
1548    
1549    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1550    
1551    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1552    exists, we return the coupling ID along with an indicator of whether the
1553    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1554    In the second case, we say the coupling is I<inverted>. The importance of an
1555    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1556    
1557    =over 4
1558    
1559    =item peg1
1560    
1561    ID of the feature of interest.
1562    
1563    =item peg2
1564    
1565    ID of the potentially coupled feature.
1566    
1567    =item RETURN
1568    
1569    Returns a three-element list. The first element contains the database ID of
1570    the coupling. The second element is FALSE if the coupling is stored in the
1571    database in the caller specified order and TRUE if it is stored in the
1572    inverted order. The third element is the coupling's score. If the coupling
1573    does not exist, all three list elements will be C<undef>.
1574    
1575    =back
1576    
1577    =cut
1578    #: Return Type $%@;
1579    sub GetCoupling {
1580        # Get the parameters.
1581        my ($self, $peg1, $peg2) = @_;
1582        # Declare the return values. We'll start with the coupling ID and undefine the
1583        # flag and score until we have more information.
1584        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1585        # Find the coupling data.
1586        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1587                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1588                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1589        # Check to see if we found anything.
1590        if (!@pegs) {
1591            # No coupling, so undefine the return value.
1592            $retVal = undef;
1593        } else {
1594            # We have a coupling! Get the score and check for inversion.
1595            $score = $pegs[0]->[1];
1596            $inverted = ($pegs[0]->[0] eq $peg1);
1597        }
1598        # Return the result.
1599        return ($retVal, $inverted, $score);
1600    }
1601    
1602    =head3 CouplingID
1603    
1604    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1605    
1606    Return the coupling ID for a pair of feature IDs.
1607    
1608    The coupling ID is currently computed by joining the feature IDs in
1609    sorted order with a space. Client modules (that is, modules which
1610    use Sprout) should not, however, count on this always being the
1611    case. This method provides a way for abstracting the concept of a
1612    coupling ID. All that we know for sure about it is that it can be
1613    generated easily from the feature IDs and the order of the IDs
1614    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1615    will have the same value as C<CouplingID("b1", "a1")>.
1616    
1617    =over 4
1618    
1619    =item peg1
1620    
1621    First feature of interest.
1622    
1623    =item peg2
1624    
1625    Second feature of interest.
1626    
1627    =item RETURN
1628    
1629    Returns the ID that would be used to represent a functional coupling of
1630    the two specified PEGs.
1631    
1632    =back
1633    
1634    =cut
1635    #: Return Type $;
1636    sub CouplingID {
1637        return join " ", sort @_;
1638    }
1639    
1640  =head3 GetEntityTypes  =head3 GetEntityTypes
1641    
1642  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1363  Line 1647 
1647  #: Return Type @;  #: Return Type @;
1648  sub GetEntityTypes {  sub GetEntityTypes {
1649          # Get the parameters.          # Get the parameters.
1650          my $self = shift @_;      my ($self) = @_;
1651          # Get the underlying database object.          # Get the underlying database object.
1652          my $erdb = $self->{_erdb};          my $erdb = $self->{_erdb};
1653          # Get its entity type list.          # Get its entity type list.
# Line 1414  Line 1698 
1698                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1699                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1700                          if ($id) {                          if ($id) {
1701                                  $retVal{$id} = $sequence;                  $retVal{$id} = uc $sequence;
1702                          }                          }
1703                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1704                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1705                  } else {                  } else {
1706                          # 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.
1707                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to upper
1708                # case.
1709                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1710                          $sequence .= $1;                          $sequence .= $1;
1711                  }                  }
1712          }          }
1713          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1714          if ($sequence) {          if ($sequence) {
1715                  $retVal {$id} = $sequence;          $retVal{$id} = uc $sequence;
1716          }          }
1717        # Close the file.
1718        close FASTAFILE;
1719          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1720          return %retVal;          return %retVal;
1721  }  }
# Line 1439  Line 1726 
1726    
1727  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
1728  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
1729  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,
1730    it will not be changed; otherwise, it will be converted. This method can also be used to
1731    perform the reverse task-- insuring that all the locations are in the old format.
1732    
1733  =over 4  =over 4
1734    
# Line 1466  Line 1755 
1755  #: Return Type @;  #: Return Type @;
1756  sub FormatLocations {  sub FormatLocations {
1757          # Get the parameters.          # Get the parameters.
1758          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1759          # Create the return list.          # Create the return list.
1760          my @retVal = ();          my @retVal = ();
1761          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1762          if ($locations eq '') {          if ($locations eq '') {
1763              confess "No locations specified.";          Confess("No locations specified.");
1764          } else {          } else {
1765                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1766                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1507  Line 1795 
1795    
1796  sub DumpData {  sub DumpData {
1797          # Get the parameters.          # Get the parameters.
1798          my $self = shift @_;      my ($self) = @_;
1799          # Get the data directory name.          # Get the data directory name.
1800          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
1801          # Dump the relations.          # Dump the relations.
# Line 1523  Line 1811 
1811  =cut  =cut
1812  #: Return Type $;  #: Return Type $;
1813  sub XMLFileName {  sub XMLFileName {
1814          my $self = shift @_;      my ($self) = @_;
1815          return $self->{_xmlName};          return $self->{_xmlName};
1816  }  }
1817    
# Line 1543  Line 1831 
1831  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
1832  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>.
1833    
1834  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'}); >>
1835    
1836  =over 4  =over 4
1837    
# Line 1561  Line 1849 
1849  #: Return Type ;  #: Return Type ;
1850  sub Insert {  sub Insert {
1851          # Get the parameters.          # Get the parameters.
1852          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
1853          # Call the underlying method.          # Call the underlying method.
1854          $self->{_erdb}->InsertObject($objectType, $fieldHash);          $self->{_erdb}->InsertObject($objectType, $fieldHash);
1855  }  }
# Line 1603  Line 1890 
1890  #: Return Type $;  #: Return Type $;
1891  sub Annotate {  sub Annotate {
1892          # Get the parameters.          # Get the parameters.
1893          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
1894          # Create the annotation ID.          # Create the annotation ID.
1895          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
1896          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1624  Line 1910 
1910    
1911  =head3 AssignFunction  =head3 AssignFunction
1912    
1913  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1914    
1915  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
1916  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.  
1917    
1918  =over 4  =over 4
1919    
# Line 1638  Line 1923 
1923    
1924  =item user  =item user
1925    
1926  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>.
1927    
1928  =item function  =item function
1929    
1930  Text of the function being assigned.  Text of the function being assigned.
1931    
1932    =item assigningUser (optional)
1933    
1934    Name of the individual user making the assignment. If omitted, defaults to the user group.
1935    
1936  =item RETURN  =item RETURN
1937    
1938  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1654  Line 1943 
1943  #: Return Type $;  #: Return Type $;
1944  sub AssignFunction {  sub AssignFunction {
1945          # Get the parameters.          # Get the parameters.
1946          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1947          my ($featureID, $user, $function) = @_;      # Default the assigning user.
1948        if (! $assigningUser) {
1949            $assigningUser = $user;
1950        }
1951          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1952          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1953          # Get the current time.          # Get the current time.
1954          my $now = time;          my $now = time;
1955          # Declare the return variable.          # Declare the return variable.
# Line 1702  Line 1994 
1994  #: Return Type @;  #: Return Type @;
1995  sub FeaturesByAlias {  sub FeaturesByAlias {
1996          # Get the parameters.          # Get the parameters.
1997          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
1998          # Declare the return variable.          # Declare the return variable.
1999          my @retVal = ();          my @retVal = ();
2000          # Parse the alias.          # Parse the alias.
# Line 1745  Line 2036 
2036  #: Return Type $;  #: Return Type $;
2037  sub Exists {  sub Exists {
2038          # Get the parameters.          # Get the parameters.
2039          my $self = shift @_;      my ($self, $entityName, $entityID) = @_;
         my ($entityName, $entityID) = @_;  
2040          # Check for the entity instance.          # Check for the entity instance.
2041          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2042          # Return an existence indicator.          # Return an existence indicator.
# Line 1776  Line 2066 
2066  #: Return Type $;  #: Return Type $;
2067  sub FeatureTranslation {  sub FeatureTranslation {
2068          # Get the parameters.          # Get the parameters.
2069          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2070          # Get the specified feature's translation.          # Get the specified feature's translation.
2071          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2072          return $retVal;          return $retVal;
# Line 1809  Line 2098 
2098  #: Return Type @;  #: Return Type @;
2099  sub Taxonomy {  sub Taxonomy {
2100          # Get the parameters.          # Get the parameters.
2101          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2102          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2103          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2104          # Declare the return variable.          # Declare the return variable.
# Line 1853  Line 2141 
2141  #: Return Type $;  #: Return Type $;
2142  sub CrudeDistance {  sub CrudeDistance {
2143          # Get the parameters.          # Get the parameters.
2144          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2145          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2146          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2147          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1901  Line 2188 
2188  #: Return Type $;  #: Return Type $;
2189  sub RoleName {  sub RoleName {
2190          # Get the parameters.          # Get the parameters.
2191          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2192          # Get the specified role's name.          # Get the specified role's name.
2193          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2194          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1935  Line 2221 
2221  #: Return Type @;  #: Return Type @;
2222  sub RoleDiagrams {  sub RoleDiagrams {
2223          # Get the parameters.          # Get the parameters.
2224          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2225          # Query for the diagrams.          # Query for the diagrams.
2226          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2227                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1944  Line 2229 
2229          return @retVal;          return @retVal;
2230  }  }
2231    
2232    =head3 GetProperties
2233    
2234    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2235    
2236    Return a list of the properties with the specified characteristics.
2237    
2238    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2239    will also be associated with genomes.) A property value is represented by a 4-tuple of
2240    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2241    
2242    =over 4
2243    
2244    =item fid
2245    
2246    ID of the feature possessing the property.
2247    
2248    =item key
2249    
2250    Name or key of the property.
2251    
2252    =item value
2253    
2254    Value of the property.
2255    
2256    =item url
2257    
2258    URL of the document that indicated the property should have this particular value, or an
2259    empty string if no such document exists.
2260    
2261    =back
2262    
2263    The parameters act as a filter for the desired data. Any non-null parameter will
2264    automatically match all the tuples returned. So, specifying just the I<$fid> will
2265    return all the properties of the specified feature; similarly, specifying the I<$key>
2266    and I<$value> parameters will return all the features having the specified property
2267    value.
2268    
2269    A single property key can have many values, representing different ideas about the
2270    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2271    virulent, and another may declare that it is not virulent. A query about the virulence of
2272    C<fig|83333.1.peg.10> would be coded as
2273    
2274        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2275    
2276    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2277    not to be filtered. The tuples returned would be
2278    
2279        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2280        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2281    
2282    =cut
2283    #: Return Type @@;
2284    sub GetProperties {
2285        # Get the parameters.
2286        my ($self, @parms) = @_;
2287        # Declare the return variable.
2288        my @retVal = ();
2289        # Now we need to create a WHERE clause that will get us the data we want. First,
2290        # we create a list of the columns containing the data for each parameter.
2291        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2292                        'Property(property-value)', 'HasProperty(evidence)');
2293        # Now we build the WHERE clause and the list of parameter values.
2294        my @where = ();
2295        my @values = ();
2296        for (my $i = 0; $i <= $#colNames; $i++) {
2297            my $parm = $parms[$i];
2298            if (defined $parm && ($parm ne '')) {
2299                push @where, "$colNames[$i] = ?";
2300                push @values, $parm;
2301            }
2302        }
2303        # Format the WHERE clause.
2304        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2305        # Ask for all the propertie values with the desired characteristics.
2306        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2307        while (my $valueObject = $query->Fetch()) {
2308            my @tuple = $valueObject->Values(\@colNames);
2309            push @retVal, \@tuple;
2310        }
2311        # Return the result.
2312        return @retVal;
2313    }
2314    
2315  =head3 FeatureProperties  =head3 FeatureProperties
2316    
2317  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 1973  Line 2341 
2341  #: Return Type @@;  #: Return Type @@;
2342  sub FeatureProperties {  sub FeatureProperties {
2343          # Get the parameters.          # Get the parameters.
2344          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2345          # Get the properties.          # Get the properties.
2346          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],
2347                                                          ['Property(property-name)', 'Property(property-value)',                                                          ['Property(property-name)', 'Property(property-value)',
# Line 2005  Line 2372 
2372  #: Return Type $;  #: Return Type $;
2373  sub DiagramName {  sub DiagramName {
2374          # Get the parameters.          # Get the parameters.
2375          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2376          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2377          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2378          return $retVal;          return $retVal;
# Line 2038  Line 2404 
2404  #: Return Type @;  #: Return Type @;
2405  sub MergedAnnotations {  sub MergedAnnotations {
2406          # Get the parameters.          # Get the parameters.
2407          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2408          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2409          my @tuples = ();          my @tuples = ();
2410          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2087  Line 2452 
2452  #: Return Type @;  #: Return Type @;
2453  sub RoleNeighbors {  sub RoleNeighbors {
2454          # Get the parameters.          # Get the parameters.
2455          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2456          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2457          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2458                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2130  Line 2494 
2494  #: Return Type @;  #: Return Type @;
2495  sub FeatureLinks {  sub FeatureLinks {
2496          # Get the parameters.          # Get the parameters.
2497          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2498          # Get the feature's links.          # Get the feature's links.
2499          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2500          # Return the feature's links.          # Return the feature's links.
# Line 2143  Line 2506 
2506  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2507    
2508  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
2509  to the role the feature performs.  to the roles the feature performs.
2510    
2511  =over 4  =over 4
2512    
# Line 2153  Line 2516 
2516    
2517  =item RETURN  =item RETURN
2518    
2519  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.
2520    
2521  =back  =back
2522    
2523  =cut  =cut
2524  #: Return Type %;  #: Return Type %@;
2525  sub SubsystemsOf {  sub SubsystemsOf {
2526          # Get the parameters.          # Get the parameters.
2527          my $self = shift @_;      my ($self, $featureID) = @_;
2528          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2529          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2530                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2531                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2171  Line 2533 
2533          my %retVal = ();          my %retVal = ();
2534          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2535          for my $record (@subsystems) {          for my $record (@subsystems) {
2536                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2537            if (exists $retVal{$subsys}) {
2538                push @{$retVal{$subsys}}, $role;
2539            } else {
2540                $retVal{$subsys} = [$role];
2541            }
2542          }          }
2543          # Return the hash.          # Return the hash.
2544          return %retVal;          return %retVal;
2545  }  }
2546    
2547    =head3 SubsystemList
2548    
2549    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2550    
2551    Return a list containing the names of the subsystems in which the specified
2552    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2553    subsystem names, not the roles.
2554    
2555    =over 4
2556    
2557    =item featureID
2558    
2559    ID of the feature whose subsystem names are desired.
2560    
2561    =item RETURN
2562    
2563    Returns a list of the names of the subsystems in which the feature participates.
2564    
2565    =back
2566    
2567    =cut
2568    #: Return Type @;
2569    sub SubsystemList {
2570        # Get the parameters.
2571        my ($self, $featureID) = @_;
2572        # Get the list of names.
2573        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2574                                    [$featureID], 'HasSSCell(from-link)');
2575        # Return the result.
2576        return @retVal;
2577    }
2578    
2579  =head3 RelatedFeatures  =head3 RelatedFeatures
2580    
2581  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2210  Line 2609 
2609  #: Return Type @;  #: Return Type @;
2610  sub RelatedFeatures {  sub RelatedFeatures {
2611          # Get the parameters.          # Get the parameters.
2612          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2613          # 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.
2614          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],
2615                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],
# Line 2259  Line 2657 
2657  #: Return Type @;  #: Return Type @;
2658  sub TaxonomySort {  sub TaxonomySort {
2659          # Get the parameters.          # Get the parameters.
2660          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
2661          # Create the working hash table.          # Create the working hash table.
2662          my %hashBuffer = ();          my %hashBuffer = ();
2663          # Loop through the features.          # Loop through the features.
# Line 2269  Line 2666 
2666                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
2667                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
2668                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
2669                  if (exists $hashBuffer{$taxonomy}) {          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);
                         push @{$hashBuffer{$taxonomy}}, $fid;  
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
2670          }          }
2671          # Sort the keys and get the elements.          # Sort the keys and get the elements.
2672          my @retVal = ();          my @retVal = ();
# Line 2342  Line 2735 
2735  #: Return Type @@;  #: Return Type @@;
2736  sub GetAll {  sub GetAll {
2737          # Get the parameters.          # Get the parameters.
2738          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2739          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Call the ERDB method.
2740          # Create the query.      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2741          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++;  
         }  
2742          # Return the resulting list.          # Return the resulting list.
2743          return @retVal;          return @retVal;
2744  }  }
# Line 2404  Line 2783 
2783  #: Return Type @;  #: Return Type @;
2784  sub GetFlat {  sub GetFlat {
2785          # Get the parameters.          # Get the parameters.
2786          my $self = shift @_;      my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
2787          # Construct the query.          # Construct the query.
2788          my $query = $self->Get($objectNames, $filterClause, $parameterList);          my $query = $self->Get($objectNames, $filterClause, $parameterList);
2789          # Create the result list.          # Create the result list.
# Line 2515  Line 2893 
2893  #: Return Type @;  #: Return Type @;
2894  sub LoadInfo {  sub LoadInfo {
2895          # Get the parameters.          # Get the parameters.
2896          my $self = shift @_;      my ($self) = @_;
2897          # 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.
2898          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
2899          # Concatenate the table names.          # Concatenate the table names.
# Line 2552  Line 2930 
2930  #: Return Type %;  #: Return Type %;
2931  sub LowBBHs {  sub LowBBHs {
2932          # Get the parsameters.          # Get the parsameters.
2933          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
2934          # Create the return hash.          # Create the return hash.
2935          my %retVal = ();          my %retVal = ();
2936          # Create a query to get the desired BBHs.          # Create a query to get the desired BBHs.
# Line 2582  Line 2959 
2959  #: Return Type %@;  #: Return Type %@;
2960  sub GetGroups {  sub GetGroups {
2961      # Get the parameters.      # Get the parameters.
2962      my $self = shift @_;      my ($self, $groupList) = @_;
     my ($groupList) = @_;  
2963      # Declare the return value.      # Declare the return value.
2964      my %retVal = ();      my %retVal = ();
2965      # Determine whether we are getting all the groups or just some.      # Determine whether we are getting all the groups or just some.
# Line 2610  Line 2986 
2986              # Loop through the groups, adding the genome ID to each group's              # Loop through the groups, adding the genome ID to each group's
2987              # list.              # list.
2988              for my $group (@groups) {              for my $group (@groups) {
2989                  if (exists $retVal{$group}) {                  Tracer::AddToListMap(\%retVal, $group, $genomeID);
                     push @{$retVal{$group}}, $genomeID;  
                 } else {  
                     $retVal{$group} = [$genomeID];  
                 }  
2990              }              }
2991          }          }
2992      }      }
# Line 2622  Line 2994 
2994      return %retVal;      return %retVal;
2995  }  }
2996    
2997    =head3 MyGenomes
2998    
2999    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3000    
3001    Return a list of the genomes to be included in the Sprout.
3002    
3003    This method is provided for use during the Sprout load. It presumes the Genome load file has
3004    already been created. (It will be in the Sprout data directory and called either C<Genome>
3005    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3006    IDs.
3007    
3008    =over 4
3009    
3010    =item dataDir
3011    
3012    Directory containing the Sprout load files.
3013    
3014    =back
3015    
3016    =cut
3017    #: Return Type @;
3018    sub MyGenomes {
3019        # Get the parameters.
3020        my ($dataDir) = @_;
3021        # Compute the genome file name.
3022        my $genomeFileName = LoadFileName($dataDir, "Genome");
3023        # Extract the genome IDs from the files.
3024        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3025        # Return the result.
3026        return @retVal;
3027    }
3028    
3029    =head3 LoadFileName
3030    
3031    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3032    
3033    Return the name of the load file for the specified table in the specified data
3034    directory.
3035    
3036    =over 4
3037    
3038    =item dataDir
3039    
3040    Directory containing the Sprout load files.
3041    
3042    =item tableName
3043    
3044    Name of the table whose load file is desired.
3045    
3046    =item RETURN
3047    
3048    Returns the name of the file containing the load data for the specified table, or
3049    C<undef> if no load file is present.
3050    
3051    =back
3052    
3053    =cut
3054    #: Return Type $;
3055    sub LoadFileName {
3056        # Get the parameters.
3057        my ($dataDir, $tableName) = @_;
3058        # Declare the return variable.
3059        my $retVal;
3060        # Check for the various file names.
3061        if (-e "$dataDir/$tableName") {
3062            $retVal = "$dataDir/$tableName";
3063        } elsif (-e "$dataDir/$tableName.dtx") {
3064            $retVal = "$dataDir/$tableName.dtx";
3065        }
3066        # Return the result.
3067        return $retVal;
3068    }
3069    
3070  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3071    
3072  =head3 ParseAssignment  =head3 ParseAssignment
3073    
3074  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3075  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3076  will be returned.  isn't, an empty list will be returned.
3077    
3078    A functional assignment is always of the form
3079    
3080        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3081    
3082    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3083    actual functional role. In most cases, the user and the assigning user will be the
3084    same, but that is not always the case.
3085    
3086  This is a static method.  This is a static method.
3087    
# Line 2647  Line 3100 
3100    
3101  =cut  =cut
3102    
3103  sub ParseAssignment {  sub _ParseAssignment {
3104          # Get the parameters.          # Get the parameters.
3105          my ($text) = @_;          my ($text) = @_;
3106          # Declare the return value.          # Declare the return value.
3107          my @retVal = ();          my @retVal = ();
3108          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3109          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3110          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3111                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3112                  @retVal = ($user, $function);          # and the assigning user.
3113            @retVal = ($1, $function, $user);
3114          }          }
3115          # Return the result list.          # Return the result list.
3116          return @retVal;          return @retVal;
# Line 2688  Line 3142 
3142      return $retVal;      return $retVal;
3143  }  }
3144    
3145    =head3 AddProperty
3146    
3147    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3148    
3149    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3150    be added to almost any object. In Sprout, they can only be added to features. In
3151    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3152    pair. If the particular key/value pair coming in is not already in the database, a new
3153    B<Property> record is created to hold it.
3154    
3155    =over 4
3156    
3157    =item peg
3158    
3159    ID of the feature to which the attribute is to be replied.
3160    
3161    =item key
3162    
3163    Name of the attribute (key).
3164    
3165    =item value
3166    
3167    Value of the attribute.
3168    
3169    =item url
3170    
3171    URL or text citation from which the property was obtained.
3172    
3173    =back
3174    
3175    =cut
3176    #: Return Type ;
3177    sub AddProperty {
3178        # Get the parameters.
3179        my ($self, $featureID, $key, $value, $url) = @_;
3180        # Declare the variable to hold the desired property ID.
3181        my $propID;
3182        # Attempt to find a property record for this key/value pair.
3183        my @properties = $self->GetFlat(['Property'],
3184                                       "Property(property-name) = ? AND Property(property-value) = ?",
3185                                       [$key, $value], 'Property(id)');
3186        if (@properties) {
3187            # Here the property is already in the database. We save its ID.
3188            $propID = $properties[0];
3189            # Here the property value does not exist. We need to generate an ID. It will be set
3190            # to a number one greater than the maximum value in the database. This call to
3191            # GetAll will stop after one record.
3192            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3193                                            1);
3194            $propID = $maxProperty[0]->[0] + 1;
3195            # Insert the new property value.
3196            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3197        }
3198        # Now we connect the incoming feature to the property.
3199        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3200    }
3201    
3202    
3203    
3204  1;  1;

Legend:
Removed from v.1.9  
changed lines
  Added in v.1.22

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3