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

Diff of /Sprout/Sprout.pm

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

revision 1.56, Wed Apr 19 03:34:15 2006 UTC revision 1.92, Mon Oct 16 07:41:50 2006 UTC
# Line 1  Line 1 
1  package Sprout;  package Sprout;
2    
3        require Exporter;
4        use ERDB;
5        @ISA = qw(Exporter ERDB);
6      use Data::Dumper;      use Data::Dumper;
7      use strict;      use strict;
8      use Carp;      use Carp;
# Line 7  Line 10 
10      use XML::Simple;      use XML::Simple;
11      use DBQuery;      use DBQuery;
12      use DBObject;      use DBObject;
     use ERDB;  
13      use Tracer;      use Tracer;
14      use FIGRules;      use FIGRules;
15        use FidCheck;
16      use Stats;      use Stats;
17      use POSIX qw(strftime);      use POSIX qw(strftime);
18        use BasicLocation;
19    
20  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
21    
# Line 32  Line 35 
35  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and
36  L</dna_seq> returns the DNA sequence for a specified genome location.  L</dna_seq> returns the DNA sequence for a specified genome location.
37    
38    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
39    
40  =cut  =cut
41    
42  #: Constructor SFXlate->new_sprout_only();  #: Constructor SFXlate->new_sprout_only();
# Line 62  Line 67 
67    
68  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
69    
70  * B<userData> user name and password, delimited by a slash (default C<root/>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
71    
72  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
73    
74    * B<sock> connection socket (default same as SEED)
75    
76  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
77    
78  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
# Line 85  Line 92 
92  sub new {  sub new {
93      # Get the parameters.      # Get the parameters.
94      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
95        # Compute the DBD directory.
96        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
97                                                      $FIG_Config::fig );
98      # 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
99      # the incoming data.      # the incoming data.
100      my $optionTable = Tracer::GetOptions({      my $optionTable = Tracer::GetOptions({
# Line 92  Line 102 
102                                                          # database type                                                          # database type
103                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
104                                                          # data file directory                                                          # data file directory
105                         xmlFileName  => "$FIG_Config::fig/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
106                                                          # database definition file name                                                          # database definition file name
107                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
108                                                          # user name and password                                                          # user name and password
109                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
110                                                          # database connection port                                                          # database connection port
111                           sock         => $FIG_Config::dbsock,
112                           host         => $FIG_Config::dbhost,
113                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
114                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
115                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 111  Line 123 
123      my $dbh;      my $dbh;
124      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
125          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
126                                  $password, $optionTable->{port});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
127      }      }
128      # Create the ERDB object.      # Create the ERDB object.
129      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
130      my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
131      # Create this object.      # Add the option table and XML file name.
132      my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
133      # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
134      bless $self;      # Set up space for the group file data.
135      return $self;      $retVal->{groupHash} = undef;
136        # Return it.
137        return $retVal;
138  }  }
139    
140  =head3 MaxSegment  =head3 MaxSegment
# Line 155  Line 169 
169      return $self->{_options}->{maxSequenceLength};      return $self->{_options}->{maxSequenceLength};
170  }  }
171    
 =head3 Get  
   
 C<< my $query = $sprout->Get(\@objectNames, $filterClause, \@parameterList); >>  
   
 This method allows a general query against the Sprout data using a specified filter clause.  
   
 The filter is a standard WHERE/ORDER BY clause with question marks as parameter markers and each  
 field name represented in the form B<I<objectName>(I<fieldName>)>. For example, the  
 following call requests all B<Genome> objects for the genus specified in the variable  
 $genus.  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ?", [$genus]); >>  
   
 The WHERE clause contains a single question mark, so there is a single additional  
 parameter representing the parameter value. It would also be possible to code  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = \'$genus\'"); >>  
   
 however, this version of the call would generate a syntax error if there were any quote  
 characters inside the variable C<$genus>.  
   
 The use of the strange parenthesized notation for field names enables us to distinguish  
 hyphens contained within field names from minus signs that participate in the computation  
 of the WHERE clause. All of the methods that manipulate fields will use this same notation.  
   
 It is possible to specify multiple entity and relationship names in order to retrieve more than  
 one object's data at the same time, which allows highly complex joined queries. For example,  
   
 C<< $query = $sprout->Get(['Genome', 'ComesFrom', 'Source'], "Genome(genus) = ?", [$genus]); >>  
   
 This query returns all the genomes for a particular genus and allows access to the  
 sources from which they came. The join clauses to go from Genome to Source are generated  
 automatically.  
   
 Finally, the filter clause can contain sort information. To do this, simply put an C<ORDER BY>  
 clause at the end of the filter. Field references in the ORDER BY section follow the same rules  
 as they do in the filter itself; in other words, each one must be of the form B<I<objectName>(I<fieldName>)>.  
 For example, the following filter string gets all genomes for a particular genus and sorts  
 them by species name.  
   
 C<< $query = $sprout->Get(['Genome'], "Genome(genus) = ? ORDER BY Genome(species)", [$genus]); >>  
   
 It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets  
 all genomes ordered by genus and species.  
   
 C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>  
   
 Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an  
 attempt to order B<Feature>s by alias may (depending on the underlying database engine used) cause  
 a single feature to appear more than once.  
   
 If multiple names are specified, then the query processor will automatically determine a  
 join path between the entities and relationships. The algorithm used is very simplistic.  
 In particular, you can't specify any entity or relationship more than once, and if a  
 relationship is recursive, the path is determined by the order in which the entity  
 and the relationship appear. For example, consider a recursive relationship B<IsParentOf>  
 which relates B<People> objects to other B<People> objects. If the join path is  
 coded as C<['People', 'IsParentOf']>, then the people returned will be parents. If, however,  
 the join path is C<['IsParentOf', 'People']>, then the people returned will be children.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item RETURN  
   
 Returns a B<DBQuery> that can be used to iterate through all of the results.  
   
 =back  
   
 =cut  
   
 sub Get {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList) = @_;  
     # We differ from the ERDB Get method in that the parameter list is passed in as a list reference  
     # rather than a list of parameters. The next step is to convert the parameters from a reference  
     # to a real list. We can only do this if the parameters have been specified.  
     my @parameters;  
     if ($parameterList) { @parameters = @{$parameterList}; }  
     return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);  
 }  
   
 =head3 GetEntity  
   
 C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>  
   
 Return an object describing the entity instance with a specified ID.  
   
 =over 4  
   
 =item entityType  
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item RETURN  
   
 Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  
 instance is found with the specified key.  
   
 =back  
   
 =cut  
   
 sub GetEntity {  
     # Get the parameters.  
     my ($self, $entityType, $ID) = @_;  
     # Call the ERDB method.  
     return $self->{_erdb}->GetEntity($entityType, $ID);  
 }  
   
 =head3 GetEntityValues  
   
 C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>  
   
 Return a list of values from a specified entity instance.  
   
 =over 4  
   
 =item entityType  
   
 Entity type name.  
   
 =item ID  
   
 ID of the desired entity.  
   
 =item fields  
   
 List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  
   
 =item RETURN  
   
 Returns a flattened list of the values of the specified fields for the specified entity.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetEntityValues {  
     # Get the parameters.  
     my ($self, $entityType, $ID, $fields) = @_;  
     # Call the ERDB method.  
     return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);  
 }  
   
 =head3 ShowMetaData  
   
 C<< $sprout->ShowMetaData($fileName); >>  
   
 This method outputs a description of the database to an HTML file in the data directory.  
   
 =over 4  
   
 =item fileName  
   
 Fully-qualified name to give to the output file.  
   
 =back  
   
 =cut  
   
 sub ShowMetaData {  
     # Get the parameters.  
     my ($self, $fileName) = @_;  
     # Compute the file name.  
     my $options = $self->{_options};  
     # Call the show method on the underlying ERDB object.  
     $self->{_erdb}->ShowMetaData($fileName);  
 }  
   
172  =head3 Load  =head3 Load
173    
174  C<< $sprout->Load($rebuild); >>;  C<< $sprout->Load($rebuild); >>;
# Line 379  Line 203 
203  sub Load {  sub Load {
204      # Get the parameters.      # Get the parameters.
205      my ($self, $rebuild) = @_;      my ($self, $rebuild) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
206      # Load the tables from the data directory.      # Load the tables from the data directory.
207      my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
208      # Return the statistics.      # Return the statistics.
209      return $retVal;      return $retVal;
210  }  }
# Line 422  Line 244 
244  sub LoadUpdate {  sub LoadUpdate {
245      # Get the parameters.      # Get the parameters.
246      my ($self, $truncateFlag, $tableList) = @_;      my ($self, $truncateFlag, $tableList) = @_;
     # Get the database object.  
     my $erdb = $self->{_erdb};  
247      # Declare the return value.      # Declare the return value.
248      my $retVal = Stats->new();      my $retVal = Stats->new();
249      # Get the data directory.      # Get the data directory.
# Line 437  Line 257 
257              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
258          } else {          } else {
259              # Attempt to load this table.              # Attempt to load this table.
260              my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);
261              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
262              $retVal->Accumulate($result);              $retVal->Accumulate($result);
263          }          }
# Line 446  Line 266 
266      return $retVal;      return $retVal;
267  }  }
268    
269    =head3 GenomeCounts
270    
271    C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>
272    
273    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
274    genomes will be included in the counts.
275    
276    =over 4
277    
278    =item complete
279    
280    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
281    counted
282    
283    =item RETURN
284    
285    A six-element list containing the number of genomes in each of six categories--
286    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
287    
288    =back
289    
290    =cut
291    
292    sub GenomeCounts {
293        # Get the parameters.
294        my ($self, $complete) = @_;
295        # Set the filter based on the completeness flag.
296        my $filter = ($complete ? "Genome(complete) = 1" : "");
297        # Get all the genomes and the related taxonomy information.
298        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
299        # Clear the counters.
300        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
301        # Loop through, counting the domains.
302        for my $genome (@genomes) {
303            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
304            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
305            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
306            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
307            elsif ($genome->[1] =~ /^env/i)      { ++$env }
308            else  { ++$unk }
309        }
310        # Return the counts.
311        return ($arch, $bact, $euk, $vir, $env, $unk);
312    }
313    
314    =head3 ContigCount
315    
316    C<< my $count = $sprout->ContigCount($genomeID); >>
317    
318    Return the number of contigs for the specified genome ID.
319    
320    =over 4
321    
322    =item genomeID
323    
324    ID of the genome whose contig count is desired.
325    
326    =item RETURN
327    
328    Returns the number of contigs for the specified genome.
329    
330    =back
331    
332    =cut
333    
334    sub ContigCount {
335        # Get the parameters.
336        my ($self, $genomeID) = @_;
337        # Get the contig count.
338        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
339        # Return the result.
340        return $retVal;
341    }
342    
343    =head3 GeneMenu
344    
345    C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); >>
346    
347    Return an HTML select menu of genomes. Each genome will be an option in the menu,
348    and will be displayed by name with the ID and a contig count attached. The selection
349    value will be the genome ID. The genomes will be sorted by genus/species name.
350    
351    =over 4
352    
353    =item attributes
354    
355    Reference to a hash mapping attributes to values for the SELECT tag generated.
356    
357    =item filterString
358    
359    A filter string for use in selecting the genomes. The filter string must conform
360    to the rules for the C<< ERDB->Get >> method.
361    
362    =item params
363    
364    Reference to a list of values to be substituted in for the parameter marks in
365    the filter string.
366    
367    =item selected (optional)
368    
369    ID of the genome to be initially selected.
370    
371    =item fast (optional)
372    
373    If specified and TRUE, the contig counts will be omitted to improve performance.
374    
375    =item RETURN
376    
377    Returns an HTML select menu with the specified genomes as selectable options.
378    
379    =back
380    
381    =cut
382    
383    sub GeneMenu {
384        # Get the parameters.
385        my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;
386        my $slowMode = ! $fast;
387        # Default to nothing selected. This prevents an execution warning if "$selected"
388        # is undefined.
389        $selected = "" unless defined $selected;
390        Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);
391        # Start the menu.
392        my $retVal = "<select " .
393            join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .
394            ">\n";
395        # Get the genomes.
396        my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',
397                                                                         'Genome(genus)',
398                                                                         'Genome(species)',
399                                                                         'Genome(unique-characterization)']);
400        # Sort them by name.
401        my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;
402        # Loop through the genomes, creating the option tags.
403        for my $genomeData (@sorted) {
404            # Get the data for this genome.
405            my ($genomeID, $genus, $species, $strain) = @{$genomeData};
406            # Get the contig count.
407            my $contigInfo = "";
408            if ($slowMode) {
409                my $count = $self->ContigCount($genomeID);
410                my $counting = ($count == 1 ? "contig" : "contigs");
411                $contigInfo = "[$count $counting]";
412            }
413            # Find out if we're selected.
414            my $selectOption = ($selected eq $genomeID ? " selected" : "");
415            # Build the option tag.
416            $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";
417        }
418        # Close the SELECT tag.
419        $retVal .= "</select>\n";
420        # Return the result.
421        return $retVal;
422    }
423    
424  =head3 Build  =head3 Build
425    
426  C<< $sprout->Build(); >>  C<< $sprout->Build(); >>
# Line 460  Line 435 
435      # Get the parameters.      # Get the parameters.
436      my ($self) = @_;      my ($self) = @_;
437      # Create the tables.      # Create the tables.
438      $self->{_erdb}->CreateTables;      $self->CreateTables();
439  }  }
440    
441  =head3 Genomes  =head3 Genomes
# Line 680  Line 655 
655      return ($contigID, $start, $dir, $len);      return ($contigID, $start, $dir, $len);
656  }  }
657    
658    
659    
660  =head3 PointLocation  =head3 PointLocation
661    
662  C<< my $found = Sprout::PointLocation($location, $point); >>  C<< my $found = Sprout::PointLocation($location, $point); >>
# Line 846  Line 823 
823      return @retVal;      return @retVal;
824  }  }
825    
826    =head3 GenomeLength
827    
828    C<< my $length = $sprout->GenomeLength($genomeID); >>
829    
830    Return the length of the specified genome in base pairs.
831    
832    =over 4
833    
834    =item genomeID
835    
836    ID of the genome whose base pair count is desired.
837    
838    =item RETURN
839    
840    Returns the number of base pairs in all the contigs of the specified
841    genome.
842    
843    =back
844    
845    =cut
846    
847    sub GenomeLength {
848        # Get the parameters.
849        my ($self, $genomeID) = @_;
850        # Declare the return variable.
851        my $retVal = 0;
852        # Get the genome's contig sequence lengths.
853        my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
854                           [$genomeID], 'IsMadeUpOf(len)');
855        # Sum the lengths.
856        map { $retVal += $_ } @lens;
857        # Return the result.
858        return $retVal;
859    }
860    
861    =head3 FeatureCount
862    
863    C<< my $count = $sprout->FeatureCount($genomeID, $type); >>
864    
865    Return the number of features of the specified type in the specified genome.
866    
867    =over 4
868    
869    =item genomeID
870    
871    ID of the genome whose feature count is desired.
872    
873    =item type
874    
875    Type of feature to count (eg. C<peg>, C<rna>, etc.).
876    
877    =item RETURN
878    
879    Returns the number of features of the specified type for the specified genome.
880    
881    =back
882    
883    =cut
884    
885    sub FeatureCount {
886        # Get the parameters.
887        my ($self, $genomeID, $type) = @_;
888        # Compute the count.
889        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
890                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
891                                    [$genomeID, $type]);
892        # Return the result.
893        return $retVal;
894    }
895    
896    =head3 GenomeAssignments
897    
898    C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>
899    
900    Return a list of a genome's assigned features. The return hash will contain each
901    assigned feature of the genome mapped to the text of its most recent functional
902    assignment.
903    
904    =over 4
905    
906    =item genomeID
907    
908    ID of the genome whose functional assignments are desired.
909    
910    =item RETURN
911    
912    Returns a reference to a hash which maps each feature to its most recent
913    functional assignment.
914    
915    =back
916    
917    =cut
918    
919    sub GenomeAssignments {
920        # Get the parameters.
921        my ($self, $genomeID) = @_;
922        # Declare the return variable.
923        my $retVal = {};
924        # Query the genome's features and annotations. We'll put the oldest annotations
925        # first so that the last assignment to go into the hash will be the correct one.
926        my $query = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],
927                               "HasFeature(from-link) = ? ORDER BY Annotation(time)",
928                               [$genomeID]);
929        # Loop through the annotations.
930        while (my $data = $query->Fetch) {
931            # Get the feature ID and annotation text.
932            my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',
933                                                    'Annotation(annotation)']);
934            # Check to see if this is an assignment. Note that the user really
935            # doesn't matter to us, other than we use it to determine whether or
936            # not this is an assignment.
937            my ($user, $assignment) = _ParseAssignment('fig', $annotation);
938            if ($user) {
939                # Here it's an assignment. We put it in the return hash, overwriting
940                # any older assignment that might be present.
941                $retVal->{$fid} = $assignment;
942            }
943        }
944        # Return the result.
945        return $retVal;
946    }
947    
948  =head3 ContigLength  =head3 ContigLength
949    
950  C<< my $length = $sprout->ContigLength($contigID); >>  C<< my $length = $sprout->ContigLength($contigID); >>
# Line 1400  Line 1499 
1499      my %retVal = ();      my %retVal = ();
1500      # Loop through the incoming features.      # Loop through the incoming features.
1501      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1502          # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1503          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
                                "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",  
                                [$featureID, $genomeID]);  
1504          # Peel off the BBHs found.          # Peel off the BBHs found.
1505          my @found = ();          my @found = ();
1506          while (my $bbh = $query->Fetch) {          for my $bbh (@bbhData) {
1507              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->[0];
1508          }          }
1509          $retVal{$featureID} = \@found;          $retVal{$featureID} = \@found;
1510      }      }
# Line 1421  Line 1518 
1518    
1519  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1520    
1521  Sprout does not support real similarities, so this method just returns the bidirectional  This method just returns the bidirectional best hits for performance reasons.
 best hits.  
1522    
1523  =over 4  =over 4
1524    
# Line 1442  Line 1538 
1538      # Get the parameters.      # Get the parameters.
1539      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1540      # Ask for the best hits.      # Ask for the best hits.
1541      my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],      my @lists = FIGRules::BBHData($featureID);
                               "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",  
                               [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],  
                               $count);  
1542      # Create the return value.      # Create the return value.
1543      my %retVal = ();      my %retVal = ();
1544      for my $tuple (@lists) {      for my $tuple (@lists) {
# Line 1455  Line 1548 
1548      return %retVal;      return %retVal;
1549  }  }
1550    
   
   
1551  =head3 IsComplete  =head3 IsComplete
1552    
1553  C<< my $flag = $sprout->IsComplete($genomeID); >>  C<< my $flag = $sprout->IsComplete($genomeID); >>
# Line 1584  Line 1675 
1675  sub CoupledFeatures {  sub CoupledFeatures {
1676      # Get the parameters.      # Get the parameters.
1677      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1678        Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1679      # Create a query to retrieve the functionally-coupled features.      # Create a query to retrieve the functionally-coupled features.
1680      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1681                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
# Line 1596  Line 1688 
1688          # Get the ID and score of the coupling.          # Get the ID and score of the coupling.
1689          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1690                                                          'Coupling(score)']);                                                          'Coupling(score)']);
1691          # The coupling ID contains the two feature IDs separated by a space. We use          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);
1692          # this information to find the ID of the other feature.          # Get the other feature that participates in the coupling.
1693          my ($fid1, $fid2) = split / /, $couplingID;          my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'],
1694          my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);                                             "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?",
1695                                               [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)');
1696            Trace("$couplingID target feature is $otherFeatureID.") if T(coupling => 4);
1697          # Attach the other feature's score to its ID.          # Attach the other feature's score to its ID.
1698          $retVal{$otherFeatureID} = $score;          $retVal{$otherFeatureID} = $score;
1699          $found = 1;          $found = 1;
# Line 1732  Line 1826 
1826      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1827      # Declare the return values. We'll start with the coupling ID and undefine the      # Declare the return values. We'll start with the coupling ID and undefine the
1828      # flag and score until we have more information.      # flag and score until we have more information.
1829      my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);      my ($retVal, $inverted, $score) = ($self->CouplingID($peg1, $peg2), undef, undef);
1830      # Find the coupling data.      # Find the coupling data.
1831      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1832                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
# Line 1753  Line 1847 
1847      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
1848  }  }
1849    
1850  =head3 CouplingID  =head3 GetSynonymGroup
   
 C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>  
1851    
1852  Return the coupling ID for a pair of feature IDs.  C<< my $id = $sprout->GetSynonymGroup($fid); >>
1853    
1854  The coupling ID is currently computed by joining the feature IDs in  Return the synonym group name for the specified feature.
 sorted order with a space. Client modules (that is, modules which  
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
1855    
1856  =over 4  =over 4
1857    
1858  =item peg1  =item fid
1859    
1860  First feature of interest.  ID of the feature whose synonym group is desired.
1861    
1862  =item peg2  =item RETURN
1863    
1864  Second feature of interest.  The name of the synonym group to which the feature belongs. If the feature does
1865    not belong to a synonym group, the feature ID itself is returned.
1866    
1867    =back
1868    
1869    =cut
1870    
1871    sub GetSynonymGroup {
1872        # Get the parameters.
1873        my ($self, $fid) = @_;
1874        # Declare the return variable.
1875        my $retVal;
1876        # Find the synonym group.
1877        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
1878                                       [$fid], 'IsSynonymGroupFor(from-link)');
1879        # Check to see if we found anything.
1880        if (@groups) {
1881            $retVal = $groups[0];
1882        } else {
1883            $retVal = $fid;
1884        }
1885        # Return the result.
1886        return $retVal;
1887    }
1888    
1889    =head3 GetBoundaries
1890    
1891    C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>
1892    
1893    Determine the begin and end boundaries for the locations in a list. All of the
1894    locations must belong to the same contig and have mostly the same direction in
1895    order for this method to produce a meaningful result. The resulting
1896    begin/end pair will contain all of the bases in any of the locations.
1897    
1898    =over 4
1899    
1900    =item locList
1901    
1902    List of locations to process.
1903    
1904  =item RETURN  =item RETURN
1905    
1906  Returns the ID that would be used to represent a functional coupling of  Returns a 3-tuple consisting of the contig ID, the beginning boundary,
1907  the two specified PEGs.  and the ending boundary. The beginning boundary will be left of the
1908    end for mostly-forward locations and right of the end for mostly-backward
1909    locations.
1910    
1911  =back  =back
1912    
1913  =cut  =cut
1914  #: Return Type $;  
1915  sub CouplingID {  sub GetBoundaries {
1916      return join " ", sort @_;      # Get the parameters.
1917        my ($self, @locList) = @_;
1918        # Set up the counters used to determine the most popular direction.
1919        my %counts = ( '+' => 0, '-' => 0 );
1920        # Get the last location and parse it.
1921        my $locObject = BasicLocation->new(pop @locList);
1922        # Prime the loop with its data.
1923        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
1924        # Count its direction.
1925        $counts{$locObject->Dir}++;
1926        # Loop through the remaining locations. Note that in most situations, this loop
1927        # will not iterate at all, because most of the time we will be dealing with a
1928        # singleton list.
1929        for my $loc (@locList) {
1930            # Create a location object.
1931            my $locObject = BasicLocation->new($loc);
1932            # Count the direction.
1933            $counts{$locObject->Dir}++;
1934            # Get the left end and the right end.
1935            my $left = $locObject->Left;
1936            my $right = $locObject->Right;
1937            # Merge them into the return variables.
1938            if ($left < $beg) {
1939                $beg = $left;
1940            }
1941            if ($right > $end) {
1942                $end = $right;
1943            }
1944        }
1945        # If the most common direction is reverse, flip the begin and end markers.
1946        if ($counts{'-'} > $counts{'+'}) {
1947            ($beg, $end) = ($end, $beg);
1948  }  }
1949        # Return the result.
1950        return ($contig, $beg, $end);
1951    }
1952    
1953    =head3 CouplingID
1954    
1955    C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>
1956    
1957    Return the coupling ID for a pair of feature IDs.
1958    
1959    The coupling ID is currently computed by joining the feature IDs in
1960    sorted order with a space. Client modules (that is, modules which
1961    use Sprout) should not, however, count on this always being the
1962    case. This method provides a way for abstracting the concept of a
1963    coupling ID. All that we know for sure about it is that it can be
1964    generated easily from the feature IDs and the order of the IDs
1965    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1966    will have the same value as C<CouplingID("b1", "a1")>.
1967    
1968    =over 4
1969    
1970    =item peg1
1971    
1972    First feature of interest.
1973    
1974    =item peg2
1975    
1976  =head3 GetEntityTypes  Second feature of interest.
1977    
1978  C<< my @entityList = $sprout->GetEntityTypes(); >>  =item RETURN
1979    
1980  Return the list of supported entity types.  Returns the ID that would be used to represent a functional coupling of
1981    the two specified PEGs.
1982    
1983    =back
1984    
1985  =cut  =cut
1986  #: Return Type @;  #: Return Type $;
1987  sub GetEntityTypes {  sub CouplingID {
1988      # Get the parameters.      my ($self, @pegs) = @_;
1989      my ($self) = @_;      return $self->DigestKey(join " ", sort @pegs);
     # Get the underlying database object.  
     my $erdb = $self->{_erdb};  
     # Get its entity type list.  
     my @retVal = $erdb->GetEntityTypes();  
1990  }  }
1991    
1992  =head3 ReadFasta  =head3 ReadFasta
# Line 1953  Line 2134 
2134      # Get the data directory name.      # Get the data directory name.
2135      my $outputDirectory = $self->{_options}->{dataDir};      my $outputDirectory = $self->{_options}->{dataDir};
2136      # Dump the relations.      # Dump the relations.
2137      $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2138  }  }
2139    
2140  =head3 XMLFileName  =head3 XMLFileName
# Line 2005  Line 2186 
2186      # Get the parameters.      # Get the parameters.
2187      my ($self, $objectType, $fieldHash) = @_;      my ($self, $objectType, $fieldHash) = @_;
2188      # Call the underlying method.      # Call the underlying method.
2189      $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2190  }  }
2191    
2192  =head3 Annotate  =head3 Annotate
# Line 2164  Line 2345 
2345      return @retVal;      return @retVal;
2346  }  }
2347    
 =head3 Exists  
   
 C<< my $found = $sprout->Exists($entityName, $entityID); >>  
   
 Return TRUE if an entity exists, else FALSE.  
   
 =over 4  
   
 =item entityName  
   
 Name of the entity type (e.g. C<Feature>) relevant to the existence check.  
   
 =item entityID  
   
 ID of the entity instance whose existence is to be checked.  
   
 =item RETURN  
   
 Returns TRUE if the entity instance exists, else FALSE.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub Exists {  
     # Get the parameters.  
     my ($self, $entityName, $entityID) = @_;  
     # Check for the entity instance.  
     Trace("Checking existence of $entityName with ID=$entityID.") if T(4);  
     my $testInstance = $self->GetEntity($entityName, $entityID);  
     # Return an existence indicator.  
     my $retVal = ($testInstance ? 1 : 0);  
     return $retVal;  
 }  
   
2348  =head3 FeatureTranslation  =head3 FeatureTranslation
2349    
2350  C<< my $translation = $sprout->FeatureTranslation($featureID); >>  C<< my $translation = $sprout->FeatureTranslation($featureID); >>
# Line 2533  Line 2679 
2679      return $retVal;      return $retVal;
2680  }  }
2681    
2682    =head3 PropertyID
2683    
2684    C<< my $id = $sprout->PropertyID($propName, $propValue); >>
2685    
2686    Return the ID of the specified property name and value pair, if the
2687    pair exists.
2688    
2689    =over 4
2690    
2691    =item propName
2692    
2693    Name of the desired property.
2694    
2695    =item propValue
2696    
2697    Value expected for the desired property.
2698    
2699    =item RETURN
2700    
2701    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2702    
2703    =back
2704    
2705    =cut
2706    
2707    sub PropertyID {
2708        # Get the parameters.
2709        my ($self, $propName, $propValue) = @_;
2710        # Try to find the ID.
2711        my ($retVal) = $self->GetFlat(['Property'],
2712                                      "Property(property-name) = ? AND Property(property-value) = ?",
2713                                      [$propName, $propValue], 'Property(id)');
2714        # Return the result.
2715        return $retVal;
2716    }
2717    
2718  =head3 MergedAnnotations  =head3 MergedAnnotations
2719    
2720  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>
# Line 2730  Line 2912 
2912      # Get the parameters.      # Get the parameters.
2913      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2914      # Get the list of names.      # Get the list of names.
2915      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
2916                                  [$featureID], 'HasSSCell(from-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
2917      # Return the result.      # Return the result, sorted.
2918      return @retVal;      return sort @retVal;
2919  }  }
2920    
2921    =head3 GenomeSubsystemData
2922    
2923    C<< my %featureData = $sprout->GenomeSubsystemData($genomeID); >>
2924    
2925    Return a hash mapping genome features to their subsystem roles.
2926    
2927    =over 4
2928    
2929    =item genomeID
2930    
2931    ID of the genome whose subsystem feature map is desired.
2932    
2933    =item RETURN
2934    
2935    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
2936    2-tuple contains a subsystem name followed by a role ID.
2937    
2938    =back
2939    
2940    =cut
2941    
2942    sub GenomeSubsystemData {
2943        # Get the parameters.
2944        my ($self, $genomeID) = @_;
2945        # Declare the return variable.
2946        my %retVal = ();
2947        # Get a list of the genome features that participate in subsystems. For each
2948        # feature we get its spreadsheet cells and the corresponding roles.
2949        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
2950                                 "HasFeature(from-link) = ?", [$genomeID],
2951                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
2952        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
2953        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
2954        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
2955        # again at the end to filter out participation in subsystems with a negative variant code.
2956        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
2957                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
2958                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
2959        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
2960        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
2961        # link these two lists together to create the result. First, we want a hash mapping
2962        # spreadsheet cells to subsystem names.
2963        my %subHash = map { $_->[0] => $_->[1] } @cellData;
2964        # We loop through @cellData to build the hash.
2965        for my $roleEntry (@roleData) {
2966            # Get the data for this feature and cell.
2967            my ($fid, $cellID, $role) = @{$roleEntry};
2968            # Check for a subsystem name.
2969            my $subsys = $subHash{$cellID};
2970            if ($subsys) {
2971                # Insure this feature has an entry in the return hash.
2972                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
2973                # Merge in this new data.
2974                push @{$retVal{$fid}}, [$subsys, $role];
2975            }
2976        }
2977        # Return the result.
2978        return %retVal;
2979    }
2980    
2981  =head3 RelatedFeatures  =head3 RelatedFeatures
2982    
# Line 2773  Line 3013 
3013      # Get the parameters.      # Get the parameters.
3014      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3015      # 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.
3016      my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                      "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                      'IsBidirectionalBestHitOf(to-link)');  
3017      # Now we loop through the features, pulling out the ones that have the correct      # Now we loop through the features, pulling out the ones that have the correct
3018      # functional assignment.      # functional assignment.
3019      my @retVal = ();      my @retVal = ();
# Line 2839  Line 3077 
3077      return @retVal;      return @retVal;
3078  }  }
3079    
 =head3 GetAll  
   
 C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>  
   
 Return a list of values taken from the objects returned by a query. The first three  
 parameters correspond to the parameters of the L</Get> method. The final parameter is  
 a list of the fields desired from each record found by the query. The field name  
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
   
 The list returned will be a list of lists. Each element of the list will contain  
 the values returned for the fields specified in the fourth parameter. If one of the  
 fields specified returns multiple values, they are flattened in with the rest. For  
 example, the following call will return a list of the features in a particular  
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
   
 C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item fields  
   
 List of the fields to be returned in each element of the list returned.  
   
 =item count  
   
 Maximum number of records to return. If omitted or 0, all available records will be returned.  
   
 =item RETURN  
   
 Returns a list of list references. Each element of the return list contains the values for the  
 fields specified in the B<fields> parameter.  
   
 =back  
   
 =cut  
 #: Return Type @@;  
 sub GetAll {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;  
     # Call the ERDB method.  
     my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,  
                                         $fields, $count);  
     # Return the resulting list.  
     return @retVal;  
 }  
   
 =head3 GetFlat  
   
 C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>  
   
 This is a variation of L</GetAll> that asks for only a single field per record and  
 returns a single flattened list.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item field  
   
 Name of the field to be used to get the elements of the list returned.  
   
 =item RETURN  
   
 Returns a list of values.  
   
 =back  
   
 =cut  
 #: Return Type @;  
 sub GetFlat {  
     # Get the parameters.  
     my ($self, $objectNames, $filterClause, $parameterList, $field) = @_;  
     # Construct the query.  
     my $query = $self->Get($objectNames, $filterClause, $parameterList);  
     # Create the result list.  
     my @retVal = ();  
     # Loop through the records, adding the field values found to the result list.  
     while (my $row = $query->Fetch()) {  
         push @retVal, $row->Value($field);  
     }  
     # Return the list created.  
     return @retVal;  
 }  
   
3080  =head3 Protein  =head3 Protein
3081    
3082  C<< my $protein = Sprout::Protein($sequence, $table); >>  C<< my $protein = Sprout::Protein($sequence, $table); >>
# Line 3030  Line 3149 
3149      # Loop through the input triples.      # Loop through the input triples.
3150      my $n = length $sequence;      my $n = length $sequence;
3151      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3152          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3153          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3154            my $triple = uc substr($sequence, $i, 3);
3155          # Translate it using the table.          # Translate it using the table.
3156          my $protein = "X";          my $protein = "X";
3157          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 3059  Line 3179 
3179      # 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.
3180      my @retVal = ($self->{_options}->{dataDir});      my @retVal = ($self->{_options}->{dataDir});
3181      # Concatenate the table names.      # Concatenate the table names.
3182      push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3183      # Return the result.      # Return the result.
3184      return @retVal;      return @retVal;
3185  }  }
3186    
3187  =head3 LowBBHs  =head3 LowBBHs
3188    
3189  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>
3190    
3191  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3192  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3095  Line 3215 
3215      my ($self, $featureID, $cutoff) = @_;      my ($self, $featureID, $cutoff) = @_;
3216      # Create the return hash.      # Create the return hash.
3217      my %retVal = ();      my %retVal = ();
3218      # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3219      my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                 [$cutoff, $featureID],  
                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3220      # Form the results into the return hash.      # Form the results into the return hash.
3221      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3222          $retVal{$pair->[0]} = $pair->[1];          $retVal{$pair->[0]} = $pair->[1];
# Line 3108  Line 3225 
3225      return %retVal;      return %retVal;
3226  }  }
3227    
3228    =head3 Sims
3229    
3230    C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>
3231    
3232    Get a list of similarities for a specified feature. Similarity information is not kept in the
3233    Sprout database; rather, they are retrieved from a network server. The similarities are
3234    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3235    so that its elements can be accessed by name.
3236    
3237    Similarities can be either raw or expanded. The raw similarities are basic
3238    hits between features with similar DNA. Expanding a raw similarity drags in any
3239    features considered substantially identical. So, for example, if features B<A1>,
3240    B<A2>, and B<A3> are all substatially identical to B<A>, then a raw similarity
3241    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3242    
3243    =over 4
3244    
3245    =item fid
3246    
3247    ID of the feature whose similarities are desired.
3248    
3249    =item maxN
3250    
3251    Maximum number of similarities to return.
3252    
3253    =item maxP
3254    
3255    Minumum allowable similarity score.
3256    
3257    =item select
3258    
3259    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3260    means only similarities to FIG features are returned; C<all> means all expanded
3261    similarities are returned; and C<figx> means similarities are expanded until the
3262    number of FIG features equals the maximum.
3263    
3264    =item max_expand
3265    
3266    The maximum number of features to expand.
3267    
3268    =item filters
3269    
3270    Reference to a hash containing filter information, or a subroutine that can be
3271    used to filter the sims.
3272    
3273    =item RETURN
3274    
3275    Returns a reference to a list of similarity objects, or C<undef> if an error
3276    occurred.
3277    
3278    =back
3279    
3280    =cut
3281    
3282    sub Sims {
3283        # Get the parameters.
3284        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3285        # Create the shim object to test for deleted FIDs.
3286        my $shim = FidCheck->new($self);
3287        # Ask the network for sims.
3288        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3289        # Return the result.
3290        return $retVal;
3291    }
3292    
3293    =head3 IsAllGenomes
3294    
3295    C<< my $flag = $sprout->IsAllGenomes(\@list, \@checkList); >>
3296    
3297    Return TRUE if all genomes in the second list are represented in the first list at
3298    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3299    compared to a list of all the genomes.
3300    
3301    =over 4
3302    
3303    =item list
3304    
3305    Reference to the list to be compared to the second list.
3306    
3307    =item checkList (optional)
3308    
3309    Reference to the comparison target list. Every genome ID in this list must occur at
3310    least once in the first list. If this parameter is omitted, a list of all the genomes
3311    is used.
3312    
3313    =item RETURN
3314    
3315    Returns TRUE if every item in the second list appears at least once in the
3316    first list, else FALSE.
3317    
3318    =back
3319    
3320    =cut
3321    
3322    sub IsAllGenomes {
3323        # Get the parameters.
3324        my ($self, $list, $checkList) = @_;
3325        # Supply the checklist if it was omitted.
3326        $checkList = [$self->Genomes()] if ! defined($checkList);
3327        # Create a hash of the original list.
3328        my %testList = map { $_ => 1 } @{$list};
3329        # Declare the return variable. We assume that the representation
3330        # is complete and stop at the first failure.
3331        my $retVal = 1;
3332        my $n = scalar @{$checkList};
3333        for (my $i = 0; $retVal && $i < $n; $i++) {
3334            if (! $testList{$checkList->[$i]}) {
3335                $retVal = 0;
3336            }
3337        }
3338        # Return the result.
3339        return $retVal;
3340    }
3341    
3342  =head3 GetGroups  =head3 GetGroups
3343    
3344  C<< my %groups = $sprout->GetGroups(\@groupList); >>  C<< my %groups = $sprout->GetGroups(\@groupList); >>
# Line 3129  Line 3360 
3360          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3361          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3362          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3363              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3364                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3365              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3366          }          }
# Line 3137  Line 3368 
3368          # Here we need all of the groups. In this case, we run through all          # Here we need all of the groups. In this case, we run through all
3369          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3370          # group. Note that we use a filter clause to insure that only genomes          # group. Note that we use a filter clause to insure that only genomes
3371          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3372          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3373                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3374          # Loop through the genomes found.          # Loop through the genomes found.
3375          for my $genome (@genomes) {          for my $genome (@genomes) {
3376              # Pop this genome's ID off the current list.              # Pop this genome's ID off the current list.
# Line 3257  Line 3488 
3488      # Get the parameters.      # Get the parameters.
3489      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3490      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3491      my $retVal = $self->{_erdb}->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);
3492      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3493      my $stats = $self->{_erdb}->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, $testFlag);
3494      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3495      # Return the result.      # Return the result.
3496      return $retVal;      return $retVal;
3497  }  }
3498    
3499  =head2 Internal Utility Methods  =head3 Fix
3500    
3501  =head3 ParseAssignment  C<< my %fixedHash = Sprout::Fix(%groupHash); >>
3502    
3503  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Prepare a genome group hash (like that returned by L</GetGroups> for processing.
3504  the user, function text, and assigning user will be returned as a 3-element list. If it  Groups with the same primary name will be combined. The primary name is the
3505  isn't, an empty list will be returned.  first capitalized word in the group name.
3506    
3507  A functional assignment is always of the form  =over 4
3508    
3509      C<set >I<YYYY>C< function to\n>I<ZZZZZ>  =item groupHash
3510    
3511  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,  Hash to be fixed up.
 the user and the assigning user (from MadeAnnotation) will be the same, but that is  
 not always the case.  
3512    
3513  In addition, the functional role may contain extra data that is stripped, such as  =item RETURN
 terminating spaces or a comment separated from the rest of the text by a tab.  
3514    
3515  This is a static method.  Returns a fixed-up version of the hash.
3516    
3517  =over 4  =back
3518    
3519  =item user  =cut
3520    
3521  Name of the assigning user.  sub Fix {
3522        # Get the parameters.
3523        my (%groupHash) = @_;
3524        # Create the result hash.
3525        my %retVal = ();
3526        # Copy over the genomes.
3527        for my $groupID (keys %groupHash) {
3528            # Make a safety copy of the group ID.
3529            my $realGroupID = $groupID;
3530            # Yank the primary name.
3531            if ($groupID =~ /([A-Z]\w+)/) {
3532                $realGroupID = $1;
3533            }
3534            # Append this group's genomes into the result hash.
3535            Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}});
3536        }
3537        # Return the result hash.
3538        return %retVal;
3539    }
3540    
3541  =item text  =head3 GroupPageName
3542    
3543  Text of the annotation.  C<< my $name = $sprout->GroupPageName($group); >>
3544    
3545    Return the name of the page for the specified NMPDR group.
3546    
3547    =over 4
3548    
3549    =item group
3550    
3551    Name of the relevant group.
3552    
3553  =item RETURN  =item RETURN
3554    
3555  Returns an empty list if the annotation is not a functional assignment; otherwise, returns  Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3556  a two-element list containing the user name and the function text.  memory it will be read in.
3557    
3558  =back  =back
3559    
3560  =cut  =cut
3561    
3562  sub _ParseAssignment {  sub GroupPageName {
3563      # Get the parameters.      # Get the parameters.
3564      my ($user, $text) = @_;      my ($self, $group) = @_;
3565      # Declare the return value.      # Declare the return variable.
3566      my @retVal = ();      my $retVal;
3567      # Check to see if this is a functional assignment.      # Check for the group file data.
3568      my ($type, $function) = split(/\n/, $text);      if (! defined $self->{groupHash}) {
3569      if ($type =~ m/^set function to$/i) {          # Read the group file.
3570          # Here we have an assignment without a user, so we use the incoming user ID.          my %groupData = Sprout::ReadGroupFile($self->{_options}->{dataDir} . "/groups.tbl");
3571          @retVal = ($user, $function);          # Store it in our object.
3572      } elsif ($type =~ m/^set (\S+) function to$/i) {          $self->{groupHash} = \%groupData;
         # Here we have an assignment with a user that is passed back to the caller.  
         @retVal = ($1, $function);  
3573      }      }
3574      # If we have an assignment, we need to clean the function text. There may be      # Compute the real group name.
3575      # extra junk at the end added as a note from the user.      my $realGroup = $group;
3576      if (@retVal) {      if ($group =~ /([A-Z]\w+)/) {
3577          $retVal[1] =~ s/(\t\S)?\s*$//;          $realGroup = $1;
3578      }      }
3579      # Return the result list.      # Return the page name.
3580      return @retVal;      $retVal = "../content/" . $self->{groupHash}->{$realGroup}->[1];
3581        # Return the result.
3582        return $retVal;
3583  }  }
3584    
3585  =head3 FriendlyTimestamp  =head3 ReadGroupFile
3586    
3587  Convert a time number to a user-friendly time stamp for display.  C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >>
3588    
3589  This is a static method.  Read in the data from the specified group file. The group file contains information
3590    about each of the NMPDR groups.
3591    
3592  =over 4  =over 4
3593    
3594  =item timeValue  =item name
3595    
3596  Numeric time value.  Name of the group.
3597    
3598    =item page
3599    
3600    Name of the group's page on the web site (e.g. C<campy.php> for
3601    Campylobacter)
3602    
3603    =item genus
3604    
3605    Genus of the group
3606    
3607    =item species
3608    
3609    Species of the group, or an empty string if the group is for an entire
3610    genus. If the group contains more than one species, the species names
3611    should be separated by commas.
3612    
3613    =back
3614    
3615    The parameters to this method are as follows
3616    
3617    =over 4
3618    
3619    =item groupFile
3620    
3621    Name of the file containing the group data.
3622    
3623  =item RETURN  =item RETURN
3624    
3625  Returns a string containing the same time in user-readable format.  Returns a hash keyed on group name. The value of each hash
3626    
3627  =back  =back
3628    
3629  =cut  =cut
3630    
3631  sub FriendlyTimestamp {  sub ReadGroupFile {
3632      my ($timeValue) = @_;      # Get the parameters.
3633      my $retVal = localtime($timeValue);      my ($groupFileName) = @_;
3634      return $retVal;      # Declare the return variable.
3635        my %retVal;
3636        # Read the group file.
3637        my @groupLines = Tracer::GetFile($groupFileName);
3638        for my $groupLine (@groupLines) {
3639            my ($name, $page, $genus, $species) = split(/\t/, $groupLine);
3640            $retVal{$name} = [$page, $genus, $species];
3641        }
3642        # Return the result.
3643        return %retVal;
3644  }  }
3645    
3646  =head3 AddProperty  =head3 AddProperty
# Line 3411  Line 3700 
3700      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3701  }  }
3702    
3703    =head2 Virtual Methods
3704    
3705    =head3 CleanKeywords
3706    
3707    C<< my $cleanedString = $sprout->CleanKeywords($searchExpression); >>
3708    
3709    Clean up a search expression or keyword list. This involves converting the periods
3710    in EC numbers to underscores, converting non-leading minus signs to underscores,
3711    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3712    characters. In addition, any extra spaces are removed.
3713    
3714    =over 4
3715    
3716    =item searchExpression
3717    
3718    Search expression or keyword list to clean. Note that a search expression may
3719    contain boolean operators which need to be preserved. This includes leading
3720    minus signs.
3721    
3722    =item RETURN
3723    
3724    Cleaned expression or keyword list.
3725    
3726    =back
3727    
3728    =cut
3729    
3730    sub CleanKeywords {
3731        # Get the parameters.
3732        my ($self, $searchExpression) = @_;
3733        # Perform the standard cleanup.
3734        my $retVal = $self->ERDB::CleanKeywords($searchExpression);
3735        # Fix the periods in EC and TC numbers.
3736        $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
3737        # Fix non-trailing periods.
3738        $retVal =~ s/\.(\w)/_$1/g;
3739        # Fix non-leading minus signs.
3740        $retVal =~ s/(\w)[\-]/$1_/g;
3741        # Fix the vertical bars and colons
3742        $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
3743        # Return the result.
3744        return $retVal;
3745    }
3746    
3747    =head2 Internal Utility Methods
3748    
3749    =head3 ParseAssignment
3750    
3751    Parse annotation text to determine whether or not it is a functional assignment. If it is,
3752    the user, function text, and assigning user will be returned as a 3-element list. If it
3753    isn't, an empty list will be returned.
3754    
3755    A functional assignment is always of the form
3756    
3757        C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3758    
3759    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3760    the user and the assigning user (from MadeAnnotation) will be the same, but that is
3761    not always the case.
3762    
3763    In addition, the functional role may contain extra data that is stripped, such as
3764    terminating spaces or a comment separated from the rest of the text by a tab.
3765    
3766    This is a static method.
3767    
3768    =over 4
3769    
3770    =item user
3771    
3772    Name of the assigning user.
3773    
3774    =item text
3775    
3776    Text of the annotation.
3777    
3778    =item RETURN
3779    
3780    Returns an empty list if the annotation is not a functional assignment; otherwise, returns
3781    a two-element list containing the user name and the function text.
3782    
3783    =back
3784    
3785    =cut
3786    
3787    sub _ParseAssignment {
3788        # Get the parameters.
3789        my ($user, $text) = @_;
3790        # Declare the return value.
3791        my @retVal = ();
3792        # Check to see if this is a functional assignment.
3793        my ($type, $function) = split(/\n/, $text);
3794        if ($type =~ m/^set function to$/i) {
3795            # Here we have an assignment without a user, so we use the incoming user ID.
3796            @retVal = ($user, $function);
3797        } elsif ($type =~ m/^set (\S+) function to$/i) {
3798            # Here we have an assignment with a user that is passed back to the caller.
3799            @retVal = ($1, $function);
3800        }
3801        # If we have an assignment, we need to clean the function text. There may be
3802        # extra junk at the end added as a note from the user.
3803        if (defined( $retVal[1] )) {
3804            $retVal[1] =~ s/(\t\S)?\s*$//;
3805        }
3806        # Return the result list.
3807        return @retVal;
3808    }
3809    
3810    =head3 FriendlyTimestamp
3811    
3812    Convert a time number to a user-friendly time stamp for display.
3813    
3814    This is a static method.
3815    
3816    =over 4
3817    
3818    =item timeValue
3819    
3820    Numeric time value.
3821    
3822    =item RETURN
3823    
3824    Returns a string containing the same time in user-readable format.
3825    
3826    =back
3827    
3828    =cut
3829    
3830    sub FriendlyTimestamp {
3831        my ($timeValue) = @_;
3832        my $retVal = localtime($timeValue);
3833        return $retVal;
3834    }
3835    
3836    
3837  1;  1;

Legend:
Removed from v.1.56  
changed lines
  Added in v.1.92

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3