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

Diff of /Sprout/Sprout.pm

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

revision 1.5, Tue Jan 25 03:02:07 2005 UTC revision 1.120, Thu Oct 2 16:32:42 2008 UTC
# Line 2  Line 2 
2    
3          use Data::Dumper;          use Data::Dumper;
4          use strict;          use strict;
         use Carp;  
5          use DBKernel;          use DBKernel;
6          use XML::Simple;          use XML::Simple;
7          use DBQuery;          use DBQuery;
8          use DBObject;      use ERDBObject;
         use ERDB;  
9          use Tracer;          use Tracer;
10          use FIGRules;          use FIGRules;
11        use FidCheck;
12          use Stats;          use Stats;
13      use POSIX qw(strftime);      use POSIX qw(strftime);
14        use BasicLocation;
15        use CustomAttributes;
16        use RemoteCustomAttributes;
17        use CGI;
18        use WikiTools;
19        use BioWords;
20        use base qw(ERDB);
21    
22  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
23    
# Line 25  Line 30 
30  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>
31  whose definition and data files are in a co-directory named F<Data>.  whose definition and data files are in a co-directory named F<Data>.
32    
33  C<< my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' }); >>      my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' });
34    
35  Once you have a sprout object, you may use it to re-create the database, load the tables from  Once you have a sprout object, you may use it to re-create the database, load the tables from
36  tab-delimited flat files and perform queries. Several special methods are provided for common  tab-delimited flat files and perform queries. Several special methods are provided for common
37  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
38  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
39    
40    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
41    
42  =cut  =cut
43    
44  #: Constructor SFXlate->new_sprout_only();  #: Constructor SFXlate->new_sprout_only();
45    
   
46  =head2 Public Methods  =head2 Public Methods
47    
48  =head3 new  =head3 new
49    
50  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
51    
52  This is the constructor for a sprout object. It connects to the database and loads the  This is the constructor for a sprout object. It connects to the database and loads the
53  database definition into memory. The positional first parameter specifies the name of the  database definition into memory. The positional first parameter specifies the name of the
# Line 51  Line 57 
57    
58  =item dbName  =item dbName
59    
60  Name of the database.  Name of the database. If omitted, the default Sprout database name is used.
61    
62  =item options  =item options
63    
# Line 63  Line 69 
69    
70  * 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>)
71    
72  * 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)
73    
74  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
75    
76    * B<sock> connection socket (default same as SEED)
77    
78  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
79    
80  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
81    
82    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
83    
84    * B<host> name of the database host
85    
86  =back  =back
87    
88  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
89  I<fig> with a password of I<admin>. The database load files are in the directory  I<fig> with a password of I<admin>. The database load files are in the directory
90  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
91    
92  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
93    
94  =cut  =cut
95    
96  sub new {  sub new {
97          # Get the parameters.          # Get the parameters.
98          my ($class, $dbName, $options) = @_;          my ($class, $dbName, $options) = @_;
99        # Default the database name if it is missing.
100        if (! defined $dbName) {
101            $dbName = $FIG_Config::sproutDB;
102        } elsif (ref $dbName eq 'HASH') {
103            $options = $dbName;
104            $dbName = $FIG_Config::sproutDB;
105        }
106        # Compute the DBD directory.
107        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
108                                                      $FIG_Config::fig );
109          # 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
110          # the incoming data.          # the incoming data.
111          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
112                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
113                                             dataDir              => 'Data',                      # data file directory                                                          # database type
114                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
115                                             userData             => 'root/',                     # user name and password                                                          # data file directory
116                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
117                                                            # database definition file name
118                           userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
119                                                            # user name and password
120                           port         => $FIG_Config::sproutPort,
121                                                            # database connection port
122                           sock         => $FIG_Config::sproutSock,
123                           host         => $FIG_Config::sprout_host,
124                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
125                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
126                           noDBOpen     => 0,               # 1 to suppress the database open
127                                            }, $options);                                            }, $options);
128          # Get the data directory.          # Get the data directory.
129          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 101  Line 131 
131          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
132          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
133          # Connect to the database.          # Connect to the database.
134          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
135        if (! $optionTable->{noDBOpen}) {
136            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
137            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
138                                    $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
139        }
140          # Create the ERDB object.          # Create the ERDB object.
141          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
142          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
143          # Create this object.      # Add the option table and XML file name.
144          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
145          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
146          bless $self;      # Set up space for the group file data.
147          return $self;      $retVal->{groupHash} = undef;
148        # Set up space for the genome hash. We use this to identify NMPDR genomes.
149        $retVal->{genomeHash} = undef;
150        # Remember the data directory name.
151        $retVal->{dataDir} = $dataDir;
152        # Return it.
153        return $retVal;
154  }  }
155    
156  =head3 MaxSegment  =head3 ca
157    
158  C<< my $length = $sprout->MaxSegment(); >>      my $ca = $sprout->ca():;
159    
160  This method returns the maximum permissible length of a feature segment. The length is important  Return the [[CustomAttributesPm]] object for retrieving object
161  because it enables us to make reasonable guesses at how to find features inside a particular  properties.
 contig region. For example, if the maximum length is 4000 and we're looking for a feature that  
 overlaps the region from 6000 to 7000 we know that the starting position must be between 2001  
 and 10999.  
162    
163  =cut  =cut
 #: Return Type $;  
 sub MaxSegment {  
         my $self = shift @_;  
         return $self->{_options}->{maxSegmentLength};  
 }  
   
 =head3 MaxSequence  
   
 C<< my $length = $sprout->MaxSequence(); >>  
   
 This method returns the maximum permissible length of a contig sequence. A contig is broken  
 into sequences in order to save memory resources. In particular, when manipulating features,  
 we generally only need a few sequences in memory rather than the entire contig.  
164    
165  =cut  sub ca {
166  #: Return Type $;      # Get the parameters.
167  sub MaxSequence {      my ($self) = @_;
168          my $self = shift @_;      # Do we already have an attribute object?
169          return $self->{_options}->{maxSequenceLength};      my $retVal = $self->{_ca};
170        if (! defined $retVal) {
171            # No, create one. How we do it depends on the configuration.
172            if ($FIG_Config::attrURL) {
173                Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
174                $retVal = RemoteCustomAttributes->new($FIG_Config::attrURL);
175            } elsif ($FIG_Config::attrDbName) {
176                Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
177                my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
178                $retVal = CustomAttributes->new(user => $user);
179            }
180            # Save it for next time.
181            $self->{_ca} = $retVal;
182        }
183        # Return the result.
184        return $retVal;
185  }  }
186    
187  =head3 Get  =head3 CoreGenomes
   
 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)"); >>  
188    
189  Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an      my @genomes = $sprout->CoreGenomes($scope);
 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.  
190    
191  If multiple names are specified, then the query processor will automatically determine a  Return the IDs of NMPDR genomes in the specified scope.
 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.  
192    
193  =over 4  =over 4
194    
195  =item objectNames  =item scope
   
 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.  
196    
197  =item parameterList  Scope of the desired genomes. C<core> covers the original core genomes,
198    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
199  List of the parameters to be substituted in for the parameters marks in the filter clause.  genomes in the system.
200    
201  =item RETURN  =item RETURN
202    
203  Returns a B<DBQuery> that can be used to iterate through all of the results.  Returns a list of the IDs for the genomes in the specified scope.
204    
205  =back  =back
206    
207  =cut  =cut
208    
209  sub Get {  sub CoreGenomes {
210          # Get the parameters.          # Get the parameters.
211          my $self = shift @_;      my ($self, $scope) = @_;
212          my ($objectNames, $filterClause, $parameterList) = @_;      # Declare the return variable.
213          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      my @retVal = ();
214          # rather than a list of parameters. The next step is to convert the parameters from a reference      # If we want all genomes, then this is easy.
215          # to a real list. We can only do this if the parameters have been specified.      if ($scope eq 'all') {
216          my @parameters;          @retVal = $self->Genomes();
217          if ($parameterList) { @parameters = @{$parameterList}; }      } else {
218          return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);          # Here we're dealing with groups. Get the hash of all the
219            # genome groups.
220            my %groups = $self->GetGroups();
221            # Loop through the groups, keeping the ones that we want.
222            for my $group (keys %groups) {
223                # Decide if we want to keep this group.
224                my $keepGroup = 0;
225                if ($scope eq 'nmpdr') {
226                    # NMPDR mode: keep all groups.
227                    $keepGroup = 1;
228                } elsif ($scope eq 'core') {
229                    # CORE mode. Only keep real core groups.
230                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
231                        $keepGroup = 1;
232                    }
233                }
234                # Add this group if we're keeping it.
235                if ($keepGroup) {
236                    push @retVal, @{$groups{$group}};
237                }
238            }
239        }
240        # Return the result.
241        return @retVal;
242  }  }
243    
244  =head3 GetEntity  =head3 SuperGroup
245    
246  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my $superGroup = $sprout->SuperGroup($groupName);
247    
248  Return an object describing the entity instance with a specified ID.  Return the name of the super-group containing the specified NMPDR genome
249    group. If no appropriate super-group can be found, an error will be
250    thrown.
251    
252  =over 4  =over 4
253    
254  =item entityType  =item groupName
   
 Entity type name.  
255    
256  =item ID  Name of the group whose super-group is desired.
   
 ID of the desired entity.  
257    
258  =item RETURN  =item RETURN
259    
260  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns the name of the super-group containing the incoming group.
 instance is found with the specified key.  
261    
262  =back  =back
263    
264  =cut  =cut
265    
266  sub GetEntity {  sub SuperGroup {
267          # Get the parameters.          # Get the parameters.
268          my $self = shift @_;      my ($self, $groupName) = @_;
269          my ($entityType, $ID) = @_;      # Declare the return variable.
270          # Create a query.      my $retVal;
271          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      # Get the group hash.
272          # Get the first (and only) object.      my %groupHash = $self->CheckGroupFile();
273          my $retVal = $query->Fetch();      # Find the super-group genus.
274        $groupName =~ /([A-Z]\w+)/;
275        my $nameThing = $1;
276        # See if it's directly in the group hash.
277        if (exists $groupHash{$nameThing}) {
278            # Yes, then it's our result.
279            $retVal = $nameThing;
280        } else {
281            # No, so we have to search.
282            for my $superGroup (keys %groupHash) {
283                # Get this super-group's item list.
284                my $list = $groupHash{$superGroup}->{contents};
285                # Search it.
286                if (grep { $_->[0] eq $nameThing } @{$list}) {
287                    $retVal = $superGroup;
288                }
289            }
290            # Make sure we found something.
291            if (! $retVal) {
292                Confess("No super-group found for \"$groupName\".");
293            }
294        }
295          # Return the result.          # Return the result.
296          return $retVal;          return $retVal;
297  }  }
298    
299  =head3 GetEntityValues  =head3 MaxSegment
   
 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  
300    
301  Returns a flattened list of the values of the specified fields for the specified entity.      my $length = $sprout->MaxSegment();
302    
303  =back  This method returns the maximum permissible length of a feature segment. The length is important
304    because it enables us to make reasonable guesses at how to find features inside a particular
305    contig region. For example, if the maximum length is 4000 and we're looking for a feature that
306    overlaps the region from 6000 to 7000 we know that the starting position must be between 2001
307    and 10999.
308    
309  =cut  =cut
310  #: Return Type @;  #: Return Type $;
311  sub GetEntityValues {  sub MaxSegment {
312          # Get the parameters.      my ($self) = @_;
313          my $self = shift @_;      return $self->{_options}->{maxSegmentLength};
         my ($entityType, $ID, $fields) = @_;  
         # Get the specified entity.  
         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 MaxSequence
   
 C<< $sprout->ShowMetaData($fileName); >>  
   
 This method outputs a description of the database to an HTML file in the data directory.  
   
 =over 4  
   
 =item fileName  
317    
318  Fully-qualified name to give to the output file.      my $length = $sprout->MaxSequence();
319    
320  =back  This method returns the maximum permissible length of a contig sequence. A contig is broken
321    into sequences in order to save memory resources. In particular, when manipulating features,
322    we generally only need a few sequences in memory rather than the entire contig.
323    
324  =cut  =cut
325    #: Return Type $;
326  sub ShowMetaData {  sub MaxSequence {
327          # Get the parameters.      my ($self) = @_;
328          my $self = shift @_;      return $self->{_options}->{maxSequenceLength};
         my ($fileName) = @_;  
         # Compute the file name.  
         my $options = $self->{_options};  
         # Call the show method on the underlying ERDB object.  
         $self->{_erdb}->ShowMetaData($fileName);  
329  }  }
330    
331  =head3 Load  =head3 Load
332    
333  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
334    
335  Load the database from files in the data directory, optionally re-creating the tables.  Load the database from files in the data directory, optionally re-creating the tables.
336    
# Line 383  Line 361 
361  #: Return Type %;  #: Return Type %;
362  sub Load {  sub Load {
363          # Get the parameters.          # Get the parameters.
364          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
365          # Load the tables from the data directory.          # Load the tables from the data directory.
366          my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
367          # Return the statistics.          # Return the statistics.
368          return $retVal;          return $retVal;
369  }  }
370    
371  =head3 LoadUpdate  =head3 LoadUpdate
372    
373  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
374    
375  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
376  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 424  Line 399 
399  =back  =back
400    
401  =cut  =cut
402  #: Return Type %;  #: Return Type $%;
403  sub LoadUpdate {  sub LoadUpdate {
404          # Get the parameters.          # Get the parameters.
405          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
406          # Declare the return value.          # Declare the return value.
407          my $retVal = Stats->new();          my $retVal = Stats->new();
408          # Get the data directory.          # Get the data directory.
# Line 439  Line 411 
411          # Loop through the incoming table names.          # Loop through the incoming table names.
412          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
413                  # Find the table's file.                  # Find the table's file.
414                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
415                  if (! -e $fileName) {          if (! $fileName) {
416                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
417                  }          } else {
418                  # Attempt to load this table.                  # Attempt to load this table.
419                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
420                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
421                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
422          }          }
423        }
424          # Return the statistics.          # Return the statistics.
425          return $retVal;          return $retVal;
426  }  }
427    
428    =head3 GenomeCounts
429    
430        my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
431    
432    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
433    genomes will be included in the counts.
434    
435    =over 4
436    
437    =item complete
438    
439    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
440    counted
441    
442    =item RETURN
443    
444    A six-element list containing the number of genomes in each of six categories--
445    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
446    
447    =back
448    
449    =cut
450    
451    sub GenomeCounts {
452        # Get the parameters.
453        my ($self, $complete) = @_;
454        # Set the filter based on the completeness flag.
455        my $filter = ($complete ? "Genome(complete) = 1" : "");
456        # Get all the genomes and the related taxonomy information.
457        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
458        # Clear the counters.
459        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
460        # Loop through, counting the domains.
461        for my $genome (@genomes) {
462            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
463            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
464            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
465            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
466            elsif ($genome->[1] =~ /^env/i)      { ++$env }
467            else  { ++$unk }
468        }
469        # Return the counts.
470        return ($arch, $bact, $euk, $vir, $env, $unk);
471    }
472    
473    =head3 ContigCount
474    
475        my $count = $sprout->ContigCount($genomeID);
476    
477    Return the number of contigs for the specified genome ID.
478    
479    =over 4
480    
481    =item genomeID
482    
483    ID of the genome whose contig count is desired.
484    
485    =item RETURN
486    
487    Returns the number of contigs for the specified genome.
488    
489    =back
490    
491    =cut
492    
493    sub ContigCount {
494        # Get the parameters.
495        my ($self, $genomeID) = @_;
496        # Get the contig count.
497        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
498        # Return the result.
499        return $retVal;
500    }
501    
502    =head3 GenomeMenu
503    
504        my $html = $sprout->GenomeMenu(%options);
505    
506    Generate a genome selection control with the specified name and options.
507    This control is almost but not quite the same as the genome control in the
508    B<SearchHelper> class. Eventually, the two will be combined.
509    
510    =over 4
511    
512    =item options
513    
514    Optional parameters for the control (see below).
515    
516    =item RETURN
517    
518    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
519    
520    =back
521    
522    The valid options are as follows.
523    
524    =over 4
525    
526    =item name
527    
528    Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
529    Terrible things will happen if you have two controls with the same name on the same page.
530    
531    =item filter
532    
533    If specified, a filter for the list of genomes to display. The filter should be in the form of a
534    list reference. The first element of the list should be the filter string, and the remaining elements
535    the filter parameters.
536    
537    =item multiSelect
538    
539    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
540    
541    =item size
542    
543    Number of rows to display in the control. The default is C<10>
544    
545    =item id
546    
547    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
548    unless this ID is unique.
549    
550    =item selected
551    
552    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
553    default is none.
554    
555    =item class
556    
557    If specified, a style class to assign to the genome control.
558    
559    =back
560    
561    =cut
562    
563    sub GenomeMenu {
564        # Get the parameters.
565        my ($self, %options) = @_;
566        # Get the control's name and ID.
567        my $menuName = $options{name} || $options{id} || 'myGenomeControl';
568        my $menuID = $options{id} || $menuName;
569        Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
570        # Compute the IDs for the status display.
571        my $divID = "${menuID}_status";
572        my $urlID = "${menuID}_url";
573        # Compute the code to show selected genomes in the status area.
574        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
575        # Check for single-select or multi-select.
576        my $multiSelect = $options{multiSelect} || 0;
577        # Get the style data.
578        my $class = $options{class} || '';
579        # Get the list of pre-selected items.
580        my $selections = $options{selected} || [];
581        if (ref $selections ne 'ARRAY') {
582            $selections = [ split /\s*,\s*/, $selections ];
583        }
584        my %selected = map { $_ => 1 } @{$selections};
585        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
586        # string or a list reference.
587        my $filterParms = $options{filter} || "";
588        if (! ref $filterParms) {
589            $filterParms = [split /\t|\\t/, $filterParms];
590        }
591        my $filterString = shift @{$filterParms};
592        # Get a list of all the genomes in group order. In fact, we only need them ordered
593        # by name (genus,species,strain), but putting primary-group in front enables us to
594        # take advantage of an existing index.
595        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
596                                       $filterParms,
597                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
598        # Create a hash to organize the genomes by group. Each group will contain a list of
599        # 2-tuples, the first element being the genome ID and the second being the genome
600        # name.
601        my %gHash = ();
602        for my $genome (@genomeList) {
603            # Get the genome data.
604            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
605            # Compute its name. This is the genus, species, strain (if any), and the contig count.
606            my $name = "$genus $species ";
607            $name .= "$strain " if $strain;
608            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
609            # Now we get the domain. The domain tells us the display style of the organism.
610            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
611            # Now compute the display group. This is normally the primary group, but if the
612            # organism is supporting, we blank it out.
613            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
614            # Push the genome into the group's list. Note that we use the real group
615            # name for the hash key here, not the display group name.
616            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
617        }
618        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
619        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
620        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
621        # that aren't "other". At some point, we will want to make this less complicated.
622        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
623                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
624        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
625        # Remember the number of NMPDR groups.
626        my $nmpdrGroupCount = scalar @groups;
627        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
628        # of the domains found.
629        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
630        my @domains = ();
631        for my $genomeData (@otherGenomes) {
632            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
633            if (exists $gHash{$domain}) {
634                push @{$gHash{$domain}}, $genomeData;
635            } else {
636                $gHash{$domain} = [$genomeData];
637                push @domains, $domain;
638            }
639        }
640        # Add the domain groups at the end of the main group list. The main group list will now
641        # contain all the categories we need to display the genomes.
642        push @groups, sort @domains;
643        # Delete the supporting group.
644        delete $gHash{$FIG_Config::otherGroup};
645        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
646        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
647        # and use that to make the selections.
648        my $nmpdrCount = 0;
649        # Create the type counters.
650        my $groupCount = 1;
651        # Get the number of rows to display.
652        my $rows = $options{size} || 10;
653        # If we're multi-row, create an onChange event.
654        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
655        # Set up the multiple-select flag.
656        my $multipleTag = ($multiSelect ? " multiple" : "" );
657        # Set up the style class.
658        my $classTag = ($class ? " class=\"$class\"" : "" );
659        # Create the SELECT tag and stuff it into the output array.
660        my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
661        # Loop through the groups.
662        for my $group (@groups) {
663            # Get the genomes in the group.
664            for my $genome (@{$gHash{$group}}) {
665                # If this is an NMPDR organism, we add an extra style and count it.
666                my $nmpdrStyle = "";
667                if ($nmpdrGroupCount > 0) {
668                    $nmpdrCount++;
669                    $nmpdrStyle = " Core";
670                }
671                # Get the organism ID, name, contig count, and domain.
672                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
673                # See if we're pre-selected.
674                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
675                # Compute the display name.
676                my $nameString = "$name ($genomeID$contigCount)";
677                # Generate the option tag.
678                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
679                push @lines, "    $optionTag";
680            }
681            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
682            # groups.
683            $nmpdrGroupCount--;
684        }
685        # Close the SELECT tag.
686        push @lines, "</SELECT>";
687        if ($rows > 1) {
688            # We're in a non-compact mode, so we need to add some selection helpers. First is
689            # the search box. This allows the user to type text and change which genomes are
690            # displayed. For multiple-select mode, we include a button that selects the displayed
691            # genes. For single-select mode, we use a plain label instead.
692            my $searchThingName = "${menuID}_SearchThing";
693            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
694                                                 : "Show genomes containing");
695            push @lines, "<br />$searchThingLabel&nbsp;" .
696                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .
697                         Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";
698            # For multi-select mode, we also have buttons to set and clear selections.
699            if ($multiSelect) {
700                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
701                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
702                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
703            }
704            # Add a hidden field we can use to generate organism page hyperlinks.
705            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";
706            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
707            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
708        }
709        # Assemble all the lines into a string.
710        my $retVal = join("\n", @lines, "");
711        # Return the result.
712        return $retVal;
713    }
714    
715    
716    =head3 Stem
717    
718        my $stem = $sprout->Stem($word);
719    
720    Return the stem of the specified word, or C<undef> if the word is not
721    stemmable. Note that even if the word is stemmable, the stem may be
722    the same as the original word.
723    
724    =over 4
725    
726    =item word
727    
728    Word to convert into a stem.
729    
730    =item RETURN
731    
732    Returns a stem of the word (which may be the word itself), or C<undef> if
733    the word is not stemmable.
734    
735    =back
736    
737    =cut
738    
739    sub Stem {
740        # Get the parameters.
741        my ($self, $word) = @_;
742        # Get the stemmer object.
743        my $stemmer = $self->{stemmer};
744        if (! defined $stemmer) {
745            # We don't have one pre-built, so we build and save it now.
746            $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
747                                     stops => "$FIG_Config::sproutData/StopWords.txt",
748                                     cache => 0);
749            $self->{stemmer} = $stemmer;
750        }
751        # Try to stem the word.
752        my $retVal = $stemmer->Process($word);
753        # Return the result.
754        return $retVal;
755    }
756    
757    
758  =head3 Build  =head3 Build
759    
760  C<< $sprout->Build(); >>      $sprout->Build();
761    
762  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
763  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 464  Line 767 
767  #: Return Type ;  #: Return Type ;
768  sub Build {  sub Build {
769          # Get the parameters.          # Get the parameters.
770          my $self = shift @_;      my ($self) = @_;
771          # Create the tables.          # Create the tables.
772          $self->{_erdb}->CreateTables;      $self->CreateTables();
773  }  }
774    
775  =head3 Genomes  =head3 Genomes
776    
777  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
778    
779  Return a list of all the genome IDs.  Return a list of all the genome IDs.
780    
# Line 479  Line 782 
782  #: Return Type @;  #: Return Type @;
783  sub Genomes {  sub Genomes {
784          # Get the parameters.          # Get the parameters.
785          my $self = shift @_;      my ($self) = @_;
786          # Get all the genomes.          # Get all the genomes.
787          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
788          # Return the list of IDs.          # Return the list of IDs.
# Line 488  Line 791 
791    
792  =head3 GenusSpecies  =head3 GenusSpecies
793    
794  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
795    
796  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
797    
# Line 509  Line 812 
812  #: Return Type $;  #: Return Type $;
813  sub GenusSpecies {  sub GenusSpecies {
814          # Get the parameters.          # Get the parameters.
815          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
816          # Get the data for the specified genome.          # Get the data for the specified genome.
817          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
818                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 521  Line 823 
823    
824  =head3 FeaturesOf  =head3 FeaturesOf
825    
826  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
827    
828  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
829    
# Line 546  Line 848 
848  #: Return Type @;  #: Return Type @;
849  sub FeaturesOf {  sub FeaturesOf {
850          # Get the parameters.          # Get the parameters.
851          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
852          # Get the features we want.          # Get the features we want.
853          my @features;          my @features;
854          if (!$ftype) {          if (!$ftype) {
# Line 567  Line 868 
868    
869  =head3 FeatureLocation  =head3 FeatureLocation
870    
871  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
872    
873  Return the location of a feature in its genome's contig segments. In a list context, this method  Return the location of a feature in its genome's contig segments. In a list context, this method
874  will return a list of the locations. In a scalar context, it will return the locations as a space-  will return a list of the locations. In a scalar context, it will return the locations as a space-
# Line 591  Line 892 
892  =item RETURN  =item RETURN
893    
894  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
895  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context. An empty list means the feature
896    wasn't found.
897    
898  =back  =back
899    
900  =cut  =cut
901  #: Return Type @;  
 #: Return Type $;  
902  sub FeatureLocation {  sub FeatureLocation {
903          # Get the parameters.          # Get the parameters.
904          my $self = shift @_;      my ($self, $featureID) = @_;
905          my ($featureID) = @_;      # Declare the return variable.
         # Create a query for the feature locations.  
         my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",  
                                                    [$featureID]);  
         # Create the return list.  
906          my @retVal = ();          my @retVal = ();
907          # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
908          # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
909          my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
910          # Loop through the query results, creating location specifiers.      if (defined $object) {
911          while (my $location = $query->Fetch()) {          # Get the location string.
912                  # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
913                  my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
914                          'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);          @retVal = split /\s*,\s*/, $locString;
                 # Check to see if we are adjacent to the previous segment.  
                 if ($prevContig eq $contigID && $dir eq $prevDir) {  
                         # Here the new segment is in the same direction on the same contig. Insure the  
                         # new segment's beginning is next to the old segment's end.  
                         if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||  
                                 ($dir eq "+" && $beg == $prevBeg + $prevLen)) {  
                                 # Here we need to merge two segments. Adjust the beginning and length values  
                                 # to include both segments.  
                                 $beg = $prevBeg;  
                                 $len += $prevLen;  
                                 # Pop the old segment off. The new one will replace it later.  
                                 pop @retVal;  
                         }  
                 }  
                 # Remember this specifier for the adjacent-segment test the next time through.  
                 ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);  
                 # Add the specifier to the list.  
                 push @retVal, "${contigID}_$beg$dir$len";  
915          }          }
916          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
917          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
918  }  }
919    
920  =head3 ParseLocation  =head3 ParseLocation
921    
922  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
923    
924  Split a location specifier into the contig ID, the starting point, the direction, and the  Split a location specifier into the contig ID, the starting point, the direction, and the
925  length.  length.
# Line 659  Line 938 
938  =back  =back
939    
940  =cut  =cut
941  #: Return Type @;  
942  sub ParseLocation {  sub ParseLocation {
943          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
944        # the first parameter.
945        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
946          my ($location) = @_;          my ($location) = @_;
947          # Parse it into segments.          # Parse it into segments.
948          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
949          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
950          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
951          if ($dir eq "_") {          if ($dir eq "_") {
# Line 680  Line 961 
961          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
962  }  }
963    
 =head3 DNASeq  
964    
 C<< my $sequence = $sprout->DNASeq(\@locationList); >>  
965    
966  This method returns the DNA sequence represented by a list of locations. The list of locations  =head3 PointLocation
967  should be of the form returned by L</featureLocation> when in a list context. In other words,  
968  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.      my $found = Sprout::PointLocation($location, $point);
969    
970    Return the offset into the specified location of the specified point on the contig. If
971    the specified point is before the location, a negative value will be returned. If it is
972    beyond the location, an undefined value will be returned. It is assumed that the offset
973    is for the location's contig. The location can either be new-style (using a C<+> or C<->
974    and a length) or old-style (using C<_> and start and end positions.
975    
976  =over 4  =over 4
977    
978  =item locationList  =item location
979    
980    A location specifier (see L</FeatureLocation> for a description).
981    
982    =item point
983    
984  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  The offset into the contig of the point in which we're interested.
 L</FeatureLocation> for more about this format).  
985    
986  =item RETURN  =item RETURN
987    
988  Returns a string of nucleotides corresponding to the DNA segments in the location list.  Returns the offset inside the specified location of the specified point, a negative
989    number if the point is before the location, or an undefined value if the point is past
990    the location. If the length of the location is 0, this method will B<always> denote
991    that it is outside the location. The offset will always be relative to the left-most
992    position in the location.
993    
994  =back  =back
995    
996  =cut  =cut
997  #: Return Type $;  
998  sub DNASeq {  sub PointLocation {
999          # Get the parameters.      # Get the parameter. Note that if we're called as an instance method, we ignore
1000          my $self = shift @_;      # the first parameter.
1001          my ($locationList) = @_;      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
1002          # Create the return string.      my ($location, $point) = @_;
1003          my $retVal = "";      # Parse out the location elements. Note that this works on both old-style and new-style
1004          # Loop through the locations.      # locations.
1005          for my $location (@{$locationList}) {      my ($contigID, $start, $dir, $len) = ParseLocation($location);
1006                  # Set up a variable to contain the DNA at this location.      # Declare the return variable.
1007                  my $locationDNA = "";      my $retVal;
1008                  # Parse out the contig ID, the beginning point, the direction, and the end point.      # Compute the offset. The computation is dependent on the direction of the location.
1009                  my ($contigID, $beg, $dir, $len) = ParseLocation($location);      my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
1010        # Return the offset if it's valid.
1011        if ($offset < $len) {
1012            $retVal = $offset;
1013        }
1014        # Return the offset found.
1015        return $retVal;
1016    }
1017    
1018    =head3 DNASeq
1019    
1020        my $sequence = $sprout->DNASeq(\@locationList);
1021    
1022    This method returns the DNA sequence represented by a list of locations. The list of locations
1023    should be of the form returned by L</featureLocation> when in a list context. In other words,
1024    each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
1025    
1026    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
1027    between positions 1401 and 1532, inclusive.
1028    
1029        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
1030    
1031    =over 4
1032    
1033    =item locationList
1034    
1035    List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
1036    I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
1037    
1038    =item RETURN
1039    
1040    Returns a string of nucleotides corresponding to the DNA segments in the location list.
1041    
1042    =back
1043    
1044    =cut
1045    #: Return Type $;
1046    sub DNASeq {
1047        # Get the parameters.
1048        my ($self, $locationList) = @_;
1049        # Create the return string.
1050        my $retVal = "";
1051        # Loop through the locations.
1052        for my $location (@{$locationList}) {
1053            # Set up a variable to contain the DNA at this location.
1054            my $locationDNA = "";
1055            # Parse out the contig ID, the beginning point, the direction, and the end point.
1056            my ($contigID, $beg, $dir, $len) = ParseLocation($location);
1057                  # Now we must create a query to return all the sequences in the contig relevant to the region                  # Now we must create a query to return all the sequences in the contig relevant to the region
1058                  # specified. First, we compute the start and stop points when reading through the sequences.                  # specified. First, we compute the start and stop points when reading through the sequences.
1059                  # For a forward transcription, the start point is the beginning; for a backward transcription,                  # For a forward transcription, the start point is the beginning; for a backward transcription,
1060                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
1061                  # before putting it in the return value.                  # before putting it in the return value.
1062                  my ($start, $stop);                  my ($start, $stop);
1063            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
1064                  if ($dir eq "+") {                  if ($dir eq "+") {
1065                          $start = $beg;                          $start = $beg;
1066                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
1067                  } else {                  } else {
1068                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
1069                          $stop = $beg;                          $stop = $beg;
1070                  }                  }
1071            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
1072                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
1073                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
1074                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 739  Line 1080 
1080                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
1081                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
1082                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
1083                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1084                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
1085                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1086                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1087                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1088                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
1089                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
1090                  }                  }
1091                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
1092                  if ($dir eq '+') {                  if ($dir eq '+') {
1093                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
1094                  } else {                  } else {
1095                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
1096                  }                  }
1097          }          }
1098          # Return the result.          # Return the result.
# Line 759  Line 1101 
1101    
1102  =head3 AllContigs  =head3 AllContigs
1103    
1104  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1105    
1106  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1107    
# Line 779  Line 1121 
1121  #: Return Type @;  #: Return Type @;
1122  sub AllContigs {  sub AllContigs {
1123          # Get the parameters.          # Get the parameters.
1124          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
1125          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
1126          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
1127                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 788  Line 1129 
1129          return @retVal;          return @retVal;
1130  }  }
1131    
1132    =head3 GenomeLength
1133    
1134        my $length = $sprout->GenomeLength($genomeID);
1135    
1136    Return the length of the specified genome in base pairs.
1137    
1138    =over 4
1139    
1140    =item genomeID
1141    
1142    ID of the genome whose base pair count is desired.
1143    
1144    =item RETURN
1145    
1146    Returns the number of base pairs in all the contigs of the specified
1147    genome.
1148    
1149    =back
1150    
1151    =cut
1152    
1153    sub GenomeLength {
1154        # Get the parameters.
1155        my ($self, $genomeID) = @_;
1156        # Declare the return variable.
1157        my $retVal = 0;
1158        # Get the genome's contig sequence lengths.
1159        my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
1160                           [$genomeID], 'IsMadeUpOf(len)');
1161        # Sum the lengths.
1162        map { $retVal += $_ } @lens;
1163        # Return the result.
1164        return $retVal;
1165    }
1166    
1167    =head3 FeatureCount
1168    
1169        my $count = $sprout->FeatureCount($genomeID, $type);
1170    
1171    Return the number of features of the specified type in the specified genome.
1172    
1173    =over 4
1174    
1175    =item genomeID
1176    
1177    ID of the genome whose feature count is desired.
1178    
1179    =item type
1180    
1181    Type of feature to count (eg. C<peg>, C<rna>, etc.).
1182    
1183    =item RETURN
1184    
1185    Returns the number of features of the specified type for the specified genome.
1186    
1187    =back
1188    
1189    =cut
1190    
1191    sub FeatureCount {
1192        # Get the parameters.
1193        my ($self, $genomeID, $type) = @_;
1194        # Compute the count.
1195        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1196                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1197                                    [$genomeID, $type]);
1198        # Return the result.
1199        return $retVal;
1200    }
1201    
1202    =head3 GenomeAssignments
1203    
1204        my $fidHash = $sprout->GenomeAssignments($genomeID);
1205    
1206    Return a list of a genome's assigned features. The return hash will contain each
1207    assigned feature of the genome mapped to the text of its most recent functional
1208    assignment.
1209    
1210    =over 4
1211    
1212    =item genomeID
1213    
1214    ID of the genome whose functional assignments are desired.
1215    
1216    =item RETURN
1217    
1218    Returns a reference to a hash which maps each feature to its most recent
1219    functional assignment.
1220    
1221    =back
1222    
1223    =cut
1224    
1225    sub GenomeAssignments {
1226        # Get the parameters.
1227        my ($self, $genomeID) = @_;
1228        # Declare the return variable.
1229        my $retVal = {};
1230        # Query the genome's features.
1231        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1232                               [$genomeID]);
1233        # Loop through the features.
1234        while (my $data = $query->Fetch) {
1235            # Get the feature ID and assignment.
1236            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1237            if ($assignment) {
1238                $retVal->{$fid} = $assignment;
1239            }
1240        }
1241        # Return the result.
1242        return $retVal;
1243    }
1244    
1245  =head3 ContigLength  =head3 ContigLength
1246    
1247  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1248    
1249  Compute the length of a contig.  Compute the length of a contig.
1250    
# Line 810  Line 1264 
1264  #: Return Type $;  #: Return Type $;
1265  sub ContigLength {  sub ContigLength {
1266          # Get the parameters.          # Get the parameters.
1267          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
1268          # Get the contig's last sequence.          # Get the contig's last sequence.
1269          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
1270                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 822  Line 1275 
1275          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
1276          if ($sequence) {          if ($sequence) {
1277                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1278                  $retVal = $start + $len;          $retVal = $start + $len - 1;
1279        }
1280        # Return the result.
1281        return $retVal;
1282    }
1283    
1284    =head3 ClusterPEGs
1285    
1286        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1287    
1288    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1289    subsystem. In order for this to work properly, the subsystem object must have
1290    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1291    B<get_row> methods. This causes the cluster numbers to be pulled into the
1292    subsystem's color hash. If a PEG is not found in the color hash, it will not
1293    appear in the output sequence.
1294    
1295    =over 4
1296    
1297    =item sub
1298    
1299    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1300    method.
1301    
1302    =item pegs
1303    
1304    Reference to the list of PEGs to be clustered.
1305    
1306    =item RETURN
1307    
1308    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1309    
1310    =back
1311    
1312    =cut
1313    #: Return Type $@@;
1314    sub ClusterPEGs {
1315        # Get the parameters.
1316        my ($self, $sub, $pegs) = @_;
1317        # Declare the return variable.
1318        my $retVal = [];
1319        # Loop through the PEGs, creating arrays for each cluster.
1320        for my $pegID (@{$pegs}) {
1321            my $clusterNumber = $sub->get_cluster_number($pegID);
1322            # Only proceed if the PEG is in a cluster.
1323            if ($clusterNumber >= 0) {
1324                # Push this PEG onto the sub-list for the specified cluster number.
1325                push @{$retVal->[$clusterNumber]}, $pegID;
1326            }
1327          }          }
1328          # Return the result.          # Return the result.
1329          return $retVal;          return $retVal;
# Line 830  Line 1331 
1331    
1332  =head3 GenesInRegion  =head3 GenesInRegion
1333    
1334  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1335    
1336  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1337    
# Line 853  Line 1354 
1354  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns a three-element list. The first element is a list of feature IDs for the features that
1355  overlap the region of interest. The second and third elements are the minimum and maximum  overlap the region of interest. The second and third elements are the minimum and maximum
1356  locations of the features provided on the specified contig. These may extend outside  locations of the features provided on the specified contig. These may extend outside
1357  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
1358    roughly by location.
1359    
1360  =back  =back
1361    
1362  =cut  =cut
1363  #: Return Type @;  
1364  sub GenesInRegion {  sub GenesInRegion {
1365          # Get the parameters.          # Get the parameters.
1366          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
1367          my ($contigID, $start, $stop) = @_;      # Get the maximum segment length.
1368        my $maximumSegmentLength = $self->MaxSegment;
1369        # Prime the values we'll use for the returned beginning and end.
1370        my @initialMinMax = ($self->ContigLength($contigID), 0);
1371        my ($min, $max) = @initialMinMax;
1372        # Get the overlapping features.
1373        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1374        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1375        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1376        # of the feature's locations.
1377        my %featureMap = ();
1378        # Loop through them to do the begin/end analysis.
1379        for my $featureObject (@featureObjects) {
1380            # Get the feature's location string. This may contain multiple actual locations.
1381            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1382            my @locationSegments = split /\s*,\s*/, $locations;
1383            # Loop through the locations.
1384            for my $locationSegment (@locationSegments) {
1385                # Construct an object for the location.
1386                my $locationObject = BasicLocation->new($locationSegment);
1387                # Merge the current segment's begin and end into the min and max.
1388                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1389                my ($beg, $end);
1390                if (exists $featureMap{$fid}) {
1391                    ($beg, $end) = @{$featureMap{$fid}};
1392                    $beg = $left if $left < $beg;
1393                    $end = $right if $right > $end;
1394                } else {
1395                    ($beg, $end) = ($left, $right);
1396                }
1397                $min = $beg if $beg < $min;
1398                $max = $end if $end > $max;
1399                # Store the feature's new extent back into the hash table.
1400                $featureMap{$fid} = [$beg, $end];
1401            }
1402        }
1403        # Now we must compute the list of the IDs for the features found. We start with a list
1404        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1405        # but the result of the sort will be the same.)
1406        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1407        # Now we sort by midpoint and yank out the feature IDs.
1408        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1409        # Return it along with the min and max.
1410        return (\@retVal, $min, $max);
1411    }
1412    
1413    =head3 GeneDataInRegion
1414    
1415        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1416    
1417    List the features which overlap a specified region in a contig.
1418    
1419    =over 4
1420    
1421    =item contigID
1422    
1423    ID of the contig containing the region of interest.
1424    
1425    =item start
1426    
1427    Offset of the first residue in the region of interest.
1428    
1429    =item stop
1430    
1431    Offset of the last residue in the region of interest.
1432    
1433    =item RETURN
1434    
1435    Returns a list of B<ERDBObjects> for the desired features. Each object will
1436    contain a B<Feature> record.
1437    
1438    =back
1439    
1440    =cut
1441    
1442    sub GeneDataInRegion {
1443        # Get the parameters.
1444        my ($self, $contigID, $start, $stop) = @_;
1445          # Get the maximum segment length.          # Get the maximum segment length.
1446          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
1447          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
1448          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1449        # ERDBObject from the query.
1450          my %featuresFound = ();          my %featuresFound = ();
1451          # Prime the values we'll use for the returned beginning and end.      # Create a table of parameters for the queries. Each query looks for features travelling in
         my ($min, $max) = ($self->ContigLength($contigID), 0);  
         # Create a table of parameters for each query. Each query looks for features travelling in  
1452          # a particular direction. The query parameters include the contig ID, the feature direction,          # a particular direction. The query parameters include the contig ID, the feature direction,
1453          # the lowest possible start position, and the highest possible start position. This works          # the lowest possible start position, and the highest possible start position. This works
1454          # because each feature segment length must be no greater than the maximum segment length.          # because each feature segment length must be no greater than the maximum segment length.
# Line 879  Line 1457 
1457          # Loop through the query parameters.          # Loop through the query parameters.
1458          for my $parms (values %queryParms) {          for my $parms (values %queryParms) {
1459                  # Create the query.                  # Create the query.
1460                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1461                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1462                          $parms);                          $parms);
1463                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1464                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1465                          # Get the data about this segment.                          # Get the data about this segment.
1466                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1467                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1468                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1469                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1470                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1471                          # length.                          # length.
1472                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1473                          if ($dir eq '+') {              my $found = $loc->Overlap($start, $stop);
                                 $end = $beg + $len;  
                                 if ($end >= $start) {  
                                         # Denote we found a useful feature.  
                                         $found = 1;  
                                 }  
                         } elsif ($dir eq '-') {  
                                 $end = $beg - $len;  
                                 if ($end <= $stop) {  
                                         # Denote we found a useful feature.  
                                         $found = 1;  
                                 }  
                         }  
1474                          if ($found) {                          if ($found) {
1475                                  # Here we need to record the feature and update the minimum and maximum.                  # Save this feature in the result list.
1476                                  $featuresFound{$featureID} = 1;                  $featuresFound{$featureID} = $segment;
                                 if ($beg < $min) { $min = $beg; }  
                                 if ($end < $min) { $min = $end; }  
                                 if ($beg > $max) { $max = $beg; }  
                                 if ($end > $max) { $max = $end; }  
1477                          }                          }
1478                  }                  }
1479          }          }
1480          # Compute a list of the IDs for the features found.      # Return the ERDB objects for the features found.
1481          my @list = (sort (keys %featuresFound));      return values %featuresFound;
         # Return it along with the min and max.  
         return (\@list, $min, $max);  
1482  }  }
1483    
1484  =head3 FType  =head3 FType
1485    
1486  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1487    
1488  Return the type of a feature.  Return the type of a feature.
1489    
# Line 944  Line 1504 
1504  #: Return Type $;  #: Return Type $;
1505  sub FType {  sub FType {
1506          # Get the parameters.          # Get the parameters.
1507          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1508          # Get the specified feature's type.          # Get the specified feature's type.
1509          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1510          # Return the result.          # Return the result.
# Line 954  Line 1513 
1513    
1514  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1515    
1516  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1517    
1518  Return the annotations of a feature.  Return the annotations of a feature.
1519    
# Line 964  Line 1523 
1523    
1524  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1525    
1526    =item rawFlag
1527    
1528    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1529    will be returned in human-readable form.
1530    
1531  =item RETURN  =item RETURN
1532    
1533  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1534    
1535  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1536    
1537  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1538    
1539  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1540    
# Line 982  Line 1546 
1546  #: Return Type @%;  #: Return Type @%;
1547  sub FeatureAnnotations {  sub FeatureAnnotations {
1548          # Get the parameters.          # Get the parameters.
1549          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1550          # 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.
1551          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1552                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 996  Line 1559 
1559                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1560                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1561                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1562            # Convert the time, if necessary.
1563            if (! $rawFlag) {
1564                $timeStamp = FriendlyTimestamp($timeStamp);
1565            }
1566                  # Assemble them into a hash.                  # Assemble them into a hash.
1567          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1568                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1569                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1570                  # Add it to the return list.                  # Add it to the return list.
1571                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1009  Line 1576 
1576    
1577  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1578    
1579  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1580    
1581  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
1582  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,
1583  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
1584  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,
1585  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.
1586  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
1587  functional assignments, we will only keep the most recent one.  recent one.
1588    
1589  =over 4  =over 4
1590    
# Line 1027  Line 1594 
1594    
1595  =item RETURN  =item RETURN
1596    
1597  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1598    
1599  =back  =back
1600    
# Line 1035  Line 1602 
1602  #: Return Type %;  #: Return Type %;
1603  sub AllFunctionsOf {  sub AllFunctionsOf {
1604          # Get the parameters.          # Get the parameters.
1605          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1606          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1607      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1608                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1609                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1610                                               'MadeAnnotation(from-link)']);
1611          # Declare the return hash.          # Declare the return hash.
1612          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1613      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1614      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1615          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1616      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1617          # Get the annotation fields.          # Get the annotation fields.
1618          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1619                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1620                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1621          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1622              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1623              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1624              # return hash.              # return hash.
1625                          $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1626                  }                  }
1627          }          }
1628          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1068  Line 1631 
1631    
1632  =head3 FunctionOf  =head3 FunctionOf
1633    
1634  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1635    
1636  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1637    
1638  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
1639  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 the functional
1640  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  
 we cannot filter on the content of the annotation itself because it's a text field; however, this  
 is not a big problem because most features only have a small number of annotations.  
1641    
1642  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
1643  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
1644  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1645  is trusted.  is trusted.
1646    
1647  If the feature is B<not> identified by a FIG ID, then the functional assignment  If the feature is B<not> identified by a FIG ID, then we search the aliases for it.
1648  information is taken from the B<ExternalAliasFunc> table. If the table does  If no matching alias is found, we return an undefined value.
 not contain an entry for the feature, an undefined value is returned.  
1649    
1650  =over 4  =over 4
1651    
# Line 1096  Line 1655 
1655    
1656  =item userID (optional)  =item userID (optional)
1657    
1658  ID of the user whose function determination is desired. If omitted, only the latest  ID of the user whose function determination is desired. If omitted, the primary
1659  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1660    
1661  =item RETURN  =item RETURN
1662    
# Line 1109  Line 1668 
1668  #: Return Type $;  #: Return Type $;
1669  sub FunctionOf {  sub FunctionOf {
1670          # Get the parameters.          # Get the parameters.
1671          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1672      # Declare the return value.      # Declare the return value.
1673      my $retVal;      my $retVal;
1674      # Determine the ID type.      # Find a FIG ID for this feature.
1675      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1676          # Here we have a FIG feature ID. We must build the list of trusted      # Only proceed if we have an ID.
1677          # users.      if ($fid) {
1678            # Here we have a FIG feature ID.
1679            if (!$userID) {
1680                # Use the primary assignment.
1681                ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1682            } else {
1683                # We must build the list of trusted users.
1684          my %trusteeTable = ();          my %trusteeTable = ();
1685          # Check the user ID.          # Check the user ID.
1686          if (!$userID) {          if (!$userID) {
# Line 1138  Line 1702 
1702              }              }
1703          }          }
1704          # Build a query for all of the feature's annotations, sorted by date.          # Build a query for all of the feature's annotations, sorted by date.
1705          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1706                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1707                                 [$featureID]);                                     [$fid]);
1708          my $timeSelected = 0;          my $timeSelected = 0;
1709          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1710          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1711              # Get the annotation text.              # Get the annotation text.
1712              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1713                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1714              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1715              my ($user, $type, $function) = split(/\n/, $text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1716              if ($type =~ m/^set $user function to$/i) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1717                    if ($actualUser) {
1718                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1719                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1720                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1721                      $retVal = $function;                      $retVal = $function;
1722                      $timeSelected = $time;                      $timeSelected = $time;
1723                  }                  }
1724              }              }
1725          }          }
1726      } else {          }
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1727      }      }
1728          # Return the assignment found.          # Return the assignment found.
1729          return $retVal;          return $retVal;
1730  }  }
1731    
1732    =head3 FunctionsOf
1733    
1734        my @functionList = $sprout->FunctionOf($featureID, $userID);
1735    
1736    Return the functional assignments of a particular feature.
1737    
1738    The functional assignment is handled differently depending on the type of feature. If
1739    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1740    assignment is a type of annotation. The format of an assignment is described in
1741    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1742    annotation itself because it's a text field; however, this is not a big problem because
1743    most features only have a small number of annotations.
1744    
1745    =over 4
1746    
1747    =item featureID
1748    
1749    ID of the feature whose functional assignments are desired.
1750    
1751    =item RETURN
1752    
1753    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1754    that user.
1755    
1756    =back
1757    
1758    =cut
1759    #: Return Type @@;
1760    sub FunctionsOf {
1761        # Get the parameters.
1762        my ($self, $featureID) = @_;
1763        # Declare the return value.
1764        my @retVal = ();
1765        # Convert to a FIG ID.
1766        my ($fid) = $self->FeaturesByAlias($featureID);
1767        # Only proceed if we found one.
1768        if ($fid) {
1769            # Here we have a FIG feature ID. We must build the list of trusted
1770            # users.
1771            my %trusteeTable = ();
1772            # Build a query for all of the feature's annotations, sorted by date.
1773            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1774                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1775                                   [$fid]);
1776            my $timeSelected = 0;
1777            # Loop until we run out of annotations.
1778            while (my $annotation = $query->Fetch()) {
1779                # Get the annotation text.
1780                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1781                                                                'Annotation(time)',
1782                                                                'MadeAnnotation(user)']);
1783                # Check to see if this is a functional assignment for a trusted user.
1784                my ($actualUser, $function) = _ParseAssignment($user, $text);
1785                if ($actualUser) {
1786                    # Here it is a functional assignment.
1787                    push @retVal, [$actualUser, $function];
1788                }
1789            }
1790        }
1791        # Return the assignments found.
1792        return @retVal;
1793    }
1794    
1795  =head3 BBHList  =head3 BBHList
1796    
1797  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1798    
1799  Return a hash mapping the features in a specified list to their bidirectional best hits  Return a hash mapping the features in a specified list to their bidirectional best hits
1800  on a specified target genome.  on a specified target genome.
# Line 1186  Line 1811 
1811    
1812  =item RETURN  =item RETURN
1813    
1814  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
1815  their best hits.  on the target genome.
1816    
1817  =back  =back
1818    
# Line 1195  Line 1820 
1820  #: Return Type %;  #: Return Type %;
1821  sub BBHList {  sub BBHList {
1822          # Get the parameters.          # Get the parameters.
1823          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1824          # Create the return structure.          # Create the return structure.
1825          my %retVal = ();          my %retVal = ();
1826          # Loop through the incoming features.          # Loop through the incoming features.
1827          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1828                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1829                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1830                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1831                                                             [$featureID, $genomeID]);          my @found = ();
1832                  # Look for the best hit.          for my $bbh (@bbhData) {
1833                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1834                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1835                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1836                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1837                }
1838                  }                  }
1839            $retVal{$featureID} = \@found;
1840          }          }
1841          # Return the mapping.          # Return the mapping.
1842          return \%retVal;          return \%retVal;
1843  }  }
1844    
1845  =head3 FeatureAliases  =head3 SimList
1846    
1847  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my %similarities = $sprout->SimList($featureID, $count);
1848    
1849  Return a list of the aliases for a specified feature.  Return a list of the similarities to the specified feature.
1850    
1851    This method just returns the bidirectional best hits for performance reasons.
1852    
1853  =over 4  =over 4
1854    
1855  =item featureID  =item featureID
1856    
1857  ID of the feature whose aliases are desired.  ID of the feature whose similarities are desired.
1858    
1859  =item RETURN  =item count
1860    
1861  Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will  Maximum number of similar features to be returned, or C<0> to return them all.
 return an empty list.  
1862    
1863  =back  =back
1864    
1865  =cut  =cut
1866  #: Return Type @;  #: Return Type %;
1867  sub FeatureAliases {  sub SimList {
1868          # Get the parameters.          # Get the parameters.
1869          my $self = shift @_;      my ($self, $featureID, $count) = @_;
1870          my ($featureID) = @_;      # Ask for the best hits.
1871          # Get the desired feature's aliases      my @lists = FIGRules::BBHData($featureID);
1872          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      # Create the return value.
1873        my %retVal = ();
1874        for my $tuple (@lists) {
1875            $retVal{$tuple->[0]} = $tuple->[1];
1876        }
1877          # Return the result.          # Return the result.
1878          return @retVal;      return %retVal;
1879  }  }
1880    
1881  =head3 GenomeOf  =head3 IsComplete
1882    
1883  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $flag = $sprout->IsComplete($genomeID);
1884    
1885  Return the genome that contains a specified feature.  Return TRUE if the specified genome is complete, else FALSE.
1886    
1887  =over 4  =over 4
1888    
1889  =item featureID  =item genomeID
1890    
1891  ID of the feature whose genome is desired.  ID of the genome whose completeness status is desired.
1892    
1893  =item RETURN  =item RETURN
1894    
1895  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1896  an undefined value.  not found.
1897    
1898  =back  =back
1899    
1900  =cut  =cut
1901  #: Return Type $;  #: Return Type $;
1902  sub GenomeOf {  sub IsComplete {
1903          # Get the parameters.          # Get the parameters.
1904          my $self = shift @_;      my ($self, $genomeID) = @_;
1905          my ($featureID) = @_;      # Declare the return variable.
         # Create a query to find the genome associated with the feature.  
         my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);  
         # Declare the return value.  
1906          my $retVal;          my $retVal;
1907          # Get the genome ID.      # Get the genome's data.
1908          if (my $relationship = $query->Fetch()) {      my $genomeData = $self->GetEntity('Genome', $genomeID);
1909                  ($retVal) = $relationship->Value('HasContig(from-link)');      if ($genomeData) {
1910            # The genome exists, so get the completeness flag.
1911            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1912          }          }
1913          # Return the value found.      # Return the result.
1914          return $retVal;          return $retVal;
1915  }  }
1916    
1917  =head3 CoupledFeatures  =head3 FeatureAliases
1918    
1919  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1920    
1921  Return the features functionally coupled with a specified feature. Features are considered  Return a list of the aliases for a specified feature.
1922  functionally coupled if they tend to be clustered on the same chromosome.  
1923    =over 4
1924    
1925    =item featureID
1926    
1927    ID of the feature whose aliases are desired.
1928    
1929    =item RETURN
1930    
1931    Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will
1932    return an empty list.
1933    
1934    =back
1935    
1936    =cut
1937    #: Return Type @;
1938    sub FeatureAliases {
1939        # Get the parameters.
1940        my ($self, $featureID) = @_;
1941        # Get the desired feature's aliases
1942        my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1943        # Return the result.
1944        return @retVal;
1945    }
1946    
1947    =head3 GenomeOf
1948    
1949        my $genomeID = $sprout->GenomeOf($featureID);
1950    
1951    Return the genome that contains a specified feature or contig.
1952    
1953    =over 4
1954    
1955    =item featureID
1956    
1957    ID of the feature or contig whose genome is desired.
1958    
1959    =item RETURN
1960    
1961    Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1962    found, returns an undefined value.
1963    
1964    =back
1965    
1966    =cut
1967    #: Return Type $;
1968    sub GenomeOf {
1969        # Get the parameters.
1970        my ($self, $featureID) = @_;
1971        # Declare the return value.
1972        my $retVal;
1973        # Parse the genome ID from the feature ID.
1974        if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1975            $retVal = $1;
1976        } else {
1977            # Find the feature by alias.
1978            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
1979            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
1980                $retVal = $1;
1981            }
1982        }
1983        # Return the value found.
1984        return $retVal;
1985    }
1986    
1987    =head3 CoupledFeatures
1988    
1989        my %coupleHash = $sprout->CoupledFeatures($featureID);
1990    
1991    Return the features functionally coupled with a specified feature. Features are considered
1992    functionally coupled if they tend to be clustered on the same chromosome.
1993    
1994  =over 4  =over 4
1995    
# Line 1307  Line 2007 
2007  #: Return Type %;  #: Return Type %;
2008  sub CoupledFeatures {  sub CoupledFeatures {
2009          # Get the parameters.          # Get the parameters.
2010          my $self = shift @_;      my ($self, $featureID) = @_;
2011          my ($featureID) = @_;      # Ask the coupling server for the data.
2012          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2013          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2014          # (B,A) will also be found.      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2015          my $query = $self->Get(['IsClusteredOnChromosomeWith'],      # Form them into a hash.
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
         # This value will be set to TRUE if we find at least one coupled feature.  
         my $found = 0;  
         # Create the return hash.  
2016          my %retVal = ();          my %retVal = ();
2017          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2018          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2019                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
2020                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
2021                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
2022                  $found = 1;              $retVal{$featureID2} = $score;
2023            }
2024          }          }
2025          # Functional coupling is reflexive. If we found at least one coupled feature, we must add          # Functional coupling is reflexive. If we found at least one coupled feature, we must add
2026          # the incoming feature as well.          # the incoming feature as well.
2027          if ($found) {      if (keys %retVal) {
2028                  $retVal{$featureID} = 9999;                  $retVal{$featureID} = 9999;
2029      }      }
2030          # Return the hash.          # Return the hash.
2031          return %retVal;          return %retVal;
2032  }  }
2033    
2034  =head3 GetEntityTypes  =head3 CouplingEvidence
2035    
2036        my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2037    
2038    Return the evidence for a functional coupling.
2039    
2040    A pair of features is considered evidence of a coupling between two other
2041    features if they occur close together on a contig and both are similar to
2042    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
2043    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
2044    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
2045    similar to B<A2>.
2046    
2047    The score of a coupling is determined by the number of pieces of evidence
2048    that are considered I<representative>. If several evidence items belong to
2049    a group of genomes that are close to each other, only one of those items
2050    is considered representative. The other evidence items are presumed to be
2051    there because of the relationship between the genomes rather than because
2052    the two proteins generated by the features have a related functionality.
2053    
2054    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
2055    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
2056    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
2057    and FALSE otherwise.
2058    
2059    =over 4
2060    
2061    =item peg1
2062    
2063    ID of the feature of interest.
2064    
2065    =item peg2
2066    
2067    ID of a feature functionally coupled to the feature of interest.
2068    
2069    =item RETURN
2070    
2071    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
2072    of interest, a feature similar to the functionally coupled feature, and a flag
2073    that is TRUE for a representative piece of evidence and FALSE otherwise.
2074    
2075    =back
2076    
2077    =cut
2078    #: Return Type @@;
2079    sub CouplingEvidence {
2080        # Get the parameters.
2081        my ($self, $peg1, $peg2) = @_;
2082        # Declare the return variable.
2083        my @retVal = ();
2084        # Get the coupling and evidence data.
2085        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2086        # Loop through the raw data, saving the ones that are in NMPDR genomes.
2087        for my $rawTuple (@rawData) {
2088            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2089                push @retVal, $rawTuple;
2090            }
2091        }
2092        # Return the result.
2093        return @retVal;
2094    }
2095    
2096    =head3 GetSynonymGroup
2097    
2098        my $id = $sprout->GetSynonymGroup($fid);
2099    
2100    Return the synonym group name for the specified feature.
2101    
2102    =over 4
2103    
2104    =item fid
2105    
2106    ID of the feature whose synonym group is desired.
2107    
2108    =item RETURN
2109    
2110    The name of the synonym group to which the feature belongs. If the feature does
2111    not belong to a synonym group, the feature ID itself is returned.
2112    
2113    =back
2114    
2115    =cut
2116    
2117    sub GetSynonymGroup {
2118        # Get the parameters.
2119        my ($self, $fid) = @_;
2120        # Declare the return variable.
2121        my $retVal;
2122        # Find the synonym group.
2123        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2124                                       [$fid], 'IsSynonymGroupFor(from-link)');
2125        # Check to see if we found anything.
2126        if (@groups) {
2127            $retVal = $groups[0];
2128        } else {
2129            $retVal = $fid;
2130        }
2131        # Return the result.
2132        return $retVal;
2133    }
2134    
2135    =head3 GetBoundaries
2136    
2137        my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2138    
2139    Determine the begin and end boundaries for the locations in a list. All of the
2140    locations must belong to the same contig and have mostly the same direction in
2141    order for this method to produce a meaningful result. The resulting
2142    begin/end pair will contain all of the bases in any of the locations.
2143    
2144  C<< my @entityList = $sprout->GetEntityTypes(); >>  =over 4
2145    
2146    =item locList
2147    
2148    List of locations to process.
2149    
2150    =item RETURN
2151    
2152    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2153    and the ending boundary. The beginning boundary will be left of the
2154    end for mostly-forward locations and right of the end for mostly-backward
2155    locations.
2156    
2157  Return the list of supported entity types.  =back
2158    
2159  =cut  =cut
2160  #: Return Type @;  
2161  sub GetEntityTypes {  sub GetBoundaries {
2162          # Get the parameters.          # Get the parameters.
2163          my $self = shift @_;      my ($self, @locList) = @_;
2164          # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
2165          my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
2166          # Get its entity type list.      # Get the last location and parse it.
2167          my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
2168        # Prime the loop with its data.
2169        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2170        # Count its direction.
2171        $counts{$locObject->Dir}++;
2172        # Loop through the remaining locations. Note that in most situations, this loop
2173        # will not iterate at all, because most of the time we will be dealing with a
2174        # singleton list.
2175        for my $loc (@locList) {
2176            # Create a location object.
2177            my $locObject = BasicLocation->new($loc);
2178            # Count the direction.
2179            $counts{$locObject->Dir}++;
2180            # Get the left end and the right end.
2181            my $left = $locObject->Left;
2182            my $right = $locObject->Right;
2183            # Merge them into the return variables.
2184            if ($left < $beg) {
2185                $beg = $left;
2186            }
2187            if ($right > $end) {
2188                $end = $right;
2189            }
2190        }
2191        # If the most common direction is reverse, flip the begin and end markers.
2192        if ($counts{'-'} > $counts{'+'}) {
2193            ($beg, $end) = ($end, $beg);
2194        }
2195        # Return the result.
2196        return ($contig, $beg, $end);
2197  }  }
2198    
2199  =head3 ReadFasta  =head3 ReadFasta
2200    
2201  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2202    
2203  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2204  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1395  Line 2240 
2240                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2241                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2242                          if ($id) {                          if ($id) {
2243                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
2244                          }                          }
2245                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2246                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2247                  } else {                  } else {
2248                          # 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.
2249                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
2250                # case.
2251                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2252                          $sequence .= $1;                          $sequence .= $1;
2253                  }                  }
2254          }          }
2255          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2256          if ($sequence) {          if ($sequence) {
2257                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
2258          }          }
2259        # Close the file.
2260        close FASTAFILE;
2261          # Return the hash constructed from the file.          # Return the hash constructed from the file.
2262          return %retVal;          return %retVal;
2263  }  }
2264    
2265  =head3 FormatLocations  =head3 FormatLocations
2266    
2267  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2268    
2269  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
2270  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
2271  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,
2272    it will not be changed; otherwise, it will be converted. This method can also be used to
2273    perform the reverse task-- insuring that all the locations are in the old format.
2274    
2275  =over 4  =over 4
2276    
# Line 1447  Line 2297 
2297  #: Return Type @;  #: Return Type @;
2298  sub FormatLocations {  sub FormatLocations {
2299          # Get the parameters.          # Get the parameters.
2300          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
2301          # Create the return list.          # Create the return list.
2302          my @retVal = ();          my @retVal = ();
2303          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
2304          if ($locations eq '') {          if ($locations eq '') {
2305              confess "No locations specified.";          Confess("No locations specified.");
2306          } else {          } else {
2307                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
2308                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1480  Line 2329 
2329    
2330  =head3 DumpData  =head3 DumpData
2331    
2332  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2333    
2334  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.
2335    
# Line 1488  Line 2337 
2337    
2338  sub DumpData {  sub DumpData {
2339          # Get the parameters.          # Get the parameters.
2340          my $self = shift @_;      my ($self) = @_;
2341          # Get the data directory name.          # Get the data directory name.
2342          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2343          # Dump the relations.          # Dump the relations.
2344          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2345  }  }
2346    
2347  =head3 XMLFileName  =head3 XMLFileName
2348    
2349  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2350    
2351  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2352    
2353  =cut  =cut
2354  #: Return Type $;  #: Return Type $;
2355  sub XMLFileName {  sub XMLFileName {
2356          my $self = shift @_;      my ($self) = @_;
2357          return $self->{_xmlName};          return $self->{_xmlName};
2358  }  }
2359    
2360    =head3 GetGenomeNameData
2361    
2362        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2363    
2364    Return the genus, species, and unique characterization for a genome. This
2365    is similar to L</GenusSpecies>, with the exception that it returns the
2366    values in three seperate fields.
2367    
2368    =over 4
2369    
2370    =item genomeID
2371    
2372    ID of the genome whose name data is desired.
2373    
2374    =item RETURN
2375    
2376    Returns a three-element list, consisting of the genus, species, and strain
2377    of the specified genome. If the genome is not found, an error occurs.
2378    
2379    =back
2380    
2381    =cut
2382    
2383    sub GetGenomeNameData {
2384        # Get the parameters.
2385        my ($self, $genomeID) = @_;
2386        # Get the desired values.
2387        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2388                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2389        # Throw an error if they were not found.
2390        if (! defined $genus) {
2391            Confess("Genome $genomeID not found in database.");
2392        }
2393        # Return the results.
2394        return ($genus, $species, $strain);
2395    }
2396    
2397    =head3 GetGenomeByNameData
2398    
2399        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2400    
2401    Return a list of the IDs of the genomes with the specified genus,
2402    species, and strain. In almost every case, there will be either zero or
2403    one IDs returned; however, two or more IDs could be returned if there are
2404    multiple versions of the genome in the database.
2405    
2406    =over 4
2407    
2408    =item genus
2409    
2410    Genus of the desired genome.
2411    
2412    =item species
2413    
2414    Species of the desired genome.
2415    
2416    =item strain
2417    
2418    Strain (unique characterization) of the desired genome. This may be an empty
2419    string, in which case it is presumed that the desired genome has no strain
2420    specified.
2421    
2422    =item RETURN
2423    
2424    Returns a list of the IDs of the genomes having the specified genus, species, and
2425    strain.
2426    
2427    =back
2428    
2429    =cut
2430    
2431    sub GetGenomeByNameData {
2432        # Get the parameters.
2433        my ($self, $genus, $species, $strain) = @_;
2434        # Try to find the genomes.
2435        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2436                                    [$genus, $species, $strain], 'Genome(id)');
2437        # Return the result.
2438        return @retVal;
2439    }
2440    
2441  =head3 Insert  =head3 Insert
2442    
2443  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2444    
2445  Insert an entity or relationship instance into the database. The entity or relationship of interest  Insert an entity or relationship instance into the database. The entity or relationship of interest
2446  is defined by a type name and then a hash of field names to values. Field values in the primary  is defined by a type name and then a hash of field names to values. Field values in the primary
# Line 1519  Line 2449 
2449  list references. For example, the following line inserts an inactive PEG feature named  list references. For example, the following line inserts an inactive PEG feature named
2450  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
2451    
2452  C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>      $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2453    
2454  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
2455  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>.
2456    
2457  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2458    
2459  =over 4  =over 4
2460    
# Line 1542  Line 2472 
2472  #: Return Type ;  #: Return Type ;
2473  sub Insert {  sub Insert {
2474          # Get the parameters.          # Get the parameters.
2475          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
2476          # Call the underlying method.          # Call the underlying method.
2477          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2478  }  }
2479    
2480  =head3 Annotate  =head3 Annotate
2481    
2482  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2483    
2484  Annotate a feature. This inserts an Annotation record into the database and links it to the  Annotate a feature. This inserts an Annotation record into the database and links it to the
2485  specified feature and user.  specified feature and user.
# Line 1584  Line 2513 
2513  #: Return Type $;  #: Return Type $;
2514  sub Annotate {  sub Annotate {
2515          # Get the parameters.          # Get the parameters.
2516          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
2517          # Create the annotation ID.          # Create the annotation ID.
2518          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
2519          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1605  Line 2533 
2533    
2534  =head3 AssignFunction  =head3 AssignFunction
2535    
2536  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2537    
2538  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
2539  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.  
2540    
2541  =over 4  =over 4
2542    
# Line 1619  Line 2546 
2546    
2547  =item user  =item user
2548    
2549  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>.
2550    
2551  =item function  =item function
2552    
2553  Text of the function being assigned.  Text of the function being assigned.
2554    
2555    =item assigningUser (optional)
2556    
2557    Name of the individual user making the assignment. If omitted, defaults to the user group.
2558    
2559  =item RETURN  =item RETURN
2560    
2561  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1635  Line 2566 
2566  #: Return Type $;  #: Return Type $;
2567  sub AssignFunction {  sub AssignFunction {
2568          # Get the parameters.          # Get the parameters.
2569          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2570          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2571        if (! $assigningUser) {
2572            $assigningUser = $user;
2573        }
2574          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2575          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2576          # Get the current time.          # Get the current time.
2577          my $now = time;          my $now = time;
2578          # Declare the return variable.          # Declare the return variable.
# Line 1659  Line 2593 
2593    
2594  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2595    
2596  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2597    
2598  Returns a list of features with the specified alias. The alias is parsed to determine  Returns a list of features with the specified alias. The alias is parsed to determine
2599  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6
# Line 1683  Line 2617 
2617  #: Return Type @;  #: Return Type @;
2618  sub FeaturesByAlias {  sub FeaturesByAlias {
2619          # Get the parameters.          # Get the parameters.
2620          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2621          # Declare the return variable.          # Declare the return variable.
2622          my @retVal = ();          my @retVal = ();
2623          # Parse the alias.          # Parse the alias.
# Line 1694  Line 2627 
2627                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2628          } else {          } else {
2629                  # Here we have a non-FIG alias. Get the features with the normalized alias.                  # Here we have a non-FIG alias. Get the features with the normalized alias.
2630                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2631          }          }
2632          # Return the result.          # Return the result.
2633          return @retVal;          return @retVal;
2634  }  }
2635    
 =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 $self = shift @_;  
         my ($entityName, $entityID) = @_;  
         # Check for the entity instance.  
         my $testInstance = $self->GetEntity($entityName, $entityID);  
         # Return an existence indicator.  
         my $retVal = ($testInstance ? 1 : 0);  
         return $retVal;  
 }  
   
2636  =head3 FeatureTranslation  =head3 FeatureTranslation
2637    
2638  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2639    
2640  Return the translation of a feature.  Return the translation of a feature.
2641    
# Line 1757  Line 2655 
2655  #: Return Type $;  #: Return Type $;
2656  sub FeatureTranslation {  sub FeatureTranslation {
2657          # Get the parameters.          # Get the parameters.
2658          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2659          # Get the specified feature's translation.          # Get the specified feature's translation.
2660          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2661          return $retVal;          return $retVal;
# Line 1766  Line 2663 
2663    
2664  =head3 Taxonomy  =head3 Taxonomy
2665    
2666  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2667    
2668  Return the taxonomy of the specified genome. This will be in the form of a list  Return the taxonomy of the specified genome. This will be in the form of a list
2669  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,
2670  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2671    
2672  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2673    
2674  =over 4  =over 4
2675    
# Line 1790  Line 2687 
2687  #: Return Type @;  #: Return Type @;
2688  sub Taxonomy {  sub Taxonomy {
2689          # Get the parameters.          # Get the parameters.
2690          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2691          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2692          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2693          # Declare the return variable.          # Declare the return variable.
# Line 1808  Line 2704 
2704    
2705  =head3 CrudeDistance  =head3 CrudeDistance
2706    
2707  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2708    
2709  Returns a crude estimate of the distance between two genomes. The distance is construed so  Returns a crude estimate of the distance between two genomes. The distance is construed so
2710  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
# Line 1834  Line 2730 
2730  #: Return Type $;  #: Return Type $;
2731  sub CrudeDistance {  sub CrudeDistance {
2732          # Get the parameters.          # Get the parameters.
2733          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2734          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2735          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2736          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1861  Line 2756 
2756    
2757  =head3 RoleName  =head3 RoleName
2758    
2759  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2760    
2761  Return the descriptive name of the role with the specified ID. In general, a role  Return the descriptive name of the role with the specified ID. In general, a role
2762  will only have a descriptive name if it is coded as an EC number.  will only have a descriptive name if it is coded as an EC number.
# Line 1882  Line 2777 
2777  #: Return Type $;  #: Return Type $;
2778  sub RoleName {  sub RoleName {
2779          # Get the parameters.          # Get the parameters.
2780          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2781          # Get the specified role's name.          # Get the specified role's name.
2782          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2783          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1896  Line 2790 
2790    
2791  =head3 RoleDiagrams  =head3 RoleDiagrams
2792    
2793  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2794    
2795  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2796    
# Line 1916  Line 2810 
2810  #: Return Type @;  #: Return Type @;
2811  sub RoleDiagrams {  sub RoleDiagrams {
2812          # Get the parameters.          # Get the parameters.
2813          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2814          # Query for the diagrams.          # Query for the diagrams.
2815          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2816                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1927  Line 2820 
2820    
2821  =head3 FeatureProperties  =head3 FeatureProperties
2822    
2823  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2824    
2825  Return a list of the properties for the specified feature. Properties are key-value pairs  Return a list of the properties for the specified feature. Properties are key-value pairs
2826  that specify special characteristics of the feature. For example, a property could indicate  that specify special characteristics of the feature. For example, a property could indicate
2827  that a feature is essential to the survival of the organism or that it has benign influence  that a feature is essential to the survival of the organism or that it has benign influence
2828  on the activities of a pathogen. Each property is returned as a triple of the form  on the activities of a pathogen. Each property is returned as a triple of the form
2829  C<($key,$value,$url)>, where C<$key> is the property name, C<$value> is its value (commonly  C<($key,@values)>, where C<$key> is the property name and  C<@values> are its values.
 a 1 or a 0, but possibly a string or a floating-point value), and C<$url> is a string describing  
 the web address or citation in which the property's value for the feature was identified.  
2830    
2831  =over 4  =over 4
2832    
# Line 1945  Line 2836 
2836    
2837  =item RETURN  =item RETURN
2838    
2839  Returns a list of triples, each triple containing the property name, its value, and a URL or  Returns a list of tuples, each tuple containing the property name and its values.
 citation.  
2840    
2841  =back  =back
2842    
# Line 1954  Line 2844 
2844  #: Return Type @@;  #: Return Type @@;
2845  sub FeatureProperties {  sub FeatureProperties {
2846          # Get the parameters.          # Get the parameters.
2847          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2848          # Get the properties.          # Get the properties.
2849          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->ca->GetAttributes($featureID);
2850                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2851                                                           'HasProperty(evidence)']);      my @retVal = ();
2852        for my $attributeRow (@attributes) {
2853            shift @{$attributeRow};
2854            push @retVal, $attributeRow;
2855        }
2856          # Return the resulting list.          # Return the resulting list.
2857          return @retVal;          return @retVal;
2858  }  }
2859    
2860  =head3 DiagramName  =head3 DiagramName
2861    
2862  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2863    
2864  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2865    
# Line 1986  Line 2879 
2879  #: Return Type $;  #: Return Type $;
2880  sub DiagramName {  sub DiagramName {
2881          # Get the parameters.          # Get the parameters.
2882          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2883          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2884          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2885          return $retVal;          return $retVal;
2886  }  }
2887    
2888    =head3 PropertyID
2889    
2890        my $id = $sprout->PropertyID($propName, $propValue);
2891    
2892    Return the ID of the specified property name and value pair, if the
2893    pair exists. Only a small subset of the FIG attributes are stored as
2894    Sprout properties, mostly for use in search optimization.
2895    
2896    =over 4
2897    
2898    =item propName
2899    
2900    Name of the desired property.
2901    
2902    =item propValue
2903    
2904    Value expected for the desired property.
2905    
2906    =item RETURN
2907    
2908    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2909    
2910    =back
2911    
2912    =cut
2913    
2914    sub PropertyID {
2915        # Get the parameters.
2916        my ($self, $propName, $propValue) = @_;
2917        # Try to find the ID.
2918        my ($retVal) = $self->GetFlat(['Property'],
2919                                      "Property(property-name) = ? AND Property(property-value) = ?",
2920                                      [$propName, $propValue], 'Property(id)');
2921        # Return the result.
2922        return $retVal;
2923    }
2924    
2925  =head3 MergedAnnotations  =head3 MergedAnnotations
2926    
2927  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2928    
2929  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2930  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2019  Line 2948 
2948  #: Return Type @;  #: Return Type @;
2949  sub MergedAnnotations {  sub MergedAnnotations {
2950          # Get the parameters.          # Get the parameters.
2951          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2952          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2953          my @tuples = ();          my @tuples = ();
2954          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2045  Line 2973 
2973    
2974  =head3 RoleNeighbors  =head3 RoleNeighbors
2975    
2976  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2977    
2978  Returns a list of the roles that occur in the same diagram as the specified role. Because  Returns a list of the roles that occur in the same diagram as the specified role. Because
2979  diagrams and roles are in a many-to-many relationship with each other, the list is  diagrams and roles are in a many-to-many relationship with each other, the list is
# Line 2068  Line 2996 
2996  #: Return Type @;  #: Return Type @;
2997  sub RoleNeighbors {  sub RoleNeighbors {
2998          # Get the parameters.          # Get the parameters.
2999          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
3000          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
3001          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
3002                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2089  Line 3016 
3016    
3017  =head3 FeatureLinks  =head3 FeatureLinks
3018    
3019  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3020    
3021  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are
3022  to external websites describing either the feature itself or the organism containing it  to external websites describing either the feature itself or the organism containing it
# Line 2111  Line 3038 
3038  #: Return Type @;  #: Return Type @;
3039  sub FeatureLinks {  sub FeatureLinks {
3040          # Get the parameters.          # Get the parameters.
3041          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
3042          # Get the feature's links.          # Get the feature's links.
3043          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
3044          # Return the feature's links.          # Return the feature's links.
# Line 2121  Line 3047 
3047    
3048  =head3 SubsystemsOf  =head3 SubsystemsOf
3049    
3050  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3051    
3052  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
3053  to the role the feature performs.  to the roles the feature performs.
3054    
3055  =over 4  =over 4
3056    
# Line 2134  Line 3060 
3060    
3061  =item RETURN  =item RETURN
3062    
3063  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.
3064    
3065  =back  =back
3066    
3067  =cut  =cut
3068  #: Return Type %;  #: Return Type %@;
3069  sub SubsystemsOf {  sub SubsystemsOf {
3070          # Get the parameters.          # Get the parameters.
3071          my $self = shift @_;      my ($self, $featureID) = @_;
3072          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
3073          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
3074                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
3075                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3076          # Create the return value.          # Create the return value.
3077          my %retVal = ();          my %retVal = ();
3078        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3079        # in two spreadsheet cells.
3080        my %dupHash = ();
3081          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
3082          for my $record (@subsystems) {          for my $record (@subsystems) {
3083                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
3084            my ($subsys, $role) = @{$record};
3085            # Insure it's the first time for both.
3086            my $dupKey = "$subsys\n$role";
3087            if (! exists $dupHash{"$subsys\n$role"}) {
3088                $dupHash{$dupKey} = 1;
3089                push @{$retVal{$subsys}}, $role;
3090            }
3091          }          }
3092          # Return the hash.          # Return the hash.
3093          return %retVal;          return %retVal;
3094  }  }
3095    
3096  =head3 RelatedFeatures  =head3 SubsystemList
3097    
3098  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3099    
3100  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list containing the names of the subsystems in which the specified
3101  have been assigned the specified function by the specified user. If no such features exists,  feature participates. Unlike L</SubsystemsOf>, this method only returns the
3102  an empty list will be returned.  subsystem names, not the roles.
3103    
3104  =over 4  =over 4
3105    
3106  =item featureID  =item featureID
3107    
3108  ID of the feature to whom the desired features are related.  ID of the feature whose subsystem names are desired.
   
 =item function  
   
 Functional assignment (as returned by C</FunctionOf>) that is used to determine which related  
 features should be selected.  
   
 =item userID  
   
 ID of the user whose functional assignments are to be used. If omitted, C<FIG> is assumed.  
3109    
3110  =item RETURN  =item RETURN
3111    
3112  Returns a list of the related features with the specified function.  Returns a list of the names of the subsystems in which the feature participates.
3113    
3114  =back  =back
3115    
3116  =cut  =cut
3117  #: Return Type @;  #: Return Type @;
3118  sub RelatedFeatures {  sub SubsystemList {
3119          # Get the parameters.          # Get the parameters.
3120          my $self = shift @_;      my ($self, $featureID) = @_;
3121          my ($featureID, $function, $userID) = @_;      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3122          # Get a list of the features that are BBHs of the incoming feature.      # the Sprout database!
3123          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3124                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3125                                                                           'IsBidirectionalBestHitOf(to-link)');      # Return the result, sorted.
3126          # Now we loop through the features, pulling out the ones that have the correct      return sort @retVal;
         # functional assignment.  
         my @retVal = ();  
         for my $bbhFeature (@bbhFeatures) {  
                 # Get this feature's functional assignment.  
                 my $newFunction = $self->FunctionOf($bbhFeature, $userID);  
                 # If it matches, add it to the result list.  
                 if ($newFunction eq $function) {  
                         push @retVal, $bbhFeature;  
                 }  
         }  
         # Return the result list.  
         return @retVal;  
3127  }  }
3128    
3129  =head3 TaxonomySort  =head3 GenomeSubsystemData
   
 C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>  
3130    
3131  Return a list formed by sorting the specified features by the taxonomy of the containing      my %featureData = $sprout->GenomeSubsystemData($genomeID);
 genome. This will cause genomes from similar organisms to float close to each other.  
3132    
3133  This task could almost be handled by the database; however, the taxonomy string in the  Return a hash mapping genome features to their subsystem roles.
 database is a text field and can't be indexed. Instead, we create a hash table that maps  
 taxonomy strings to lists of features. We then process the hash table using a key sort  
 and merge the feature lists together to create the output.  
3134    
3135  =over 4  =over 4
3136    
3137  =item $featureIDs  =item genomeID
3138    
3139  List of features to be taxonomically sorted.  ID of the genome whose subsystem feature map is desired.
3140    
3141  =item RETURN  =item RETURN
3142    
3143  Returns the list of features sorted by the taxonomies of the containing genomes.  Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
3144    2-tuple contains a subsystem name followed by a role ID.
3145    
3146  =back  =back
3147    
3148  =cut  =cut
3149  #: Return Type @;  
3150  sub TaxonomySort {  sub GenomeSubsystemData {
3151          # Get the parameters.          # Get the parameters.
3152          my $self = shift @_;      my ($self, $genomeID) = @_;
3153          my ($featureIDs) = @_;      # Declare the return variable.
3154          # Create the working hash table.      my %retVal = ();
3155          my %hashBuffer = ();      # Get a list of the genome features that participate in subsystems. For each
3156          # Loop through the features.      # feature we get its subsystem ID and the corresponding roles.
3157          for my $fid (@{$featureIDs}) {      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3158                  # Get the taxonomy of the feature's genome.                                   "HasFeature(from-link) = ?", [$genomeID],
3159                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3160                                                                                  [$fid], 'Genome(taxonomy)');      # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3161                  # Add this feature to the hash buffer.      # a non-negative variant code.
3162                  if (exists $hashBuffer{$taxonomy}) {      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3163                          push @{$hashBuffer{$taxonomy}}, $fid;                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3164                  } else {                                                  [$genomeID], 'ParticipatesIn(to-link)');
3165                          $hashBuffer{$taxonomy} = [$fid];      # We loop through @roleData to build the hash.
3166                  }      for my $roleEntry (@roleData) {
3167            # Get the data for this feature and cell.
3168            my ($fid, $role, $subsys) = @{$roleEntry};
3169            Trace("Subsystem for $fid is $subsys.") if T(4);
3170            # Check the subsystem;
3171            if ($subs{$subsys}) {
3172                Trace("Subsystem found.") if T(4);
3173                # Insure this feature has an entry in the return hash.
3174                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3175                # Merge in this new data.
3176                push @{$retVal{$fid}}, [$subsys, $role];
3177          }          }
         # Sort the keys and get the elements.  
         my @retVal = ();  
         for my $taxon (sort keys %hashBuffer) {  
                 push @retVal, @{$hashBuffer{$taxon}};  
3178          }          }
3179          # Return the result.          # Return the result.
3180          return @retVal;      return %retVal;
3181  }  }
3182    
3183  =head3 GetAll  =head3 RelatedFeatures
   
 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.  
3184    
3185  The list returned will be a list of lists. Each element of the list will contain      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
 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.  
3186    
3187  C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  Return a list of the features which are bi-directional best hits of the specified feature and
3188    have been assigned the specified function by the specified user. If no such features exists,
3189    an empty list will be returned.
3190    
3191  =over 4  =over 4
3192    
3193  =item objectNames  =item featureID
   
 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  
3194    
3195  List of the parameters to be substituted in for the parameters marks in the filter clause.  ID of the feature to whom the desired features are related.
3196    
3197  =item fields  =item function
3198    
3199  List of the fields to be returned in each element of the list returned.  Functional assignment (as returned by C</FunctionOf>) that is used to determine which related
3200    features should be selected.
3201    
3202  =item count  =item userID
3203    
3204  Maximum number of records to return. If omitted or 0, all available records will be returned.  ID of the user whose functional assignments are to be used. If omitted, C<FIG> is assumed.
3205    
3206  =item RETURN  =item RETURN
3207    
3208  Returns a list of list references. Each element of the return list contains the values for the  Returns a list of the related features with the specified function.
 fields specified in the B<fields> parameter.  
3209    
3210  =back  =back
3211    
3212  =cut  =cut
3213  #: Return Type @@;  #: Return Type @;
3214  sub GetAll {  sub RelatedFeatures {
3215          # Get the parameters.          # Get the parameters.
3216          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
3217          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Get a list of the features that are BBHs of the incoming feature.
3218          # Create the query.      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
3219          my $query = $self->Get($objectNames, $filterClause, $parameterList);      # Now we loop through the features, pulling out the ones that have the correct
3220          # Set up a counter of the number of records read.      # functional assignment.
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
3221          my @retVal = ();          my @retVal = ();
3222          while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {      for my $bbhFeature (@bbhFeatures) {
3223                  my @rowData = $row->Values($fields);          # Get this feature's functional assignment.
3224                  push @retVal, \@rowData;          my $newFunction = $self->FunctionOf($bbhFeature, $userID);
3225                  $fetched++;          # If it matches, add it to the result list.
3226            if ($newFunction eq $function) {
3227                push @retVal, $bbhFeature;
3228          }          }
3229          # Return the resulting list.      }
3230        # Return the result list.
3231          return @retVal;          return @retVal;
3232  }  }
3233    
3234  =head3 GetFlat  =head3 TaxonomySort
   
 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.  
3235    
3236  =item filterClause      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3237    
3238  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Return a list formed by sorting the specified features by the taxonomy of the containing
3239  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  genome. This will cause genomes from similar organisms to float close to each other.
 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.  
3240    
3241  =item parameterList  This task could almost be handled by the database; however, the taxonomy string in the
3242    database is a text field and can't be indexed. Instead, we create a hash table that maps
3243    taxonomy strings to lists of features. We then process the hash table using a key sort
3244    and merge the feature lists together to create the output.
3245    
3246  List of the parameters to be substituted in for the parameters marks in the filter clause.  =over 4
3247    
3248  =item field  =item $featureIDs
3249    
3250  Name of the field to be used to get the elements of the list returned.  List of features to be taxonomically sorted.
3251    
3252  =item RETURN  =item RETURN
3253    
3254  Returns a list of values.  Returns the list of features sorted by the taxonomies of the containing genomes.
3255    
3256  =back  =back
3257    
3258  =cut  =cut
3259  #: Return Type @;  #: Return Type @;
3260  sub GetFlat {  sub TaxonomySort {
3261          # Get the parameters.          # Get the parameters.
3262          my $self = shift @_;      my ($self, $featureIDs) = @_;
3263          my ($objectNames, $filterClause, $parameterList, $field) = @_;      # Create the working hash table.
3264          # Construct the query.      my %hashBuffer = ();
3265          my $query = $self->Get($objectNames, $filterClause, $parameterList);      # Loop through the features.
3266          # Create the result list.      for my $fid (@{$featureIDs}) {
3267            # Get the taxonomy of the feature's genome.
3268            my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3269                                            [$fid], 'Genome(taxonomy)');
3270            # Add this feature to the hash buffer.
3271            push @{$hashBuffer{$taxonomy}}, $fid;
3272        }
3273        # Sort the keys and get the elements.
3274          my @retVal = ();          my @retVal = ();
3275          # Loop through the records, adding the field values found to the result list.      for my $taxon (sort keys %hashBuffer) {
3276          while (my $row = $query->Fetch()) {          push @retVal, @{$hashBuffer{$taxon}};
                 push @retVal, $row->Value($field);  
3277          }          }
3278          # Return the list created.      # Return the result.
3279          return @retVal;          return @retVal;
3280  }  }
3281    
3282  =head3 Protein  =head3 Protein
3283    
3284  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3285    
3286  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3287    
# Line 2471  Line 3351 
3351          # Loop through the input triples.          # Loop through the input triples.
3352          my $n = length $sequence;          my $n = length $sequence;
3353          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3354                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3355                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3356            my $triple = uc substr($sequence, $i, 3);
3357                  # Translate it using the table.                  # Translate it using the table.
3358                  my $protein = "X";                  my $protein = "X";
3359                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2486  Line 3367 
3367    
3368  =head3 LoadInfo  =head3 LoadInfo
3369    
3370  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3371    
3372  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3373  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 2496  Line 3377 
3377  #: Return Type @;  #: Return Type @;
3378  sub LoadInfo {  sub LoadInfo {
3379          # Get the parameters.          # Get the parameters.
3380          my $self = shift @_;      my ($self) = @_;
3381          # 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.
3382          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3383          # Concatenate the table names.          # Concatenate the table names.
3384          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3385          # Return the result.          # Return the result.
3386          return @retVal;          return @retVal;
3387  }  }
3388    
3389    =head3 BBHMatrix
3390    
3391        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3392    
3393    Find all the bidirectional best hits for the features of a genome in a
3394    specified list of target genomes. The return value will be a hash mapping
3395    features in the original genome to their bidirectional best hits in the
3396    target genomes.
3397    
3398    =over 4
3399    
3400    =item genomeID
3401    
3402    ID of the genome whose features are to be examined for bidirectional best hits.
3403    
3404    =item cutoff
3405    
3406    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3407    
3408    =item targets
3409    
3410    List of target genomes. Only pairs originating in the original
3411    genome and landing in one of the target genomes will be returned.
3412    
3413    =item RETURN
3414    
3415    Returns a hash mapping each feature in the original genome to a hash mapping its
3416    BBH pegs in the target genomes to their scores.
3417    
3418    =back
3419    
3420    =cut
3421    
3422    sub BBHMatrix {
3423        # Get the parameters.
3424        my ($self, $genomeID, $cutoff, @targets) = @_;
3425        # Declare the return variable.
3426        my %retVal = ();
3427        # Ask for the BBHs.
3428        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3429        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3430        for my $bbhData (@bbhList) {
3431            my ($peg1, $peg2, $score) = @{$bbhData};
3432            if (! exists $retVal{$peg1}) {
3433                $retVal{$peg1} = { $peg2 => $score };
3434            } else {
3435                $retVal{$peg1}->{$peg2} = $score;
3436            }
3437        }
3438        # Return the result.
3439        return %retVal;
3440    }
3441    
3442    
3443    =head3 SimMatrix
3444    
3445        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3446    
3447    Find all the similarities for the features of a genome in a
3448    specified list of target genomes. The return value will be a hash mapping
3449    features in the original genome to their similarites in the
3450    target genomes.
3451    
3452    =over 4
3453    
3454    =item genomeID
3455    
3456    ID of the genome whose features are to be examined for similarities.
3457    
3458    =item cutoff
3459    
3460    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3461    
3462    =item targets
3463    
3464    List of target genomes. Only pairs originating in the original
3465    genome and landing in one of the target genomes will be returned.
3466    
3467    =item RETURN
3468    
3469    Returns a hash mapping each feature in the original genome to a hash mapping its
3470    similar pegs in the target genomes to their scores.
3471    
3472    =back
3473    
3474    =cut
3475    
3476    sub SimMatrix {
3477        # Get the parameters.
3478        my ($self, $genomeID, $cutoff, @targets) = @_;
3479        # Declare the return variable.
3480        my %retVal = ();
3481        # Get the list of features in the source organism.
3482        my @fids = $self->FeaturesOf($genomeID);
3483        # Ask for the sims. We only want similarities to fig features.
3484        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3485        if (! defined $simList) {
3486            Confess("Unable to retrieve similarities from server.");
3487        } else {
3488            Trace("Processing sims.") if T(3);
3489            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3490            # Create a hash for the target genomes.
3491            my %targetHash = map { $_ => 1 } @targets;
3492            for my $simData (@{$simList}) {
3493                # Get the PEGs and the score.
3494                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3495                # Insure the second ID is in the target list.
3496                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3497                if (exists $targetHash{$genome2}) {
3498                    # Here it is. Now we need to add it to the return hash. How we do that depends
3499                    # on whether or not $peg1 is new to us.
3500                    if (! exists $retVal{$peg1}) {
3501                        $retVal{$peg1} = { $peg2 => $score };
3502                    } else {
3503                        $retVal{$peg1}->{$peg2} = $score;
3504                    }
3505                }
3506            }
3507        }
3508        # Return the result.
3509        return %retVal;
3510    }
3511    
3512    
3513  =head3 LowBBHs  =head3 LowBBHs
3514    
3515  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3516    
3517  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
3518  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 2533  Line 3538 
3538  #: Return Type %;  #: Return Type %;
3539  sub LowBBHs {  sub LowBBHs {
3540          # Get the parsameters.          # Get the parsameters.
3541          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3542          # Create the return hash.          # Create the return hash.
3543          my %retVal = ();          my %retVal = ();
3544          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3545          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3546          # Form the results into the return hash.          # Form the results into the return hash.
3547          for my $pair (@bbhList) {          for my $pair (@bbhList) {
3548                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3549            if ($self->Exists('Feature', $fid)) {
3550                $retVal{$fid} = $pair->[1];
3551            }
3552        }
3553        # Return the result.
3554        return %retVal;
3555    }
3556    
3557    =head3 Sims
3558    
3559        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3560    
3561    Get a list of similarities for a specified feature. Similarity information is not kept in the
3562    Sprout database; rather, they are retrieved from a network server. The similarities are
3563    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3564    so that its elements can be accessed by name.
3565    
3566    Similarities can be either raw or expanded. The raw similarities are basic
3567    hits between features with similar DNA. Expanding a raw similarity drags in any
3568    features considered substantially identical. So, for example, if features B<A1>,
3569    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3570    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3571    
3572    =over 4
3573    
3574    =item fid
3575    
3576    ID of the feature whose similarities are desired, or reference to a list of IDs
3577    of features whose similarities are desired.
3578    
3579    =item maxN
3580    
3581    Maximum number of similarities to return.
3582    
3583    =item maxP
3584    
3585    Minumum allowable similarity score.
3586    
3587    =item select
3588    
3589    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3590    means only similarities to FIG features are returned; C<all> means all expanded
3591    similarities are returned; and C<figx> means similarities are expanded until the
3592    number of FIG features equals the maximum.
3593    
3594    =item max_expand
3595    
3596    The maximum number of features to expand.
3597    
3598    =item filters
3599    
3600    Reference to a hash containing filter information, or a subroutine that can be
3601    used to filter the sims.
3602    
3603    =item RETURN
3604    
3605    Returns a reference to a list of similarity objects, or C<undef> if an error
3606    occurred.
3607    
3608    =back
3609    
3610    =cut
3611    
3612    sub Sims {
3613        # Get the parameters.
3614        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3615        # Create the shim object to test for deleted FIDs.
3616        my $shim = FidCheck->new($self);
3617        # Ask the network for sims.
3618        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3619        # Return the result.
3620        return $retVal;
3621    }
3622    
3623    =head3 IsAllGenomes
3624    
3625        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3626    
3627    Return TRUE if all genomes in the second list are represented in the first list at
3628    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3629    compared to a list of all the genomes.
3630    
3631    =over 4
3632    
3633    =item list
3634    
3635    Reference to the list to be compared to the second list.
3636    
3637    =item checkList (optional)
3638    
3639    Reference to the comparison target list. Every genome ID in this list must occur at
3640    least once in the first list. If this parameter is omitted, a list of all the genomes
3641    is used.
3642    
3643    =item RETURN
3644    
3645    Returns TRUE if every item in the second list appears at least once in the
3646    first list, else FALSE.
3647    
3648    =back
3649    
3650    =cut
3651    
3652    sub IsAllGenomes {
3653        # Get the parameters.
3654        my ($self, $list, $checkList) = @_;
3655        # Supply the checklist if it was omitted.
3656        $checkList = [$self->Genomes()] if ! defined($checkList);
3657        # Create a hash of the original list.
3658        my %testList = map { $_ => 1 } @{$list};
3659        # Declare the return variable. We assume that the representation
3660        # is complete and stop at the first failure.
3661        my $retVal = 1;
3662        my $n = scalar @{$checkList};
3663        for (my $i = 0; $retVal && $i < $n; $i++) {
3664            if (! $testList{$checkList->[$i]}) {
3665                $retVal = 0;
3666            }
3667          }          }
3668          # Return the result.          # Return the result.
3669        return $retVal;
3670    }
3671    
3672    =head3 GetGroups
3673    
3674        my %groups = $sprout->GetGroups(\@groupList);
3675    
3676    Return a hash mapping each group to the IDs of the genomes in the group.
3677    A list of groups may be specified, in which case only those groups will be
3678    shown. Alternatively, if no parameter is supplied, all groups will be
3679    included. Genomes that are not in any group are omitted.
3680    
3681    =cut
3682    #: Return Type %@;
3683    sub GetGroups {
3684        # Get the parameters.
3685        my ($self, $groupList) = @_;
3686        # Declare the return value.
3687        my %retVal = ();
3688        # Determine whether we are getting all the groups or just some.
3689        if (defined $groupList) {
3690            # Here we have a group list. Loop through them individually,
3691            # getting a list of the relevant genomes.
3692            for my $group (@{$groupList}) {
3693                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3694                    [$group], "Genome(id)");
3695                $retVal{$group} = \@genomeIDs;
3696            }
3697        } else {
3698            # Here we need all of the groups. In this case, we run through all
3699            # of the genome records, putting each one found into the appropriate
3700            # group. Note that we use a filter clause to insure that only genomes
3701            # in real NMPDR groups are included in the return set.
3702            my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3703                                        [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3704            # Loop through the genomes found.
3705            for my $genome (@genomes) {
3706                # Get the genome ID and group, and add this genome to the group's list.
3707                my ($genomeID, $group) = @{$genome};
3708                push @{$retVal{$group}}, $genomeID;
3709            }
3710        }
3711        # Return the hash we just built.
3712          return %retVal;          return %retVal;
3713  }  }
3714    
3715    =head3 MyGenomes
3716    
3717        my @genomes = Sprout::MyGenomes($dataDir);
3718    
3719    Return a list of the genomes to be included in the Sprout.
3720    
3721    This method is provided for use during the Sprout load. It presumes the Genome load file has
3722    already been created. (It will be in the Sprout data directory and called either C<Genome>
3723    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3724    IDs.
3725    
3726    =over 4
3727    
3728    =item dataDir
3729    
3730    Directory containing the Sprout load files.
3731    
3732    =back
3733    
3734    =cut
3735    #: Return Type @;
3736    sub MyGenomes {
3737        # Get the parameters.
3738        my ($dataDir) = @_;
3739        # Compute the genome file name.
3740        my $genomeFileName = LoadFileName($dataDir, "Genome");
3741        # Extract the genome IDs from the files.
3742        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3743        # Return the result.
3744        return @retVal;
3745    }
3746    
3747    =head3 LoadFileName
3748    
3749        my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3750    
3751    Return the name of the load file for the specified table in the specified data
3752    directory.
3753    
3754    =over 4
3755    
3756    =item dataDir
3757    
3758    Directory containing the Sprout load files.
3759    
3760    =item tableName
3761    
3762    Name of the table whose load file is desired.
3763    
3764    =item RETURN
3765    
3766    Returns the name of the file containing the load data for the specified table, or
3767    C<undef> if no load file is present.
3768    
3769    =back
3770    
3771    =cut
3772    #: Return Type $;
3773    sub LoadFileName {
3774        # Get the parameters.
3775        my ($dataDir, $tableName) = @_;
3776        # Declare the return variable.
3777        my $retVal;
3778        # Check for the various file names.
3779        if (-e "$dataDir/$tableName") {
3780            $retVal = "$dataDir/$tableName";
3781        } elsif (-e "$dataDir/$tableName.dtx") {
3782            $retVal = "$dataDir/$tableName.dtx";
3783        }
3784        # Return the result.
3785        return $retVal;
3786    }
3787    
3788    =head3 DeleteGenome
3789    
3790        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3791    
3792    Delete a genome from the database.
3793    
3794    =over 4
3795    
3796    =item genomeID
3797    
3798    ID of the genome to delete
3799    
3800    =item testFlag
3801    
3802    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3803    
3804    =item RETURN
3805    
3806    Returns a statistics object describing the rows deleted.
3807    
3808    =back
3809    
3810    =cut
3811    #: Return Type $%;
3812    sub DeleteGenome {
3813        # Get the parameters.
3814        my ($self, $genomeID, $testFlag) = @_;
3815        # Perform the delete for the genome's features.
3816        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3817        # Perform the delete for the primary genome data.
3818        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3819        $retVal->Accumulate($stats);
3820        # Return the result.
3821        return $retVal;
3822    }
3823    
3824    =head3 Fix
3825    
3826        my %fixedHash = $sprout->Fix(%groupHash);
3827    
3828    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3829    The groups will be combined into the appropriate super-groups.
3830    
3831    =over 4
3832    
3833    =item groupHash
3834    
3835    Hash to be fixed up.
3836    
3837    =item RETURN
3838    
3839    Returns a fixed-up version of the hash.
3840    
3841    =back
3842    
3843    =cut
3844    
3845    sub Fix {
3846        # Get the parameters.
3847        my ($self, %groupHash) = @_;
3848        # Create the result hash.
3849        my %retVal = ();
3850        # Copy over the genomes.
3851        for my $groupID (keys %groupHash) {
3852            # Get the super-group name.
3853            my $realGroupID = $self->SuperGroup($groupID);
3854            # Append this group's genomes into the result hash
3855            # using the super-group name.
3856            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3857        }
3858        # Return the result hash.
3859        return %retVal;
3860    }
3861    
3862    =head3 GroupPageName
3863    
3864        my $name = $sprout->GroupPageName($group);
3865    
3866    Return the name of the page for the specified NMPDR group.
3867    
3868    =over 4
3869    
3870    =item group
3871    
3872    Name of the relevant group.
3873    
3874    =item RETURN
3875    
3876    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3877    memory it will be read in.
3878    
3879    =back
3880    
3881    =cut
3882    
3883    sub GroupPageName {
3884        # Get the parameters.
3885        my ($self, $group) = @_;
3886        # Check for the group file data.
3887        my %superTable = $self->CheckGroupFile();
3888        # Compute the real group name.
3889        my $realGroup = $self->SuperGroup($group);
3890        # Get the associated page name.
3891        my $retVal = "../content/$superTable{$realGroup}->{page}";
3892        # Return the result.
3893        return $retVal;
3894    }
3895    
3896    
3897    =head3 AddProperty
3898    
3899        $sprout->AddProperty($featureID, $key, @values);
3900    
3901    Add a new attribute value (Property) to a feature.
3902    
3903    =over 4
3904    
3905    =item peg
3906    
3907    ID of the feature to which the attribute is to be added.
3908    
3909    =item key
3910    
3911    Name of the attribute (key).
3912    
3913    =item values
3914    
3915    Values of the attribute.
3916    
3917    =back
3918    
3919    =cut
3920    #: Return Type ;
3921    sub AddProperty {
3922        # Get the parameters.
3923        my ($self, $featureID, $key, @values) = @_;
3924        # Add the property using the attached attributes object.
3925        $self->ca->AddAttribute($featureID, $key, @values);
3926    }
3927    
3928    =head3 CheckGroupFile
3929    
3930        my %groupData = $sprout->CheckGroupFile();
3931    
3932    Get the group file hash. The group file hash describes the relationship
3933    between a group and the super-group to which it belongs for purposes of
3934    display. The super-group name is computed from the first capitalized word
3935    in the actual group name. For each super-group, the group file contains
3936    the page name and a list of the species expected to be in the group.
3937    Each species is specified by a genus and a species name. A species name
3938    of C<0> implies an entire genus.
3939    
3940    This method returns a hash from super-group names to a hash reference. Each
3941    resulting hash reference contains the following fields.
3942    
3943    =over 4
3944    
3945    =item page
3946    
3947    The super-group's web page in the NMPDR.
3948    
3949    =item contents
3950    
3951    A list of 2-tuples, each containing a genus name followed by a species name
3952    (or 0, indicating all species). This list indicates which organisms belong
3953    in the super-group.
3954    
3955    =back
3956    
3957    =cut
3958    
3959    sub CheckGroupFile {
3960        # Get the parameters.
3961        my ($self) = @_;
3962        # Check to see if we already have this hash.
3963        if (! defined $self->{groupHash}) {
3964            # We don't, so we need to read it in.
3965            my %groupHash;
3966            # Read the group file.
3967            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3968            # Loop through the list of sort-of groups.
3969            for my $groupLine (@groupLines) {
3970                my ($name, $page, @contents) = split /\t/, $groupLine;
3971                $groupHash{$name} = { page => $page,
3972                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3973                                    };
3974            }
3975            # Save the hash.
3976            $self->{groupHash} = \%groupHash;
3977        }
3978        # Return the result.
3979        return %{$self->{groupHash}};
3980    }
3981    
3982    =head2 Virtual Methods
3983    
3984    =head3 CleanKeywords
3985    
3986        my $cleanedString = $sprout->CleanKeywords($searchExpression);
3987    
3988    Clean up a search expression or keyword list. This involves converting the periods
3989    in EC numbers to underscores, converting non-leading minus signs to underscores,
3990    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3991    characters. In addition, any extra spaces are removed.
3992    
3993    =over 4
3994    
3995    =item searchExpression
3996    
3997    Search expression or keyword list to clean. Note that a search expression may
3998    contain boolean operators which need to be preserved. This includes leading
3999    minus signs.
4000    
4001    =item RETURN
4002    
4003    Cleaned expression or keyword list.
4004    
4005    =back
4006    
4007    =cut
4008    
4009    sub CleanKeywords {
4010        # Get the parameters.
4011        my ($self, $searchExpression) = @_;
4012        # Get the stemmer.
4013        my $stemmer = $self->GetStemmer();
4014        # Convert the search expression using the stemmer.
4015        my $retVal = $stemmer->PrepareSearchExpression($searchExpression);
4016        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4017        # Return the result.
4018        return $retVal;
4019    }
4020    
4021    =head3 GetSourceObject
4022    
4023        my $source = $erdb->GetSourceObject();
4024    
4025    Return the object to be used in creating load files for this database.
4026    
4027    =cut
4028    
4029    sub GetSourceObject {
4030        # Get access to the FIG code.
4031        require FIG;
4032        # Return a FIG object.
4033        return FIG->new();
4034    }
4035    
4036    =head3 SectionList
4037    
4038        my @sections = $erdb->SectionList($source);
4039    
4040    Return a list of the names for the different data sections used when loading this database.
4041    The default is an empty string, in which case there is only one section representing the
4042    entire database.
4043    
4044    =over 4
4045    
4046    =item source
4047    
4048    Source object used to access the data from which the database is loaded. This is the
4049    same object returned by L</GetSourceObject>; however, we ask the caller to pass it
4050    in as a parameter so that we don't end up creating multiple copies of a potentially
4051    expensive data structure.
4052    
4053    =item RETURN
4054    
4055    Returns a list of section names.
4056    
4057    =back
4058    
4059    =cut
4060    
4061    sub SectionList {
4062        # Get the parameters.
4063        my ($self, $source) = @_;
4064        # Ask the BaseSproutLoader for a section list.
4065        require BaseSproutLoader;
4066        my @retVal = BaseSproutLoader::GetSectionList($self, $source);
4067        # Return the list.
4068        return @retVal;
4069    }
4070    
4071    =head3 Loader
4072    
4073        my $groupLoader = $erdb->Loader($groupName, $source, $options);
4074    
4075    Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used
4076    by [[ERDBGeneratorPl]] to create the load group objects. If you are not using
4077    [[ERDBGeneratorPl]], you don't need to override this method.
4078    
4079    =over 4
4080    
4081    =item groupName
4082    
4083    Name of the load group whose object is to be returned. The group name is
4084    guaranteed to be a single word with only the first letter capitalized.
4085    
4086    =item source
4087    
4088    The source object used to access the data from which the load file is derived. This
4089    is the same object returned by L</GetSourceObject>; however, we ask the caller to pass
4090    it in as a parameter so that we don't end up creating multiple copies of a potentially
4091    expensive data structure.
4092    
4093    =item options
4094    
4095    Reference to a hash of command-line options.
4096    
4097    =item RETURN
4098    
4099    Returns an [[ERDBLoadGroupPm]] object that can be used to process the specified load group
4100    for this database.
4101    
4102    =back
4103    
4104    =cut
4105    
4106    sub Loader {
4107        # Get the parameters.
4108        my ($self, $groupName, $source, $options) = @_;
4109        # Compute the loader name.
4110        my $loaderClass = "${groupName}SproutLoader";
4111        # Pull in its definition.
4112        require "$loaderClass.pm";
4113        # Create an object for it.
4114        my $retVal = eval("$loaderClass->new(\$self, \$source, \$options)");
4115        # Insure it worked.
4116        Confess("Could not create $loaderClass object: $@") if $@;
4117        # Return it to the caller.
4118        return $retVal;
4119    }
4120    
4121    =head3 LoadGroupList
4122    
4123        my @groups = $erdb->LoadGroupList();
4124    
4125    Returns a list of the names for this database's load groups. This method is used
4126    by [[ERDBGeneratorPl]] when the user wishes to load all table groups. The default
4127    is a single group called 'All' that loads everything.
4128    
4129    =cut
4130    
4131    sub LoadGroupList {
4132        # Return the list.
4133        return qw(Genome Subsystem Annotation Property Source Reaction Synonym Drug Feature);
4134    }
4135    
4136    =head3 LoadDirectory
4137    
4138        my $dirName = $erdb->LoadDirectory();
4139    
4140    Return the name of the directory in which load files are kept. The default is
4141    the FIG temporary directory, which is a really bad choice, but it's always there.
4142    
4143    =cut
4144    
4145    sub LoadDirectory {
4146        # Get the parameters.
4147        my ($self) = @_;
4148        # Return the directory name.
4149        return $self->{dataDir};
4150    }
4151    
4152  =head2 Internal Utility Methods  =head2 Internal Utility Methods