[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 1.126, Thu Apr 2 01:47:00 2009 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 ERDBQuery;
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 qw(-nosticky);
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.
   
 =cut  
39    
40  #: Constructor SFXlate->new_sprout_only();  The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
41    
42    =cut
43    
44  =head2 Public Methods  =head2 Public Methods
45    
46  =head3 new  =head3 new
47    
48  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
49    
50  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
51  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 55 
55    
56  =item dbName  =item dbName
57    
58  Name of the database.  Name of the database. If omitted, the default Sprout database name is used.
59    
60  =item options  =item options
61    
# Line 63  Line 67 
67    
68  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
69    
70  * B<userData> user name and password, delimited by a slash (default C<root/>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
71    
72  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
73    
74    * B<sock> connection socket (default same as SEED)
75    
76  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
77    
78  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
79    
80    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
81    
82    * B<host> name of the database host
83    
84  =back  =back
85    
86  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
87  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
88  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
89    
90  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' });
91    
92    In order to work properly with [[ERDBGeneratorPl]], the constructor has an alternate
93    form.
94    
95        my $sprout = Sprout->new(dbd => $filename);
96    
97    Where I<$fileName> is the name of the DBD file. This enables us to specify an alternate
98    DBD for the loader, which is important when the database format changes.
99    
100  =cut  =cut
101    
102  sub new {  sub new {
103          # Get the parameters.          # Get the parameters.
104          my ($class, $dbName, $options) = @_;          my ($class, $dbName, $options) = @_;
105        # Check for the alternate signature, and default the database name if it is missing.
106        if ($dbName eq 'dbd') {
107            $dbName = $FIG_Config::sproutDB;
108            $options = { xmlFileName => $options };
109        } elsif (! defined $dbName) {
110            $dbName = $FIG_Config::sproutDB;
111        } elsif (ref $dbName eq 'HASH') {
112            $options = $dbName;
113            $dbName = $FIG_Config::sproutDB;
114        }
115        # Compute the DBD directory.
116        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
117                                                      $FIG_Config::fig );
118          # 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
119          # the incoming data.          # the incoming data.
120          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
121                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
122                                             dataDir              => 'Data',                      # data file directory                                                          # database type
123                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
124                                             userData             => 'root/',                     # user name and password                                                          # data file directory
125                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
126                                                            # database definition file name
127                           userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
128                                                            # user name and password
129                           port         => $FIG_Config::sproutPort,
130                                                            # database connection port
131                           sock         => $FIG_Config::sproutSock,
132                           host         => $FIG_Config::sprout_host,
133                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
134                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
135                           noDBOpen     => 0,               # 1 to suppress the database open
136                           demandDriven => 0,               # 1 for forward-only queries
137                                            }, $options);                                            }, $options);
138          # Get the data directory.          # Get the data directory.
139          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 101  Line 141 
141          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
142          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
143          # Connect to the database.          # Connect to the database.
144          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
145        if (! $optionTable->{noDBOpen}) {
146            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
147            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
148                                    $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
149        }
150          # Create the ERDB object.          # Create the ERDB object.
151          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
152          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName, %$optionTable);
153          # Create this object.      # Add the option table and XML file name.
154          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
155          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
156          bless $self;      # Set up space for the group file data.
157          return $self;      $retVal->{groupHash} = undef;
158        # Set up space for the genome hash. We use this to identify NMPDR genomes
159        # and remember genome data.
160        $retVal->{genomeHash} = {};
161        $retVal->{genomeHashFilled} = 0;
162        # Remember the data directory name.
163        $retVal->{dataDir} = $dataDir;
164        # Return it.
165        return $retVal;
166  }  }
167    
168  =head3 MaxSegment  =head3 ca
169    
170  C<< my $length = $sprout->MaxSegment(); >>      my $ca = $sprout->ca():;
171    
172  This method returns the maximum permissible length of a feature segment. The length is important  Return the [[CustomAttributesPm]] object for retrieving object
173  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.  
174    
175  =cut  =cut
 #: Return Type $;  
 sub MaxSegment {  
         my $self = shift @_;  
         return $self->{_options}->{maxSegmentLength};  
 }  
   
 =head3 MaxSequence  
176    
177  C<< my $length = $sprout->MaxSequence(); >>  sub ca {
178        # Get the parameters.
179  This method returns the maximum permissible length of a contig sequence. A contig is broken      my ($self) = @_;
180  into sequences in order to save memory resources. In particular, when manipulating features,      # Do we already have an attribute object?
181  we generally only need a few sequences in memory rather than the entire contig.      my $retVal = $self->{_ca};
182        if (! defined $retVal) {
183  =cut          # No, create one. How we do it depends on the configuration.
184  #: Return Type $;          if ($FIG_Config::attrURL) {
185  sub MaxSequence {              Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
186          my $self = shift @_;              $retVal = RemoteCustomAttributes->new($FIG_Config::attrURL);
187          return $self->{_options}->{maxSequenceLength};          } elsif ($FIG_Config::attrDbName) {
188                Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
189                my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
190                $retVal = CustomAttributes->new(user => $user);
191            }
192            # Save it for next time.
193            $self->{_ca} = $retVal;
194        }
195        # Return the result.
196        return $retVal;
197  }  }
198    
199  =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)"); >>  
200    
201  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.  
202    
203  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.  
204    
205  =over 4  =over 4
206    
207  =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.  
208    
209  =item parameterList  Scope of the desired genomes. C<core> covers the original core genomes,
210    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
211  List of the parameters to be substituted in for the parameters marks in the filter clause.  genomes in the system.
212    
213  =item RETURN  =item RETURN
214    
215  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.
216    
217  =back  =back
218    
219  =cut  =cut
220    
221  sub Get {  sub CoreGenomes {
222          # Get the parameters.          # Get the parameters.
223          my $self = shift @_;      my ($self, $scope) = @_;
224          my ($objectNames, $filterClause, $parameterList) = @_;      # Declare the return variable.
225          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      my @retVal = ();
226          # rather than a list of parameters. The next step is to convert the parameters from a reference      # If we want all genomes, then this is easy.
227          # to a real list. We can only do this if the parameters have been specified.      if ($scope eq 'all') {
228          my @parameters;          @retVal = $self->Genomes();
229          if ($parameterList) { @parameters = @{$parameterList}; }      } else {
230          return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);          # Here we're dealing with groups. Get the hash of all the
231            # genome groups.
232            my %groups = $self->GetGroups();
233            # Loop through the groups, keeping the ones that we want.
234            for my $group (keys %groups) {
235                # Decide if we want to keep this group.
236                my $keepGroup = 0;
237                if ($scope eq 'nmpdr') {
238                    # NMPDR mode: keep all groups.
239                    $keepGroup = 1;
240                } elsif ($scope eq 'core') {
241                    # CORE mode. Only keep real core groups.
242                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
243                        $keepGroup = 1;
244                    }
245                }
246                # Add this group if we're keeping it.
247                if ($keepGroup) {
248                    push @retVal, @{$groups{$group}};
249                }
250            }
251        }
252        # Return the result.
253        return @retVal;
254  }  }
255    
256  =head3 GetEntity  =head3 SuperGroup
257    
258  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my $superGroup = $sprout->SuperGroup($groupName);
259    
260  Return an object describing the entity instance with a specified ID.  Return the name of the super-group containing the specified NMPDR genome
261    group. If no appropriate super-group can be found, an error will be
262    thrown.
263    
264  =over 4  =over 4
265    
266  =item entityType  =item groupName
   
 Entity type name.  
267    
268  =item ID  Name of the group whose super-group is desired.
   
 ID of the desired entity.  
269    
270  =item RETURN  =item RETURN
271    
272  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.  
273    
274  =back  =back
275    
276  =cut  =cut
277    
278  sub GetEntity {  sub SuperGroup {
279          # Get the parameters.          # Get the parameters.
280          my $self = shift @_;      my ($self, $groupName) = @_;
281          my ($entityType, $ID) = @_;      # Declare the return variable.
282          # Create a query.      my $retVal;
283          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      # Get the group hash.
284          # Get the first (and only) object.      my %groupHash = $self->CheckGroupFile();
285          my $retVal = $query->Fetch();      # Find the super-group genus.
286        $groupName =~ /([A-Z]\w+)/;
287        my $nameThing = $1;
288        # See if it's directly in the group hash.
289        if (exists $groupHash{$nameThing}) {
290            # Yes, then it's our result.
291            $retVal = $nameThing;
292        } else {
293            # No, so we have to search.
294            for my $superGroup (keys %groupHash) {
295                # Get this super-group's item list.
296                my $list = $groupHash{$superGroup}->{contents};
297                # Search it.
298                if (grep { $_->[0] eq $nameThing } @{$list}) {
299                    $retVal = $superGroup;
300                }
301            }
302        }
303          # Return the result.          # Return the result.
304          return $retVal;          return $retVal;
305  }  }
306    
307  =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  
308    
309  Returns a flattened list of the values of the specified fields for the specified entity.      my $length = $sprout->MaxSegment();
310    
311  =back  This method returns the maximum permissible length of a feature segment. The length is important
312    because it enables us to make reasonable guesses at how to find features inside a particular
313    contig region. For example, if the maximum length is 4000 and we're looking for a feature that
314    overlaps the region from 6000 to 7000 we know that the starting position must be between 2001
315    and 10999.
316    
317  =cut  =cut
318  #: Return Type @;  #: Return Type $;
319  sub GetEntityValues {  sub MaxSegment {
320          # Get the parameters.      my ($self) = @_;
321          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;  
322  }  }
323    
324  =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  
325    
326  Fully-qualified name to give to the output file.      my $length = $sprout->MaxSequence();
327    
328  =back  This method returns the maximum permissible length of a contig sequence. A contig is broken
329    into sequences in order to save memory resources. In particular, when manipulating features,
330    we generally only need a few sequences in memory rather than the entire contig.
331    
332  =cut  =cut
333    #: Return Type $;
334  sub ShowMetaData {  sub MaxSequence {
335          # Get the parameters.      my ($self) = @_;
336          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);  
337  }  }
338    
339  =head3 Load  =head3 Load
340    
341  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
342    
343  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.
344    
# Line 364  Line 350 
350  The files are loaded based on the presumption that each line of the file is a record in the  The files are loaded based on the presumption that each line of the file is a record in the
351  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
352  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
353  be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  be presented in the order given in the relation tables produced by the database documentation.
354    
355  =over 4  =over 4
356    
# Line 383  Line 369 
369  #: Return Type %;  #: Return Type %;
370  sub Load {  sub Load {
371          # Get the parameters.          # Get the parameters.
372          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
373          # Load the tables from the data directory.          # Load the tables from the data directory.
374          my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
375          # Return the statistics.          # Return the statistics.
376          return $retVal;          return $retVal;
377  }  }
378    
379  =head3 LoadUpdate  =head3 LoadUpdate
380    
381  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
382    
383  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
384  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 407 
407  =back  =back
408    
409  =cut  =cut
410  #: Return Type %;  #: Return Type $%;
411  sub LoadUpdate {  sub LoadUpdate {
412          # Get the parameters.          # Get the parameters.
413          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
414          # Declare the return value.          # Declare the return value.
415          my $retVal = Stats->new();          my $retVal = Stats->new();
416          # Get the data directory.          # Get the data directory.
# Line 439  Line 419 
419          # Loop through the incoming table names.          # Loop through the incoming table names.
420          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
421                  # Find the table's file.                  # Find the table's file.
422                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
423                  if (! -e $fileName) {          if (! $fileName) {
424                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
425                  }          } else {
426                  # Attempt to load this table.                  # Attempt to load this table.
427                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
428                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
429                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
430          }          }
431        }
432          # Return the statistics.          # Return the statistics.
433          return $retVal;          return $retVal;
434  }  }
435    
436    =head3 GenomeCounts
437    
438        my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
439    
440    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
441    genomes will be included in the counts.
442    
443    =over 4
444    
445    =item complete
446    
447    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
448    counted
449    
450    =item RETURN
451    
452    A six-element list containing the number of genomes in each of six categories--
453    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
454    
455    =back
456    
457    =cut
458    
459    sub GenomeCounts {
460        # Get the parameters.
461        my ($self, $complete) = @_;
462        # Set the filter based on the completeness flag.
463        my $filter = ($complete ? "Genome(complete) = 1" : "");
464        # Get all the genomes and the related taxonomy information.
465        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
466        # Clear the counters.
467        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
468        # Loop through, counting the domains.
469        for my $genome (@genomes) {
470            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
471            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
472            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
473            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
474            elsif ($genome->[1] =~ /^env/i)      { ++$env }
475            else  { ++$unk }
476        }
477        # Return the counts.
478        return ($arch, $bact, $euk, $vir, $env, $unk);
479    }
480    
481    =head3 ContigCount
482    
483        my $count = $sprout->ContigCount($genomeID);
484    
485    Return the number of contigs for the specified genome ID.
486    
487    =over 4
488    
489    =item genomeID
490    
491    ID of the genome whose contig count is desired.
492    
493    =item RETURN
494    
495    Returns the number of contigs for the specified genome.
496    
497    =back
498    
499    =cut
500    
501    sub ContigCount {
502        # Get the parameters.
503        my ($self, $genomeID) = @_;
504        # Get the contig count.
505        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
506        # Return the result.
507        return $retVal;
508    }
509    
510    =head3 GenomeMenu
511    
512        my $html = $sprout->GenomeMenu(%options);
513    
514    Generate a genome selection control with the specified name and options.
515    This control is almost but not quite the same as the genome control in the
516    B<SearchHelper> class. Eventually, the two will be combined.
517    
518    =over 4
519    
520    =item options
521    
522    Optional parameters for the control (see below).
523    
524    =item RETURN
525    
526    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
527    
528    =back
529    
530    The valid options are as follows.
531    
532    =over 4
533    
534    =item name
535    
536    Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
537    Terrible things will happen if you have two controls with the same name on the same page.
538    
539    =item filter
540    
541    If specified, a filter for the list of genomes to display. The filter should be in the form of a
542    list reference, a string, or a hash reference. If it is a list reference, the first element
543    of the list should be the filter string, and the remaining elements the filter parameters. If it is a
544    string, it will be split into a list at each included tab. If it is a hash reference, it should be
545    a hash that maps genomes which should be included to a TRUE value.
546    
547    =item multiSelect
548    
549    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
550    
551    =item size
552    
553    Number of rows to display in the control. The default is C<10>
554    
555    =item id
556    
557    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
558    unless this ID is unique.
559    
560    =item selected
561    
562    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
563    default is none.
564    
565    =item class
566    
567    If specified, a style class to assign to the genome control.
568    
569    =back
570    
571    =cut
572    
573    sub GenomeMenu {
574        # Get the parameters.
575        my ($self, %options) = @_;
576        # Get the control's name and ID.
577        my $menuName = $options{name} || $options{id} || 'myGenomeControl';
578        my $menuID = $options{id} || $menuName;
579        Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
580        # Compute the IDs for the status display.
581        my $divID = "${menuID}_status";
582        my $urlID = "${menuID}_url";
583        # Compute the code to show selected genomes in the status area.
584        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
585        # Check for single-select or multi-select.
586        my $multiSelect = $options{multiSelect} || 0;
587        # Get the style data.
588        my $class = $options{class} || '';
589        # Get the list of pre-selected items.
590        my $selections = $options{selected} || [];
591        if (ref $selections ne 'ARRAY') {
592            $selections = [ split /\s*,\s*/, $selections ];
593        }
594        my %selected = map { $_ => 1 } @{$selections};
595        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
596        # string, a hash reference, or a list reference.
597        my ($filterHash, $filterString);
598        my $filterParms = $options{filter} || "";
599        if (ref $filterParms eq 'HASH') {
600            $filterHash = $filterParms;
601            $filterParms = [];
602            $filterString = "";
603        } else {
604            if (! ref $filterParms) {
605                $filterParms = [split /\t|\\t/, $filterParms];
606            }
607            $filterString = shift @{$filterParms};
608        }
609        # Check for possible subsystem filtering. If there is one, we will tack the
610        # relationship onto the object name list.
611        my @objectNames = qw(Genome);
612        if ($filterString =~ /ParticipatesIn\(/) {
613            push @objectNames, 'ParticipatesIn';
614        }
615        # Get a list of all the genomes in group order. In fact, we only need them ordered
616        # by name (genus,species,strain), but putting primary-group in front enables us to
617        # take advantage of an existing index.
618        my @genomeList = $self->GetAll(\@objectNames, "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
619                                       $filterParms,
620                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
621        # Apply the hash filter (if any).
622        if (defined $filterHash) {
623            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
624        }
625        # Create a hash to organize the genomes by group. Each group will contain a list of
626        # 2-tuples, the first element being the genome ID and the second being the genome
627        # name.
628        my %gHash = ();
629        for my $genome (@genomeList) {
630            # Get the genome data.
631            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
632            # Compute its name. This is the genus, species, strain (if any), and the contig count.
633            my $name = "$genus $species ";
634            $name .= "$strain " if $strain;
635            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
636            # Now we get the domain. The domain tells us the display style of the organism.
637            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
638            # Now compute the display group. This is normally the primary group, but if the
639            # organism is supporting, we blank it out.
640            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
641            # Push the genome into the group's list. Note that we use the real group
642            # name for the hash key here, not the display group name.
643            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
644        }
645        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
646        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
647        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
648        # that aren't "other". At some point, we will want to make this less complicated.
649        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
650                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
651        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
652        # Remember the number of NMPDR groups.
653        my $nmpdrGroupCount = scalar @groups;
654        # Are there any supporting genomes?
655        if (exists $gHash{$FIG_Config::otherGroup}) {
656            # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
657            # of the domains found.
658            my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
659            my @domains = ();
660            for my $genomeData (@otherGenomes) {
661                my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
662                if (exists $gHash{$domain}) {
663                    push @{$gHash{$domain}}, $genomeData;
664                } else {
665                    $gHash{$domain} = [$genomeData];
666                    push @domains, $domain;
667                }
668            }
669            # Add the domain groups at the end of the main group list. The main group list will now
670            # contain all the categories we need to display the genomes.
671            push @groups, sort @domains;
672            # Delete the supporting group.
673            delete $gHash{$FIG_Config::otherGroup};
674        }
675        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
676        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
677        # and use that to make the selections.
678        my $nmpdrCount = 0;
679        # Create the type counters.
680        my $groupCount = 1;
681        # Get the number of rows to display.
682        my $rows = $options{size} || 10;
683        # If we're multi-row, create an onChange event.
684        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
685        # Set up the multiple-select flag.
686        my $multipleTag = ($multiSelect ? " multiple" : "" );
687        # Set up the style class.
688        my $classTag = ($class ? " $class" : "" );
689        # Create the SELECT tag and stuff it into the output array.
690        my @lines = qq(<SELECT name="$menuName" id="$menuID" class="genomeSelect $class" $onChangeTag$multipleTag$classTag size="$rows">);
691        # Loop through the groups.
692        for my $group (@groups) {
693            # Get the genomes in the group.
694            for my $genome (@{$gHash{$group}}) {
695                # If this is an NMPDR organism, we add an extra style and count it.
696                my $nmpdrStyle = "";
697                if ($nmpdrGroupCount > 0) {
698                    $nmpdrCount++;
699                    $nmpdrStyle = " Core";
700                }
701                # Get the organism ID, name, contig count, and domain.
702                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
703                # See if we're pre-selected.
704                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
705                # Compute the display name.
706                my $nameString = "$name ($genomeID$contigCount)";
707                # Generate the option tag.
708                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
709                push @lines, "    $optionTag";
710            }
711            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
712            # groups.
713            $nmpdrGroupCount--;
714        }
715        # Close the SELECT tag.
716        push @lines, "</SELECT>";
717        if ($rows > 1) {
718            # We're in a non-compact mode, so we need to add some selection helpers. First is
719            # the search box. This allows the user to type text and change which genomes are
720            # displayed. For multiple-select mode, we include a button that selects the displayed
721            # genes. For single-select mode, we use a plain label instead.
722            my $searchThingName = "${menuID}_SearchThing";
723            my $searchThingLabel = "Type to narrow selection";
724            my $searchThingButton = "";
725            if ($multiSelect) {
726                $searchThingButton = qq(<INPUT type="button" name="MacroSearch" class="button" value="Go" onClick="selectShowing('$menuID', '$searchThingName'); $showSelect;" />);
727            }
728            push @lines, "<br />$searchThingLabel&nbsp;" .
729                         qq(<INPUT type="text" id="$searchThingName" name="$searchThingName" class="genomeSearchThing" onKeyup="showTyped('$menuID', '$searchThingName');" />) .
730                         $searchThingButton .
731                         Hint("GenomeControl", 28) . "<br />";
732            # For multi-select mode, we also have buttons to set and clear selections.
733            if ($multiSelect) {
734                push @lines, qq(<INPUT type="button" name="ClearAll" class="bigButton genomeButton" value="Clear All" onClick="clearAll(getElementById('$menuID')); $showSelect" />);
735                push @lines, qq(<INPUT type="button" name="SelectAll" class="bigButton genomeButton" value="Select All" onClick="selectAll(getElementById('$menuID')); $showSelect" />);
736                push @lines, qq(<INPUT type="button" name="NMPDROnly" class="bigButton genomeButton" value="Select NMPDR" onClick="selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;" />);
737            }
738            # Add a hidden field we can use to generate organism page hyperlinks.
739            push @lines, qq(<INPUT type="hidden" id="$urlID" value="$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=" />);
740            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
741            push @lines, qq(<DIV id="$divID" class="Panel"></DIV>);
742        }
743        # Assemble all the lines into a string.
744        my $retVal = join("\n", @lines, "");
745        # Return the result.
746        return $retVal;
747    }
748    
749    =head3 Cleanup
750    
751        $sprout->Cleanup();
752    
753    Release the internal cache structures to free up memory.
754    
755    =cut
756    
757    sub Cleanup {
758        # Get the parameters.
759        my ($self) = @_;
760        # Delete the stemmer.
761        delete $self->{stemmer};
762        # Delete the attribute database.
763        delete $self->{_ca};
764        # Delete the group hash.
765        delete $self->{groupHash};
766        # Is there a FIG object?
767        if (defined $self->{fig}) {
768            # Yes, clear its subsystem cache.
769            $self->{fig}->clear_subsystem_cache();
770        }
771    }
772    
773    
774    =head3 Stem
775    
776        my $stem = $sprout->Stem($word);
777    
778    Return the stem of the specified word, or C<undef> if the word is not
779    stemmable. Note that even if the word is stemmable, the stem may be
780    the same as the original word.
781    
782    =over 4
783    
784    =item word
785    
786    Word to convert into a stem.
787    
788    =item RETURN
789    
790    Returns a stem of the word (which may be the word itself), or C<undef> if
791    the word is not stemmable.
792    
793    =back
794    
795    =cut
796    
797    sub Stem {
798        # Get the parameters.
799        my ($self, $word) = @_;
800        # Get the stemmer object.
801        my $stemmer = $self->{stemmer};
802        if (! defined $stemmer) {
803            # We don't have one pre-built, so we build and save it now.
804            $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
805                                     stops => "$FIG_Config::sproutData/StopWords.txt",
806                                     cache => 0);
807            $self->{stemmer} = $stemmer;
808        }
809        # Try to stem the word.
810        my $retVal = $stemmer->Process($word);
811        # Return the result.
812        return $retVal;
813    }
814    
815    
816  =head3 Build  =head3 Build
817    
818  C<< $sprout->Build(); >>      $sprout->Build();
819    
820  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.
821  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 825 
825  #: Return Type ;  #: Return Type ;
826  sub Build {  sub Build {
827          # Get the parameters.          # Get the parameters.
828          my $self = shift @_;      my ($self) = @_;
829          # Create the tables.          # Create the tables.
830          $self->{_erdb}->CreateTables;      $self->CreateTables();
831  }  }
832    
833  =head3 Genomes  =head3 Genomes
834    
835  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
836    
837  Return a list of all the genome IDs.  Return a list of all the genome IDs.
838    
# Line 479  Line 840 
840  #: Return Type @;  #: Return Type @;
841  sub Genomes {  sub Genomes {
842          # Get the parameters.          # Get the parameters.
843          my $self = shift @_;      my ($self) = @_;
844          # Get all the genomes.          # Get all the genomes.
845          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
846          # Return the list of IDs.          # Return the list of IDs.
# Line 488  Line 849 
849    
850  =head3 GenusSpecies  =head3 GenusSpecies
851    
852  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
853    
854  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
855    
# Line 509  Line 870 
870  #: Return Type $;  #: Return Type $;
871  sub GenusSpecies {  sub GenusSpecies {
872          # Get the parameters.          # Get the parameters.
873          my $self = shift @_;      my ($self, $genomeID) = @_;
874          my ($genomeID) = @_;      # Declare the return value.
875          # Get the data for the specified genome.      my $retVal;
876          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      # Get the genome data.
877                                                                                                                            'Genome(unique-characterization)']);      my $genomeData = $self->_GenomeData($genomeID);
878          # Format the result and return it.      # Only proceed if we found the genome.
879          my $retVal = join(' ', @values);      if (defined $genomeData) {
880            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
881        }
882        # Return it.
883          return $retVal;          return $retVal;
884  }  }
885    
886  =head3 FeaturesOf  =head3 FeaturesOf
887    
888  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
889    
890  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
891    
# Line 546  Line 910 
910  #: Return Type @;  #: Return Type @;
911  sub FeaturesOf {  sub FeaturesOf {
912          # Get the parameters.          # Get the parameters.
913          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
914          # Get the features we want.          # Get the features we want.
915          my @features;          my @features;
916          if (!$ftype) {          if (!$ftype) {
# Line 567  Line 930 
930    
931  =head3 FeatureLocation  =head3 FeatureLocation
932    
933  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
934    
935  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
936  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 954 
954  =item RETURN  =item RETURN
955    
956  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
957  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
958    wasn't found.
959    
960  =back  =back
961    
962  =cut  =cut
963  #: Return Type @;  
 #: Return Type $;  
964  sub FeatureLocation {  sub FeatureLocation {
965          # Get the parameters.          # Get the parameters.
966          my $self = shift @_;      my ($self, $featureID) = @_;
967          my ($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.  
968          my @retVal = ();          my @retVal = ();
969          # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
970          # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
971          my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
972          # Loop through the query results, creating location specifiers.      if (defined $object) {
973          while (my $location = $query->Fetch()) {          # Get the location string.
974                  # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
975                  my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
976                          '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$len";  
977          }          }
978          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
979          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
980  }  }
981    
982  =head3 ParseLocation  =head3 ParseLocation
983    
984  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
985    
986  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
987  length.  length.
# Line 659  Line 1000 
1000  =back  =back
1001    
1002  =cut  =cut
1003  #: Return Type @;  
1004  sub ParseLocation {  sub ParseLocation {
1005          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
1006        # the first parameter.
1007        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
1008          my ($location) = @_;          my ($location) = @_;
1009          # Parse it into segments.          # Parse it into segments.
1010          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
1011          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
1012          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
1013          if ($dir eq "_") {          if ($dir eq "_") {
# Line 680  Line 1023 
1023          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
1024  }  }
1025    
 =head3 DNASeq  
1026    
1027  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  =head3 PointLocation
1028    
1029  This method returns the DNA sequence represented by a list of locations. The list of locations      my $found = Sprout::PointLocation($location, $point);
1030  should be of the form returned by L</featureLocation> when in a list context. In other words,  
1031  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  Return the offset into the specified location of the specified point on the contig. If
1032    the specified point is before the location, a negative value will be returned. If it is
1033    beyond the location, an undefined value will be returned. It is assumed that the offset
1034    is for the location's contig. The location can either be new-style (using a C<+> or C<->
1035    and a length) or old-style (using C<_> and start and end positions.
1036    
1037  =over 4  =over 4
1038    
1039  =item locationList  =item location
1040    
1041  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  A location specifier (see L</FeatureLocation> for a description).
1042  L</FeatureLocation> for more about this format).  
1043    =item point
1044    
1045    The offset into the contig of the point in which we're interested.
1046    
1047    =item RETURN
1048    
1049    Returns the offset inside the specified location of the specified point, a negative
1050    number if the point is before the location, or an undefined value if the point is past
1051    the location. If the length of the location is 0, this method will B<always> denote
1052    that it is outside the location. The offset will always be relative to the left-most
1053    position in the location.
1054    
1055    =back
1056    
1057    =cut
1058    
1059    sub PointLocation {
1060        # Get the parameter. Note that if we're called as an instance method, we ignore
1061        # the first parameter.
1062        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
1063        my ($location, $point) = @_;
1064        # Parse out the location elements. Note that this works on both old-style and new-style
1065        # locations.
1066        my ($contigID, $start, $dir, $len) = ParseLocation($location);
1067        # Declare the return variable.
1068        my $retVal;
1069        # Compute the offset. The computation is dependent on the direction of the location.
1070        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
1071        # Return the offset if it's valid.
1072        if ($offset < $len) {
1073            $retVal = $offset;
1074        }
1075        # Return the offset found.
1076        return $retVal;
1077    }
1078    
1079    =head3 DNASeq
1080    
1081        my $sequence = $sprout->DNASeq(\@locationList);
1082    
1083    This method returns the DNA sequence represented by a list of locations. The list of locations
1084    should be of the form returned by L</featureLocation> when in a list context. In other words,
1085    each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
1086    
1087    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
1088    between positions 1401 and 1532, inclusive.
1089    
1090        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
1091    
1092    =over 4
1093    
1094    =item locationList
1095    
1096    List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
1097    I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
1098    
1099  =item RETURN  =item RETURN
1100    
# Line 705  Line 1106 
1106  #: Return Type $;  #: Return Type $;
1107  sub DNASeq {  sub DNASeq {
1108          # Get the parameters.          # Get the parameters.
1109          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
1110          # Create the return string.          # Create the return string.
1111          my $retVal = "";          my $retVal = "";
1112          # Loop through the locations.          # Loop through the locations.
# Line 721  Line 1121 
1121                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
1122                  # before putting it in the return value.                  # before putting it in the return value.
1123                  my ($start, $stop);                  my ($start, $stop);
1124            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
1125                  if ($dir eq "+") {                  if ($dir eq "+") {
1126                          $start = $beg;                          $start = $beg;
1127                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
1128                  } else {                  } else {
1129                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
1130                          $stop = $beg;                          $stop = $beg;
1131                  }                  }
1132            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
1133                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
1134                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
1135                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 739  Line 1141 
1141                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
1142                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
1143                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
1144                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1145                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
1146                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1147                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1148                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1149                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
1150                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
1151                  }                  }
1152                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
1153                  if ($dir eq '+') {                  if ($dir eq '+') {
1154                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
1155                  } else {                  } else {
1156                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
1157                  }                  }
1158          }          }
1159          # Return the result.          # Return the result.
# Line 759  Line 1162 
1162    
1163  =head3 AllContigs  =head3 AllContigs
1164    
1165  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1166    
1167  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1168    
# Line 779  Line 1182 
1182  #: Return Type @;  #: Return Type @;
1183  sub AllContigs {  sub AllContigs {
1184          # Get the parameters.          # Get the parameters.
1185          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
1186          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
1187          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
1188                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 788  Line 1190 
1190          return @retVal;          return @retVal;
1191  }  }
1192    
1193    =head3 GenomeLength
1194    
1195        my $length = $sprout->GenomeLength($genomeID);
1196    
1197    Return the length of the specified genome in base pairs.
1198    
1199    =over 4
1200    
1201    =item genomeID
1202    
1203    ID of the genome whose base pair count is desired.
1204    
1205    =item RETURN
1206    
1207    Returns the number of base pairs in all the contigs of the specified
1208    genome.
1209    
1210    =back
1211    
1212    =cut
1213    
1214    sub GenomeLength {
1215        # Get the parameters.
1216        my ($self, $genomeID) = @_;
1217        # Declare the return variable.
1218        my $retVal = 0;
1219        # Get the genome data.
1220        my $genomeData = $self->_GenomeData($genomeID);
1221        # Only proceed if it exists.
1222        if (defined $genomeData) {
1223            $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1224        }
1225        # Return the result.
1226        return $retVal;
1227    }
1228    
1229    =head3 FeatureCount
1230    
1231        my $count = $sprout->FeatureCount($genomeID, $type);
1232    
1233    Return the number of features of the specified type in the specified genome.
1234    
1235    =over 4
1236    
1237    =item genomeID
1238    
1239    ID of the genome whose feature count is desired.
1240    
1241    =item type
1242    
1243    Type of feature to count (eg. C<peg>, C<rna>, etc.).
1244    
1245    =item RETURN
1246    
1247    Returns the number of features of the specified type for the specified genome.
1248    
1249    =back
1250    
1251    =cut
1252    
1253    sub FeatureCount {
1254        # Get the parameters.
1255        my ($self, $genomeID, $type) = @_;
1256        # Compute the count.
1257        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1258                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1259                                    [$genomeID, $type]);
1260        # Return the result.
1261        return $retVal;
1262    }
1263    
1264    =head3 GenomeAssignments
1265    
1266        my $fidHash = $sprout->GenomeAssignments($genomeID);
1267    
1268    Return a list of a genome's assigned features. The return hash will contain each
1269    assigned feature of the genome mapped to the text of its most recent functional
1270    assignment.
1271    
1272    =over 4
1273    
1274    =item genomeID
1275    
1276    ID of the genome whose functional assignments are desired.
1277    
1278    =item RETURN
1279    
1280    Returns a reference to a hash which maps each feature to its most recent
1281    functional assignment.
1282    
1283    =back
1284    
1285    =cut
1286    
1287    sub GenomeAssignments {
1288        # Get the parameters.
1289        my ($self, $genomeID) = @_;
1290        # Declare the return variable.
1291        my $retVal = {};
1292        # Query the genome's features.
1293        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1294                               [$genomeID]);
1295        # Loop through the features.
1296        while (my $data = $query->Fetch) {
1297            # Get the feature ID and assignment.
1298            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1299            if ($assignment) {
1300                $retVal->{$fid} = $assignment;
1301            }
1302        }
1303        # Return the result.
1304        return $retVal;
1305    }
1306    
1307  =head3 ContigLength  =head3 ContigLength
1308    
1309  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1310    
1311  Compute the length of a contig.  Compute the length of a contig.
1312    
# Line 810  Line 1326 
1326  #: Return Type $;  #: Return Type $;
1327  sub ContigLength {  sub ContigLength {
1328          # Get the parameters.          # Get the parameters.
1329          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
1330          # Get the contig's last sequence.          # Get the contig's last sequence.
1331          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
1332                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 822  Line 1337 
1337          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
1338          if ($sequence) {          if ($sequence) {
1339                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1340                  $retVal = $start + $len;          $retVal = $start + $len - 1;
1341        }
1342        # Return the result.
1343        return $retVal;
1344    }
1345    
1346    =head3 ClusterPEGs
1347    
1348        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1349    
1350    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1351    subsystem. In order for this to work properly, the subsystem object must have
1352    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1353    B<get_row> methods. This causes the cluster numbers to be pulled into the
1354    subsystem's color hash. If a PEG is not found in the color hash, it will not
1355    appear in the output sequence.
1356    
1357    =over 4
1358    
1359    =item sub
1360    
1361    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1362    method.
1363    
1364    =item pegs
1365    
1366    Reference to the list of PEGs to be clustered.
1367    
1368    =item RETURN
1369    
1370    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1371    
1372    =back
1373    
1374    =cut
1375    #: Return Type $@@;
1376    sub ClusterPEGs {
1377        # Get the parameters.
1378        my ($self, $sub, $pegs) = @_;
1379        # Declare the return variable.
1380        my $retVal = [];
1381        # Loop through the PEGs, creating arrays for each cluster.
1382        for my $pegID (@{$pegs}) {
1383            my $clusterNumber = $sub->get_cluster_number($pegID);
1384            # Only proceed if the PEG is in a cluster.
1385            if ($clusterNumber >= 0) {
1386                # Push this PEG onto the sub-list for the specified cluster number.
1387                push @{$retVal->[$clusterNumber]}, $pegID;
1388            }
1389          }          }
1390          # Return the result.          # Return the result.
1391          return $retVal;          return $retVal;
# Line 830  Line 1393 
1393    
1394  =head3 GenesInRegion  =head3 GenesInRegion
1395    
1396  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1397    
1398  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1399    
# Line 853  Line 1416 
1416  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
1417  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
1418  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
1419  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
1420    roughly by location.
1421    
1422  =back  =back
1423    
1424  =cut  =cut
1425  #: Return Type @;  
1426  sub GenesInRegion {  sub GenesInRegion {
1427          # Get the parameters.          # Get the parameters.
1428          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
1429          my ($contigID, $start, $stop) = @_;      # Get the maximum segment length.
1430        my $maximumSegmentLength = $self->MaxSegment;
1431        # Prime the values we'll use for the returned beginning and end.
1432        my @initialMinMax = ($self->ContigLength($contigID), 0);
1433        my ($min, $max) = @initialMinMax;
1434        # Get the overlapping features.
1435        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1436        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1437        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1438        # of the feature's locations.
1439        my %featureMap = ();
1440        # Loop through them to do the begin/end analysis.
1441        for my $featureObject (@featureObjects) {
1442            # Get the feature's location string. This may contain multiple actual locations.
1443            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1444            my @locationSegments = split /\s*,\s*/, $locations;
1445            # Loop through the locations.
1446            for my $locationSegment (@locationSegments) {
1447                # Construct an object for the location.
1448                my $locationObject = BasicLocation->new($locationSegment);
1449                # Merge the current segment's begin and end into the min and max.
1450                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1451                my ($beg, $end);
1452                if (exists $featureMap{$fid}) {
1453                    ($beg, $end) = @{$featureMap{$fid}};
1454                    $beg = $left if $left < $beg;
1455                    $end = $right if $right > $end;
1456                } else {
1457                    ($beg, $end) = ($left, $right);
1458                }
1459                $min = $beg if $beg < $min;
1460                $max = $end if $end > $max;
1461                # Store the feature's new extent back into the hash table.
1462                $featureMap{$fid} = [$beg, $end];
1463            }
1464        }
1465        # Now we must compute the list of the IDs for the features found. We start with a list
1466        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1467        # but the result of the sort will be the same.)
1468        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1469        # Now we sort by midpoint and yank out the feature IDs.
1470        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1471        # Return it along with the min and max.
1472        return (\@retVal, $min, $max);
1473    }
1474    
1475    =head3 GeneDataInRegion
1476    
1477        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1478    
1479    List the features which overlap a specified region in a contig.
1480    
1481    =over 4
1482    
1483    =item contigID
1484    
1485    ID of the contig containing the region of interest.
1486    
1487    =item start
1488    
1489    Offset of the first residue in the region of interest.
1490    
1491    =item stop
1492    
1493    Offset of the last residue in the region of interest.
1494    
1495    =item RETURN
1496    
1497    Returns a list of B<ERDBObjects> for the desired features. Each object will
1498    contain a B<Feature> record.
1499    
1500    =back
1501    
1502    =cut
1503    
1504    sub GeneDataInRegion {
1505        # Get the parameters.
1506        my ($self, $contigID, $start, $stop) = @_;
1507          # Get the maximum segment length.          # Get the maximum segment length.
1508          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
1509          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
1510          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1511        # ERDBObject from the query.
1512          my %featuresFound = ();          my %featuresFound = ();
1513          # Prime the values we'll use for the returned beginning and end.      # Create a table of parameters for the queries. Each query looks for features travelling in
         my ($min, $max) = ($self->ContigLength($contigID), 0);  
         # Create a table of parameters for each query. Each query looks for features travelling in  
1514          # 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,
1515          # 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
1516          # 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 1519 
1519          # Loop through the query parameters.          # Loop through the query parameters.
1520          for my $parms (values %queryParms) {          for my $parms (values %queryParms) {
1521                  # Create the query.                  # Create the query.
1522                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1523                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1524                          $parms);                          $parms);
1525                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1526                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1527                          # Get the data about this segment.                          # Get the data about this segment.
1528                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1529                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1530                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1531                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1532                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1533                          # length.                          # length.
1534                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1535                          if ($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.  
                                         $found = 1;  
                                 }  
                         }  
1536                          if ($found) {                          if ($found) {
1537                                  # Here we need to record the feature and update the minimum and maximum.                  # Save this feature in the result list.
1538                                  $featuresFound{$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; }  
1539                          }                          }
1540                  }                  }
1541          }          }
1542          # Compute a list of the IDs for the features found.      # Return the ERDB objects for the features found.
1543          my @list = (sort (keys %featuresFound));      return values %featuresFound;
         # Return it along with the min and max.  
         return (\@list, $min, $max);  
1544  }  }
1545    
1546  =head3 FType  =head3 FType
1547    
1548  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1549    
1550  Return the type of a feature.  Return the type of a feature.
1551    
# Line 944  Line 1566 
1566  #: Return Type $;  #: Return Type $;
1567  sub FType {  sub FType {
1568          # Get the parameters.          # Get the parameters.
1569          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1570          # Get the specified feature's type.          # Get the specified feature's type.
1571          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1572          # Return the result.          # Return the result.
# Line 954  Line 1575 
1575    
1576  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1577    
1578  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1579    
1580  Return the annotations of a feature.  Return the annotations of a feature.
1581    
# Line 964  Line 1585 
1585    
1586  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1587    
1588    =item rawFlag
1589    
1590    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1591    will be returned in human-readable form.
1592    
1593  =item RETURN  =item RETURN
1594    
1595  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.
1596    
1597  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1598    
1599  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1600    
1601  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1602    
# Line 982  Line 1608 
1608  #: Return Type @%;  #: Return Type @%;
1609  sub FeatureAnnotations {  sub FeatureAnnotations {
1610          # Get the parameters.          # Get the parameters.
1611          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1612          # 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.
1613          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1614                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 996  Line 1621 
1621                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1622                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1623                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1624            # Convert the time, if necessary.
1625            if (! $rawFlag) {
1626                $timeStamp = FriendlyTimestamp($timeStamp);
1627            }
1628                  # Assemble them into a hash.                  # Assemble them into a hash.
1629          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1630                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1631                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1632                  # Add it to the return list.                  # Add it to the return list.
1633                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1009  Line 1638 
1638    
1639  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1640    
1641  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1642    
1643  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
1644  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,
1645  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
1646  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,
1647  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.
1648  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
1649  functional assignments, we will only keep the most recent one.  recent one.
1650    
1651  =over 4  =over 4
1652    
# Line 1027  Line 1656 
1656    
1657  =item RETURN  =item RETURN
1658    
1659  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1660    
1661  =back  =back
1662    
# Line 1035  Line 1664 
1664  #: Return Type %;  #: Return Type %;
1665  sub AllFunctionsOf {  sub AllFunctionsOf {
1666          # Get the parameters.          # Get the parameters.
1667          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1668          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1669      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1670                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1671                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1672                                               'MadeAnnotation(from-link)']);
1673          # Declare the return hash.          # Declare the return hash.
1674          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1675      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1676      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1677          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1678      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1679          # Get the annotation fields.          # Get the annotation fields.
1680          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1681                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1682                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1683          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1684              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1685              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1686              # return hash.              # return hash.
1687                          $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1688                  }                  }
1689          }          }
1690          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1068  Line 1693 
1693    
1694  =head3 FunctionOf  =head3 FunctionOf
1695    
1696  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1697    
1698  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1699    
1700  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
1701  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
1702  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.  
1703    
1704  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
1705  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
1706  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
1707  is trusted.  is trusted.
1708    
1709  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.
1710  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.  
1711    
1712  =over 4  =over 4
1713    
# Line 1096  Line 1717 
1717    
1718  =item userID (optional)  =item userID (optional)
1719    
1720  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
1721  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1722    
1723  =item RETURN  =item RETURN
1724    
# Line 1109  Line 1730 
1730  #: Return Type $;  #: Return Type $;
1731  sub FunctionOf {  sub FunctionOf {
1732          # Get the parameters.          # Get the parameters.
1733          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1734      # Declare the return value.      # Declare the return value.
1735      my $retVal;      my $retVal;
1736      # Determine the ID type.      # Find a FIG ID for this feature.
1737      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1738          # Here we have a FIG feature ID. We must build the list of trusted      # Only proceed if we have an ID.
1739          # users.      if ($fid) {
1740            # Here we have a FIG feature ID.
1741            if (!$userID) {
1742                # Use the primary assignment.
1743                ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1744            } else {
1745                # We must build the list of trusted users.
1746          my %trusteeTable = ();          my %trusteeTable = ();
1747          # Check the user ID.          # Check the user ID.
1748          if (!$userID) {          if (!$userID) {
# Line 1138  Line 1764 
1764              }              }
1765          }          }
1766          # 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.
1767          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1768                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1769                                 [$featureID]);                                     [$fid]);
1770          my $timeSelected = 0;          my $timeSelected = 0;
1771          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1772          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1773              # Get the annotation text.              # Get the annotation text.
1774              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1775                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1776              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1777              my ($user, $type, $function) = split(/\n/, $text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1778              if ($type =~ m/^set $user function to$/i) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1779                    if ($actualUser) {
1780                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1781                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1782                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1783                      $retVal = $function;                      $retVal = $function;
1784                      $timeSelected = $time;                      $timeSelected = $time;
1785                  }                  }
1786              }              }
1787          }          }
1788      } else {          }
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1789      }      }
1790          # Return the assignment found.          # Return the assignment found.
1791          return $retVal;          return $retVal;
1792  }  }
1793    
1794    =head3 FunctionsOf
1795    
1796        my @functionList = $sprout->FunctionOf($featureID, $userID);
1797    
1798    Return the functional assignments of a particular feature.
1799    
1800    The functional assignment is handled differently depending on the type of feature. If
1801    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1802    assignment is a type of annotation. The format of an assignment is described in
1803    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1804    annotation itself because it's a text field; however, this is not a big problem because
1805    most features only have a small number of annotations.
1806    
1807    =over 4
1808    
1809    =item featureID
1810    
1811    ID of the feature whose functional assignments are desired.
1812    
1813    =item RETURN
1814    
1815    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1816    that user.
1817    
1818    =back
1819    
1820    =cut
1821    #: Return Type @@;
1822    sub FunctionsOf {
1823        # Get the parameters.
1824        my ($self, $featureID) = @_;
1825        # Declare the return value.
1826        my @retVal = ();
1827        # Convert to a FIG ID.
1828        my ($fid) = $self->FeaturesByAlias($featureID);
1829        # Only proceed if we found one.
1830        if ($fid) {
1831            # Here we have a FIG feature ID. We must build the list of trusted
1832            # users.
1833            my %trusteeTable = ();
1834            # Build a query for all of the feature's annotations, sorted by date.
1835            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1836                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1837                                   [$fid]);
1838            my $timeSelected = 0;
1839            # Loop until we run out of annotations.
1840            while (my $annotation = $query->Fetch()) {
1841                # Get the annotation text.
1842                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1843                                                                'Annotation(time)',
1844                                                                'MadeAnnotation(user)']);
1845                # Check to see if this is a functional assignment for a trusted user.
1846                my ($actualUser, $function) = _ParseAssignment($user, $text);
1847                if ($actualUser) {
1848                    # Here it is a functional assignment.
1849                    push @retVal, [$actualUser, $function];
1850                }
1851            }
1852        }
1853        # Return the assignments found.
1854        return @retVal;
1855    }
1856    
1857  =head3 BBHList  =head3 BBHList
1858    
1859  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1860    
1861  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
1862  on a specified target genome.  on a specified target genome.
# Line 1186  Line 1873 
1873    
1874  =item RETURN  =item RETURN
1875    
1876  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
1877  their best hits.  on the target genome.
1878    
1879  =back  =back
1880    
# Line 1195  Line 1882 
1882  #: Return Type %;  #: Return Type %;
1883  sub BBHList {  sub BBHList {
1884          # Get the parameters.          # Get the parameters.
1885          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1886          # Create the return structure.          # Create the return structure.
1887          my %retVal = ();          my %retVal = ();
1888          # Loop through the incoming features.          # Loop through the incoming features.
1889          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1890                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1891                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my $bbhData = FIGRules::BBHData($featureID);
1892                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1893                                                             [$featureID, $genomeID]);          my @found = ();
1894                  # Look for the best hit.          for my $bbh (@$bbhData) {
1895                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1896                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1897                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1898                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1899                }
1900                  }                  }
1901            $retVal{$featureID} = \@found;
1902          }          }
1903          # Return the mapping.          # Return the mapping.
1904          return \%retVal;          return \%retVal;
1905  }  }
1906    
1907  =head3 FeatureAliases  =head3 SimList
1908    
1909  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my %similarities = $sprout->SimList($featureID, $count);
1910    
1911  Return a list of the aliases for a specified feature.  Return a list of the similarities to the specified feature.
1912    
1913    This method just returns the bidirectional best hits for performance reasons.
1914    
1915  =over 4  =over 4
1916    
1917  =item featureID  =item featureID
1918    
1919  ID of the feature whose aliases are desired.  ID of the feature whose similarities are desired.
1920    
1921  =item RETURN  =item count
1922    
1923  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.  
1924    
1925  =back  =back
1926    
1927  =cut  =cut
1928  #: Return Type @;  #: Return Type %;
1929  sub FeatureAliases {  sub SimList {
1930          # Get the parameters.          # Get the parameters.
1931          my $self = shift @_;      my ($self, $featureID, $count) = @_;
1932          my ($featureID) = @_;      # Ask for the best hits.
1933          # Get the desired feature's aliases      my $lists = FIGRules::BBHData($featureID);
1934          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      # Create the return value.
1935        my %retVal = ();
1936        for my $tuple (@$lists) {
1937            $retVal{$tuple->[0]} = $tuple->[1];
1938        }
1939          # Return the result.          # Return the result.
1940          return @retVal;      return %retVal;
1941  }  }
1942    
1943  =head3 GenomeOf  =head3 IsComplete
1944    
1945  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $flag = $sprout->IsComplete($genomeID);
1946    
1947  Return the genome that contains a specified feature.  Return TRUE if the specified genome is complete, else FALSE.
1948    
1949  =over 4  =over 4
1950    
1951  =item featureID  =item genomeID
1952    
1953  ID of the feature whose genome is desired.  ID of the genome whose completeness status is desired.
1954    
1955  =item RETURN  =item RETURN
1956    
1957  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
1958  an undefined value.  not found.
1959    
1960  =back  =back
1961    
1962  =cut  =cut
1963  #: Return Type $;  #: Return Type $;
1964  sub GenomeOf {  sub IsComplete {
1965          # Get the parameters.          # Get the parameters.
1966          my $self = shift @_;      my ($self, $genomeID) = @_;
1967          my ($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.  
1968          my $retVal;          my $retVal;
1969          # Get the genome ID.      # Get the genome's data.
1970          if (my $relationship = $query->Fetch()) {      my $genomeData = $self->_GenomeData($genomeID);
1971                  ($retVal) = $relationship->Value('HasContig(from-link)');      # Only proceed if it exists.
1972        if (defined $genomeData) {
1973            # The genome exists, so get the completeness flag.
1974            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1975          }          }
1976          # Return the value found.      # Return the result.
1977          return $retVal;          return $retVal;
1978  }  }
1979    
1980  =head3 CoupledFeatures  =head3 FeatureAliases
1981    
1982  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1983    
1984  Return the features functionally coupled with a specified feature. Features are considered  Return a list of the aliases for a specified feature.
 functionally coupled if they tend to be clustered on the same chromosome.  
1985    
1986  =over 4  =over 4
1987    
1988  =item featureID  =item featureID
1989    
1990  ID of the feature whose functionally-coupled brethren are desired.  ID of the feature whose aliases are desired.
1991    
1992  =item RETURN  =item RETURN
1993    
1994  A hash mapping the functionally-coupled feature IDs to the coupling score.  Returns a list of the feature's aliases. If the feature is not found or has no aliases, it will
1995    return an empty list.
1996    
1997  =back  =back
1998    
1999  =cut  =cut
2000  #: Return Type %;  #: Return Type @;
2001  sub CoupledFeatures {  sub FeatureAliases {
2002          # Get the parameters.      # Get the parameters.
2003          my $self = shift @_;      my ($self, $featureID) = @_;
2004          my ($featureID) = @_;      # Get the desired feature's aliases
2005          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
2006          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      # Return the result.
2007          # (B,A) will also be found.      return @retVal;
2008          my $query = $self->Get(['IsClusteredOnChromosomeWith'],  }
2009                                                     "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
2010          # This value will be set to TRUE if we find at least one coupled feature.  =head3 GenomeOf
2011          my $found = 0;  
2012          # Create the return hash.      my $genomeID = $sprout->GenomeOf($featureID);
2013    
2014    Return the genome that contains a specified feature or contig.
2015    
2016    =over 4
2017    
2018    =item featureID
2019    
2020    ID of the feature or contig whose genome is desired.
2021    
2022    =item RETURN
2023    
2024    Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
2025    found, returns an undefined value.
2026    
2027    =back
2028    
2029    =cut
2030    #: Return Type $;
2031    sub GenomeOf {
2032        # Get the parameters.
2033        my ($self, $featureID) = @_;
2034        # Declare the return value.
2035        my $retVal;
2036        # Parse the genome ID from the feature ID.
2037        if ($featureID =~ /^fig\|(\d+\.\d+)/) {
2038            $retVal = $1;
2039        } else {
2040            # Find the feature by alias.
2041            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
2042            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
2043                $retVal = $1;
2044            }
2045        }
2046        # Return the value found.
2047        return $retVal;
2048    }
2049    
2050    =head3 CoupledFeatures
2051    
2052        my %coupleHash = $sprout->CoupledFeatures($featureID);
2053    
2054    Return the features functionally coupled with a specified feature. Features are considered
2055    functionally coupled if they tend to be clustered on the same chromosome.
2056    
2057    =over 4
2058    
2059    =item featureID
2060    
2061    ID of the feature whose functionally-coupled brethren are desired.
2062    
2063    =item RETURN
2064    
2065    A hash mapping the functionally-coupled feature IDs to the coupling score.
2066    
2067    =back
2068    
2069    =cut
2070    #: Return Type %;
2071    sub CoupledFeatures {
2072        # Get the parameters.
2073        my ($self, $featureID) = @_;
2074        # Ask the coupling server for the data.
2075        Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2076        my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2077        Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2078        # Form them into a hash.
2079          my %retVal = ();          my %retVal = ();
2080          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2081          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2082                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
2083                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
2084                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
2085                  $found = 1;              $retVal{$featureID2} = $score;
2086          }          }
         # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
         # the incoming feature as well.  
         if ($found) {  
                 $retVal{$featureID} = 9999;  
2087      }      }
2088          # Return the hash.          # Return the hash.
2089          return %retVal;          return %retVal;
2090  }  }
2091    
2092  =head3 GetEntityTypes  =head3 CouplingEvidence
2093    
2094        my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2095    
2096    Return the evidence for a functional coupling.
2097    
2098    A pair of features is considered evidence of a coupling between two other
2099    features if they occur close together on a contig and both are similar to
2100    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
2101    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
2102    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
2103    similar to B<A2>.
2104    
2105    The score of a coupling is determined by the number of pieces of evidence
2106    that are considered I<representative>. If several evidence items belong to
2107    a group of genomes that are close to each other, only one of those items
2108    is considered representative. The other evidence items are presumed to be
2109    there because of the relationship between the genomes rather than because
2110    the two proteins generated by the features have a related functionality.
2111    
2112    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
2113    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
2114    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
2115    and FALSE otherwise.
2116    
2117    =over 4
2118    
2119    =item peg1
2120    
2121    ID of the feature of interest.
2122    
2123    =item peg2
2124    
2125    ID of a feature functionally coupled to the feature of interest.
2126    
2127    =item RETURN
2128    
2129    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
2130    of interest, a feature similar to the functionally coupled feature, and a flag
2131    that is TRUE for a representative piece of evidence and FALSE otherwise.
2132    
2133    =back
2134    
2135    =cut
2136    #: Return Type @@;
2137    sub CouplingEvidence {
2138        # Get the parameters.
2139        my ($self, $peg1, $peg2) = @_;
2140        # Declare the return variable.
2141        my @retVal = ();
2142        # Get the coupling and evidence data.
2143        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2144        # Loop through the raw data, saving the ones that are in NMPDR genomes.
2145        for my $rawTuple (@rawData) {
2146            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2147                push @retVal, $rawTuple;
2148            }
2149        }
2150        # Return the result.
2151        return @retVal;
2152    }
2153    
2154    =head3 GetSynonymGroup
2155    
2156        my $id = $sprout->GetSynonymGroup($fid);
2157    
2158    Return the synonym group name for the specified feature.
2159    
2160    =over 4
2161    
2162    =item fid
2163    
2164    ID of the feature whose synonym group is desired.
2165    
2166    =item RETURN
2167    
2168    The name of the synonym group to which the feature belongs. If the feature does
2169    not belong to a synonym group, the feature ID itself is returned.
2170    
2171    =back
2172    
2173    =cut
2174    
2175    sub GetSynonymGroup {
2176        # Get the parameters.
2177        my ($self, $fid) = @_;
2178        # Declare the return variable.
2179        my $retVal;
2180        # Find the synonym group.
2181        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2182                                       [$fid], 'IsSynonymGroupFor(from-link)');
2183        # Check to see if we found anything.
2184        if (@groups) {
2185            $retVal = $groups[0];
2186        } else {
2187            $retVal = $fid;
2188        }
2189        # Return the result.
2190        return $retVal;
2191    }
2192    
2193    =head3 GetBoundaries
2194    
2195        my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2196    
2197  C<< my @entityList = $sprout->GetEntityTypes(); >>  Determine the begin and end boundaries for the locations in a list. All of the
2198    locations must belong to the same contig and have mostly the same direction in
2199    order for this method to produce a meaningful result. The resulting
2200    begin/end pair will contain all of the bases in any of the locations.
2201    
2202  Return the list of supported entity types.  =over 4
2203    
2204    =item locList
2205    
2206    List of locations to process.
2207    
2208    =item RETURN
2209    
2210    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2211    and the ending boundary. The beginning boundary will be left of the
2212    end for mostly-forward locations and right of the end for mostly-backward
2213    locations.
2214    
2215    =back
2216    
2217  =cut  =cut
2218  #: Return Type @;  
2219  sub GetEntityTypes {  sub GetBoundaries {
2220          # Get the parameters.          # Get the parameters.
2221          my $self = shift @_;      my ($self, @locList) = @_;
2222          # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
2223          my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
2224          # Get its entity type list.      # Get the last location and parse it.
2225          my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
2226        # Prime the loop with its data.
2227        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2228        # Count its direction.
2229        $counts{$locObject->Dir}++;
2230        # Loop through the remaining locations. Note that in most situations, this loop
2231        # will not iterate at all, because most of the time we will be dealing with a
2232        # singleton list.
2233        for my $loc (@locList) {
2234            # Create a location object.
2235            my $locObject = BasicLocation->new($loc);
2236            # Count the direction.
2237            $counts{$locObject->Dir}++;
2238            # Get the left end and the right end.
2239            my $left = $locObject->Left;
2240            my $right = $locObject->Right;
2241            # Merge them into the return variables.
2242            if ($left < $beg) {
2243                $beg = $left;
2244            }
2245            if ($right > $end) {
2246                $end = $right;
2247            }
2248        }
2249        # If the most common direction is reverse, flip the begin and end markers.
2250        if ($counts{'-'} > $counts{'+'}) {
2251            ($beg, $end) = ($end, $beg);
2252        }
2253        # Return the result.
2254        return ($contig, $beg, $end);
2255  }  }
2256    
2257  =head3 ReadFasta  =head3 ReadFasta
2258    
2259  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2260    
2261  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2262  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1395  Line 2298 
2298                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2299                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2300                          if ($id) {                          if ($id) {
2301                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
2302                          }                          }
2303                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2304                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2305                  } else {                  } else {
2306                          # 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.
2307                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
2308                # case.
2309                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2310                          $sequence .= $1;                          $sequence .= $1;
2311                  }                  }
2312          }          }
2313          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2314          if ($sequence) {          if ($sequence) {
2315                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
2316          }          }
2317        # Close the file.
2318        close FASTAFILE;
2319          # Return the hash constructed from the file.          # Return the hash constructed from the file.
2320          return %retVal;          return %retVal;
2321  }  }
2322    
2323  =head3 FormatLocations  =head3 FormatLocations
2324    
2325  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2326    
2327  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
2328  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
2329  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,
2330    it will not be changed; otherwise, it will be converted. This method can also be used to
2331    perform the reverse task-- insuring that all the locations are in the old format.
2332    
2333  =over 4  =over 4
2334    
# Line 1447  Line 2355 
2355  #: Return Type @;  #: Return Type @;
2356  sub FormatLocations {  sub FormatLocations {
2357          # Get the parameters.          # Get the parameters.
2358          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
2359          # Create the return list.          # Create the return list.
2360          my @retVal = ();          my @retVal = ();
2361          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
2362          if ($locations eq '') {          if ($locations eq '') {
2363              confess "No locations specified.";          Confess("No locations specified.");
2364          } else {          } else {
2365                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
2366                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1480  Line 2387 
2387    
2388  =head3 DumpData  =head3 DumpData
2389    
2390  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2391    
2392  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.
2393    
# Line 1488  Line 2395 
2395    
2396  sub DumpData {  sub DumpData {
2397          # Get the parameters.          # Get the parameters.
2398          my $self = shift @_;      my ($self) = @_;
2399          # Get the data directory name.          # Get the data directory name.
2400          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2401          # Dump the relations.          # Dump the relations.
2402          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2403  }  }
2404    
2405  =head3 XMLFileName  =head3 XMLFileName
2406    
2407  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2408    
2409  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2410    
2411  =cut  =cut
2412  #: Return Type $;  #: Return Type $;
2413  sub XMLFileName {  sub XMLFileName {
2414          my $self = shift @_;      my ($self) = @_;
2415          return $self->{_xmlName};          return $self->{_xmlName};
2416  }  }
2417    
2418    =head3 GetGenomeNameData
2419    
2420        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2421    
2422    Return the genus, species, and unique characterization for a genome. This
2423    is similar to L</GenusSpecies>, with the exception that it returns the
2424    values in three seperate fields.
2425    
2426    =over 4
2427    
2428    =item genomeID
2429    
2430    ID of the genome whose name data is desired.
2431    
2432    =item RETURN
2433    
2434    Returns a three-element list, consisting of the genus, species, and strain
2435    of the specified genome. If the genome is not found, an error occurs.
2436    
2437    =back
2438    
2439    =cut
2440    
2441    sub GetGenomeNameData {
2442        # Get the parameters.
2443        my ($self, $genomeID) = @_;
2444        # Declare the return variables.
2445        my ($genus, $species, $strain);
2446        # Get the genome's data.
2447        my $genomeData = $self->_GenomeData($genomeID);
2448        # Only proceed if the genome exists.
2449        if (defined $genomeData) {
2450            # Get the desired values.
2451            ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2452                                                               'Genome(species)',
2453                                                               'Genome(unique-characterization)']);
2454        } else {
2455            # Throw an error because they were not found.
2456            Confess("Genome $genomeID not found in database.");
2457        }
2458        # Return the results.
2459        return ($genus, $species, $strain);
2460    }
2461    
2462    =head3 GetGenomeByNameData
2463    
2464        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2465    
2466    Return a list of the IDs of the genomes with the specified genus,
2467    species, and strain. In almost every case, there will be either zero or
2468    one IDs returned; however, two or more IDs could be returned if there are
2469    multiple versions of the genome in the database.
2470    
2471    =over 4
2472    
2473    =item genus
2474    
2475    Genus of the desired genome.
2476    
2477    =item species
2478    
2479    Species of the desired genome.
2480    
2481    =item strain
2482    
2483    Strain (unique characterization) of the desired genome. This may be an empty
2484    string, in which case it is presumed that the desired genome has no strain
2485    specified.
2486    
2487    =item RETURN
2488    
2489    Returns a list of the IDs of the genomes having the specified genus, species, and
2490    strain.
2491    
2492    =back
2493    
2494    =cut
2495    
2496    sub GetGenomeByNameData {
2497        # Get the parameters.
2498        my ($self, $genus, $species, $strain) = @_;
2499        # Try to find the genomes.
2500        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2501                                    [$genus, $species, $strain], 'Genome(id)');
2502        # Return the result.
2503        return @retVal;
2504    }
2505    
2506  =head3 Insert  =head3 Insert
2507    
2508  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2509    
2510  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
2511  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 2514 
2514  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
2515  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>.
2516    
2517  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']});
2518    
2519  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
2520  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>.
2521    
2522  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'});
2523    
2524  =over 4  =over 4
2525    
# Line 1542  Line 2537 
2537  #: Return Type ;  #: Return Type ;
2538  sub Insert {  sub Insert {
2539          # Get the parameters.          # Get the parameters.
2540          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
2541          # Call the underlying method.          # Call the underlying method.
2542          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2543  }  }
2544    
2545  =head3 Annotate  =head3 Annotate
2546    
2547  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2548    
2549  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
2550  specified feature and user.  specified feature and user.
# Line 1584  Line 2578 
2578  #: Return Type $;  #: Return Type $;
2579  sub Annotate {  sub Annotate {
2580          # Get the parameters.          # Get the parameters.
2581          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
2582          # Create the annotation ID.          # Create the annotation ID.
2583          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
2584          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1605  Line 2598 
2598    
2599  =head3 AssignFunction  =head3 AssignFunction
2600    
2601  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2602    
2603  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
2604  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.  
2605    
2606  =over 4  =over 4
2607    
# Line 1619  Line 2611 
2611    
2612  =item user  =item user
2613    
2614  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>.
2615    
2616  =item function  =item function
2617    
2618  Text of the function being assigned.  Text of the function being assigned.
2619    
2620    =item assigningUser (optional)
2621    
2622    Name of the individual user making the assignment. If omitted, defaults to the user group.
2623    
2624  =item RETURN  =item RETURN
2625    
2626  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1635  Line 2631 
2631  #: Return Type $;  #: Return Type $;
2632  sub AssignFunction {  sub AssignFunction {
2633          # Get the parameters.          # Get the parameters.
2634          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2635          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2636        if (! $assigningUser) {
2637            $assigningUser = $user;
2638        }
2639          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2640          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2641          # Get the current time.          # Get the current time.
2642          my $now = time;          my $now = time;
2643          # Declare the return variable.          # Declare the return variable.
# Line 1659  Line 2658 
2658    
2659  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2660    
2661  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2662    
2663  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
2664  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 2682 
2682  #: Return Type @;  #: Return Type @;
2683  sub FeaturesByAlias {  sub FeaturesByAlias {
2684          # Get the parameters.          # Get the parameters.
2685          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2686          # Declare the return variable.          # Declare the return variable.
2687          my @retVal = ();          my @retVal = ();
2688          # Parse the alias.          # Parse the alias.
# Line 1694  Line 2692 
2692                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2693          } else {          } else {
2694                  # 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.
2695                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2696          }          }
2697          # Return the result.          # Return the result.
2698          return @retVal;          return @retVal;
2699  }  }
2700    
 =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;  
 }  
   
2701  =head3 FeatureTranslation  =head3 FeatureTranslation
2702    
2703  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2704    
2705  Return the translation of a feature.  Return the translation of a feature.
2706    
# Line 1757  Line 2720 
2720  #: Return Type $;  #: Return Type $;
2721  sub FeatureTranslation {  sub FeatureTranslation {
2722          # Get the parameters.          # Get the parameters.
2723          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2724          # Get the specified feature's translation.          # Get the specified feature's translation.
2725          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2726          return $retVal;          return $retVal;
# Line 1766  Line 2728 
2728    
2729  =head3 Taxonomy  =head3 Taxonomy
2730    
2731  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2732    
2733  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
2734  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>,
2735  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2736    
2737  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2738    
2739  =over 4  =over 4
2740    
# Line 1790  Line 2752 
2752  #: Return Type @;  #: Return Type @;
2753  sub Taxonomy {  sub Taxonomy {
2754          # Get the parameters.          # Get the parameters.
2755          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
         # Find the specified genome's taxonomy string.  
         my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2756          # Declare the return variable.          # Declare the return variable.
2757          my @retVal = ();          my @retVal = ();
2758          # If we found the genome, return its taxonomy string.      # Get the genome data.
2759          if ($list) {      my $genomeData = $self->_GenomeData($genome);
2760                  @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2761        if (defined $genomeData) {
2762            # Create the taxonomy from the taxonomy string.
2763            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2764          } else {          } else {
2765            # Genome doesn't exist, so emit a warning.
2766                  Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);                  Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);
2767          }          }
2768          # Return the value found.          # Return the value found.
# Line 1808  Line 2771 
2771    
2772  =head3 CrudeDistance  =head3 CrudeDistance
2773    
2774  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2775    
2776  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
2777  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 2797 
2797  #: Return Type $;  #: Return Type $;
2798  sub CrudeDistance {  sub CrudeDistance {
2799          # Get the parameters.          # Get the parameters.
2800          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2801          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2802          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2803          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1845  Line 2807 
2807          }          }
2808          my @taxA = $self->Taxonomy($genomeA);          my @taxA = $self->Taxonomy($genomeA);
2809          my @taxB = $self->Taxonomy($genomeB);          my @taxB = $self->Taxonomy($genomeB);
2810          # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2811          # taxonomies.      my $retVal = FIGRules::CrudeDistanceFormula(\@taxA, \@taxB);
         my $retVal = 1.0;  
         # Initialize the subtraction amount. This amount determines the distance reduction caused  
         # by a mismatch at the current level.  
         my $v = 0.5;  
         # Loop through the taxonomies.  
         for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) {  
             $retVal -= $v;  
                 $v /= 2;  
         }  
2812      return $retVal;      return $retVal;
2813  }  }
2814    
2815  =head3 RoleName  =head3 RoleName
2816    
2817  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2818    
2819  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
2820  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 2835 
2835  #: Return Type $;  #: Return Type $;
2836  sub RoleName {  sub RoleName {
2837          # Get the parameters.          # Get the parameters.
2838          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2839          # Get the specified role's name.          # Get the specified role's name.
2840          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2841          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1896  Line 2848 
2848    
2849  =head3 RoleDiagrams  =head3 RoleDiagrams
2850    
2851  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2852    
2853  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2854    
# Line 1916  Line 2868 
2868  #: Return Type @;  #: Return Type @;
2869  sub RoleDiagrams {  sub RoleDiagrams {
2870          # Get the parameters.          # Get the parameters.
2871          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2872          # Query for the diagrams.          # Query for the diagrams.
2873          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2874                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1927  Line 2878 
2878    
2879  =head3 FeatureProperties  =head3 FeatureProperties
2880    
2881  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2882    
2883  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
2884  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
2885  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
2886  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
2887  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.  
2888    
2889  =over 4  =over 4
2890    
# Line 1945  Line 2894 
2894    
2895  =item RETURN  =item RETURN
2896    
2897  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.  
2898    
2899  =back  =back
2900    
# Line 1954  Line 2902 
2902  #: Return Type @@;  #: Return Type @@;
2903  sub FeatureProperties {  sub FeatureProperties {
2904          # Get the parameters.          # Get the parameters.
2905          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2906          # Get the properties.          # Get the properties.
2907          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->ca->GetAttributes($featureID);
2908                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2909                                                           'HasProperty(evidence)']);      my @retVal = ();
2910        for my $attributeRow (@attributes) {
2911            shift @{$attributeRow};
2912            push @retVal, $attributeRow;
2913        }
2914          # Return the resulting list.          # Return the resulting list.
2915          return @retVal;          return @retVal;
2916  }  }
2917    
2918  =head3 DiagramName  =head3 DiagramName
2919    
2920  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2921    
2922  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2923    
# Line 1986  Line 2937 
2937  #: Return Type $;  #: Return Type $;
2938  sub DiagramName {  sub DiagramName {
2939          # Get the parameters.          # Get the parameters.
2940          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2941          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2942          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2943          return $retVal;          return $retVal;
2944  }  }
2945    
2946    =head3 PropertyID
2947    
2948        my $id = $sprout->PropertyID($propName, $propValue);
2949    
2950    Return the ID of the specified property name and value pair, if the
2951    pair exists. Only a small subset of the FIG attributes are stored as
2952    Sprout properties, mostly for use in search optimization.
2953    
2954    =over 4
2955    
2956    =item propName
2957    
2958    Name of the desired property.
2959    
2960    =item propValue
2961    
2962    Value expected for the desired property.
2963    
2964    =item RETURN
2965    
2966    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2967    
2968    =back
2969    
2970    =cut
2971    
2972    sub PropertyID {
2973        # Get the parameters.
2974        my ($self, $propName, $propValue) = @_;
2975        # Try to find the ID.
2976        my ($retVal) = $self->GetFlat(['Property'],
2977                                      "Property(property-name) = ? AND Property(property-value) = ?",
2978                                      [$propName, $propValue], 'Property(id)');
2979        # Return the result.
2980        return $retVal;
2981    }
2982    
2983  =head3 MergedAnnotations  =head3 MergedAnnotations
2984    
2985  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2986    
2987  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2988  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2019  Line 3006 
3006  #: Return Type @;  #: Return Type @;
3007  sub MergedAnnotations {  sub MergedAnnotations {
3008          # Get the parameters.          # Get the parameters.
3009          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
3010          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
3011          my @tuples = ();          my @tuples = ();
3012          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2045  Line 3031 
3031    
3032  =head3 RoleNeighbors  =head3 RoleNeighbors
3033    
3034  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
3035    
3036  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
3037  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 3054 
3054  #: Return Type @;  #: Return Type @;
3055  sub RoleNeighbors {  sub RoleNeighbors {
3056          # Get the parameters.          # Get the parameters.
3057          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
3058          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
3059          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
3060                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2089  Line 3074 
3074    
3075  =head3 FeatureLinks  =head3 FeatureLinks
3076    
3077  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3078    
3079  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
3080  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 3096 
3096  #: Return Type @;  #: Return Type @;
3097  sub FeatureLinks {  sub FeatureLinks {
3098          # Get the parameters.          # Get the parameters.
3099          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
3100          # Get the feature's links.          # Get the feature's links.
3101          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
3102          # Return the feature's links.          # Return the feature's links.
# Line 2121  Line 3105 
3105    
3106  =head3 SubsystemsOf  =head3 SubsystemsOf
3107    
3108  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3109    
3110  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
3111  to the role the feature performs.  to the roles the feature performs.
3112    
3113  =over 4  =over 4
3114    
# Line 2134  Line 3118 
3118    
3119  =item RETURN  =item RETURN
3120    
3121  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.
3122    
3123  =back  =back
3124    
3125  =cut  =cut
3126  #: Return Type %;  #: Return Type %@;
3127  sub SubsystemsOf {  sub SubsystemsOf {
3128          # Get the parameters.          # Get the parameters.
3129          my $self = shift @_;      my ($self, $featureID) = @_;
3130          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
3131          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
3132                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
3133                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3134          # Create the return value.          # Create the return value.
3135          my %retVal = ();          my %retVal = ();
3136        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3137        # in two spreadsheet cells.
3138        my %dupHash = ();
3139          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
3140          for my $record (@subsystems) {          for my $record (@subsystems) {
3141                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
3142            my ($subsys, $role) = @{$record};
3143            # Insure it's the first time for both.
3144            my $dupKey = "$subsys\n$role";
3145            if (! exists $dupHash{"$subsys\n$role"}) {
3146                $dupHash{$dupKey} = 1;
3147                push @{$retVal{$subsys}}, $role;
3148            }
3149          }          }
3150          # Return the hash.          # Return the hash.
3151          return %retVal;          return %retVal;
3152  }  }
3153    
3154  =head3 RelatedFeatures  =head3 SubsystemList
3155    
3156  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3157    
3158  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
3159  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
3160  an empty list will be returned.  subsystem names, not the roles.
3161    
3162  =over 4  =over 4
3163    
3164  =item featureID  =item featureID
3165    
3166  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.  
3167    
3168  =item RETURN  =item RETURN
3169    
3170  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.
3171    
3172  =back  =back
3173    
3174  =cut  =cut
3175  #: Return Type @;  #: Return Type @;
3176  sub RelatedFeatures {  sub SubsystemList {
3177          # Get the parameters.          # Get the parameters.
3178          my $self = shift @_;      my ($self, $featureID) = @_;
3179          my ($featureID, $function, $userID) = @_;      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3180          # Get a list of the features that are BBHs of the incoming feature.      # the Sprout database!
3181          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3182                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3183                                                                           'IsBidirectionalBestHitOf(to-link)');      # Return the result, sorted.
3184          # 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;  
3185  }  }
3186    
3187  =head3 TaxonomySort  =head3 GenomeSubsystemData
3188    
3189  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3190    
3191  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a hash mapping genome features to their subsystem roles.
 genome. This will cause genomes from similar organisms to float close to each other.  
   
 This task could almost be handled by the database; however, the taxonomy string in the  
 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.  
3192    
3193  =over 4  =over 4
3194    
3195  =item $featureIDs  =item genomeID
3196    
3197  List of features to be taxonomically sorted.  ID of the genome whose subsystem feature map is desired.
3198    
3199  =item RETURN  =item RETURN
3200    
3201  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
3202    2-tuple contains a subsystem name followed by a role ID.
3203    
3204  =back  =back
3205    
3206  =cut  =cut
3207  #: Return Type @;  
3208  sub TaxonomySort {  sub GenomeSubsystemData {
3209          # Get the parameters.          # Get the parameters.
3210          my $self = shift @_;      my ($self, $genomeID) = @_;
3211          my ($featureIDs) = @_;      # Declare the return variable.
3212          # Create the working hash table.      my %retVal = ();
3213          my %hashBuffer = ();      # Get a list of the genome features that participate in subsystems. For each
3214          # Loop through the features.      # feature we get its subsystem ID and the corresponding roles.
3215          for my $fid (@{$featureIDs}) {      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3216                  # Get the taxonomy of the feature's genome.                                   "HasFeature(from-link) = ?", [$genomeID],
3217                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3218                                                                                  [$fid], 'Genome(taxonomy)');      # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3219                  # Add this feature to the hash buffer.      # a non-negative variant code.
3220                  if (exists $hashBuffer{$taxonomy}) {      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3221                          push @{$hashBuffer{$taxonomy}}, $fid;                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3222                  } else {                                                  [$genomeID], 'ParticipatesIn(to-link)');
3223                          $hashBuffer{$taxonomy} = [$fid];      # We loop through @roleData to build the hash.
3224                  }      for my $roleEntry (@roleData) {
3225            # Get the data for this feature and cell.
3226            my ($fid, $role, $subsys) = @{$roleEntry};
3227            Trace("Subsystem for $fid is $subsys.") if T(4);
3228            # Check the subsystem;
3229            if ($subs{$subsys}) {
3230                Trace("Subsystem found.") if T(4);
3231                # Insure this feature has an entry in the return hash.
3232                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3233                # Merge in this new data.
3234                push @{$retVal{$fid}}, [$subsys, $role];
3235          }          }
         # Sort the keys and get the elements.  
         my @retVal = ();  
         for my $taxon (sort keys %hashBuffer) {  
                 push @retVal, @{$hashBuffer{$taxon}};  
3236          }          }
3237          # Return the result.          # Return the result.
3238          return @retVal;      return %retVal;
3239  }  }
3240    
3241  =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.  
3242    
3243  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.  
3244    
3245  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
3246    have been assigned the specified function by the specified user. If no such features exists,
3247    an empty list will be returned.
3248    
3249  =over 4  =over 4
3250    
3251  =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  
3252    
3253  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.
3254    
3255  =item fields  =item function
3256    
3257  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
3258    features should be selected.
3259    
3260  =item count  =item userID
3261    
3262  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.
3263    
3264  =item RETURN  =item RETURN
3265    
3266  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.  
3267    
3268  =back  =back
3269    
3270  =cut  =cut
3271  #: Return Type @@;  #: Return Type @;
3272  sub GetAll {  sub RelatedFeatures {
3273          # Get the parameters.          # Get the parameters.
3274          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
3275          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Get a list of the features that are BBHs of the incoming feature.
3276          # Create the query.      my $bbhData = FIGRules::BBHData($featureID);
3277          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @bbhFeatures = map { $_->[0] } @$bbhData;
3278          # Set up a counter of the number of records read.      # Now we loop through the features, pulling out the ones that have the correct
3279          my $fetched = 0;      # functional assignment.
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
3280          my @retVal = ();          my @retVal = ();
3281          while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {      for my $bbhFeature (@bbhFeatures) {
3282                  my @rowData = $row->Values($fields);          # Get this feature's functional assignment.
3283                  push @retVal, \@rowData;          my $newFunction = $self->FunctionOf($bbhFeature, $userID);
3284                  $fetched++;          # If it matches, add it to the result list.
3285            if ($newFunction eq $function) {
3286                push @retVal, $bbhFeature;
3287          }          }
3288          # Return the resulting list.      }
3289        # Return the result list.
3290          return @retVal;          return @retVal;
3291  }  }
3292    
3293  =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.  
3294    
3295  =item filterClause      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3296    
3297  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
3298  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.  
3299    
3300  =item parameterList  This task could almost be handled by the database; however, the taxonomy string in the
3301    database is a text field and can't be indexed. Instead, we create a hash table that maps
3302    taxonomy strings to lists of features. We then process the hash table using a key sort
3303    and merge the feature lists together to create the output.
3304    
3305  List of the parameters to be substituted in for the parameters marks in the filter clause.  =over 4
3306    
3307  =item field  =item $featureIDs
3308    
3309  Name of the field to be used to get the elements of the list returned.  List of features to be taxonomically sorted.
3310    
3311  =item RETURN  =item RETURN
3312    
3313  Returns a list of values.  Returns the list of features sorted by the taxonomies of the containing genomes.
3314    
3315  =back  =back
3316    
3317  =cut  =cut
3318  #: Return Type @;  #: Return Type @;
3319  sub GetFlat {  sub TaxonomySort {
3320          # Get the parameters.          # Get the parameters.
3321          my $self = shift @_;      my ($self, $featureIDs) = @_;
3322          my ($objectNames, $filterClause, $parameterList, $field) = @_;      # Create the working hash table.
3323          # Construct the query.      my %hashBuffer = ();
3324          my $query = $self->Get($objectNames, $filterClause, $parameterList);      # Loop through the features.
3325          # Create the result list.      for my $fid (@{$featureIDs}) {
3326            # Get the taxonomy of the feature's genome.
3327            my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3328                                            [$fid], 'Genome(taxonomy)');
3329            # Add this feature to the hash buffer.
3330            push @{$hashBuffer{$taxonomy}}, $fid;
3331        }
3332        # Sort the keys and get the elements.
3333          my @retVal = ();          my @retVal = ();
3334          # Loop through the records, adding the field values found to the result list.      for my $taxon (sort keys %hashBuffer) {
3335          while (my $row = $query->Fetch()) {          push @retVal, @{$hashBuffer{$taxon}};
                 push @retVal, $row->Value($field);  
3336          }          }
3337          # Return the list created.      # Return the result.
3338          return @retVal;          return @retVal;
3339  }  }
3340    
3341  =head3 Protein  =head3 Protein
3342    
3343  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3344    
3345  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3346    
# Line 2471  Line 3410 
3410          # Loop through the input triples.          # Loop through the input triples.
3411          my $n = length $sequence;          my $n = length $sequence;
3412          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3413                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3414                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3415            my $triple = uc substr($sequence, $i, 3);
3416                  # Translate it using the table.                  # Translate it using the table.
3417                  my $protein = "X";                  my $protein = "X";
3418                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2486  Line 3426 
3426    
3427  =head3 LoadInfo  =head3 LoadInfo
3428    
3429  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3430    
3431  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
3432  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 3436 
3436  #: Return Type @;  #: Return Type @;
3437  sub LoadInfo {  sub LoadInfo {
3438          # Get the parameters.          # Get the parameters.
3439          my $self = shift @_;      my ($self) = @_;
3440          # 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.
3441          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3442          # Concatenate the table names.          # Concatenate the table names.
3443          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3444          # Return the result.          # Return the result.
3445          return @retVal;          return @retVal;
3446  }  }
3447    
3448    =head3 BBHMatrix
3449    
3450        my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3451    
3452    Find all the bidirectional best hits for the features of a genome in a
3453    specified list of target genomes. The return value will be a hash mapping
3454    features in the original genome to their bidirectional best hits in the
3455    target genomes.
3456    
3457    =over 4
3458    
3459    =item genomeID
3460    
3461    ID of the genome whose features are to be examined for bidirectional best hits.
3462    
3463    =item cutoff
3464    
3465    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3466    
3467    =item targets
3468    
3469    List of target genomes. Only pairs originating in the original
3470    genome and landing in one of the target genomes will be returned.
3471    
3472    =item RETURN
3473    
3474    Returns a reference to a hash mapping each feature in the original genome
3475    to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3476    
3477    =back
3478    
3479    =cut
3480    
3481    sub BBHMatrix {
3482        # Get the parameters.
3483        my ($self, $genomeID, $cutoff, @targets) = @_;
3484        # Declare the return variable.
3485        my %retVal = ();
3486        # Ask for the BBHs.
3487        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3488        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3489        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3490        for my $bbhData (@bbhList) {
3491            my ($peg1, $peg2, $score) = @{$bbhData};
3492            if (! exists $retVal{$peg1}) {
3493                $retVal{$peg1} = { $peg2 => $score };
3494            } else {
3495                $retVal{$peg1}->{$peg2} = $score;
3496            }
3497        }
3498        # Return the result.
3499        return \%retVal;
3500    }
3501    
3502    
3503    =head3 SimMatrix
3504    
3505        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3506    
3507    Find all the similarities for the features of a genome in a
3508    specified list of target genomes. The return value will be a hash mapping
3509    features in the original genome to their similarites in the
3510    target genomes.
3511    
3512    =over 4
3513    
3514    =item genomeID
3515    
3516    ID of the genome whose features are to be examined for similarities.
3517    
3518    =item cutoff
3519    
3520    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3521    
3522    =item targets
3523    
3524    List of target genomes. Only pairs originating in the original
3525    genome and landing in one of the target genomes will be returned.
3526    
3527    =item RETURN
3528    
3529    Returns a hash mapping each feature in the original genome to a hash mapping its
3530    similar pegs in the target genomes to their scores.
3531    
3532    =back
3533    
3534    =cut
3535    
3536    sub SimMatrix {
3537        # Get the parameters.
3538        my ($self, $genomeID, $cutoff, @targets) = @_;
3539        # Declare the return variable.
3540        my %retVal = ();
3541        # Get the list of features in the source organism.
3542        my @fids = $self->FeaturesOf($genomeID);
3543        # Ask for the sims. We only want similarities to fig features.
3544        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3545        if (! defined $simList) {
3546            Confess("Unable to retrieve similarities from server.");
3547        } else {
3548            Trace("Processing sims.") if T(3);
3549            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3550            # Create a hash for the target genomes.
3551            my %targetHash = map { $_ => 1 } @targets;
3552            for my $simData (@{$simList}) {
3553                # Get the PEGs and the score.
3554                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3555                # Insure the second ID is in the target list.
3556                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3557                if (exists $targetHash{$genome2}) {
3558                    # Here it is. Now we need to add it to the return hash. How we do that depends
3559                    # on whether or not $peg1 is new to us.
3560                    if (! exists $retVal{$peg1}) {
3561                        $retVal{$peg1} = { $peg2 => $score };
3562                    } else {
3563                        $retVal{$peg1}->{$peg2} = $score;
3564                    }
3565                }
3566            }
3567        }
3568        # Return the result.
3569        return %retVal;
3570    }
3571    
3572    
3573  =head3 LowBBHs  =head3 LowBBHs
3574    
3575  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3576    
3577  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
3578  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 3598 
3598  #: Return Type %;  #: Return Type %;
3599  sub LowBBHs {  sub LowBBHs {
3600          # Get the parsameters.          # Get the parsameters.
3601          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3602          # Create the return hash.          # Create the return hash.
3603          my %retVal = ();          my %retVal = ();
3604          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3605          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3606          # Form the results into the return hash.          # Form the results into the return hash.
3607          for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3608                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3609            if ($self->Exists('Feature', $fid)) {
3610                $retVal{$fid} = $pair->[1];
3611            }
3612          }          }
3613          # Return the result.          # Return the result.
3614          return %retVal;          return %retVal;
3615  }  }
3616    
3617  =head2 Internal Utility Methods  =head3 Sims
3618    
3619  =head3 ParseAssignment      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3620    
3621  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Get a list of similarities for a specified feature. Similarity information is not kept in the
3622  the user and function text will be returned as a 2-element list. If it isn't, an empty list  Sprout database; rather, they are retrieved from a network server. The similarities are
3623  will be returned.  returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3624    so that its elements can be accessed by name.
3625    
3626    Similarities can be either raw or expanded. The raw similarities are basic
3627    hits between features with similar DNA. Expanding a raw similarity drags in any
3628    features considered substantially identical. So, for example, if features B<A1>,
3629    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3630    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3631    
3632  This is a static method.  =over 4
3633    
3634    =item fid
3635    
3636    ID of the feature whose similarities are desired, or reference to a list of IDs
3637    of features whose similarities are desired.
3638    
3639    =item maxN
3640    
3641    Maximum number of similarities to return.
3642    
3643    =item maxP
3644    
3645    Minumum allowable similarity score.
3646    
3647    =item select
3648    
3649    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3650    means only similarities to FIG features are returned; C<all> means all expanded
3651    similarities are returned; and C<figx> means similarities are expanded until the
3652    number of FIG features equals the maximum.
3653    
3654    =item max_expand
3655    
3656    The maximum number of features to expand.
3657    
3658    =item filters
3659    
3660    Reference to a hash containing filter information, or a subroutine that can be
3661    used to filter the sims.
3662    
3663    =item RETURN
3664    
3665    Returns a reference to a list of similarity objects, or C<undef> if an error
3666    occurred.
3667    
3668    =back
3669    
3670    =cut
3671    
3672    sub Sims {
3673        # Get the parameters.
3674        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3675        # Create the shim object to test for deleted FIDs.
3676        my $shim = FidCheck->new($self);
3677        # Ask the network for sims.
3678        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3679        # Return the result.
3680        return $retVal;
3681    }
3682    
3683    =head3 IsAllGenomes
3684    
3685        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3686    
3687    Return TRUE if all genomes in the second list are represented in the first list at
3688    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3689    compared to a list of all the genomes.
3690    
3691  =over 4  =over 4
3692    
3693  =item text  =item list
3694    
3695  Text of the annotation.  Reference to the list to be compared to the second list.
3696    
3697    =item checkList (optional)
3698    
3699    Reference to the comparison target list. Every genome ID in this list must occur at
3700    least once in the first list. If this parameter is omitted, a list of all the genomes
3701    is used.
3702    
3703  =item RETURN  =item RETURN
3704    
3705  Returns an empty list if the annotation is not a functional assignment; otherwise, returns  Returns TRUE if every item in the second list appears at least once in the
3706  a two-element list containing the user name and the function text.  first list, else FALSE.
3707    
3708  =back  =back
3709    
3710  =cut  =cut
3711    
3712  sub ParseAssignment {  sub IsAllGenomes {
3713        # Get the parameters.
3714        my ($self, $list, $checkList) = @_;
3715        # Supply the checklist if it was omitted.
3716        $checkList = [$self->Genomes()] if ! defined($checkList);
3717        # Create a hash of the original list.
3718        my %testList = map { $_ => 1 } @{$list};
3719        # Declare the return variable. We assume that the representation
3720        # is complete and stop at the first failure.
3721        my $retVal = 1;
3722        my $n = scalar @{$checkList};
3723        for (my $i = 0; $retVal && $i < $n; $i++) {
3724            if (! $testList{$checkList->[$i]}) {
3725                $retVal = 0;
3726            }
3727        }
3728        # Return the result.
3729        return $retVal;
3730    }
3731    
3732    =head3 GetGroups
3733    
3734        my %groups = $sprout->GetGroups(\@groupList);
3735    
3736    Return a hash mapping each group to the IDs of the genomes in the group.
3737    A list of groups may be specified, in which case only those groups will be
3738    shown. Alternatively, if no parameter is supplied, all groups will be
3739    included. Genomes that are not in any group are omitted.
3740    
3741    =cut
3742    #: Return Type %@;
3743    sub GetGroups {
3744          # Get the parameters.          # Get the parameters.
3745          my ($text) = @_;      my ($self, $groupList) = @_;
3746          # Declare the return value.          # Declare the return value.
3747          my @retVal = ();      my %retVal = ();
3748          # Check to see if this is a functional assignment.      # Determine whether we are getting all the groups or just some.
3749          my ($user, $type, $function) = split(/\n/, $text);      if (defined $groupList) {
3750          if ($type =~ m/^set $user function to$/i) {          # Here we have a group list. Loop through them individually,
3751                  # Here it is, so we return the user name and function text.          # getting a list of the relevant genomes.
3752                  @retVal = ($user, $function);          for my $group (@{$groupList}) {
3753                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3754                    [$group], "Genome(id)");
3755                $retVal{$group} = \@genomeIDs;
3756          }          }
3757          # Return the result list.      } else {
3758            # Here we need all of the groups. In this case, we run through all
3759            # of the genome records, putting each one found into the appropriate
3760            # group. Note that we use a filter clause to insure that only genomes
3761            # in real NMPDR groups are included in the return set.
3762            my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3763                                        [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3764            # Loop through the genomes found.
3765            for my $genome (@genomes) {
3766                # Get the genome ID and group, and add this genome to the group's list.
3767                my ($genomeID, $group) = @{$genome};
3768                push @{$retVal{$group}}, $genomeID;
3769            }
3770        }
3771        # Return the hash we just built.
3772        return %retVal;
3773    }
3774    
3775    =head3 MyGenomes
3776    
3777        my @genomes = Sprout::MyGenomes($dataDir);
3778    
3779    Return a list of the genomes to be included in the Sprout.
3780    
3781    This method is provided for use during the Sprout load. It presumes the Genome load file has
3782    already been created. (It will be in the Sprout data directory and called either C<Genome>
3783    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3784    IDs.
3785    
3786    =over 4
3787    
3788    =item dataDir
3789    
3790    Directory containing the Sprout load files.
3791    
3792    =back
3793    
3794    =cut
3795    #: Return Type @;
3796    sub MyGenomes {
3797        # Get the parameters.
3798        my ($dataDir) = @_;
3799        # Compute the genome file name.
3800        my $genomeFileName = LoadFileName($dataDir, "Genome");
3801        # Extract the genome IDs from the files.
3802        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3803        # Return the result.
3804          return @retVal;          return @retVal;
3805  }  }
3806    
3807  =head3 FriendlyTimestamp  =head3 LoadFileName
3808    
3809  Convert a time number to a user-friendly time stamp for display.      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3810    
3811  This is a static method.  Return the name of the load file for the specified table in the specified data
3812    directory.
3813    
3814  =over 4  =over 4
3815    
3816  =item timeValue  =item dataDir
3817    
3818  Numeric time value.  Directory containing the Sprout load files.
3819    
3820    =item tableName
3821    
3822    Name of the table whose load file is desired.
3823    
3824  =item RETURN  =item RETURN
3825    
3826  Returns a string containing the same time in user-readable format.  Returns the name of the file containing the load data for the specified table, or
3827    C<undef> if no load file is present.
3828    
3829    =back
3830    
3831    =cut
3832    #: Return Type $;
3833    sub LoadFileName {
3834        # Get the parameters.
3835        my ($dataDir, $tableName) = @_;
3836        # Declare the return variable.
3837        my $retVal;
3838        # Check for the various file names.
3839        if (-e "$dataDir/$tableName") {
3840            $retVal = "$dataDir/$tableName";
3841        } elsif (-e "$dataDir/$tableName.dtx") {
3842            $retVal = "$dataDir/$tableName.dtx";
3843        }
3844        # Return the result.
3845        return $retVal;
3846    }
3847    
3848    =head3 DeleteGenome
3849    
3850        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3851    
3852    Delete a genome from the database.
3853    
3854    =over 4
3855    
3856    =item genomeID
3857    
3858    ID of the genome to delete
3859    
3860    =item testFlag
3861    
3862    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3863    
3864    =item RETURN
3865    
3866    Returns a statistics object describing the rows deleted.
3867    
3868    =back
3869    
3870    =cut
3871    #: Return Type $%;
3872    sub DeleteGenome {
3873        # Get the parameters.
3874        my ($self, $genomeID, $testFlag) = @_;
3875        # Perform the delete for the genome's features.
3876        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3877        # Perform the delete for the primary genome data.
3878        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3879        $retVal->Accumulate($stats);
3880        # Return the result.
3881        return $retVal;
3882    }
3883    
3884    =head3 Fix
3885    
3886        my %fixedHash = $sprout->Fix(%groupHash);
3887    
3888    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3889    The groups will be combined into the appropriate super-groups.
3890    
3891    =over 4
3892    
3893    =item groupHash
3894    
3895    Hash to be fixed up.
3896    
3897    =item RETURN
3898    
3899    Returns a fixed-up version of the hash.
3900    
3901    =back
3902    
3903    =cut
3904    
3905    sub Fix {
3906        # Get the parameters.
3907        my ($self, %groupHash) = @_;
3908        # Create the result hash.
3909        my %retVal = ();
3910        # Copy over the genomes.
3911        for my $groupID (keys %groupHash) {
3912            # Get the super-group name.
3913            my $realGroupID = $self->SuperGroup($groupID);
3914            # Append this group's genomes into the result hash
3915            # using the super-group name.
3916            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3917        }
3918        # Return the result hash.
3919        return %retVal;
3920    }
3921    
3922    =head3 GroupPageName
3923    
3924        my $name = $sprout->GroupPageName($group);
3925    
3926    Return the name of the page for the specified NMPDR group.
3927    
3928    =over 4
3929    
3930    =item group
3931    
3932    Name of the relevant group.
3933    
3934    =item RETURN
3935    
3936    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3937    memory it will be read in.
3938    
3939    =back
3940    
3941    =cut
3942    
3943    sub GroupPageName {
3944        # Get the parameters.
3945        my ($self, $group) = @_;
3946        # Check for the group file data.
3947        my %superTable = $self->CheckGroupFile();
3948        # Compute the real group name.
3949        my $realGroup = $self->SuperGroup($group);
3950        # Get the associated page name.
3951        my $retVal = "../content/$superTable{$realGroup}->{page}";
3952        # Return the result.
3953        return $retVal;
3954    }
3955    
3956    
3957    =head3 AddProperty
3958    
3959        $sprout->AddProperty($featureID, $key, @values);
3960    
3961    Add a new attribute value (Property) to a feature.
3962    
3963    =over 4
3964    
3965    =item peg
3966    
3967    ID of the feature to which the attribute is to be added.
3968    
3969    =item key
3970    
3971    Name of the attribute (key).
3972    
3973    =item values
3974    
3975    Values of the attribute.
3976    
3977    =back
3978    
3979    =cut
3980    #: Return Type ;
3981    sub AddProperty {
3982        # Get the parameters.
3983        my ($self, $featureID, $key, @values) = @_;
3984        # Add the property using the attached attributes object.
3985        $self->ca->AddAttribute($featureID, $key, @values);
3986    }
3987    
3988    =head3 CheckGroupFile
3989    
3990        my %groupData = $sprout->CheckGroupFile();
3991    
3992    Get the group file hash. The group file hash describes the relationship
3993    between a group and the super-group to which it belongs for purposes of
3994    display. The super-group name is computed from the first capitalized word
3995    in the actual group name. For each super-group, the group file contains
3996    the page name and a list of the species expected to be in the group.
3997    Each species is specified by a genus and a species name. A species name
3998    of C<0> implies an entire genus.
3999    
4000    This method returns a hash from super-group names to a hash reference. Each
4001    resulting hash reference contains the following fields.
4002    
4003    =over 4
4004    
4005    =item specials
4006    
4007    Reference to a hash whose keys are the names of special species.
4008    
4009    =item contents
4010    
4011    A list of 2-tuples, each containing a genus name followed by a species name
4012    (or 0, indicating all species). This list indicates which organisms belong
4013    in the super-group.
4014    
4015    =back
4016    
4017    =cut
4018    
4019    sub CheckGroupFile {
4020        # Get the parameters.
4021        my ($self) = @_;
4022        # Check to see if we already have this hash.
4023        if (! defined $self->{groupHash}) {
4024            # We don't, so we need to read it in.
4025            my %groupHash;
4026            # Read the group file.
4027            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4028            # Loop through the list of sort-of groups.
4029            for my $groupLine (@groupLines) {
4030                my ($name, $specials, @contents) = split /\t/, $groupLine;
4031                $groupHash{$name} = { specials => { map { $_ => 1 } split /\s*,\s*/, $specials },
4032                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4033                                    };
4034            }
4035            # Save the hash.
4036            $self->{groupHash} = \%groupHash;
4037        }
4038        # Return the result.
4039        return %{$self->{groupHash}};
4040    }
4041    
4042    =head2 Virtual Methods
4043    
4044    =head3 CleanKeywords
4045    
4046        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4047    
4048    Clean up a search expression or keyword list. This involves converting the periods
4049    in EC numbers to underscores, converting non-leading minus signs to underscores,
4050    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4051    characters. In addition, any extra spaces are removed.
4052    
4053    =over 4
4054    
4055    =item searchExpression
4056    
4057    Search expression or keyword list to clean. Note that a search expression may
4058    contain boolean operators which need to be preserved. This includes leading
4059    minus signs.
4060    
4061    =item RETURN
4062    
4063    Cleaned expression or keyword list.
4064    
4065    =back
4066    
4067    =cut
4068    
4069    sub CleanKeywords {
4070        # Get the parameters.
4071        my ($self, $searchExpression) = @_;
4072        # Get the stemmer.