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

Diff of /Sprout/Sprout.pm

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

revision 1.3, Tue Jan 25 01:00:20 2005 UTC revision 1.127, Mon May 4 18:49:49 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(%parms)
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 incoming parameter hash has the following permissible
52  database.  members (others will be ignored without error.
53    
54  =over 4  =over 4
55    
56    =item DBD
57    
58    Name of the XML file containing the database definition (default C<SproutDBD.xml> in
59    the DBD directory).
60    
61  =item dbName  =item dbName
62    
63  Name of the database.  Name of the database. If omitted, the default Sprout database name is used.
64    
65  =item options  =item options
66    
67  Table of options.  Sub-hash of special options.
68    
69  * B<dbType> type of database (currently C<mysql> for MySQL and C<pg> for PostgreSQL) (default C<mysql>)  * B<dbType> type of database (currently C<mysql> for MySQL and C<pg> for PostgreSQL) (default C<mysql>)
70    
71  * B<dataDir> directory containing the database definition file and the flat files used to load the data (default C<Data>)  * B<dataDir> directory containing the database definition file and the flat files used to load the data (default C<Data>)
72    
73  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
   
 * B<userData> user name and password, delimited by a slash (default C<root/>)  
74    
75  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
76    
77    * B<sock> connection socket (default same as SEED)
78    
79  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
80    
81  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
82    
83    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
84    
85    * B<host> name of the database host
86    
87  =back  =back
88    
89  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
90  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
91  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
92    
93  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new(dbName => 'Sprout', options => { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
94    
95    The odd constructor signature is a result of Sprout's status as the first ERDB database,
96    and the need to make it compatible with the needs of its younger siblings.
97    
98  =cut  =cut
99    
100  sub new {  sub new {
101          # Get the parameters.          # Get the parameters.
102          my ($class, $dbName, $options) = @_;      my ($class, %parms) = @_;
103        # Look for an options hash.
104        my $options = $parms{options} || {};
105        # Plug in the DBD and name parameters.
106        if ($parms{DBD}) {
107            $options->{xmlFileName} = $parms{DBD};
108        }
109        my $dbName = $parms{dbName} || $FIG_Config::sproutDB;
110        # Compute the DBD directory.
111        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
112                                                      $FIG_Config::fig );
113          # 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
114          # the incoming data.          # the incoming data.
115          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
116                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
117                                             dataDir              => 'Data',                      # data file directory                                                          # database type
118                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
119                                             userData             => 'root/',                     # user name and password                                                          # data file directory
120                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
121                                                            # database definition file name
122                           userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
123                                                            # user name and password
124                           port         => $FIG_Config::sproutPort,
125                                                            # database connection port
126                           sock         => $FIG_Config::sproutSock,
127                           host         => $FIG_Config::sprout_host,
128                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
129                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
130                           noDBOpen     => 0,               # 1 to suppress the database open
131                           demandDriven => 0,               # 1 for forward-only queries
132                                            }, $options);                                            }, $options);
133          # Get the data directory.          # Get the data directory.
134          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 101  Line 136 
136          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
137          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
138          # Connect to the database.          # Connect to the database.
139          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
140        if (! $optionTable->{noDBOpen}) {
141            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
142            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
143                                    $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
144        }
145          # Create the ERDB object.          # Create the ERDB object.
146          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
147          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName, %$optionTable);
148          # Create this object.      # Add the option table and XML file name.
149          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
150          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
151          bless $self;      # Set up space for the group file data.
152          return $self;      $retVal->{groupHash} = undef;
153        # Set up space for the genome hash. We use this to identify NMPDR genomes
154        # and remember genome data.
155        $retVal->{genomeHash} = {};
156        $retVal->{genomeHashFilled} = 0;
157        # Remember the data directory name.
158        $retVal->{dataDir} = $dataDir;
159        # Return it.
160        return $retVal;
161  }  }
162    
163  =head3 MaxSegment  =head3 ca
164    
165  C<< my $length = $sprout->MaxSegment(); >>      my $ca = $sprout->ca():;
166    
167  This method returns the maximum permissible length of a feature segment. The length is important  Return the [[CustomAttributesPm]] object for retrieving object
168  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.  
169    
170  =cut  =cut
 #: Return Type $;  
 sub MaxSegment {  
         my $self = shift @_;  
         return $self->{_options}->{maxSegmentLength};  
 }  
   
 =head3 MaxSequence  
   
 C<< my $length = $sprout->MaxSequence(); >>  
   
 This method returns the maximum permissible length of a contig sequence. A contig is broken  
 into sequences in order to save memory resources. In particular, when manipulating features,  
 we generally only need a few sequences in memory rather than the entire contig.  
171    
172  =cut  sub ca {
173  #: Return Type $;      # Get the parameters.
174  sub MaxSequence {      my ($self) = @_;
175          my $self = shift @_;      # Do we already have an attribute object?
176          return $self->{_options}->{maxSequenceLength};      my $retVal = $self->{_ca};
177        if (! defined $retVal) {
178            # No, create one. How we do it depends on the configuration.
179            if ($FIG_Config::attrURL) {
180                Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
181                $retVal = RemoteCustomAttributes->new($FIG_Config::attrURL);
182            } elsif ($FIG_Config::attrDbName) {
183                Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
184                my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
185                $retVal = CustomAttributes->new(user => $user);
186            }
187            # Save it for next time.
188            $self->{_ca} = $retVal;
189        }
190        # Return the result.
191        return $retVal;
192  }  }
193    
194  =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)"); >>  
195    
196  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.  
197    
198  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.  
199    
200  =over 4  =over 4
201    
202  =item objectNames  =item scope
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
203    
204  WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  Scope of the desired genomes. C<core> covers the original core genomes,
205  be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
206  B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  genomes in the system.
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
207    
208  =item RETURN  =item RETURN
209    
210  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.
211    
212  =back  =back
213    
214  =cut  =cut
215    
216  sub Get {  sub CoreGenomes {
217          # Get the parameters.          # Get the parameters.
218          my $self = shift @_;      my ($self, $scope) = @_;
219          my ($objectNames, $filterClause, $parameterList) = @_;      # Declare the return variable.
220          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      my @retVal = ();
221          # rather than a list of parameters. The next step is to convert the parameters from a reference      # If we want all genomes, then this is easy.
222          # to a real list. We can only do this if the parameters have been specified.      if ($scope eq 'all') {
223          my @parameters;          @retVal = $self->Genomes();
224          if ($parameterList) { @parameters = @{$parameterList}; }      } else {
225          return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);          # Here we're dealing with groups. Get the hash of all the
226            # genome groups.
227            my %groups = $self->GetGroups();
228            # Loop through the groups, keeping the ones that we want.
229            for my $group (keys %groups) {
230                # Decide if we want to keep this group.
231                my $keepGroup = 0;
232                if ($scope eq 'nmpdr') {
233                    # NMPDR mode: keep all groups.
234                    $keepGroup = 1;
235                } elsif ($scope eq 'core') {
236                    # CORE mode. Only keep real core groups.
237                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
238                        $keepGroup = 1;
239                    }
240                }
241                # Add this group if we're keeping it.
242                if ($keepGroup) {
243                    push @retVal, @{$groups{$group}};
244                }
245            }
246        }
247        # Return the result.
248        return @retVal;
249  }  }
250    
251  =head3 GetEntity  =head3 SuperGroup
252    
253  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my $superGroup = $sprout->SuperGroup($groupName);
254    
255  Return an object describing the entity instance with a specified ID.  Return the name of the super-group containing the specified NMPDR genome
256    group. If no appropriate super-group can be found, an error will be
257    thrown.
258    
259  =over 4  =over 4
260    
261  =item entityType  =item groupName
   
 Entity type name.  
   
 =item ID  
262    
263  ID of the desired entity.  Name of the group whose super-group is desired.
264    
265  =item RETURN  =item RETURN
266    
267  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.  
268    
269  =back  =back
270    
271  =cut  =cut
272    
273  sub GetEntity {  sub SuperGroup {
274          # Get the parameters.          # Get the parameters.
275          my $self = shift @_;      my ($self, $groupName) = @_;
276          my ($entityType, $ID) = @_;      # Declare the return variable.
277          # Create a query.      my $retVal;
278          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      # Get the group hash.
279          # Get the first (and only) object.      my %groupHash = $self->CheckGroupFile();
280          my $retVal = $query->Fetch();      # Find the super-group genus.
281        $groupName =~ /([A-Z]\w+)/;
282        my $nameThing = $1;
283        # See if it's directly in the group hash.
284        if (exists $groupHash{$nameThing}) {
285            # Yes, then it's our result.
286            $retVal = $nameThing;
287        } else {
288            # No, so we have to search.
289            for my $superGroup (keys %groupHash) {
290                # Get this super-group's item list.
291                my $list = $groupHash{$superGroup}->{contents};
292                # Search it.
293                if (grep { $_->[0] eq $nameThing } @{$list}) {
294                    $retVal = $superGroup;
295                }
296            }
297        }
298          # Return the result.          # Return the result.
299          return $retVal;          return $retVal;
300  }  }
301    
302  =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  
303    
304  Returns a flattened list of the values of the specified fields for the specified entity.      my $length = $sprout->MaxSegment();
305    
306  =back  This method returns the maximum permissible length of a feature segment. The length is important
307    because it enables us to make reasonable guesses at how to find features inside a particular
308    contig region. For example, if the maximum length is 4000 and we're looking for a feature that
309    overlaps the region from 6000 to 7000 we know that the starting position must be between 2001
310    and 10999.
311    
312  =cut  =cut
313  #: Return Type @;  #: Return Type $;
314  sub GetEntityValues {  sub MaxSegment {
315          # Get the parameters.      my ($self) = @_;
316          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;  
317  }  }
318    
319  =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  
320    
321  Fully-qualified name to give to the output file.      my $length = $sprout->MaxSequence();
322    
323  =back  This method returns the maximum permissible length of a contig sequence. A contig is broken
324    into sequences in order to save memory resources. In particular, when manipulating features,
325    we generally only need a few sequences in memory rather than the entire contig.
326    
327  =cut  =cut
328    #: Return Type $;
329  sub ShowMetaData {  sub MaxSequence {
330          # Get the parameters.      my ($self) = @_;
331          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);  
332  }  }
333    
334  =head3 Load  =head3 Load
335    
336  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
337    
338  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.
339    
# Line 364  Line 345 
345  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
346  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
347  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
348  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.
349    
350  =over 4  =over 4
351    
# Line 383  Line 364 
364  #: Return Type %;  #: Return Type %;
365  sub Load {  sub Load {
366          # Get the parameters.          # Get the parameters.
367          my $self = shift @_;      my ($self, $rebuild) = @_;
         my ($rebuild) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
368          # Load the tables from the data directory.          # Load the tables from the data directory.
369          my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
370          # Return the statistics.          # Return the statistics.
371          return $retVal;          return $retVal;
372  }  }
373    
374  =head3 LoadUpdate  =head3 LoadUpdate
375    
376  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
377    
378  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
379  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 402 
402  =back  =back
403    
404  =cut  =cut
405  #: Return Type %;  #: Return Type $%;
406  sub LoadUpdate {  sub LoadUpdate {
407          # Get the parameters.          # Get the parameters.
408          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
         my ($truncateFlag, $tableList) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
409          # Declare the return value.          # Declare the return value.
410          my $retVal = Stats->new();          my $retVal = Stats->new();
411          # Get the data directory.          # Get the data directory.
# Line 439  Line 414 
414          # Loop through the incoming table names.          # Loop through the incoming table names.
415          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
416                  # Find the table's file.                  # Find the table's file.
417                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
418                  if (! -e $fileName) {          if (! $fileName) {
419                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
420                  }          } else {
421                  # Attempt to load this table.                  # Attempt to load this table.
422                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
423                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
424                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
425          }          }
426        }
427          # Return the statistics.          # Return the statistics.
428          return $retVal;          return $retVal;
429  }  }
430    
431    =head3 GenomeCounts
432    
433        my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
434    
435    Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
436    genomes will be included in the counts.
437    
438    =over 4
439    
440    =item complete
441    
442    TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
443    counted
444    
445    =item RETURN
446    
447    A six-element list containing the number of genomes in each of six categories--
448    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
449    
450    =back
451    
452    =cut
453    
454    sub GenomeCounts {
455        # Get the parameters.
456        my ($self, $complete) = @_;
457        # Set the filter based on the completeness flag.
458        my $filter = ($complete ? "Genome(complete) = 1" : "");
459        # Get all the genomes and the related taxonomy information.
460        my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
461        # Clear the counters.
462        my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
463        # Loop through, counting the domains.
464        for my $genome (@genomes) {
465            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
466            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
467            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
468            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
469            elsif ($genome->[1] =~ /^env/i)      { ++$env }
470            else  { ++$unk }
471        }
472        # Return the counts.
473        return ($arch, $bact, $euk, $vir, $env, $unk);
474    }
475    
476    =head3 ContigCount
477    
478        my $count = $sprout->ContigCount($genomeID);
479    
480    Return the number of contigs for the specified genome ID.
481    
482    =over 4
483    
484    =item genomeID
485    
486    ID of the genome whose contig count is desired.
487    
488    =item RETURN
489    
490    Returns the number of contigs for the specified genome.
491    
492    =back
493    
494    =cut
495    
496    sub ContigCount {
497        # Get the parameters.
498        my ($self, $genomeID) = @_;
499        # Get the contig count.
500        my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
501        # Return the result.
502        return $retVal;
503    }
504    
505    =head3 GenomeMenu
506    
507        my $html = $sprout->GenomeMenu(%options);
508    
509    Generate a genome selection control with the specified name and options.
510    This control is almost but not quite the same as the genome control in the
511    B<SearchHelper> class. Eventually, the two will be combined.
512    
513    =over 4
514    
515    =item options
516    
517    Optional parameters for the control (see below).
518    
519    =item RETURN
520    
521    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
522    
523    =back
524    
525    The valid options are as follows.
526    
527    =over 4
528    
529    =item name
530    
531    Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
532    Terrible things will happen if you have two controls with the same name on the same page.
533    
534    =item filter
535    
536    If specified, a filter for the list of genomes to display. The filter should be in the form of a
537    list reference, a string, or a hash reference. If it is a list reference, the first element
538    of the list should be the filter string, and the remaining elements the filter parameters. If it is a
539    string, it will be split into a list at each included tab. If it is a hash reference, it should be
540    a hash that maps genomes which should be included to a TRUE value.
541    
542    =item multiSelect
543    
544    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
545    
546    =item size
547    
548    Number of rows to display in the control. The default is C<10>
549    
550    =item id
551    
552    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
553    unless this ID is unique.
554    
555    =item selected
556    
557    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
558    default is none.
559    
560    =item class
561    
562    If specified, a style class to assign to the genome control.
563    
564    =back
565    
566    =cut
567    
568    sub GenomeMenu {
569        # Get the parameters.
570        my ($self, %options) = @_;
571        # Get the control's name and ID.
572        my $menuName = $options{name} || $options{id} || 'myGenomeControl';
573        my $menuID = $options{id} || $menuName;
574        Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
575        # Compute the IDs for the status display.
576        my $divID = "${menuID}_status";
577        my $urlID = "${menuID}_url";
578        # Compute the code to show selected genomes in the status area.
579        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
580        # Check for single-select or multi-select.
581        my $multiSelect = $options{multiSelect} || 0;
582        # Get the style data.
583        my $class = $options{class} || '';
584        # Get the list of pre-selected items.
585        my $selections = $options{selected} || [];
586        if (ref $selections ne 'ARRAY') {
587            $selections = [ split /\s*,\s*/, $selections ];
588        }
589        my %selected = map { $_ => 1 } @{$selections};
590        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
591        # string, a hash reference, or a list reference.
592        my ($filterHash, $filterString);
593        my $filterParms = $options{filter} || "";
594        if (ref $filterParms eq 'HASH') {
595            $filterHash = $filterParms;
596            $filterParms = [];
597            $filterString = "";
598        } else {
599            if (! ref $filterParms) {
600                $filterParms = [split /\t|\\t/, $filterParms];
601            }
602            $filterString = shift @{$filterParms};
603        }
604        # Check for possible subsystem filtering. If there is one, we will tack the
605        # relationship onto the object name list.
606        my @objectNames = qw(Genome);
607        if ($filterString =~ /ParticipatesIn\(/) {
608            push @objectNames, 'ParticipatesIn';
609        }
610        # Get a list of all the genomes in group order. In fact, we only need them ordered
611        # by name (genus,species,strain), but putting primary-group in front enables us to
612        # take advantage of an existing index.
613        my @genomeList = $self->GetAll(\@objectNames, "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
614                                       $filterParms,
615                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
616        # Apply the hash filter (if any).
617        if (defined $filterHash) {
618            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
619        }
620        # Create a hash to organize the genomes by group. Each group will contain a list of
621        # 2-tuples, the first element being the genome ID and the second being the genome
622        # name.
623        my %gHash = ();
624        for my $genome (@genomeList) {
625            # Get the genome data.
626            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
627            # Compute its name. This is the genus, species, strain (if any), and the contig count.
628            my $name = "$genus $species ";
629            $name .= "$strain " if $strain;
630            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
631            # Now we get the domain. The domain tells us the display style of the organism.
632            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
633            # Now compute the display group. This is normally the primary group, but if the
634            # organism is supporting, we blank it out.
635            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
636            # Push the genome into the group's list. Note that we use the real group
637            # name for the hash key here, not the display group name.
638            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
639        }
640        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
641        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
642        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
643        # that aren't "other". At some point, we will want to make this less complicated.
644        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
645                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
646        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
647        # Remember the number of NMPDR groups.
648        my $nmpdrGroupCount = scalar @groups;
649        # Are there any supporting genomes?
650        if (exists $gHash{$FIG_Config::otherGroup}) {
651            # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
652            # of the domains found.
653            my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
654            my @domains = ();
655            for my $genomeData (@otherGenomes) {
656                my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
657                if (exists $gHash{$domain}) {
658                    push @{$gHash{$domain}}, $genomeData;
659                } else {
660                    $gHash{$domain} = [$genomeData];
661                    push @domains, $domain;
662                }
663            }
664            # Add the domain groups at the end of the main group list. The main group list will now
665            # contain all the categories we need to display the genomes.
666            push @groups, sort @domains;
667            # Delete the supporting group.
668            delete $gHash{$FIG_Config::otherGroup};
669        }
670        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
671        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
672        # and use that to make the selections.
673        my $nmpdrCount = 0;
674        # Create the type counters.
675        my $groupCount = 1;
676        # Get the number of rows to display.
677        my $rows = $options{size} || 10;
678        # If we're multi-row, create an onChange event.
679        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
680        # Set up the multiple-select flag.
681        my $multipleTag = ($multiSelect ? " multiple" : "" );
682        # Set up the style class.
683        my $classTag = ($class ? " $class" : "" );
684        # Create the SELECT tag and stuff it into the output array.
685        my @lines = qq(<SELECT name="$menuName" id="$menuID" class="genomeSelect $class" $onChangeTag$multipleTag$classTag size="$rows">);
686        # Loop through the groups.
687        for my $group (@groups) {
688            # Get the genomes in the group.
689            for my $genome (@{$gHash{$group}}) {
690                # If this is an NMPDR organism, we add an extra style and count it.
691                my $nmpdrStyle = "";
692                if ($nmpdrGroupCount > 0) {
693                    $nmpdrCount++;
694                    $nmpdrStyle = " Core";
695                }
696                # Get the organism ID, name, contig count, and domain.
697                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
698                # See if we're pre-selected.
699                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
700                # Compute the display name.
701                my $nameString = "$name ($genomeID$contigCount)";
702                # Generate the option tag.
703                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
704                push @lines, "    $optionTag";
705            }
706            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
707            # groups.
708            $nmpdrGroupCount--;
709        }
710        # Close the SELECT tag.
711        push @lines, "</SELECT>";
712        if ($rows > 1) {
713            # We're in a non-compact mode, so we need to add some selection helpers. First is
714            # the search box. This allows the user to type text and change which genomes are
715            # displayed. For multiple-select mode, we include a button that selects the displayed
716            # genes. For single-select mode, we use a plain label instead.
717            my $searchThingName = "${menuID}_SearchThing";
718            my $searchThingLabel = "Type to narrow selection";
719            my $searchThingButton = "";
720            if ($multiSelect) {
721                $searchThingButton = qq(<INPUT type="button" name="MacroSearch" class="button" value="Go" onClick="selectShowing('$menuID', '$searchThingName'); $showSelect;" />);
722            }
723            push @lines, "<br />$searchThingLabel&nbsp;" .
724                         qq(<INPUT type="text" id="$searchThingName" name="$searchThingName" class="genomeSearchThing" onKeyup="showTyped('$menuID', '$searchThingName');" />) .
725                         $searchThingButton .
726                         Hint("GenomeControl", 28) . "<br />";
727            # For multi-select mode, we also have buttons to set and clear selections.
728            if ($multiSelect) {
729                push @lines, qq(<INPUT type="button" name="ClearAll" class="bigButton genomeButton" value="Clear All" onClick="clearAll(getElementById('$menuID')); $showSelect" />);
730                push @lines, qq(<INPUT type="button" name="SelectAll" class="bigButton genomeButton" value="Select All" onClick="selectAll(getElementById('$menuID')); $showSelect" />);
731                push @lines, qq(<INPUT type="button" name="NMPDROnly" class="bigButton genomeButton" value="Select NMPDR" onClick="selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;" />);
732            }
733            # Add a hidden field we can use to generate organism page hyperlinks.
734            push @lines, qq(<INPUT type="hidden" id="$urlID" value="$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=" />);
735            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
736            push @lines, qq(<DIV id="$divID" class="Panel"></DIV>);
737        }
738        # Assemble all the lines into a string.
739        my $retVal = join("\n", @lines, "");
740        # Return the result.
741        return $retVal;
742    }
743    
744    =head3 Cleanup
745    
746        $sprout->Cleanup();
747    
748    Release the internal cache structures to free up memory.
749    
750    =cut
751    
752    sub Cleanup {
753        # Get the parameters.
754        my ($self) = @_;
755        # Delete the stemmer.
756        delete $self->{stemmer};
757        # Delete the attribute database.
758        delete $self->{_ca};
759        # Delete the group hash.
760        delete $self->{groupHash};
761        # Is there a FIG object?
762        if (defined $self->{fig}) {
763            # Yes, clear its subsystem cache.
764            $self->{fig}->clear_subsystem_cache();
765        }
766    }
767    
768    
769    =head3 Stem
770    
771        my $stem = $sprout->Stem($word);
772    
773    Return the stem of the specified word, or C<undef> if the word is not
774    stemmable. Note that even if the word is stemmable, the stem may be
775    the same as the original word.
776    
777    =over 4
778    
779    =item word
780    
781    Word to convert into a stem.
782    
783    =item RETURN
784    
785    Returns a stem of the word (which may be the word itself), or C<undef> if
786    the word is not stemmable.
787    
788    =back
789    
790    =cut
791    
792    sub Stem {
793        # Get the parameters.
794        my ($self, $word) = @_;
795        # Get the stemmer object.
796        my $stemmer = $self->{stemmer};
797        if (! defined $stemmer) {
798            # We don't have one pre-built, so we build and save it now.
799            $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
800                                     stops => "$FIG_Config::sproutData/StopWords.txt",
801                                     cache => 0);
802            $self->{stemmer} = $stemmer;
803        }
804        # Try to stem the word.
805        my $retVal = $stemmer->Process($word);
806        # Return the result.
807        return $retVal;
808    }
809    
810    
811  =head3 Build  =head3 Build
812    
813  C<< $sprout->Build(); >>      $sprout->Build();
814    
815  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.
816  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 820 
820  #: Return Type ;  #: Return Type ;
821  sub Build {  sub Build {
822          # Get the parameters.          # Get the parameters.
823          my $self = shift @_;      my ($self) = @_;
824          # Create the tables.          # Create the tables.
825          $self->{_erdb}->CreateTables;      $self->CreateTables();
826  }  }
827    
828  =head3 Genomes  =head3 Genomes
829    
830  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
831    
832  Return a list of all the genome IDs.  Return a list of all the genome IDs.
833    
# Line 479  Line 835 
835  #: Return Type @;  #: Return Type @;
836  sub Genomes {  sub Genomes {
837          # Get the parameters.          # Get the parameters.
838          my $self = shift @_;      my ($self) = @_;
839          # Get all the genomes.          # Get all the genomes.
840          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
841          # Return the list of IDs.          # Return the list of IDs.
# Line 488  Line 844 
844    
845  =head3 GenusSpecies  =head3 GenusSpecies
846    
847  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
848    
849  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
850    
# Line 509  Line 865 
865  #: Return Type $;  #: Return Type $;
866  sub GenusSpecies {  sub GenusSpecies {
867          # Get the parameters.          # Get the parameters.
868          my $self = shift @_;      my ($self, $genomeID) = @_;
869          my ($genomeID) = @_;      # Declare the return value.
870          # Get the data for the specified genome.      my $retVal;
871          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      # Get the genome data.
872                                                                                                                            'Genome(unique-characterization)']);      my $genomeData = $self->_GenomeData($genomeID);
873          # Format the result and return it.      # Only proceed if we found the genome.
874          my $retVal = join(' ', @values);      if (defined $genomeData) {
875            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
876        }
877        # Return it.
878          return $retVal;          return $retVal;
879  }  }
880    
881  =head3 FeaturesOf  =head3 FeaturesOf
882    
883  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
884    
885  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
886    
# Line 546  Line 905 
905  #: Return Type @;  #: Return Type @;
906  sub FeaturesOf {  sub FeaturesOf {
907          # Get the parameters.          # Get the parameters.
908          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
909          # Get the features we want.          # Get the features we want.
910          my @features;          my @features;
911          if (!$ftype) {          if (!$ftype) {
# Line 567  Line 925 
925    
926  =head3 FeatureLocation  =head3 FeatureLocation
927    
928  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
929    
930  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
931  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 949 
949  =item RETURN  =item RETURN
950    
951  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
952  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
953    wasn't found.
954    
955  =back  =back
956    
957  =cut  =cut
958  #: Return Type @;  
 #: Return Type $;  
959  sub FeatureLocation {  sub FeatureLocation {
960          # Get the parameters.          # Get the parameters.
961          my $self = shift @_;      my ($self, $featureID) = @_;
962          my ($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.  
963          my @retVal = ();          my @retVal = ();
964          # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
965          # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
966          my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
967          # Loop through the query results, creating location specifiers.      if (defined $object) {
968          while (my $location = $query->Fetch()) {          # Get the location string.
969                  # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
970                  my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
971                          '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$len";  
972          }          }
973          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
974          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
975  }  }
976    
977  =head3 ParseLocation  =head3 ParseLocation
978    
979  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
980    
981  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
982  length.  length.
# Line 659  Line 995 
995  =back  =back
996    
997  =cut  =cut
998  #: Return Type @;  
999  sub ParseLocation {  sub ParseLocation {
1000          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
1001        # the first parameter.
1002        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
1003          my ($location) = @_;          my ($location) = @_;
1004          # Parse it into segments.          # Parse it into segments.
1005          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
1006          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
1007          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
1008          if ($dir eq "_") {          if ($dir eq "_") {
# Line 680  Line 1018 
1018          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
1019  }  }
1020    
 =head3 DNASeq  
1021    
1022  C<< my $sequence = $sprout->DNASeq(\@locationList); >>  =head3 PointLocation
1023    
1024  This method returns the DNA sequence represented by a list of locations. The list of locations      my $found = Sprout::PointLocation($location, $point);
1025  should be of the form returned by L</featureLocation> when in a list context. In other words,  
1026  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  Return the offset into the specified location of the specified point on the contig. If
1027    the specified point is before the location, a negative value will be returned. If it is
1028    beyond the location, an undefined value will be returned. It is assumed that the offset
1029    is for the location's contig. The location can either be new-style (using a C<+> or C<->
1030    and a length) or old-style (using C<_> and start and end positions.
1031    
1032  =over 4  =over 4
1033    
1034  =item locationList  =item location
1035    
1036    A location specifier (see L</FeatureLocation> for a description).
1037    
1038    =item point
1039    
1040    The offset into the contig of the point in which we're interested.
1041    
1042    =item RETURN
1043    
1044    Returns the offset inside the specified location of the specified point, a negative
1045    number if the point is before the location, or an undefined value if the point is past
1046    the location. If the length of the location is 0, this method will B<always> denote
1047    that it is outside the location. The offset will always be relative to the left-most
1048    position in the location.
1049    
1050    =back
1051    
1052    =cut
1053    
1054    sub PointLocation {
1055        # Get the parameter. Note that if we're called as an instance method, we ignore
1056        # the first parameter.
1057        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
1058        my ($location, $point) = @_;
1059        # Parse out the location elements. Note that this works on both old-style and new-style
1060        # locations.
1061        my ($contigID, $start, $dir, $len) = ParseLocation($location);
1062        # Declare the return variable.
1063        my $retVal;
1064        # Compute the offset. The computation is dependent on the direction of the location.
1065        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
1066        # Return the offset if it's valid.
1067        if ($offset < $len) {
1068            $retVal = $offset;
1069        }
1070        # Return the offset found.
1071        return $retVal;
1072    }
1073    
1074    =head3 DNASeq
1075    
1076        my $sequence = $sprout->DNASeq(\@locationList);
1077    
1078    This method returns the DNA sequence represented by a list of locations. The list of locations
1079    should be of the form returned by L</featureLocation> when in a list context. In other words,
1080    each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
1081    
1082    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
1083    between positions 1401 and 1532, inclusive.
1084    
1085        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
1086    
1087    =over 4
1088    
1089    =item locationList
1090    
1091  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
1092  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
1093    
1094  =item RETURN  =item RETURN
1095    
# Line 705  Line 1101 
1101  #: Return Type $;  #: Return Type $;
1102  sub DNASeq {  sub DNASeq {
1103          # Get the parameters.          # Get the parameters.
1104          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
1105          # Create the return string.          # Create the return string.
1106          my $retVal = "";          my $retVal = "";
1107          # Loop through the locations.          # Loop through the locations.
# Line 721  Line 1116 
1116                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
1117                  # before putting it in the return value.                  # before putting it in the return value.
1118                  my ($start, $stop);                  my ($start, $stop);
1119            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
1120                  if ($dir eq "+") {                  if ($dir eq "+") {
1121                          $start = $beg;                          $start = $beg;
1122                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
1123                  } else {                  } else {
1124                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
1125                          $stop = $beg;                          $stop = $beg;
1126                  }                  }
1127            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
1128                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
1129                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
1130                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 739  Line 1136 
1136                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
1137                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
1138                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
1139                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
1140                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
1141                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
1142                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
1143                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
1144                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
1145                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
1146                  }                  }
1147                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
1148                  if ($dir eq '+') {                  if ($dir eq '+') {
1149                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
1150                  } else {                  } else {
1151                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
1152                  }                  }
1153          }          }
1154          # Return the result.          # Return the result.
# Line 759  Line 1157 
1157    
1158  =head3 AllContigs  =head3 AllContigs
1159    
1160  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1161    
1162  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1163    
# Line 779  Line 1177 
1177  #: Return Type @;  #: Return Type @;
1178  sub AllContigs {  sub AllContigs {
1179          # Get the parameters.          # Get the parameters.
1180          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
1181          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
1182          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
1183                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 788  Line 1185 
1185          return @retVal;          return @retVal;
1186  }  }
1187    
1188    =head3 GenomeLength
1189    
1190        my $length = $sprout->GenomeLength($genomeID);
1191    
1192    Return the length of the specified genome in base pairs.
1193    
1194    =over 4
1195    
1196    =item genomeID
1197    
1198    ID of the genome whose base pair count is desired.
1199    
1200    =item RETURN
1201    
1202    Returns the number of base pairs in all the contigs of the specified
1203    genome.
1204    
1205    =back
1206    
1207    =cut
1208    
1209    sub GenomeLength {
1210        # Get the parameters.
1211        my ($self, $genomeID) = @_;
1212        # Declare the return variable.
1213        my $retVal = 0;
1214        # Get the genome data.
1215        my $genomeData = $self->_GenomeData($genomeID);
1216        # Only proceed if it exists.
1217        if (defined $genomeData) {
1218            $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1219        }
1220        # Return the result.
1221        return $retVal;
1222    }
1223    
1224    =head3 FeatureCount
1225    
1226        my $count = $sprout->FeatureCount($genomeID, $type);
1227    
1228    Return the number of features of the specified type in the specified genome.
1229    
1230    =over 4
1231    
1232    =item genomeID
1233    
1234    ID of the genome whose feature count is desired.
1235    
1236    =item type
1237    
1238    Type of feature to count (eg. C<peg>, C<rna>, etc.).
1239    
1240    =item RETURN
1241    
1242    Returns the number of features of the specified type for the specified genome.
1243    
1244    =back
1245    
1246    =cut
1247    
1248    sub FeatureCount {
1249        # Get the parameters.
1250        my ($self, $genomeID, $type) = @_;
1251        # Compute the count.
1252        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
1253                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
1254                                    [$genomeID, $type]);
1255        # Return the result.
1256        return $retVal;
1257    }
1258    
1259    =head3 GenomeAssignments
1260    
1261        my $fidHash = $sprout->GenomeAssignments($genomeID);
1262    
1263    Return a list of a genome's assigned features. The return hash will contain each
1264    assigned feature of the genome mapped to the text of its most recent functional
1265    assignment.
1266    
1267    =over 4
1268    
1269    =item genomeID
1270    
1271    ID of the genome whose functional assignments are desired.
1272    
1273    =item RETURN
1274    
1275    Returns a reference to a hash which maps each feature to its most recent
1276    functional assignment.
1277    
1278    =back
1279    
1280    =cut
1281    
1282    sub GenomeAssignments {
1283        # Get the parameters.
1284        my ($self, $genomeID) = @_;
1285        # Declare the return variable.
1286        my $retVal = {};
1287        # Query the genome's features.
1288        my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
1289                               [$genomeID]);
1290        # Loop through the features.
1291        while (my $data = $query->Fetch) {
1292            # Get the feature ID and assignment.
1293            my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1294            if ($assignment) {
1295                $retVal->{$fid} = $assignment;
1296            }
1297        }
1298        # Return the result.
1299        return $retVal;
1300    }
1301    
1302  =head3 ContigLength  =head3 ContigLength
1303    
1304  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1305    
1306  Compute the length of a contig.  Compute the length of a contig.
1307    
# Line 810  Line 1321 
1321  #: Return Type $;  #: Return Type $;
1322  sub ContigLength {  sub ContigLength {
1323          # Get the parameters.          # Get the parameters.
1324          my $self = shift @_;      my ($self, $contigID) = @_;
         my ($contigID) = @_;  
1325          # Get the contig's last sequence.          # Get the contig's last sequence.
1326          my $query = $self->Get(['IsMadeUpOf'],          my $query = $self->Get(['IsMadeUpOf'],
1327                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",                  "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
# Line 822  Line 1332 
1332          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
1333          if ($sequence) {          if ($sequence) {
1334                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
1335                  $retVal = $start + $len;          $retVal = $start + $len - 1;
1336        }
1337        # Return the result.
1338        return $retVal;
1339    }
1340    
1341    =head3 ClusterPEGs
1342    
1343        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1344    
1345    Cluster the PEGs in a list according to the cluster coding scheme of the specified
1346    subsystem. In order for this to work properly, the subsystem object must have
1347    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1348    B<get_row> methods. This causes the cluster numbers to be pulled into the
1349    subsystem's color hash. If a PEG is not found in the color hash, it will not
1350    appear in the output sequence.
1351    
1352    =over 4
1353    
1354    =item sub
1355    
1356    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
1357    method.
1358    
1359    =item pegs
1360    
1361    Reference to the list of PEGs to be clustered.
1362    
1363    =item RETURN
1364    
1365    Returns a list of the PEGs, grouped into smaller lists by cluster number.
1366    
1367    =back
1368    
1369    =cut
1370    #: Return Type $@@;
1371    sub ClusterPEGs {
1372        # Get the parameters.
1373        my ($self, $sub, $pegs) = @_;
1374        # Declare the return variable.
1375        my $retVal = [];
1376        # Loop through the PEGs, creating arrays for each cluster.
1377        for my $pegID (@{$pegs}) {
1378            my $clusterNumber = $sub->get_cluster_number($pegID);
1379            # Only proceed if the PEG is in a cluster.
1380            if ($clusterNumber >= 0) {
1381                # Push this PEG onto the sub-list for the specified cluster number.
1382                push @{$retVal->[$clusterNumber]}, $pegID;
1383            }
1384          }          }
1385          # Return the result.          # Return the result.
1386          return $retVal;          return $retVal;
# Line 830  Line 1388 
1388    
1389  =head3 GenesInRegion  =head3 GenesInRegion
1390    
1391  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1392    
1393  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1394    
# Line 853  Line 1411 
1411  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
1412  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
1413  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
1414  the start and stop values.  the start and stop values. The first element (that is, the list of features) is sorted
1415    roughly by location.
1416    
1417  =back  =back
1418    
1419  =cut  =cut
1420  #: Return Type @;  
1421  sub GenesInRegion {  sub GenesInRegion {
1422          # Get the parameters.          # Get the parameters.
1423          my $self = shift @_;      my ($self, $contigID, $start, $stop) = @_;
1424          my ($contigID, $start, $stop) = @_;      # Get the maximum segment length.
1425        my $maximumSegmentLength = $self->MaxSegment;
1426        # Prime the values we'll use for the returned beginning and end.
1427        my @initialMinMax = ($self->ContigLength($contigID), 0);
1428        my ($min, $max) = @initialMinMax;
1429        # Get the overlapping features.
1430        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1431        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1432        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1433        # of the feature's locations.
1434        my %featureMap = ();
1435        # Loop through them to do the begin/end analysis.
1436        for my $featureObject (@featureObjects) {
1437            # Get the feature's location string. This may contain multiple actual locations.
1438            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1439            my @locationSegments = split /\s*,\s*/, $locations;
1440            # Loop through the locations.
1441            for my $locationSegment (@locationSegments) {
1442                # Construct an object for the location.
1443                my $locationObject = BasicLocation->new($locationSegment);
1444                # Merge the current segment's begin and end into the min and max.
1445                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1446                my ($beg, $end);
1447                if (exists $featureMap{$fid}) {
1448                    ($beg, $end) = @{$featureMap{$fid}};
1449                    $beg = $left if $left < $beg;
1450                    $end = $right if $right > $end;
1451                } else {
1452                    ($beg, $end) = ($left, $right);
1453                }
1454                $min = $beg if $beg < $min;
1455                $max = $end if $end > $max;
1456                # Store the feature's new extent back into the hash table.
1457                $featureMap{$fid} = [$beg, $end];
1458            }
1459        }
1460        # Now we must compute the list of the IDs for the features found. We start with a list
1461        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1462        # but the result of the sort will be the same.)
1463        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1464        # Now we sort by midpoint and yank out the feature IDs.
1465        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1466        # Return it along with the min and max.
1467        return (\@retVal, $min, $max);
1468    }
1469    
1470    =head3 GeneDataInRegion
1471    
1472        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1473    
1474    List the features which overlap a specified region in a contig.
1475    
1476    =over 4
1477    
1478    =item contigID
1479    
1480    ID of the contig containing the region of interest.
1481    
1482    =item start
1483    
1484    Offset of the first residue in the region of interest.
1485    
1486    =item stop
1487    
1488    Offset of the last residue in the region of interest.
1489    
1490    =item RETURN
1491    
1492    Returns a list of B<ERDBObjects> for the desired features. Each object will
1493    contain a B<Feature> record.
1494    
1495    =back
1496    
1497    =cut
1498    
1499    sub GeneDataInRegion {
1500        # Get the parameters.
1501        my ($self, $contigID, $start, $stop) = @_;
1502          # Get the maximum segment length.          # Get the maximum segment length.
1503          my $maximumSegmentLength = $self->MaxSegment;          my $maximumSegmentLength = $self->MaxSegment;
1504          # Create a hash to receive the feature list. We use a hash so that we can eliminate          # Create a hash to receive the feature list. We use a hash so that we can eliminate
1505          # duplicates easily.      # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1506        # ERDBObject from the query.
1507          my %featuresFound = ();          my %featuresFound = ();
1508          # Prime the values we'll use for the returned beginning and end.      # Create a table of parameters for the queries. Each query looks for features travelling in
         my ($min, $max) = ($self->ContigLength($contigID), 0);  
         # Create a table of parameters for each query. Each query looks for features travelling in  
1509          # 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,
1510          # 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
1511          # 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 1514 
1514          # Loop through the query parameters.          # Loop through the query parameters.
1515          for my $parms (values %queryParms) {          for my $parms (values %queryParms) {
1516                  # Create the query.                  # Create the query.
1517                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1518                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1519                          $parms);                          $parms);
1520                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1521                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1522                          # Get the data about this segment.                          # Get the data about this segment.
1523                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1524                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1525                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1526                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1527                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1528                          # length.                          # length.
1529                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1530                          if ($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.  
                                         $found = 1;  
                                 }  
                         }  
1531                          if ($found) {                          if ($found) {
1532                                  # Here we need to record the feature and update the minimum and maximum.                  # Save this feature in the result list.
1533                                  $featuresFound{$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; }  
1534                          }                          }
1535                  }                  }
1536          }          }
1537          # Compute a list of the IDs for the features found.      # Return the ERDB objects for the features found.
1538          my @list = (sort (keys %featuresFound));      return values %featuresFound;
         # Return it along with the min and max.  
         return (\@list, $min, $max);  
1539  }  }
1540    
1541  =head3 FType  =head3 FType
1542    
1543  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1544    
1545  Return the type of a feature.  Return the type of a feature.
1546    
# Line 944  Line 1561 
1561  #: Return Type $;  #: Return Type $;
1562  sub FType {  sub FType {
1563          # Get the parameters.          # Get the parameters.
1564          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1565          # Get the specified feature's type.          # Get the specified feature's type.
1566          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1567          # Return the result.          # Return the result.
# Line 954  Line 1570 
1570    
1571  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1572    
1573  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1574    
1575  Return the annotations of a feature.  Return the annotations of a feature.
1576    
# Line 964  Line 1580 
1580    
1581  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1582    
1583    =item rawFlag
1584    
1585    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1586    will be returned in human-readable form.
1587    
1588  =item RETURN  =item RETURN
1589    
1590  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.
1591    
1592  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1593    
1594  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1595    
1596  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1597    
# Line 982  Line 1603 
1603  #: Return Type @%;  #: Return Type @%;
1604  sub FeatureAnnotations {  sub FeatureAnnotations {
1605          # Get the parameters.          # Get the parameters.
1606          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1607          # 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.
1608          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1609                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 996  Line 1616 
1616                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1617                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1618                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1619            # Convert the time, if necessary.
1620            if (! $rawFlag) {
1621                $timeStamp = FriendlyTimestamp($timeStamp);
1622            }
1623                  # Assemble them into a hash.                  # Assemble them into a hash.
1624          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1625                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1626                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1627                  # Add it to the return list.                  # Add it to the return list.
1628                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1009  Line 1633 
1633    
1634  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1635    
1636  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1637    
1638  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
1639  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,
1640  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
1641  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,
1642  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.
1643  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1644    recent one.
1645    
1646  =over 4  =over 4
1647    
# Line 1026  Line 1651 
1651    
1652  =item RETURN  =item RETURN
1653    
1654  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1655    
1656  =back  =back
1657    
# Line 1034  Line 1659 
1659  #: Return Type %;  #: Return Type %;
1660  sub AllFunctionsOf {  sub AllFunctionsOf {
1661          # Get the parameters.          # Get the parameters.
1662          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1663          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1664          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1665                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1666                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1667                                               'MadeAnnotation(from-link)']);
1668          # Declare the return hash.          # Declare the return hash.
1669          my %retVal;          my %retVal;
1670        # Now we sort the assignments by timestamp in reverse.
1671        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1672          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1673          for my $text (@query) {      for my $annotation (@sortedQuery) {
1674            # Get the annotation fields.
1675            my ($timeStamp, $text, $user) = @{$annotation};
1676                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1677                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1678                  if ($user) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1679                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1680                          $retVal{$function} = $user;              # previous assignment for this user, so we stuff it in the
1681                # return hash.
1682                $retVal{$actualUser} = $function;
1683                  }                  }
1684          }          }
1685          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1057  Line 1688 
1688    
1689  =head3 FunctionOf  =head3 FunctionOf
1690    
1691  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1692    
1693  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1694    
1695  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
1696  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
1697  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.  
1698    
1699  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
1700  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
1701  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
1702  is trusted.  is trusted.
1703    
1704  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.
1705  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.  
1706    
1707  =over 4  =over 4
1708    
# Line 1085  Line 1712 
1712    
1713  =item userID (optional)  =item userID (optional)
1714    
1715  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
1716  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1717    
1718  =item RETURN  =item RETURN
1719    
# Line 1098  Line 1725 
1725  #: Return Type $;  #: Return Type $;
1726  sub FunctionOf {  sub FunctionOf {
1727          # Get the parameters.          # Get the parameters.
1728          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
         my ($featureID, $userID) = @_;  
1729      # Declare the return value.      # Declare the return value.
1730      my $retVal;      my $retVal;
1731      # Determine the ID type.      # Find a FIG ID for this feature.
1732      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1733          # Here we have a FIG feature ID. We must build the list of trusted      # Only proceed if we have an ID.
1734          # users.      if ($fid) {
1735            # Here we have a FIG feature ID.
1736            if (!$userID) {
1737                # Use the primary assignment.
1738                ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1739            } else {
1740                # We must build the list of trusted users.
1741          my %trusteeTable = ();          my %trusteeTable = ();
1742          # Check the user ID.          # Check the user ID.
1743          if (!$userID) {          if (!$userID) {
# Line 1127  Line 1759 
1759              }              }
1760          }          }
1761          # 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.
1762          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1763                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1764                                 [$featureID]);                                     [$fid]);
1765          my $timeSelected = 0;          my $timeSelected = 0;
1766          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1767          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1768              # Get the annotation text.              # Get the annotation text.
1769              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1770                                                             'Annotation(time)', 'MadeAnnotation(from-link)']);
1771              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1772              my ($user, $type, $function) = split(/\n/, $text);                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1773              if ($type =~ m/^set $user function to$/i) {                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1774                    if ($actualUser) {
1775                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1776                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1777                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                      if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1778                      $retVal = $function;                      $retVal = $function;
1779                      $timeSelected = $time;                      $timeSelected = $time;
1780                  }                  }
1781              }              }
1782          }          }
1783      } else {          }
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['func']);  
1784      }      }
1785          # Return the assignment found.          # Return the assignment found.
1786          return $retVal;          return $retVal;
1787  }  }
1788    
1789    =head3 FunctionsOf
1790    
1791        my @functionList = $sprout->FunctionOf($featureID, $userID);
1792    
1793    Return the functional assignments of a particular feature.
1794    
1795    The functional assignment is handled differently depending on the type of feature. If
1796    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1797    assignment is a type of annotation. The format of an assignment is described in
1798    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1799    annotation itself because it's a text field; however, this is not a big problem because
1800    most features only have a small number of annotations.
1801    
1802    =over 4
1803    
1804    =item featureID
1805    
1806    ID of the feature whose functional assignments are desired.
1807    
1808    =item RETURN
1809    
1810    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1811    that user.
1812    
1813    =back
1814    
1815    =cut
1816    #: Return Type @@;
1817    sub FunctionsOf {
1818        # Get the parameters.
1819        my ($self, $featureID) = @_;
1820        # Declare the return value.
1821        my @retVal = ();
1822        # Convert to a FIG ID.
1823        my ($fid) = $self->FeaturesByAlias($featureID);
1824        # Only proceed if we found one.
1825        if ($fid) {
1826            # Here we have a FIG feature ID. We must build the list of trusted
1827            # users.
1828            my %trusteeTable = ();
1829            # Build a query for all of the feature's annotations, sorted by date.
1830            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1831                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1832                                   [$fid]);
1833            my $timeSelected = 0;
1834            # Loop until we run out of annotations.
1835            while (my $annotation = $query->Fetch()) {
1836                # Get the annotation text.
1837                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1838                                                                'Annotation(time)',
1839                                                                'MadeAnnotation(user)']);
1840                # Check to see if this is a functional assignment for a trusted user.
1841                my ($actualUser, $function) = _ParseAssignment($user, $text);
1842                if ($actualUser) {
1843                    # Here it is a functional assignment.
1844                    push @retVal, [$actualUser, $function];
1845                }
1846            }
1847        }
1848        # Return the assignments found.
1849        return @retVal;
1850    }
1851    
1852  =head3 BBHList  =head3 BBHList
1853    
1854  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1855    
1856  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
1857  on a specified target genome.  on a specified target genome.
# Line 1175  Line 1868 
1868    
1869  =item RETURN  =item RETURN
1870    
1871  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
1872  their best hits.  on the target genome.
1873    
1874  =back  =back
1875    
# Line 1184  Line 1877 
1877  #: Return Type %;  #: Return Type %;
1878  sub BBHList {  sub BBHList {
1879          # Get the parameters.          # Get the parameters.
1880          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1881          # Create the return structure.          # Create the return structure.
1882          my %retVal = ();          my %retVal = ();
1883          # Loop through the incoming features.          # Loop through the incoming features.
1884          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1885                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1886                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my $bbhData = FIGRules::BBHData($featureID);
1887                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1888                                                             [$featureID, $genomeID]);          my @found = ();
1889                  # Look for the best hit.          for my $bbh (@$bbhData) {
1890                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1891                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1892                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1893                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1894                  }                  }
1895          }          }
1896            $retVal{$featureID} = \@found;
1897        }
1898          # Return the mapping.          # Return the mapping.
1899          return \%retVal;          return \%retVal;
1900  }  }
1901    
1902  =head3 FeatureAliases  =head3 SimList
1903    
1904  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my %similarities = $sprout->SimList($featureID, $count);
1905    
1906  Return a list of the aliases for a specified feature.  Return a list of the similarities to the specified feature.
1907    
1908    This method just returns the bidirectional best hits for performance reasons.
1909    
1910  =over 4  =over 4
1911    
1912  =item featureID  =item featureID
1913    
1914  ID of the feature whose aliases are desired.  ID of the feature whose similarities are desired.
1915    
1916  =item RETURN  =item count
1917    
1918  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.  
1919    
1920  =back  =back
1921    
1922  =cut  =cut
1923  #: Return Type @;  #: Return Type %;
1924  sub FeatureAliases {  sub SimList {
1925          # Get the parameters.          # Get the parameters.
1926          my $self = shift @_;      my ($self, $featureID, $count) = @_;
1927          my ($featureID) = @_;      # Ask for the best hits.
1928          # Get the desired feature's aliases      my $lists = FIGRules::BBHData($featureID);
1929          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      # Create the return value.
1930        my %retVal = ();
1931        for my $tuple (@$lists) {
1932            $retVal{$tuple->[0]} = $tuple->[1];
1933        }
1934          # Return the result.          # Return the result.
1935          return @retVal;      return %retVal;
1936  }  }
1937    
1938  =head3 GenomeOf  =head3 IsComplete
1939    
1940  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $flag = $sprout->IsComplete($genomeID);
1941    
1942  Return the genome that contains a specified feature.  Return TRUE if the specified genome is complete, else FALSE.
1943    
1944  =over 4  =over 4
1945    
1946  =item featureID  =item genomeID
1947    
1948  ID of the feature whose genome is desired.  ID of the genome whose completeness status is desired.
1949    
1950  =item RETURN  =item RETURN
1951    
1952  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
1953  an undefined value.  not found.
1954    
1955  =back  =back
1956    
1957  =cut  =cut
1958  #: Return Type $;  #: Return Type $;
1959  sub GenomeOf {  sub IsComplete {
1960          # Get the parameters.          # Get the parameters.
1961          my $self = shift @_;      my ($self, $genomeID) = @_;
1962          my ($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.  
1963          my $retVal;          my $retVal;
1964          # Get the genome ID.      # Get the genome's data.
1965          if (my $relationship = $query->Fetch()) {      my $genomeData = $self->_GenomeData($genomeID);
1966                  ($retVal) = $relationship->Value('HasContig(from-link)');      # Only proceed if it exists.
1967        if (defined $genomeData) {
1968            # The genome exists, so get the completeness flag.
1969            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1970          }          }
1971          # Return the value found.      # Return the result.
1972          return $retVal;          return $retVal;
1973  }  }
1974    
1975  =head3 CoupledFeatures  =head3 FeatureAliases
1976    
1977  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1978    
1979  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.  
1980    
1981  =over 4  =over 4
1982    
1983  =item featureID  =item featureID
1984    
1985  ID of the feature whose functionally-coupled brethren are desired.  ID of the feature whose aliases are desired.
1986    
1987  =item RETURN  =item RETURN
1988    
1989  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
1990    return an empty list.
1991    
1992  =back  =back
1993    
1994  =cut  =cut
1995  #: Return Type %;  #: Return Type @;
1996  sub CoupledFeatures {  sub FeatureAliases {
1997          # Get the parameters.          # Get the parameters.
1998          my $self = shift @_;      my ($self, $featureID) = @_;
1999          my ($featureID) = @_;      # Get the desired feature's aliases
2000          # 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)');
2001          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      # Return the result.
2002          # (B,A) will also be found.      return @retVal;
2003          my $query = $self->Get(['IsClusteredOnChromosomeWith'],  }
2004                                                     "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
2005          # This value will be set to TRUE if we find at least one coupled feature.  =head3 GenomeOf
2006          my $found = 0;  
2007          # Create the return hash.      my $genomeID = $sprout->GenomeOf($featureID);
2008    
2009    Return the genome that contains a specified feature or contig.
2010    
2011    =over 4
2012    
2013    =item featureID
2014    
2015    ID of the feature or contig whose genome is desired.
2016    
2017    =item RETURN
2018    
2019    Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
2020    found, returns an undefined value.
2021    
2022    =back
2023    
2024    =cut
2025    #: Return Type $;
2026    sub GenomeOf {
2027        # Get the parameters.
2028        my ($self, $featureID) = @_;
2029        # Declare the return value.
2030        my $retVal;
2031        # Parse the genome ID from the feature ID.
2032        if ($featureID =~ /^fig\|(\d+\.\d+)/) {
2033            $retVal = $1;
2034        } else {
2035            # Find the feature by alias.
2036            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
2037            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
2038                $retVal = $1;
2039            }
2040        }
2041        # Return the value found.
2042        return $retVal;
2043    }
2044    
2045    =head3 CoupledFeatures
2046    
2047        my %coupleHash = $sprout->CoupledFeatures($featureID);
2048    
2049    Return the features functionally coupled with a specified feature. Features are considered
2050    functionally coupled if they tend to be clustered on the same chromosome.
2051    
2052    =over 4
2053    
2054    =item featureID
2055    
2056    ID of the feature whose functionally-coupled brethren are desired.
2057    
2058    =item RETURN
2059    
2060    A hash mapping the functionally-coupled feature IDs to the coupling score.
2061    
2062    =back
2063    
2064    =cut
2065    #: Return Type %;
2066    sub CoupledFeatures {
2067        # Get the parameters.
2068        my ($self, $featureID) = @_;
2069        # Ask the coupling server for the data.
2070        Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2071        my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2072        Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2073        # Form them into a hash.
2074          my %retVal = ();          my %retVal = ();
2075          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2076          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2077                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
2078                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
2079                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
2080                  $found = 1;              $retVal{$featureID2} = $score;
2081          }          }
         # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
         # the incoming feature as well.  
         if ($found) {  
                 $retVal{$featureID} = 9999;  
2082      }      }
2083          # Return the hash.          # Return the hash.
2084          return %retVal;          return %retVal;
2085  }  }
2086    
2087  =head3 GetEntityTypes  =head3 CouplingEvidence
2088    
2089        my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2090    
2091    Return the evidence for a functional coupling.
2092    
2093    A pair of features is considered evidence of a coupling between two other
2094    features if they occur close together on a contig and both are similar to
2095    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
2096    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
2097    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
2098    similar to B<A2>.
2099    
2100    The score of a coupling is determined by the number of pieces of evidence
2101    that are considered I<representative>. If several evidence items belong to
2102    a group of genomes that are close to each other, only one of those items
2103    is considered representative. The other evidence items are presumed to be
2104    there because of the relationship between the genomes rather than because
2105    the two proteins generated by the features have a related functionality.
2106    
2107    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
2108    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
2109    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
2110    and FALSE otherwise.
2111    
2112    =over 4
2113    
2114    =item peg1
2115    
2116    ID of the feature of interest.
2117    
2118    =item peg2
2119    
2120    ID of a feature functionally coupled to the feature of interest.
2121    
2122    =item RETURN
2123    
2124    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
2125    of interest, a feature similar to the functionally coupled feature, and a flag
2126    that is TRUE for a representative piece of evidence and FALSE otherwise.
2127    
2128    =back
2129    
2130    =cut
2131    #: Return Type @@;
2132    sub CouplingEvidence {
2133        # Get the parameters.
2134        my ($self, $peg1, $peg2) = @_;
2135        # Declare the return variable.
2136        my @retVal = ();
2137        # Get the coupling and evidence data.
2138        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2139        # Loop through the raw data, saving the ones that are in NMPDR genomes.
2140        for my $rawTuple (@rawData) {
2141            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2142                push @retVal, $rawTuple;
2143            }
2144        }
2145        # Return the result.
2146        return @retVal;
2147    }
2148    
2149    =head3 GetSynonymGroup
2150    
2151        my $id = $sprout->GetSynonymGroup($fid);
2152    
2153    Return the synonym group name for the specified feature.
2154    
2155    =over 4
2156    
2157    =item fid
2158    
2159    ID of the feature whose synonym group is desired.
2160    
2161    =item RETURN
2162    
2163    The name of the synonym group to which the feature belongs. If the feature does
2164    not belong to a synonym group, the feature ID itself is returned.
2165    
2166    =back
2167    
2168    =cut
2169    
2170    sub GetSynonymGroup {
2171        # Get the parameters.
2172        my ($self, $fid) = @_;
2173        # Declare the return variable.
2174        my $retVal;
2175        # Find the synonym group.
2176        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
2177                                       [$fid], 'IsSynonymGroupFor(from-link)');
2178        # Check to see if we found anything.
2179        if (@groups) {
2180            $retVal = $groups[0];
2181        } else {
2182            $retVal = $fid;
2183        }
2184        # Return the result.
2185        return $retVal;
2186    }
2187    
2188    =head3 GetBoundaries
2189    
2190        my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2191    
2192    Determine the begin and end boundaries for the locations in a list. All of the
2193    locations must belong to the same contig and have mostly the same direction in
2194    order for this method to produce a meaningful result. The resulting
2195    begin/end pair will contain all of the bases in any of the locations.
2196    
2197  C<< my @entityList = $sprout->GetEntityTypes(); >>  =over 4
2198    
2199    =item locList
2200    
2201    List of locations to process.
2202    
2203    =item RETURN
2204    
2205    Returns a 3-tuple consisting of the contig ID, the beginning boundary,
2206    and the ending boundary. The beginning boundary will be left of the
2207    end for mostly-forward locations and right of the end for mostly-backward
2208    locations.
2209    
2210  Return the list of supported entity types.  =back
2211    
2212  =cut  =cut
2213  #: Return Type @;  
2214  sub GetEntityTypes {  sub GetBoundaries {
2215          # Get the parameters.          # Get the parameters.
2216          my $self = shift @_;      my ($self, @locList) = @_;
2217          # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
2218          my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
2219          # Get its entity type list.      # Get the last location and parse it.
2220          my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
2221        # Prime the loop with its data.
2222        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
2223        # Count its direction.
2224        $counts{$locObject->Dir}++;
2225        # Loop through the remaining locations. Note that in most situations, this loop
2226        # will not iterate at all, because most of the time we will be dealing with a
2227        # singleton list.
2228        for my $loc (@locList) {
2229            # Create a location object.
2230            my $locObject = BasicLocation->new($loc);
2231            # Count the direction.
2232            $counts{$locObject->Dir}++;
2233            # Get the left end and the right end.
2234            my $left = $locObject->Left;
2235            my $right = $locObject->Right;
2236            # Merge them into the return variables.
2237            if ($left < $beg) {
2238                $beg = $left;
2239            }
2240            if ($right > $end) {
2241                $end = $right;
2242            }
2243        }
2244        # If the most common direction is reverse, flip the begin and end markers.
2245        if ($counts{'-'} > $counts{'+'}) {
2246            ($beg, $end) = ($end, $beg);
2247        }
2248        # Return the result.
2249        return ($contig, $beg, $end);
2250  }  }
2251    
2252  =head3 ReadFasta  =head3 ReadFasta
2253    
2254  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2255    
2256  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2257  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1384  Line 2293 
2293                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
2294                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
2295                          if ($id) {                          if ($id) {
2296                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
2297                          }                          }
2298                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
2299                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
2300                  } else {                  } else {
2301                          # 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.
2302                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
2303                # case.
2304                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
2305                          $sequence .= $1;                          $sequence .= $1;
2306                  }                  }
2307          }          }
2308          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
2309          if ($sequence) {          if ($sequence) {
2310                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
2311          }          }
2312        # Close the file.
2313        close FASTAFILE;
2314          # Return the hash constructed from the file.          # Return the hash constructed from the file.
2315          return %retVal;          return %retVal;
2316  }  }
2317    
2318  =head3 FormatLocations  =head3 FormatLocations
2319    
2320  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2321    
2322  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
2323  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
2324  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,
2325    it will not be changed; otherwise, it will be converted. This method can also be used to
2326    perform the reverse task-- insuring that all the locations are in the old format.
2327    
2328  =over 4  =over 4
2329    
# Line 1436  Line 2350 
2350  #: Return Type @;  #: Return Type @;
2351  sub FormatLocations {  sub FormatLocations {
2352          # Get the parameters.          # Get the parameters.
2353          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
2354          # Create the return list.          # Create the return list.
2355          my @retVal = ();          my @retVal = ();
2356          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
2357          if ($locations eq '') {          if ($locations eq '') {
2358              confess "No locations specified.";          Confess("No locations specified.");
2359          } else {          } else {
2360                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
2361                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1469  Line 2382 
2382    
2383  =head3 DumpData  =head3 DumpData
2384    
2385  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2386    
2387  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.
2388    
# Line 1477  Line 2390 
2390    
2391  sub DumpData {  sub DumpData {
2392          # Get the parameters.          # Get the parameters.
2393          my $self = shift @_;      my ($self) = @_;
2394          # Get the data directory name.          # Get the data directory name.
2395          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2396          # Dump the relations.          # Dump the relations.
2397          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2398  }  }
2399    
2400  =head3 XMLFileName  =head3 XMLFileName
2401    
2402  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2403    
2404  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2405    
2406  =cut  =cut
2407  #: Return Type $;  #: Return Type $;
2408  sub XMLFileName {  sub XMLFileName {
2409          my $self = shift @_;      my ($self) = @_;
2410          return $self->{_xmlName};          return $self->{_xmlName};
2411  }  }
2412    
2413    =head3 GetGenomeNameData
2414    
2415        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2416    
2417    Return the genus, species, and unique characterization for a genome. This
2418    is similar to L</GenusSpecies>, with the exception that it returns the
2419    values in three seperate fields.
2420    
2421    =over 4
2422    
2423    =item genomeID
2424    
2425    ID of the genome whose name data is desired.
2426    
2427    =item RETURN
2428    
2429    Returns a three-element list, consisting of the genus, species, and strain
2430    of the specified genome. If the genome is not found, an error occurs.
2431    
2432    =back
2433    
2434    =cut
2435    
2436    sub GetGenomeNameData {
2437        # Get the parameters.
2438        my ($self, $genomeID) = @_;
2439        # Declare the return variables.
2440        my ($genus, $species, $strain);
2441        # Get the genome's data.
2442        my $genomeData = $self->_GenomeData($genomeID);
2443        # Only proceed if the genome exists.
2444        if (defined $genomeData) {
2445            # Get the desired values.
2446            ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2447                                                               'Genome(species)',
2448                                                               'Genome(unique-characterization)']);
2449        } else {
2450            # Throw an error because they were not found.
2451            Confess("Genome $genomeID not found in database.");
2452        }
2453        # Return the results.
2454        return ($genus, $species, $strain);
2455    }
2456    
2457    =head3 GetGenomeByNameData
2458    
2459        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2460    
2461    Return a list of the IDs of the genomes with the specified genus,
2462    species, and strain. In almost every case, there will be either zero or
2463    one IDs returned; however, two or more IDs could be returned if there are
2464    multiple versions of the genome in the database.
2465    
2466    =over 4
2467    
2468    =item genus
2469    
2470    Genus of the desired genome.
2471    
2472    =item species
2473    
2474    Species of the desired genome.
2475    
2476    =item strain
2477    
2478    Strain (unique characterization) of the desired genome. This may be an empty
2479    string, in which case it is presumed that the desired genome has no strain
2480    specified.
2481    
2482    =item RETURN
2483    
2484    Returns a list of the IDs of the genomes having the specified genus, species, and
2485    strain.
2486    
2487    =back
2488    
2489    =cut
2490    
2491    sub GetGenomeByNameData {
2492        # Get the parameters.
2493        my ($self, $genus, $species, $strain) = @_;
2494        # Try to find the genomes.
2495        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2496                                    [$genus, $species, $strain], 'Genome(id)');
2497        # Return the result.
2498        return @retVal;
2499    }
2500    
2501  =head3 Insert  =head3 Insert
2502    
2503  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2504    
2505  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
2506  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 1508  Line 2509 
2509  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
2510  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>.
2511    
2512  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']});
2513    
2514  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
2515  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>.
2516    
2517  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'});
2518    
2519  =over 4  =over 4
2520    
# Line 1531  Line 2532 
2532  #: Return Type ;  #: Return Type ;
2533  sub Insert {  sub Insert {
2534          # Get the parameters.          # Get the parameters.
2535          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
2536          # Call the underlying method.          # Call the underlying method.
2537          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2538  }  }
2539    
2540  =head3 Annotate  =head3 Annotate
2541    
2542  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2543    
2544  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
2545  specified feature and user.  specified feature and user.
# Line 1573  Line 2573 
2573  #: Return Type $;  #: Return Type $;
2574  sub Annotate {  sub Annotate {
2575          # Get the parameters.          # Get the parameters.
2576          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
2577          # Create the annotation ID.          # Create the annotation ID.
2578          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
2579          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1594  Line 2593 
2593    
2594  =head3 AssignFunction  =head3 AssignFunction
2595    
2596  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2597    
2598  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
2599  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.  
2600    
2601  =over 4  =over 4
2602    
# Line 1608  Line 2606 
2606    
2607  =item user  =item user
2608    
2609  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>.
2610    
2611  =item function  =item function
2612    
2613  Text of the function being assigned.  Text of the function being assigned.
2614    
2615    =item assigningUser (optional)
2616    
2617    Name of the individual user making the assignment. If omitted, defaults to the user group.
2618    
2619  =item RETURN  =item RETURN
2620    
2621  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1624  Line 2626 
2626  #: Return Type $;  #: Return Type $;
2627  sub AssignFunction {  sub AssignFunction {
2628          # Get the parameters.          # Get the parameters.
2629          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2630          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2631        if (! $assigningUser) {
2632            $assigningUser = $user;
2633        }
2634          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2635          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2636          # Get the current time.          # Get the current time.
2637          my $now = time;          my $now = time;
2638          # Declare the return variable.          # Declare the return variable.
# Line 1648  Line 2653 
2653    
2654  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2655    
2656  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2657    
2658  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
2659  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 1672  Line 2677 
2677  #: Return Type @;  #: Return Type @;
2678  sub FeaturesByAlias {  sub FeaturesByAlias {
2679          # Get the parameters.          # Get the parameters.
2680          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2681          # Declare the return variable.          # Declare the return variable.
2682          my @retVal = ();          my @retVal = ();
2683          # Parse the alias.          # Parse the alias.
# Line 1683  Line 2687 
2687                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2688          } else {          } else {
2689                  # 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.
2690                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2691          }          }
2692          # Return the result.          # Return the result.
2693          return @retVal;          return @retVal;
2694  }  }
2695    
 =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;  
 }  
   
2696  =head3 FeatureTranslation  =head3 FeatureTranslation
2697    
2698  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2699    
2700  Return the translation of a feature.  Return the translation of a feature.
2701    
# Line 1746  Line 2715 
2715  #: Return Type $;  #: Return Type $;
2716  sub FeatureTranslation {  sub FeatureTranslation {
2717          # Get the parameters.          # Get the parameters.
2718          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2719          # Get the specified feature's translation.          # Get the specified feature's translation.
2720          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2721          return $retVal;          return $retVal;
# Line 1755  Line 2723 
2723    
2724  =head3 Taxonomy  =head3 Taxonomy
2725    
2726  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2727    
2728  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
2729  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>,
2730  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2731    
2732  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2733    
2734  =over 4  =over 4
2735    
# Line 1779  Line 2747 
2747  #: Return Type @;  #: Return Type @;
2748  sub Taxonomy {  sub Taxonomy {
2749          # Get the parameters.          # Get the parameters.
2750          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
         # Find the specified genome's taxonomy string.  
         my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2751          # Declare the return variable.          # Declare the return variable.
2752          my @retVal = ();          my @retVal = ();
2753          # If we found the genome, return its taxonomy string.      # Get the genome data.
2754          if ($list) {      my $genomeData = $self->_GenomeData($genome);
2755                  @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2756        if (defined $genomeData) {
2757            # Create the taxonomy from the taxonomy string.
2758            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2759          } else {          } else {
2760            # Genome doesn't exist, so emit a warning.
2761                  Trace("Genome \"$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);
2762          }          }
2763          # Return the value found.          # Return the value found.
# Line 1797  Line 2766 
2766    
2767  =head3 CrudeDistance  =head3 CrudeDistance
2768    
2769  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2770    
2771  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
2772  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 1823  Line 2792 
2792  #: Return Type $;  #: Return Type $;
2793  sub CrudeDistance {  sub CrudeDistance {
2794          # Get the parameters.          # Get the parameters.
2795          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2796          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2797          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2798          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1834  Line 2802 
2802          }          }
2803          my @taxA = $self->Taxonomy($genomeA);          my @taxA = $self->Taxonomy($genomeA);
2804          my @taxB = $self->Taxonomy($genomeB);          my @taxB = $self->Taxonomy($genomeB);
2805          # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2806          # 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;  
         }  
2807      return $retVal;      return $retVal;
2808  }  }
2809    
2810  =head3 RoleName  =head3 RoleName
2811    
2812  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2813    
2814  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
2815  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 1871  Line 2830 
2830  #: Return Type $;  #: Return Type $;
2831  sub RoleName {  sub RoleName {
2832          # Get the parameters.          # Get the parameters.
2833          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2834          # Get the specified role's name.          # Get the specified role's name.
2835          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2836          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1885  Line 2843 
2843    
2844  =head3 RoleDiagrams  =head3 RoleDiagrams
2845    
2846  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2847    
2848  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2849    
# Line 1905  Line 2863 
2863  #: Return Type @;  #: Return Type @;
2864  sub RoleDiagrams {  sub RoleDiagrams {
2865          # Get the parameters.          # Get the parameters.
2866          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2867          # Query for the diagrams.          # Query for the diagrams.
2868          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2869                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1916  Line 2873 
2873    
2874  =head3 FeatureProperties  =head3 FeatureProperties
2875    
2876  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2877    
2878  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
2879  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
2880  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
2881  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
2882  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.  
2883    
2884  =over 4  =over 4
2885    
# Line 1934  Line 2889 
2889    
2890  =item RETURN  =item RETURN
2891    
2892  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.  
2893    
2894  =back  =back
2895    
# Line 1943  Line 2897 
2897  #: Return Type @@;  #: Return Type @@;
2898  sub FeatureProperties {  sub FeatureProperties {
2899          # Get the parameters.          # Get the parameters.
2900          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2901          # Get the properties.          # Get the properties.
2902          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->ca->GetAttributes($featureID);
2903                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2904                                                           'HasProperty(evidence)']);      my @retVal = ();
2905        for my $attributeRow (@attributes) {
2906            shift @{$attributeRow};
2907            push @retVal, $attributeRow;
2908        }
2909          # Return the resulting list.          # Return the resulting list.
2910          return @retVal;          return @retVal;
2911  }  }
2912    
2913  =head3 DiagramName  =head3 DiagramName
2914    
2915  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2916    
2917  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2918    
# Line 1975  Line 2932 
2932  #: Return Type $;  #: Return Type $;
2933  sub DiagramName {  sub DiagramName {
2934          # Get the parameters.          # Get the parameters.
2935          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2936          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2937          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2938          return $retVal;          return $retVal;
2939  }  }
2940    
2941    =head3 PropertyID
2942    
2943        my $id = $sprout->PropertyID($propName, $propValue);
2944    
2945    Return the ID of the specified property name and value pair, if the
2946    pair exists. Only a small subset of the FIG attributes are stored as
2947    Sprout properties, mostly for use in search optimization.
2948    
2949    =over 4
2950    
2951    =item propName
2952    
2953    Name of the desired property.
2954    
2955    =item propValue
2956    
2957    Value expected for the desired property.
2958    
2959    =item RETURN
2960    
2961    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2962    
2963    =back
2964    
2965    =cut
2966    
2967    sub PropertyID {
2968        # Get the parameters.
2969        my ($self, $propName, $propValue) = @_;
2970        # Try to find the ID.
2971        my ($retVal) = $self->GetFlat(['Property'],
2972                                      "Property(property-name) = ? AND Property(property-value) = ?",
2973                                      [$propName, $propValue], 'Property(id)');
2974        # Return the result.
2975        return $retVal;
2976    }
2977    
2978  =head3 MergedAnnotations  =head3 MergedAnnotations
2979    
2980  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2981    
2982  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2983  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2008  Line 3001 
3001  #: Return Type @;  #: Return Type @;
3002  sub MergedAnnotations {  sub MergedAnnotations {
3003          # Get the parameters.          # Get the parameters.
3004          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
3005          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
3006          my @tuples = ();          my @tuples = ();
3007          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 2034  Line 3026 
3026    
3027  =head3 RoleNeighbors  =head3 RoleNeighbors
3028    
3029  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
3030    
3031  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
3032  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 2057  Line 3049 
3049  #: Return Type @;  #: Return Type @;
3050  sub RoleNeighbors {  sub RoleNeighbors {
3051          # Get the parameters.          # Get the parameters.
3052          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
3053          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
3054          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
3055                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2078  Line 3069 
3069    
3070  =head3 FeatureLinks  =head3 FeatureLinks
3071    
3072  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3073    
3074  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
3075  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 2100  Line 3091 
3091  #: Return Type @;  #: Return Type @;
3092  sub FeatureLinks {  sub FeatureLinks {
3093          # Get the parameters.          # Get the parameters.
3094          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
3095          # Get the feature's links.          # Get the feature's links.
3096          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
3097          # Return the feature's links.          # Return the feature's links.
# Line 2110  Line 3100 
3100    
3101  =head3 SubsystemsOf  =head3 SubsystemsOf
3102    
3103  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3104    
3105  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
3106  to the role the feature performs.  to the roles the feature performs.
3107    
3108  =over 4  =over 4
3109    
# Line 2123  Line 3113 
3113    
3114  =item RETURN  =item RETURN
3115    
3116  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.
3117    
3118  =back  =back
3119    
3120  =cut  =cut
3121  #: Return Type %;  #: Return Type %@;
3122  sub SubsystemsOf {  sub SubsystemsOf {
3123          # Get the parameters.          # Get the parameters.
3124          my $self = shift @_;      my ($self, $featureID) = @_;
3125          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
3126          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
3127                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
3128                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
3129          # Create the return value.          # Create the return value.
3130          my %retVal = ();          my %retVal = ();
3131        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
3132        # in two spreadsheet cells.
3133        my %dupHash = ();
3134          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
3135          for my $record (@subsystems) {          for my $record (@subsystems) {
3136                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
3137            my ($subsys, $role) = @{$record};
3138            # Insure it's the first time for both.
3139            my $dupKey = "$subsys\n$role";
3140            if (! exists $dupHash{"$subsys\n$role"}) {
3141                $dupHash{$dupKey} = 1;
3142                push @{$retVal{$subsys}}, $role;
3143            }
3144          }          }
3145          # Return the hash.          # Return the hash.
3146          return %retVal;          return %retVal;
3147  }  }
3148    
3149  =head3 RelatedFeatures  =head3 SubsystemList
3150    
3151  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3152    
3153  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
3154  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
3155  an empty list will be returned.  subsystem names, not the roles.
3156    
3157  =over 4  =over 4
3158    
3159  =item featureID  =item featureID
3160    
3161  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.  
3162    
3163  =item RETURN  =item RETURN
3164    
3165  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.
3166    
3167  =back  =back
3168    
3169  =cut  =cut
3170  #: Return Type @;  #: Return Type @;
3171  sub RelatedFeatures {  sub SubsystemList {
3172          # Get the parameters.          # Get the parameters.
3173          my $self = shift @_;      my ($self, $featureID) = @_;
3174          my ($featureID, $function, $userID) = @_;      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3175          # Get a list of the features that are BBHs of the incoming feature.      # the Sprout database!
3176          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3177                                                                           "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3178                                                                           'IsBidirectionalBestHitOf(to-link)');      # Return the result, sorted.
3179          # 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;  
3180  }  }
3181    
3182  =head3 TaxonomySort  =head3 GenomeSubsystemData
3183    
3184  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3185    
3186  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.  
3187    
3188  =over 4  =over 4
3189    
3190  =item $featureIDs  =item genomeID
3191    
3192  List of features to be taxonomically sorted.  ID of the genome whose subsystem feature map is desired.
3193    
3194  =item RETURN  =item RETURN
3195    
3196  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
3197    2-tuple contains a subsystem name followed by a role ID.
3198    
3199  =back  =back
3200    
3201  =cut  =cut
3202  #: Return Type @;  
3203  sub TaxonomySort {  sub GenomeSubsystemData {
3204          # Get the parameters.          # Get the parameters.
3205          my $self = shift @_;      my ($self, $genomeID) = @_;
3206          my ($featureIDs) = @_;      # Declare the return variable.
3207          # Create the working hash table.      my %retVal = ();
3208          my %hashBuffer = ();      # Get a list of the genome features that participate in subsystems. For each
3209          # Loop through the features.      # feature we get its subsystem ID and the corresponding roles.
3210          for my $fid (@{$featureIDs}) {      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3211                  # Get the taxonomy of the feature's genome.                                   "HasFeature(from-link) = ?", [$genomeID],
3212                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3213                                                                                  [$fid], 'Genome(taxonomy)');      # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3214                  # Add this feature to the hash buffer.      # a non-negative variant code.
3215                  if (exists $hashBuffer{$taxonomy}) {      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3216                          push @{$hashBuffer{$taxonomy}}, $fid;                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3217                  } else {                                                  [$genomeID], 'ParticipatesIn(to-link)');
3218                          $hashBuffer{$taxonomy} = [$fid];      # We loop through @roleData to build the hash.
3219                  }      for my $roleEntry (@roleData) {
3220            # Get the data for this feature and cell.
3221            my ($fid, $role, $subsys) = @{$roleEntry};
3222            Trace("Subsystem for $fid is $subsys.") if T(4);
3223            # Check the subsystem;
3224            if ($subs{$subsys}) {
3225                Trace("Subsystem found.") if T(4);
3226                # Insure this feature has an entry in the return hash.
3227                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3228                # Merge in this new data.
3229                push @{$retVal{$fid}}, [$subsys, $role];
3230          }          }
         # Sort the keys and get the elements.  
         my @retVal = ();  
         for my $taxon (sort keys %hashBuffer) {  
                 push @retVal, @{$hashBuffer{$taxon}};  
3231          }          }
3232          # Return the result.          # Return the result.
3233          return @retVal;      return %retVal;
3234  }  }
3235    
3236  =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.  
3237    
3238  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.  
3239    
3240  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
3241    have been assigned the specified function by the specified user. If no such features exists,
3242    an empty list will be returned.
3243    
3244  =over 4  =over 4
3245    
3246  =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  
3247    
3248  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.
3249    
3250  =item fields  =item function
3251    
3252  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
3253    features should be selected.
3254    
3255  =item count  =item userID
3256    
3257  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.
3258    
3259  =item RETURN  =item RETURN
3260    
3261  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.  
3262    
3263  =back  =back
3264    
3265  =cut  =cut
3266  #: Return Type @@;  #: Return Type @;
3267  sub GetAll {  sub RelatedFeatures {
3268          # Get the parameters.          # Get the parameters.
3269          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
3270          my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;      # Get a list of the features that are BBHs of the incoming feature.
3271          # Create the query.      my $bbhData = FIGRules::BBHData($featureID);
3272          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @bbhFeatures = map { $_->[0] } @$bbhData;
3273          # Set up a counter of the number of records read.      # Now we loop through the features, pulling out the ones that have the correct
3274          my $fetched = 0;      # functional assignment.
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
3275          my @retVal = ();          my @retVal = ();
3276          while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {      for my $bbhFeature (@bbhFeatures) {
3277                  my @rowData = $row->Values($fields);          # Get this feature's functional assignment.
3278                  push @retVal, \@rowData;          my $newFunction = $self->FunctionOf($bbhFeature, $userID);
3279                  $fetched++;          # If it matches, add it to the result list.
3280            if ($newFunction eq $function) {
3281                push @retVal, $bbhFeature;
3282          }          }
3283          # Return the resulting list.      }
3284        # Return the result list.
3285          return @retVal;          return @retVal;
3286  }  }
3287    
3288  =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.  
3289    
3290  =item filterClause      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3291    
3292  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
3293  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.  
3294    
3295  =item parameterList  This task could almost be handled by the database; however, the taxonomy string in the
3296    database is a text field and can't be indexed. Instead, we create a hash table that maps
3297    taxonomy strings to lists of features. We then process the hash table using a key sort
3298    and merge the feature lists together to create the output.
3299    
3300  List of the parameters to be substituted in for the parameters marks in the filter clause.  =over 4
3301    
3302  =item field  =item $featureIDs
3303    
3304  Name of the field to be used to get the elements of the list returned.  List of features to be taxonomically sorted.
3305    
3306  =item RETURN  =item RETURN
3307    
3308  Returns a list of values.  Returns the list of features sorted by the taxonomies of the containing genomes.
3309    
3310  =back  =back
3311    
3312  =cut  =cut
3313  #: Return Type @;  #: Return Type @;
3314  sub GetFlat {  sub TaxonomySort {
3315          # Get the parameters.          # Get the parameters.
3316          my $self = shift @_;      my ($self, $featureIDs) = @_;
3317          my ($objectNames, $filterClause, $parameterList, $field) = @_;      # Create the working hash table.
3318          # Construct the query.      my %hashBuffer = ();
3319          my $query = $self->Get($objectNames, $filterClause, $parameterList);      # Loop through the features.
3320          # Create the result list.      for my $fid (@{$featureIDs}) {
3321            # Get the taxonomy of the feature's genome.
3322            my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3323                                            [$fid], 'Genome(taxonomy)');
3324            # Add this feature to the hash buffer.
3325            push @{$hashBuffer{$taxonomy}}, $fid;
3326        }
3327        # Sort the keys and get the elements.
3328          my @retVal = ();          my @retVal = ();
3329          # Loop through the records, adding the field values found to the result list.      for my $taxon (sort keys %hashBuffer) {
3330          while (my $row = $query->Fetch()) {          push @retVal, @{$hashBuffer{$taxon}};
                 push @retVal, $row->Value($field);  
3331          }          }
3332          # Return the list created.      # Return the result.
3333          return @retVal;          return @retVal;
3334  }  }
3335    
3336  =head3 Protein  =head3 Protein
3337    
3338  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3339    
3340  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3341    
# Line 2460  Line 3405 
3405          # Loop through the input triples.          # Loop through the input triples.
3406          my $n = length $sequence;          my $n = length $sequence;
3407          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3408                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3409                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3410            my $triple = uc substr($sequence, $i, 3);
3411                  # Translate it using the table.                  # Translate it using the table.
3412                  my $protein = "X";                  my $protein = "X";
3413                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2475  Line 3421 
3421    
3422  =head3 LoadInfo  =head3 LoadInfo
3423    
3424  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3425    
3426  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
3427  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 2485  Line 3431 
3431  #: Return Type @;  #: Return Type @;
3432  sub LoadInfo {  sub LoadInfo {
3433          # Get the parameters.          # Get the parameters.
3434          my $self = shift @_;      my ($self) = @_;
3435          # 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.
3436          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3437          # Concatenate the table names.          # Concatenate the table names.
3438          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3439          # Return the result.          # Return the result.
3440          return @retVal;          return @retVal;
3441  }  }
3442    
3443    =head3 BBHMatrix
3444    
3445        my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3446    
3447    Find all the bidirectional best hits for the features of a genome in a
3448    specified list of target genomes. The return value will be a hash mapping
3449    features in the original genome to their bidirectional best hits in the
3450    target genomes.
3451    
3452    =over 4
3453    
3454    =item genomeID
3455    
3456    ID of the genome whose features are to be examined for bidirectional best hits.
3457    
3458    =item cutoff
3459    
3460    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3461    
3462    =item targets
3463    
3464    List of target genomes. Only pairs originating in the original
3465    genome and landing in one of the target genomes will be returned.
3466    
3467    =item RETURN
3468    
3469    Returns a reference to a hash mapping each feature in the original genome
3470    to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3471    
3472    =back
3473    
3474    =cut
3475    
3476    sub BBHMatrix {
3477        # Get the parameters.
3478        my ($self, $genomeID, $cutoff, @targets) = @_;
3479        # Declare the return variable.
3480        my %retVal = ();
3481        # Ask for the BBHs.
3482        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3483        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3484        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3485        for my $bbhData (@bbhList) {
3486            my ($peg1, $peg2, $score) = @{$bbhData};
3487            if (! exists $retVal{$peg1}) {
3488                $retVal{$peg1} = { $peg2 => $score };
3489            } else {
3490                $retVal{$peg1}->{$peg2} = $score;
3491            }
3492        }
3493        # Return the result.
3494        return \%retVal;
3495    }
3496    
3497    
3498    =head3 SimMatrix
3499    
3500        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3501    
3502    Find all the similarities for the features of a genome in a
3503    specified list of target genomes. The return value will be a hash mapping
3504    features in the original genome to their similarites in the
3505    target genomes.
3506    
3507    =over 4
3508    
3509    =item genomeID
3510    
3511    ID of the genome whose features are to be examined for similarities.
3512    
3513    =item cutoff
3514    
3515    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3516    
3517    =item targets
3518    
3519    List of target genomes. Only pairs originating in the original
3520    genome and landing in one of the target genomes will be returned.
3521    
3522    =item RETURN
3523    
3524    Returns a hash mapping each feature in the original genome to a hash mapping its
3525    similar pegs in the target genomes to their scores.
3526    
3527    =back
3528    
3529    =cut
3530    
3531    sub SimMatrix {
3532        # Get the parameters.
3533        my ($self, $genomeID, $cutoff, @targets) = @_;
3534        # Declare the return variable.
3535        my %retVal = ();
3536        # Get the list of features in the source organism.
3537        my @fids = $self->FeaturesOf($genomeID);
3538        # Ask for the sims. We only want similarities to fig features.
3539        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3540        if (! defined $simList) {
3541            Confess("Unable to retrieve similarities from server.");
3542        } else {
3543            Trace("Processing sims.") if T(3);
3544            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3545            # Create a hash for the target genomes.
3546            my %targetHash = map { $_ => 1 } @targets;
3547            for my $simData (@{$simList}) {
3548                # Get the PEGs and the score.
3549                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3550                # Insure the second ID is in the target list.
3551                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3552                if (exists $targetHash{$genome2}) {
3553                    # Here it is. Now we need to add it to the return hash. How we do that depends
3554                    # on whether or not $peg1 is new to us.
3555                    if (! exists $retVal{$peg1}) {
3556                        $retVal{$peg1} = { $peg2 => $score };
3557                    } else {
3558                        $retVal{$peg1}->{$peg2} = $score;
3559                    }
3560                }
3561            }
3562        }
3563        # Return the result.
3564        return %retVal;
3565    }
3566    
3567    
3568  =head3 LowBBHs  =head3 LowBBHs
3569    
3570  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3571    
3572  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
3573  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 2522  Line 3593 
3593  #: Return Type %;  #: Return Type %;
3594  sub LowBBHs {  sub LowBBHs {
3595          # Get the parsameters.          # Get the parsameters.
3596          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3597          # Create the return hash.          # Create the return hash.
3598          my %retVal = ();          my %retVal = ();
3599          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3600          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3601          # Form the results into the return hash.          # Form the results into the return hash.
3602          for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3603                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3604            if ($self->Exists('Feature', $fid)) {
3605                $retVal{$fid} = $pair->[1];
3606            }
3607          }          }
3608          # Return the result.          # Return the result.
3609          return %retVal;          return %retVal;
3610  }  }
3611    
3612  =head2 Internal Utility Methods  =head3 Sims
3613    
3614  =head3 ParseAssignment      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3615    
3616  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
3617  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
3618  will be returned.  returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3619    so that its elements can be accessed by name.
3620    
3621    Similarities can be either raw or expanded. The raw similarities are basic
3622    hits between features with similar DNA. Expanding a raw similarity drags in any
3623    features considered substantially identical. So, for example, if features B<A1>,
3624    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3625    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3626    
3627  This is a static method.  =over 4
3628    
3629    =item fid
3630    
3631    ID of the feature whose similarities are desired, or reference to a list of IDs
3632    of features whose similarities are desired.
3633    
3634    =item maxN
3635    
3636    Maximum number of similarities to return.
3637    
3638    =item maxP
3639    
3640    Minumum allowable similarity score.
3641    
3642    =item select
3643    
3644    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3645    means only similarities to FIG features are returned; C<all> means all expanded
3646    similarities are returned; and C<figx> means similarities are expanded until the
3647    number of FIG features equals the maximum.
3648    
3649    =item max_expand
3650    
3651    The maximum number of features to expand.
3652    
3653    =item filters
3654    
3655    Reference to a hash containing filter information, or a subroutine that can be
3656    used to filter the sims.
3657    
3658    =item RETURN
3659    
3660    Returns a reference to a list of similarity objects, or C<undef> if an error
3661    occurred.
3662    
3663    =back
3664    
3665    =cut
3666    
3667    sub Sims {
3668        # Get the parameters.
3669        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3670        # Create the shim object to test for deleted FIDs.
3671        my $shim = FidCheck->new($self);
3672        # Ask the network for sims.
3673        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3674        # Return the result.
3675        return $retVal;
3676    }
3677    
3678    =head3 IsAllGenomes
3679    
3680        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3681    
3682    Return TRUE if all genomes in the second list are represented in the first list at
3683    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3684    compared to a list of all the genomes.
3685    
3686  =over 4  =over 4
3687    
3688  =item text  =item list
3689    
3690  Text of the annotation.  Reference to the list to be compared to the second list.
3691    
3692    =item checkList (optional)
3693    
3694    Reference to the comparison target list. Every genome ID in this list must occur at
3695    least once in the first list. If this parameter is omitted, a list of all the genomes
3696    is used.
3697    
3698  =item RETURN  =item RETURN
3699    
3700  Returns an empty list if the annotation is not a functional assignment; otherwise, returns  Returns TRUE if every item in the second list appears at least once in the
3701  a two-element list containing the user name and the function text.  first list, else FALSE.
3702    
3703  =back  =back
3704    
3705  =cut  =cut
3706    
3707  sub ParseAssignment {  sub IsAllGenomes {
3708        # Get the parameters.
3709        my ($self, $list, $checkList) = @_;
3710        # Supply the checklist if it was omitted.
3711        $checkList = [$self->Genomes()] if ! defined($checkList);
3712        # Create a hash of the original list.
3713        my %testList = map { $_ => 1 } @{$list};
3714        # Declare the return variable. We assume that the representation
3715        # is complete and stop at the first failure.
3716        my $retVal = 1;
3717        my $n = scalar @{$checkList};
3718        for (my $i = 0; $retVal && $i < $n; $i++) {
3719            if (! $testList{$checkList->[$i]}) {
3720                $retVal = 0;
3721            }
3722        }
3723        # Return the result.
3724        return $retVal;
3725    }
3726    
3727    =head3 GetGroups
3728    
3729        my %groups = $sprout->GetGroups(\@groupList);
3730    
3731    Return a hash mapping each group to the IDs of the genomes in the group.
3732    A list of groups may be specified, in which case only those groups will be
3733    shown. Alternatively, if no parameter is supplied, all groups will be
3734    included. Genomes that are not in any group are omitted.
3735    
3736    =cut
3737    #: Return Type %@;
3738    sub GetGroups {
3739          # Get the parameters.          # Get the parameters.
3740          my ($text) = @_;      my ($self, $groupList) = @_;
3741          # Declare the return value.          # Declare the return value.
3742          my @retVal = ();      my %retVal = ();
3743          # Check to see if this is a functional assignment.      # Determine whether we are getting all the groups or just some.
3744          my ($user, $type, $function) = split(/\n/, $text);      if (defined $groupList) {
3745          if ($type =~ m/^set $user function to$/i) {          # Here we have a group list. Loop through them individually,
3746                  # Here it is, so we return the user name and function text.          # getting a list of the relevant genomes.
3747                  @retVal = ($user, $function);          for my $group (@{$groupList}) {
3748                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3749                    [$group], "Genome(id)");
3750                $retVal{$group} = \@genomeIDs;
3751          }          }
3752          # Return the result list.      } else {
3753            # Here we need all of the groups. In this case, we run through all
3754            # of the genome records, putting each one found into the appropriate
3755            # group. Note that we use a filter clause to insure that only genomes
3756            # in real NMPDR groups are included in the return set.
3757            my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3758                                        [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3759            # Loop through the genomes found.
3760            for my $genome (@genomes) {
3761                # Get the genome ID and group, and add this genome to the group's list.
3762                my ($genomeID, $group) = @{$genome};
3763                push @{$retVal{$group}}, $genomeID;
3764            }
3765        }
3766        # Return the hash we just built.
3767        return %retVal;
3768    }
3769    
3770    =head3 MyGenomes
3771    
3772        my @genomes = Sprout::MyGenomes($dataDir);
3773    
3774    Return a list of the genomes to be included in the Sprout.
3775    
3776    This method is provided for use during the Sprout load. It presumes the Genome load file has
3777    already been created. (It will be in the Sprout data directory and called either C<Genome>
3778    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3779    IDs.
3780    
3781    =over 4
3782    
3783    =item dataDir
3784    
3785    Directory containing the Sprout load files.
3786    
3787    =back
3788    
3789    =cut
3790    #: Return Type @;
3791    sub MyGenomes {
3792        # Get the parameters.
3793        my ($dataDir) = @_;
3794        # Compute the genome file name.
3795        my $genomeFileName = LoadFileName($dataDir, "Genome");
3796        # Extract the genome IDs from the files.
3797        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3798        # Return the result.
3799          return @retVal;          return @retVal;
3800  }  }
3801    
3802  =head3 FriendlyTimestamp  =head3 LoadFileName
3803    
3804  Convert a time number to a user-friendly time stamp for display.      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3805    
3806  This is a static method.  Return the name of the load file for the specified table in the specified data
3807    directory.
3808    
3809  =over 4  =over 4
3810    
3811  =item timeValue  =item dataDir
3812    
3813  Numeric time value.  Directory containing the Sprout load files.
3814    
3815    =item tableName
3816    
3817    Name of the table whose load file is desired.
3818    
3819  =item RETURN  =item RETURN
3820    
3821  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
3822    C<undef> if no load file is present.
3823    
3824  =back  =back
3825    
3826  =cut  =cut
3827    #: Return Type $;
3828  sub FriendlyTimestamp {  sub LoadFileName {
3829      my ($timeValue) = @_;      # Get the parameters.
3830      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my ($dataDir, $tableName) = @_;
3831        # Declare the return variable.
3832        my $retVal;
3833        # Check for the various file names.
3834        if (-e "$dataDir/$tableName") {
3835            $retVal = "$dataDir/$tableName";
3836        } elsif (-e "$dataDir/$tableName.dtx") {
3837            $retVal = "$dataDir/$tableName.dtx";
3838        }
3839        # Return the result.
3840      return $retVal;      return $retVal;
3841  }  }
3842    
3843    =head3 DeleteGenome
3844    
3845        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3846    
3847    Delete a genome from the database.
3848    
3849    =over 4
3850    
3851    =item genomeID
3852    
3853    ID of the genome to delete
3854    
3855    =item testFlag
3856    
3857    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3858    
3859    =item RETURN
3860    
3861    Returns a statistics object describing the rows deleted.
3862    
3863    =back
3864    
3865    =cut
3866    #: Return Type $%;
3867    sub DeleteGenome {
3868        # Get the parameters.
3869        my ($self, $genomeID, $testFlag) = @_;
3870        # Perform the delete for the genome's features.
3871        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3872        # Perform the delete for the primary genome data.
3873        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3874        $retVal->Accumulate($stats);
3875        # Return the result.
3876        return $retVal;
3877    }
3878    
3879    =head3 Fix
3880    
3881        my %fixedHash = $sprout->Fix(%groupHash);
3882    
3883    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3884    The groups will be combined into the appropriate super-groups.
3885    
3886    =over 4
3887    
3888    =item groupHash
3889    
3890    Hash to be fixed up.
3891    
3892    =item RETURN
3893    
3894    Returns a fixed-up version of the hash.
3895    
3896    =back
3897    
3898    =cut
3899    
3900    sub Fix {
3901        # Get the parameters.
3902        my ($self, %groupHash) = @_;
3903        # Create the result hash.
3904        my %retVal = ();
3905        # Copy over the genomes.
3906        for my $groupID (keys %groupHash) {
3907            # Get the super-group name.
3908            my $realGroupID = $self->SuperGroup($groupID);
3909            # Append this group's genomes into the result hash
3910            # using the super-group name.
3911            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3912        }
3913        # Return the result hash.
3914        return %retVal;
3915    }
3916    
3917    =head3 GroupPageName
3918    
3919        my $name = $sprout->GroupPageName($group);
3920    
3921    Return the name of the page for the specified NMPDR group.
3922    
3923    =over 4
3924    
3925    =item group
3926    
3927    Name of the relevant group.
3928    
3929    =item RETURN
3930    
3931    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3932    memory it will be read in.
3933    
3934    =back
3935    
3936    =cut
3937    
3938    sub GroupPageName {
3939        # Get the parameters.
3940        my ($self, $group) = @_;
3941        # Check for the group file data.
3942        my %superTable = $self->CheckGroupFile();
3943        # Compute the real group name.
3944        my $realGroup = $self->SuperGroup($group);
3945        # Get the associated page name.
3946        my $retVal = "../content/$superTable{$realGroup}->{page}";
3947        # Return the result.
3948        return $retVal;
3949    }
3950    
3951    
3952    =head3 AddProperty
3953    
3954        $sprout->AddProperty($featureID, $key, @values);
3955    
3956    Add a new attribute value (Property) to a feature.
3957    
3958    =over 4
3959    
3960    =item peg
3961    
3962    ID of the feature to which the attribute is to be added.
3963    
3964    =item key
3965    
3966    Name of the attribute (key).
3967    
3968    =item values
3969    
3970    Values of the attribute.
3971    
3972    =back
3973    
3974    =cut
3975    #: Return Type ;
3976    sub AddProperty {
3977        # Get the parameters.
3978        my ($self, $featureID, $key, @values) = @_;
3979        # Add the property using the attached attributes object.
3980        $self->ca->AddAttribute($featureID, $key, @values);
3981    }
3982    
3983    =head3 CheckGroupFile
3984    
3985        my %groupData = $sprout->CheckGroupFile();
3986    
3987    Get the group file hash. The group file hash describes the relationship
3988    between a group and the super-group to which it belongs for purposes of
3989    display. The super-group name is computed from the first capitalized word
3990    in the actual group name. For each super-group, the group file contains
3991    the page name and a list of the species expected to be in the group.
3992    Each species is specified by a genus and a species name. A species name
3993    of C<0> implies an entire genus.
3994    
3995    This method returns a hash from super-group names to a hash reference. Each
3996    resulting hash reference contains the following fields.
3997    
3998    =over 4
3999    
4000    =item specials
4001    
4002    Reference to a hash whose keys are the names of special species.
4003    
4004    =item contents
4005    
4006    A list of 2-tuples, each containing a genus name followed by a species name
4007    (or 0, indicating all species). This list indicates which organisms belong
4008    in the super-group.
4009    
4010    =back
4011    
4012    =cut
4013    
4014    sub CheckGroupFile {
4015        # Get the parameters.
4016        my ($self) = @_;
4017        # Check to see if we already have this hash.
4018        if (! defined $self->{groupHash}) {
4019            # We don't, so we need to read it in.
4020            my %groupHash;
4021            # Read the group file.
4022            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
4023            # Loop through the list of sort-of groups.
4024            for my $groupLine (@groupLines) {
4025                my ($name, $specials, @contents) = split /\t/, $groupLine;
4026                $groupHash{$name} = { specials => { map { $_ => 1 } split /\s*,\s*/, $specials },
4027                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
4028                                    };
4029            }
4030            # Save the hash.
4031            $self->{groupHash} = \%groupHash;
4032        }
4033        # Return the result.
4034        return %{$self->{groupHash}};
4035    }
4036    
4037    =head2 Virtual Methods
4038    
4039    =head3 CleanKeywords
4040    
4041        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4042    
4043    Clean up a search expression or keyword list. This involves converting the periods
4044    in EC numbers to underscores, converting non-leading minus signs to underscores,
4045    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4046    characters. In addition, any extra spaces are removed.
4047    
4048    =over 4
4049    
4050    =item searchExpression
4051    
4052    Search expression or keyword list to clean. Note that a search expression may
4053    contain boolean operators which need to be preserved. This includes leading
4054    minus signs.
4055    
4056    =item RETURN
4057    
4058    Cleaned expression or keyword list.
4059    
4060    =back
4061    
4062    =cut
4063    
4064    sub CleanKeywords {
4065        # Get the parameters.
4066        my ($self, $searchExpression) = @_;
4067        # Get the stemmer.
4068        my $stemmer = $self->GetStemmer();
4069        # Convert the search expression using the stemmer.
4070        my $retVal = $stemmer->PrepareSearchExpression($searchExpression);