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

Diff of /Sprout/Sprout.pm

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

revision 1.1, Sun Jan 23 16:12:29 2005 UTC revision 1.105, Wed Jan 30 22:14:02 2008 UTC
# Line 2  Line 2 
2    
3          use Data::Dumper;          use Data::Dumper;
4          use strict;          use strict;
         use Carp;  
5          use DBKernel;          use DBKernel;
6          use XML::Simple;          use XML::Simple;
7          use DBQuery;          use DBQuery;
8          use DBObject;      use ERDBObject;
         use ERDB;  
9          use Tracer;          use Tracer;
10          use FIGRules;          use FIGRules;
11        use FidCheck;
12          use Stats;          use Stats;
13        use POSIX qw(strftime);
14        use BasicLocation;
15        use CustomAttributes;
16        use RemoteCustomAttributes;
17        use base qw(ERDB);
18    
19  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
20    
# Line 24  Line 27 
27  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>
28  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>.
29    
30  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' });
31    
32  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
33  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
34  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
35  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
36    
37    The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
38    
39  =cut  =cut
40    
41  #  #: Constructor SFXlate->new_sprout_only();
42    
43  =head2 Public Methods  =head2 Public Methods
44    
45  =head3 new  =head3 new
46    
47  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
48    
49  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
50  database definition into memory. The positional first parameter specifies the name of the  database definition into memory. The positional first parameter specifies the name of the
# Line 61  Line 66 
66    
67  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
68    
69  * B<userData> user name and password, delimited by a slash (default C<root/>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
70    
71  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
72    
73    * B<sock> connection socket (default same as SEED)
74    
75  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
76    
77  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
78    
79    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
80    
81    * B<host> name of the database host
82    
83  =back  =back
84    
85  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
86  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
87  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
88    
89  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
90    
91  =cut  =cut
92    
93  sub new {  sub new {
94          # Get the parameters.          # Get the parameters.
95          my ($class, $dbName, $options) = @_;          my ($class, $dbName, $options) = @_;
96        # Compute the DBD directory.
97        my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
98                                                      $FIG_Config::fig );
99          # 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
100          # the incoming data.          # the incoming data.
101          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
102                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
103                                             dataDir              => 'Data',                      # data file directory                                                          # database type
104                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
105                                             userData             => 'root/',                     # user name and password                                                          # data file directory
106                                             port                 => 0,                           # database connection port                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
107                                                            # database definition file name
108                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
109                                                            # user name and password
110                           port         => $FIG_Config::dbport,
111                                                            # database connection port
112                           sock         => $FIG_Config::dbsock,
113                           host         => $FIG_Config::sprout_host,
114                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
115                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
116                           noDBOpen     => 0,               # 1 to suppress the database open
117                                            }, $options);                                            }, $options);
118          # Get the data directory.          # Get the data directory.
119          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 99  Line 121 
121          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
122          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
123          # Connect to the database.          # Connect to the database.
124          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
125        if (! $optionTable->{noDBOpen}) {
126            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
127            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
128                                    $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
129        }
130          # Create the ERDB object.          # Create the ERDB object.
131          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
132          my $erdb = ERDB->new($dbh, $xmlFileName);      my $retVal = ERDB::new($class, $dbh, $xmlFileName);
133          # Create this object.      # Add the option table and XML file name.
134          my $self = { _erdb => $erdb, _options => $optionTable, _xmlName => $xmlFileName };      $retVal->{_options} = $optionTable;
135          # Bless and return it.      $retVal->{_xmlName} = $xmlFileName;
136          bless $self;      # Set up space for the group file data.
137          return $self;      $retVal->{groupHash} = undef;
138        # Set up space for the genome hash. We use this to identify NMPDR genomes.
139        $retVal->{genomeHash} = undef;
140        # Connect to the attributes.
141        if ($FIG_Config::attrURL) {
142            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
143            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
144        } elsif ($FIG_Config::attrDbName) {
145            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
146            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
147            $retVal->{_ca} = CustomAttributes->new(user => $user);
148        }
149        # Return it.
150        return $retVal;
151  }  }
152    
153  =head3 MaxSegment  =head3 MaxSegment
154    
155  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
156    
157  This method returns the maximum permissible length of a feature segment. The length is important  This method returns the maximum permissible length of a feature segment. The length is important
158  because it enables us to make reasonable guesses at how to find features inside a particular  because it enables us to make reasonable guesses at how to find features inside a particular
# Line 121  Line 161 
161  and 10999.  and 10999.
162    
163  =cut  =cut
164    #: Return Type $;
165  sub MaxSegment {  sub MaxSegment {
166          my $self = shift @_;      my ($self) = @_;
167          return $self->{_options}->{maxSegmentLength};          return $self->{_options}->{maxSegmentLength};
168  }  }
169    
170  =head3 MaxSequence  =head3 MaxSequence
171    
172  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
173    
174  This method returns the maximum permissible length of a contig sequence. A contig is broken  This method returns the maximum permissible length of a contig sequence. A contig is broken
175  into sequences in order to save memory resources. In particular, when manipulating features,  into sequences in order to save memory resources. In particular, when manipulating features,
176  we generally only need a few sequences in memory rather than the entire contig.  we generally only need a few sequences in memory rather than the entire contig.
177    
178  =cut  =cut
179    #: Return Type $;
180  sub MaxSequence {  sub MaxSequence {
181          my $self = shift @_;      my ($self) = @_;
182          return $self->{_options}->{maxSequenceLength};          return $self->{_options}->{maxSequenceLength};
183  }  }
184    
185  =head3 Get  =head3 Load
   
 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]); >>  
186    
187  It is also permissible to specify I<only> an ORDER BY clause. For example, the following invocation gets      $sprout->Load($rebuild);;
 all genomes ordered by genus and species.  
188    
189  C<< $query = $sprout->Get(['Genome'], "ORDER BY Genome(genus), Genome(species)"); >>  Load the database from files in the data directory, optionally re-creating the tables.
190    
191  Odd things may happen if one of the ORDER BY fields is in a secondary relation. So, for example, an  This method always deletes the data from the database before loading, even if the tables are not
192  attempt to order B<Feature>s by alias may (depending on the underlying database engine used) cause  re-created. The data is loaded into the relations from files in the data directory either having the
193  a single feature to appear more than once.  same name as the target relation with no extension or with an extension of C<.dtx>. Files without an
194    extension are used in preference to the files with an extension.
195    
196  If multiple names are specified, then the query processor will automatically determine a  The files are loaded based on the presumption that each line of the file is a record in the
197  join path between the entities and relationships. The algorithm used is very simplistic.  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
198  In particular, you can't specify any entity or relationship more than once, and if a  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
199  relationship is recursive, the path is determined by the order in which the entity  be presented in the order given in the relation tables produced by the L</ShowMetaData> method.
 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.  
200    
201  =over 4  =over 4
202    
203  =item objectNames  =item rebuild
   
 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  
204    
205  List of the parameters to be substituted in for the parameters marks in the filter clause.  TRUE if the data tables need to be created or re-created, else FALSE
206    
207  =item RETURN  =item RETURN
208    
209  Returns a B<DBQuery> that can be used to iterate through all of the results.  Returns a statistical object containing the number of records read, the number of duplicates found,
210    the number of errors, and a list of the error messages.
211    
212  =back  =back
213    
214  =cut  =cut
215    #: Return Type %;
216  sub Get {  sub Load {
217          # Get the parameters.          # Get the parameters.
218          my $self = shift @_;      my ($self, $rebuild) = @_;
219          my ($objectNames, $filterClause, $parameterList) = @_;      # Load the tables from the data directory.
220          # We differ from the ERDB Get method in that the parameter list is passed in as a list reference      my $retVal = $self->LoadTables($self->{_options}->{dataDir}, $rebuild);
221          # rather than a list of parameters. The next step is to convert the parameters from a reference      # Return the statistics.
222          # to a real list. We can only do this if the parameters have been specified.      return $retVal;
         my @parameters;  
         if ($parameterList) { @parameters = @{$parameterList}; }  
         return $self->{_erdb}->Get($objectNames, $filterClause, @parameters);  
223  }  }
224    
225  =head3 GetEntity  =head3 LoadUpdate
226    
227  C<< my $entityObject = $sprout->GetEntity($entityType, $ID); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
228    
229  Return an object describing the entity instance with a specified ID.  Load updates to one or more database tables. This method enables the client to make changes to one
230    or two tables without reloading the whole database. For each table, there must be a corresponding
231    file in the data directory, either with the same name as the table, or with a C<.dtx> suffix. So,
232    for example, to make updates to the B<FeatureTranslation> relation, there must be a
233    C<FeatureTranslation.dtx> file in the data directory. Unlike a full load, files without an extension
234    are not examined. This allows update files to co-exist with files from an original load.
235    
236  =over 4  =over 4
237    
238  =item entityType  =item truncateFlag
239    
240  Entity type name.  TRUE if the tables should be rebuilt before loading, else FALSE. A value of TRUE therefore causes
241    current data and schema of the tables to be replaced, while a value of FALSE means the new data
242    is added to the existing data in the various relations.
243    
244  =item ID  =item tableList
245    
246  ID of the desired entity.  List of the tables to be updated.
247    
248  =item RETURN  =item RETURN
249    
250  Returns a B<DBObject> representing the desired entity instance, or an undefined value if no  Returns a statistical object containing the number of records read, the number of duplicates found,
251  instance is found with the specified key.  the number of errors encountered, and a list of error messages.
252    
253  =back  =back
254    
255  =cut  =cut
256    #: Return Type $%;
257  sub GetEntity {  sub LoadUpdate {
258          # Get the parameters.          # Get the parameters.
259          my $self = shift @_;      my ($self, $truncateFlag, $tableList) = @_;
260          my ($entityType, $ID) = @_;      # Declare the return value.
261          # Create a query.      my $retVal = Stats->new();
262          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      # Get the data directory.
263          # Get the first (and only) object.      my $optionTable = $self->{_options};
264          my $retVal = $query->Fetch();      my $dataDir = $optionTable->{dataDir};
265          # Return the result.      # Loop through the incoming table names.
266        for my $tableName (@{$tableList}) {
267            # Find the table's file.
268            my $fileName = LoadFileName($dataDir, $tableName);
269            if (! $fileName) {
270                Trace("No load file found for $tableName in $dataDir.") if T(0);
271            } else {
272                # Attempt to load this table.
273                my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
274                # Accumulate the resulting statistics.
275                $retVal->Accumulate($result);
276            }
277        }
278        # Return the statistics.
279          return $retVal;          return $retVal;
280  }  }
281    
282  =head3 GetEntityValues  =head3 GenomeCounts
283    
284  C<< my @values = GetEntityValues($entityType, $ID, \@fields); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
285    
286  Return a list of values from a specified entity instance.  Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
287    genomes will be included in the counts.
288    
289  =over 4  =over 4
290    
291  =item entityType  =item complete
   
 Entity type name.  
292    
293  =item ID  TRUE if only complete genomes are to be counted, FALSE if all genomes are to be
294    counted
 ID of the desired entity.  
   
 =item fields  
   
 List of field names, each of the form I<objectName>C<(>I<fieldName>C<)>.  
295    
296  =item RETURN  =item RETURN
297    
298  Returns a flattened list of the values of the specified fields for the specified entity.  A six-element list containing the number of genomes in each of six categories--
299    Archaea, Bacteria, Eukaryota, Viral, Environmental, and Unknown, respectively.
300    
301  =back  =back
302    
303  =cut  =cut
304    
305  sub GetEntityValues {  sub GenomeCounts {
306          # Get the parameters.          # Get the parameters.
307          my $self = shift @_;      my ($self, $complete) = @_;
308          my ($entityType, $ID, $fields) = @_;      # Set the filter based on the completeness flag.
309          # Get the specified entity.      my $filter = ($complete ? "Genome(complete) = 1" : "");
310          my $entity = $self->GetEntity($entityType, $ID);      # Get all the genomes and the related taxonomy information.
311          # Declare the return list.      my @genomes = $self->GetAll(['Genome'], $filter, [], ['Genome(id)', 'Genome(taxonomy)']);
312          my @retVal = ();      # Clear the counters.
313          # If we found the entity, push the values into the return list.      my ($arch, $bact, $euk, $vir, $env, $unk) = (0, 0, 0, 0, 0, 0);
314          if ($entity) {      # Loop through, counting the domains.
315                  push @retVal, $entity->Values($fields);      for my $genome (@genomes) {
316            if    ($genome->[1] =~ /^archaea/i)  { ++$arch }
317            elsif ($genome->[1] =~ /^bacter/i)   { ++$bact }
318            elsif ($genome->[1] =~ /^eukar/i)    { ++$euk }
319            elsif ($genome->[1] =~ /^vir/i)      { ++$vir }
320            elsif ($genome->[1] =~ /^env/i)      { ++$env }
321            else  { ++$unk }
322          }          }
323          # Return the result.      # Return the counts.
324          return @retVal;      return ($arch, $bact, $euk, $vir, $env, $unk);
325  }  }
326    
327  =head3 ShowMetaData  =head3 ContigCount
328    
329  C<< $sprout->ShowMetaData($fileName); >>      my $count = $sprout->ContigCount($genomeID);
330    
331  This method outputs a description of the database to an HTML file in the data directory.  Return the number of contigs for the specified genome ID.
332    
333  =over 4  =over 4
334    
335  =item fileName  =item genomeID
336    
337  Fully-qualified name to give to the output file.  ID of the genome whose contig count is desired.
338    
339    =item RETURN
340    
341    Returns the number of contigs for the specified genome.
342    
343  =back  =back
344    
345  =cut  =cut
346    
347  sub ShowMetaData {  sub ContigCount {
348          # Get the parameters.          # Get the parameters.
349          my $self = shift @_;      my ($self, $genomeID) = @_;
350          my ($fileName) = @_;      # Get the contig count.
351          # Compute the file name.      my $retVal = $self->GetCount(['Contig', 'HasContig'], "HasContig(from-link) = ?", [$genomeID]);
352          my $options = $self->{_options};      # Return the result.
353          # Call the show method on the underlying ERDB object.      return $retVal;
         $self->{_erdb}->ShowMetaData($fileName);  
354  }  }
355    
356  =head3 Load  =head3 GeneMenu
   
 C<< $sprout->Load($rebuild); >>;  
   
 Load the database from files in the data directory, optionally re-creating the tables.  
357    
358  This method always deletes the data from the database before loading, even if the tables are not      my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected);
 re-created. The data is loaded into the relations from files in the data directory either having the  
 same name as the target relation with no extension or with an extension of C<.dtx>. Files without an  
 extension are used in preference to the files with an extension.  
359    
360  The files are loaded based on the presumption that each line of the file is a record in the  Return an HTML select menu of genomes. Each genome will be an option in the menu,
361  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  and will be displayed by name with the ID and a contig count attached. The selection
362  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  value will be the genome ID. The genomes will be sorted by genus/species name.
 be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  
363    
364  =over 4  =over 4
365    
366  =item rebuild  =item attributes
   
 TRUE if the data tables need to be created or re-created, else FALSE  
   
 =item RETURN  
   
 Returns a statistical object containing the number of records read, the number of duplicates found,  
 the number of errors, and a list of the error messages.  
   
 =back  
   
 =cut  
367    
368  sub Load {  Reference to a hash mapping attributes to values for the SELECT tag generated.
         # Get the parameters.  
         my $self = shift @_;  
         my ($rebuild) = @_;  
         # Get the database object.  
         my $erdb = $self->{_erdb};  
         # Load the tables from the data directory.  
         my $retVal = $erdb->LoadTables($self->{_options}->{dataDir}, $rebuild);  
         # Return the statistics.  
         return $retVal;  
 }  
369    
370  =head3 LoadUpdate  =item filterString
371    
372  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  A filter string for use in selecting the genomes. The filter string must conform
373    to the rules for the C<< ERDB->Get >> method.
374    
375  Load updates to one or more database tables. This method enables the client to make changes to one  =item params
 or two tables without reloading the whole database. For each table, there must be a corresponding  
 file in the data directory, either with the same name as the table, or with a C<.dtx> suffix. So,  
 for example, to make updates to the B<FeatureTranslation> relation, there must be a  
 C<FeatureTranslation.dtx> file in the data directory. Unlike a full load, files without an extension  
 are not examined. This allows update files to co-exist with files from an original load.  
376    
377  =over 4  Reference to a list of values to be substituted in for the parameter marks in
378    the filter string.
379    
380  =item truncateFlag  =item selected (optional)
381    
382  TRUE if the tables should be rebuilt before loading, else FALSE. A value of TRUE therefore causes  ID of the genome to be initially selected.
 current data and schema of the tables to be replaced, while a value of FALSE means the new data  
 is added to the existing data in the various relations.  
383    
384  =item tableList  =item fast (optional)
385    
386  List of the tables to be updated.  If specified and TRUE, the contig counts will be omitted to improve performance.
387    
388  =item RETURN  =item RETURN
389    
390  Returns a statistical object containing the number of records read, the number of duplicates found,  Returns an HTML select menu with the specified genomes as selectable options.
 the number of errors encountered, and a list of error messages.  
391    
392  =back  =back
393    
394  =cut  =cut
395    
396  sub LoadUpdate {  sub GeneMenu {
397          # Get the parameters.          # Get the parameters.
398          my $self = shift @_;      my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;
399          my ($truncateFlag, $tableList) = @_;      my $slowMode = ! $fast;
400          # Get the database object.      # Default to nothing selected. This prevents an execution warning if "$selected"
401          my $erdb = $self->{_erdb};      # is undefined.
402          # Declare the return value.      $selected = "" unless defined $selected;
403          my $retVal = Stats->new();      Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);
404          # Get the data directory.      # Start the menu.
405          my $optionTable = $self->{_options};      my $retVal = "<select " .
406          my $dataDir = $optionTable->{dataDir};          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .
407          # Loop through the incoming table names.          ">\n";
408          for my $tableName (@{$tableList}) {      # Get the genomes.
409                  # Find the table's file.      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',
410                  my $fileName = "$dataDir/$tableName";                                                                       'Genome(genus)',
411                  if (! -e $fileName) {                                                                       'Genome(species)',
412                          $fileName = "$fileName.dtx";                                                                       'Genome(unique-characterization)']);
413                  }      # Sort them by name.
414                  # Attempt to load this table.      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;
415                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);      # Loop through the genomes, creating the option tags.
416                  # Accumulate the resulting statistics.      for my $genomeData (@sorted) {
417                  $retVal->Accumulate($result);          # Get the data for this genome.
418            my ($genomeID, $genus, $species, $strain) = @{$genomeData};
419            # Get the contig count.
420            my $contigInfo = "";
421            if ($slowMode) {
422                my $count = $self->ContigCount($genomeID);
423                my $counting = ($count == 1 ? "contig" : "contigs");
424                $contigInfo = "[$count $counting]";
425            }
426            # Find out if we're selected.
427            my $selectOption = ($selected eq $genomeID ? " selected" : "");
428            # Build the option tag.
429            $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";
430          }          }
431          # Return the statistics.      # Close the SELECT tag.
432        $retVal .= "</select>\n";
433        # Return the result.
434          return $retVal;          return $retVal;
435  }  }
436    
437  =head3 Build  =head3 Build
438    
439  C<< $sprout->Build(); >>      $sprout->Build();
440    
441  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.
442  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
443  changed.  changed.
444    
445  =cut  =cut
446    #: Return Type ;
447  sub Build {  sub Build {
448          # Get the parameters.          # Get the parameters.
449          my $self = shift @_;      my ($self) = @_;
450          # Create the tables.          # Create the tables.
451          $self->{_erdb}->CreateTables;      $self->CreateTables();
452  }  }
453    
454  =head3 Genomes  =head3 Genomes
455    
456  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
457    
458  Return a list of all the genome IDs.  Return a list of all the genome IDs.
459    
460  =cut  =cut
461    #: Return Type @;
462  sub Genomes {  sub Genomes {
463          # Get the parameters.          # Get the parameters.
464          my $self = shift @_;      my ($self) = @_;
465          # Get all the genomes.          # Get all the genomes.
466          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');          my @retVal = $self->GetFlat(['Genome'], "", [], 'Genome(id)');
467          # Return the list of IDs.          # Return the list of IDs.
# Line 486  Line 470 
470    
471  =head3 GenusSpecies  =head3 GenusSpecies
472    
473  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
474    
475  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
476    
# Line 504  Line 488 
488  =back  =back
489    
490  =cut  =cut
491    #: Return Type $;
492  sub GenusSpecies {  sub GenusSpecies {
493          # Get the parameters.          # Get the parameters.
494          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
495          # Get the data for the specified genome.          # Get the data for the specified genome.
496          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',          my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',
497                                                                                                                            'Genome(unique-characterization)']);                                                                                                                            'Genome(unique-characterization)']);
# Line 519  Line 502 
502    
503  =head3 FeaturesOf  =head3 FeaturesOf
504    
505  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
506    
507  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
508    
# Line 541  Line 524 
524  =back  =back
525    
526  =cut  =cut
527    #: Return Type @;
528  sub FeaturesOf {  sub FeaturesOf {
529          # Get the parameters.          # Get the parameters.
530          my $self = shift @_;      my ($self, $genomeID,$ftype) = @_;
         my ($genomeID,$ftype) = @_;  
531          # Get the features we want.          # Get the features we want.
532          my @features;          my @features;
533          if (!$ftype) {          if (!$ftype) {
# Line 565  Line 547 
547    
548  =head3 FeatureLocation  =head3 FeatureLocation
549    
550  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
551    
552  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
553  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 589  Line 571 
571  =item RETURN  =item RETURN
572    
573  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
574  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
575    
576  =back  =back
577    
# Line 597  Line 579 
579    
580  sub FeatureLocation {  sub FeatureLocation {
581          # Get the parameters.          # Get the parameters.
582          my $self = shift @_;      my ($self, $featureID) = @_;
583          my ($featureID) = @_;      # Get the feature record.
584          # Create a query for the feature locations.      my $object = $self->GetEntity('Feature', $featureID);
585          my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",      Confess("Feature $featureID not found.") if ! defined($object);
586                                                     [$featureID]);      # Get the location string.
587        my $locString = $object->PrimaryValue('Feature(location-string)');
588          # Create the return list.          # Create the return list.
589          my @retVal = ();      my @retVal = split /\s*,\s*/, $locString;
         # Set up the variables used to determine if we have adjacent segments. This initial setup will  
         # not match anything.  
         my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);  
         # Loop through the query results, creating location specifiers.  
         while (my $location = $query->Fetch()) {  
                 # Get the location parameters.  
                 my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',  
                         'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);  
                 # Check to see if we are adjacent to the previous segment.  
                 if ($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$len";  
         }  
590          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
591          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
592  }  }
593    
594  =head3 ParseLocation  =head3 ParseLocation
595    
596  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
597    
598  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
599  length.  length.
# Line 658  Line 614 
614  =cut  =cut
615    
616  sub ParseLocation {  sub ParseLocation {
617          # Get the parameter.      # Get the parameter. Note that if we're called as an instance method, we ignore
618        # the first parameter.
619        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
620          my ($location) = @_;          my ($location) = @_;
621          # Parse it into segments.          # Parse it into segments.
622          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
623          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
624          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
625          if ($dir eq "_") {          if ($dir eq "_") {
# Line 677  Line 635 
635          return ($contigID, $start, $dir, $len);          return ($contigID, $start, $dir, $len);
636  }  }
637    
638    
639    
640    =head3 PointLocation
641    
642        my $found = Sprout::PointLocation($location, $point);
643    
644    Return the offset into the specified location of the specified point on the contig. If
645    the specified point is before the location, a negative value will be returned. If it is
646    beyond the location, an undefined value will be returned. It is assumed that the offset
647    is for the location's contig. The location can either be new-style (using a C<+> or C<->
648    and a length) or old-style (using C<_> and start and end positions.
649    
650    =over 4
651    
652    =item location
653    
654    A location specifier (see L</FeatureLocation> for a description).
655    
656    =item point
657    
658    The offset into the contig of the point in which we're interested.
659    
660    =item RETURN
661    
662    Returns the offset inside the specified location of the specified point, a negative
663    number if the point is before the location, or an undefined value if the point is past
664    the location. If the length of the location is 0, this method will B<always> denote
665    that it is outside the location. The offset will always be relative to the left-most
666    position in the location.
667    
668    =back
669    
670    =cut
671    
672    sub PointLocation {
673        # Get the parameter. Note that if we're called as an instance method, we ignore
674        # the first parameter.
675        shift if UNIVERSAL::isa($_[0],__PACKAGE__);
676        my ($location, $point) = @_;
677        # Parse out the location elements. Note that this works on both old-style and new-style
678        # locations.
679        my ($contigID, $start, $dir, $len) = ParseLocation($location);
680        # Declare the return variable.
681        my $retVal;
682        # Compute the offset. The computation is dependent on the direction of the location.
683        my $offset = (($dir == '+') ? $point - $start : $point - ($start - $len + 1));
684        # Return the offset if it's valid.
685        if ($offset < $len) {
686            $retVal = $offset;
687        }
688        # Return the offset found.
689        return $retVal;
690    }
691    
692  =head3 DNASeq  =head3 DNASeq
693    
694  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
695    
696  This method returns the DNA sequence represented by a list of locations. The list of locations  This method returns the DNA sequence represented by a list of locations. The list of locations
697  should be of the form returned by L</feature_location> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
698  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
699    
700    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
701    between positions 1401 and 1532, inclusive.
702    
703        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
704    
705  =over 4  =over 4
706    
707  =item locationList  =item locationList
708    
709  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
710  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
711    
712  =item RETURN  =item RETURN
713    
# Line 699  Line 716 
716  =back  =back
717    
718  =cut  =cut
719    #: Return Type $;
720  sub DNASeq {  sub DNASeq {
721          # Get the parameters.          # Get the parameters.
722          my $self = shift @_;      my ($self, $locationList) = @_;
         my ($locationList) = @_;  
723          # Create the return string.          # Create the return string.
724          my $retVal = "";          my $retVal = "";
725          # Loop through the locations.          # Loop through the locations.
# Line 718  Line 734 
734                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
735                  # before putting it in the return value.                  # before putting it in the return value.
736                  my ($start, $stop);                  my ($start, $stop);
737            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
738                  if ($dir eq "+") {                  if ($dir eq "+") {
739                          $start = $beg;                          $start = $beg;
740                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
741                  } else {                  } else {
742                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
743                          $stop = $beg;                          $stop = $beg;
744                  }                  }
745            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
746                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
747                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
748                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 736  Line 754 
754                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
755                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
756                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
757                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
758                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
759                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
760                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
761                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
762                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
763                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
764                  }                  }
765                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
766                  if ($dir eq '+') {                  if ($dir eq '+') {
767                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
768                  } else {                  } else {
769                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
770                  }                  }
771          }          }
772          # Return the result.          # Return the result.
# Line 756  Line 775 
775    
776  =head3 AllContigs  =head3 AllContigs
777    
778  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
779    
780  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
781    
# Line 773  Line 792 
792  =back  =back
793    
794  =cut  =cut
795    #: Return Type @;
796  sub AllContigs {  sub AllContigs {
797          # Get the parameters.          # Get the parameters.
798          my $self = shift @_;      my ($self, $genomeID) = @_;
         my ($genomeID) = @_;  
799          # Ask for the genome's Contigs.          # Ask for the genome's Contigs.
800          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],          my @retVal = $self->GetFlat(['HasContig'], "HasContig(from-link) = ?", [$genomeID],
801                                                                  'HasContig(to-link)');                                                                  'HasContig(to-link)');
# Line 785  Line 803 
803          return @retVal;          return @retVal;
804  }  }
805    
806  =head3 ContigLength  =head3 GenomeLength
807    
808  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->GenomeLength($genomeID);
809    
810  Compute the length of a contig.  Return the length of the specified genome in base pairs.
811    
812  =over 4  =over 4
813    
814  =item contigID  =item genomeID
815    
816  ID of the contig whose length is desired.  ID of the genome whose base pair count is desired.
817    
818    =item RETURN
819    
820    Returns the number of base pairs in all the contigs of the specified
821    genome.
822    
823  =back  =back
824    
825  =cut  =cut
826    
827  sub ContigLength {  sub GenomeLength {
828          # Get the parameters.          # Get the parameters.
829          my $self = shift @_;      my ($self, $genomeID) = @_;
830          my ($contigID) = @_;      # Declare the return variable.
         # Get the contig's last sequence.  
         my $query = $self->Get(['IsMadeUpOf'],  
                 "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",  
                 [$contigID]);  
         my $sequence = $query->Fetch();  
         # Declare the return value.  
831          my $retVal = 0;          my $retVal = 0;
832          # Set it from the sequence data, if any.      # Get the genome's contig sequence lengths.
833          if ($sequence) {      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',
834                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                         [$genomeID], 'IsMadeUpOf(len)');
835                  $retVal = $start + $len;      # Sum the lengths.
836          }      map { $retVal += $_ } @lens;
837          # Return the result.          # Return the result.
838          return $retVal;          return $retVal;
839  }  }
840    
841  =head3 GenesInRegion  =head3 FeatureCount
842    
843  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my $count = $sprout->FeatureCount($genomeID, $type);
844    
845  List the features which overlap a specified region in a contig.  Return the number of features of the specified type in the specified genome.
846    
847  =over 4  =over 4
848    
849  =item contigID  =item genomeID
850    
851  ID of the contig containing the region of interest.  ID of the genome whose feature count is desired.
852    
853  =item start  =item type
854    
855  Offset of the first residue in the region of interest.  Type of feature to count (eg. C<peg>, C<rna>, etc.).
856    
857  =item stop  =item RETURN
858    
859  Offset of the last residue in the region of interest.  Returns the number of features of the specified type for the specified genome.
860    
861    =back
862    
863    =cut
864    
865    sub FeatureCount {
866        # Get the parameters.
867        my ($self, $genomeID, $type) = @_;
868        # Compute the count.
869        my $retVal = $self->GetCount(['HasFeature', 'Feature'],
870                                    "HasFeature(from-link) = ? AND Feature(feature-type) = ?",
871                                    [$genomeID, $type]);
872        # Return the result.
873        return $retVal;
874    }
875    
876    =head3 GenomeAssignments
877    
878        my $fidHash = $sprout->GenomeAssignments($genomeID);
879    
880    Return a list of a genome's assigned features. The return hash will contain each
881    assigned feature of the genome mapped to the text of its most recent functional
882    assignment.
883    
884    =over 4
885    
886    =item genomeID
887    
888    ID of the genome whose functional assignments are desired.
889    
890  =item RETURN  =item RETURN
891    
892  Returns a three-element list. The first element is a list of feature IDs for the features that  Returns a reference to a hash which maps each feature to its most recent
893  overlap the region of interest. The second and third elements are the minimum and maximum  functional assignment.
 locations of the features provided on the specified contig. These may extend outside  
 the start and stop values.  
894    
895  =back  =back
896    
897  =cut  =cut
898    
899  sub GenesInRegion {  sub GenomeAssignments {
900          # Get the parameters.          # Get the parameters.
901          my $self = shift @_;      my ($self, $genomeID) = @_;
902          my ($contigID, $start, $stop) = @_;      # Declare the return variable.
903          # Get the maximum segment length.      my $retVal = {};
904          my $maximumSegmentLength = $self->MaxSegment;      # Query the genome's features.
905          # Create a hash to receive the feature list. We use a hash so that we can eliminate      my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
906          # duplicates easily.                             [$genomeID]);
907          my %featuresFound = ();      # Loop through the features.
908          # Prime the values we'll use for the returned beginning and end.      while (my $data = $query->Fetch) {
909          my ($min, $max) = ($self->ContigLength($contigID), 0);          # Get the feature ID and assignment.
910          # Create a table of parameters for each query. Each query looks for features travelling in          my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
911          # a particular direction. The query parameters include the contig ID, the feature direction,          if ($assignment) {
912          # the lowest possible start position, and the highest possible start position. This works              $retVal->{$fid} = $assignment;
913          # because each feature segment length must be no greater than the maximum segment length.          }
914          my %queryParms = (forward => [$contigID, '+', $start - $maximumSegmentLength + 1, $stop],      }
915                                            reverse => [$contigID, '-', $start, $stop + $maximumSegmentLength - 1]);      # Return the result.
916          # Loop through the query parameters.      return $retVal;
917          for my $parms (values %queryParms) {  }
918    
919    =head3 ContigLength
920    
921        my $length = $sprout->ContigLength($contigID);
922    
923    Compute the length of a contig.
924    
925    =over 4
926    
927    =item contigID
928    
929    ID of the contig whose length is desired.
930    
931    =item RETURN
932    
933    Returns the number of positions in the contig.
934    
935    =back
936    
937    =cut
938    #: Return Type $;
939    sub ContigLength {
940        # Get the parameters.
941        my ($self, $contigID) = @_;
942        # Get the contig's last sequence.
943        my $query = $self->Get(['IsMadeUpOf'],
944            "IsMadeUpOf(from-link) = ? ORDER BY IsMadeUpOf(start-position) DESC",
945            [$contigID]);
946        my $sequence = $query->Fetch();
947        # Declare the return value.
948        my $retVal = 0;
949        # Set it from the sequence data, if any.
950        if ($sequence) {
951            my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
952            $retVal = $start + $len - 1;
953        }
954        # Return the result.
955        return $retVal;
956    }
957    
958    =head3 ClusterPEGs
959    
960        my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
961    
962    Cluster the PEGs in a list according to the cluster coding scheme of the specified
963    subsystem. In order for this to work properly, the subsystem object must have
964    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
965    B<get_row> methods. This causes the cluster numbers to be pulled into the
966    subsystem's color hash. If a PEG is not found in the color hash, it will not
967    appear in the output sequence.
968    
969    =over 4
970    
971    =item sub
972    
973    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
974    method.
975    
976    =item pegs
977    
978    Reference to the list of PEGs to be clustered.
979    
980    =item RETURN
981    
982    Returns a list of the PEGs, grouped into smaller lists by cluster number.
983    
984    =back
985    
986    =cut
987    #: Return Type $@@;
988    sub ClusterPEGs {
989        # Get the parameters.
990        my ($self, $sub, $pegs) = @_;
991        # Declare the return variable.
992        my $retVal = [];
993        # Loop through the PEGs, creating arrays for each cluster.
994        for my $pegID (@{$pegs}) {
995            my $clusterNumber = $sub->get_cluster_number($pegID);
996            # Only proceed if the PEG is in a cluster.
997            if ($clusterNumber >= 0) {
998                # Push this PEG onto the sub-list for the specified cluster number.
999                push @{$retVal->[$clusterNumber]}, $pegID;
1000            }
1001        }
1002        # Return the result.
1003        return $retVal;
1004    }
1005    
1006    =head3 GenesInRegion
1007    
1008        my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1009    
1010    List the features which overlap a specified region in a contig.
1011    
1012    =over 4
1013    
1014    =item contigID
1015    
1016    ID of the contig containing the region of interest.
1017    
1018    =item start
1019    
1020    Offset of the first residue in the region of interest.
1021    
1022    =item stop
1023    
1024    Offset of the last residue in the region of interest.
1025    
1026    =item RETURN
1027    
1028    Returns a three-element list. The first element is a list of feature IDs for the features that
1029    overlap the region of interest. The second and third elements are the minimum and maximum
1030    locations of the features provided on the specified contig. These may extend outside
1031    the start and stop values. The first element (that is, the list of features) is sorted
1032    roughly by location.
1033    
1034    =back
1035    
1036    =cut
1037    
1038    sub GenesInRegion {
1039        # Get the parameters.
1040        my ($self, $contigID, $start, $stop) = @_;
1041        # Get the maximum segment length.
1042        my $maximumSegmentLength = $self->MaxSegment;
1043        # Prime the values we'll use for the returned beginning and end.
1044        my @initialMinMax = ($self->ContigLength($contigID), 0);
1045        my ($min, $max) = @initialMinMax;
1046        # Get the overlapping features.
1047        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1048        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1049        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1050        # of the feature's locations.
1051        my %featureMap = ();
1052        # Loop through them to do the begin/end analysis.
1053        for my $featureObject (@featureObjects) {
1054            # Get the feature's location string. This may contain multiple actual locations.
1055            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1056            my @locationSegments = split /\s*,\s*/, $locations;
1057            # Loop through the locations.
1058            for my $locationSegment (@locationSegments) {
1059                # Construct an object for the location.
1060                my $locationObject = BasicLocation->new($locationSegment);
1061                # Merge the current segment's begin and end into the min and max.
1062                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1063                my ($beg, $end);
1064                if (exists $featureMap{$fid}) {
1065                    ($beg, $end) = @{$featureMap{$fid}};
1066                    $beg = $left if $left < $beg;
1067                    $end = $right if $right > $end;
1068                } else {
1069                    ($beg, $end) = ($left, $right);
1070                }
1071                $min = $beg if $beg < $min;
1072                $max = $end if $end > $max;
1073                # Store the feature's new extent back into the hash table.
1074                $featureMap{$fid} = [$beg, $end];
1075            }
1076        }
1077        # Now we must compute the list of the IDs for the features found. We start with a list
1078        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1079        # but the result of the sort will be the same.)
1080        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1081        # Now we sort by midpoint and yank out the feature IDs.
1082        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1083        # Return it along with the min and max.
1084        return (\@retVal, $min, $max);
1085    }
1086    
1087    =head3 GeneDataInRegion
1088    
1089        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1090    
1091    List the features which overlap a specified region in a contig.
1092    
1093    =over 4
1094    
1095    =item contigID
1096    
1097    ID of the contig containing the region of interest.
1098    
1099    =item start
1100    
1101    Offset of the first residue in the region of interest.
1102    
1103    =item stop
1104    
1105    Offset of the last residue in the region of interest.
1106    
1107    =item RETURN
1108    
1109    Returns a list of B<ERDBObjects> for the desired features. Each object will
1110    contain a B<Feature> record.
1111    
1112    =back
1113    
1114    =cut
1115    
1116    sub GeneDataInRegion {
1117        # Get the parameters.
1118        my ($self, $contigID, $start, $stop) = @_;
1119        # Get the maximum segment length.
1120        my $maximumSegmentLength = $self->MaxSegment;
1121        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1122        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1123        # ERDBObject from the query.
1124        my %featuresFound = ();
1125        # Create a table of parameters for the queries. Each query looks for features travelling in
1126        # a particular direction. The query parameters include the contig ID, the feature direction,
1127        # the lowest possible start position, and the highest possible start position. This works
1128        # because each feature segment length must be no greater than the maximum segment length.
1129        my %queryParms = (forward => [$contigID, '+', $start - $maximumSegmentLength + 1, $stop],
1130                          reverse => [$contigID, '-', $start, $stop + $maximumSegmentLength - 1]);
1131        # Loop through the query parameters.
1132        for my $parms (values %queryParms) {
1133                  # Create the query.                  # Create the query.
1134                  my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1135                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",                          "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1136                          $parms);                          $parms);
1137                  # Loop through the feature segments found.                  # Loop through the feature segments found.
1138                  while (my $segment = $query->Fetch) {                  while (my $segment = $query->Fetch) {
1139                          # Get the data about this segment.                          # Get the data about this segment.
1140                          my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1141                                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1142                          # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1143                          # this will be the case if the segment is the maximum length, so to fine-tune                          # this will be the case if the segment is the maximum length, so to fine-tune
1144                          # the results we insure that the inequality from the query holds using the actual                          # the results we insure that the inequality from the query holds using the actual
1145                          # length.                          # length.
1146                          my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1147                          if ($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.  
                                         $found = 1;  
                                 }  
                         }  
1148                          if ($found) {                          if ($found) {
1149                                  # Here we need to record the feature and update the minimum and maximum.                  # Save this feature in the result list.
1150                                  $featuresFound{$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; }  
1151                          }                          }
1152                  }                  }
1153          }          }
1154          # Compute a list of the IDs for the features found.      # Return the ERDB objects for the features found.
1155          my @list = (sort (keys %featuresFound));      return values %featuresFound;
         # Return it along with the min and max.  
         return (\@list, $min, $max);  
1156  }  }
1157    
1158  =head3 FType  =head3 FType
1159    
1160  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1161    
1162  Return the type of a feature.  Return the type of a feature.
1163    
# Line 934  Line 1175 
1175  =back  =back
1176    
1177  =cut  =cut
1178    #: Return Type $;
1179  sub FType {  sub FType {
1180          # Get the parameters.          # Get the parameters.
1181          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1182          # Get the specified feature's type.          # Get the specified feature's type.
1183          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);          my ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(feature-type)']);
1184          # Return the result.          # Return the result.
# Line 947  Line 1187 
1187    
1188  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1189    
1190  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1191    
1192  Return the annotations of a feature.  Return the annotations of a feature.
1193    
# Line 957  Line 1197 
1197    
1198  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1199    
1200    =item rawFlag
1201    
1202    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1203    will be returned in human-readable form.
1204    
1205  =item RETURN  =item RETURN
1206    
1207  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.
# Line 972  Line 1217 
1217  =back  =back
1218    
1219  =cut  =cut
1220    #: Return Type @%;
1221  sub FeatureAnnotations {  sub FeatureAnnotations {
1222          # Get the parameters.          # Get the parameters.
1223          my $self = shift @_;      my ($self, $featureID, $rawFlag) = @_;
         my ($featureID) = @_;  
1224          # 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.
1225          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1226                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 989  Line 1233 
1233                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1234                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1235                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1236            # Convert the time, if necessary.
1237            if (! $rawFlag) {
1238                $timeStamp = FriendlyTimestamp($timeStamp);
1239            }
1240                  # Assemble them into a hash.                  # Assemble them into a hash.
1241                  my $annotationHash = { featureID => $featureID, timeStamp => $timeStamp,          my $annotationHash = { featureID => $featureID,
1242                                   timeStamp => $timeStamp,
1243                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1244                  # Add it to the return list.                  # Add it to the return list.
1245                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1001  Line 1250 
1250    
1251  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1252    
1253  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1254    
1255  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
1256  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,
1257  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
1258  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,
1259  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.
1260  features only have a small number of annotations.  Finally, if a single user has multiple functional assignments, we will only keep the most
1261    recent one.
1262    
1263  =over 4  =over 4
1264    
# Line 1016  Line 1266 
1266    
1267  ID of the feature whose functional assignments are desired.  ID of the feature whose functional assignments are desired.
1268    
1269    =item RETURN
1270    
1271    Returns a hash mapping the user IDs to functional assignment IDs.
1272    
1273  =back  =back
1274    
1275  =cut  =cut
1276    #: Return Type %;
1277  sub AllFunctionsOf {  sub AllFunctionsOf {
1278          # Get the parameters.          # Get the parameters.
1279          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1280          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1281          my @query = $self->GetFlat(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1282                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1283                                                          [$featureID], 'Annotation(annotation)');                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1284                                               'MadeAnnotation(from-link)']);
1285          # Declare the return hash.          # Declare the return hash.
1286          my %retVal;          my %retVal;
1287        # Now we sort the assignments by timestamp in reverse.
1288        my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1289          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1290          for my $text (@query) {      for my $annotation (@sortedQuery) {
1291            # Get the annotation fields.
1292            my ($timeStamp, $text, $user) = @{$annotation};
1293                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1294                  my ($user, $function) = ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1295                  if ($user) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1296                          # Here it is, so stuff it in the return hash.              # Here it is a functional assignment and there has been no
1297                          $retVal{$function} = $user;              # previous assignment for this user, so we stuff it in the
1298                # return hash.
1299                $retVal{$actualUser} = $function;
1300                  }                  }
1301          }          }
1302          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1045  Line 1305 
1305    
1306  =head3 FunctionOf  =head3 FunctionOf
1307    
1308  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1309    
1310    Return the most recently-determined functional assignment of a particular feature.
1311    
1312  Return the most recently-determined functional assignment of a particular feature. A functional  The functional assignment is handled differently depending on the type of feature. If
1313  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  the feature is identified by a FIG ID (begins with the string C<fig|>), then the functional
1314  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  assignment is taken from the B<Feature> or C<Annotation> table, depending.
1315  we cannot filter on the content of the annotation itself because it's a text field; however, this  
1316  is not a big problem because most features only have a small number of annotations.  Each user has an associated list of trusted users. The assignment returned will be the most
1317    recent one by at least one of the trusted users. If no trusted user list is available, then
1318    the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1319    is trusted.
1320    
1321    If the feature is B<not> identified by a FIG ID, then the functional assignment
1322    information is taken from the B<ExternalAliasFunc> table. If the table does
1323    not contain an entry for the feature, an undefined value is returned.
1324    
1325  =over 4  =over 4
1326    
# Line 1061  Line 1330 
1330    
1331  =item userID (optional)  =item userID (optional)
1332    
1333  ID of the user whose function determination is desired. If omitted, C<FIG> is assumed.  ID of the user whose function determination is desired. If omitted, the primary
1334    functional assignment in the B<Feature> table will be returned.
1335    
1336  =item RETURN  =item RETURN
1337    
# Line 1070  Line 1340 
1340  =back  =back
1341    
1342  =cut  =cut
1343    #: Return Type $;
1344  sub FunctionOf {  sub FunctionOf {
1345          # Get the parameters.          # Get the parameters.
1346          my $self = shift @_;      my ($self, $featureID, $userID) = @_;
1347          my ($featureID, $userID) = @_;      # Declare the return value.
         if (!$userID) { $userID = 'FIG'; }  
         # Build a query for all of the feature's annotation, sorted by date.  
         my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],  
                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);  
         # Declare the return value. We'll set this to the most recent annotation for the  
         # specified user.  
1348          my $retVal;          my $retVal;
1349        # Determine the ID type.
1350        if ($featureID =~ m/^fig\|/) {
1351            # Here we have a FIG feature ID.
1352            if (!$userID) {
1353                # Use the primary assignment.
1354                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1355            } else {
1356                # We must build the list of trusted users.
1357                my %trusteeTable = ();
1358                # Check the user ID.
1359                if (!$userID) {
1360                    # No user ID, so only FIG is trusted.
1361                    $trusteeTable{FIG} = 1;
1362                } else {
1363                    # Add this user's ID.
1364                    $trusteeTable{$userID} = 1;
1365                    # Look for the trusted users in the database.
1366                    my @trustees = $self->GetFlat(['IsTrustedBy'], 'IsTrustedBy(from-link) = ?', [$userID], 'IsTrustedBy(to-link)');
1367                    if (! @trustees) {
1368                        # None were found, so build a default list.
1369                        $trusteeTable{FIG} = 1;
1370                    } else {
1371                        # Otherwise, put all the trustees in.
1372                        for my $trustee (@trustees) {
1373                            $trusteeTable{$trustee} = 1;
1374                        }
1375                    }
1376                }
1377                # Build a query for all of the feature's annotations, sorted by date.
1378                my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1379                                       "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1380                                       [$featureID]);
1381          my $timeSelected = 0;          my $timeSelected = 0;
1382          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1383          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1384                  # Get the annotation text.                  # Get the annotation text.
1385                  my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);                  my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1386                  # Check to see if this is a functional assignment for the desired user.                                                           'Annotation(time)', 'MadeAnnotation(from-link)']);
1387                  my ($user, $type, $function) = split(/\n/, $text);                  # Check to see if this is a functional assignment for a trusted user.
1388                  if ($type =~ m/^set $userID function to$/i) {                  my ($actualUser, $function) = _ParseAssignment($user, $text);
1389                          # Here it is, so we check the time and save the assignment value.                  Trace("Assignment user is $actualUser, text is $function.") if T(4);
1390                          if ($time > $timeSelected) {                  if ($actualUser) {
1391                        # Here it is a functional assignment. Check the time and the user
1392                        # name. The time must be recent and the user must be trusted.
1393                        if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1394                                  $retVal = $function;                                  $retVal = $function;
1395                                  $timeSelected = $time;                                  $timeSelected = $time;
1396                          }                          }
1397                  }                  }
1398          }          }
1399            }
1400        } else {
1401            # Here we have a non-FIG feature ID. In this case the user ID does not
1402            # matter. We simply get the information from the External Alias Function
1403            # table.
1404            ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);
1405        }
1406          # Return the assignment found.          # Return the assignment found.
1407          return $retVal;          return $retVal;
1408  }  }
1409    
1410    =head3 FunctionsOf
1411    
1412        my @functionList = $sprout->FunctionOf($featureID, $userID);
1413    
1414    Return the functional assignments of a particular feature.
1415    
1416    The functional assignment is handled differently depending on the type of feature. If
1417    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1418    assignment is a type of annotation. The format of an assignment is described in
1419    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1420    annotation itself because it's a text field; however, this is not a big problem because
1421    most features only have a small number of annotations.
1422    
1423    If the feature is B<not> identified by a FIG ID, then the functional assignment
1424    information is taken from the B<ExternalAliasFunc> table. If the table does
1425    not contain an entry for the feature, an empty list is returned.
1426    
1427    =over 4
1428    
1429    =item featureID
1430    
1431    ID of the feature whose functional assignments are desired.
1432    
1433    =item RETURN
1434    
1435    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1436    that user.
1437    
1438    =back
1439    
1440    =cut
1441    #: Return Type @@;
1442    sub FunctionsOf {
1443        # Get the parameters.
1444        my ($self, $featureID) = @_;
1445        # Declare the return value.
1446        my @retVal = ();
1447        # Determine the ID type.
1448        if ($featureID =~ m/^fig\|/) {
1449            # Here we have a FIG feature ID. We must build the list of trusted
1450            # users.
1451            my %trusteeTable = ();
1452            # Build a query for all of the feature's annotations, sorted by date.
1453            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1454                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1455                                   [$featureID]);
1456            my $timeSelected = 0;
1457            # Loop until we run out of annotations.
1458            while (my $annotation = $query->Fetch()) {
1459                # Get the annotation text.
1460                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1461                                                                'Annotation(time)',
1462                                                                'MadeAnnotation(user)']);
1463                # Check to see if this is a functional assignment for a trusted user.
1464                my ($actualUser, $function) = _ParseAssignment($user, $text);
1465                if ($actualUser) {
1466                    # Here it is a functional assignment.
1467                    push @retVal, [$actualUser, $function];
1468                }
1469            }
1470        } else {
1471            # Here we have a non-FIG feature ID. In this case the user ID does not
1472            # matter. We simply get the information from the External Alias Function
1473            # table.
1474            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1475                                                     ['ExternalAliasFunc(func)']);
1476            push @retVal, map { ['master', $_] } @assignments;
1477        }
1478        # Return the assignments found.
1479        return @retVal;
1480    }
1481    
1482  =head3 BBHList  =head3 BBHList
1483    
1484  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1485    
1486  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
1487  on a specified target genome.  on a specified target genome.
# Line 1120  Line 1498 
1498    
1499  =item RETURN  =item RETURN
1500    
1501  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
1502  their best hits.  on the target genome.
1503    
1504  =back  =back
1505    
1506  =cut  =cut
1507    #: Return Type %;
1508  sub BBHList {  sub BBHList {
1509          # Get the parameters.          # Get the parameters.
1510          my $self = shift @_;      my ($self, $genomeID, $featureList) = @_;
         my ($genomeID, $featureList) = @_;  
1511          # Create the return structure.          # Create the return structure.
1512          my %retVal = ();          my %retVal = ();
1513          # Loop through the incoming features.          # Loop through the incoming features.
1514          for my $featureID (@{$featureList}) {          for my $featureID (@{$featureList}) {
1515                  # Create a query to get the feature's best hit.          # Ask the server for the feature's best hit.
1516                  my $query = $self->Get(['IsBidirectionalBestHitOf'],          my @bbhData = FIGRules::BBHData($featureID);
1517                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",          # Peel off the BBHs found.
1518                                                             [$featureID, $genomeID]);          my @found = ();
1519                  # Look for the best hit.          for my $bbh (@bbhData) {
1520                  my $bbh = $query->Fetch;              my $fid = $bbh->[0];
1521                  if ($bbh) {              my $bbGenome = $self->GenomeOf($fid);
1522                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              if ($bbGenome eq $genomeID) {
1523                          $retVal{$featureID} = $targetFeature;                  push @found, $fid;
1524                }
1525                  }                  }
1526            $retVal{$featureID} = \@found;
1527          }          }
1528          # Return the mapping.          # Return the mapping.
1529          return \%retVal;          return \%retVal;
1530  }  }
1531    
1532    =head3 SimList
1533    
1534        my %similarities = $sprout->SimList($featureID, $count);
1535    
1536    Return a list of the similarities to the specified feature.
1537    
1538    This method just returns the bidirectional best hits for performance reasons.
1539    
1540    =over 4
1541    
1542    =item featureID
1543    
1544    ID of the feature whose similarities are desired.
1545    
1546    =item count
1547    
1548    Maximum number of similar features to be returned, or C<0> to return them all.
1549    
1550    =back
1551    
1552    =cut
1553    #: Return Type %;
1554    sub SimList {
1555        # Get the parameters.
1556        my ($self, $featureID, $count) = @_;
1557        # Ask for the best hits.
1558        my @lists = FIGRules::BBHData($featureID);
1559        # Create the return value.
1560        my %retVal = ();
1561        for my $tuple (@lists) {
1562            $retVal{$tuple->[0]} = $tuple->[1];
1563        }
1564        # Return the result.
1565        return %retVal;
1566    }
1567    
1568    =head3 IsComplete
1569    
1570        my $flag = $sprout->IsComplete($genomeID);
1571    
1572    Return TRUE if the specified genome is complete, else FALSE.
1573    
1574    =over 4
1575    
1576    =item genomeID
1577    
1578    ID of the genome whose completeness status is desired.
1579    
1580    =item RETURN
1581    
1582    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1583    not found.
1584    
1585    =back
1586    
1587    =cut
1588    #: Return Type $;
1589    sub IsComplete {
1590        # Get the parameters.
1591        my ($self, $genomeID) = @_;
1592        # Declare the return variable.
1593        my $retVal;
1594        # Get the genome's data.
1595        my $genomeData = $self->GetEntity('Genome', $genomeID);
1596        if ($genomeData) {
1597            # The genome exists, so get the completeness flag.
1598            $retVal = $genomeData->PrimaryValue('Genome(complete)');
1599        }
1600        # Return the result.
1601        return $retVal;
1602    }
1603    
1604  =head3 FeatureAliases  =head3 FeatureAliases
1605    
1606  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1607    
1608  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1609    
# Line 1170  Line 1621 
1621  =back  =back
1622    
1623  =cut  =cut
1624    #: Return Type @;
1625  sub FeatureAliases {  sub FeatureAliases {
1626          # Get the parameters.          # Get the parameters.
1627          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
1628          # Get the desired feature's aliases          # Get the desired feature's aliases
1629          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1630          # Return the result.          # Return the result.
1631          return @retVal;          return @retVal;
1632  }  }
1633    
1634  =head3 GenomeOf  =head3 GenomeOf
1635    
1636  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1637    
1638  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1639    
1640  =over 4  =over 4
1641    
1642  =item featureID  =item featureID
1643    
1644  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1645    
1646  =item RETURN  =item RETURN
1647    
1648  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1649  an undefined value.  found, returns an undefined value.
1650    
1651  =back  =back
1652    
1653  =cut  =cut
1654    #: Return Type $;
1655  sub GenomeOf {  sub GenomeOf {
1656          # Get the parameters.          # Get the parameters.
1657          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
         # Create a query to find the genome associated with the feature.  
         my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);  
1658          # Declare the return value.          # Declare the return value.
1659          my $retVal;          my $retVal;
1660          # Get the genome ID.      # Parse the genome ID from the feature ID.
1661          if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1662                  ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1663        } else {
1664            Confess("Invalid feature ID $featureID.");
1665          }          }
1666          # Return the value found.          # Return the value found.
1667          return $retVal;          return $retVal;
# Line 1220  Line 1669 
1669    
1670  =head3 CoupledFeatures  =head3 CoupledFeatures
1671    
1672  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1673    
1674  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1675  functionally coupled if they tend to be clustered on the same chromosome.  functionally coupled if they tend to be clustered on the same chromosome.
# Line 1238  Line 1687 
1687  =back  =back
1688    
1689  =cut  =cut
1690    #: Return Type %;
1691  sub CoupledFeatures {  sub CoupledFeatures {
1692          # Get the parameters.          # Get the parameters.
1693          my $self = shift @_;      my ($self, $featureID) = @_;
1694          my ($featureID) = @_;      # Ask the coupling server for the data.
1695          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1696          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1697          # (B,A) will also be found.      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1698          my $query = $self->Get(['IsClusteredOnChromosomeWith'],      # Form them into a hash.
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
         # This value will be set to TRUE if we find at least one coupled feature.  
         my $found = 0;  
         # Create the return hash.  
1699          my %retVal = ();          my %retVal = ();
1700          # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1701          while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1702                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          my ($featureID2, $score) = @{$pair};
1703                                                                      'IsClusteredOnChromosomeWith(score)']);          # Only proceed if the feature is in NMPDR.
1704                  $retVal{$otherFeatureID} = $score;          if ($self->_CheckFeature($featureID2)) {
1705                  $found = 1;              $retVal{$featureID2} = $score;
1706            }
1707          }          }
1708          # Functional coupling is reflexive. If we found at least one coupled feature, we must add          # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1709          # the incoming feature as well.          # the incoming feature as well.
1710          if ($found) {      if (keys %retVal) {
1711                  $retVal{$featureID} = 9999;                  $retVal{$featureID} = 9999;
1712      }      }
1713          # Return the hash.          # Return the hash.
1714          return %retVal;          return %retVal;
1715  }  }
1716    
1717  =head3 GetEntityTypes  =head3 CouplingEvidence
1718    
1719        my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
1720    
1721    Return the evidence for a functional coupling.
1722    
1723    A pair of features is considered evidence of a coupling between two other
1724    features if they occur close together on a contig and both are similar to
1725    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1726    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1727    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1728    similar to B<A2>.
1729    
1730    The score of a coupling is determined by the number of pieces of evidence
1731    that are considered I<representative>. If several evidence items belong to
1732    a group of genomes that are close to each other, only one of those items
1733    is considered representative. The other evidence items are presumed to be
1734    there because of the relationship between the genomes rather than because
1735    the two proteins generated by the features have a related functionality.
1736    
1737    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1738    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1739    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1740    and FALSE otherwise.
1741    
1742    =over 4
1743    
1744    =item peg1
1745    
1746    ID of the feature of interest.
1747    
1748    =item peg2
1749    
1750    ID of a feature functionally coupled to the feature of interest.
1751    
1752    =item RETURN
1753    
1754    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1755    of interest, a feature similar to the functionally coupled feature, and a flag
1756    that is TRUE for a representative piece of evidence and FALSE otherwise.
1757    
1758    =back
1759    
1760    =cut
1761    #: Return Type @@;
1762    sub CouplingEvidence {
1763        # Get the parameters.
1764        my ($self, $peg1, $peg2) = @_;
1765        # Declare the return variable.
1766        my @retVal = ();
1767        # Get the coupling and evidence data.
1768        my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
1769        # Loop through the raw data, saving the ones that are in NMPDR genomes.
1770        for my $rawTuple (@rawData) {
1771            if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
1772                push @retVal, $rawTuple;
1773            }
1774        }
1775        # Return the result.
1776        return @retVal;
1777    }
1778    
1779    =head3 GetSynonymGroup
1780    
1781        my $id = $sprout->GetSynonymGroup($fid);
1782    
1783    Return the synonym group name for the specified feature.
1784    
1785    =over 4
1786    
1787    =item fid
1788    
1789    ID of the feature whose synonym group is desired.
1790    
1791    =item RETURN
1792    
1793    The name of the synonym group to which the feature belongs. If the feature does
1794    not belong to a synonym group, the feature ID itself is returned.
1795    
1796    =back
1797    
1798    =cut
1799    
1800    sub GetSynonymGroup {
1801        # Get the parameters.
1802        my ($self, $fid) = @_;
1803        # Declare the return variable.
1804        my $retVal;
1805        # Find the synonym group.
1806        my @groups = $self->GetFlat(['IsSynonymGroupFor'], "IsSynonymGroupFor(to-link) = ?",
1807                                       [$fid], 'IsSynonymGroupFor(from-link)');
1808        # Check to see if we found anything.
1809        if (@groups) {
1810            $retVal = $groups[0];
1811        } else {
1812            $retVal = $fid;
1813        }
1814        # Return the result.
1815        return $retVal;
1816    }
1817    
1818    =head3 GetBoundaries
1819    
1820        my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
1821    
1822    Determine the begin and end boundaries for the locations in a list. All of the
1823    locations must belong to the same contig and have mostly the same direction in
1824    order for this method to produce a meaningful result. The resulting
1825    begin/end pair will contain all of the bases in any of the locations.
1826    
1827    =over 4
1828    
1829    =item locList
1830    
1831    List of locations to process.
1832    
1833    =item RETURN
1834    
1835  C<< my @entityList = $sprout->GetEntityTypes(); >>  Returns a 3-tuple consisting of the contig ID, the beginning boundary,
1836    and the ending boundary. The beginning boundary will be left of the
1837    end for mostly-forward locations and right of the end for mostly-backward
1838    locations.
1839    
1840  Return the list of supported entity types.  =back
1841    
1842  =cut  =cut
1843    
1844  sub GetEntityTypes {  sub GetBoundaries {
1845          # Get the parameters.          # Get the parameters.
1846          my $self = shift @_;      my ($self, @locList) = @_;
1847          # Get the underlying database object.      # Set up the counters used to determine the most popular direction.
1848          my $erdb = $self->{_erdb};      my %counts = ( '+' => 0, '-' => 0 );
1849          # Get its entity type list.      # Get the last location and parse it.
1850          my @retVal = $erdb->GetEntityTypes();      my $locObject = BasicLocation->new(pop @locList);
1851        # Prime the loop with its data.
1852        my ($contig, $beg, $end) = ($locObject->Contig, $locObject->Left, $locObject->Right);
1853        # Count its direction.
1854        $counts{$locObject->Dir}++;
1855        # Loop through the remaining locations. Note that in most situations, this loop
1856        # will not iterate at all, because most of the time we will be dealing with a
1857        # singleton list.
1858        for my $loc (@locList) {
1859            # Create a location object.
1860            my $locObject = BasicLocation->new($loc);
1861            # Count the direction.
1862            $counts{$locObject->Dir}++;
1863            # Get the left end and the right end.
1864            my $left = $locObject->Left;
1865            my $right = $locObject->Right;
1866            # Merge them into the return variables.
1867            if ($left < $beg) {
1868                $beg = $left;
1869            }
1870            if ($right > $end) {
1871                $end = $right;
1872            }
1873        }
1874        # If the most common direction is reverse, flip the begin and end markers.
1875        if ($counts{'-'} > $counts{'+'}) {
1876            ($beg, $end) = ($end, $beg);
1877        }
1878        # Return the result.
1879        return ($contig, $beg, $end);
1880  }  }
1881    
1882  =head3 ReadFasta  =head3 ReadFasta
1883    
1884  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
1885    
1886  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
1887  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1310  Line 1904 
1904  =back  =back
1905    
1906  =cut  =cut
1907    #: Return Type %;
1908  sub ReadFasta {  sub ReadFasta {
1909          # Get the parameters.          # Get the parameters.
1910          my ($fileName, $prefix) = @_;          my ($fileName, $prefix) = @_;
# Line 1329  Line 1923 
1923                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1924                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1925                          if ($id) {                          if ($id) {
1926                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1927                          }                          }
1928                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1929                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1930                  } else {                  } else {
1931                          # 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.
1932                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1933                # case.
1934                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1935                          $sequence .= $1;                          $sequence .= $1;
1936                  }                  }
1937          }          }
1938          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1939          if ($sequence) {          if ($sequence) {
1940                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1941          }          }
1942        # Close the file.
1943        close FASTAFILE;
1944          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1945          return %retVal;          return %retVal;
1946  }  }
1947    
1948  =head3 FormatLocations  =head3 FormatLocations
1949    
1950  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
1951    
1952  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
1953  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
1954  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,
1955    it will not be changed; otherwise, it will be converted. This method can also be used to
1956    perform the reverse task-- insuring that all the locations are in the old format.
1957    
1958  =over 4  =over 4
1959    
# Line 1378  Line 1977 
1977  =back  =back
1978    
1979  =cut  =cut
1980    #: Return Type @;
1981  sub FormatLocations {  sub FormatLocations {
1982          # Get the parameters.          # Get the parameters.
1983          my $self = shift @_;      my ($self, $prefix, $locations, $oldFormat) = @_;
         my ($prefix, $locations, $oldFormat) = @_;  
1984          # Create the return list.          # Create the return list.
1985          my @retVal = ();          my @retVal = ();
1986          # Check to see if any locations were passed in.          # Check to see if any locations were passed in.
1987          if ($locations eq '') {          if ($locations eq '') {
1988              confess "No locations specified.";          Confess("No locations specified.");
1989          } else {          } else {
1990                  # Loop through the locations, converting them to the new format.                  # Loop through the locations, converting them to the new format.
1991                  for my $location (@{$locations}) {                  for my $location (@{$locations}) {
# Line 1414  Line 2012 
2012    
2013  =head3 DumpData  =head3 DumpData
2014    
2015  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2016    
2017  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.
2018    
# Line 1422  Line 2020 
2020    
2021  sub DumpData {  sub DumpData {
2022          # Get the parameters.          # Get the parameters.
2023          my $self = shift @_;      my ($self) = @_;
2024          # Get the data directory name.          # Get the data directory name.
2025          my $outputDirectory = $self->{_options}->{dataDir};          my $outputDirectory = $self->{_options}->{dataDir};
2026          # Dump the relations.          # Dump the relations.
2027          $self->{_erdb}->DumpRelations($outputDirectory);      $self->DumpRelations($outputDirectory);
2028  }  }
2029    
2030  =head3 XMLFileName  =head3 XMLFileName
2031    
2032  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2033    
2034  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2035    
2036  =cut  =cut
2037    #: Return Type $;
2038  sub XMLFileName {  sub XMLFileName {
2039          my $self = shift @_;      my ($self) = @_;
2040          return $self->{_xmlName};          return $self->{_xmlName};
2041  }  }
2042    
2043    =head3 GetGenomeNameData
2044    
2045        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2046    
2047    Return the genus, species, and unique characterization for a genome. This
2048    is similar to L</GenusSpecies>, with the exception that it returns the
2049    values in three seperate fields.
2050    
2051    =over 4
2052    
2053    =item genomeID
2054    
2055    ID of the genome whose name data is desired.
2056    
2057    =item RETURN
2058    
2059    Returns a three-element list, consisting of the genus, species, and strain
2060    of the specified genome. If the genome is not found, an error occurs.
2061    
2062    =back
2063    
2064    =cut
2065    
2066    sub GetGenomeNameData {
2067        # Get the parameters.
2068        my ($self, $genomeID) = @_;
2069        # Get the desired values.
2070        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2071                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2072        # Throw an error if they were not found.
2073        if (! defined $genus) {
2074            Confess("Genome $genomeID not found in database.");
2075        }
2076        # Return the results.
2077        return ($genus, $species, $strain);
2078    }
2079    
2080    =head3 GetGenomeByNameData
2081    
2082        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2083    
2084    Return a list of the IDs of the genomes with the specified genus,
2085    species, and strain. In almost every case, there will be either zero or
2086    one IDs returned; however, two or more IDs could be returned if there are
2087    multiple versions of the genome in the database.
2088    
2089    =over 4
2090    
2091    =item genus
2092    
2093    Genus of the desired genome.
2094    
2095    =item species
2096    
2097    Species of the desired genome.
2098    
2099    =item strain
2100    
2101    Strain (unique characterization) of the desired genome. This may be an empty
2102    string, in which case it is presumed that the desired genome has no strain
2103    specified.
2104    
2105    =item RETURN
2106    
2107    Returns a list of the IDs of the genomes having the specified genus, species, and
2108    strain.
2109    
2110    =back
2111    
2112    =cut
2113    
2114    sub GetGenomeByNameData {
2115        # Get the parameters.
2116        my ($self, $genus, $species, $strain) = @_;
2117        # Try to find the genomes.
2118        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2119                                    [$genus, $species, $strain], 'Genome(id)');
2120        # Return the result.
2121        return @retVal;
2122    }
2123    
2124  =head3 Insert  =head3 Insert
2125    
2126  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2127    
2128  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
2129  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 1453  Line 2132 
2132  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
2133  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>.
2134    
2135  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']});
2136    
2137  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
2138  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>.
2139    
2140  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'});
2141    
2142  =over 4  =over 4
2143    
# Line 1473  Line 2152 
2152  =back  =back
2153    
2154  =cut  =cut
2155    #: Return Type ;
2156  sub Insert {  sub Insert {
2157          # Get the parameters.          # Get the parameters.
2158          my $self = shift @_;      my ($self, $objectType, $fieldHash) = @_;
         my ($objectType, $fieldHash) = @_;  
2159          # Call the underlying method.          # Call the underlying method.
2160          $self->{_erdb}->InsertObject($objectType, $fieldHash);      $self->InsertObject($objectType, $fieldHash);
2161  }  }
2162    
2163  =head3 Annotate  =head3 Annotate
2164    
2165  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2166    
2167  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
2168  specified feature and user.  specified feature and user.
# Line 1515  Line 2193 
2193  =back  =back
2194    
2195  =cut  =cut
2196    #: Return Type $;
2197  sub Annotate {  sub Annotate {
2198          # Get the parameters.          # Get the parameters.
2199          my $self = shift @_;      my ($self, $fid, $timestamp, $user, $text) = @_;
         my ($fid, $timestamp, $user, $text) = @_;  
2200          # Create the annotation ID.          # Create the annotation ID.
2201          my $aid = "$fid:$timestamp";          my $aid = "$fid:$timestamp";
2202          # Insert the Annotation object.          # Insert the Annotation object.
# Line 1539  Line 2216 
2216    
2217  =head3 AssignFunction  =head3 AssignFunction
2218    
2219  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2220    
2221  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
2222  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.  
2223    
2224  =over 4  =over 4
2225    
# Line 1553  Line 2229 
2229    
2230  =item user  =item user
2231    
2232  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>.
2233    
2234  =item function  =item function
2235    
2236  Text of the function being assigned.  Text of the function being assigned.
2237    
2238    =item assigningUser (optional)
2239    
2240    Name of the individual user making the assignment. If omitted, defaults to the user group.
2241    
2242  =item RETURN  =item RETURN
2243    
2244  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1566  Line 2246 
2246  =back  =back
2247    
2248  =cut  =cut
2249    #: Return Type $;
2250  sub AssignFunction {  sub AssignFunction {
2251          # Get the parameters.          # Get the parameters.
2252          my $self = shift @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
2253          my ($featureID, $user, $function) = @_;      # Default the assigning user.
2254        if (! $assigningUser) {
2255            $assigningUser = $user;
2256        }
2257          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
2258          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
2259          # Get the current time.          # Get the current time.
2260          my $now = time;          my $now = time;
2261          # Declare the return variable.          # Declare the return variable.
# Line 1593  Line 2276 
2276    
2277  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2278    
2279  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2280    
2281  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
2282  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 1614  Line 2297 
2297  =back  =back
2298    
2299  =cut  =cut
2300    #: Return Type @;
2301  sub FeaturesByAlias {  sub FeaturesByAlias {
2302          # Get the parameters.          # Get the parameters.
2303          my $self = shift @_;      my ($self, $alias) = @_;
         my ($alias) = @_;  
2304          # Declare the return variable.          # Declare the return variable.
2305          my @retVal = ();          my @retVal = ();
2306          # Parse the alias.          # Parse the alias.
# Line 1628  Line 2310 
2310                  push @retVal, $mappedAlias;                  push @retVal, $mappedAlias;
2311          } else {          } else {
2312                  # 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.
2313                  @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2314          }          }
2315          # Return the result.          # Return the result.
2316          return @retVal;          return @retVal;
2317  }  }
2318    
 =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  
   
 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;  
 }  
   
2319  =head3 FeatureTranslation  =head3 FeatureTranslation
2320    
2321  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2322    
2323  Return the translation of a feature.  Return the translation of a feature.
2324    
# Line 1688  Line 2335 
2335  =back  =back
2336    
2337  =cut  =cut
2338    #: Return Type $;
2339  sub FeatureTranslation {  sub FeatureTranslation {
2340          # Get the parameters.          # Get the parameters.
2341          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2342          # Get the specified feature's translation.          # Get the specified feature's translation.
2343          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);          my ($retVal) = $self->GetEntityValues("Feature", $featureID, ['Feature(translation)']);
2344          return $retVal;          return $retVal;
# Line 1700  Line 2346 
2346    
2347  =head3 Taxonomy  =head3 Taxonomy
2348    
2349  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2350    
2351  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
2352  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>,
2353  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2354    
2355  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2356    
2357  =over 4  =over 4
2358    
# Line 1721  Line 2367 
2367  =back  =back
2368    
2369  =cut  =cut
2370    #: Return Type @;
2371  sub Taxonomy {  sub Taxonomy {
2372          # Get the parameters.          # Get the parameters.
2373          my $self = shift @_;      my ($self, $genome) = @_;
         my ($genome) = @_;  
2374          # Find the specified genome's taxonomy string.          # Find the specified genome's taxonomy string.
2375          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);          my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);
2376          # Declare the return variable.          # Declare the return variable.
# Line 1742  Line 2387 
2387    
2388  =head3 CrudeDistance  =head3 CrudeDistance
2389    
2390  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2391    
2392  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
2393  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 1765  Line 2410 
2410  =back  =back
2411    
2412  =cut  =cut
2413    #: Return Type $;
2414  sub CrudeDistance {  sub CrudeDistance {
2415          # Get the parameters.          # Get the parameters.
2416          my $self = shift @_;      my ($self, $genome1, $genome2) = @_;
         my ($genome1, $genome2) = @_;  
2417          # Insure that the distance is commutative by sorting the genome IDs.          # Insure that the distance is commutative by sorting the genome IDs.
2418          my ($genomeA, $genomeB);          my ($genomeA, $genomeB);
2419          if ($genome2 < $genome2) {          if ($genome2 < $genome2) {
# Line 1795  Line 2439 
2439    
2440  =head3 RoleName  =head3 RoleName
2441    
2442  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2443    
2444  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
2445  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 1813  Line 2457 
2457  =back  =back
2458    
2459  =cut  =cut
2460    #: Return Type $;
2461  sub RoleName {  sub RoleName {
2462          # Get the parameters.          # Get the parameters.
2463          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2464          # Get the specified role's name.          # Get the specified role's name.
2465          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);          my ($retVal) = $self->GetEntityValues('Role', $roleID, ['Role(name)']);
2466          # Use the ID if the role has no name.          # Use the ID if the role has no name.
# Line 1830  Line 2473 
2473    
2474  =head3 RoleDiagrams  =head3 RoleDiagrams
2475    
2476  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2477    
2478  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2479    
# Line 1847  Line 2490 
2490  =back  =back
2491    
2492  =cut  =cut
2493    #: Return Type @;
2494  sub RoleDiagrams {  sub RoleDiagrams {
2495          # Get the parameters.          # Get the parameters.
2496          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2497          # Query for the diagrams.          # Query for the diagrams.
2498          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @retVal = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2499                                                                  'RoleOccursIn(to-link)');                                                                  'RoleOccursIn(to-link)');
# Line 1859  Line 2501 
2501          return @retVal;          return @retVal;
2502  }  }
2503    
2504    =head3 GetProperties
2505    
2506        my @list = $sprout->GetProperties($fid, $key, $value, $url);
2507    
2508    Return a list of the properties with the specified characteristics.
2509    
2510    Properties are the Sprout analog of the FIG attributes. The call is
2511    passed directly to the CustomAttributes or RemoteCustomAttributes object
2512    contained in this object.
2513    
2514    This method returns a series of tuples that match the specified criteria. Each tuple
2515    will contain an object ID, a key, and one or more values. The parameters to this
2516    method therefore correspond structurally to the values expected in each tuple. In
2517    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2518    of the parameters. So, for example,
2519    
2520        my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2521    
2522    would return something like
2523    
2524        ['fig}100226.1.peg.1004', 'structure', 1, 2]
2525        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2526        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2527        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2528    
2529    Use of C<undef> in any position acts as a wild card (all values). You can also specify
2530    a list reference in the ID column. Thus,
2531    
2532        my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2533    
2534    would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2535    features.
2536    
2537    In addition to values in multiple sections, a single attribute key can have multiple
2538    values, so even
2539    
2540        my @attributeList = $sprout->GetProperties($peg, 'virulent');
2541    
2542    which has no wildcard in the key or the object ID, may return multiple tuples.
2543    
2544    =over 4
2545    
2546    =item objectID
2547    
2548    ID of object whose attributes are desired. If the attributes are desired for multiple
2549    objects, this parameter can be specified as a list reference. If the attributes are
2550    desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2551    attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
2552    
2553    =item key
2554    
2555    Attribute key name. A value of C<undef> or an empty string will match all
2556    attribute keys. If the values are desired for multiple keys, this parameter can be
2557    specified as a list reference. Finally, you can specify attributes for a range of
2558    keys by putting a percent sign (C<%>) at the end.
2559    
2560    =item values
2561    
2562    List of the desired attribute values, section by section. If C<undef>
2563    or an empty string is specified, all values in that section will match. A
2564    generic match can be requested by placing a percent sign (C<%>) at the end.
2565    In that case, all values that match up to and not including the percent sign
2566    will match. You may also specify a regular expression enclosed
2567    in slashes. All values that match the regular expression will be returned. For
2568    performance reasons, only values have this extra capability.
2569    
2570    =item RETURN
2571    
2572    Returns a list of tuples. The first element in the tuple is an object ID, the
2573    second is an attribute key, and the remaining elements are the sections of
2574    the attribute value. All of the tuples will match the criteria set forth in
2575    the parameter list.
2576    
2577    =back
2578    
2579    =cut
2580    
2581    sub GetProperties {
2582        # Get the parameters.
2583        my ($self, @parms) = @_;
2584        # Declare the return variable.
2585        my @retVal = $self->{_ca}->GetAttributes(@parms);
2586        # Return the result.
2587        return @retVal;
2588    }
2589    
2590  =head3 FeatureProperties  =head3 FeatureProperties
2591    
2592  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2593    
2594  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
2595  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
2596  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
2597  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
2598  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.  
2599    
2600  =over 4  =over 4
2601    
# Line 1879  Line 2605 
2605    
2606  =item RETURN  =item RETURN
2607    
2608  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.  
2609    
2610  =back  =back
2611    
2612  =cut  =cut
2613    #: Return Type @@;
2614  sub FeatureProperties {  sub FeatureProperties {
2615          # Get the parameters.          # Get the parameters.
2616          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2617          # Get the properties.          # Get the properties.
2618          my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2619                                                          ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2620                                                           'HasProperty(evidence)']);      my @retVal = ();
2621        for my $attributeRow (@attributes) {
2622            shift @{$attributeRow};
2623            push @retVal, $attributeRow;
2624        }
2625          # Return the resulting list.          # Return the resulting list.
2626          return @retVal;          return @retVal;
2627  }  }
2628    
2629  =head3 DiagramName  =head3 DiagramName
2630    
2631  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2632    
2633  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2634    
# Line 1917  Line 2645 
2645  =back  =back
2646    
2647  =cut  =cut
2648    #: Return Type $;
2649  sub DiagramName {  sub DiagramName {
2650          # Get the parameters.          # Get the parameters.
2651          my $self = shift @_;      my ($self, $diagramID) = @_;
         my ($diagramID) = @_;  
2652          # Get the specified diagram's name and return it.          # Get the specified diagram's name and return it.
2653          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);          my ($retVal) = $self->GetEntityValues('Diagram', $diagramID, ['Diagram(name)']);
2654          return $retVal;          return $retVal;
2655  }  }
2656    
2657    =head3 PropertyID
2658    
2659        my $id = $sprout->PropertyID($propName, $propValue);
2660    
2661    Return the ID of the specified property name and value pair, if the
2662    pair exists. Only a small subset of the FIG attributes are stored as
2663    Sprout properties, mostly for use in search optimization.
2664    
2665    =over 4
2666    
2667    =item propName
2668    
2669    Name of the desired property.
2670    
2671    =item propValue
2672    
2673    Value expected for the desired property.
2674    
2675    =item RETURN
2676    
2677    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2678    
2679    =back
2680    
2681    =cut
2682    
2683    sub PropertyID {
2684        # Get the parameters.
2685        my ($self, $propName, $propValue) = @_;
2686        # Try to find the ID.
2687        my ($retVal) = $self->GetFlat(['Property'],
2688                                      "Property(property-name) = ? AND Property(property-value) = ?",
2689                                      [$propName, $propValue], 'Property(id)');
2690        # Return the result.
2691        return $retVal;
2692    }
2693    
2694  =head3 MergedAnnotations  =head3 MergedAnnotations
2695    
2696  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2697    
2698  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2699  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 1950  Line 2714 
2714  =back  =back
2715    
2716  =cut  =cut
2717    #: Return Type @;
2718  sub MergedAnnotations {  sub MergedAnnotations {
2719          # Get the parameters.          # Get the parameters.
2720          my $self = shift @_;      my ($self, $list) = @_;
         my ($list) = @_;  
2721          # Create a list to hold the annotation tuples found.          # Create a list to hold the annotation tuples found.
2722          my @tuples = ();          my @tuples = ();
2723          # Loop through the features in the input list.          # Loop through the features in the input list.
# Line 1969  Line 2732 
2732          }          }
2733          # Sort the result list by timestamp.          # Sort the result list by timestamp.
2734          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;          my @retVal = sort { $a->[1] <=> $b->[1] } @tuples;
2735        # Loop through and make the time stamps friendly.
2736        for my $tuple (@retVal) {
2737            $tuple->[1] = FriendlyTimestamp($tuple->[1]);
2738        }
2739          # Return the sorted list.          # Return the sorted list.
2740          return @retVal;          return @retVal;
2741  }  }
2742    
2743  =head3 RoleNeighbors  =head3 RoleNeighbors
2744    
2745  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2746    
2747  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
2748  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 1995  Line 2762 
2762  =back  =back
2763    
2764  =cut  =cut
2765    #: Return Type @;
2766  sub RoleNeighbors {  sub RoleNeighbors {
2767          # Get the parameters.          # Get the parameters.
2768          my $self = shift @_;      my ($self, $roleID) = @_;
         my ($roleID) = @_;  
2769          # Get all the diagrams containing this role.          # Get all the diagrams containing this role.
2770          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],          my @diagrams = $self->GetFlat(['RoleOccursIn'], "RoleOccursIn(from-link) = ?", [$roleID],
2771                                                                    'RoleOccursIn(to-link)');                                                                    'RoleOccursIn(to-link)');
# Line 2019  Line 2785 
2785    
2786  =head3 FeatureLinks  =head3 FeatureLinks
2787    
2788  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
2789    
2790  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
2791  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 2038  Line 2804 
2804  =back  =back
2805    
2806  =cut  =cut
2807    #: Return Type @;
2808  sub FeatureLinks {  sub FeatureLinks {
2809          # Get the parameters.          # Get the parameters.
2810          my $self = shift @_;      my ($self, $featureID) = @_;
         my ($featureID) = @_;  
2811          # Get the feature's links.          # Get the feature's links.
2812          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);          my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(link)']);
2813          # Return the feature's links.          # Return the feature's links.
# Line 2051  Line 2816 
2816    
2817  =head3 SubsystemsOf  =head3 SubsystemsOf
2818    
2819  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
2820    
2821  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
2822  to the role the feature performs.  to the roles the feature performs.
2823    
2824  =over 4  =over 4
2825    
# Line 2064  Line 2829 
2829    
2830  =item RETURN  =item RETURN
2831    
2832  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.
2833    
2834  =back  =back
2835    
2836  =cut  =cut
2837    #: Return Type %@;
2838  sub SubsystemsOf {  sub SubsystemsOf {
2839          # Get the parameters.          # Get the parameters.
2840          my $self = shift @_;      my ($self, $featureID) = @_;
2841          my ($featureID) = @_;      # Get the subsystem list.
         # Use the SSCell to connect features to subsystems.  
2842          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2843                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2844                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2845          # Create the return value.          # Create the return value.
2846          my %retVal = ();          my %retVal = ();
2847        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2848        # in two spreadsheet cells.
2849        my %dupHash = ();
2850          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2851          for my $record (@subsystems) {          for my $record (@subsystems) {
2852                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2853            my ($subsys, $role) = @{$record};
2854            # Insure it's the first time for both.
2855            my $dupKey = "$subsys\n$role";
2856            if (! exists $dupHash{"$subsys\n$role"}) {
2857                $dupHash{$dupKey} = 1;
2858                push @{$retVal{$subsys}}, $role;
2859            }
2860          }          }
2861          # Return the hash.          # Return the hash.
2862          return %retVal;          return %retVal;
2863  }  }
2864    
2865    =head3 SubsystemList
2866    
2867        my @subsystems = $sprout->SubsystemList($featureID);
2868    
2869    Return a list containing the names of the subsystems in which the specified
2870    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2871    subsystem names, not the roles.
2872    
2873    =over 4
2874    
2875    =item featureID
2876    
2877    ID of the feature whose subsystem names are desired.
2878    
2879    =item RETURN
2880    
2881    Returns a list of the names of the subsystems in which the feature participates.
2882    
2883    =back
2884    
2885    =cut
2886    #: Return Type @;
2887    sub SubsystemList {
2888        # Get the parameters.
2889        my ($self, $featureID) = @_;
2890        # Get the list of names.
2891        my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
2892                                    [$featureID], 'HasRoleInSubsystem(to-link)');
2893        # Return the result, sorted.
2894        return sort @retVal;
2895    }
2896    
2897    =head3 GenomeSubsystemData
2898    
2899        my %featureData = $sprout->GenomeSubsystemData($genomeID);
2900    
2901    Return a hash mapping genome features to their subsystem roles.
2902    
2903    =over 4
2904    
2905    =item genomeID
2906    
2907    ID of the genome whose subsystem feature map is desired.
2908    
2909    =item RETURN
2910    
2911    Returns a hash mapping each feature of the genome to a list of 2-tuples. Eacb
2912    2-tuple contains a subsystem name followed by a role ID.
2913    
2914    =back
2915    
2916    =cut
2917    
2918    sub GenomeSubsystemData {
2919        # Get the parameters.
2920        my ($self, $genomeID) = @_;
2921        # Declare the return variable.
2922        my %retVal = ();
2923        # Get a list of the genome features that participate in subsystems. For each
2924        # feature we get its spreadsheet cells and the corresponding roles.
2925        my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],
2926                                 "HasFeature(from-link) = ?", [$genomeID],
2927                                 ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);
2928        # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems
2929        # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the
2930        # list. We use it at the beginning to get all the spreadsheet cells for the genome and
2931        # again at the end to filter out participation in subsystems with a negative variant code.
2932        my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],
2933                                     "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",
2934                                     [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);
2935        # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.
2936        # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We
2937        # link these two lists together to create the result. First, we want a hash mapping
2938        # spreadsheet cells to subsystem names.
2939        my %subHash = map { $_->[0] => $_->[1] } @cellData;
2940        # We loop through @cellData to build the hash.
2941        for my $roleEntry (@roleData) {
2942            # Get the data for this feature and cell.
2943            my ($fid, $cellID, $role) = @{$roleEntry};
2944            # Check for a subsystem name.
2945            my $subsys = $subHash{$cellID};
2946            if ($subsys) {
2947                # Insure this feature has an entry in the return hash.
2948                if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
2949                # Merge in this new data.
2950                push @{$retVal{$fid}}, [$subsys, $role];
2951            }
2952        }
2953        # Return the result.
2954        return %retVal;
2955    }
2956    
2957  =head3 RelatedFeatures  =head3 RelatedFeatures
2958    
2959  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
2960    
2961  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
2962  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2118  Line 2984 
2984  =back  =back
2985    
2986  =cut  =cut
2987    #: Return Type @;
2988  sub RelatedFeatures {  sub RelatedFeatures {
2989          # Get the parameters.          # Get the parameters.
2990          my $self = shift @_;      my ($self, $featureID, $function, $userID) = @_;
         my ($featureID, $function, $userID) = @_;  
2991          # Get a list of the features that are BBHs of the incoming feature.          # Get a list of the features that are BBHs of the incoming feature.
2992          my @bbhFeatures = $self->GetFlat(['IsBidirectionalBestHitOf'],      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);
                                                                          "IsBidirectionalBestHitOf(from-link) = ?", [$featureID],  
                                                                          'IsBidirectionalBestHitOf(to-link)');  
2993          # Now we loop through the features, pulling out the ones that have the correct          # Now we loop through the features, pulling out the ones that have the correct
2994          # functional assignment.          # functional assignment.
2995          my @retVal = ();          my @retVal = ();
# Line 2144  Line 3007 
3007    
3008  =head3 TaxonomySort  =head3 TaxonomySort
3009    
3010  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3011    
3012  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3013  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2167  Line 3030 
3030  =back  =back
3031    
3032  =cut  =cut
3033    #: Return Type @;
3034  sub TaxonomySort {  sub TaxonomySort {
3035          # Get the parameters.          # Get the parameters.
3036          my $self = shift @_;      my ($self, $featureIDs) = @_;
         my ($featureIDs) = @_;  
3037          # Create the working hash table.          # Create the working hash table.
3038          my %hashBuffer = ();          my %hashBuffer = ();
3039          # Loop through the features.          # Loop through the features.
# Line 2180  Line 3042 
3042                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",                  my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3043                                                                                  [$fid], 'Genome(taxonomy)');                                                                                  [$fid], 'Genome(taxonomy)');
3044                  # Add this feature to the hash buffer.                  # Add this feature to the hash buffer.
                 if (exists $hashBuffer{$taxonomy}) {  
3045                          push @{$hashBuffer{$taxonomy}}, $fid;                          push @{$hashBuffer{$taxonomy}}, $fid;
                 } else {  
                         $hashBuffer{$taxonomy} = [$fid];  
                 }  
3046          }          }
3047          # Sort the keys and get the elements.          # Sort the keys and get the elements.
3048          my @retVal = ();          my @retVal = ();
# Line 2195  Line 3053 
3053          return @retVal;          return @retVal;
3054  }  }
3055    
3056  =head3 GetAll  =head3 Protein
3057    
3058  C<< my @list = $sprout->GetAll(\@objectNames, $filterClause, \@parameters, \@fields, $count); >>      my $protein = Sprout::Protein($sequence, $table);
   
 Return a list of values taken from the objects returned by a query. The first three  
 parameters correspond to the parameters of the L</Get> method. The final parameter is  
 a list of the fields desired from each record found by the query. The field name  
 syntax is the standard syntax used for fields in the B<ERDB> system--  
 B<I<objectName>(I<fieldName>)>-- where I<objectName> is the name of the relevant entity  
 or relationship and I<fieldName> is the name of the field.  
   
 The list returned will be a list of lists. Each element of the list will contain  
 the values returned for the fields specified in the fourth parameter. If one of the  
 fields specified returns multiple values, they are flattened in with the rest. For  
 example, the following call will return a list of the features in a particular  
 spreadsheet cell, and each feature will be represented by a list containing the  
 feature ID followed by all of its aliases.  
   
 C<< $query = $sprout->Get(['ContainsFeature', 'Feature'], "ContainsFeature(from-link) = ?", [$ssCellID], ['Feature(id)', 'Feature(alias)']); >>  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item fields  
   
 List of the fields to be returned in each element of the list returned.  
   
 =item count  
   
 Maximum number of records to return. If omitted or 0, all available records will be returned.  
   
 =item RETURN  
   
 Returns a list of list references. Each element of the return list contains the values for the  
 fields specified in the B<fields> parameter.  
   
 =back  
   
 =cut  
   
 sub GetAll {  
         # Get the parameters.  
         my $self = shift @_;  
         my ($objectNames, $filterClause, $parameterList, $fields, $count) = @_;  
         # Create the query.  
         my $query = $self->Get($objectNames, $filterClause, $parameterList);  
         # Set up a counter of the number of records read.  
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
         # Return the resulting list.  
         return @retVal;  
 }  
   
 =head3 GetFlat  
   
 C<< my @list = $sprout->GetFlat(\@objectNames, $filterClause, $parameterList, $field); >>  
   
 This is a variation of L</GetAll> that asks for only a single field per record and  
 returns a single flattened list.  
   
 =over 4  
   
 =item objectNames  
   
 List containing the names of the entity and relationship objects to be retrieved.  
   
 =item filterClause  
   
 WHERE/ORDER BY clause (without the WHERE) to be used to filter and sort the query. The WHERE clause can  
 be parameterized with parameter markers (C<?>). Each field used must be specified in the standard form  
 B<I<objectName>(I<fieldName>)>. Any parameters specified in the filter clause should be added to the  
 parameter list as additional parameters. The fields in a filter clause can come from primary  
 entity relations, relationship relations, or secondary entity relations; however, all of the  
 entities and relationships involved must be included in the list of object names.  
   
 =item parameterList  
   
 List of the parameters to be substituted in for the parameters marks in the filter clause.  
   
 =item field  
   
 Name of the field to be used to get the elements of the list returned.  
   
 =item RETURN  
   
 Returns a list of values.  
   
 =back  
   
 =cut  
   
 sub GetFlat {  
         # Get the parameters.  
         my $self = shift @_;  
         my ($objectNames, $filterClause, $parameterList, $field) = @_;  
         # Construct the query.  
         my $query = $self->Get($objectNames, $filterClause, $parameterList);  
         # Create the result list.  
         my @retVal = ();  
         # Loop through the records, adding the field values found to the result list.  
         while (my $row = $query->Fetch()) {  
                 push @retVal, $row->Value($field);  
         }  
         # Return the list created.  
         return @retVal;  
 }  
   
 =head3 Protein  
   
 C<< my $protein = Sprout::Protein($sequence, $table); >>  
3059    
3060  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3061    
# Line 2401  Line 3125 
3125          # Loop through the input triples.          # Loop through the input triples.
3126          my $n = length $sequence;          my $n = length $sequence;
3127          for (my $i = 0; $i < $n; $i += 3) {          for (my $i = 0; $i < $n; $i += 3) {
3128                  # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3129                  my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3130            my $triple = uc substr($sequence, $i, 3);
3131                  # Translate it using the table.                  # Translate it using the table.
3132                  my $protein = "X";                  my $protein = "X";
3133                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }                  if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 2416  Line 3141 
3141    
3142  =head3 LoadInfo  =head3 LoadInfo
3143    
3144  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3145    
3146  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
3147  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
3148  to load the entire database.  to load the entire database.
3149    
3150  =cut  =cut
3151    #: Return Type @;
3152  sub LoadInfo {  sub LoadInfo {
3153          # Get the parameters.          # Get the parameters.
3154          my $self = shift @_;      my ($self) = @_;
3155          # 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.
3156          my @retVal = ($self->{_options}->{dataDir});          my @retVal = ($self->{_options}->{dataDir});
3157          # Concatenate the table names.          # Concatenate the table names.
3158          push @retVal, $self->{_erdb}->GetTableNames();      push @retVal, $self->GetTableNames();
3159          # Return the result.          # Return the result.
3160          return @retVal;          return @retVal;
3161  }  }
3162    
3163    =head3 BBHMatrix
3164    
3165        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3166    
3167    Find all the bidirectional best hits for the features of a genome in a
3168    specified list of target genomes. The return value will be a hash mapping
3169    features in the original genome to their bidirectional best hits in the
3170    target genomes.
3171    
3172    =over 4
3173    
3174    =item genomeID
3175    
3176    ID of the genome whose features are to be examined for bidirectional best hits.
3177    
3178    =item cutoff
3179    
3180    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3181    
3182    =item targets
3183    
3184    List of target genomes. Only pairs originating in the original
3185    genome and landing in one of the target genomes will be returned.
3186    
3187    =item RETURN
3188    
3189    Returns a hash mapping each feature in the original genome to a hash mapping its
3190    BBH pegs in the target genomes to their scores.
3191    
3192    =back
3193    
3194    =cut
3195    
3196    sub BBHMatrix {
3197        # Get the parameters.
3198        my ($self, $genomeID, $cutoff, @targets) = @_;
3199        # Declare the return variable.
3200        my %retVal = ();
3201        # Ask for the BBHs.
3202        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3203        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3204        for my $bbhData (@bbhList) {
3205            my ($peg1, $peg2, $score) = @{$bbhData};
3206            if (! exists $retVal{$peg1}) {
3207                $retVal{$peg1} = { $peg2 => $score };
3208            } else {
3209                $retVal{$peg1}->{$peg2} = $score;
3210            }
3211        }
3212        # Return the result.
3213        return %retVal;
3214    }
3215    
3216    
3217    =head3 SimMatrix
3218    
3219        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3220    
3221    Find all the similarities for the features of a genome in a
3222    specified list of target genomes. The return value will be a hash mapping
3223    features in the original genome to their similarites in the
3224    target genomes.
3225    
3226    =over 4
3227    
3228    =item genomeID
3229    
3230    ID of the genome whose features are to be examined for similarities.
3231    
3232    =item cutoff
3233    
3234    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3235    
3236    =item targets
3237    
3238    List of target genomes. Only pairs originating in the original
3239    genome and landing in one of the target genomes will be returned.
3240    
3241    =item RETURN
3242    
3243    Returns a hash mapping each feature in the original genome to a hash mapping its
3244    similar pegs in the target genomes to their scores.
3245    
3246    =back
3247    
3248    =cut
3249    
3250    sub SimMatrix {
3251        # Get the parameters.
3252        my ($self, $genomeID, $cutoff, @targets) = @_;
3253        # Declare the return variable.
3254        my %retVal = ();
3255        # Get the list of features in the source organism.
3256        my @fids = $self->FeaturesOf($genomeID);
3257        # Ask for the sims. We only want similarities to fig features.
3258        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3259        if (! defined $simList) {
3260            Confess("Unable to retrieve similarities from server.");
3261        } else {
3262            Trace("Processing sims.") if T(3);
3263            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3264            # Create a hash for the target genomes.
3265            my %targetHash = map { $_ => 1 } @targets;
3266            for my $simData (@{$simList}) {
3267                # Get the PEGs and the score.
3268                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3269                # Insure the second ID is in the target list.
3270                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3271                if (exists $targetHash{$genome2}) {
3272                    # Here it is. Now we need to add it to the return hash. How we do that depends
3273                    # on whether or not $peg1 is new to us.
3274                    if (! exists $retVal{$peg1}) {
3275                        $retVal{$peg1} = { $peg2 => $score };
3276                    } else {
3277                        $retVal{$peg1}->{$peg2} = $score;
3278                    }
3279                }
3280            }
3281        }
3282        # Return the result.
3283        return %retVal;
3284    }
3285    
3286    
3287  =head3 LowBBHs  =head3 LowBBHs
3288    
3289  C<< my %bbhMap = $sprout->GoodBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3290    
3291  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
3292  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 2460  Line 3309 
3309  =back  =back
3310    
3311  =cut  =cut
3312    #: Return Type %;
3313  sub LowBBHs {  sub LowBBHs {
3314          # Get the parsameters.          # Get the parsameters.
3315          my $self = shift @_;      my ($self, $featureID, $cutoff) = @_;
         my ($featureID, $cutoff) = @_;  
3316          # Create the return hash.          # Create the return hash.
3317          my %retVal = ();          my %retVal = ();
3318          # Create a query to get the desired BBHs.      # Query for the desired BBHs.
3319          my @bbhList = $self->GetAll(['IsBidirectionalBestHitOf'],      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
                                                                 'IsBidirectionalBestHitOf(sc) <= ? AND IsBidirectionalBestHitOf(from-link) = ?',  
                                                                 [$cutoff, $featureID],  
                                                                 ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(sc)']);  
3320          # Form the results into the return hash.          # Form the results into the return hash.
3321          for my $pair (@bbhList) {          for my $pair (@bbhList) {
3322                  $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3323            if ($self->Exists('Feature', $fid)) {
3324                $retVal{$fid} = $pair->[1];
3325            }
3326        }
3327        # Return the result.
3328        return %retVal;
3329    }
3330    
3331    =head3 Sims
3332    
3333        my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3334    
3335    Get a list of similarities for a specified feature. Similarity information is not kept in the
3336    Sprout database; rather, they are retrieved from a network server. The similarities are
3337    returned as B<Sim> objects. A Sim object is actually a list reference that has been blessed
3338    so that its elements can be accessed by name.
3339    
3340    Similarities can be either raw or expanded. The raw similarities are basic
3341    hits between features with similar DNA. Expanding a raw similarity drags in any
3342    features considered substantially identical. So, for example, if features B<A1>,
3343    B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3344    B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3345    
3346    =over 4
3347    
3348    =item fid
3349    
3350    ID of the feature whose similarities are desired, or reference to a list of IDs
3351    of features whose similarities are desired.
3352    
3353    =item maxN
3354    
3355    Maximum number of similarities to return.
3356    
3357    =item maxP
3358    
3359    Minumum allowable similarity score.
3360    
3361    =item select
3362    
3363    Selection criterion: C<raw> means only raw similarities are returned; C<fig>
3364    means only similarities to FIG features are returned; C<all> means all expanded
3365    similarities are returned; and C<figx> means similarities are expanded until the
3366    number of FIG features equals the maximum.
3367    
3368    =item max_expand
3369    
3370    The maximum number of features to expand.
3371    
3372    =item filters
3373    
3374    Reference to a hash containing filter information, or a subroutine that can be
3375    used to filter the sims.
3376    
3377    =item RETURN
3378    
3379    Returns a reference to a list of similarity objects, or C<undef> if an error
3380    occurred.
3381    
3382    =back
3383    
3384    =cut
3385    
3386    sub Sims {
3387        # Get the parameters.
3388        my ($self, $fid, $maxN, $maxP, $select, $max_expand, $filters) = @_;
3389        # Create the shim object to test for deleted FIDs.
3390        my $shim = FidCheck->new($self);
3391        # Ask the network for sims.
3392        my $retVal = FIGRules::GetNetworkSims($shim, $fid, {}, $maxN, $maxP, $select, $max_expand, $filters);
3393        # Return the result.
3394        return $retVal;
3395    }
3396    
3397    =head3 IsAllGenomes
3398    
3399        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3400    
3401    Return TRUE if all genomes in the second list are represented in the first list at
3402    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3403    compared to a list of all the genomes.
3404    
3405    =over 4
3406    
3407    =item list
3408    
3409    Reference to the list to be compared to the second list.
3410    
3411    =item checkList (optional)
3412    
3413    Reference to the comparison target list. Every genome ID in this list must occur at
3414    least once in the first list. If this parameter is omitted, a list of all the genomes
3415    is used.
3416    
3417    =item RETURN
3418    
3419    Returns TRUE if every item in the second list appears at least once in the
3420    first list, else FALSE.
3421    
3422    =back
3423    
3424    =cut
3425    
3426    sub IsAllGenomes {
3427        # Get the parameters.
3428        my ($self, $list, $checkList) = @_;
3429        # Supply the checklist if it was omitted.
3430        $checkList = [$self->Genomes()] if ! defined($checkList);
3431        # Create a hash of the original list.
3432        my %testList = map { $_ => 1 } @{$list};
3433        # Declare the return variable. We assume that the representation
3434        # is complete and stop at the first failure.
3435        my $retVal = 1;
3436        my $n = scalar @{$checkList};
3437        for (my $i = 0; $retVal && $i < $n; $i++) {
3438            if (! $testList{$checkList->[$i]}) {
3439                $retVal = 0;
3440            }
3441        }
3442        # Return the result.
3443        return $retVal;
3444    }
3445    
3446    =head3 GetGroups
3447    
3448        my %groups = $sprout->GetGroups(\@groupList);
3449    
3450    Return a hash mapping each group to the IDs of the genomes in the group.
3451    A list of groups may be specified, in which case only those groups will be
3452    shown. Alternatively, if no parameter is supplied, all groups will be
3453    included. Genomes that are not in any group are omitted.
3454    
3455    =cut
3456    #: Return Type %@;
3457    sub GetGroups {
3458        # Get the parameters.
3459        my ($self, $groupList) = @_;
3460        # Declare the return value.
3461        my %retVal = ();
3462        # Determine whether we are getting all the groups or just some.
3463        if (defined $groupList) {
3464            # Here we have a group list. Loop through them individually,
3465            # getting a list of the relevant genomes.
3466            for my $group (@{$groupList}) {
3467                my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3468                    [$group], "Genome(id)");
3469                $retVal{$group} = \@genomeIDs;
3470            }
3471        } else {
3472            # Here we need all of the groups. In this case, we run through all
3473            # of the genome records, putting each one found into the appropriate
3474            # group. Note that we use a filter clause to insure that only genomes
3475            # in real NMPDR groups are included in the return set.
3476            my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3477                                        [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3478            # Loop through the genomes found.
3479            for my $genome (@genomes) {
3480                # Get the genome ID and group, and add this genome to the group's list.
3481                my ($genomeID, $group) = @{$genome};
3482                push @{$retVal{$group}}, $genomeID;
3483            }
3484        }
3485        # Return the hash we just built.
3486        return %retVal;
3487    }
3488    
3489    =head3 MyGenomes
3490    
3491        my @genomes = Sprout::MyGenomes($dataDir);
3492    
3493    Return a list of the genomes to be included in the Sprout.
3494    
3495    This method is provided for use during the Sprout load. It presumes the Genome load file has
3496    already been created. (It will be in the Sprout data directory and called either C<Genome>
3497    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3498    IDs.
3499    
3500    =over 4
3501    
3502    =item dataDir
3503    
3504    Directory containing the Sprout load files.
3505    
3506    =back
3507    
3508    =cut
3509    #: Return Type @;
3510    sub MyGenomes {
3511        # Get the parameters.
3512        my ($dataDir) = @_;
3513        # Compute the genome file name.
3514        my $genomeFileName = LoadFileName($dataDir, "Genome");
3515        # Extract the genome IDs from the files.
3516        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3517        # Return the result.
3518        return @retVal;
3519    }
3520    
3521    =head3 LoadFileName
3522    
3523        my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3524    
3525    Return the name of the load file for the specified table in the specified data
3526    directory.
3527    
3528    =over 4
3529    
3530    =item dataDir
3531    
3532    Directory containing the Sprout load files.
3533    
3534    =item tableName
3535    
3536    Name of the table whose load file is desired.
3537    
3538    =item RETURN
3539    
3540    Returns the name of the file containing the load data for the specified table, or
3541    C<undef> if no load file is present.
3542    
3543    =back
3544    
3545    =cut
3546    #: Return Type $;
3547    sub LoadFileName {
3548        # Get the parameters.
3549        my ($dataDir, $tableName) = @_;
3550        # Declare the return variable.
3551        my $retVal;
3552        # Check for the various file names.
3553        if (-e "$dataDir/$tableName") {
3554            $retVal = "$dataDir/$tableName";
3555        } elsif (-e "$dataDir/$tableName.dtx") {
3556            $retVal = "$dataDir/$tableName.dtx";
3557          }          }
3558          # Return the result.          # Return the result.
3559        return $retVal;
3560    }
3561    
3562    =head3 DeleteGenome
3563    
3564        my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3565    
3566    Delete a genome from the database.
3567    
3568    =over 4
3569    
3570    =item genomeID
3571    
3572    ID of the genome to delete
3573    
3574    =item testFlag
3575    
3576    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3577    
3578    =item RETURN
3579    
3580    Returns a statistics object describing the rows deleted.
3581    
3582    =back
3583    
3584    =cut
3585    #: Return Type $%;
3586    sub DeleteGenome {
3587        # Get the parameters.
3588        my ($self, $genomeID, $testFlag) = @_;
3589        # Perform the delete for the genome's features.
3590        my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3591        # Perform the delete for the primary genome data.
3592        my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3593        $retVal->Accumulate($stats);
3594        # Return the result.
3595        return $retVal;
3596    }
3597    
3598    =head3 Fix
3599    
3600        my %fixedHash = $sprout->Fix(%groupHash);
3601    
3602    Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3603    The groups will be combined into the appropriate super-groups.
3604    
3605    =over 4
3606    
3607    =item groupHash
3608    
3609    Hash to be fixed up.
3610    
3611    =item RETURN
3612    
3613    Returns a fixed-up version of the hash.
3614    
3615    =back
3616    
3617    =cut
3618    
3619    sub Fix {
3620        # Get the parameters.
3621        my ($self, %groupHash) = @_;
3622        # Create the result hash.
3623        my %retVal = ();
3624        # Get the super-group table.
3625        my %superTable = $self->CheckGroupFile();
3626        # Copy over the genomes.
3627        for my $groupID (keys %groupHash) {
3628            # Get the super-group name.
3629            my $realGroupID;
3630            if ($groupID =~ /([A-Z]\w+)/) {
3631                if (! defined($superTable{$1})) {
3632                    Confess("Super-group name not found for group $groupID.");
3633                } else {
3634                    $realGroupID = $1;
3635                }
3636            } else {
3637                Confess("Invalid group name $groupID.");
3638            }
3639            # Append this group's genomes into the result hash.
3640            push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3641        }
3642        # Return the result hash.
3643          return %retVal;          return %retVal;
3644  }  }
3645    
3646    =head3 GroupPageName
3647    
3648        my $name = $sprout->GroupPageName($group);
3649    
3650    Return the name of the page for the specified NMPDR group.
3651    
3652    =over 4
3653    
3654    =item group
3655    
3656    Name of the relevant group.
3657    
3658    =item RETURN
3659    
3660    Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3661    memory it will be read in.
3662    
3663    =back
3664    
3665    =cut
3666    
3667    sub GroupPageName {
3668        # Get the parameters.
3669        my ($self, $group) = @_;
3670        # Declare the return variable.
3671        my $retVal;
3672        # Check for the group file data.
3673        my %superTable = $self->CheckGroupFile();
3674        # Compute the real group name.
3675        if ($group =~ /([A-Z]\w+)/) {
3676            my $realGroup = $1;
3677            if (! defined($superTable{$1})) {
3678                Confess("No super-group found for \"$group\".");
3679            } else {
3680                $retVal = "../content/$superTable{$1}->{page}";
3681            }
3682        } else {
3683            Confess("\"group\" is not a valid group name.");
3684        }
3685        # Return the result.
3686        return $retVal;
3687    }
3688    
3689    
3690    =head3 AddProperty
3691    
3692        $sprout->AddProperty($featureID, $key, @values);
3693    
3694    Add a new attribute value (Property) to a feature.
3695    
3696    =over 4
3697    
3698    =item peg
3699    
3700    ID of the feature to which the attribute is to be added.
3701    
3702    =item key
3703    
3704    Name of the attribute (key).
3705    
3706    =item values
3707    
3708    Values of the attribute.
3709    
3710    =back
3711    
3712    =cut
3713    #: Return Type ;
3714    sub AddProperty {
3715        # Get the parameters.
3716        my ($self, $featureID, $key, @values) = @_;
3717        # Add the property using the attached attributes object.
3718        $self->{_ca}->AddAttribute($featureID, $key, @values);
3719    }
3720    
3721    =head3 CheckGroupFile
3722    
3723        my %groupData = $sprout->CheckGroupFile();
3724    
3725    Get the group file hash. The group file hash describes the relationship
3726    between a group and the super-group to which it belongs for purposes of
3727    display. The super-group name is computed from the first capitalized word
3728    in the actual group name. For each super-group, the group file contains
3729    the page name and a list of the species expected to be in the group.
3730    Each species is specified by a genus and a species name. A species name
3731    of C<0> implies an entire genus.
3732    
3733    This method returns a hash from super-group names to a hash reference. Each
3734    resulting hash reference contains the following fields.
3735    
3736    =over 4
3737    
3738    =item page
3739    
3740    The super-group's web page in the NMPDR.
3741    
3742    =item contents
3743    
3744    A list of 2-tuples, each containing a genus name followed by a species name
3745    (or 0, indicating all species). This list indicates which organisms belong
3746    in the super-group.
3747    
3748    =back
3749    
3750    =cut
3751    
3752    sub CheckGroupFile{
3753        # Get the parameters.
3754        my ($self) = @_;
3755        # Check to see if we already have this hash.
3756        if (! defined $self->{groupHash}) {
3757            # We don't, so we need to read it in.
3758            my %groupHash;
3759            # Read the group file.
3760            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3761            # Loop through the list of sort-of groups.
3762            for my $groupLine (@groupLines) {
3763                my ($name, $page, @contents) = split /\t/, $groupLine;
3764                $groupHash{$name} = { page => $page,
3765                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3766                                    };
3767            }
3768            # Save the hash.
3769            $self->{groupHash} = \%groupHash;
3770        }
3771        # Return the result.
3772        return %{$self->{groupHash}};
3773    }
3774    
3775    =head2 Virtual Methods
3776    
3777    =head3 CleanKeywords
3778    
3779        my $cleanedString = $sprout->CleanKeywords($searchExpression);
3780    
3781    Clean up a search expression or keyword list. This involves converting the periods
3782    in EC numbers to underscores, converting non-leading minus signs to underscores,
3783    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3784    characters. In addition, any extra spaces are removed.
3785    
3786    =over 4
3787    
3788    =item searchExpression
3789    
3790    Search expression or keyword list to clean. Note that a search expression may
3791    contain boolean operators which need to be preserved. This includes leading
3792    minus signs.
3793    
3794    =item RETURN
3795    
3796    Cleaned expression or keyword list.
3797    
3798    =back
3799    
3800    =cut
3801    
3802    sub CleanKeywords {
3803        # Get the parameters.
3804        my ($self, $searchExpression) = @_;
3805        # Perform the standard cleanup.
3806        my $retVal = $self->ERDB::CleanKeywords($searchExpression);
3807        # Fix the periods in EC and TC numbers.
3808        $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
3809        # Fix non-trailing periods.
3810        $retVal =~ s/\.(\w)/_$1/g;
3811        # Fix non-leading minus signs.
3812        $retVal =~ s/(\w)[\-]/$1_/g;
3813        # Fix the vertical bars and colons
3814        $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
3815        # Return the result.
3816        return $retVal;
3817    }
3818    
3819  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3820    
3821  =head3 ParseAssignment  =head3 ParseAssignment
3822    
3823  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3824  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3825  will be returned.  isn't, an empty list will be returned.
3826    
3827    A functional assignment is always of the form
3828    
3829        set YYYY function to
3830        ZZZZ
3831    
3832    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3833    the user and the assigning user (from MadeAnnotation) will be the same, but that is
3834    not always the case.
3835    
3836    In addition, the functional role may contain extra data that is stripped, such as
3837    terminating spaces or a comment separated from the rest of the text by a tab.
3838    
3839  This is a static method.  This is a static method.
3840    
3841  =over 4  =over 4
3842    
3843    =item user
3844    
3845    Name of the assigning user.
3846    
3847  =item text  =item text
3848    
3849  Text of the annotation.  Text of the annotation.
# Line 2505  Line 3857 
3857    
3858  =cut  =cut
3859    
3860  sub ParseAssignment {  sub _ParseAssignment {
3861          # Get the parameters.          # Get the parameters.
3862          my ($text) = @_;      my ($user, $text) = @_;
3863          # Declare the return value.          # Declare the return value.
3864          my @retVal = ();          my @retVal = ();
3865          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3866          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3867          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set function to$/i) {
3868                  # Here it is, so we return the user name and function text.          # Here we have an assignment without a user, so we use the incoming user ID.
3869                  @retVal = ($user, $function);                  @retVal = ($user, $function);
3870        } elsif ($type =~ m/^set (\S+) function to$/i) {
3871            # Here we have an assignment with a user that is passed back to the caller.
3872            @retVal = ($1, $function);
3873        }
3874        # If we have an assignment, we need to clean the function text. There may be
3875        # extra junk at the end added as a note from the user.
3876        if (defined( $retVal[1] )) {
3877            $retVal[1] =~ s/(\t\S)?\s*$//;
3878          }          }
3879          # Return the result list.          # Return the result list.
3880          return @retVal;          return @retVal;
3881  }  }
3882    
3883    =head3 _CheckFeature
3884    
3885        my $flag = $sprout->_CheckFeature($fid);
3886    
3887    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
3888    
3889    =over 4
3890    
3891    =item fid
3892    
3893    Feature ID to check.
3894    
3895    =item RETURN
3896    
3897    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
3898    
3899    =back
3900    
3901    =cut
3902    
3903    sub _CheckFeature {
3904        # Get the parameters.
3905        my ($self, $fid) = @_;
3906        # Insure we have a genome hash.
3907        if (! defined $self->{genomeHash}) {
3908            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
3909            $self->{genomeHash} = \%genomeHash;
3910        }
3911        # Get the feature's genome ID.
3912        my ($genomeID) = FIGRules::ParseFeatureID($fid);
3913        # Return an indicator of whether or not the genome ID is in the hash.
3914        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
3915    }
3916    
3917    =head3 FriendlyTimestamp
3918    
3919    Convert a time number to a user-friendly time stamp for display.
3920    
3921    This is a static method.
3922    
3923    =over 4
3924    
3925    =item timeValue
3926    
3927    Numeric time value.
3928    
3929    =item RETURN
3930    
3931    Returns a string containing the same time in user-readable format.
3932    
3933    =back
3934    
3935    =cut
3936    
3937    sub FriendlyTimestamp {
3938        my ($timeValue) = @_;
3939        my $retVal = localtime($timeValue);
3940        return $retVal;
3941    }
3942    
3943    
3944  1;  1;

Legend:
Removed from v.1.1  
changed lines
  Added in v.1.105

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3